[{"id":"doi:10.5281/zenodo.20026013","type":"article-journal","title":"UAV-Based Crop Disease Detection Using Hybrid AI and IoT Integration","abstract":"Timely identification of crop diseases is essential for improving agricultural productivity and ensuring food security. This paper presents an intelligent crop disease detection framework that integrates Unmanned Aerial Vehicles (UAVs), Internet of Things (IoT) sensors, and hybrid deep learning techniques. UAVs are employed to capture high-resolution aerial imagery, while IoT devices collect environmental parameters such as temperature, humidity, and soil moisture. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model is developed to learn both spatial and temporal patterns from multimodal data. The proposed approach achieves an accuracy of 97.2%, outperforming conventional machine learning and standalone deep learning models. Furthermore, the system incorporates energy-efficient UAV operation and explainable AI methods to enhance interpretability. Experimental evaluation demonstrates that the proposed framework is reliable, scalable, and suitable for real-world precision agriculture applications.","author":[{"family":"Mohanty","given":"Sushanta"},{"family":"Mahalwar","given":"Abha"},{"family":"Dora","given":"Sidhartha"},{"family":"Mallick","given":"Chandrakant"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20026013","URL":"https://doi.org/10.5281/zenodo.20026013","source":"datacite"},{"id":"doi:10.5281/zenodo.20026014","type":"article-journal","title":"UAV-Based Crop Disease Detection Using Hybrid AI and IoT Integration","abstract":"Timely identification of crop diseases is essential for improving agricultural productivity and ensuring food security. This paper presents an intelligent crop disease detection framework that integrates Unmanned Aerial Vehicles (UAVs), Internet of Things (IoT) sensors, and hybrid deep learning techniques. UAVs are employed to capture high-resolution aerial imagery, while IoT devices collect environmental parameters such as temperature, humidity, and soil moisture. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model is developed to learn both spatial and temporal patterns from multimodal data. The proposed approach achieves an accuracy of 97.2%, outperforming conventional machine learning and standalone deep learning models. Furthermore, the system incorporates energy-efficient UAV operation and explainable AI methods to enhance interpretability. Experimental evaluation demonstrates that the proposed framework is reliable, scalable, and suitable for real-world precision agriculture applications.","author":[{"family":"Mohanty","given":"Sushanta"},{"family":"Mahalwar","given":"Abha"},{"family":"Dora","given":"Sidhartha"},{"family":"Mallick","given":"Chandrakant"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20026014","URL":"https://doi.org/10.5281/zenodo.20026014","source":"datacite"},{"id":"doi:10.5281/zenodo.20140862","type":"article-journal","title":"State of the alternative protein research and innovation ecosystem in Denmark, 2020-2025","abstract":"This country deep-dive report, produced by GFI Europe (Good Food Institute Europe), maps Denmark's research and innovation ecosystem for alternative proteins – spanning plant-based proteins, precision fermentation, and cultivated meat and seafood – across 2020 to 2025. Denmark recorded the most rapid growth in alternative protein research output of any country in this series, with peer-reviewed publications growing 461% from 23 in 2020 to 129 in 2025 – reaching 388 total publications across the period and ranking fifth in Europe by publication volume. Despite receiving just €24 million in total public funding (tenth in Europe by that measure), Denmark ranks fifth in Europe on a per capita basis at €4 per person, and its ecosystem is uniquely shaped by the Novo Nordisk Foundation, a private nonprofit funder whose investment substantially outpaces government contributions and supports a broad mix of plant-based and fermentation research. Danish innovators filed 433 patents between 2015 and 2025 – the sixth highest total in Europe – with plant-based innovations accounting for 89.1% of all filings and annual patent volume growing continuously since 2019 to reach 108 in 2025. Denmark is competitive across all three alternative protein pillars, ranking third in Europe for plant-based publications, fifth for fermentation, and sixth for cultivated meat and seafood; Aarhus University ranked second in Europe overall for alternative protein research output across the full period. The analysis draws on three data streams: public funding records from GFI Europe's Research Grants Tracker and Dimensions.ai (2010–2025, retrieved February 2026); academic publication data from Dimensions.ai (2020–2025, retrieved January 2026); and patent data from Dimensions.ai (2015–2025, retrieved February 2026). All records were screened against predefined inclusion and exclusion criteria, with geographic scope covering EU27 member states plus Norway, Switzerland, and the United Kingdom. Denmark's long history in plant-based food research – initially driven by nonprofit funders and now increasingly aligned with government priorities – positions it as one of Europe's most productive and broad-based alternative protein ecosystems, with continued government support essential to sustaining this momentum in the protein transition. This report is intended for researchers, policymakers, research funders, and innovation agencies seeking a data-driven assessment of Denmark's alternative protein research and innovation landscape and its positioning within the wider European ecosystem. This report is part of GFI Europe's series \"State of the European Alternative Protein Research and Innovation Ecosystem\" (DOI: 10.5281/zenodo.20124302). For more information visit https://gfieurope.org.","author":[{"family":"Child","given":"Stella"},{"family":"Hunt","given":"David"},{"family":"Europe","given":"Good"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20140862","URL":"https://doi.org/10.5281/zenodo.20140862","source":"datacite"},{"id":"doi:10.5281/zenodo.20140863","type":"article-journal","title":"State of the alternative protein research and innovation ecosystem in Denmark, 2020-2025","abstract":"This country deep-dive report, produced by GFI Europe (Good Food Institute Europe), maps Denmark's research and innovation ecosystem for alternative proteins – spanning plant-based proteins, precision fermentation, and cultivated meat and seafood – across 2020 to 2025. Denmark recorded the most rapid growth in alternative protein research output of any country in this series, with peer-reviewed publications growing 461% from 23 in 2020 to 129 in 2025 – reaching 388 total publications across the period and ranking fifth in Europe by publication volume. Despite receiving just €24 million in total public funding (tenth in Europe by that measure), Denmark ranks fifth in Europe on a per capita basis at €4 per person, and its ecosystem is uniquely shaped by the Novo Nordisk Foundation, a private nonprofit funder whose investment substantially outpaces government contributions and supports a broad mix of plant-based and fermentation research. Danish innovators filed 433 patents between 2015 and 2025 – the sixth highest total in Europe – with plant-based innovations accounting for 89.1% of all filings and annual patent volume growing continuously since 2019 to reach 108 in 2025. Denmark is competitive across all three alternative protein pillars, ranking third in Europe for plant-based publications, fifth for fermentation, and sixth for cultivated meat and seafood; Aarhus University ranked second in Europe overall for alternative protein research output across the full period. The analysis draws on three data streams: public funding records from GFI Europe's Research Grants Tracker and Dimensions.ai (2010–2025, retrieved February 2026); academic publication data from Dimensions.ai (2020–2025, retrieved January 2026); and patent data from Dimensions.ai (2015–2025, retrieved February 2026). All records were screened against predefined inclusion and exclusion criteria, with geographic scope covering EU27 member states plus Norway, Switzerland, and the United Kingdom. Denmark's long history in plant-based food research – initially driven by nonprofit funders and now increasingly aligned with government priorities – positions it as one of Europe's most productive and broad-based alternative protein ecosystems, with continued government support essential to sustaining this momentum in the protein transition. This report is intended for researchers, policymakers, research funders, and innovation agencies seeking a data-driven assessment of Denmark's alternative protein research and innovation landscape and its positioning within the wider European ecosystem. This report is part of GFI Europe's series \"State of the European Alternative Protein Research and Innovation Ecosystem\" (DOI: 10.5281/zenodo.20124302). For more information visit https://gfieurope.org.","author":[{"family":"Child","given":"Stella"},{"family":"Hunt","given":"David"},{"family":"Europe","given":"Good"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20140863","URL":"https://doi.org/10.5281/zenodo.20140863","source":"datacite"},{"id":"doi:10.5281/zenodo.19854962","type":"article-journal","title":"Location Aware and Environmental Condition for Smart Crop Prediction and Calendar Generation Using ML","abstract":"Agriculture plays a vital role in ensuring both and potential financial setbacks. Advancements in machine learning offer promising solutions to these challenges by selecting the most suitable crops remains a significant enabling data-driven decision-making in agriculture. By challenge due to variations in soil characteristics, climatic conditions, and geographical diversity. This study proposes an automated crop prediction system based on machine learning techniques, with a particular focus on the Random Forest analyzing critical parameters such as soil characteristics, algorithm due to its reliability and strong predictive climatic conditions, and geographic location, it becomes performance. The system evaluates key factors such as soil possible to recommend crops that are better suited to properties, weather conditions, and location-specific data to specific environments. In this study, an automated smart generate accurate crop recommendations. Additionally, it crop prediction system is developed that integrates hardware integrates hardware sensors and data-driven methods to sensors to gather real-time environmental data. The system enhance prediction accuracy and provide real-time insights. To employs the Random Forest algorithm to generate accurate further support farmers, the proposed model includes an automated cultivation calendar that assists in planning key agricultural activities, including sowing, irrigation, and agricultural activities efficiently. This approach aims to improve crop productivity, ensure optimal use of resources, decision-making, minimize the risk of crop failure, enhance and promote sustainable farming practices. agricultural productivity, and promote sustainable farming practices.","author":[{"family":"Shinde","given":"Prof"},{"family":"Khandve","given":"Mr"},{"family":"Kawade","given":"Ms"},{"family":"Ghule","given":"Mr"},{"family":"Kale","given":"Ms"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19854962","URL":"https://doi.org/10.5281/zenodo.19854962","source":"datacite"},{"id":"doi:10.5281/zenodo.19854963","type":"article-journal","title":"Location Aware and Environmental Condition for Smart Crop Prediction and Calendar Generation Using ML","abstract":"Agriculture plays a vital role in ensuring both and potential financial setbacks. Advancements in machine learning offer promising solutions to these challenges by selecting the most suitable crops remains a significant enabling data-driven decision-making in agriculture. By challenge due to variations in soil characteristics, climatic conditions, and geographical diversity. This study proposes an automated crop prediction system based on machine learning techniques, with a particular focus on the Random Forest analyzing critical parameters such as soil characteristics, algorithm due to its reliability and strong predictive climatic conditions, and geographic location, it becomes performance. The system evaluates key factors such as soil possible to recommend crops that are better suited to properties, weather conditions, and location-specific data to specific environments. In this study, an automated smart generate accurate crop recommendations. Additionally, it crop prediction system is developed that integrates hardware integrates hardware sensors and data-driven methods to sensors to gather real-time environmental data. The system enhance prediction accuracy and provide real-time insights. To employs the Random Forest algorithm to generate accurate further support farmers, the proposed model includes an automated cultivation calendar that assists in planning key agricultural activities, including sowing, irrigation, and agricultural activities efficiently. This approach aims to improve crop productivity, ensure optimal use of resources, decision-making, minimize the risk of crop failure, enhance and promote sustainable farming practices. agricultural productivity, and promote sustainable farming practices.","author":[{"family":"Shinde","given":"Prof"},{"family":"Khandve","given":"Mr"},{"family":"Kawade","given":"Ms"},{"family":"Ghule","given":"Mr"},{"family":"Kale","given":"Ms"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19854963","URL":"https://doi.org/10.5281/zenodo.19854963","source":"datacite"},{"id":"doi:10.5281/zenodo.20437937","type":"article-journal","title":"Data for: A hybrid biophysical-machine learning framework for diurnal surface energy flux estimation using proximal sensing","abstract":"Thermal-based remote sensing of surface energy fluxes has traditionally relied on high spatial resolution satellite data with revisit frequencies on the order of weeks. In this study, we evaluate a biophysics-based analytical surface energy balance model for predicting latent energy (LE) and sensible heat (H) fluxes using proximal sensing observations. The Surface Temperature Initiated Closure (STIC1.2) model has been extensively validated across a wide range of spatial and temporal scales using various satellite-derived thermal datasets. Here we extend this validation by applying STIC at sub-hourly temporal resolution over multiple growing seasons for four distinct agricultural systems. We further develop and evaluate novel STIC variants that incorporate machine learning (ML) techniques to eliminate the need for specific surface energy balance observations, specifically net radiation and soil heat flux, thereby enhancing model applicability in data-sparse settings. The integration of an ML component to estimate surface available energy is shown to have strong predictive performance for both LE (R2 = 0.81-0.94) and H (R2 = 0.46-0.72) across all agricultural systems examined here, demonstrating the potential of hybrid biophysical – machine learning approaches for surface energy balance modeling with minimal data requirements. This study concludes with a novel application of explainable machine learning (exML) to diagnose sources of model error. This exML framework attributes residual prediction errors to both model input variables and environmental drivers not explicitly included in the simulation experiments. This approach provides a new pathway for improving model design and integrating previously overlooked yet influential variables into future model iterations.","author":[{"family":"Cross","given":"James"},{"family":"Mallick","given":"Kanishka"},{"family":"Aslan-Sungur","given":"Guler"},{"family":"Vanloocke","given":"Andy"},{"family":"Drewry","given":"Darren"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20437937","URL":"https://doi.org/10.5281/zenodo.20437937","source":"datacite"},{"id":"doi:10.5281/zenodo.20437939","type":"article-journal","title":"Data for: A hybrid biophysical-machine learning framework for diurnal surface energy flux estimation using proximal sensing","abstract":"Thermal-based remote sensing of surface energy fluxes has traditionally relied on high spatial resolution satellite data with revisit frequencies on the order of weeks. In this study, we evaluate a biophysics-based analytical surface energy balance model for predicting latent energy (LE) and sensible heat (H) fluxes using proximal sensing observations. The Surface Temperature Initiated Closure (STIC1.2) model has been extensively validated across a wide range of spatial and temporal scales using various satellite-derived thermal datasets. Here we extend this validation by applying STIC at sub-hourly temporal resolution over multiple growing seasons for four distinct agricultural systems. We further develop and evaluate novel STIC variants that incorporate machine learning (ML) techniques to eliminate the need for specific surface energy balance observations, specifically net radiation and soil heat flux, thereby enhancing model applicability in data-sparse settings. The integration of an ML component to estimate surface available energy is shown to have strong predictive performance for both LE (R2 = 0.81-0.94) and H (R2 = 0.46-0.72) across all agricultural systems examined here, demonstrating the potential of hybrid biophysical – machine learning approaches for surface energy balance modeling with minimal data requirements. This study concludes with a novel application of explainable machine learning (exML) to diagnose sources of model error. This exML framework attributes residual prediction errors to both model input variables and environmental drivers not explicitly included in the simulation experiments. This approach provides a new pathway for improving model design and integrating previously overlooked yet influential variables into future model iterations.","author":[{"family":"Cross","given":"James"},{"family":"Mallick","given":"Kanishka"},{"family":"Aslan-Sungur","given":"Guler"},{"family":"Vanloocke","given":"Andy"},{"family":"Drewry","given":"Darren"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20437939","URL":"https://doi.org/10.5281/zenodo.20437939","source":"datacite"},{"id":"doi:10.5281/zenodo.21922412","type":"article-journal","title":"Energy-Aware Robotics: Review of Path Planning and Power Optimization for Long-Endurance UAVs","abstract":"There is no gain saying of the obvious fact that Long-endurance, Unmanned Aerial Vehicles are critical not only for surveillance and precision agriculture, but also for disaster response, and environmental monitoring. However, battery capacity remains the primary constraint, with most multirotor UAVs limited to about 25–45 minutes of flight time. This review examines 2020–2026 research on energy-aware robotics, focusing on path planning and power optimization strategies that has the potential to extend UAV endurance. Following PRISMA 2020 guidelines, 112 peer-reviewed studies from IEEE Xplore, ACM, and Scopus were analyzed. Findings show three dominant approaches: 1.wind- and terrain-aware path planning, 2. hybrid energy systems including solar and fuel cells, and 3. learning-based power management. Results indicate that integrating environmental models with trajectory optimization can reduce energy consumption by 18–34%, while hybrid platforms achieve 2–8 times flight time over battery-only systems. Key gaps still persist in real-time energy prediction, multi-UAV coordination under energy constraints, and standardized energy benchmarks. However, we propose a four-layer framework: Environmental Modeling to Energy-Predictive Planning to Adaptive Control and to Fleet Energy Management. The review concludes that no single method is sufficient on its own alone hence long-endurance UAVs require co-design of hardware, algorithms, and mission planning.","author":[{"family":"Thankgod","given":"Ezirim"},{"family":"Muhammed","given":"Sani"},{"family":"Onyekachi","given":"Aniugo"},{"family":"Frank","given":"Nwaokolo"},{"family":"Immanuel","given":"Obi"},{"family":"Chinedu","given":"Okoronkwo"},{"family":"Momoh","given":"Aminu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21922412","URL":"https://doi.org/10.5281/zenodo.21922412","source":"datacite"},{"id":"doi:10.5281/zenodo.21922411","type":"article-journal","title":"Energy-Aware Robotics: Review of Path Planning and Power Optimization for Long-Endurance UAVs","abstract":"There is no gain saying of the obvious fact that Long-endurance, Unmanned Aerial Vehicles are critical not only for surveillance and precision agriculture, but also for disaster response, and environmental monitoring. However, battery capacity remains the primary constraint, with most multirotor UAVs limited to about 25–45 minutes of flight time. This review examines 2020–2026 research on energy-aware robotics, focusing on path planning and power optimization strategies that has the potential to extend UAV endurance. Following PRISMA 2020 guidelines, 112 peer-reviewed studies from IEEE Xplore, ACM, and Scopus were analyzed. Findings show three dominant approaches: 1.wind- and terrain-aware path planning, 2. hybrid energy systems including solar and fuel cells, and 3. learning-based power management. Results indicate that integrating environmental models with trajectory optimization can reduce energy consumption by 18–34%, while hybrid platforms achieve 2–8 times flight time over battery-only systems. Key gaps still persist in real-time energy prediction, multi-UAV coordination under energy constraints, and standardized energy benchmarks. However, we propose a four-layer framework: Environmental Modeling to Energy-Predictive Planning to Adaptive Control and to Fleet Energy Management. The review concludes that no single method is sufficient on its own alone hence long-endurance UAVs require co-design of hardware, algorithms, and mission planning.","author":[{"family":"Thankgod","given":"Ezirim"},{"family":"Muhammed","given":"Sani"},{"family":"Onyekachi","given":"Aniugo"},{"family":"Frank","given":"Nwaokolo"},{"family":"Immanuel","given":"Obi"},{"family":"Chinedu","given":"Okoronkwo"},{"family":"Momoh","given":"Aminu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21922411","URL":"https://doi.org/10.5281/zenodo.21922411","source":"datacite"},{"id":"doi:10.70062/slrj.v1i1.50","type":"article-journal","title":"Systematic Literature Review on CNN and YOLO Algorithms for Detecting Plant Diseases in Precision Agriculture","abstract":"Computer vision-based algorithms, especially Convolutional Neural Networks (CNN) and You Only Look Once (YOLO), have become the leading approaches in plant disease detection. CNN excels in extracting complex visual features for disease classification, while YOLO provides high-efficiency real-time object detection capabilities. Both algorithms have shown promising results in various studies, especially with controlled datasets. However, challenges remain in their application in real-world conditions, such as environmental diversity, overlapping symptoms, and poorly annotated data. Future research has the potential to optimize these algorithms through the development of lighter models, the use of transfer learning techniques, and multi-modal data integration. In addition, further exploration of a wider range of diseases, crops, and environmental conditions can expand the application of these algorithms. By leveraging these innovations, computer vision-based plant disease management can be improved to support sustainable precision agriculture.","author":[{"family":"Sasmoko","given":"Dani"},{"family":"Siswanto","given":"Eko"},{"family":"Febryantahanuji","given":"Febryantahanuji"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70062/slrj.v1i1.50","URL":"https://doi.org/10.70062/slrj.v1i1.50","source":"openalex"},{"id":"doi:10.5281/zenodo.20146495","type":"article-journal","title":"State of the alternative protein research and innovation ecosystem in Spain, 2020-2025","abstract":"This country deep-dive report, produced by the Good Food Institute Europe (GFI Europe), maps the state of the alternative protein research and innovation ecosystem in Spain across 2020–2025, including a supplementary summary in Spanish language. Spain produced 367 peer-reviewed publications on alternative proteins over the period, ranking sixth in Europe, with output growing by 542% – from 19 publications in 2020 to 122 in 2025 – the strongest publication growth rate of any European country. Despite this, Spain ranked only eleventh in Europe for published patent volume with 113 total patents, highlighting a significant gap between research output and commercial translation. Domestic public funding reached €26 million between 2020 and 2025, placing Spain ninth in Europe at approximately €1 per person; however, domestic investment dropped off sharply in recent years. By contrast, Spanish researchers led European Commission-funded projects worth over €60 million, making Spain the leading recipient of EU alternative protein funding 2020–2025, out of a cumulative European total exceeding €460 million. Of Spain's publications, 72% addressed plant-based proteins, 17% fermentation-made proteins and ingredients, and 3% cultivated meat and seafood. Research was conducted using bibliometric and patent data from Dimensions.ai, with funding data from GFI's Research Grants Tracker and Dimensions.ai; all records were screened against predefined inclusion/exclusion criteria. Publication and funding data cover 2020–2025; patent data covers 2015–2025. Spain's trajectory – strong academic output and European Commission funding capture alongside low domestic investment and limited patent activity – reflects the uneven development of national alternative protein ecosystems and the need for sustained policy commitment to the protein transition. If Spain prioritises alternative proteins, the sector could contribute €10 billion annually and support over 34,000 jobs by 2040. This report is intended for researchers, policymakers, research funders, and industry stakeholders seeking to understand Spain's position within the European alternative protein research and innovation landscape. This report is part of GFI Europe's series: State of the European Alternative Protein Research and Innovation Ecosystem (series DOI: 10.5281/zenodo.20124302). For more information visit https://gfieurope.org/","author":[{"family":"Child","given":"Stella"},{"family":"Hunt","given":"David"},{"family":"Europe","given":"Good"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20146495","URL":"https://doi.org/10.5281/zenodo.20146495","source":"datacite"},{"id":"doi:10.5281/zenodo.20146496","type":"article-journal","title":"State of the alternative protein research and innovation ecosystem in Spain, 2020-2025","abstract":"This country deep-dive report, produced by the Good Food Institute Europe (GFI Europe), maps the state of the alternative protein research and innovation ecosystem in Spain across 2020–2025, including a supplementary summary in Spanish language. Spain produced 367 peer-reviewed publications on alternative proteins over the period, ranking sixth in Europe, with output growing by 542% – from 19 publications in 2020 to 122 in 2025 – the strongest publication growth rate of any European country. Despite this, Spain ranked only eleventh in Europe for published patent volume with 113 total patents, highlighting a significant gap between research output and commercial translation. Domestic public funding reached €26 million between 2020 and 2025, placing Spain ninth in Europe at approximately €1 per person; however, domestic investment dropped off sharply in recent years. By contrast, Spanish researchers led European Commission-funded projects worth over €60 million, making Spain the leading recipient of EU alternative protein funding 2020–2025, out of a cumulative European total exceeding €460 million. Of Spain's publications, 72% addressed plant-based proteins, 17% fermentation-made proteins and ingredients, and 3% cultivated meat and seafood. Research was conducted using bibliometric and patent data from Dimensions.ai, with funding data from GFI's Research Grants Tracker and Dimensions.ai; all records were screened against predefined inclusion/exclusion criteria. Publication and funding data cover 2020–2025; patent data covers 2015–2025. Spain's trajectory – strong academic output and European Commission funding capture alongside low domestic investment and limited patent activity – reflects the uneven development of national alternative protein ecosystems and the need for sustained policy commitment to the protein transition. If Spain prioritises alternative proteins, the sector could contribute €10 billion annually and support over 34,000 jobs by 2040. This report is intended for researchers, policymakers, research funders, and industry stakeholders seeking to understand Spain's position within the European alternative protein research and innovation landscape. This report is part of GFI Europe's series: State of the European Alternative Protein Research and Innovation Ecosystem (series DOI: 10.5281/zenodo.20124302). For more information visit https://gfieurope.org/","author":[{"family":"Child","given":"Stella"},{"family":"Hunt","given":"David"},{"family":"Europe","given":"Good"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20146496","URL":"https://doi.org/10.5281/zenodo.20146496","source":"datacite"},{"id":"doi:10.5281/zenodo.20411865","type":"article-journal","title":"Acceleration of AI in Agriculture","abstract":"The continuous advancement of Artificial Intelligence (AI) has brought substantial changes to contemporary agricultural methods, by paving the most efficient way for sustainable farming practices.AI driven-agricultural technologies including farm advisory services,decision support systems and other chatbot solutions bought up some of the excellent changes in the agricultural sector.This findings align with earlier and recent studies on practical implementation of AI-based agricultural tools and their performance indicators. AI technologies in agriculture can contribute to increase in farm productivity,optimum utilization of available resources and improved access to better farming knowledge, especially for small-scale farmers. Nevertheless, issues such as reliance on large datasets, language diversity and infrastructural challenges remain significant. This study explores the current status of AI driven-agricultural technologies and outlines the future pathways toward developing scalable, inclusive and intelligent agricultural systems.","author":[{"family":"Tejaswini","given":"Katta"},{"family":"Devy","given":"Dr"},{"family":"Naveen","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20411865","URL":"https://doi.org/10.5281/zenodo.20411865","source":"datacite"},{"id":"doi:10.5281/zenodo.20411866","type":"article-journal","title":"Acceleration of AI in Agriculture","abstract":"The continuous advancement of Artificial Intelligence (AI) has brought substantial changes to contemporary agricultural methods, by paving the most efficient way for sustainable farming practices.AI driven-agricultural technologies including farm advisory services,decision support systems and other chatbot solutions bought up some of the excellent changes in the agricultural sector.This findings align with earlier and recent studies on practical implementation of AI-based agricultural tools and their performance indicators. AI technologies in agriculture can contribute to increase in farm productivity,optimum utilization of available resources and improved access to better farming knowledge, especially for small-scale farmers. Nevertheless, issues such as reliance on large datasets, language diversity and infrastructural challenges remain significant. This study explores the current status of AI driven-agricultural technologies and outlines the future pathways toward developing scalable, inclusive and intelligent agricultural systems.","author":[{"family":"Tejaswini","given":"Katta"},{"family":"Devy","given":"Dr"},{"family":"Naveen","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20411866","URL":"https://doi.org/10.5281/zenodo.20411866","source":"datacite"},{"id":"doi:10.5281/zenodo.21915529","type":"article-journal","title":"AI-Based Cocoa Pod Disease Detection to Support Farmers in Upper Denkyira","abstract":"Cocoa farmers in Upper Denkyira East Municipality, Ghana, can lose trees and harvests when pod diseases are noticed too late, and manual field inspection is often the only diagnostic option available. This paper presents a lightweight, mobile-deployable image classification system for early cocoa pod disease awareness. We apply transfer learning with a MobileNetV2 convolutional neural network, pre-trained on ImageNet, to a public cocoa pod image dataset across three classes: healthy, black pod rot, and pod borer. The model is paired with a farmer-facing advisory layer that translates each prediction into short, actionable guidance. Based on the test-set confusion matrix (n = 448), the model achieves approximately 88.2% overall accuracy, with strong performance on the majority \"healthy\" class (recall ≈ 0.97) but a substantially weaker recall on black pod rot (≈ 0.60) and an extremely small, statistically unreliable pod borer test sample (n = 4). Training curves further show validation accuracy peaking at epoch 4 (90.7%) before declining at epoch 5, an early sign of overfitting that this paper discusses openly. We situate these results against the parallel cassava leaf disease work by the same authors, discuss the model's limitations — including its reliance on secondary, non-Ghana-collected imagery, severe class imbalance in the pod borer class, and the absence of early stopping — and outline a path toward field validation and offline mobile deployment via TensorFlow Lite. This work demonstrates that existing, publicly documented deep learning techniques can be adapted at low cost into a locally-relevant decision-support tool for cocoa farmers in Upper Denkyira East.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21915529","URL":"https://doi.org/10.5281/zenodo.21915529","source":"datacite"},{"id":"doi:10.5281/zenodo.21915530","type":"article-journal","title":"AI-Based Cocoa Pod Disease Detection to Support Farmers in Upper Denkyira","abstract":"Cocoa farmers in Upper Denkyira East Municipality, Ghana, can lose trees and harvests when pod diseases are noticed too late, and manual field inspection is often the only diagnostic option available. This paper presents a lightweight, mobile-deployable image classification system for early cocoa pod disease awareness. We apply transfer learning with a MobileNetV2 convolutional neural network, pre-trained on ImageNet, to a public cocoa pod image dataset across three classes: healthy, black pod rot, and pod borer. The model is paired with a farmer-facing advisory layer that translates each prediction into short, actionable guidance. Based on the test-set confusion matrix (n = 448), the model achieves approximately 88.2% overall accuracy, with strong performance on the majority \"healthy\" class (recall ≈ 0.97) but a substantially weaker recall on black pod rot (≈ 0.60) and an extremely small, statistically unreliable pod borer test sample (n = 4). Training curves further show validation accuracy peaking at epoch 4 (90.7%) before declining at epoch 5, an early sign of overfitting that this paper discusses openly. We situate these results against the parallel cassava leaf disease work by the same authors, discuss the model's limitations — including its reliance on secondary, non-Ghana-collected imagery, severe class imbalance in the pod borer class, and the absence of early stopping — and outline a path toward field validation and offline mobile deployment via TensorFlow Lite. This work demonstrates that existing, publicly documented deep learning techniques can be adapted at low cost into a locally-relevant decision-support tool for cocoa farmers in Upper Denkyira East.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21915530","URL":"https://doi.org/10.5281/zenodo.21915530","source":"datacite"},{"id":"doi:10.57760/sciencedb.28364","type":"article-journal","title":"Chinese Cropland Parcel Dataset","abstract":"In order to address the challenge of fine-grained land parcel extraction in complex agricultural landscapes in China, this study developed the China Farmland Parcel Dataset (CCPD). This dataset is based on 5-meter resolution remote sensing images and covers 367 representative sample areas from 31 provincial-level administrative regions in China (excluding Hong Kong, Macao, and Taiwan), with a total area of 18485 square kilometers and 280016 manually mapped independent cultivated land parcels. CCPD not only provides high-precision vector data, but also supports pixel level structured labels, covering typical forms such as plain farmland, sloping farmland, and terraced farmland. It aims to provide a high-quality benchmark platform for the development, training, and evaluation of intelligent farmland extraction algorithms, and to assist in precision agriculture and fragmented land management","author":[{"family":"Zhu","given":"Zeqi"},{"family":"Chang","given":"Kexin"},{"family":"Xiong","given":"Li"},{"family":"Wen","given":"Qi"},{"family":"Li","given":"Shengyang"},{"family":"Duan","given":"Sibo"},{"family":"Yin","given":"Xiuyu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.57760/sciencedb.28364","URL":"https://doi.org/10.57760/sciencedb.28364","source":"datacite"},{"id":"doi:10.24412/1998-5533-2026-2-148-153","type":"article-journal","title":"Беспилотные авиационные системы в агропромышленном комплексе: анализ и перспективные сценарии применения для Республики Татарстан","abstract":"Цель исследования заключается в анализе текущего состояния и перспектив применения беспилотных авиационных систем (БАС) в агропромышленном комплексе Республики Татарстан, а также в разработке сценариев их внедрения и применения для повышения эффективности сельскохозяйственного производства. Актуальность исследования обусловлена необходимостью цифровой трансформации АПК и решения системных проблем отрасли, включая старение материально-технической базы, дефицит квалифицированных кадров и снижение рентабельности производства.Основные результаты исследования демонстрируют значительный потенциал применения БАС в АПК, включая существенную экономию на горюче-смазочных материалах и средствах защиты растений, повышение урожайности за счет точечного мониторинга и обработки полей, снижение негативного воздействия на почву. Практическая значимость работы заключается в разработке двух сценариев внедрения БАС: модели сервисного обслуживания и формирования полноценной региональной экосистемы «БАС-АПК». Предложенные решения позволяют оптимизировать производственные процессы, повысить эффективность использования техники и снизить операционные затраты.","author":[{"family":"Васильевич","given":"Хоменко"},{"family":"Радикович","given":"Хайруллин"},{"family":"Геннадьевич","given":"Дегтярев"},{"family":"Леонидович","given":"Стариков"}],"issued":{"date-parts":[[2026]]},"DOI":"10.24412/1998-5533-2026-2-148-153","URL":"https://doi.org/10.24412/1998-5533-2026-2-148-153","source":"datacite"},{"id":"doi:10.5281/zenodo.20068012","type":"article-journal","title":"Smart Agriculture Monitoring and Controlling System","abstract":"The agricultural issue in the planet is still an important one that is subject to the conditions of unpredictable weather conditions, the inefficient use of water and the impossibility to monitor the field that leads to severe reduction of crop production and the overall final production. The unavailability of automated decisionmaking systems in the majority of the developing areas also contributes to the waste of resources and manual labour. In an attempt to address these limitations, the present study suggests the implementation of an IoT-based Smart Agriculture Monitoring and Controlling System that would be able to execute real-time sensing, analytics and automated irrigation control. In order to make the field dynamically controlled, the system is composed of an ESP32 microcontroller, a soil moisture sensor, temperature–humidity sensor DHT11 and a water pump, which is driven by the relay. As the critical parameters of the environment are constantly tracked, it becomes possible to identify the condition of soil dryness, changes in climatic conditions, and the need to irrigate the land with high accuracy and start the automatic control of pumps according to the algorithms of the threshold. The proposed architecture aims at saving energy through the use of power, is wireless, modular, and scalable in the application within large farmlands. The wireless platform using ESP32 will most likely increase the speed of decision-making, reduce the water wastage, and increase the reliability when compared to the traditional hand-operated irrigation systems. Coupling of irrigation, sensor communication stability, and precision of moisture sensors have been demonstrated to be effective through the experimental validation and ensure optimal allocation of water and a minimum number of false triggers. The system is cost effective, economical and can accommodate the modern precision agricultural demands and operation offering a viable solution towards smart farming automation and management of agricultural resources.","author":[{"family":"Gaikwad","given":"Pranav"},{"family":"Parashar","given":"Gaurav"},{"family":"Garande","given":"Dada"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20068012","URL":"https://doi.org/10.5281/zenodo.20068012","source":"datacite"},{"id":"doi:10.5281/zenodo.20068013","type":"article-journal","title":"Smart Agriculture Monitoring and Controlling System","abstract":"The agricultural issue in the planet is still an important one that is subject to the conditions of unpredictable weather conditions, the inefficient use of water and the impossibility to monitor the field that leads to severe reduction of crop production and the overall final production. The unavailability of automated decisionmaking systems in the majority of the developing areas also contributes to the waste of resources and manual labour. In an attempt to address these limitations, the present study suggests the implementation of an IoT-based Smart Agriculture Monitoring and Controlling System that would be able to execute real-time sensing, analytics and automated irrigation control. In order to make the field dynamically controlled, the system is composed of an ESP32 microcontroller, a soil moisture sensor, temperature–humidity sensor DHT11 and a water pump, which is driven by the relay. As the critical parameters of the environment are constantly tracked, it becomes possible to identify the condition of soil dryness, changes in climatic conditions, and the need to irrigate the land with high accuracy and start the automatic control of pumps according to the algorithms of the threshold. The proposed architecture aims at saving energy through the use of power, is wireless, modular, and scalable in the application within large farmlands. The wireless platform using ESP32 will most likely increase the speed of decision-making, reduce the water wastage, and increase the reliability when compared to the traditional hand-operated irrigation systems. Coupling of irrigation, sensor communication stability, and precision of moisture sensors have been demonstrated to be effective through the experimental validation and ensure optimal allocation of water and a minimum number of false triggers. The system is cost effective, economical and can accommodate the modern precision agricultural demands and operation offering a viable solution towards smart farming automation and management of agricultural resources.","author":[{"family":"Gaikwad","given":"Pranav"},{"family":"Parashar","given":"Gaurav"},{"family":"Garande","given":"Dada"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20068013","URL":"https://doi.org/10.5281/zenodo.20068013","source":"datacite"},{"id":"doi:10.5281/zenodo.20926402","type":"article-journal","title":"A Review of Deep Learning Models for Automated Plant Leaf Disease Diagnosis and Prevention","abstract":"Crop diseases are a major challenge in modern agriculture, often leading to reduced crop productivity, economic losses, and threats to food security. Early and accurate identification of plant diseases is essential for implementing timely preventive measures and minimizing the spread of infections. Recent advances in deep learning have significantly improved the automation of crop disease detection through the analysis of leaf images. Among the various deep learning architectures, VGG16 and ResNet50 have emerged as highly effective models due to their strong feature extraction capabilities and classification performance. This survey paper presents a comprehensive review of crop disease detection and prevention techniques that utilize leaf image analysis with a particular focus on ensemble approaches combining VGG16 and ResNet50. The study examines the fundamental principles of image-based disease recognition, data preprocessing methods, transfer learning strategies, feature extraction mechanisms, and ensemble learning techniques employed in recent research. Furthermore, it analyzes the strengths and limitations of individual and hybrid deep learning models in terms of accuracy, computational efficiency, robustness, and real-world applicability. The survey also highlights the role of disease prevention systems that integrate predictive analytics and decision-support mechanisms to assist farmers in managing crop health effectively. Key challenges, including dataset diversity, environmental variability, model generalization, and deployment in resource-constrained agricultural settings, are discussed in detail.","author":[{"family":"Gosavi","given":"Prof"},{"family":"Gavali","given":"Sujal"},{"family":"Kodre","given":"Ayush"},{"family":"Kondhalkar","given":"Prajwal"},{"family":"Gaikwad","given":"Pranit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20926402","URL":"https://doi.org/10.5281/zenodo.20926402","source":"datacite"},{"id":"doi:10.5281/zenodo.20926403","type":"article-journal","title":"A Review of Deep Learning Models for Automated Plant Leaf Disease Diagnosis and Prevention","abstract":"Crop diseases are a major challenge in modern agriculture, often leading to reduced crop productivity, economic losses, and threats to food security. Early and accurate identification of plant diseases is essential for implementing timely preventive measures and minimizing the spread of infections. Recent advances in deep learning have significantly improved the automation of crop disease detection through the analysis of leaf images. Among the various deep learning architectures, VGG16 and ResNet50 have emerged as highly effective models due to their strong feature extraction capabilities and classification performance. This survey paper presents a comprehensive review of crop disease detection and prevention techniques that utilize leaf image analysis with a particular focus on ensemble approaches combining VGG16 and ResNet50. The study examines the fundamental principles of image-based disease recognition, data preprocessing methods, transfer learning strategies, feature extraction mechanisms, and ensemble learning techniques employed in recent research. Furthermore, it analyzes the strengths and limitations of individual and hybrid deep learning models in terms of accuracy, computational efficiency, robustness, and real-world applicability. The survey also highlights the role of disease prevention systems that integrate predictive analytics and decision-support mechanisms to assist farmers in managing crop health effectively. Key challenges, including dataset diversity, environmental variability, model generalization, and deployment in resource-constrained agricultural settings, are discussed in detail.","author":[{"family":"Gosavi","given":"Prof"},{"family":"Gavali","given":"Sujal"},{"family":"Kodre","given":"Ayush"},{"family":"Kondhalkar","given":"Prajwal"},{"family":"Gaikwad","given":"Pranit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20926403","URL":"https://doi.org/10.5281/zenodo.20926403","source":"datacite"},{"id":"doi:10.17632/vxz8hnrcfm.1","type":"article-journal","title":"[Supplementary Material] Detecting Hurricane-Induced Fallen Pecan Trees: A Novel UAV-Based Deep Learning Approach","abstract":"Hurricane events strongly affect the pecan crop by uprooting and lodging trees. Additionally, current fallen-tree monitoring relies on manual field surveys, which are invasive, time-consuming, and costly, constraining timely decision-making. Therefore, in this study, we deployed a deep learning (DL) framework based on the You Only Look Once (YOLO26) model to detect fallen pecan trees using unmanned aerial vehicle (UAV) RGB images. Flights were conducted over four pecan fields, ten days after Hurricane Helene crossed the state of Georgia, USA. As a result, 546 images were acquired and individually analyzed to detect fallen trees. Initially, ground-truth data were generated through assisted image processing, resulting in 2,408 annotations labeled “Fallen”. For our analysis, three fields were considered for the model development (training and validation). Subsequently, to ensure the model accuracy and reliability, a fourth independent field was used as the test dataset. Our results showed that the fallen tree detection models achieved a precision of 80.98–88.48%, a recall of 61.25–72.08%, and a mAP@50 of 70.93–77.50%. Among the evaluated variants, YOLO26m demonstrated the best performance on the independent test dataset, achieving an R2 of 0.74 and a mean absolute error (MAE) of 0.61 trees per image. Furthermore, we designed a user-friendly platform as a proof of concept to evaluate the model’s operability. This study, therefore, presents a novel UAV-based object detection framework for detecting fallen pecan trees, empowering stakeholders with a precise, accurate, non-invasive, safe, and rapid solution. These findings also support precision agriculture practices and promote the integration of advanced technologies into tree-crop management systems.","author":[{"family":"Barbosa","given":"Marcelo"},{"family":"Porto","given":"Romário"},{"family":"Dos Santos","given":"Regimar"},{"family":"Wells","given":"Lenny"},{"family":"Oliveira","given":"Luan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/vxz8hnrcfm.1","URL":"https://doi.org/10.17632/vxz8hnrcfm.1","source":"datacite"},{"id":"doi:10.17632/vxz8hnrcfm","type":"article-journal","title":"[Supplementary Material] Detecting Hurricane-Induced Fallen Pecan Trees: A Novel UAV-Based Deep Learning Approach","abstract":"Hurricane events strongly affect the pecan crop by uprooting and lodging trees. Additionally, current fallen-tree monitoring relies on manual field surveys, which are invasive, time-consuming, and costly, constraining timely decision-making. Therefore, in this study, we deployed a deep learning (DL) framework based on the You Only Look Once (YOLO26) model to detect fallen pecan trees using unmanned aerial vehicle (UAV) RGB images. Flights were conducted over four pecan fields, ten days after Hurricane Helene crossed the state of Georgia, USA. As a result, 546 images were acquired and individually analyzed to detect fallen trees. Initially, ground-truth data were generated through assisted image processing, resulting in 2,408 annotations labeled “Fallen”. For our analysis, three fields were considered for the model development (training and validation). Subsequently, to ensure the model accuracy and reliability, a fourth independent field was used as the test dataset. Our results showed that the fallen tree detection models achieved a precision of 80.98–88.48%, a recall of 61.25–72.08%, and a mAP@50 of 70.93–77.50%. Among the evaluated variants, YOLO26m demonstrated the best performance on the independent test dataset, achieving an R2 of 0.74 and a mean absolute error (MAE) of 0.61 trees per image. Furthermore, we designed a user-friendly platform as a proof of concept to evaluate the model’s operability. This study, therefore, presents a novel UAV-based object detection framework for detecting fallen pecan trees, empowering stakeholders with a precise, accurate, non-invasive, safe, and rapid solution. These findings also support precision agriculture practices and promote the integration of advanced technologies into tree-crop management systems.","author":[{"family":"Barbosa","given":"Marcelo"},{"family":"Porto","given":"Romário"},{"family":"Dos Santos","given":"Regimar"},{"family":"Wells","given":"Lenny"},{"family":"Oliveira","given":"Luan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/vxz8hnrcfm","URL":"https://doi.org/10.17632/vxz8hnrcfm","source":"datacite"},{"id":"doi:10.5281/zenodo.20846561","type":"article-journal","title":"GrapeAI: A Dual Deep-Learning Approach for Vineyard Canopy Coverage Estimation and Foliar Disease Diagnosis","abstract":"Grapevine farming continues to suffer significant yield losses from fungal foliar disease that is presently diagnosed mainly through manual, agronomist-led field inspection. This paper describes GrapeAI, a two-stage computer-vision pipeline that pairs a self-trained segmentation network for canopy-cover estimation with a transfer-learning-based classifier for foliar disease recognition. The segmentation stage, built around a U-Net style encoder-decoder [5] trained on a custom-labelled set of 587 canopy images, outputs a binary vegetation mask from which percentage canopy cover is calculated. The recognition stage fine-tunes an EfficientNet-B4 network [7], pretrained on ImageNet [15], to separate four conditions: Black Rot, Esca, Leaf Blight, and Healthy. The two outputs feed a severity estimator and a rule-based advisory module that together generate a treatment and pruning recommendation. On held-out data the segmentation network reaches close to 0.85 IoU and the classifier reaches a weighted F1-score near 93%, results broadly comparable to published single-purpose grape-disease systems while additionally providing canopy quantification absent from most prior work. Furthermore, the proposed framework contributes toward the advancement of smart agriculture by enabling continuous crop monitoring through automated image analysis. Unlike conventional approaches that focus solely on disease classification, the integration of canopy assessment and severity evaluation provides a more comprehensive understanding of vineyard health. The generated insights can assist growers in optimizing pruning schedules, improving resource utilization, and reducing the risk of yield loss caused by delayed disease management. The modular architecture of the system also allows future integration with mobile devices, IoT-based sensing platforms, and drone-acquired imagery, making it suitable for large-scale vineyard monitoring and precision farming applications.","author":[{"family":"Ingle","given":"Prof"},{"family":"Mane","given":"Jay"},{"family":"Pansare","given":"Utkal"},{"family":"Patil","given":"Shailesh"},{"family":"Patil","given":"Jay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20846561","URL":"https://doi.org/10.5281/zenodo.20846561","source":"datacite"},{"id":"doi:10.5281/zenodo.20846562","type":"article-journal","title":"GrapeAI: A Dual Deep-Learning Approach for Vineyard Canopy Coverage Estimation and Foliar Disease Diagnosis","abstract":"Grapevine farming continues to suffer significant yield losses from fungal foliar disease that is presently diagnosed mainly through manual, agronomist-led field inspection. This paper describes GrapeAI, a two-stage computer-vision pipeline that pairs a self-trained segmentation network for canopy-cover estimation with a transfer-learning-based classifier for foliar disease recognition. The segmentation stage, built around a U-Net style encoder-decoder [5] trained on a custom-labelled set of 587 canopy images, outputs a binary vegetation mask from which percentage canopy cover is calculated. The recognition stage fine-tunes an EfficientNet-B4 network [7], pretrained on ImageNet [15], to separate four conditions: Black Rot, Esca, Leaf Blight, and Healthy. The two outputs feed a severity estimator and a rule-based advisory module that together generate a treatment and pruning recommendation. On held-out data the segmentation network reaches close to 0.85 IoU and the classifier reaches a weighted F1-score near 93%, results broadly comparable to published single-purpose grape-disease systems while additionally providing canopy quantification absent from most prior work. Furthermore, the proposed framework contributes toward the advancement of smart agriculture by enabling continuous crop monitoring through automated image analysis. Unlike conventional approaches that focus solely on disease classification, the integration of canopy assessment and severity evaluation provides a more comprehensive understanding of vineyard health. The generated insights can assist growers in optimizing pruning schedules, improving resource utilization, and reducing the risk of yield loss caused by delayed disease management. The modular architecture of the system also allows future integration with mobile devices, IoT-based sensing platforms, and drone-acquired imagery, making it suitable for large-scale vineyard monitoring and precision farming applications.","author":[{"family":"Ingle","given":"Prof"},{"family":"Mane","given":"Jay"},{"family":"Pansare","given":"Utkal"},{"family":"Patil","given":"Shailesh"},{"family":"Patil","given":"Jay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20846562","URL":"https://doi.org/10.5281/zenodo.20846562","source":"datacite"},{"id":"doi:10.5281/zenodo.21893516","type":"article-journal","title":"Pineapple Leaf Disease Dataset: Field-Acquired Images for Deep Learning-Based Plant Health Assessment","abstract":"This dataset contains original field-acquired images of pineapple leaves for deep learning-based disease classification and precision agriculture research. Images were collected from pineapple cultivation regions in Vazhakulam, Kerala, India. The dataset consists of four classes: Healthy, Mealybug Wilt, Fusarium Rot, and Leaf Blight. For each class, 50 unique pineapple leaf specimens were selected, and each specimen was photographed with a minimum of 20 distinct original images from different viewpoints, distances, and orientations. The dataset contains a total of 4,476 original images, comprising 1,157 Fusarium images, 1,118 Healthy Leaf images, 1,112 Leaf Blight images, and 1,089 Mealybug Wilt images. All images were captured under natural field conditions with the leaves remaining attached to the pineapple plants; no leaves were cut or detached for image acquisition. The dataset contains original images only and does not include artificially augmented images. Each specimen is assigned a unique ID, and the images are organized class-wise and specimen-wise. Metadata describing the image name, class, specimen ID, collection information, camera is provided with the dataset. The dataset is intended for research in pineapple leaf disease classification, computer vision, deep learning, and precision agriculture.","author":[{"family":"Raj","given":"Saranya"},{"family":"Prakash","given":"Nupur"},{"family":"Malik","given":"Nidhi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21893516","URL":"https://doi.org/10.5281/zenodo.21893516","source":"datacite"},{"id":"doi:10.5281/zenodo.21893515","type":"article-journal","title":"Pineapple Leaf Disease Dataset: Field-Acquired Images for Deep Learning-Based Plant Health Assessment","abstract":"This dataset contains original field-acquired images of pineapple leaves for deep learning-based disease classification and precision agriculture research. Images were collected from pineapple cultivation regions in Vazhakulam, Kerala, India. The dataset consists of four classes: Healthy, Mealybug Wilt, Fusarium Rot, and Leaf Blight. For each class, 50 unique pineapple leaf specimens were selected, and each specimen was photographed with a minimum of 20 distinct original images from different viewpoints, distances, and orientations. The dataset contains a total of 4,476 original images, comprising 1,157 Fusarium images, 1,118 Healthy Leaf images, 1,112 Leaf Blight images, and 1,089 Mealybug Wilt images. All images were captured under natural field conditions with the leaves remaining attached to the pineapple plants; no leaves were cut or detached for image acquisition. The dataset contains original images only and does not include artificially augmented images. Each specimen is assigned a unique ID, and the images are organized class-wise and specimen-wise. Metadata describing the image name, class, specimen ID, collection information, camera is provided with the dataset. The dataset is intended for research in pineapple leaf disease classification, computer vision, deep learning, and precision agriculture.","author":[{"family":"Raj","given":"Saranya"},{"family":"Prakash","given":"Nupur"},{"family":"Malik","given":"Nidhi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21893515","URL":"https://doi.org/10.5281/zenodo.21893515","source":"datacite"},{"id":"doi:10.5281/zenodo.21892368","type":"article-journal","title":"AI-Based Cassava Leaf Disease Detection to Support Smallholder Farmers in Ghana","abstract":"Late detection of cassava leaf disease is a major cause of crop loss among smallholder farmers in Ghana, where manual field inspection is often the only diagnostic tool available. This paper presents a lightweight, mobile-deployable image classification system for early cassava disease awareness. We apply transfer learning with a MobileNetV2 convolutional neural network, pretrained on ImageNet, to the public iCassava leaf image dataset across five classes: healthy, Cassava Bacterial Blight (CBB), Cassava Brown Streak Disease (CBSD), Cassava Green Mite (CGM), and Cassava Mosaic Disease (CMD). The model is paired with a farmer-facing advisory layer that translates each prediction into short, actionable guidance. On a held-out test set (n = 1,885) the model achieves 76.71% overall accuracy (test loss: 0.6479; weighted F1: 0.75; macro F1: 0.64) after 5 training epochs with the MobileNetV2 base frozen. Per-class analysis reveals substantial variation in performance: the majority class (CMD) reaches 0.90 recall, while the minority class (CBB) reaches only 0.30 recall, driven largely by confusion with CBSD. We situate these results against prior work on the same dataset lineage, discuss the model's limitations — including its reliance on secondary, non-Ghana-collected imagery and its uncorrected class imbalance — and outline a path toward field validation and offline mobile deployment via TensorFlow Lite. This work demonstrates that existing, publicly documented deep learning techniques can be adapted at low cost into a locally-relevant decision-support tool for Ghanaian agricultural extension. Keywords: cassava disease detection, transfer learning, MobileNetV2, precision agriculture, Ghana, smallholder farming, class imbalance","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21892368","URL":"https://doi.org/10.5281/zenodo.21892368","source":"datacite"},{"id":"doi:10.5281/zenodo.21892369","type":"article-journal","title":"AI-Based Cassava Leaf Disease Detection to Support Smallholder Farmers in Ghana","abstract":"Late detection of cassava leaf disease is a major cause of crop loss among smallholder farmers in Ghana, where manual field inspection is often the only diagnostic tool available. This paper presents a lightweight, mobile-deployable image classification system for early cassava disease awareness. We apply transfer learning with a MobileNetV2 convolutional neural network, pretrained on ImageNet, to the public iCassava leaf image dataset across five classes: healthy, Cassava Bacterial Blight (CBB), Cassava Brown Streak Disease (CBSD), Cassava Green Mite (CGM), and Cassava Mosaic Disease (CMD). The model is paired with a farmer-facing advisory layer that translates each prediction into short, actionable guidance. On a held-out test set (n = 1,885) the model achieves 76.71% overall accuracy (test loss: 0.6479; weighted F1: 0.75; macro F1: 0.64) after 5 training epochs with the MobileNetV2 base frozen. Per-class analysis reveals substantial variation in performance: the majority class (CMD) reaches 0.90 recall, while the minority class (CBB) reaches only 0.30 recall, driven largely by confusion with CBSD. We situate these results against prior work on the same dataset lineage, discuss the model's limitations — including its reliance on secondary, non-Ghana-collected imagery and its uncorrected class imbalance — and outline a path toward field validation and offline mobile deployment via TensorFlow Lite. This work demonstrates that existing, publicly documented deep learning techniques can be adapted at low cost into a locally-relevant decision-support tool for Ghanaian agricultural extension. Keywords: cassava disease detection, transfer learning, MobileNetV2, precision agriculture, Ghana, smallholder farming, class imbalance","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21892369","URL":"https://doi.org/10.5281/zenodo.21892369","source":"datacite"},{"id":"doi:10.5281/zenodo.21887478","type":"article-journal","title":"Sunflower Seed Oil Yield Prediction using Machine Learning","abstract":"Sunflower (Helianthus annuus L.) is a highly cultivated oilseed crop, appreciated for its high-quality edible oil. Manual rating of seed yield potential is time consuming and subjective in nature. This study proposes a deep learning-based sunflower seed oil yield prediction system using MobileNetV2. In this study, the model was trained to classify seeds into high- and low-yield categories based on visual features of seeds, including texture, shape, and color. The framework achieved an accuracy rate of 92.3% and was deployed in a Gradio web interface for real-time prediction. This system enhances low-cost, efficient and scalable tools in precision agriculture and seed quality assessment [1].","author":[{"family":"Srinivasa","given":"MG"},{"family":"Prabhu","given":"Rachana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21887478","URL":"https://doi.org/10.5281/zenodo.21887478","source":"datacite"},{"id":"doi:10.5281/zenodo.21887479","type":"article-journal","title":"Sunflower Seed Oil Yield Prediction using Machine Learning","abstract":"Sunflower (Helianthus annuus L.) is a highly cultivated oilseed crop, appreciated for its high-quality edible oil. Manual rating of seed yield potential is time consuming and subjective in nature. This study proposes a deep learning-based sunflower seed oil yield prediction system using MobileNetV2. In this study, the model was trained to classify seeds into high- and low-yield categories based on visual features of seeds, including texture, shape, and color. The framework achieved an accuracy rate of 92.3% and was deployed in a Gradio web interface for real-time prediction. This system enhances low-cost, efficient and scalable tools in precision agriculture and seed quality assessment [1].","author":[{"family":"Srinivasa","given":"MG"},{"family":"Prabhu","given":"Rachana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21887479","URL":"https://doi.org/10.5281/zenodo.21887479","source":"datacite"},{"id":"doi:10.5281/zenodo.21864642","type":"article-journal","title":"AI-based biomimetic route optimization for micro-UAV systems inspired by honeybee foraging behavior","abstract":"This conference paper proposes an AI-based biomimetic route optimization framework for micro-UAV systems inspired by the foraging behavior of honeybees (Apis mellifera). The study combines field observations, expert interviews and microscopic biomimetic evidence to interpret honeybee behavior as a model for adaptive route planning. Hive entry-exit activity, weather parameters, activity intensity and environmental conditions were recorded at three observation points in the Goygol and Dashkasan regions of Azerbaijan. The findings show that honeybee foraging behavior can be translated into micro-UAV route optimization principles such as decentralized search, adaptive path selection, exploration-exploitation balance, inter-agent communication and environmental responsiveness. The proposed model may support more energy-efficient, adaptive and resilient micro-UAV operations in environmental monitoring, search and rescue missions, precision agriculture and distributed observation systems.","author":[{"family":"Qadimli","given":"Nushaba"},{"family":"Mammadov","given":"Ulvi"},{"family":"Hasilov","given":"Elvin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21864642","URL":"https://doi.org/10.5281/zenodo.21864642","source":"datacite"},{"id":"doi:10.5281/zenodo.21864641","type":"article-journal","title":"AI-based biomimetic route optimization for micro-UAV systems inspired by honeybee foraging behavior","abstract":"This conference paper proposes an AI-based biomimetic route optimization framework for micro-UAV systems inspired by the foraging behavior of honeybees (Apis mellifera). The study combines field observations, expert interviews and microscopic biomimetic evidence to interpret honeybee behavior as a model for adaptive route planning. Hive entry-exit activity, weather parameters, activity intensity and environmental conditions were recorded at three observation points in the Goygol and Dashkasan regions of Azerbaijan. The findings show that honeybee foraging behavior can be translated into micro-UAV route optimization principles such as decentralized search, adaptive path selection, exploration-exploitation balance, inter-agent communication and environmental responsiveness. The proposed model may support more energy-efficient, adaptive and resilient micro-UAV operations in environmental monitoring, search and rescue missions, precision agriculture and distributed observation systems.","author":[{"family":"Qadimli","given":"Nushaba"},{"family":"Mammadov","given":"Ulvi"},{"family":"Hasilov","given":"Elvin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21864641","URL":"https://doi.org/10.5281/zenodo.21864641","source":"datacite"},{"id":"doi:10.5281/zenodo.21859213","type":"article-journal","title":"Emerging Trends in Robotics and Automation for Sustainable Development in Nigeria","abstract":"Nigeria faces significant developmental challenges in agriculture, healthcare, waste management, and infrastructure, which hinder progress toward the Sustainable Development Goals (SDGs). Emerging trends in robotics and automation offer transformative solutions to enhance efficiency, reduce human error, and optimize resource utilization. This article explores four key trends: autonomous agricultural robots for precision farming, automated waste-sorting systems for the circular economy, drone-based healthcare logistics, and AI-driven infrastructure monitoring. Using a mixed-method approach combining case study analysis and secondary data from Nigerian pilot projects (2019–2025), the study evaluates the feasibility, socio-economic impacts, and sustainability potential of these technologies. Findings indicate that robotics can increase crop yields by up to 40%, reduce post-harvest losses by 25%, improve medical supply delivery times by 70%, and enhance waste recycling rates from 10% to 45%. However, challenges such as high initial costs, inadequate power supply, low digital literacy, and policy gaps remain pervasive. The article presents a table of seven ongoing automation initiatives in Nigeria and discusses their outcomes. Recommendations include government-backed innovation hubs, public-private partnerships for renewable-powered robotics, and curriculum reforms in tertiary institutions. Conclusively, strategic deployment of robotics and automation aligns with SDGs 2 (zero hunger), 3 (good health), 9 (industry innovation), 11 (sustainable cities), and 12 (responsible consumption). Nigeria must adopt a phased, inclusive automation roadmap to achieve sustainable development.","author":[{"family":"Ifeachor","given":"Henry"},{"family":"Chukwukadibia","given":"Agha"},{"family":"Ebubechukwu","given":"Onwualia"},{"family":"Chukwuemeka","given":"Eneh"},{"family":"Francis","given":"Okoye"},{"family":"Clara","given":"Omulu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21859213","URL":"https://doi.org/10.5281/zenodo.21859213","source":"datacite"},{"id":"doi:10.5281/zenodo.21859212","type":"article-journal","title":"Emerging Trends in Robotics and Automation for Sustainable Development in Nigeria","abstract":"Nigeria faces significant developmental challenges in agriculture, healthcare, waste management, and infrastructure, which hinder progress toward the Sustainable Development Goals (SDGs). Emerging trends in robotics and automation offer transformative solutions to enhance efficiency, reduce human error, and optimize resource utilization. This article explores four key trends: autonomous agricultural robots for precision farming, automated waste-sorting systems for the circular economy, drone-based healthcare logistics, and AI-driven infrastructure monitoring. Using a mixed-method approach combining case study analysis and secondary data from Nigerian pilot projects (2019–2025), the study evaluates the feasibility, socio-economic impacts, and sustainability potential of these technologies. Findings indicate that robotics can increase crop yields by up to 40%, reduce post-harvest losses by 25%, improve medical supply delivery times by 70%, and enhance waste recycling rates from 10% to 45%. However, challenges such as high initial costs, inadequate power supply, low digital literacy, and policy gaps remain pervasive. The article presents a table of seven ongoing automation initiatives in Nigeria and discusses their outcomes. Recommendations include government-backed innovation hubs, public-private partnerships for renewable-powered robotics, and curriculum reforms in tertiary institutions. Conclusively, strategic deployment of robotics and automation aligns with SDGs 2 (zero hunger), 3 (good health), 9 (industry innovation), 11 (sustainable cities), and 12 (responsible consumption). Nigeria must adopt a phased, inclusive automation roadmap to achieve sustainable development.","author":[{"family":"Ifeachor","given":"Henry"},{"family":"Chukwukadibia","given":"Agha"},{"family":"Ebubechukwu","given":"Onwualia"},{"family":"Chukwuemeka","given":"Eneh"},{"family":"Francis","given":"Okoye"},{"family":"Clara","given":"Omulu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21859212","URL":"https://doi.org/10.5281/zenodo.21859212","source":"datacite"},{"id":"doi:10.5281/zenodo.21848384","type":"article-journal","title":"Development of a Deep Learning-Based Smart Irrigation System Using IoT for Automated Crop Water Optimization","abstract":"Conventional irrigation systems account for approximately 70% of global freshwater withdrawals yet routinely waste 25%–40% of applied water through static time-based scheduling that fails to account for dynamic soil and atmospheric variability. This study developed and field-validated a smart irrigation system integrating a multi-sensor IoT network with a hybrid convolutional neural network–long short-term memory (CNN- LSTM) deep learning architecture for automated, data-driven binary irrigation scheduling across three economically important crop types. Over an 18-month field trial (January 2023–June 2024), capacitive soil moisture, DHT22 temperature-humidity, and SR05 pyranometer sensors were deployed across 12 active sensing nodes in 0.5-hectare plots of maize (Zea mays), tomato (Solanum lycopersicum), and wheat (Triticum aestivum) in a semi-arid climate zone, generating 52,416 multivariate time-series observations. On the technical modelling front, benchmarked against artificial neural network, support vector machine, random forest, and standalone LSTM baselines, the CNN -LSTM achieved the highest binary classification accuracies of 94.7%, 93.2%, and 95.6% for maize, tomato, and wheat, respectively, with RMSE values below 0.045 across all crops. On the applied field-performance front, relative to conventional fixed-schedule control plots maintained across four replicates per crop, the system reduced seasonal water consumption by a statistically significant mean of 37.5% (95% CI: 35.1%–39.9%, p < 0.001) and improved end-of-season crop yield by a mean of 21.2% (95% CI: 19.7%– 22.7%, p < 0.001). These results demonstrate the practical feasibility of IoT -integrated deep learning irrigation within a semi-arid, sandy loam experimental context, with potential implications for precision water management in comparable agroclimatic settings pending multi-site external validation.","author":[{"family":"Eberechi","given":"Uchegbu"},{"family":"Kelechi","given":"Inyama"},{"family":"Chinenye","given":"Duru"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21848384","URL":"https://doi.org/10.5281/zenodo.21848384","source":"datacite"},{"id":"doi:10.5281/zenodo.21848383","type":"article-journal","title":"Development of a Deep Learning-Based Smart Irrigation System Using IoT for Automated Crop Water Optimization","abstract":"Conventional irrigation systems account for approximately 70% of global freshwater withdrawals yet routinely waste 25%–40% of applied water through static time-based scheduling that fails to account for dynamic soil and atmospheric variability. This study developed and field-validated a smart irrigation system integrating a multi-sensor IoT network with a hybrid convolutional neural network–long short-term memory (CNN- LSTM) deep learning architecture for automated, data-driven binary irrigation scheduling across three economically important crop types. Over an 18-month field trial (January 2023–June 2024), capacitive soil moisture, DHT22 temperature-humidity, and SR05 pyranometer sensors were deployed across 12 active sensing nodes in 0.5-hectare plots of maize (Zea mays), tomato (Solanum lycopersicum), and wheat (Triticum aestivum) in a semi-arid climate zone, generating 52,416 multivariate time-series observations. On the technical modelling front, benchmarked against artificial neural network, support vector machine, random forest, and standalone LSTM baselines, the CNN -LSTM achieved the highest binary classification accuracies of 94.7%, 93.2%, and 95.6% for maize, tomato, and wheat, respectively, with RMSE values below 0.045 across all crops. On the applied field-performance front, relative to conventional fixed-schedule control plots maintained across four replicates per crop, the system reduced seasonal water consumption by a statistically significant mean of 37.5% (95% CI: 35.1%–39.9%, p < 0.001) and improved end-of-season crop yield by a mean of 21.2% (95% CI: 19.7%– 22.7%, p < 0.001). These results demonstrate the practical feasibility of IoT -integrated deep learning irrigation within a semi-arid, sandy loam experimental context, with potential implications for precision water management in comparable agroclimatic settings pending multi-site external validation.","author":[{"family":"Eberechi","given":"Uchegbu"},{"family":"Kelechi","given":"Inyama"},{"family":"Chinenye","given":"Duru"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21848383","URL":"https://doi.org/10.5281/zenodo.21848383","source":"datacite"},{"id":"doi:10.17863/cam.127911","type":"article-journal","title":"The optical nose: Monolayer sensitization of Au surfaces for plasmonic gas sensing.","abstract":"Robust real-time gas sensing is important for many fields, including agriculture and health care analysis of breath/biofluid volatiles. Ammonia is ambiently present at parts per billion (ppb) to parts per million (ppm) levels, but current detection technologies suffer long measurement times, instability, cost, and issues with selectivity. Here, surface-enhanced Raman spectroscopy (SERS) is markedly improved through precision precleaning protocols, which allow surface sensitization of the metal facets using a water monolayer. Harnessing monolayer aggregates of densely packed gold nanoparticles with sub-nanometer spacing defined by rigid scaffolding molecules gives sub-ppm detection of ammonia at room temperature. Accessing the poorly studied high-wave number [&gt;2500 per centimeter (cm-1)] region provides much improved discriminatory capabilities, enabling us to generalize this approach to a range of volatile organic carbon (VOC) molecules including ethanol, methanol, and acetone.","author":[{"family":"Wyatt","given":"Elle"},{"family":"Sibug-Torres","given":"Sarah"},{"family":"Niihori","given":"Marika"},{"family":"Beattie","given":"James"},{"family":"Jones","given":"Tabitha"},{"family":"Spiesshofer","given":"Nicolas"},{"family":"Hofmann","given":"Jana"},{"family":"De Nijs","given":"Bart"},{"family":"Baumberg","given":"Jeremy"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17863/cam.127911","URL":"https://doi.org/10.17863/cam.127911","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33145205","type":"article-journal","title":"CitrusCultivar-BD: A Real-World Annotated Dataset of Lemon and Pomelo Cultivars","abstract":"CitrusCultivar-BD is a real-world annotated image dataset developed to support research in computer vision, artificial intelligence, machine learning, and precision agriculture. The dataset contains 1,820 images of eleven citrus cultivars commonly grown in Bangladesh, including multiple lemon and pomelo varieties: BARI Lemon-1, BARI Lemon-2, BARI Lemon-3, BARI Lemon-4, BARI Pomelo-2, BARI Pomelo-5, Colombo Lemon, Elachi Lemon, Paper Lemon, Pomelo, and Seedless Lemon .The images were collected under diverse environmental conditions, capturing variations in lighting, viewing angles, fruit orientation, background complexity, and maturity stages to reflect real-world agricultural scenarios. Each image was manually annotated following a standardized labeling protocol to ensure high-quality and consistent class assignments.The dataset is intended for applications such as citrus cultivar identification, image classification, object detection, plant phenotyping, automated crop monitoring, smart farming, and agricultural decision-support systems. Researchers can use this dataset to develop, train, and evaluate deep learning and computer vision models for automated fruit variety recognition and precision agriculture applications.The repository includes image data, annotation files, metadata, and supporting documentation to facilitate reproducible research and benchmarking. The dataset provides a valuable resource for advancing AI-driven agricultural technologies and promoting the development of intelligent citrus cultivation systems.","author":[{"family":"Rahman","given":"Md"},{"family":"Rahman","given":"Tarek"},{"family":"Ahmmed","given":"Farhana"},{"family":"Arju","given":"Aminul"},{"family":"Ashik","given":"Khorshed"},{"family":"Jishan","given":"Jehen"},{"family":"Alif","given":"Md"},{"family":"Islam","given":"Sadia"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33145205","URL":"https://doi.org/10.6084/m9.figshare.33145205","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33145205.v1","type":"article-journal","title":"CitrusCultivar-BD: A Real-World Annotated Dataset of Lemon and Pomelo Cultivars","abstract":"CitrusCultivar-BD is a real-world annotated image dataset developed to support research in computer vision, artificial intelligence, machine learning, and precision agriculture. The dataset contains 1,820 images of eleven citrus cultivars commonly grown in Bangladesh, including multiple lemon and pomelo varieties: BARI Lemon-1, BARI Lemon-2, BARI Lemon-3, BARI Lemon-4, BARI Pomelo-2, BARI Pomelo-5, Colombo Lemon, Elachi Lemon, Paper Lemon, Pomelo, and Seedless Lemon .The images were collected under diverse environmental conditions, capturing variations in lighting, viewing angles, fruit orientation, background complexity, and maturity stages to reflect real-world agricultural scenarios. Each image was manually annotated following a standardized labeling protocol to ensure high-quality and consistent class assignments.The dataset is intended for applications such as citrus cultivar identification, image classification, object detection, plant phenotyping, automated crop monitoring, smart farming, and agricultural decision-support systems. Researchers can use this dataset to develop, train, and evaluate deep learning and computer vision models for automated fruit variety recognition and precision agriculture applications.The repository includes image data, annotation files, metadata, and supporting documentation to facilitate reproducible research and benchmarking. The dataset provides a valuable resource for advancing AI-driven agricultural technologies and promoting the development of intelligent citrus cultivation systems.","author":[{"family":"Rahman","given":"Md"},{"family":"Rahman","given":"Tarek"},{"family":"Ahmmed","given":"Farhana"},{"family":"Arju","given":"Aminul"},{"family":"Ashik","given":"Khorshed"},{"family":"Jishan","given":"Jehen"},{"family":"Alif","given":"Md"},{"family":"Islam","given":"Sadia"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33145205.v1","URL":"https://doi.org/10.6084/m9.figshare.33145205.v1","source":"datacite"},{"id":"doi:10.7910/dvn/yxgpcg","type":"article-journal","title":"Baseline Survey Dataset on Agricultural Practices, Dietary Diversity, and Socio-Economic Indicators in Vihiga County, Kenya (2018)","abstract":"This dataset originates from a baseline survey conducted between November 12 and November 30, 2018, in Vihiga County, Kenya. The survey was part of the project titled \"Improving access to and benefits from a wealth of diverse seeds to support on-farm biodiversity for healthy people in resilient landscapes.\" The primary purpose of the study was to assess key indicators of agricultural practices, dietary diversity, socio-economic status, and food security at the household level. It aimed to establish a foundational understanding of the community's agricultural and nutritional landscape, serving as a benchmark for future interventions. The dataset includes detailed information on demographic and socio-economic characteristics, household income, market access, wealth profiles, household food security, dietary changes, maternal nutritional knowledge, and attitudes. Additionally, it captures household agricultural practices, including the adoption of climate-smart technologies, social seed networks for traditional leafy vegetables and legumes, and smart poultry farming practices. Quantitative 24-hour dietary recall data for women and children was also collected to assess dietary diversity and nutritional adequacy. &lt;br&gt; The principal investigators sought to answer key questions such as: &lt;ul&gt; &lt;li&gt;i) What is the current state of dietary diversity and nutritional practices among women and children?&lt;/li&gt; &lt;li&gt;ii) How are socio-economic factors and market access influencing household food security?&lt;/li&gt; &lt;li&gt;iii) What role do agricultural practices and farm diversity play in household resilience and nutrition? &lt;/li&gt; &lt;li&gt;iv) What are the existing knowledge, attitudes, and practices surrounding maternal nutrition and climate-smart farming technologies?&lt;/li&gt; &lt;/ul&gt; This dataset provides a comprehensive snapshot of the intervention and comparison sites, enabling insights into the baseline conditions and laying the groundwork for evaluating the project's impact. &lt;br&gt; &lt;br&gt; Methodology: The baseline data was collected as part of a survey conducted in Vihiga County, Kenya, from November 12 to November 30, 2018. The study employed a quasi-randomized controlled design, sampling households from three categories: proposed intervention areas (216 households), comparison areas (160 households), and areas with prior interventions conducted before this baseline study (55 households). Including the previously intervened areas aimed to assess differences over time between these areas and the newly selected intervention areas. Households were eligible if they included at least one woman of reproductive age (15–49 years) and a child aged 6–23 months. The survey utilized structured tools, including a household questionnaire and a 24-hour dietary recall. The household questionnaire captured demographic and socio-economic data, household income, market access, food security, wealth profiles, agricultural practices, and maternal nutritional knowledge and attitudes. The dietary recall focused on quantitative intake data for women and children over two non-consecutive days, with a second recall conducted for over 50% of the sample. Data collection was conducted by trained local enumerators with at least a bachelor's degree. The baseline survey was paper-based for all components. Completed forms were manually reviewed, digitized, and subjected to rigorous cleaning and validation before analysis to ensure data reliability and accuracy. The collected data provides a critical reference point for evaluating the impact of interventions on agricultural practices, nutrition education, and household resilience.","author":[{"family":"Termote","given":"Celine"},{"family":"Aluso","given":"Lillian"},{"family":"Akingbemisilu","given":"Tosin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7910/dvn/yxgpcg","URL":"https://doi.org/10.7910/dvn/yxgpcg","source":"datacite"},{"id":"doi:10.5281/zenodo.18662099","type":"article-journal","title":"RumexDrone Image Dataset","abstract":"RumexDrone is an openly available RGB image dataset for the detection of Rumex in Swiss grasslands. The data were collected in Switzerland between 2020 and 2025 with a DJI Matrice 300 RTK carrying a Zenmuse P1 camera equipped with 35 mm or 50 mm lenses in nadir configuration, typically at about 12 m above ground level using single-shot autofocus. The repository combines four complementary data products designed for different reuse scenarios. AGS_Multiple_Fields contains five fully annotated field subsets totaling 11,155 image tiles of 1024 × 678 pixels. AGS_Multiple_Fields_Embeddings contains 1,513 annotated tiles selected from 50 flights using distances computed on PCA-reduced image embeddings to favor visual diversity. AGS_Multiple_Fields-Flights contains 179 full-resolution flight images of 8192 × 5460 pixels organized by flight date and location. AGS_Multi_Rumex contains randomly selected annotated images from 15 highlighting images at different vegetation stages and light conditions. Across the repository, images and annotations are linked by filename, and the data are intended for object detection, annotation-efficient sampling, benchmark design, domain generalization, and site-specific weed mapping in grassland and pasture systems. The dataset is released through Zenodo under the Creative Commons Attribution 4.0 International license. By packaging raw flight images together with multiple curated annotated subsets, RumexDrone supports direct reuse in common computer vision workflows and methodological comparisons across alternative data selection strategies. For more information about our research projects and publications, please visit: Agroscope Smart Farming","author":[{"family":"Nasser","given":"Hassan"},{"family":"Schrag","given":"Fabian"},{"family":"Sax","given":"Markus"},{"family":"Anken","given":"Thomas"},{"family":"Stoop","given":"Ralph"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18662099","URL":"https://doi.org/10.5281/zenodo.18662099","source":"datacite"},{"id":"doi:10.17632/9zgkwwv9j8.4","type":"article-journal","title":"Apple Disease Dataset","abstract":"This dataset contains images of Manalagi apple varieties from Indonesia. The data represent both healthy and diseased fruit. All data were collected from apple orchards owned by farmers. The dataset consists of four categories: one healthy fruit class and three disease classes: Anthracnose, Black Pox, and Powdery Mildew. Images were captured using a digital camera and a smartphone. To increase the quantity and variety of data, image augmentation was performed. The augmentation techniques used included rotation (45°, 90°, 180°, 225°, and 270°), flipping (vertical and horizontal), noise addition (Gaussian noise, speckle noise, and salt-and-pepper noise), and image transformations such as vertical and horizontal shifts, saturation changes, and brightness adjustments. This process aims to enrich the data variety so that the model can learn more robustly to various field conditions. Dataset Summary: - Total original data: 579 images - Total data after augmentation: 8,396 images - Image resolution: 1024 × 1024 pixels Data Distribution: - Healthy: 102 → 1,530 images - Anthracnose: 163 → 2,445 images - Black Pox: 166 → 2,201 images - Powdery Mildew: 148 → 2,220 images Dataset Description: - This dataset focuses on fruit diseases (fruit-based dataset), which is still rare compared to public datasets that generally focus on leaves. - The data is collected directly from orchards under natural conditions, reflecting real world variations such as lighting, background, and disease manifestations. - Augmentation techniques help improve the performance of deep learning models by expanding the data variety and reducing the risk of overfitting. - This dataset can be used as a benchmark for training, validating, and evaluating apple disease classification models. - This dataset also supports the development of automated disease detection systems, smart farming, and AI based applications in agriculture.","author":[{"family":"Febriantono","given":"Aldiki"},{"family":"Girsang","given":"Abba"},{"family":"Suharjito","given":"Suharjito"},{"family":"Anggreainy","given":"Maria"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/9zgkwwv9j8.4","URL":"https://doi.org/10.17632/9zgkwwv9j8.4","source":"datacite"},{"id":"doi:10.7910/dvn/nhxois","type":"article-journal","title":"Endline Survey Dataset on Agricultural Practices, Dietary Diversity, Socio-Economic Indicators, and Household Decision-Making in Vihiga County, Kenya (2020)","abstract":"This dataset originates from an endline survey conducted in Vihiga County, Kenya, between November and December 2020, as part of the project titled \"Improving access to and benefits from a wealth of diverse seeds to support on-farm biodiversity for healthy people in resilient landscapes.\" &lt;br&gt; The survey aimed to assess the outcomes of agricultural and nutritional interventions implemented in the study area, building on the baseline conducted in 2018. The dataset includes detailed information on demographic and socio-economic characteristics, household income, market access, wealth profiles, household food security, dietary changes, maternal nutritional knowledge, and attitudes and.&lt;br&gt; Additionally, it captures household agricultural practices, including the adoption of climate-smart technologies, social seed networks for traditional leafy vegetables and legumes, smart poultry farming practices and household decision-making among women. Quantitative 24-hour dietary recall data for women and children was also collected to assess dietary diversity and nutritional adequacy. The survey targeted households across intervention and comparison sublocations, capturing the perspectives of direct beneficiaries, indirect beneficiaries, and non-beneficiaries. &lt;br&gt; &lt;ul&gt; The principal investigators sought to address critical questions such as: &lt;li&gt;i) How have dietary diversity and nutritional practices evolved since the baseline survey? &lt;/li&gt; &lt;li&gt;ii) What impact have the agricultural and nutrition interventions had on household food security and resilience?&lt;/li&gt; &lt;li&gt;iii) How do household decision-making dynamics, particularly among women, influence agricultural and nutritional outcomes? &lt;/li&gt; &lt;li&gt;iv) What are the differences in outcomes between households in intervention and comparison areas? &lt;/li&gt; &lt;li&gt;v) This dataset offers a comprehensive view of the study area's agricultural, nutritional, and socio-economic landscape, providing valuable insights for evaluating the project's long-term impact.&lt;/li&gt; &lt;/ul&gt; &lt;br&gt; &lt;br&gt; Methodology: The endline data was collected through a survey conducted in Vihiga County, Kenya, from November to December 2020. &lt;br&gt; The study employed a quasi-randomized study design, sampling households from three categories: proposed intervention areas (198 households), comparison areas (198 households), and areas with prior interventions conducted before this baseline study (63 households). In total, 459 households were sampled. Including the previously intervened areas aimed to assess differences over time between these areas and the newly selected intervention areas. Households were eligible if they included at least one woman of reproductive age (15–49 years) and a child aged 6–23 months. In the intervention sublocations, 31 direct beneficiary and 167 indirect beneficiary households were purposively included from the newly intervention site to evaluate differences between participants directly involved in the agricultural and nutritional interventions and non-participants. &lt;br&gt; The survey utilized structured data collection tools, including a household questionnaire capturing demographic and socio-economic characteristics, household income, market access, food security, wealth profiles, agricultural practices, and maternal nutritional knowledge; a section on household decision-making, focusing on women's roles and dynamics in decision-making processes; a 24-hour dietary recall for women and children, collected over two non-consecutive days to assess dietary diversity and adequacy, with the second recall conducted for over 50% of the sample. &lt;br&gt; Data collection was conducted by trained enumerators using the KoBo Toolbox for digital data capture. &lt;br&gt; The dietary recall remained paper-based, with data digitized for analysis. Rigorous cleaning and validation processes were applied to ensure data accur","author":[{"family":"Termote","given":"Celine"},{"family":"Aluso","given":"Lillian"},{"family":"Akingbemisilu","given":"Tosin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7910/dvn/nhxois","URL":"https://doi.org/10.7910/dvn/nhxois","source":"datacite"},{"id":"doi:10.5281/zenodo.19654890","type":"article-journal","title":"From Mechanization to Autonomy: The Agrocycle as a Framework for Sustainable Robotic Farming","abstract":"This study examines the transition from conventional agricultural mechanization to autonomous robotic farming through the conceptual lens of the agrocycle, a holistic framework that integrates all agricultural operations across the full production year into a continuous, data-driven system. Rather than evaluating isolated field tasks, the agrocycle treats soil preparation, crop management, plant protection, pruning, and harvesting as interdependent components of a single adaptive operational loop. Within this framework, the performance of the PeK Automotive autonomous robotic platform (Slopehelper agrosystem) is empirically compared with a conventional tractor–implement system under comparable field conditions. Field experiments were conducted in temperate Central European vineyard and orchard systems, combining quantitative indicators—such as energy consumption, operational time, positional precision, soil compaction, and CO₂ emissions—with system-level indices including Operational Efficiency, Continuity, and System Resilience. Results demonstrate that the autonomous system achieved up to a 96% reduction in energy consumption per hectare, a 72% decrease in soil compaction, and the complete elimination of local CO₂ emissions. Despite slightly longer task durations in some operations, overall agrocycle feasibility and cost efficiency improved by more than threefold due to the absence of labor costs, optimized energy use, and uninterrupted autonomous operation. Beyond performance gains, the findings highlight a fundamental shift in agricultural systems logic. Autonomy, when embedded within the agrocycle framework, transforms farming from task-based mechanization toward a cyber-physical, self-optimizing production system aligned with the principles of Agriculture 5.0. The study concludes that the agrocycle represents both a practical and conceptual pathway toward resilient, subsidy-independent, and climate-resilient agricultural production, demonstrating that the move from mechanization to autonomy is not merely a technological substitution but a systemic transformation of modern agriculture. Keywords: Autonomous agriculture, Agrocycle, Agricultural robotics, Agriculture 5.0, Digital twin farming, Sustainable farming systems, Precision agriculture, Soil compaction, Energy efficiency, Robotic field operations REFERENCES Al-Amin, A. K. M. A., et al. (2024). Economics of strip cropping with autonomous machines. Agronomy Journal, 116(3), e21536. https://doi.org/10.1002/agj2.21536 Al-Amin, A. K. M. A., Lowenberg-DeBoer, J., et al. (2023). Economics of field size and shape for autonomous crop machines. Precision Agriculture, 24, 1798–1821. https://doi.org/10.1007/s11119-023-10016-w Bai, Z., Caspari, T., Gonzalez, M. R., Batjes, N. H., Mäder, P., Bünemann, E. K., de Goede, R., Brussaard, L., Xu, M., Ferreira, C. S. S., Reintam, E., Fan, H., Mihelič, R., Glavan, M., & Tóth, Z. (2018). Soil information is essential to addressing the sustainable development goals. Geoderma Regional, 13, e00175. https://doi.org/10.1016/j.geodrs.2018.e00175 Bongiovanni, R., & Lowenberg-DeBoer, J. (2004). Precision agriculture and sustainability. Precision Agriculture, 5(4), 359–387. https://doi.org/10.1023/B:PRAG.0000040806.39604.aa Calleja-Huerta, A., et al. (2024). Evolution of topsoil structure after compaction with a lightweight autonomous field robot. Soil Science Society of America Journal, 88(5), e20719. https://doi.org/10.1002/saj2.20719 European Commission. (2020). A Farm to Fork Strategy for a fair, healthy and environmentally-friendly food system. Brussels: European Commission. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:52020DC0381 ISO. (2018). ISO 18497:2018 Agricultural machinery and tractors—Safety of highly automated agricultural machines—Principles for design. Geneva: International Organization for Standardization. (See also ISO 18497-1:2024 update.) Lagnelöv, O., et al. (2023). Impact of lowered vehicle weight of electric aut","author":[{"family":"Kostkin","given":"Mikhail"},{"family":"Vavpotič","given":"Žiga"},{"family":"Agalar","given":"MF"},{"family":"Germšek","given":"Blaž"},{"family":"Öz","given":"Sabri"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19654890","URL":"https://doi.org/10.5281/zenodo.19654890","source":"datacite"},{"id":"doi:10.5281/zenodo.19654891","type":"article-journal","title":"From Mechanization to Autonomy: The Agrocycle as a Framework for Sustainable Robotic Farming","abstract":"This study examines the transition from conventional agricultural mechanization to autonomous robotic farming through the conceptual lens of the agrocycle, a holistic framework that integrates all agricultural operations across the full production year into a continuous, data-driven system. Rather than evaluating isolated field tasks, the agrocycle treats soil preparation, crop management, plant protection, pruning, and harvesting as interdependent components of a single adaptive operational loop. Within this framework, the performance of the PeK Automotive autonomous robotic platform (Slopehelper agrosystem) is empirically compared with a conventional tractor–implement system under comparable field conditions. Field experiments were conducted in temperate Central European vineyard and orchard systems, combining quantitative indicators—such as energy consumption, operational time, positional precision, soil compaction, and CO₂ emissions—with system-level indices including Operational Efficiency, Continuity, and System Resilience. Results demonstrate that the autonomous system achieved up to a 96% reduction in energy consumption per hectare, a 72% decrease in soil compaction, and the complete elimination of local CO₂ emissions. Despite slightly longer task durations in some operations, overall agrocycle feasibility and cost efficiency improved by more than threefold due to the absence of labor costs, optimized energy use, and uninterrupted autonomous operation. Beyond performance gains, the findings highlight a fundamental shift in agricultural systems logic. Autonomy, when embedded within the agrocycle framework, transforms farming from task-based mechanization toward a cyber-physical, self-optimizing production system aligned with the principles of Agriculture 5.0. The study concludes that the agrocycle represents both a practical and conceptual pathway toward resilient, subsidy-independent, and climate-resilient agricultural production, demonstrating that the move from mechanization to autonomy is not merely a technological substitution but a systemic transformation of modern agriculture. Keywords: Autonomous agriculture, Agrocycle, Agricultural robotics, Agriculture 5.0, Digital twin farming, Sustainable farming systems, Precision agriculture, Soil compaction, Energy efficiency, Robotic field operations REFERENCES Al-Amin, A. K. M. A., et al. (2024). Economics of strip cropping with autonomous machines. Agronomy Journal, 116(3), e21536. https://doi.org/10.1002/agj2.21536 Al-Amin, A. K. M. A., Lowenberg-DeBoer, J., et al. (2023). Economics of field size and shape for autonomous crop machines. Precision Agriculture, 24, 1798–1821. https://doi.org/10.1007/s11119-023-10016-w Bai, Z., Caspari, T., Gonzalez, M. R., Batjes, N. H., Mäder, P., Bünemann, E. K., de Goede, R., Brussaard, L., Xu, M., Ferreira, C. S. S., Reintam, E., Fan, H., Mihelič, R., Glavan, M., & Tóth, Z. (2018). Soil information is essential to addressing the sustainable development goals. Geoderma Regional, 13, e00175. https://doi.org/10.1016/j.geodrs.2018.e00175 Bongiovanni, R., & Lowenberg-DeBoer, J. (2004). Precision agriculture and sustainability. Precision Agriculture, 5(4), 359–387. https://doi.org/10.1023/B:PRAG.0000040806.39604.aa Calleja-Huerta, A., et al. (2024). Evolution of topsoil structure after compaction with a lightweight autonomous field robot. Soil Science Society of America Journal, 88(5), e20719. https://doi.org/10.1002/saj2.20719 European Commission. (2020). A Farm to Fork Strategy for a fair, healthy and environmentally-friendly food system. Brussels: European Commission. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:52020DC0381 ISO. (2018). ISO 18497:2018 Agricultural machinery and tractors—Safety of highly automated agricultural machines—Principles for design. Geneva: International Organization for Standardization. (See also ISO 18497-1:2024 update.) Lagnelöv, O., et al. (2023). Impact of lowered vehicle weight of electric aut","author":[{"family":"Kostkin","given":"Mikhail"},{"family":"Vavpotič","given":"Žiga"},{"family":"Agalar","given":"MF"},{"family":"Germšek","given":"Blaž"},{"family":"Öz","given":"Sabri"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19654891","URL":"https://doi.org/10.5281/zenodo.19654891","source":"datacite"},{"id":"doi:10.5281/zenodo.19595730","type":"article-journal","title":"LAPORAN STUDI KELAYAKAN BISNIS TEKNOLOGI INFORMASI SISTEM MONITORING PINTAR BERBASIS IoT & WEB DASHBOARD UNTUK OPTIMALISASI BUDIDAYA JAMUR SHIITAKE (Lentinula edodes)","abstract":"Laporan ini menyajikan studi kelayakan bisnis komprehensif untuk sistem monitoring mikroklimat pintar berbasis Internet of Things (IoT) guna mengoptimalisasi budidaya jamur Shiitake. Budidaya jamur Shiitake di Indonesia menghadapi kendala serius berupa ketergantungan pada kondisi lingkungan yang sangat spesifik, dengan kebutuhan suhu antara 22-30°C dan kelembapan 70-90%. Kegagalan menjaga parameter ini secara konvensional seringkali menyebabkan kontaminasi patogen hingga 30%. Sistem yang diusulkan mengadopsi arsitektur three-layer IoT menggunakan mikrokontroler ESP32, berbagai sensor lingkungan presisi, dan protokol komunikasi MQTT untuk transmisi data real-time ke web dashboard berbasis React.js. Berdasarkan analisis pasar, terdapat defisit pasokan nasional sebesar 5.200 ton per tahun, yang membuka peluang besar bagi produsen lokal yang mampu menjamin kualitas produk melalui teknologi. Evaluasi finansial selama horizon lima tahun menunjukkan hasil yang sangat positif: Investasi Awal (CAPEX): Rp 12.450.000. Return on Investment (ROI): 87,1% per tahun. Net Present Value (NPV): Rp 70.842.000 (pada discount rate 12%). Payback Period: 6,4 bulan. Studi ini menyimpulkan bahwa implementasi sistem monitoring pintar ini sangat layak secara teknis maupun finansial untuk meningkatkan produktivitas dan kesejahteraan petani jamur di Indonesia.","author":[{"family":"Duryat","given":"Nandang"},{"family":"Ropiq","given":"Ainur"},{"family":"Faiz Caniggia","given":"Syeddinul"},{"family":"L Junior","given":"Brian"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19595730","URL":"https://doi.org/10.5281/zenodo.19595730","source":"datacite"},{"id":"doi:10.5281/zenodo.19595731","type":"article-journal","title":"LAPORAN STUDI KELAYAKAN BISNIS TEKNOLOGI INFORMASI SISTEM MONITORING PINTAR BERBASIS IoT & WEB DASHBOARD UNTUK OPTIMALISASI BUDIDAYA JAMUR SHIITAKE (Lentinula edodes)","abstract":"Laporan ini menyajikan studi kelayakan bisnis komprehensif untuk sistem monitoring mikroklimat pintar berbasis Internet of Things (IoT) guna mengoptimalisasi budidaya jamur Shiitake. Budidaya jamur Shiitake di Indonesia menghadapi kendala serius berupa ketergantungan pada kondisi lingkungan yang sangat spesifik, dengan kebutuhan suhu antara 22-30°C dan kelembapan 70-90%. Kegagalan menjaga parameter ini secara konvensional seringkali menyebabkan kontaminasi patogen hingga 30%. Sistem yang diusulkan mengadopsi arsitektur three-layer IoT menggunakan mikrokontroler ESP32, berbagai sensor lingkungan presisi, dan protokol komunikasi MQTT untuk transmisi data real-time ke web dashboard berbasis React.js. Berdasarkan analisis pasar, terdapat defisit pasokan nasional sebesar 5.200 ton per tahun, yang membuka peluang besar bagi produsen lokal yang mampu menjamin kualitas produk melalui teknologi. Evaluasi finansial selama horizon lima tahun menunjukkan hasil yang sangat positif: Investasi Awal (CAPEX): Rp 12.450.000. Return on Investment (ROI): 87,1% per tahun. Net Present Value (NPV): Rp 70.842.000 (pada discount rate 12%). Payback Period: 6,4 bulan. Studi ini menyimpulkan bahwa implementasi sistem monitoring pintar ini sangat layak secara teknis maupun finansial untuk meningkatkan produktivitas dan kesejahteraan petani jamur di Indonesia.","author":[{"family":"Duryat","given":"Nandang"},{"family":"Ropiq","given":"Ainur"},{"family":"Faiz Caniggia","given":"Syeddinul"},{"family":"L Junior","given":"Brian"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19595731","URL":"https://doi.org/10.5281/zenodo.19595731","source":"datacite"},{"id":"doi:10.5281/zenodo.19594563","type":"article-journal","title":"Smart Crop and Nutrient Advisory System using Machine Learning","abstract":"Precision agriculture demands intelligent systems that integrate soil, environmental, and regional parameters for optimized crop planning. This research proposes a hybrid AI-based Smart Crop and Nutrient Advisory system combining multiple machine learning models including Random Forest, XGBoost, CatBoost, Support Vector Machine, and Logistic Regression along with generative AI for region-specific recommendations. It offers crop recommendations and nutrient advice tailored to specific regions. By considering soil factors like nitrogen, phosphorus, potassium, pH, temperature, rainfall, and seasonal conditions, the system improves prediction reliability. A synthetic multi-regional dataset was used for training and stratified validation. Experimental results demonstrate superior ensemble model accuracy in multi-class crop prediction. A generative AI module provides contextual nutrient guidance and expert advisory responses through an interactive web interface, supporting real-time decision-making and sustainable farming practices. The system also incorporates a multilingual quick summary and voice assistance module to improve accessibility for farmers.","author":[{"family":"Sivadharshini","given":"Mrs"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19594563","URL":"https://doi.org/10.5281/zenodo.19594563","source":"datacite"},{"id":"doi:10.5281/zenodo.19594564","type":"article-journal","title":"Smart Crop and Nutrient Advisory System using Machine Learning","abstract":"Precision agriculture demands intelligent systems that integrate soil, environmental, and regional parameters for optimized crop planning. This research proposes a hybrid AI-based Smart Crop and Nutrient Advisory system combining multiple machine learning models including Random Forest, XGBoost, CatBoost, Support Vector Machine, and Logistic Regression along with generative AI for region-specific recommendations. It offers crop recommendations and nutrient advice tailored to specific regions. By considering soil factors like nitrogen, phosphorus, potassium, pH, temperature, rainfall, and seasonal conditions, the system improves prediction reliability. A synthetic multi-regional dataset was used for training and stratified validation. Experimental results demonstrate superior ensemble model accuracy in multi-class crop prediction. A generative AI module provides contextual nutrient guidance and expert advisory responses through an interactive web interface, supporting real-time decision-making and sustainable farming practices. The system also incorporates a multilingual quick summary and voice assistance module to improve accessibility for farmers.","author":[{"family":"Sivadharshini","given":"Mrs"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19594564","URL":"https://doi.org/10.5281/zenodo.19594564","source":"datacite"},{"id":"doi:10.48550/arxiv.2506.14170","type":"manuscript","title":"Progressive Multimodal Interaction Network for Reliable Quantification of Fish Feeding Intensity in Aquaculture","abstract":"Accurate quantification of fish feeding intensity is crucial for precision feeding in aquaculture, as it directly affects feed utilization and farming efficiency. Although multimodal fusion has proven to be an effective solution, existing methods often overlook the inconsistencies in responses and decision conflicts between different modalities, thus limiting the reliability of the quantification results. To address this issue, this paper proposes a Progressive Multimodal Interaction Network (PMIN) that integrates image, audio, and water-wave data for fish feeding intensity quantification. Specifically, a unified feature extraction framework is first constructed to map inputs from different modalities into a structurally consistent feature space, thereby reducing representational discrepancies across modalities. Then, an auxiliary-modality reinforcement primary-modality mechanism is designed to facilitate the fusion of cross-modal information, which is achieved through channel aware recalibration and dual-stage attention interaction. Furthermore, a decision fusion strategy based on adaptive evidence reasoning is introduced to jointly model the confidence, reliability, and conflicts of modality-specific outputs, so as to improve the stability and robustness of the final judgment. Experiments are conducted on a multimodal fish feeding intensity dataset containing 7089 samples. The results show that PMIN has an accuracy of 96.76%, while maintaining relatively low parameter count and computational cost, and its overall performance outperforms both homogeneous and heterogeneous comparison models. Ablation studies, comparative experiments, and real-world application results further validate the effectiveness and superiority of the proposed method. It can provide reliable support for automated feeding monitoring and precise feeding decisions in smart aquaculture.","author":[{"family":"Zhang","given":"Shulong"},{"family":"Yao","given":"Mingyuan"},{"family":"Zhao","given":"Jiayin"},{"family":"Li","given":"Daoliang"},{"family":"Chen","given":"Yingyi"},{"family":"Wang","given":"Haihua"}],"issued":{"date-parts":[[2025]]},"DOI":"10.48550/arxiv.2506.14170","URL":"https://doi.org/10.48550/arxiv.2506.14170","source":"datacite"},{"id":"doi:10.5281/zenodo.19534419","type":"article-journal","title":"Smart Farming Advisory System using Artificial Intelligence","abstract":"This paper presents an AI-driven Smart Farming Advisory System designed to assist farmers in making data-driven agricultural decisions. The system integrates machine learning algorithms, including Random Forest, Decision Tree, and K-Nearest Neighbors, to recommend suitable crops based on soil nutrients (NPK), pH, rainfall, and temperature. The proposed system also includes an alternative crop suggestion module using Euclidean distance, enabling farmers to identify viable substitute crops under changing environmental conditions. Additionally, a profit estimation module utilizes real-time market data from Agmarknet to predict expected earnings. To enhance usability, an AI-powered chatbot based on the Gemini API provides real-time advisory support, including crop care, pest management, and fertilizer recommendations. The system achieved an accuracy of 87% using the Random Forest model, demonstrating strong performance. This work contributes to sustainable agriculture by combining predictive analytics, financial insights, and conversational AI into a unified, scalable solution.","author":[{"family":"Flinto","given":"Kavin"},{"family":"Deva","given":"Sachin"},{"family":"Balaji","given":"Suresh"},{"family":"Elakiya","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19534419","URL":"https://doi.org/10.5281/zenodo.19534419","source":"datacite"},{"id":"doi:10.5281/zenodo.19534420","type":"article-journal","title":"Smart Farming Advisory System using Artificial Intelligence","abstract":"This paper presents an AI-driven Smart Farming Advisory System designed to assist farmers in making data-driven agricultural decisions. The system integrates machine learning algorithms, including Random Forest, Decision Tree, and K-Nearest Neighbors, to recommend suitable crops based on soil nutrients (NPK), pH, rainfall, and temperature. The proposed system also includes an alternative crop suggestion module using Euclidean distance, enabling farmers to identify viable substitute crops under changing environmental conditions. Additionally, a profit estimation module utilizes real-time market data from Agmarknet to predict expected earnings. To enhance usability, an AI-powered chatbot based on the Gemini API provides real-time advisory support, including crop care, pest management, and fertilizer recommendations. The system achieved an accuracy of 87% using the Random Forest model, demonstrating strong performance. This work contributes to sustainable agriculture by combining predictive analytics, financial insights, and conversational AI into a unified, scalable solution.","author":[{"family":"Flinto","given":"Kavin"},{"family":"Deva","given":"Sachin"},{"family":"Balaji","given":"Suresh"},{"family":"Elakiya","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19534420","URL":"https://doi.org/10.5281/zenodo.19534420","source":"datacite"},{"id":"doi:10.5281/zenodo.19489364","type":"article-journal","title":"IoT-Zoo Network Traffic 8 hour capture","abstract":"This dataset consists of 34269178 network packet samples extracted from the IoT-Zoo testbed. It represents a 28800-second execution of a heterogeneous IoT environment, featuring 43 distinct device profiles spanning Urban Observatory, Industrial, e-Health, and Smart Farming domains. Technical Specifications The dataset is the result of a synchronized fusion between two network analysis engines (Scapy and Tshark), providing a high-dimensional view of each packet. Unlike flow-based datasets, this is a packet-level collection, where each row represents an individual network frame. Dataset Characteristics Total Samples: 34269178 packets. Total Features: 17 columns. Trace Duration: 28800 seconds. Device Heterogeneity: Covers telemetry from multiple domains with preserved temporal dynamics. Application Semantics: Includes structured payloads (JSON/XML) replayed from real-world datasets. Column Definitions (Schema) pkt_index: Unique sequential identifier for each packet. ip_ttl: time to live value for the ip header, decreases by 1 at each router. tcp_seq: TCP sequence number, used to identify the sequence of tcp segments. tcp_flags_str: Human-readable TCP flag mnemonics (e.g., PA, S, A) extracted via Scapy. frame.time_epoch: High-precision Unix timestamp of arrival. frame.len: The total length of the Ethernet frame in bytes. ip_src / ip_dst: Source and Destination IPv4 addresses. ip_proto: Layer 3 protocol identifier (e.g., 6 for TCP). tcp.src_port / dst_port: Layer 4 source and destination ports (e.g., 1883 for MQTT). tcp_flags_hex: Raw TCP flags in hexadecimal format (0x00000000), optimized for numerical Machine Learning input. _ws.col.protocol: Application layer protocol identified via Tshark's deep packet inspection (e.g., MQTT, NTP, DNS, RTSP). mqtt.topic: Represents the publish/subscribe channel for MQTT messages, representing the origin topic and device. Only populated for MQTT packets; empty otherwise mqtt.msgtype: MQTT message type. mqtt.qos: MQTT Quality of Service level goes from 0 to 2. mqtt.len: Length of MQTT payload in bytes. Intended Use This CSV is ready for downstream Machine Learning tasks such as: Anomaly Detection: Using frame_len and time_epoch (IAT) to identify volumetric or timing-based attacks. Protocol Classification: Leveraging app_protocol and tcp_flags_hex for identifying IoT-specific behaviors. Security Research: Serving as a baseline for legitimate IoT traffic patterns in heterogeneous environments.","author":[{"family":"Bitzki","given":"Leonardo"},{"family":"Kreutz","given":"Diego"},{"family":"Nogueira","given":"Angelo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19489364","URL":"https://doi.org/10.5281/zenodo.19489364","source":"datacite"},{"id":"doi:10.5281/zenodo.19489363","type":"article-journal","title":"IoT-Zoo Network Traffic 8 hour capture","abstract":"This dataset consists of 34269178 network packet samples extracted from the IoT-Zoo testbed. It represents a 28800-second execution of a heterogeneous IoT environment, featuring 43 distinct device profiles spanning Urban Observatory, Industrial, e-Health, and Smart Farming domains. Technical Specifications The dataset is the result of a synchronized fusion between two network analysis engines (Scapy and Tshark), providing a high-dimensional view of each packet. Unlike flow-based datasets, this is a packet-level collection, where each row represents an individual network frame. Dataset Characteristics Total Samples: 34269178 packets. Total Features: 17 columns. Trace Duration: 28800 seconds. Device Heterogeneity: Covers telemetry from multiple domains with preserved temporal dynamics. Application Semantics: Includes structured payloads (JSON/XML) replayed from real-world datasets. Column Definitions (Schema) pkt_index: Unique sequential identifier for each packet. ip_ttl: time to live value for the ip header, decreases by 1 at each router. tcp_seq: TCP sequence number, used to identify the sequence of tcp segments. tcp_flags_str: Human-readable TCP flag mnemonics (e.g., PA, S, A) extracted via Scapy. frame.time_epoch: High-precision Unix timestamp of arrival. frame.len: The total length of the Ethernet frame in bytes. ip_src / ip_dst: Source and Destination IPv4 addresses. ip_proto: Layer 3 protocol identifier (e.g., 6 for TCP). tcp.src_port / dst_port: Layer 4 source and destination ports (e.g., 1883 for MQTT). tcp_flags_hex: Raw TCP flags in hexadecimal format (0x00000000), optimized for numerical Machine Learning input. _ws.col.protocol: Application layer protocol identified via Tshark's deep packet inspection (e.g., MQTT, NTP, DNS, RTSP). mqtt.topic: Represents the publish/subscribe channel for MQTT messages, representing the origin topic and device. Only populated for MQTT packets; empty otherwise mqtt.msgtype: MQTT message type. mqtt.qos: MQTT Quality of Service level goes from 0 to 2. mqtt.len: Length of MQTT payload in bytes. Intended Use This CSV is ready for downstream Machine Learning tasks such as: Anomaly Detection: Using frame_len and time_epoch (IAT) to identify volumetric or timing-based attacks. Protocol Classification: Leveraging app_protocol and tcp_flags_hex for identifying IoT-specific behaviors. Security Research: Serving as a baseline for legitimate IoT traffic patterns in heterogeneous environments.","author":[{"family":"Bitzki","given":"Leonardo"},{"family":"Kreutz","given":"Diego"},{"family":"Nogueira","given":"Angelo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19489363","URL":"https://doi.org/10.5281/zenodo.19489363","source":"datacite"},{"id":"doi:10.5281/zenodo.19468695","type":"article-journal","title":"AI Based Plant Disease Recommendation and Solution","abstract":"A productivity and food security, creating a need for intelligent and accessible diagnostic tools. This paper presents a web- based smart agriculture system that integrates deep learning–based plant disease recognition with an AI-driven advisory framework. A Convolutional Neural Network (CNN) is trained on a multi-classleaf image dataset to automatically classify plant diseases across 38 categories. User-submitted leaf images are processed to generate classifications and confidence scores, allowing the user to rapidly identify whether a leaf has a certain disease without assistance from an expert. The classification output can be generated through the Streamlit interface, which allows a user to upload an image or capture one with their camera to provide real-time feedback. In addition to generating classifications, the system will use AI to provide an explanation of the classification in a structured format that states the symptoms, causes, and recommended treatments for diseases. Unlike conventional static recommendation systems, the proposed approach leverages a large language model to provide adaptive and context-aware guidance.To enhance further enables users to seek general farming guidance within the same platform.system offers scalable and user-centric solution for intelligent crop health management.","author":[{"family":"Vinde","given":"Piyush"},{"family":"Chavan","given":"Aneesh"},{"family":"Gadai","given":"Rohit"},{"family":"Yadav","given":"Aarin"},{"family":"Sall","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19468695","URL":"https://doi.org/10.5281/zenodo.19468695","source":"datacite"},{"id":"doi:10.5281/zenodo.19468696","type":"article-journal","title":"AI Based Plant Disease Recommendation and Solution","abstract":"A productivity and food security, creating a need for intelligent and accessible diagnostic tools. This paper presents a web- based smart agriculture system that integrates deep learning–based plant disease recognition with an AI-driven advisory framework. A Convolutional Neural Network (CNN) is trained on a multi-classleaf image dataset to automatically classify plant diseases across 38 categories. User-submitted leaf images are processed to generate classifications and confidence scores, allowing the user to rapidly identify whether a leaf has a certain disease without assistance from an expert. The classification output can be generated through the Streamlit interface, which allows a user to upload an image or capture one with their camera to provide real-time feedback. In addition to generating classifications, the system will use AI to provide an explanation of the classification in a structured format that states the symptoms, causes, and recommended treatments for diseases. Unlike conventional static recommendation systems, the proposed approach leverages a large language model to provide adaptive and context-aware guidance.To enhance further enables users to seek general farming guidance within the same platform.system offers scalable and user-centric solution for intelligent crop health management.","author":[{"family":"Vinde","given":"Piyush"},{"family":"Chavan","given":"Aneesh"},{"family":"Gadai","given":"Rohit"},{"family":"Yadav","given":"Aarin"},{"family":"Sall","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19468696","URL":"https://doi.org/10.5281/zenodo.19468696","source":"datacite"},{"id":"doi:10.5281/zenodo.19353231","type":"article-journal","title":"AI-Driven Crop Quality Assessment using Deep Learning and Image Analysis with Integrated Smart Farming Support System","abstract":"Assessing Crop Quality plays an important role in the area of Agriculture as it impacts on the pricing and storage and acceptance in Market. Conventional quality inspection methods highly rely on human expertise, which may be time-consuming, subjective, and inconsistent. To overcome these, Artificial intelligence based Crop Quality Verification system by image analysis is introduced in this project. The proposed system consists of image processing techniques and deep learning models, namely Convolutional Neural Networks (CNNs) to analyze crop images and classify them as either good or poor quality crop images. The results are represented in a graphical manner showing good quality crops with a green colour and with the poor quality of crops with a red colour along with the distribution of quality in a pie-cut chart. In addition to quality classification the system provides weather updates, market prices, multiple language support and an interactive chat feature to help farmers. A fastapi-powered backend is connecting already trained model of AI with a user friendly web interface created with the help of such technologies as html, css, and java script. Transfer Learning using Pre-trained CNN model is used for extracting important features from the crop images in an efficient way in order to increase the classification performance. In total, the proposed solution addresses the issues of accuracy limitation and reduces the manual effort and can be seen as a scalable and cost-effective method for automated crop quality assessment to contribute to smart and efficient agricultural practices.","author":[{"family":"Sindhu","given":"Chavali"},{"family":"Benita","given":"D"},{"family":"Anusuya","given":"G"},{"family":"Mohandoss","given":"Dr"},{"family":"Akila","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19353231","URL":"https://doi.org/10.5281/zenodo.19353231","source":"datacite"},{"id":"doi:10.5281/zenodo.19353230","type":"article-journal","title":"AI-Driven Crop Quality Assessment using Deep Learning and Image Analysis with Integrated Smart Farming Support System","abstract":"Assessing Crop Quality plays an important role in the area of Agriculture as it impacts on the pricing and storage and acceptance in Market. Conventional quality inspection methods highly rely on human expertise, which may be time-consuming, subjective, and inconsistent. To overcome these, Artificial intelligence based Crop Quality Verification system by image analysis is introduced in this project. The proposed system consists of image processing techniques and deep learning models, namely Convolutional Neural Networks (CNNs) to analyze crop images and classify them as either good or poor quality crop images. The results are represented in a graphical manner showing good quality crops with a green colour and with the poor quality of crops with a red colour along with the distribution of quality in a pie-cut chart. In addition to quality classification the system provides weather updates, market prices, multiple language support and an interactive chat feature to help farmers. A fastapi-powered backend is connecting already trained model of AI with a user friendly web interface created with the help of such technologies as html, css, and java script. Transfer Learning using Pre-trained CNN model is used for extracting important features from the crop images in an efficient way in order to increase the classification performance. In total, the proposed solution addresses the issues of accuracy limitation and reduces the manual effort and can be seen as a scalable and cost-effective method for automated crop quality assessment to contribute to smart and efficient agricultural practices.","author":[{"family":"Sindhu","given":"Chavali"},{"family":"Benita","given":"D"},{"family":"Anusuya","given":"G"},{"family":"Mohandoss","given":"Dr"},{"family":"Akila","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19353230","URL":"https://doi.org/10.5281/zenodo.19353230","source":"datacite"},{"id":"doi:10.5281/zenodo.19202810","type":"article-journal","title":"The SOILL Learning Journey","abstract":"The SOILL Learning Journey poster was showcased at the 3rd European Carbon Farming Summit in Padua (17–19 March 2026). It presents the SOILL Learning Journey developed by Climate KIC and LGI Sustainable Innovation to support Soil Health Living Labs in moving from ambition to real impact. While establishing a Living Lab is not the main challenge, making it effective requires structure, tools, and a clear pathway to scale. The SOILL approach addresses this by guiding labs across key dimensions, from governance and finance to soil monitoring and real-world interventions, enabling the transition from local experimentation to Europe-wide impact. Positioned within Europe's leading forum for regenerative agriculture and carbon farming, the work contributes to ongoing efforts to scale collaborative climate action in the agricultural sector.","author":[{"family":"Visser","given":"Saskia"},{"family":"Drijvers","given":"Bram"},{"family":"Gallagher","given":"Karen"},{"family":"Finch","given":"Tessa"},{"family":"Burnfield","given":"Cecilia"},{"family":"Loubiere","given":"Agnès"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19202810","URL":"https://doi.org/10.5281/zenodo.19202810","source":"datacite"},{"id":"doi:10.5281/zenodo.19202811","type":"article-journal","title":"The SOILL Learning Journey","abstract":"The SOILL Learning Journey poster was showcased at the 3rd European Carbon Farming Summit in Padua (17–19 March 2026). It presents the SOILL Learning Journey developed by Climate KIC and LGI Sustainable Innovation to support Soil Health Living Labs in moving from ambition to real impact. While establishing a Living Lab is not the main challenge, making it effective requires structure, tools, and a clear pathway to scale. The SOILL approach addresses this by guiding labs across key dimensions, from governance and finance to soil monitoring and real-world interventions, enabling the transition from local experimentation to Europe-wide impact. Positioned within Europe's leading forum for regenerative agriculture and carbon farming, the work contributes to ongoing efforts to scale collaborative climate action in the agricultural sector.","author":[{"family":"Visser","given":"Saskia"},{"family":"Drijvers","given":"Bram"},{"family":"Gallagher","given":"Karen"},{"family":"Finch","given":"Tessa"},{"family":"Burnfield","given":"Cecilia"},{"family":"Loubiere","given":"Agnès"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19202811","URL":"https://doi.org/10.5281/zenodo.19202811","source":"datacite"},{"id":"doi:10.17632/tccrdw75t8.2","type":"article-journal","title":"RGB Image Dataset for Cabbage Maturity Classification at 100 and 135 Days After Transplanting (DAT) for Machine Learning Applications","abstract":"This dataset was developed to support research on automated crop maturity detection using computer vision and deep learning techniques. The hypothesis is that RGB image features of cabbage heads captured under field conditions contain sufficient information to distinguish between mature and premature harvesting stages. By training deep learning models, it is possible to predict the optimal harvesting stage, supporting precision agriculture and reducing subjectivity in decisions. The dataset consists of RGB images of cabbage plants collected from an experimental agricultural field. Images were captured at two growth stages defined by days after transplanting (DAT): 100 DAT (premature) and 135 DAT (mature). A total of 616 images were collected (320 mature cabbage samples (Class 1) and 296 premature samples (Class 2)). All images were captured using a 16-megapixel RGB camera (Canon PowerShot SX170) under natural field lighting conditions. The original resolution was 1632 × 1553 pixels, preserving key visual characteristics such as leaf arrangement, head compactness, and size. To ensure compatibility with deep learning architectures and reduce computational requirements, all images were resized to 224 × 224 pixels. This standardized input size enables efficient training of convolutional neural networks used in agricultural image analysis. Although resizing improves computational efficiency and standardizes model input, it may slightly reduce the ability to capture very fine details such as subtle leaf textures. However, the resized images retain the main morphological features needed for distinguishing maturity stages. The dataset shows clear visual differences between classes. Mature cabbages exhibit larger, denser, and more compact heads, while premature cabbages show looser leaf structures and less head formation. These patterns provide useful features for machine learning algorithms. This dataset supports applications including training and evaluation of deep learning models for crop maturity detection, development of computer vision systems for automated harvesting, research in precision agriculture and smart farming, and benchmarking algorithms for agricultural image classification. Each image is labeled according to its maturity stage: Class 1 (mature, 135 DAT) and Class 2 (premature, 100 DAT), enabling easy integration with machine learning workflows. Overall, this dataset provides a valuable resource for advancing research in AI-based crop maturity prediction and intelligent agricultural harvesting systems. The authors gratefully acknowledge financial support from ICAR–CIAE under the CRP-FMPF project.","author":[{"family":"Kumar","given":"Manoj"},{"family":"Rawat","given":"S"},{"family":"Goutam","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/tccrdw75t8.2","URL":"https://doi.org/10.17632/tccrdw75t8.2","source":"datacite"},{"id":"doi:10.17632/tccrdw75t8","type":"article-journal","title":"RGB Image Dataset for Cabbage Maturity Classification at 100 and 135 Days After Transplanting (DAT) for Machine Learning Applications","abstract":"This dataset was developed to support research on automated crop maturity detection using computer vision and deep learning techniques. The hypothesis is that RGB image features of cabbage heads captured under field conditions contain sufficient information to distinguish between mature and premature harvesting stages. By training deep learning models, it is possible to predict the optimal harvesting stage, supporting precision agriculture and reducing subjectivity in decisions. The dataset consists of RGB images of cabbage plants collected from an experimental agricultural field. Images were captured at two growth stages defined by days after transplanting (DAT): 100 DAT (premature) and 135 DAT (mature). A total of 616 images were collected (320 mature cabbage samples (Class 1) and 296 premature samples (Class 2)). All images were captured using a 16-megapixel RGB camera (Canon PowerShot SX170) under natural field lighting conditions. The original resolution was 1632 × 1553 pixels, preserving key visual characteristics such as leaf arrangement, head compactness, and size. To ensure compatibility with deep learning architectures and reduce computational requirements, all images were resized to 224 × 224 pixels. This standardized input size enables efficient training of convolutional neural networks used in agricultural image analysis. Although resizing improves computational efficiency and standardizes model input, it may slightly reduce the ability to capture very fine details such as subtle leaf textures. However, the resized images retain the main morphological features needed for distinguishing maturity stages. The dataset shows clear visual differences between classes. Mature cabbages exhibit larger, denser, and more compact heads, while premature cabbages show looser leaf structures and less head formation. These patterns provide useful features for machine learning algorithms. This dataset supports applications including training and evaluation of deep learning models for crop maturity detection, development of computer vision systems for automated harvesting, research in precision agriculture and smart farming, and benchmarking algorithms for agricultural image classification. Each image is labeled according to its maturity stage: Class 1 (mature, 135 DAT) and Class 2 (premature, 100 DAT), enabling easy integration with machine learning workflows. Overall, this dataset provides a valuable resource for advancing research in AI-based crop maturity prediction and intelligent agricultural harvesting systems. The authors gratefully acknowledge financial support from ICAR–CIAE under the CRP-FMPF project.","author":[{"family":"Kumar","given":"Manoj"},{"family":"Rawat","given":"S"},{"family":"Goutam","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/tccrdw75t8","URL":"https://doi.org/10.17632/tccrdw75t8","source":"datacite"},{"id":"doi:10.17632/tccrdw75t8.1","type":"article-journal","title":"RGB Image Dataset for Cabbage Maturity Classification at 100 and 135 Days After Transplanting (DAT) for Machine Learning Applications","abstract":"This dataset was developed to support research on automated crop maturity detection using computer vision and deep learning techniques. The hypothesis is that RGB image features of cabbage heads captured under field conditions contain sufficient information to distinguish between mature and premature harvesting stages. By training deep learning models, it is possible to predict the optimal harvesting stage, supporting precision agriculture and reducing subjectivity in decisions. The dataset consists of RGB images of cabbage plants collected from an experimental agricultural field. Images were captured at two growth stages defined by days after transplanting (DAT): 100 DAT (premature) and 135 DAT (mature). A total of 616 images were collected (320 mature cabbage samples (Class 1) and 296 premature samples (Class 2)). All images were captured using a 16-megapixel RGB camera (Canon PowerShot SX170) under natural field lighting conditions. The original resolution was 1632 × 1553 pixels, preserving key visual characteristics such as leaf arrangement, head compactness, and size. To ensure compatibility with deep learning architectures and reduce computational requirements, all images were resized to 224 × 224 pixels. This standardized input size enables efficient training of convolutional neural networks used in agricultural image analysis. Although resizing improves computational efficiency and standardizes model input, it may slightly reduce the ability to capture very fine details such as subtle leaf textures. However, the resized images retain the main morphological features needed for distinguishing maturity stages. The dataset shows clear visual differences between classes. Mature cabbages exhibit larger, denser, and more compact heads, while premature cabbages show looser leaf structures and less head formation. These patterns provide useful features for machine learning algorithms. This dataset supports applications including training and evaluation of deep learning models for crop maturity detection, development of computer vision systems for automated harvesting, research in precision agriculture and smart farming, and benchmarking algorithms for agricultural image classification. Each image is labeled according to its maturity stage: Class 1 (mature, 135 DAT) and Class 2 (premature, 100 DAT), enabling easy integration with machine learning workflows. Overall, this dataset provides a valuable resource for advancing research in AI-based crop maturity prediction and intelligent agricultural harvesting systems. The authors gratefully acknowledge financial support from ICAR–CIAE under the CRP-FMPF project.","author":[{"family":"Kumar","given":"Manoj"},{"family":"Rawat","given":"S"},{"family":"Goutam","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/tccrdw75t8.1","URL":"https://doi.org/10.17632/tccrdw75t8.1","source":"datacite"},{"id":"doi:10.5281/zenodo.19161318","type":"article-journal","title":"AgriSense - Smart Farming Assistant Using IoT and Artificial Intelligence","abstract":"Modern agriculture faces unprecedented challenges due to climate change, water scarcity, and the increasing demand for food security. \"AgriSense\" is an intelligent farming assistant designed to bridge the gap between traditional agricultural practices and precision farming through the integration of the Internet of Things (IoT) and Artificial Intelligence (AI). The proposed system utilizes a Raspberry Pi-based edge gateway to collect real-time data from soil moisture, temperature, and humidity sensors. By employing a multimodal AI approach, AgriSense leverages Long Short-Term Memory (LSTM) networks for predictive irrigation and Convolutional Neural Networks (CNNs) for early-stage crop disease detection. A Flask-based web dashboard provides farmers with a centralized interface for real-time monitoring and automated control. Experimental results and literature reviews indicate that such integrated systems can improve irrigation efficiency by up to 30%, increase crop yields by 20-30%, and achieve disease detection accuracies exceeding 90%. AgriSense offers a scalable, low-cost solution for smallholder farmers to optimize resource utilization and enhance sustainable agricultural productivity.","author":[{"family":"Srivastava","given":"Arushi"},{"family":"Kashyap","given":"Himanshu"},{"family":"Shukla","given":"Er"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19161318","URL":"https://doi.org/10.5281/zenodo.19161318","source":"datacite"},{"id":"doi:10.5281/zenodo.19161317","type":"article-journal","title":"AgriSense - Smart Farming Assistant Using IoT and Artificial Intelligence","abstract":"Modern agriculture faces unprecedented challenges due to climate change, water scarcity, and the increasing demand for food security. \"AgriSense\" is an intelligent farming assistant designed to bridge the gap between traditional agricultural practices and precision farming through the integration of the Internet of Things (IoT) and Artificial Intelligence (AI). The proposed system utilizes a Raspberry Pi-based edge gateway to collect real-time data from soil moisture, temperature, and humidity sensors. By employing a multimodal AI approach, AgriSense leverages Long Short-Term Memory (LSTM) networks for predictive irrigation and Convolutional Neural Networks (CNNs) for early-stage crop disease detection. A Flask-based web dashboard provides farmers with a centralized interface for real-time monitoring and automated control. Experimental results and literature reviews indicate that such integrated systems can improve irrigation efficiency by up to 30%, increase crop yields by 20-30%, and achieve disease detection accuracies exceeding 90%. AgriSense offers a scalable, low-cost solution for smallholder farmers to optimize resource utilization and enhance sustainable agricultural productivity.","author":[{"family":"Srivastava","given":"Arushi"},{"family":"Kashyap","given":"Himanshu"},{"family":"Shukla","given":"Er"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19161317","URL":"https://doi.org/10.5281/zenodo.19161317","source":"datacite"},{"id":"doi:10.22004/ag.econ.396338","type":"article-journal","title":"TRANSFORMING INDIAN AGRICULTURE THROUGH SMART FARMING TECHNOLOGIES: AN EXTENSIVE ANALYSIS OF ROBOTICS, AI, AND IOT APPLICATIONS","abstract":"Indian agriculture is facing several challenges, such as climate change, irregular weather patterns, soil degradation, shortage of farm labour, and declining interest of youth in farming. To overcome these problems, smart farming technologies have emerged as an effective solution. This review paper discusses the role of modern technologies such as artificial intelligence, robotics, drones, sensors, Internet of Things (IoT), and Geographic Information Systems (GIS) in transforming traditional agriculture into technology-driven farming in India. Smart farming systems help farmers in selecting suitable crops, monitoring weather conditions, managing water resources, detecting pests and diseases at early stages, and maintaining optimal temperature and humidity for better crop growth. Automated weather stations, soil and climate sensors, robotic surveillance, and drone-based monitoring provide real-time data, which supports timely decision-making and reduces crop losses. Centralised data management platforms and decision-support systems also improve farm planning, productivity, and sustainability. The review highlights the importance of training farmers, students, and researchers in advanced agricultural technologies and emphasises the role of agricultural universities and research centres in promoting digital agriculture. Smart farming initiatives also create opportunities to attract young people to agriculture by reducing physical labour and increasing efficiency. Overall, smart farming technologies provide a sustainable approach to enhancing Indian agriculture, ensuring food security, and supporting future generations of farmers.","author":[{"family":"Srinivas","given":"D"},{"family":"Venkateshwarlu","given":"M"},{"family":"Rajya Laxmi","given":"K"},{"family":"Ugandhar","given":"T"}],"issued":{"date-parts":[[2025]]},"DOI":"10.22004/ag.econ.396338","URL":"https://doi.org/10.22004/ag.econ.396338","source":"datacite"},{"id":"oa:W7130338875","type":"article-journal","title":"Next‐Generation Microencapsulation Technologies for Probiotic Protection and Precision Delivery","abstract":"Probiotics offer well-documented benefits, including improved gastrointestinal function, microbiota modulation, and immune enhancement. However, their therapeutic potential is limited by poor survival during oral delivery due to gastric acid, bile salts, and pathological gut conditions. Microencapsulation has emerged as a transformative strategy to enhance probiotic viability by shielding them from environmental stressors. This review comprehensively examines cutting-edge microencapsulation materials and innovative techniques that improve probiotic stability under thermal, oxidative, and gastrointestinal stresses. We highlight advanced delivery systems, such as pH-responsive and inflammation-targeted microcapsules, which enable precise intestinal release and enhanced colonisation. Additionally, we critically assess safety considerations and industrial scalability challenges, emphasising the need for biocompatible materials and cost-effective production. By integrating recent breakthroughs with practical applications, this review underscores the potential of next-generation microencapsulation to enable safer, more efficient, and personalised probiotic therapies.","author":[{"family":"Zhu","given":"Yixin"},{"family":"Lv","given":"Longxian"},{"family":"Du","given":"Bingbing"},{"family":"Zhao","given":"Mingrui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1111/1751-7915.70305","URL":"https://doi.org/10.1111/1751-7915.70305","source":"openalex"},{"id":"oa:W4412055618","type":"article-journal","title":"Overview of the Application Progress of Digital Twins in Agriculture","abstract":"This paper reviews and discusses the application of digital twin (DT) technology in agriculture. The article first introduces the key concepts of digital twin technology, discusses the interdisciplinary technologies required for the application of digital twin technology in agriculture, and analyzes the characteristics and challenges of digital twin implementation in different regions. After that, according to the digital twin rating evaluation system proposed by predecessors, the specific studies on several agricultural digital twins this year were analyzed and graded, and it was concluded that most of the agricultural digital twins are still in their infancy. Finally, the article looks forward to the future of digital twin technology in agriculture, indicating its potential to transform crop monitoring, environmental management, and decision-making through intelligent real-time systems.","author":[{"family":"Gong","given":"Jue"},{"family":"Chen","given":"Jie"},{"family":"Chen","given":"Zixi"},{"family":"Chi","given":"Hongyi"},{"family":"Liu","given":"Jianglong"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1145/3736426.3736473","URL":"https://doi.org/10.1145/3736426.3736473","source":"openalex"},{"id":"oa:W4409966134","type":"article-journal","title":"Application of Transformer-Based Deep Learning Models for Predicting the Suitability of Water for Agricultural Purposes","abstract":"Water is the most vital component for the sustainability of living beings on Earth. From plants to human beings, every single living being on Earth needs water for its survival. In this research, a novel model has been developed in order to predict the suitability of water for agricultural purposes. This research developed the ALBERT Base v2 model for detecting water quality and suitability and a model named the ALBERT Water Potability Detection (ALBERT-WPD) model, customized from the ALBERT Base v2 transformer model. The model was tested using a dataset from Kaggle, and the performance was evaluated. The research used ten parameters. The performance of both models was measured using metrics, accuracy, precision, recall, and F1-score. In this research, traditional models (CNN and RNN) were developed and compared against the ALBERT model to measure its performance and its efficiency in water potability prediction. The findings revealed that the ALBERT models gained higher accuracies than the traditional models: the Base v2 model gained 91% and the altered ALBERT-WPD rendered 96% accuracy. The classification results (precision, recall, and F1-score) obtained for the ALBERT-WPD model for the potability class were 93%, 98%, and 96% and those for the non-potability class were 98%, 95%, and 96%, respectively. The study found that using transformer models for water potability detection procures higher accuracy with the model optimization method. The study concludes that using transformer models (BERT-based) in water potability detection procures higher accuracy (>95%) with fewer parameters in comparison with traditional models (CNN and RNN) which utilize more parameters. The findings show that the transformer models exhibit rapid data processing and handle large datasets efficiently; the handling of such datasets is complicated when using traditional models, as they have vanishing gradient and encounter temporal data loss challenges. Thus, the significance of the proposed research dwells within the use of “transformers” as an advanced machine learning model to predict water potability and quality, showing that transformers are the future of machine learning.","author":[{"family":"Rejini","given":"K"},{"family":"James","given":"Visumathi"},{"family":"Genitha","given":"CH"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/w17091347","URL":"https://doi.org/10.3390/w17091347","source":"openalex"},{"id":"oa:W4414026802","type":"article-journal","title":"Advancements and Challenges in Allelopathy: a Global Perspective on Agricultural Practices","abstract":"Abstract In plants, allelopathy refers to the positive or negative effects that one plant has on another through the release of chemical compounds into the environment, typically from roots, leaves, stems, flowers, fruits, or decaying plant matter. Allelopathy plays an important role in plant competition, crop rotation, weed suppression, and ecosystem dynamics, is now getting attention as a promising method for sustainable agriculture. This paper explains the advantages and disadvantages, as well as the differences in its application in agricultural practices between developed and developing countries. In developed countries, allelopathy application can be optimized by improved technologies, appropriate crop management practices, and careful selection of allelopathic species. Allelochemicals such as phenolics, terpenoids, alkaloids, and momilactones are potentially applied in sustainable agriculture through some marketed bioherbicides, cover crops, and crop rotation for weed and pest control. Although breeding and genetic engineering aim to enhance allelopathic traits in crops have been extensively studied, but desired allelopathic crops have not yet succeeded. In contrast, developing countries face challenges in development of commercial bioherbicides due to limited funding, poor infrastructure, and restricted access to technologies for isolating bioactive compounds and synthesizing bioherbicides from allelochemicals. Therefore, smallholder farmers have accustomed to use traditional allelopathic materials, such as neem, mustard, and garlic extracts, but these are not officially recognized because there are neither proper regulations nor scientific standardization have been approved. To solve these problems, this review suggests increasing knowledge-sharing, technology transfer, and research cooperation between developed and developing countries. Also, improving policies and regulations for bioherbicides in developing countries will aid farmers to extend the use of allelochemical-derived compounds in agricultural practices. By applying the findings from this paper, many countries can optimize their allelopathy-based farming systems according to their local conditions, contributing to sustainable agriculture, environmental protection, and food security.","author":[{"family":"Xuan","given":"Tran"},{"family":"Chien","given":"Nguyen"},{"family":"Khanh","given":"Tran"},{"family":"Viet","given":"Tran"},{"family":"Minh","given":"Tran"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s10343-025-01217-6","URL":"https://doi.org/10.1007/s10343-025-01217-6","source":"openalex"},{"id":"oa:W4413248198","type":"article-journal","title":"Achieving the Sustainable Agricultural Development Goals by Adopting the New Energy Electric Agricultural Machinery: An Analysis of Opportunities and Challenges of China","abstract":"New energy is a type of renewable energy that has the characteristics of protecting the environment and conserving energy. Agriculture is an industry that concerns the national economy and people’s livelihood. Agricultural mechanization is a key factor in achieving high-quality agricultural development. At present, China is the world’s largest producer and user of agricultural machinery. The use of traditional agricultural machinery powered mainly by internal combustion engines is currently the main source of carbon emissions in China’s agricultural production. How to achieve effective application and sustainable development of electric new energy technology in agricultural machinery is the primary issue facing China and countries around the world. This article takes the application and development status of electric new energy technology in agricultural machinery as the research object. Firstly, we provided an overview of China’s primary energy production and utilization as well as the national agricultural mechanization situation. Secondly, the research and application status of new energy electric agricultural machinery in China were elaborated on. Finally, some major challenges and opportunities faced by China’s development of new energy electric agricultural machinery were analyzed. We firmly believe that China’s active development of new energy technologies in agricultural machinery plays an important role and practical significance in building a community with a shared future for mankind, reducing carbon emissions from agricultural production, and achieving sustainable agricultural development goals.","author":[{"family":"Yang","given":"Hongguang"},{"family":"Ding","given":"Fujie"},{"family":"Gu","given":"Fengwei"},{"family":"Wu","given":"Feng"},{"family":"Yu","given":"Zhaoyang"},{"family":"Zhang","given":"Peng"},{"family":"Wang","given":"Jiangtao"},{"family":"Hu","given":"Zhichao"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/en18164211","URL":"https://doi.org/10.3390/en18164211","source":"openalex"},{"id":"oa:W7134230685","type":"article-journal","title":"A review on multifunctional applications of MgO nanostructures: from material science to environmental and agricultural innovations","abstract":"ions, exhibits hygroscopic properties and is a white, solid mineral with diverse technological applications. These nanoparticles demonstrate versatile applications across multiple disciplines, including agriculture, drug delivery, environmental remediation, antimicrobial treatments, and supercapacitor technologies. Previous studies describe diverse synthesis methodologies including sol-gel routes, flame synthesis, and hydrothermal methods, whereas this review focuses primarily on green synthesis approaches. The green synthesis methodology employs plant extracts that serve dual functions as both reducing agents and capping agents in the formation and stabilization of metal oxide nanoparticles. Biosynthesized MgO NPs exhibit distinctive properties, including controlled morphology, high surface area, tunable particle size distribution, and enhanced stabilization. These characteristics position MgO NPs as promising candidates for addressing contemporary environmental challenges and advancing energy storage technologies. This review critically analyzes recent developments in biosynthesized MgO NPs, highlighting the advantages of green synthesis over conventional methods and identifying key research gaps and future directions in this rapidly evolving field.","author":[{"family":"Mahiba","given":"GGJ"},{"family":"Prabakaran","given":"A"},{"family":"Balraj","given":"Babu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1039/d5ra07016c","URL":"https://doi.org/10.1039/d5ra07016c","source":"openalex"},{"id":"oa:W4411893177","type":"article-journal","title":"Insecticide Resistance in Agricultural Pests: Mechanisms, Case Studies, and Future Directions","abstract":"Pesticide resistance is an escalating global challenge that threatens agricultural productivity, food security, and the sustainability of pest control methods. Over 600 insect species have developed resistance, compromising the effectiveness of chemical controls and exacerbating pest outbreaks. Species such as Helicoverpa armigera and Bemisia tabaci serve as prominent examples of pests displaying this growing resistance problem. This study aims to explore the underlying mechanisms of pesticide resistance in key agricultural pests, identify the major contributing factors, assess the effectiveness of current management strategies, and examine potential future tools and technologies for combating resistance. The study integrates data from global case studies, specifically focusing on Helicoverpa armigera in India and Bemisia tabaci in China. It also synthesizes information on various resistance mechanisms, including metabolic, target-site, penetration, and behavioral processes. Several resistance management strategies, such as pesticide rotation, integrated pest management (IPM), and refuge policies, are evaluated for their effectiveness. Metabolic and target-site resistance mechanisms are particularly prevalent in resistant insect populations. Contributing factors include overuse of single pesticide classes, sub-lethal dosages, inadequate treatment regimens, and monoculture farming. IPM and pesticide rotation employing different modes of action are among the most effective current strategies. Emerging technologies RNA interference (RNAi) and CRISPR gene editing , offer promising new approaches. Addressing pesticide resistance requires a comprehensive, multi-faceted strategy that incorporates genetic tools, real-time monitoring, biopesticide development, and stronger regulatory frameworks. International cooperation, farmer education, and scientifically informed policies will be critical to future success.","author":[{"family":"Khudhair","given":"Ihsan"},{"family":"Abbood","given":"Naseer"},{"family":"Elamier","given":"Yasser"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32792/utq/utjsci/v12i1.1381","URL":"https://doi.org/10.32792/utq/utjsci/v12i1.1381","source":"openalex"},{"id":"oa:W4414947089","type":"article-journal","title":"Mapping the Scientific Labour Organization in Agricultural and Remote Sensing Research","abstract":"Scientific labour organization is becoming relevant in the context of the rapidly changing requirements of the modern market, especially in the growing human interaction with robotic systems and artificial intelligence. The purpose of this study is to conduct a bibliometric and content analysis of scientific labour organization in agriculture, with a focus on the integration of remote sensing technologies and precision farming. The methodological basis of the work included bibliometric and content analysis of scientific articles selected from the Web of Science database for the period 1992-2025, using clusterization (CiteSpace 6.3.R1). The results showed a steady increase in publication activity: since 2017, the number of papers has increased to four per year, and the peak of citations occurred in 2022. Cluster analysis revealed two dominant areas: “Industry 4.0” (77 articles, the average publication year is 2016, S = 0.99) and “Precision Agriculture” (34 articles, the average year is 2014, S = 1.0). These clusters have shown that sustainable land use technologies and precision farming innovations are changing the organization of labor and management of agricultural enterprises. The results demonstrate the growing interest in the problems of labor organization in the context of the digitalization of the agricultural sector, the strengthening of interdisciplinary ties and the expansion of the range of applied research. In the future, it is advisable to expand databases for analysis, include more intersectoral research and develop organizational models that take into account the social and ethical aspects of the introduction of new technologies.","author":[{"family":"Konstantinova","given":"Kristina"},{"family":"Bekmukhamedov","given":"Nurlan"},{"family":"Zhumabay","given":"Nurdaulet"}],"issued":{"date-parts":[[2025]]},"DOI":"10.51176/1997-9967-2025-3-139-151","URL":"https://doi.org/10.51176/1997-9967-2025-3-139-151","source":"openalex"},{"id":"oa:W7127636525","type":"article-journal","title":"Cropland concentration powers sustainable intensification of agriculture in China","abstract":"Over the past few decades, China’s cropland configuration has changed markedly, with important implications for food security and agricultural sustainability. Here we examine how cropland spatial-temporal concentration relates to agricultural intensification across China from 2000 to 2020. We mapped cropland distribution for five benchmark years using Google Earth Engine platform and 234,804 Landsat images and quantified cropland landscape configuration. These data were combined with provincial statistics on crop yield, fertilizer application, irrigation water use, and agricultural machinery power. We find that cropland experienced a contraction phase from 2000 to 2015 followed by a recovery phase after 2015. During contraction, increases in crop production commonly coincided with rising fertilizer and machinery inputs, whereas during recovery these inputs declined in most regions, alongside increased cropland contiguity. Overall, agricultural intensification in China became more sustainable by reducing reliance on fertilizer and machinery inputs and placing greater emphasis on cropland-use efficiency and environmental protection. Agricultural intensification in China became more sustainable from 2000 to 2020 by reducing reliance on fertilizer and machinery and focusing on resource efficiency and environmental protection, based on remote sensing and landscape index analysis.","author":[{"family":"Liu","given":"Shibin"},{"family":"Ling","given":"Long"},{"family":"He","given":"Fakun"},{"family":"Lei","given":"Jie"},{"family":"Huang","given":"Wenbin"},{"family":"Long","given":"Jiamei"},{"family":"Han","given":"Jichong"},{"family":"Wan","given":"Long"},{"family":"Qi","given":"Jiaguo"},{"family":"Shao","given":"Huaiyong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1038/s43247-026-03259-8","URL":"https://doi.org/10.1038/s43247-026-03259-8","source":"openalex"},{"id":"oa:W4410545869","type":"article-journal","title":"Digital and Entrepreneurial Competencies for the Bioeconomy: Perceptions and Training Needs of Agricultural Professionals in Greece, Italy, Portugal, and Sweden","abstract":"As the European Union advances its bioeconomy strategy, the agricultural sector emerges as a key domain requiring targeted upskilling in digital and entrepreneurial competencies. This study examines how agricultural professionals perceive the importance of these competencies and identifies related training needs, drawing on the European Commission’s Digital Competence Framework (DigComp) and Entrepreneurship Competence Framework (EntreComp). Using a quantitative survey methodology, data were collected from 140 respondents, including farmers, agronomists, consultants, entrepreneurs, and policymakers, in four European countries: Greece, Italy, Portugal, and Sweden. Descriptive and non-parametric analyses (Mann–Whitney U and Kruskal–Wallis tests) revealed strong recognition of digital competencies across all groups, with significant variation by country, while perceptions of entrepreneurial competencies differed mainly by professional role. Moreover, a significant lack of formal bioeconomy-related education was identified. The findings underscore the need for targeted, competence-based education and policy interventions to equip professionals with the skills required for a sustainable and innovation-driven agricultural sector.","author":[{"family":"Petropoulos","given":"Dimitrios"},{"family":"Deirmentzoglou","given":"Georgios"},{"family":"Αποστολόπουλος","given":"Νικόλαος"},{"family":"Paris","given":"Bas"},{"family":"Michas","given":"Dimitris"},{"family":"Balafoutis","given":"Athanasios"},{"family":"Athanasopoulou","given":"Elena"},{"family":"Nibbi","given":"Leonardo"},{"family":"Li","given":"Hailong"},{"family":"Carvalho","given":"Lara"},{"family":"Silva","given":"Maria"},{"family":"Silva","given":"Fernando"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15101106","URL":"https://doi.org/10.3390/agriculture15101106","source":"openalex"},{"id":"oa:W4417525269","type":"article-journal","title":"Assessing the Role of Artificial Intelligence in Transforming Decision-Making Across Modern Agricultural Systems.","abstract":"Artificial Intelligence (AI) is revolutionizing the agricultural sector by enhancing data-driven decision-making, improving resource utilization, and supporting sustainable food production. This review explores how AI-based tools—such as machine learning, computer vision, and predictive analytics—are reshaping decision processes across key agricultural domains including crop management, livestock monitoring, soil optimization, and supply chain logistics. It examines the integration of AI with Internet of Things (IoT) sensors, drones, and satellite imaging to enable precision agriculture and real-time adaptive strategies. Furthermore, the paper evaluates the ethical, infrastructural, and technical challenges associated with implementing AI-driven systems, particularly in developing regions. Through a synthesis of current literature and emerging case studies, this review highlights the potential of AI to reduce uncertainty, support policy formulation, and foster resilience against climate variability. The paper concludes by identifying future research directions focused on explainable AI (XAI), edge computing, and the democratization of agricultural intelligence systems to ensure inclusivity and global scalability.","author":[{"family":"Independent Researcher","given":"Usa"},{"family":"Michael","given":"Olamidotun"},{"family":"Ogunsola","given":"Omodolapo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47191/etj/v10i12.06","URL":"https://doi.org/10.47191/etj/v10i12.06","source":"openalex"},{"id":"oa:W7133343452","type":"article-journal","title":"Quantum Computing for Precision Agriculture in Challenging Environments: A Case Study from Northern Morocco","abstract":"Abstract. The legalization of medical cannabis in Morocco’s northern Rif region requires precision agriculture systems capable of supporting highly controlled, traceable and quality-driven cultivation. Medical cannabis is biologically sensitive to micro-variations in soil moisture, vapor pressure deficit (VPD), canopy temperature and nutrient levels, which makes it a demanding testbed for advanced decision-support methods. In this work, we propose and numerically evaluate an end-to-end hybrid quantum–classical framework that combines IoT sensor networks, Sentinel-2 and UAV imagery, GIS integration and quantum-enhanced analytics for regulated medical cannabis cultivation in the Al-Hoceïma region. The framework instantiates three quantum modules: (i) a variational quantum linear solver (VQLS) for Kriging-based spatial interpolation under sparse sensing, (ii) a variational quantum classifier (VQC) for early stress detection from multi-source features, and (iii) a Quantum Approximate Optimization Algorithm (QAOA) for constrained irrigation scheduling. All experiments are conducted on synthetic yet agro-ecologically calibrated data generated for a 4-hectare virtual plot; no real cannabis-field data or quantum hardware are used. In this controlled simulation setting, the quantum-inspired modules achieve moderate improvements over classical baselines (Kriging, Random Forest, neural networks, MILP), for example reducing interpolation RMSE by about 20% and improving early-stress F1-score by several percentage points. We explicitly do not claim hardware-level quantum advantage, nor do we provide a formal proof that VQLS or VQC must outper- form classical Kriging or machine learning in this regime. Instead, the contribution is a transparent formulation and simulation- based assessment of quantum-compatible workflows for precision agriculture in regulated contexts, together with a critical discus- sion of their current limitations and the conditions under which they might become competitive in practice.","author":[{"family":"Ahmed","given":"Mohamed"},{"family":"Boudhir","given":"Anouar"},{"family":"Mahboub","given":"Aziz"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5194/isprs-archives-xlviii-4-w19-2025-29-2026","URL":"https://doi.org/10.5194/isprs-archives-xlviii-4-w19-2025-29-2026","source":"openalex"},{"id":"oa:W7127441965","type":"article-journal","title":"Seeds of change: Mapping the landscape of precision farming technology adoption among agricultural entrepreneurs","abstract":"This study focuses on identifying the application of precision farming technology in agriculture entrepreneurship by applying a systematic literature review approach. The documents in the English language available in the Scopus, Dimensions, and Web of Science, databases are considered. A total of 229 documents during the period 1995–2023 were selected through the SPAR-4-SLR protocol to understand the role and adoption of precision farming technology by agriculture entrepreneurs. The study investigates the evolution over the period to examine the evolution, factors influencing the adoption, the impact of these technologies, the contribution to sustainable development, differences in the adoption in developing and developed countries, barriers faced during the adoption, future trends in the precision farming technology adoption, and recommendations for the improvement. The major findings are; factors influence precision farming technology in agriculture entrepreneurship are; readiness for technology integration, knowledge, finance, and accessibility. The enhancement in productivity, efficiency, and sustainability is also considered a driving factors. Developed countries like the USA and the European Union countries have largely adopted the PFT compared the developing countries. Initial costs, inadequate expertise, lack of infrastructure, etc. were the major challenges encountered. This study is purely a literature review and lacks the advantages of applying a quantitative study. This study fills the existing research gap and directions for further research. The study provides managerial implications to prepare suitable policies, plans, and programs to promote precision farming technology adoption and impart awareness for enriching knowledge among agricultural entrepreneurs and farmers. The novelty of the study is based on the structured literature review.","author":[{"family":"Alka","given":"TA"},{"family":"Sreenivasan","given":"Aswathy"},{"family":"Suresh","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s44447-025-00101-z","URL":"https://doi.org/10.1007/s44447-025-00101-z","source":"openalex"},{"id":"oa:W7125578641","type":"article-journal","title":"The intersection of artificial intelligence and food systems: exploring technological breakthroughs and data-driven agriculture","abstract":"Food security is an international challenge that is constantly exposed to climate change, rapid population increases, economic inequalities and geopolitical unrest. Thus, new solutions must be developed to address these issues. Artificial intelligence (AI) has become one such solutions and it has helped to enhance different food production, processing and distribution phases. Precision farming can be improved through AI because it allows the efficient management of resources such as water or fertilizers to increase crop yields. AI helps in the monitoring of animal health and optimization of feeding in livestock farming. In addition AI technologies simplify harvesting and enhancement after harvesting with enhanced sorting and grading. AI improves food processing through enhanced quality control and safety and optimizes logistics by improving routes, reducing spoilage and ensuring timely delivery. Another area where AI can be useful in reducing waste is tracking and minimizing food waste at all levels, however AI can also be applied to personalized nutrition services to assist people in making healthier food choices. The implementation of AI in food supply chain can help countries become more efficient and sustainable, governments need to enhance technology through good policies, better infrastructure and extensive access to these technologies.","author":[{"family":"Ahmed","given":"Naseer"},{"family":"Kour","given":"Rajvinder"},{"family":"Jan","given":"Tawseefa"},{"family":"Sharma","given":"Seerat"},{"family":"Singh","given":"Tajendra"},{"family":"Chauhan","given":"Praneet"},{"family":"Ghanghas","given":"Sachin"},{"family":"Sheikh","given":"Imran"},{"family":"Rafatullah","given":"Mohd"},{"family":"Setyawan","given":"Hendrix"},{"family":"Huda","given":"Nurul"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/23311932.2026.2615165","URL":"https://doi.org/10.1080/23311932.2026.2615165","source":"openalex"},{"id":"doi:10.83199/qwy2-k853","type":"article-journal","title":"Re-engineering soils to improve the access of crop root systems to water and nutrients stored in the subsoil","abstract":"Data includes: Plant estabishment and germination counts Grain yield and harvest index (and tield compnents - physiological maturioty, total weight, grain weight, head number) Soil compaction/depths Soil water content, water infiltration, water repellance, water retention Grain quality Soil sampling (physical and chemical analyses) Pogo analysis Early biomass (dry wt, wet wt) Crop canopy cover (Drone NVDI measurements)/temperature Leaf chlorophyll content Ploughing depth Anthesis biomass and tiller counts Assessment of amelioratiuon efficacy. Paddock yield data, historical satellite imagery NVDI, assessment of yield potential Trial site-year information including: Weather conditions (rainfall and temperature during growing season Nitrogen test resultys Stage of growth of the wheat crop to which the nitrogen was applied Type of vegeation present Soil type, soil sampling analysis of chemical and physical data, historical yield data pre and poast soil amelioration treatments, NVDI, soil penetration resistance","author":[{"family":"Azam","given":"Gaus"},{"family":"Betti","given":"Giacomo"},{"family":"Gazey","given":"Christopher"},{"family":"Van Burgel","given":"Andrew"},{"family":"Edwards","given":"Tom"}],"issued":{"date-parts":[[2023]]},"DOI":"10.83199/qwy2-k853","URL":"https://doi.org/10.83199/qwy2-k853","source":"datacite"},{"id":"doi:10.17863/cam.94160","type":"article-journal","title":"A Simple Reversed Iontophoresis-Based Sensor to Enable In Vivo Multiplexed Measurement of Plant Biomarkers Using Screen-Printed Electrodes.","abstract":"The direct quantification of plant biomarkers in sap is crucial to enhancing crop production. However, current approaches are inaccurate, involving the measurement of non-specific parameters such as colour intensity of leaves, or requiring highly invasive processes for the extraction of sap. In addition, these methods rely on bulky and expensive equipment, and they are time-consuming. The present work reports for the first time a low-cost sensing device that can be used for the simultaneous determination of sap K+ and pH in living plants by means of reverse iontophoresis. A screen-printed electrode was modified by deposition of a K+-selective membrane, achieving a super-Nernstian sensitivity of 70 mV Log[K+]−1 and a limit of detection within the micromolar level. In addition, the cathode material of the reverse iontophoresis device was modified by electrodeposition of RuOx particles. This electrode could be used for the direct extraction of ions from plant leaves and the amperometric determination of pH within the physiological range (pH 3−8), triggered by the selective reaction of RuOx with H+. A portable and low-cost (&lt;£60) microcontroller-based device was additionally designed to enable its use in low-resource settings. The applicability of this system was demonstrated by measuring the changes in concentration of K+ and pH in tomato plants before and after watering with deionised water. These results represent a step forward in the design of affordable and non-invasive devices for the monitoring of key biomarkers in plants, with a plethora of applications in smart farming and precision agriculture among others.","author":[{"family":"Ruiz-Gonzalez","given":"Antonio"},{"family":"Kempson","given":"Harriet"},{"family":"Haseloff","given":"Jim"}],"issued":{"date-parts":[[2023]]},"DOI":"10.17863/cam.94160","URL":"https://doi.org/10.17863/cam.94160","source":"datacite"},{"id":"doi:10.6084/m9.figshare.23696655","type":"article-journal","title":"Current Trends in Agriculture &amp; Allied Sciences (Volume-1).pdf","abstract":"We are delighted to publish our book entitled “Current Trends in Agriculture &amp; Allied Sciences (Volume-1)”. This Books Provides basic ideas related to Recent Emerging Trends in the field of Agriculture, Horticulture, Fishery, Forestry, Dairy Science and other allied sciences. The Book Chapter Consisting of different thematic areas i.e., Advance methods used in Agriculture (IoT, AI, Drone, GIS, GPS, Remote Sensing), Current Trends in Social Science , Crop Production, Crop Protection, Behavioural Science , Marketing &amp; Management, Current Trends in Agriculture, Horticulture, Food Technology, Community Science, Dairy Science, Fishery, Forestry and Animal Sciences, Nutrition-Sensitive Agriculture, Smart Farming &amp; Precision Agriculture, Sustainable Crop Cultivation Strategies, Nano-Science in Agriculture, Drones and Robotics Applications in Agriculture, Smart Packaging Technology, Management of Agricultural Waste, Valorization of Fruits and Vegetables By-products in Food, Pharmaceutical, and Cosmetics Industries and Environmental Impact of Agriculture. This Books consisting of 29 Chapter contribute by Professors, Scientists, Ph.D. Scholar of different institutes throughout India. A humble attempt is made in this book to present basic concepts of Recent Tools and Techniques, Block Chain Technology, Artificial Intelligence and IoT, Smart Farming, Precision Agriculture Approaches, High Tech Agriculture, Latest Methodology used in the agriculture and allied sectors. We hope that this book will be helpful for the researchers in the development of genuine research studies. We are highly indebted to the authors for providing Scientific and Technical chapters for the compilation of books. Any suggestions or inputs from academicians and researcher to improve the book will be highly solicited and will be a great contribution to the discipline of Agricultural Research. The Editors is thankful to the Authors for the contribution in the book chapter. We are also thankful to SP Publishing, Bhubaneswar, India for the entire support and cooperation in publishing the book.","author":[{"family":"Almoselhy","given":"Rania"},{"family":"Chandran","given":"Ravindran"},{"family":"Juliet Mary S J","given":"Abisha"}],"issued":{"date-parts":[[2023]]},"DOI":"10.6084/m9.figshare.23696655","URL":"https://doi.org/10.6084/m9.figshare.23696655","source":"datacite"},{"id":"oa:W4390877753","type":"article-journal","title":"Effects of Peanut Rust Disease (Puccinia arachidis Speg.) on Agricultural Production: Current Control Strategies and Progress in Breeding for Resistance","abstract":"Speg.) disease constitutes a significant global biotic stress, representing a substantial economic threat to the peanut industry by inducing noteworthy reductions in seed yields and compromising oil quality. This comprehensive review delves into the distinctive characteristics and detrimental symptoms associated with peanut rust, scrutinizing its epidemiology and the control strategies that are currently implemented. Notably, host resistance emerges as the most favored strategy due to its potential to surmount the limitations inherent in other approaches. The review further considers the recent advancements in peanut rust resistance breeding, integrating the use of molecular marker technology and the identification of rust resistance genes. Our findings indicate that the ongoing refinement of control strategies, especially through the development and application of immune or highly resistant peanut varieties, will have a profound impact on the global peanut industry.","author":[{"family":"You","given":"Yu"},{"family":"Liao","given":"Junhua"},{"family":"He","given":"Zemin"},{"family":"Khurshid","given":"Muhammad"},{"family":"Wang","given":"CL"},{"family":"Zhang","given":"Zhenzhen"},{"family":"Mao","given":"Jinxiong"},{"family":"Xia","given":"Youlin"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/genes15010102","URL":"https://doi.org/10.3390/genes15010102","source":"openalex"},{"id":"oa:W4403841306","type":"article-journal","title":"Maintaining Agricultural Production Profitability—A Simulation Approach to Wheat Market Dynamics","abstract":"Profitability is a complex notion, intertwined with theoretical, socio-economic, and modern economic considerations. While traditionally linked to monopoly advantages, contemporary views broaden this to include shareholder value creation. In agriculture, profitability faces impediments such as rising input costs, market volatility, and economic disparities, emphasizing technological innovation, market conditions, and policy as crucial determinants. This study presents an econometric simulation model to analyze and forecast wheat production profitability in Poland from 2023 to 2027, providing insights into production efficiencies, market dynamics, and policy impacts. Using a system of recursive equations, the model forecasts profitability, integrating econometric techniques with expert insights. It examines variables like resource use, production levels, and price changes, validated through FADN data. The findings reveal that price relations and production efficiencies are the key to profitability. The model highlights market volatility, particularly through “price scissors”, as the main factor influencing profitability. Favorable price conditions significantly boost profitability and incentivize production. The model is a critical tool for analyzing wheat profitability, highlighting the influence of market and policy changes. Future work could extend the model’s use to other regions or crops, incorporating advanced technologies to improve accuracy. This study offers valuable insights for agricultural economics, aiding stakeholders in strategic decision-making.","author":[{"family":"Bezat-Jarzębowska","given":"Agnieszka"},{"family":"Rembisz","given":"Włodzimierz"},{"family":"Jarzębowski","given":"Sebastian"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/agriculture14111910","URL":"https://doi.org/10.3390/agriculture14111910","source":"openalex"},{"id":"oa:W4404679725","type":"article-journal","title":"Internet of Things Integrated Deep‐Learning Algorithms Monitoring and Predicting Abnormalities in Agriculture Land","abstract":"ABSTRACT The Internet of Things (IoT) plays an essential role in the majority of the recent real‐time applications to speed up the process of immediate actions against abnormal behavior. Surveillance monitoring systems using CCTV and web cameras were used in earlier applications; nevertheless, they could only monitor and generate videos. The data transmission rate in the surveillance monitoring systems was poor due to the less‐performance internet technologies used in the earlier systems. Since they were restricted in data transmission speed, data size carried, communication distance, and sensing range. This paper integrates the fifth‐generation Internet technology (5G) IoT devices and sensors and deep‐learning algorithms to improve the efficiency of agriculture surveillance monitoring systems. It helps monitor, generate, and analyze the IoT data that can be processed immediately and predict the abnormal activities happening in agriculture. Landowners can take immediate action to save and recover the crops and their domestic animals concerning abnormal actions. This paper implements a Convolution Neural Network (CNN) algorithm for analyzing the IoT data and predicting abnormal activities. The experiment result is verified and compared with the other state‐of‐the‐art methods to evaluate the performance of the proposed CNN.","author":[{"family":"Selvam","given":"Prabu"},{"family":"Krishnamoorthy","given":"N"},{"family":"Kumar","given":"SP"},{"family":"Lokeshwaran","given":"K"},{"family":"Lokesh","given":"Madineni"},{"family":"Syamala","given":"Maganti"},{"family":"Vidhya","given":"RG"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1002/itl2.607","URL":"https://doi.org/10.1002/itl2.607","source":"openalex"},{"id":"oa:W4322730773","type":"article-journal","title":"Changing the logic in agricultural extension: evidence from a demand-driven extension programme in Kenya","abstract":"Developing countries have recognised the need to strengthen their agricultural extension services as an engine for improving productivity, reaching marginalised, poor and female farmers and addressing new challenges, such as environmental degradation and climate change. However, structuring effective and viable extension systems remains a major challenge in most places. This paper studies the Plantwise extension programme in Kenya, an initiative that supports and increases collaboration among actors in the national plant health system, establishes and maintains a network of plant clinics – a physical interface between farmers and crop protection experts – to address the needs of smallholders, and collects key information in the process that can be used for informing policy and for monitoring and evaluation purposes. To assess the programme in Kenya, we conducted a longitudinal mixed-methods evaluation of the programme from 2014 to 2018. Our results show that Plantwise has altered the way the Government of Kenya addresses crop protection. The programme is innovative and improves knowledge at multiple levels. At the farm level, Plantwise has contributed to improvements in the use of agricultural practices, inputs and maize productivity, a major staple crop. The results show that the Plantwise approach is a reasonable alternative to other agricultural extension systems that support smallholder farmers.","author":[{"family":"Bonilla","given":"Juan"},{"family":"Coombes","given":"Andrea"},{"family":"Romney","given":"DL"},{"family":"Winters","given":"Paul"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1080/19439342.2023.2181848","URL":"https://doi.org/10.1080/19439342.2023.2181848","source":"openalex"},{"id":"oa:W4399485097","type":"article-journal","title":"Precision prevention in worksite health–A scoping review on research trends and gaps","abstract":"OBJECTIVES: To map the current state of precision prevention research in the workplace setting, specifically to study contexts and characteristics, and to analyze the precision prevention approach in the stages of risk assessment/data monitoring, data analytics, and the health promotion interventions implemented. METHODS: Six international databases were searched for studies published between January 2010 and May 2023, using the term \"precision prevention\" or its synonyms in the context of worksite health promotion. RESULTS: After screening 3,249 articles, 129 studies were reviewed. Around three-quarters of the studies addressed an intervention (95/129, 74%). Only 14% (18/129) of the articles primarily focused on risk assessment and data monitoring, and 12% of the articles (16/129) mainly included data analytics studies. Most of the studies focused on behavioral outcomes (61/160, 38%), followed by psychological (37/160, 23%) and physiological (31/160, 19%) outcomes of health (multiple answers were possible). In terms of study designs, randomized controlled trials were used in more than a third of all studies (39%), followed by cross-sectional studies (18%), while newer designs (e.g., just-in-time-adaptive-interventions) are currently rarely used. The main data analyses of all studies were regression analyses (44% with analyses of variance or linear mixed models), whereas machine learning methods (e.g., Algorithms, Markov Models) were conducted only in 8% of the articles. DISCUSSION: Although there is a growing number of precision prevention studies in the workplace, there are still research gaps in applying new data analysis methods (e.g., machine learning) and implementing innovative study designs. In the future, it is desirable to take a holistic approach to precision prevention in the workplace that encompasses all the stages of precision prevention (risk assessment/data monitoring, data analytics and interventions) and links them together as a cycle.","author":[{"family":"Mess","given":"Filip"},{"family":"Blaschke","given":"Simon"},{"family":"Schick","given":"Teresa"},{"family":"Friedrich","given":"Julian"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1371/journal.pone.0304951","URL":"https://doi.org/10.1371/journal.pone.0304951","source":"openalex"},{"id":"oa:W4405320699","type":"article-journal","title":"A Bluetooth-Based Automated Agricultural Machinery Positioning System","abstract":"With the rapid advancement of technology, precision agriculture, as a modern agricultural production model, has seen significant progress in recent years. Its widespread adoption is gradually transforming traditional farming methods, providing strong support for the modernization of global agriculture. In particular, the application of positioning technology plays a crucial role in precision agriculture. This paper focuses on an automated agricultural machinery positioning system based on Bluetooth technology. The system uses Bluetooth at the 2.4 GHz frequency for transmission, processing Constant Tone Extension (CTE) and Received Signal Strength Indicator (RSSI) signals collected from blind nodes. The Propagator Direct Data Acquisition (PDDA) algorithm is employed to calculate angle information from CTE signals, while the Two-Ray Ground Reflection Model is applied to manage the correlation between RSSI and distance, making it suitable for outdoor environments. These two types of data are fused for positioning, with an optimized objective function converting the positioning task into an optimization problem. An Adaptive Secretary Bird Optimization Algorithm (ASBOA) is introduced to enhance the accuracy and efficiency of the positioning process. In the simulation, anchor and blind nodes are deployed to simulate a real farm environment. Anchor nodes receive CTE and RSSI signals from blind nodes. Considering that the tags mounted on agricultural machinery are set at a fixed height in real scenarios, the simulation also fixes the tags at this height. We then compare the accuracy of five algorithms in both static and dynamic tracking. The final simulation results indicate that ASBOA achieves satisfactory high-precision positioning, both for static points and dynamic tracking, theoretically meeting the needs for continuous positioning and laying a solid foundation for future field trials.","author":[{"family":"Bian","given":"Wentao"},{"family":"Liu","given":"Yanyi"},{"family":"Wu","given":"Yin"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/electronics13244902","URL":"https://doi.org/10.3390/electronics13244902","source":"openalex"},{"id":"oa:W4404068181","type":"article-journal","title":"Machine Learning Based Agricultural Profitability Recommendation Systems: A Paradigm Shift in Crop Cultivation.","abstract":"In India, the demand for fruits and vegetables has been consistently increasing alongside the rising population, making crop production a crucial aspect of agriculture. However, despite the growing demand and potential profitability, farmers have been slow to transition from traditional food grain crops to fruits and vegetables. In this paper, we explore the changing demands of food categories in India, highlighting the shift towards increased consumption of fruits and vegetables. Despite the potential benefits, farmers face various challenges and uncertainties associated with cultivating these crops. To address this, we propose the use of Machine Learning (ML) and Deep Learning (DL) techniques to analyze historical market price data for fruits and vegetables from 2016 to 2021 and predict future prices. This accurate prediction system will aid farmers in deciding which crops to grow and when to harvest, ultimately maximizing profits.","author":[{"family":"Sable","given":"Nilesh"},{"family":"Patil","given":"Rajkumar"},{"family":"Deore","given":"Mahendra"},{"family":"Bhimanpallewar","given":"Ratnmala"},{"family":"Mahalle","given":"Parikshit"}],"issued":{"date-parts":[[2024]]},"DOI":"10.9781/ijimai.2024.10.005","URL":"https://doi.org/10.9781/ijimai.2024.10.005","source":"openalex"},{"id":"oa:W4401818841","type":"article-journal","title":"Weed detection in agricultural fields using machine vision","abstract":"Weeds have the potential to cause significant damage to agricultural fields, so the development of weed detection and automatic weed control in these areas is very important. Weed detection based on RGB images allows more efficient management of crop fields, reducing production costs and increasing yields. Conventional weed control methods can often be time-consuming and costly. It can also cause environmental damage through overuse of chemicals. Automated weed detection and control technologies enable precision agriculture, where weeds are accurately identified and targeted, minimizing chemical use and environmental impact. Overall, weed detection and automated weed control represent a significant step forward in agriculture, helping farmers to reduce production costs, increase crop safety, and develop more sustainable agricultural practices. Thanks to technological advances, we can expect more efficient and environmentally friendly solutions for weed control in the future. Developing weed detection and automated control technologies is crucial for enhancing agricultural efficiency. Employing RGB images for weed identification not only lowers production costs but also mitigates environmental damage caused by excessive chemical use. This study explores automated weed detection systems, emphasizing their role in precision agriculture, which ensures minimal chemical use while maximizing crop safety and sustainability.","author":[{"family":"Moldvai","given":"László"},{"family":"Ambrus","given":"Bálint"},{"family":"Teschner","given":"Gergely"},{"family":"Nyéki","given":"Anikó"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1051/bioconf/202412501004","URL":"https://doi.org/10.1051/bioconf/202412501004","source":"openalex"},{"id":"doi:10.5281/zenodo.19597966","type":"article-journal","title":"Crop Disease Prediction & Solution Recommendation System Using Chatbots","abstract":"Agriculture plays a crucial role in economic development, yet farmers often face challenges in selecting suitable crops, managing soil fertility, and preventing diseases, which ultimately affect productivity and profitability. This paper presents an intelligent Crop Prediction and Solution Recommendation System that integrates Machine Learning (ML) techniques to assist farmers in making data-driven decisions. The system focuses on analyzing soil properties, predicting appropriate crops, and recommending fertilizers and preventive measures for diseases and pests. The proposed system collects real-time soil data such as moisture, temperature, and nutrient content using embedded sensors and microcontrollers. This data is combined with historical datasets obtained from agricultural sources and undergoes preprocessing steps including cleaning, normalization, and feature scaling to ensure accuracy. Machine learning algorithms such as Random Forest and Linear Regression are applied to predict crop suitability and expected yield. Additionally, pattern recognition techniques are used to identify potential disease occurrences and provide preventive recommendations.","author":[{"family":"Kale","given":"Sakshi"},{"family":"Morey","given":"Sneha"},{"family":"Murade","given":"Prajakta"},{"family":"Rajput","given":"Pooja"},{"family":"Darane","given":"Vaishnavi"},{"family":"Sahu","given":"Prof"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19597966","URL":"https://doi.org/10.5281/zenodo.19597966","source":"datacite"},{"id":"doi:10.5281/zenodo.20285555","type":"article-journal","title":"Plant Disease Prediction System using Raspberry PI and Image Processing","abstract":"Agriculture plays a vital role in sustaining human life, as crop health directly impacts food security and economic development. One of the major challenges faced by farmers is the timely and accurate detection of plant diseases, especially leaf-based infections that spread quickly and significantly reduce crop yield. Conventional disease identification methods depend on manual inspection, which is time-consuming, labor-intensive, and requires expert knowledge. To overcome these limitations, this work proposes an automated real-time leaf disease detection and pesticide recommendation system using Raspberry Pi and deep learning techniques. The system uses a CSI camera module to capture live images of plant leaves, which are analyzed through a custom-trained YOLOv5 model for accurate disease detection under different environmental conditions. When a disease is identified above a specified confidence threshold, the system retrieves suitable pesticide recommendations from a predefined database. The results are displayed on an I2C-based LCD module and recorded through terminal output. In addition, Twilio cloud communication service sends SMS alerts with disease details and pesticide suggestions, allowing farmers to receive notifications remotely. The system also highlights infected leaf regions using bounding boxes and labels for easy visual interpretation. Developed using Python, OpenCV, and PyTorch, it is optimized for low power consumption, portability, and affordability. This solution reduces human error, supports early disease detection, and promotes precision agriculture and sustainable farming practices.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20285555","URL":"https://doi.org/10.5281/zenodo.20285555","source":"datacite"},{"id":"doi:10.5281/zenodo.20285556","type":"article-journal","title":"Plant Disease Prediction System using Raspberry PI and Image Processing","abstract":"Agriculture plays a vital role in sustaining human life, as crop health directly impacts food security and economic development. One of the major challenges faced by farmers is the timely and accurate detection of plant diseases, especially leaf-based infections that spread quickly and significantly reduce crop yield. Conventional disease identification methods depend on manual inspection, which is time-consuming, labor-intensive, and requires expert knowledge. To overcome these limitations, this work proposes an automated real-time leaf disease detection and pesticide recommendation system using Raspberry Pi and deep learning techniques. The system uses a CSI camera module to capture live images of plant leaves, which are analyzed through a custom-trained YOLOv5 model for accurate disease detection under different environmental conditions. When a disease is identified above a specified confidence threshold, the system retrieves suitable pesticide recommendations from a predefined database. The results are displayed on an I2C-based LCD module and recorded through terminal output. In addition, Twilio cloud communication service sends SMS alerts with disease details and pesticide suggestions, allowing farmers to receive notifications remotely. The system also highlights infected leaf regions using bounding boxes and labels for easy visual interpretation. Developed using Python, OpenCV, and PyTorch, it is optimized for low power consumption, portability, and affordability. This solution reduces human error, supports early disease detection, and promotes precision agriculture and sustainable farming practices.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20285556","URL":"https://doi.org/10.5281/zenodo.20285556","source":"datacite"},{"id":"doi:10.5281/zenodo.21486085","type":"article-journal","title":"SmartAgriDoctor: Plant and Crop Disease Detection and Diagnosis Using Deep Learning","abstract":"Agriculture is still a staple of food security but the global productivity is threatened by the disease on plants. Traditional methods of manual inspection are usually subjective, time consuming and unproductive and are not conducive to being monitored industrial scale. This paper introduces SmartAgriDoctor which is a Deep learning-based system for automated Crop Disease Detection and Diagnosis using Convolutional Neural Networks (CNNs). The proposed framework passes through the phases of preprocessing, feature extraction and classification of the images from the New Plant Disease Dataset in order to identify between healthy and diseased leaves of plants. The dataset was augmented using random rotation, flip and contrast normalization to augment the generalization skills. The optimized CNN model that was trained and validated with 80,000 labelled images was able to achieve the Knowledge Level of 97.8% overall classification with the precision, recall and F1 score of 97.4%, 97.6% and 97.5% respectively. Experimental results demonstrate the robustness of the model under different class of diseases and environment variations; Due to low weight design of the system, it can be sent to the mobile devices and edge devices to conduct real-time diagnose to farmers and agronomists. Overall, SmartAgriDoctor is a very interesting example of the real-life application of Deep learning in precision agriculture leading to an early detection of the diseases, lesser losses of crop and sustainable agriculture.","author":[{"family":"Kunder","given":"Harish"},{"family":"Thimmaraju","given":"MB"},{"family":"Koli","given":"Abhishek"},{"family":"Habalkar","given":"Sujal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21486085","URL":"https://doi.org/10.5281/zenodo.21486085","source":"datacite"},{"id":"doi:10.5281/zenodo.21486086","type":"article-journal","title":"SmartAgriDoctor: Plant and Crop Disease Detection and Diagnosis Using Deep Learning","abstract":"Agriculture is still a staple of food security but the global productivity is threatened by the disease on plants. Traditional methods of manual inspection are usually subjective, time consuming and unproductive and are not conducive to being monitored industrial scale. This paper introduces SmartAgriDoctor which is a Deep learning-based system for automated Crop Disease Detection and Diagnosis using Convolutional Neural Networks (CNNs). The proposed framework passes through the phases of preprocessing, feature extraction and classification of the images from the New Plant Disease Dataset in order to identify between healthy and diseased leaves of plants. The dataset was augmented using random rotation, flip and contrast normalization to augment the generalization skills. The optimized CNN model that was trained and validated with 80,000 labelled images was able to achieve the Knowledge Level of 97.8% overall classification with the precision, recall and F1 score of 97.4%, 97.6% and 97.5% respectively. Experimental results demonstrate the robustness of the model under different class of diseases and environment variations; Due to low weight design of the system, it can be sent to the mobile devices and edge devices to conduct real-time diagnose to farmers and agronomists. Overall, SmartAgriDoctor is a very interesting example of the real-life application of Deep learning in precision agriculture leading to an early detection of the diseases, lesser losses of crop and sustainable agriculture.","author":[{"family":"Kunder","given":"Harish"},{"family":"Thimmaraju","given":"MB"},{"family":"Koli","given":"Abhishek"},{"family":"Habalkar","given":"Sujal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21486086","URL":"https://doi.org/10.5281/zenodo.21486086","source":"datacite"},{"id":"doi:10.5281/zenodo.21700237","type":"article-journal","title":"TerraHawk – AI Drone-Based Precision Agriculture System","abstract":"This work presents a farmer-oriented assistant that combines real-time crop detection with knowledge-based agronomic guidance. The system uses a YOLOv5-based computer vision module to detect crops and visually annotate images and videos with bounding boxes and confidence scores. It also features a bilingual chatbot (English/Kannada) that answers specific questions using a curated agricultural knowledge base. The backend is built with Fast API and offers unified REST endpoints for detection, chat, and history. Meanwhile, a React and Vite frontend delivers an interactive user interface for uploading media, viewing annotated results, and chatting with the assistant. From a design perspective, the system features a modular architecture. The detection model is wrapped in a lightweight layer and works with a multi-stage retrieval pipeline. This pipeline uses exact matching, crop-intent keywords, fuzzy token overlap, and semantic embeddings with FAISS. This design ensures strong, low-latency performance on standard hardware. It also lowers the chance of incorrect answers by using template-based response generation and explicit logging. The paper details the overall architecture, reviews related work in crop detection and agricultural decision support, and compares the proposed crop detection subsystem to traditional and modern machine learning methods. The discussion covers strengths, limitations, and design trade-offs, especially regarding deployment challenges, extensibility, and suitability for smallholder farming contexts.","author":[{"family":"Daniel","given":"EJ"},{"family":"Hr","given":"Harshavardhan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21700237","URL":"https://doi.org/10.5281/zenodo.21700237","source":"datacite"},{"id":"doi:10.5281/zenodo.21700238","type":"article-journal","title":"TerraHawk – AI Drone-Based Precision Agriculture System","abstract":"This work presents a farmer-oriented assistant that combines real-time crop detection with knowledge-based agronomic guidance. The system uses a YOLOv5-based computer vision module to detect crops and visually annotate images and videos with bounding boxes and confidence scores. It also features a bilingual chatbot (English/Kannada) that answers specific questions using a curated agricultural knowledge base. The backend is built with Fast API and offers unified REST endpoints for detection, chat, and history. Meanwhile, a React and Vite frontend delivers an interactive user interface for uploading media, viewing annotated results, and chatting with the assistant. From a design perspective, the system features a modular architecture. The detection model is wrapped in a lightweight layer and works with a multi-stage retrieval pipeline. This pipeline uses exact matching, crop-intent keywords, fuzzy token overlap, and semantic embeddings with FAISS. This design ensures strong, low-latency performance on standard hardware. It also lowers the chance of incorrect answers by using template-based response generation and explicit logging. The paper details the overall architecture, reviews related work in crop detection and agricultural decision support, and compares the proposed crop detection subsystem to traditional and modern machine learning methods. The discussion covers strengths, limitations, and design trade-offs, especially regarding deployment challenges, extensibility, and suitability for smallholder farming contexts.","author":[{"family":"Daniel","given":"EJ"},{"family":"Hr","given":"Harshavardhan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21700238","URL":"https://doi.org/10.5281/zenodo.21700238","source":"datacite"},{"id":"doi:10.5281/zenodo.19860823","type":"article-journal","title":"Multi-Model Plant Disease Classification Framework Using Deep Learning and Machine Learning","abstract":"The timely and precise diagnosis of plant diseases is important in improving the yield of crops, reducing economic losses as well as sustainable agricultural production. The paper postulates a multi-model plant disease classification system, which combines deep learning-based image classification with machine learning-based tabular data analysis in enhancing the dependability of detecting the disease. The suggested framework is also unlike traditional models that use a single prediction method by pooling predictions of heterogeneous models that enhance confidence of determining the presence of a disease. It concentrates on rice, potato, and sugarcane crops with the use of the leaf images in classifying the disease and the environment characteristics in forecasting the presence of the disease. To classify rice diseases, a MobileNetV2 is trained using the images of leaves, and the classifier divides the rice diseases into three categories, with 100 percent classification accuracy. The EfficientNetB0 is used in the classification of potato and sugarcane disease with an accuracy of 98 and 97 percent respectively of the disease category. Besides the image-based models, LightGBM classifier is also trained on tabular data in terms of temperature, humidity, rainfall and soil pH, to determine the presence of a disease with an accuracy rate of 86%. The last framework combines the predictions of both the deep learning and machine learning prediction models to enhance the likelihood of making the correct choices of identifying disease instead of a single modality. The findings indicate that the integration of environmental data and image data improves the robustness and provides better-classification of plant diseases that can be used in real-world agriculture.","author":[{"family":"Muthuvel","given":"S"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19860823","URL":"https://doi.org/10.5281/zenodo.19860823","source":"datacite"},{"id":"doi:10.5281/zenodo.19860824","type":"article-journal","title":"Multi-Model Plant Disease Classification Framework Using Deep Learning and Machine Learning","abstract":"The timely and precise diagnosis of plant diseases is important in improving the yield of crops, reducing economic losses as well as sustainable agricultural production. The paper postulates a multi-model plant disease classification system, which combines deep learning-based image classification with machine learning-based tabular data analysis in enhancing the dependability of detecting the disease. The suggested framework is also unlike traditional models that use a single prediction method by pooling predictions of heterogeneous models that enhance confidence of determining the presence of a disease. It concentrates on rice, potato, and sugarcane crops with the use of the leaf images in classifying the disease and the environment characteristics in forecasting the presence of the disease. To classify rice diseases, a MobileNetV2 is trained using the images of leaves, and the classifier divides the rice diseases into three categories, with 100 percent classification accuracy. The EfficientNetB0 is used in the classification of potato and sugarcane disease with an accuracy of 98 and 97 percent respectively of the disease category. Besides the image-based models, LightGBM classifier is also trained on tabular data in terms of temperature, humidity, rainfall and soil pH, to determine the presence of a disease with an accuracy rate of 86%. The last framework combines the predictions of both the deep learning and machine learning prediction models to enhance the likelihood of making the correct choices of identifying disease instead of a single modality. The findings indicate that the integration of environmental data and image data improves the robustness and provides better-classification of plant diseases that can be used in real-world agriculture.","author":[{"family":"Muthuvel","given":"S"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19860824","URL":"https://doi.org/10.5281/zenodo.19860824","source":"datacite"},{"id":"doi:10.5281/zenodo.21578133","type":"article-journal","title":"Agriculture Drone-Based Solution for Crop Spraying and Wild Animal Deterrence","abstract":"Agriculture faces major challenges such as inefficient pesticide application and crop damage caused by wild animals. This paper presents the design and implementation of a multifunctional unmanned aerial vehicle (UAV) for precision crop spraying and wild animal deterrence. The proposed system integrates GPS-based navigation, an automated spraying mechanism, and a deterrence unit that uses sound and light signals to repel animals without causing harm. The drone ensures uniform distribution of agrochemicals, reduces farmers' direct exposure to pesticides, and lowers labor requirements and operational costs. Experimental field testing demonstrated improved spraying efficiency, better coverage accuracy, and effective deterrence of wild animals. The developed system offers a sustainable, safe, and cost-effective solution for modern smart agriculture.","author":[{"family":"Kangne","given":"Krushna"},{"family":"Kolhe","given":"Yash"},{"family":"Gaikwad","given":"Harshal"},{"family":"Labhade","given":"Aditya"},{"family":"Kothawade","given":"VE"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21578133","URL":"https://doi.org/10.5281/zenodo.21578133","source":"datacite"},{"id":"doi:10.5281/zenodo.21578134","type":"article-journal","title":"Agriculture Drone-Based Solution for Crop Spraying and Wild Animal Deterrence","abstract":"Agriculture faces major challenges such as inefficient pesticide application and crop damage caused by wild animals. This paper presents the design and implementation of a multifunctional unmanned aerial vehicle (UAV) for precision crop spraying and wild animal deterrence. The proposed system integrates GPS-based navigation, an automated spraying mechanism, and a deterrence unit that uses sound and light signals to repel animals without causing harm. The drone ensures uniform distribution of agrochemicals, reduces farmers' direct exposure to pesticides, and lowers labor requirements and operational costs. Experimental field testing demonstrated improved spraying efficiency, better coverage accuracy, and effective deterrence of wild animals. The developed system offers a sustainable, safe, and cost-effective solution for modern smart agriculture.","author":[{"family":"Kangne","given":"Krushna"},{"family":"Kolhe","given":"Yash"},{"family":"Gaikwad","given":"Harshal"},{"family":"Labhade","given":"Aditya"},{"family":"Kothawade","given":"VE"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21578134","URL":"https://doi.org/10.5281/zenodo.21578134","source":"datacite"},{"id":"doi:10.5281/zenodo.20531863","type":"article-journal","title":"Next-Generation Technology Adoption for Food & Agri Sustainability Toward Safer Food: An Indian Perspective","abstract":"15 Next-Generation Technology Adoption for Food & Agri Sustainability Toward Safer Food: An Indian Perspective Sweta Singh1*, Niraj Kumar2, Kunal Singh3 1Faculty, State institute of Food processing and technology, Lucknow (U.P) 2Faculty of Engineering & Technology, MGCGV, Chitrakoot Satna (M.P) 3Assistant professor, Shri Ramswaroop memorial university, Barabanki (U.P) *Corresponding Email.id: swetasingh3701@gmail.com DOI : 10.5281/zenodo.20531864 Abstract Indi’s food system is undergoing a rapid digital and green transformation. Next-generation technologies AI/ML, IoT sensors, drones, satellite/remote sensing, biosensors, blockchain traceability, and sustainable cold-chain offer practical pathways to raise productivity, cut post-harvest losses, reduce chemical footprints, and assure food safety. This chapter synthesizes India’s policy and regulatory context (FSSAI, Eat Right India, FoSCoS), major technology building blocks (AgriStack/Digital Public Infrastructure, smart farming, precision input management, rapid testing, and traceability), and field-level enablers (clusters, training, financing). It proposes a step-wise adoption roadmap for Indian stakeholders from smallholders to FPOs and MSME food businesses along with measurable indicators and guardrails for data governance, inclusion, and climate resilience. The chapter concludes with India-specific recommendations to scale safe, sustainable, and trusted food from “soil to plate.” Keywords: AgriStack; cold chain; traceability; natural farming; precision agriculture; post-harvest losses","author":[{"family":"Singh","given":"Sweta"},{"family":"Kumar","given":"Niraj"},{"family":"Singh","given":"Kunal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531863","URL":"https://doi.org/10.5281/zenodo.20531863","source":"datacite"},{"id":"doi:10.5281/zenodo.20531864","type":"article-journal","title":"Next-Generation Technology Adoption for Food & Agri Sustainability Toward Safer Food: An Indian Perspective","abstract":"15 Next-Generation Technology Adoption for Food & Agri Sustainability Toward Safer Food: An Indian Perspective Sweta Singh1*, Niraj Kumar2, Kunal Singh3 1Faculty, State institute of Food processing and technology, Lucknow (U.P) 2Faculty of Engineering & Technology, MGCGV, Chitrakoot Satna (M.P) 3Assistant professor, Shri Ramswaroop memorial university, Barabanki (U.P) *Corresponding Email.id: swetasingh3701@gmail.com DOI : 10.5281/zenodo.20531864 Abstract Indi’s food system is undergoing a rapid digital and green transformation. Next-generation technologies AI/ML, IoT sensors, drones, satellite/remote sensing, biosensors, blockchain traceability, and sustainable cold-chain offer practical pathways to raise productivity, cut post-harvest losses, reduce chemical footprints, and assure food safety. This chapter synthesizes India’s policy and regulatory context (FSSAI, Eat Right India, FoSCoS), major technology building blocks (AgriStack/Digital Public Infrastructure, smart farming, precision input management, rapid testing, and traceability), and field-level enablers (clusters, training, financing). It proposes a step-wise adoption roadmap for Indian stakeholders from smallholders to FPOs and MSME food businesses along with measurable indicators and guardrails for data governance, inclusion, and climate resilience. The chapter concludes with India-specific recommendations to scale safe, sustainable, and trusted food from “soil to plate.” Keywords: AgriStack; cold chain; traceability; natural farming; precision agriculture; post-harvest losses","author":[{"family":"Singh","given":"Sweta"},{"family":"Kumar","given":"Niraj"},{"family":"Singh","given":"Kunal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531864","URL":"https://doi.org/10.5281/zenodo.20531864","source":"datacite"},{"id":"doi:10.17632/xwnvpkpkxk.2","type":"article-journal","title":"A Multi-Stage Maize Leaf Image Dataset for Classification of Spodoptera exigua damage","abstract":"Maize is a crop of paramount importance for global food and feed production, yet its growth is frequently threatened by insect pests. Among these, the beet armyworm (Spodoptera exigua) is a major pest that inflicts severe damage during the seedling stage. Accurate recognition and grading of pest leaf damage are essential for effective precision control. To support the development of intelligent agriculture, we established a field-based image dataset targeting Spodoptera exigua damage on maize leaves. Images were collected under natural light and complex field backgrounds across three critical seedling stages (V4, V6, and V8).","author":[{"family":"Zhong","given":"Chengcheng"},{"family":"Liu","given":"Yichen"},{"family":"Zhang","given":"Zitong"},{"family":"Zhang","given":"Kai"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/xwnvpkpkxk.2","URL":"https://doi.org/10.17632/xwnvpkpkxk.2","source":"datacite"},{"id":"doi:10.17632/xwnvpkpkxk","type":"article-journal","title":"A Multi-Stage Maize Leaf Image Dataset for Classification of Spodoptera exigua damage","abstract":"Maize is a crop of paramount importance for global food and feed production, yet its growth is frequently threatened by insect pests. Among these, the beet armyworm (Spodoptera exigua) is a major pest that inflicts severe damage during the seedling stage. Accurate recognition and grading of pest leaf damage are essential for effective precision control. To support the development of intelligent agriculture, we established a field-based image dataset targeting Spodoptera exigua damage on maize leaves. Images were collected under natural light and complex field backgrounds across three critical seedling stages (V4, V6, and V8).","author":[{"family":"Zhong","given":"Chengcheng"},{"family":"Liu","given":"Yichen"},{"family":"Zhang","given":"Zitong"},{"family":"Zhang","given":"Kai"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/xwnvpkpkxk","URL":"https://doi.org/10.17632/xwnvpkpkxk","source":"datacite"},{"id":"doi:10.5281/zenodo.19814228","type":"article-journal","title":"Soil Organic Carbon Map - Region of Central Macedonia","abstract":"The dataset provides a regional Soil Organic Carbon (SOC) prediction map for croplands in Central Macedonia, Greece, generated within the ScaleAgData project, which focuses on scaling local agricultural data into regional agri-environmental products . The map was produced using a federated 1D convolutional neural network (CNN) , combining a continental model trained on LUCAS 2018 data with regional refinement while preserving data privacy. Model inputs include a 2024 Sentinel-2 bare soil reflectance composite, derived through multi-temporal filtering (NDVI, NBR2, and scene classification) to isolate bare soil pixels, alongside historical SOC measurements (2018–2024). The output is a continuous raster map at Sentinel-2 spatial resolution, representing SOC distribution across agricultural areas and supporting high-resolution soil monitoring and precision agriculture applications.","author":[{"family":"Ampas","given":"Haris"},{"family":"Chadoulos","given":"Christos"},{"family":"Karyotis","given":"Konstantinos"},{"family":"Zalidis","given":"George"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19814228","URL":"https://doi.org/10.5281/zenodo.19814228","source":"datacite"},{"id":"doi:10.5281/zenodo.19814229","type":"article-journal","title":"Soil Organic Carbon Map - Region of Central Macedonia","abstract":"The dataset provides a regional Soil Organic Carbon (SOC) prediction map for croplands in Central Macedonia, Greece, generated within the ScaleAgData project, which focuses on scaling local agricultural data into regional agri-environmental products . The map was produced using a federated 1D convolutional neural network (CNN) , combining a continental model trained on LUCAS 2018 data with regional refinement while preserving data privacy. Model inputs include a 2024 Sentinel-2 bare soil reflectance composite, derived through multi-temporal filtering (NDVI, NBR2, and scene classification) to isolate bare soil pixels, alongside historical SOC measurements (2018–2024). The output is a continuous raster map at Sentinel-2 spatial resolution, representing SOC distribution across agricultural areas and supporting high-resolution soil monitoring and precision agriculture applications.","author":[{"family":"Ampas","given":"Haris"},{"family":"Chadoulos","given":"Christos"},{"family":"Karyotis","given":"Konstantinos"},{"family":"Zalidis","given":"George"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19814229","URL":"https://doi.org/10.5281/zenodo.19814229","source":"datacite"},{"id":"doi:10.5281/zenodo.20531052","type":"article-journal","title":"Biochar and Soil Carbon Management","abstract":"07 Biochar and Soil Carbon Management Arpita Mishra1, Hirak Banerjee1, Sushree Panda2 1Bidhan Chadra Krishi Viswavidyalaya, Department of Agronomy, Nadia, West Bengal. 2Kalinga Institute of Social Sciences, Department of Natural Farming, Bhubaneswar, Odisha. Corresponding author email: arpita.mishra206@gmail.com DOI : 10.5281/zenodo.20531053 Abstract The escalating global population exerts immense pressure on agricultural systems, necessitating innovative strategies to ensure food security. The increasing demand, along with unsustainable agricultural methods and the widespread application of agrochemicals, has resulted in a notable deterioration of soil fertility and overall ecosystem health. Consequently, modern agriculture faces the dual challenge of increasing productivity per unit area sustainably to meet caloric demands and addressing the detrimental impacts of climate change on soil health and agricultural output. Therefore, there exists a pressing necessity to enhance agricultural productivity while concurrently ensuring environmental sustainability. Central to these objectives is the maintenance of an optimal level of organic matter, which is essential for safeguarding the physical, chemical, and biological health of the soil, supporting sustained agricultural output, while simultaneously ensuring ecological balance. Biochar, a stable carbon-rich material produced from organic residues via pyrolysis, emerges as a holistic solution that synergistically integrates these goals. Its application to agricultural soils boosts soil organic carbon stocks, improves nutrient retention, and enhances water-holding capacity—factors crucial for the resilience and productivity of next-generation farming systems. As a long-term carbon sink, biochar supports climate mitigation by sequestering atmospheric CO₂ for centuries and reducing emissions of potent greenhouse gases like methane and nitrous oxide. Unlocking biochar's potential entails collective developments in smart agriculture, such as precision application technology, legislative incentives, and community engagement customized to local conditions. Adopting biochar-based soil carbon management creates a virtuous loop by converting agricultural waste into a regenerative input, restoring agroecosystem health, and contributing to a climate-resilient, sustainable food future. This book chapter dives into the application of biochar in fostering efficient crop and soil carbon management with an eye toward a sustainable future. Key words: Biochar, soil carbon management, sustainable agriculture, soil health.","author":[{"family":"Mishra","given":"Arpita"},{"family":"Banerjee","given":"Hirak"},{"family":"Panda","given":"Sushree"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531052","URL":"https://doi.org/10.5281/zenodo.20531052","source":"datacite"},{"id":"doi:10.5281/zenodo.20531053","type":"article-journal","title":"Biochar and Soil Carbon Management","abstract":"07 Biochar and Soil Carbon Management Arpita Mishra1, Hirak Banerjee1, Sushree Panda2 1Bidhan Chadra Krishi Viswavidyalaya, Department of Agronomy, Nadia, West Bengal. 2Kalinga Institute of Social Sciences, Department of Natural Farming, Bhubaneswar, Odisha. Corresponding author email: arpita.mishra206@gmail.com DOI : 10.5281/zenodo.20531053 Abstract The escalating global population exerts immense pressure on agricultural systems, necessitating innovative strategies to ensure food security. The increasing demand, along with unsustainable agricultural methods and the widespread application of agrochemicals, has resulted in a notable deterioration of soil fertility and overall ecosystem health. Consequently, modern agriculture faces the dual challenge of increasing productivity per unit area sustainably to meet caloric demands and addressing the detrimental impacts of climate change on soil health and agricultural output. Therefore, there exists a pressing necessity to enhance agricultural productivity while concurrently ensuring environmental sustainability. Central to these objectives is the maintenance of an optimal level of organic matter, which is essential for safeguarding the physical, chemical, and biological health of the soil, supporting sustained agricultural output, while simultaneously ensuring ecological balance. Biochar, a stable carbon-rich material produced from organic residues via pyrolysis, emerges as a holistic solution that synergistically integrates these goals. Its application to agricultural soils boosts soil organic carbon stocks, improves nutrient retention, and enhances water-holding capacity—factors crucial for the resilience and productivity of next-generation farming systems. As a long-term carbon sink, biochar supports climate mitigation by sequestering atmospheric CO₂ for centuries and reducing emissions of potent greenhouse gases like methane and nitrous oxide. Unlocking biochar's potential entails collective developments in smart agriculture, such as precision application technology, legislative incentives, and community engagement customized to local conditions. Adopting biochar-based soil carbon management creates a virtuous loop by converting agricultural waste into a regenerative input, restoring agroecosystem health, and contributing to a climate-resilient, sustainable food future. This book chapter dives into the application of biochar in fostering efficient crop and soil carbon management with an eye toward a sustainable future. Key words: Biochar, soil carbon management, sustainable agriculture, soil health.","author":[{"family":"Mishra","given":"Arpita"},{"family":"Banerjee","given":"Hirak"},{"family":"Panda","given":"Sushree"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531053","URL":"https://doi.org/10.5281/zenodo.20531053","source":"datacite"},{"id":"doi:10.5281/zenodo.21608306","type":"article-journal","title":"A Study of Clinical Image Segmentation Using Deep Learning Methods","abstract":"Rapidly, deep learning approaches have emerged as the go-to approach for assessing medical picture segmentation. The basic ideas of this study is to apply on picture segmentation , along with an analysis of various contributions made to the deep learning medical field, covering main common problems that have been published recently. In remote sensing applications such as precision agriculture and urban planning, deep learning-based image segmentation has proven effective in segmenting satellite images. Additionally, Deep Learning algorithm has been used to segment photos taken by drones (UAVs), giving a chance to solve the environmental issues associated with warming. Deep learning research can be used a different type of tasks, like as object detection, image's classification, segmentation, and registration. First, an overview of deep learning frameworks, applications, and methodologies is given. The best uses for deep learning techniques are briefly described. According to this study, there has been prior experience with several methods in the medical image segmentation class limited classification accuracy, limited segmentation resolution, and poor picture enhancement are just a few of the issues in medical image analysis that deep learning has been developed to address. In order to address these current problems and enhance the development of medical image segmentation challenges, we offer recommendations for further study.","author":[{"family":"Srivastava","given":"Anshu"},{"family":"Chandra","given":"Abhishek"},{"family":"Zaidi","given":"Abid"},{"family":"Sonker","given":"Akshay"},{"family":"Dwivedi","given":"Shashank"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21608306","URL":"https://doi.org/10.5281/zenodo.21608306","source":"datacite"},{"id":"doi:10.5281/zenodo.21608307","type":"article-journal","title":"A Study of Clinical Image Segmentation Using Deep Learning Methods","abstract":"Rapidly, deep learning approaches have emerged as the go-to approach for assessing medical picture segmentation. The basic ideas of this study is to apply on picture segmentation , along with an analysis of various contributions made to the deep learning medical field, covering main common problems that have been published recently. In remote sensing applications such as precision agriculture and urban planning, deep learning-based image segmentation has proven effective in segmenting satellite images. Additionally, Deep Learning algorithm has been used to segment photos taken by drones (UAVs), giving a chance to solve the environmental issues associated with warming. Deep learning research can be used a different type of tasks, like as object detection, image's classification, segmentation, and registration. First, an overview of deep learning frameworks, applications, and methodologies is given. The best uses for deep learning techniques are briefly described. According to this study, there has been prior experience with several methods in the medical image segmentation class limited classification accuracy, limited segmentation resolution, and poor picture enhancement are just a few of the issues in medical image analysis that deep learning has been developed to address. In order to address these current problems and enhance the development of medical image segmentation challenges, we offer recommendations for further study.","author":[{"family":"Srivastava","given":"Anshu"},{"family":"Chandra","given":"Abhishek"},{"family":"Zaidi","given":"Abid"},{"family":"Sonker","given":"Akshay"},{"family":"Dwivedi","given":"Shashank"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21608307","URL":"https://doi.org/10.5281/zenodo.21608307","source":"datacite"},{"id":"doi:10.5281/zenodo.21606952","type":"article-journal","title":"Target Detection by Optimizing Anomaly Detection in Hyperspectral Image Processing using AI/ML","abstract":"Anomaly detection in hyperspectral images involves identifying deviations or outliers within the high-dimensional spectral data captured across numerous contiguous wavelength bands. Hyperspectral imaging provides detailed spectral information, making it a powerful tool for detecting subtle variations in materials or objects that are not visible in traditional imaging techniques. The proposed system employs advanced machine learning techniques, including convolutional neural networks (CNNs) and autoencoders, to analyse hyperspectral images for anomalies. By training the models on a dataset of normal hyperspectral images, the system learns the inherent spectral characteristics and identifies patterns of typical data. New hyperspectral data is then analysed to detect deviations that may indicate potential anomalies. This approach is particularly effective in applications such as remote sensing, environmental monitoring, precision agriculture, mineral exploration, and quality control, where detecting anomalies like land degradation, crop stress, or material defects is crucial.","author":[{"family":"Selvam","given":"MM"},{"family":"Ansar","given":"Shaik"},{"family":"Praveen","given":"Moramreddy"},{"family":"Sireesha","given":"Akula"},{"family":"Surekha","given":"Padarthi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21606952","URL":"https://doi.org/10.5281/zenodo.21606952","source":"datacite"},{"id":"doi:10.5281/zenodo.21606953","type":"article-journal","title":"Target Detection by Optimizing Anomaly Detection in Hyperspectral Image Processing using AI/ML","abstract":"Anomaly detection in hyperspectral images involves identifying deviations or outliers within the high-dimensional spectral data captured across numerous contiguous wavelength bands. Hyperspectral imaging provides detailed spectral information, making it a powerful tool for detecting subtle variations in materials or objects that are not visible in traditional imaging techniques. The proposed system employs advanced machine learning techniques, including convolutional neural networks (CNNs) and autoencoders, to analyse hyperspectral images for anomalies. By training the models on a dataset of normal hyperspectral images, the system learns the inherent spectral characteristics and identifies patterns of typical data. New hyperspectral data is then analysed to detect deviations that may indicate potential anomalies. This approach is particularly effective in applications such as remote sensing, environmental monitoring, precision agriculture, mineral exploration, and quality control, where detecting anomalies like land degradation, crop stress, or material defects is crucial.","author":[{"family":"Selvam","given":"MM"},{"family":"Ansar","given":"Shaik"},{"family":"Praveen","given":"Moramreddy"},{"family":"Sireesha","given":"Akula"},{"family":"Surekha","given":"Padarthi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21606953","URL":"https://doi.org/10.5281/zenodo.21606953","source":"datacite"},{"id":"doi:10.5281/zenodo.21606279","type":"article-journal","title":"Strom Impact Assessment on Banana Plantation Using  Deep Learning","abstract":"The project focuses on storm impact assessment on banana plantations using deep learning and image processing techniques. It leverages drone-acquired images to perform semantic segmentation to identify damaged and undamaged regions within the plantation. A pre-trained DeepLabV3 model with a ResNet-50 backbone is fine-tuned for this purpose. The segmented images are analyzed to count standing and fallen trees, estimate yield loss, and assess overall plantation health. To enhance accuracy, the approach integrates machine learning algorithms such as Cross-Entropy Loss, Adam Optimizer, and Connected Component Analysis. The system offers a fast, automated, and scalable solution for precision agriculture, enabling timely decision-making and disaster recovery planning.","author":[{"family":"Wale","given":"Devaki"},{"family":"Mali","given":"Prajakta"},{"family":"Darade","given":"Snehal"},{"family":"Ghadage","given":"Janahvi"},{"family":"Misal","given":"Nikita"},{"family":"Doshi","given":"PS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21606279","URL":"https://doi.org/10.5281/zenodo.21606279","source":"datacite"},{"id":"doi:10.5281/zenodo.21606280","type":"article-journal","title":"Strom Impact Assessment on Banana Plantation Using  Deep Learning","abstract":"The project focuses on storm impact assessment on banana plantations using deep learning and image processing techniques. It leverages drone-acquired images to perform semantic segmentation to identify damaged and undamaged regions within the plantation. A pre-trained DeepLabV3 model with a ResNet-50 backbone is fine-tuned for this purpose. The segmented images are analyzed to count standing and fallen trees, estimate yield loss, and assess overall plantation health. To enhance accuracy, the approach integrates machine learning algorithms such as Cross-Entropy Loss, Adam Optimizer, and Connected Component Analysis. The system offers a fast, automated, and scalable solution for precision agriculture, enabling timely decision-making and disaster recovery planning.","author":[{"family":"Wale","given":"Devaki"},{"family":"Mali","given":"Prajakta"},{"family":"Darade","given":"Snehal"},{"family":"Ghadage","given":"Janahvi"},{"family":"Misal","given":"Nikita"},{"family":"Doshi","given":"PS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21606280","URL":"https://doi.org/10.5281/zenodo.21606280","source":"datacite"},{"id":"doi:10.5281/zenodo.20737262","type":"article-journal","title":"GOOGLE EARTH ENGINE (GEE): INTEGRATING VEGETATION INDICES FOR AGRICULTURAL AND FOREST  MONITORING","abstract":"Google Earth Engine (GEE) provides a fast, scalable, and cost-effective cloud computing platform for sustainable agriculture and effective forest management. This study uses the GEE cloud platform and Copernicus Sentinel-2 data for timely and accurate vegetation monitoring, crop health assessment, and canopy dynamics tracking. Traditional field monitoring methods are time-consuming and limited in spatial coverage. To address this, we processed Sentinel-2 multispectral imagery to generate cloud-free composite images and calculated ten key vegetation indices, including NDVI, EVI, NDMI, and others (GNDVI, NDWI, NDRE, RENDVI, SAVI, MSAVI, and NDMSI). The results demonstrate that integrating Earth observation technologies with cloud computing enhances data-driven agricultural and environmental decision-making with high spatial and temporal precision.","author":[{"family":"Nepali","given":"Sujan"},{"family":"Thapa","given":"Jiya"},{"family":"Thapa","given":"Narayan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20737262","URL":"https://doi.org/10.5281/zenodo.20737262","source":"datacite"},{"id":"doi:10.5281/zenodo.20737263","type":"article-journal","title":"GOOGLE EARTH ENGINE (GEE): INTEGRATING VEGETATION INDICES FOR AGRICULTURAL AND FOREST  MONITORING","abstract":"Google Earth Engine (GEE) provides a fast, scalable, and cost-effective cloud computing platform for sustainable agriculture and effective forest management. This study uses the GEE cloud platform and Copernicus Sentinel-2 data for timely and accurate vegetation monitoring, crop health assessment, and canopy dynamics tracking. Traditional field monitoring methods are time-consuming and limited in spatial coverage. To address this, we processed Sentinel-2 multispectral imagery to generate cloud-free composite images and calculated ten key vegetation indices, including NDVI, EVI, NDMI, and others (GNDVI, NDWI, NDRE, RENDVI, SAVI, MSAVI, and NDMSI). The results demonstrate that integrating Earth observation technologies with cloud computing enhances data-driven agricultural and environmental decision-making with high spatial and temporal precision.","author":[{"family":"Nepali","given":"Sujan"},{"family":"Thapa","given":"Jiya"},{"family":"Thapa","given":"Narayan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20737263","URL":"https://doi.org/10.5281/zenodo.20737263","source":"datacite"},{"id":"doi:10.5281/zenodo.21549416","type":"article-journal","title":"Revolutionizing Agricultural Machinery: The Role of AI, IoT, and Renewable Energy in Enhancing Efficiency and Sustainability","abstract":"Modern agriculture has seen tremendous development using AI, IoT, and renewable energy, enhancing efficiency and sustainability to tackle resource scarcity, climate change, and food security. AI enables precision farming through autonomous machinery and predictive analytics, optimizing soil health, crop yields, and pest control. IoT integrates sensors and drones to monitor soil moisture, weather, and equipment in real-time, cutting water use by 30% and improving fuel efficiency. Renewable solutions like solar irrigation, biofuels, and electric machinery reduce fossil fuel dependence, lowering emissions. Synergistically, AI optimizes energy use in solar-powered systems, while IoT devices, powered by renewables, enable remote monitoring. Challenges of high costs, infrastructure gaps, and technical barriers, like demand policy support, training, and investment. Together, these innovations promise resilient, resource-efficient agriculture, balancing productivity with planetary health to ensure sustainable food security.","author":[{"family":"Balai","given":"Pritam"},{"family":"Sheikh","given":"Asaruddin"},{"family":"Rabha","given":"Garima"},{"family":"Das","given":"Samiran"},{"family":"Kuli","given":"Bhaba"},{"family":"Raj","given":"Mohit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21549416","URL":"https://doi.org/10.5281/zenodo.21549416","source":"datacite"},{"id":"doi:10.5281/zenodo.21549417","type":"article-journal","title":"Revolutionizing Agricultural Machinery: The Role of AI, IoT, and Renewable Energy in Enhancing Efficiency and Sustainability","abstract":"Modern agriculture has seen tremendous development using AI, IoT, and renewable energy, enhancing efficiency and sustainability to tackle resource scarcity, climate change, and food security. AI enables precision farming through autonomous machinery and predictive analytics, optimizing soil health, crop yields, and pest control. IoT integrates sensors and drones to monitor soil moisture, weather, and equipment in real-time, cutting water use by 30% and improving fuel efficiency. Renewable solutions like solar irrigation, biofuels, and electric machinery reduce fossil fuel dependence, lowering emissions. Synergistically, AI optimizes energy use in solar-powered systems, while IoT devices, powered by renewables, enable remote monitoring. Challenges of high costs, infrastructure gaps, and technical barriers, like demand policy support, training, and investment. Together, these innovations promise resilient, resource-efficient agriculture, balancing productivity with planetary health to ensure sustainable food security.","author":[{"family":"Balai","given":"Pritam"},{"family":"Sheikh","given":"Asaruddin"},{"family":"Rabha","given":"Garima"},{"family":"Das","given":"Samiran"},{"family":"Kuli","given":"Bhaba"},{"family":"Raj","given":"Mohit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21549417","URL":"https://doi.org/10.5281/zenodo.21549417","source":"datacite"},{"id":"doi:10.5281/zenodo.21547902","type":"article-journal","title":"Early Identification and Classification of High-Impact Cotton Plant Diseases through IoT","abstract":"Cotton, often referred to as \"white gold,\" is one of India's most critical cash crops, forming the backbone of both the agricultural and textile sectors. However, despite its economic significance, cotton cultivation is increasingly threatened by the emergence of severe plant diseases such as Bacterial Blight, Cotton Leaf Curl Virus (CLCuV), and Fusarium Wilt. These diseases not only diminish yield but also exacerbate rural distress, especially in drought-prone regions like Marathwada, Maharashtra. This research explores the biological characteristics and economic impact of these diseases, reviews conventional and advanced detection methods, and proposes a hybrid technological framework involving IoT sensors and Convolutional Neural Networks (CNN) for early disease diagnosis. With real-time monitoring, image-based classification, and predictive analytics, this model aims to empower farmers, reduce production losses, and promote sustainable cotton farming practices.","author":[{"family":"Shaikh","given":"Farooque"},{"family":"Bansod","given":"Nagsen"},{"family":"Kadam","given":"Anand"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21547902","URL":"https://doi.org/10.5281/zenodo.21547902","source":"datacite"},{"id":"doi:10.5281/zenodo.21547903","type":"article-journal","title":"Early Identification and Classification of High-Impact Cotton Plant Diseases through IoT","abstract":"Cotton, often referred to as \"white gold,\" is one of India's most critical cash crops, forming the backbone of both the agricultural and textile sectors. However, despite its economic significance, cotton cultivation is increasingly threatened by the emergence of severe plant diseases such as Bacterial Blight, Cotton Leaf Curl Virus (CLCuV), and Fusarium Wilt. These diseases not only diminish yield but also exacerbate rural distress, especially in drought-prone regions like Marathwada, Maharashtra. This research explores the biological characteristics and economic impact of these diseases, reviews conventional and advanced detection methods, and proposes a hybrid technological framework involving IoT sensors and Convolutional Neural Networks (CNN) for early disease diagnosis. With real-time monitoring, image-based classification, and predictive analytics, this model aims to empower farmers, reduce production losses, and promote sustainable cotton farming practices.","author":[{"family":"Shaikh","given":"Farooque"},{"family":"Bansod","given":"Nagsen"},{"family":"Kadam","given":"Anand"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21547903","URL":"https://doi.org/10.5281/zenodo.21547903","source":"datacite"},{"id":"doi:10.5281/zenodo.21546579","type":"article-journal","title":"A Review of Artificial Intelligence Techniques for Cotton Leaf Disease Identification","abstract":"Cotton is one of the most important cash crops worldwide, and its productivity is severely affected by leaf diseases that reduce yield and fiber quality. Traditional disease identification methods rely on expert knowledge and manual inspection, which are time-consuming, subjective, and often impractical for large-scale agricultural monitoring. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated, accurate, and scalable cotton leaf disease identification using image-based analysis. This review comprehensively analyzes state-of-the-art AI techniques employed for cotton leaf disease detection and classification. It covers conventional image processing approaches, handcrafted feature-based machine learning models, and modern deep learning architecture such as convolutional neural networks, transformers, ensemble learning, and explainable AI frameworks. Additionally, the role of publicly available datasets, data augmentation, lightweight models, and resource-efficient architectures is discussed. By synthesizing findings from recent literature, this review highlights key research trends, performance improvements, and practical limitations of existing approaches. The paper also identifies critical challenges and future research directions to support the development of robust, interpretable, and deployable AI-based systems for precision cotton agriculture.","author":[{"family":"Patel","given":"Toral"},{"family":"Degadwala","given":"Sheshang"},{"family":"Soni","given":"Dharvi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21546579","URL":"https://doi.org/10.5281/zenodo.21546579","source":"datacite"},{"id":"doi:10.5281/zenodo.21546580","type":"article-journal","title":"A Review of Artificial Intelligence Techniques for Cotton Leaf Disease Identification","abstract":"Cotton is one of the most important cash crops worldwide, and its productivity is severely affected by leaf diseases that reduce yield and fiber quality. Traditional disease identification methods rely on expert knowledge and manual inspection, which are time-consuming, subjective, and often impractical for large-scale agricultural monitoring. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated, accurate, and scalable cotton leaf disease identification using image-based analysis. This review comprehensively analyzes state-of-the-art AI techniques employed for cotton leaf disease detection and classification. It covers conventional image processing approaches, handcrafted feature-based machine learning models, and modern deep learning architecture such as convolutional neural networks, transformers, ensemble learning, and explainable AI frameworks. Additionally, the role of publicly available datasets, data augmentation, lightweight models, and resource-efficient architectures is discussed. By synthesizing findings from recent literature, this review highlights key research trends, performance improvements, and practical limitations of existing approaches. The paper also identifies critical challenges and future research directions to support the development of robust, interpretable, and deployable AI-based systems for precision cotton agriculture.","author":[{"family":"Patel","given":"Toral"},{"family":"Degadwala","given":"Sheshang"},{"family":"Soni","given":"Dharvi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21546580","URL":"https://doi.org/10.5281/zenodo.21546580","source":"datacite"},{"id":"doi:10.5281/zenodo.21412129","type":"article-journal","title":"SMART HYDROPHOONIC AUTOMATION SYSTEM","abstract":"The Smart Hydroponics Automation System is an innovative agricultural solution based on the Internet of Things that makes it possible to cultivate without soil with more precision, efficiency, and sustainability. This system makes use of multiple sensors such as the soil moisture sensor, water level sensor, and DHT11 to continuously monitor important environmental variables like the level of nutrient solution, humidity, and temperature. A microcontroller processes the collected sensor data and displays the real-time readings on an LCD screen for local surveillance To ensure intelligent automated control, the system incorporates a relay module that based on predetermined thresholds, controls the switching of water pumps, motors for nutrient dosing, and cooling or aeration devices. When sensor readings indicate unfavorable conditions, the relay. The connected electrical components are automatically turned ON or OFF to maintain optimal plant growth. Due to its battery-powered operation, the system is suitable for agricultural settings that are off-grid or remote. Additionally, the IoT-enabled cloud application provides remote access to live sensor data, historical analysis, notifications, and manual control of the hydroponics setup through a handheld device This makes real-time decision-making more efficient while reducing manual intervention. The system ensures precise operation through wireless monitoring, relay-based switching, and automated control. nutrient delivery, reduced water wastage, consistent plant health, and improved yield. Overall, the smart Using a hydroponics system, you can find a long-term, low-cost, and cutting-edge answer to today's agriculture challenges by combining IoT, automation, and relay-based control mechanisms.","author":[{"family":"Pramod"},{"family":"Vijaylaxmi"},{"family":"Kavya"},{"family":"Kiran","given":"KV"},{"family":"Suprit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21412129","URL":"https://doi.org/10.5281/zenodo.21412129","source":"datacite"},{"id":"doi:10.5281/zenodo.21412130","type":"article-journal","title":"SMART HYDROPHOONIC AUTOMATION SYSTEM","abstract":"The Smart Hydroponics Automation System is an innovative agricultural solution based on the Internet of Things that makes it possible to cultivate without soil with more precision, efficiency, and sustainability. This system makes use of multiple sensors such as the soil moisture sensor, water level sensor, and DHT11 to continuously monitor important environmental variables like the level of nutrient solution, humidity, and temperature. A microcontroller processes the collected sensor data and displays the real-time readings on an LCD screen for local surveillance To ensure intelligent automated control, the system incorporates a relay module that based on predetermined thresholds, controls the switching of water pumps, motors for nutrient dosing, and cooling or aeration devices. When sensor readings indicate unfavorable conditions, the relay. The connected electrical components are automatically turned ON or OFF to maintain optimal plant growth. Due to its battery-powered operation, the system is suitable for agricultural settings that are off-grid or remote. Additionally, the IoT-enabled cloud application provides remote access to live sensor data, historical analysis, notifications, and manual control of the hydroponics setup through a handheld device This makes real-time decision-making more efficient while reducing manual intervention. The system ensures precise operation through wireless monitoring, relay-based switching, and automated control. nutrient delivery, reduced water wastage, consistent plant health, and improved yield. Overall, the smart Using a hydroponics system, you can find a long-term, low-cost, and cutting-edge answer to today's agriculture challenges by combining IoT, automation, and relay-based control mechanisms.","author":[{"family":"Pramod"},{"family":"Vijaylaxmi"},{"family":"Kavya"},{"family":"Kiran","given":"KV"},{"family":"Suprit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21412130","URL":"https://doi.org/10.5281/zenodo.21412130","source":"datacite"},{"id":"doi:10.5281/zenodo.20375393","type":"article-journal","title":"Development of Machine Learning Models for Predicting Nitrogen Deficiency Levels in Rice Crop","abstract":"Development of Machine Learning Models for Predicting Nitrogen Deficiency Levels in Rice Crop Lwekiza Nelson Ndiwaita1, Kadeghe Goodluck Fue2, Mawazo J Shitindi3 1 Sokoine University of Agriculture, College of Agriculture, Department of Crop Science and Horticulture, P. O. Box 3005, Chuo-Kikuu, Morogoro, Tanzania. 2 Department of Agricultural Engineering, School of Engineering and Technology, Sokoine University of Agriculture, Morogoro, Tanzania. 3 Sokoine University of Agriculture, Department of Soil and Geological Sciences, College of Agriculture, P. O. Box 3008, Chuo-Kikuu, Morogoro, Tanzania. *Corresponding author. E-mail: lwekizandiwaita@gmail.com 3.1 Abstract This research paper develops machine learning models, specifically CNN architectures, to predict nitrogen deficiency levels in rice crops using RGB and NDVI imagery from field experiments in Tanzania. It evaluates models like MobileNetV3-Large and EfficientNetV2-S, achieving up to 75.3% accuracy on RGB data, addressing challenges in precision agriculture for smallholder farmers. The paper focuses on classifying four nitrogen treatment levels (0%, 50%, 100%, 150% of the recommended rate) in rice variety SARO 5 at Sokoine University of Agriculture. RGB imagery from GoPro Hero 10 and NDVI from Mapir Survey3 cameras were collected at multiple growth stages (40-90 DAP). Experiments used a randomized complete block design with controlled nitrogen applications via urea. Images underwent preprocessing (resizing, augmentation) before training seven pretrained CNNs with transfer learning. Performance metrics included accuracy, precision, recall, F1-score, confusion matrices, and t-SNE visualizations. MobileNetV3-Large topped RGB accuracy at 75.3%, tying EfficientNetV2-S on NDVI at 73.45%; RGB slightly outperformed NDVI overall. T0 (zero nitrogen) was easiest to classify, while T1 (50%) was most challenging due to spectral overlap. EfficientNetV2-S showed superior precision and training stability, recommending both for farmer tools Keywords: Nitrogen deficiency, rice crop, convolutional neural network, NDVI, RGB imagery, deep learning, Tanzania, precision agriculture","author":[{"family":"Fue","given":"Kadeghe"},{"family":"Shitindi","given":"Mawazo"},{"family":"Ndiwaita","given":"Lwekiza"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20375393","URL":"https://doi.org/10.5281/zenodo.20375393","source":"datacite"},{"id":"doi:10.5281/zenodo.20375394","type":"article-journal","title":"Development of Machine Learning Models for Predicting Nitrogen Deficiency Levels in Rice Crop","abstract":"Development of Machine Learning Models for Predicting Nitrogen Deficiency Levels in Rice Crop Lwekiza Nelson Ndiwaita1, Kadeghe Goodluck Fue2, Mawazo J Shitindi3 1 Sokoine University of Agriculture, College of Agriculture, Department of Crop Science and Horticulture, P. O. Box 3005, Chuo-Kikuu, Morogoro, Tanzania. 2 Department of Agricultural Engineering, School of Engineering and Technology, Sokoine University of Agriculture, Morogoro, Tanzania. 3 Sokoine University of Agriculture, Department of Soil and Geological Sciences, College of Agriculture, P. O. Box 3008, Chuo-Kikuu, Morogoro, Tanzania. *Corresponding author. E-mail: lwekizandiwaita@gmail.com 3.1 Abstract This research paper develops machine learning models, specifically CNN architectures, to predict nitrogen deficiency levels in rice crops using RGB and NDVI imagery from field experiments in Tanzania. It evaluates models like MobileNetV3-Large and EfficientNetV2-S, achieving up to 75.3% accuracy on RGB data, addressing challenges in precision agriculture for smallholder farmers. The paper focuses on classifying four nitrogen treatment levels (0%, 50%, 100%, 150% of the recommended rate) in rice variety SARO 5 at Sokoine University of Agriculture. RGB imagery from GoPro Hero 10 and NDVI from Mapir Survey3 cameras were collected at multiple growth stages (40-90 DAP). Experiments used a randomized complete block design with controlled nitrogen applications via urea. Images underwent preprocessing (resizing, augmentation) before training seven pretrained CNNs with transfer learning. Performance metrics included accuracy, precision, recall, F1-score, confusion matrices, and t-SNE visualizations. MobileNetV3-Large topped RGB accuracy at 75.3%, tying EfficientNetV2-S on NDVI at 73.45%; RGB slightly outperformed NDVI overall. T0 (zero nitrogen) was easiest to classify, while T1 (50%) was most challenging due to spectral overlap. EfficientNetV2-S showed superior precision and training stability, recommending both for farmer tools Keywords: Nitrogen deficiency, rice crop, convolutional neural network, NDVI, RGB imagery, deep learning, Tanzania, precision agriculture","author":[{"family":"Fue","given":"Kadeghe"},{"family":"Shitindi","given":"Mawazo"},{"family":"Ndiwaita","given":"Lwekiza"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20375394","URL":"https://doi.org/10.5281/zenodo.20375394","source":"datacite"},{"id":"doi:10.5281/zenodo.19547095","type":"article-journal","title":"Global Research Trends in Irrigation and Water Availability Dataset 2000–2024 A Scientometric Analysis","abstract":"This dataset provides a curated collection of bibliographic records used in a scientometric analysis of global research trends in irrigation and water availability from 2000 to 2024. The dataset was developed to support the study entitled “Global research trends in irrigation and water availability using scientometric analysis for sustainable water management”. The data were retrieved from two major international scientific databases, Web of Science and Scopus, ensuring broad coverage of peer-reviewed literature. A structured Boolean search strategy was applied to identify publications at the intersection of irrigation practices, water resource management, and water availability, with emphasis on topics such as water use efficiency and precision agriculture. The dataset includes cleaned and standardized bibliographic metadata, such as authors, article titles, abstracts, keywords, publication year, journal names, citation counts, digital object identifiers (DOI), and country information (when available). Data processing involved merging records from different sources, removing duplicates, and harmonizing metadata using the Bibliometrix package in R. This dataset enables the replication of the scientometric analysis presented in the associated study and can be reused for further research on water resources, irrigation systems, sustainability, and global scientific collaboration networks. It is particularly relevant for studies addressing water security, climate change impacts on agriculture, and Sustainable Development Goal 6 (Clean Water and Sanitation). The dataset is provided in CSV format and accompanied by documentation describing the data structure, variables, and methodological procedures. Related Publication:Assane, C., Rodrigues, A. M., Rubio Neto, A., & da Silva Júnior, É. D. Global Research Trends in Irrigation and Water Availability: A Scientometric Analysis for Water Security and Sustainable Management. (under review) Notes:The dataset includes only English-language peer-reviewed articles and review papers indexed in Web of Science and Scopus databases. Other document types and regional databases were not included in this version.","author":[{"family":"Assane","given":"Célsio"},{"family":"De Melo Rodrigues","given":"Andriane"},{"family":"Rubio Neto","given":"Aurélio"},{"family":"Damásio Da Silva Júnior","given":"Édio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19547095","URL":"https://doi.org/10.5281/zenodo.19547095","source":"datacite"},{"id":"doi:10.5281/zenodo.19547096","type":"article-journal","title":"Global Research Trends in Irrigation and Water Availability Dataset 2000–2024 A Scientometric Analysis","abstract":"This dataset provides a curated collection of bibliographic records used in a scientometric analysis of global research trends in irrigation and water availability from 2000 to 2024. The dataset was developed to support the study entitled “Global research trends in irrigation and water availability using scientometric analysis for sustainable water management”. The data were retrieved from two major international scientific databases, Web of Science and Scopus, ensuring broad coverage of peer-reviewed literature. A structured Boolean search strategy was applied to identify publications at the intersection of irrigation practices, water resource management, and water availability, with emphasis on topics such as water use efficiency and precision agriculture. The dataset includes cleaned and standardized bibliographic metadata, such as authors, article titles, abstracts, keywords, publication year, journal names, citation counts, digital object identifiers (DOI), and country information (when available). Data processing involved merging records from different sources, removing duplicates, and harmonizing metadata using the Bibliometrix package in R. This dataset enables the replication of the scientometric analysis presented in the associated study and can be reused for further research on water resources, irrigation systems, sustainability, and global scientific collaboration networks. It is particularly relevant for studies addressing water security, climate change impacts on agriculture, and Sustainable Development Goal 6 (Clean Water and Sanitation). The dataset is provided in CSV format and accompanied by documentation describing the data structure, variables, and methodological procedures. Related Publication:Assane, C., Rodrigues, A. M., Rubio Neto, A., & da Silva Júnior, É. D. Global Research Trends in Irrigation and Water Availability: A Scientometric Analysis for Water Security and Sustainable Management. (under review) Notes:The dataset includes only English-language peer-reviewed articles and review papers indexed in Web of Science and Scopus databases. Other document types and regional databases were not included in this version.","author":[{"family":"Assane","given":"Célsio"},{"family":"De Melo Rodrigues","given":"Andriane"},{"family":"Rubio Neto","given":"Aurélio"},{"family":"Damásio Da Silva Júnior","given":"Édio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19547096","URL":"https://doi.org/10.5281/zenodo.19547096","source":"datacite"},{"id":"doi:10.48550/arxiv.2608.11053","type":"manuscript","title":"A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa","abstract":"The application of computer vision in agriculture has shown significant potential for improving crop monitoring and precision farming. However, many existing approaches rely on controlled datasets that do not adequately represent realworld farming conditions, particularly in underrepresented regions such as Africa. This study presents a comparative evaluation of six object detection models YOLOv5, YOLOv8, YOLO11, YOLO26, Faster R-CNN, and RT-DETR using a real-world dataset, AgriAISeg 1 , collected manually from Nigerian farms. AgriAISeg comprises 3,382 images of sesame, cabbage, and tomato crops captured under varying environmental conditions, including changes in illumination, occlusion, and viewing perspectives. Models were trained, and performance was assessed using precision, recall, mAP@0.5, and mAP@0.5:0.95. The results show that RT-DETR achieved the highest overall performance with a precision of 0.768 and mAP@0.5:0.95 of 0.624, while YOLOv8 and YOLO11 also demonstrated strong and consistent performance. In contrast, Faster R-CNN recorded significantly lower accuracy, with an overall mAP@0.5 of 0.466, indicating reduced effectiveness under complex field conditions. In addition, YOLO-based models exhibited superior training efficiency compared to Faster R-CNN.These findings demonstrate that modern one-stage and transformer-based detectors provide more reliable and efficient solutions for plant detection in realworld agricultural environments.","author":[{"family":"Tijjani","given":"Ismail"},{"family":"Ibrahim","given":"Sunusi"},{"family":"Khaleel","given":"Amina"},{"family":"Akinola","given":"Lanre"},{"family":"Jibrin","given":"Fatima"},{"family":"Aliyu","given":"Muhammad"},{"family":"Dalhat","given":"Abdullahi"},{"family":"Suiudeen","given":"Abdullahi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2608.11053","URL":"https://doi.org/10.48550/arxiv.2608.11053","source":"datacite"},{"id":"doi:10.48550/arxiv.2605.02524","type":"manuscript","title":"A Coupled Physics-Informed Neural Network for Greenhouse Climate State Reconstruction and Parameter Identification under Sparse Sensor Measurements","abstract":"Accurate reconstruction of greenhouse climate variables from sparse sensor measurements is essential for intelligent environmental monitoring, automated climate control, and precision agriculture. In practical greenhouse operation, sensor failures, communication interruptions, calibration drift, and measurement noise frequently result in incomplete observations, making reliable estimation of indoor temperature and relative humidity a challenging inverse problem. This paper presents a coupled physics-informed neural network (PINN) for simultaneous reconstruction of greenhouse temperature and relative humidity and identification of unknown physical parameters governing a reduced greenhouse climate model. The framework integrates measurement data with coupled energy- and moisture-balance equations and initial-condition constraints, enabling climate state estimation and parameter identification within a unified learning framework. The methodology is evaluated using real greenhouse measurements under two validation protocols: random interpolation from sparse observations (Experiment A) and chronological temporal extrapolation over an unseen future interval (Experiment B). The proposed PINN is compared with a fully connected neural network, a long short-term memory (LSTM) network, and a gated recurrent unit (GRU) network. Under interpolation, the proposed PINN achieves the highest temperature reconstruction accuracy with an RMSE of $0.4495\\,^{\\circ}\\mathrm{C}$ and an $R^2$ value of 0.9636, while simultaneously identifying physically interpretable model parameters. The two protocols provide complementary assessments of greenhouse climate reconstruction under interpolation and temporal extrapolation. The proposed framework provides a practical foundation for intelligent greenhouse monitoring, virtual sensing, digital twins, and automated greenhouse climate management.","author":[{"family":"Biswas","given":"Sani"},{"family":"Ansari","given":"Khursheed"},{"family":"Akhtar","given":"Md"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2605.02524","URL":"https://doi.org/10.48550/arxiv.2605.02524","source":"datacite"},{"id":"doi:10.48550/arxiv.2608.07984","type":"manuscript","title":"AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining","abstract":"Field-based agricultural computer vision is important for precision agriculture, yet it largely depends on expensive annotations and costly adaptation of large pretrained models. We introduce AgriField-40K, a field-centric dataset curated from 17 public resources and covering diverse crops, weeds, and field conditions. Building on this, we present AgriMAE, a parameter-efficient continual pretraining baseline that adapts a masked autoencoder pretrained on natural images by training only lightweight adapters. We further explore semantic feature reconstruction as an alternative pretraining objective and evaluate transfer across multiple tasks. AgriMAE consistently improves downstream performance and can match or even outperform full fine-tuning while using up to $9\\times$ fewer trainable parameters, showing that AgriField-40K is a practical resource for continual pretraining in agricultural vision. Project page: https://dtu-pas.github.io/agrifield40k/","author":[{"family":"Tzouras","given":"Vasileios"},{"family":"Pegios","given":"Paraskevas"},{"family":"Nalpantidis","given":"Lazaros"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2608.07984","URL":"https://doi.org/10.48550/arxiv.2608.07984","source":"datacite"},{"id":"doi:10.5281/zenodo.20690806","type":"article-journal","title":"An IOT-Driven Smart Agriculture Framework for Precision Farming, Resource Optimization, and Crop Health Monitoring","abstract":"Abstract The integration of the Internet of Things (IoT) into agriculture is revolutionizing the way food is produced, managed, and distributed. By combining networks of smart sensors, advanced communication protocols, distributed computing, and artificial intelligence (AI), IoT-based smart farming systems allow for precision monitoring and management of agricultural resources. These systems enable farmers to optimize irrigation, monitor crop health, and make real-time, data-driven decisions, thereby addressing challenges such as water scarcity, climate variability, and the growing demand for food. This paper presents an expanded IoT-driven smart agriculture framework with modular architecture, incorporating a perception layer, network layer, compute layer, application layer, and end-user layer. The framework integrates AI-based predictive analytics, blockchain for supply chain transparency, and renewable energy-powered devices. A pilot implementation on a 5-hectare wheat farm demonstrated a 30% reduction in water usage, early disease detection accuracy of 92%, and improved scalability for multi-crop environments. Comparative analysis with conventional farming practices shows significant improvements in resource efficiency and operational sustainability. The paper provides a detailed literature review, system design, experimental methodology, and future research directions, with a focus on interoperability, cost-effectiveness, and sustainability.","author":[{"family":"Irfan","given":"Engr"},{"family":"Zaka","given":"Engr"},{"family":"Rehman","given":"Engr"},{"family":"Sattar","given":"Bushra"},{"family":"Haider","given":"Syed"},{"family":"Hayat","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.20690806","URL":"https://doi.org/10.5281/zenodo.20690806","source":"datacite"},{"id":"doi:10.5281/zenodo.20690807","type":"article-journal","title":"An IOT-Driven Smart Agriculture Framework for Precision Farming, Resource Optimization, and Crop Health Monitoring","abstract":"Abstract The integration of the Internet of Things (IoT) into agriculture is revolutionizing the way food is produced, managed, and distributed. By combining networks of smart sensors, advanced communication protocols, distributed computing, and artificial intelligence (AI), IoT-based smart farming systems allow for precision monitoring and management of agricultural resources. These systems enable farmers to optimize irrigation, monitor crop health, and make real-time, data-driven decisions, thereby addressing challenges such as water scarcity, climate variability, and the growing demand for food. This paper presents an expanded IoT-driven smart agriculture framework with modular architecture, incorporating a perception layer, network layer, compute layer, application layer, and end-user layer. The framework integrates AI-based predictive analytics, blockchain for supply chain transparency, and renewable energy-powered devices. A pilot implementation on a 5-hectare wheat farm demonstrated a 30% reduction in water usage, early disease detection accuracy of 92%, and improved scalability for multi-crop environments. Comparative analysis with conventional farming practices shows significant improvements in resource efficiency and operational sustainability. The paper provides a detailed literature review, system design, experimental methodology, and future research directions, with a focus on interoperability, cost-effectiveness, and sustainability.","author":[{"family":"Irfan","given":"Engr"},{"family":"Zaka","given":"Engr"},{"family":"Rehman","given":"Engr"},{"family":"Sattar","given":"Bushra"},{"family":"Haider","given":"Syed"},{"family":"Hayat","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.20690807","URL":"https://doi.org/10.5281/zenodo.20690807","source":"datacite"},{"id":"doi:10.5281/zenodo.20531554","type":"article-journal","title":"Nano-Technology for Modern Agriculture","abstract":"11 Nano-Technology for Modern Agriculture Pooja1, Kinjal Mondal1*, Khaidem Aruna Devi1, Poonam Kumari1, Mamta1 1Department of Molecular Biology and Biotechnology, Maharana Pratap University of Agriculture and Technology, Udaipur-313001, Rajasthan, India Corresponding author: kinjal.mondal1234@gmail.com DOI : 10.5281/zenodo.20531555 Abstract Nanotechnology is coming out as a revolutionary technology in current agriculture with innovative capabilities to boost crop productivity, efficiency in the use of resources and sustainable farming practices. Nanoscale materials and devices utilized in agriculture facilitate precision farming by enabling the targeted delivery of agrochemicals, including fertilizers, pesticides, and herbicides, to specific areas, thereby minimizing environmental contamination and input wastage. Nanoparticles have the potential to enhance nutrient bioavailability, promote plant productivity and increase resistance to both biotic and abiotic stresses. Moreover, nano-sensors offer a real-time measurement of soil health, moisture and plant diseases, which helps in data-driven decision-making. Nano-formulations also help in increasing the shelf life and controlled release of active ingredients, which increases their efficacy and a decrease in frequency of application. Moreover, nanotechnology supports genetic engineering, water purification, and detection of pathogens, which are major issues in food security in the world. Although it has a tremendous potential, the toxicity of nanoparticles, lack of regulation, and environmental effects are issues that warrant extensive risk analyses and the implementation of safe guidelines in the application of these nanoparticles in the environment. Overall, nanotechnology offers a feasible avenue for advancing contemporary agriculture by enhancing efficiency, resilience, and environmental compatibility, therefore aligning with sustainable development and climate-smart agricultural practices. Conducting more research, enhancing regulatory oversight, and collaborating with stakeholders is essential to optimize the benefits of nanotechnology for modern agriculture and mitigate risks associated to it. Keywords: Nanotechnology, precision farming, nanoparticles, nano-sensors","author":[{"family":"Pooja"},{"family":"Mondol","given":"Kinjal"},{"family":"Devi","given":"Aruna"},{"family":"Kumari","given":"Poonam"},{"family":"Mamta"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531554","URL":"https://doi.org/10.5281/zenodo.20531554","source":"datacite"},{"id":"doi:10.5281/zenodo.20531555","type":"article-journal","title":"Nano-Technology for Modern Agriculture","abstract":"11 Nano-Technology for Modern Agriculture Pooja1, Kinjal Mondal1*, Khaidem Aruna Devi1, Poonam Kumari1, Mamta1 1Department of Molecular Biology and Biotechnology, Maharana Pratap University of Agriculture and Technology, Udaipur-313001, Rajasthan, India Corresponding author: kinjal.mondal1234@gmail.com DOI : 10.5281/zenodo.20531555 Abstract Nanotechnology is coming out as a revolutionary technology in current agriculture with innovative capabilities to boost crop productivity, efficiency in the use of resources and sustainable farming practices. Nanoscale materials and devices utilized in agriculture facilitate precision farming by enabling the targeted delivery of agrochemicals, including fertilizers, pesticides, and herbicides, to specific areas, thereby minimizing environmental contamination and input wastage. Nanoparticles have the potential to enhance nutrient bioavailability, promote plant productivity and increase resistance to both biotic and abiotic stresses. Moreover, nano-sensors offer a real-time measurement of soil health, moisture and plant diseases, which helps in data-driven decision-making. Nano-formulations also help in increasing the shelf life and controlled release of active ingredients, which increases their efficacy and a decrease in frequency of application. Moreover, nanotechnology supports genetic engineering, water purification, and detection of pathogens, which are major issues in food security in the world. Although it has a tremendous potential, the toxicity of nanoparticles, lack of regulation, and environmental effects are issues that warrant extensive risk analyses and the implementation of safe guidelines in the application of these nanoparticles in the environment. Overall, nanotechnology offers a feasible avenue for advancing contemporary agriculture by enhancing efficiency, resilience, and environmental compatibility, therefore aligning with sustainable development and climate-smart agricultural practices. Conducting more research, enhancing regulatory oversight, and collaborating with stakeholders is essential to optimize the benefits of nanotechnology for modern agriculture and mitigate risks associated to it. Keywords: Nanotechnology, precision farming, nanoparticles, nano-sensors","author":[{"family":"Pooja"},{"family":"Mondol","given":"Kinjal"},{"family":"Devi","given":"Aruna"},{"family":"Kumari","given":"Poonam"},{"family":"Mamta"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20531555","URL":"https://doi.org/10.5281/zenodo.20531555","source":"datacite"},{"id":"doi:10.5281/zenodo.21868051","type":"article-journal","title":"Smart Fields and Green Futures: India's Agri-Tech Transformation  and Sustainability in Digital Era","abstract":"Indian agriculture, the backbone of country's economy, has passed through different phases like the pre-independence agrarian system, post-independence reforms, Green Revolution, and the current era of precision agriculture based on integration of digital technologies and sustainable use of resources. Indian agriculture is undergoing a fundamental shift, transforming from traditional, labor-intensive farming to data-driven, adaptive agri-tech farming. This review traces that evolutionary trajectory, with special emphasis on Artificial Intelligence (AI) as the engine of the next agricultural transformation. Integrating advanced agricultural technologies like drones, remote sensing, Geographic Information Systems (GIS), Internet of Things (IoT), machine learning, deep learning, robotics, blockchain, cloud computing, and big data analysis are revolutionizing the site-specific crop production, disease diagnosis, weather forecasting, etc. These innovations facilitate the data-driven decisions, more efficient and sustainable use of resources, cost reduction, enhanced yield and climate resilience leading towards smart fields and greener future. This review synthesizes recent literature and policy documents to structure India's agri-tech transformation into national digital public infrastructure, including the Digital Agriculture Mission and AgriStack; precision farming technologies such as IoT, remote sensing and machine learning; digital agricultural marketing and financial inclusion, exemplified by the electronic National Agricultural Market (e-NAM); and climate-resilient, sustainable agriculture enabled by digital decision-support tools. Results show that although digital adoption has accelerated rapidly since 2021, gaps in digital proficiency, rural connectivity, data governance and smallholder affordability remain persistent barriers to equitable outcomes. Thus, there is a need of actionable policy measures to promote agri-tech adoption in India to ensure that technological growth is in sync with environmental sustainability and livelihood security.","author":[{"family":"Haider"},{"family":"Aprajita","given":"Raj"},{"family":"Dharmendra K","given":"Janghel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21868051","URL":"https://doi.org/10.5281/zenodo.21868051","source":"datacite"},{"id":"doi:10.5281/zenodo.21868052","type":"article-journal","title":"Smart Fields and Green Futures: India's Agri-Tech Transformation  and Sustainability in Digital Era","abstract":"Indian agriculture, the backbone of country's economy, has passed through different phases like the pre-independence agrarian system, post-independence reforms, Green Revolution, and the current era of precision agriculture based on integration of digital technologies and sustainable use of resources. Indian agriculture is undergoing a fundamental shift, transforming from traditional, labor-intensive farming to data-driven, adaptive agri-tech farming. This review traces that evolutionary trajectory, with special emphasis on Artificial Intelligence (AI) as the engine of the next agricultural transformation. Integrating advanced agricultural technologies like drones, remote sensing, Geographic Information Systems (GIS), Internet of Things (IoT), machine learning, deep learning, robotics, blockchain, cloud computing, and big data analysis are revolutionizing the site-specific crop production, disease diagnosis, weather forecasting, etc. These innovations facilitate the data-driven decisions, more efficient and sustainable use of resources, cost reduction, enhanced yield and climate resilience leading towards smart fields and greener future. This review synthesizes recent literature and policy documents to structure India's agri-tech transformation into national digital public infrastructure, including the Digital Agriculture Mission and AgriStack; precision farming technologies such as IoT, remote sensing and machine learning; digital agricultural marketing and financial inclusion, exemplified by the electronic National Agricultural Market (e-NAM); and climate-resilient, sustainable agriculture enabled by digital decision-support tools. Results show that although digital adoption has accelerated rapidly since 2021, gaps in digital proficiency, rural connectivity, data governance and smallholder affordability remain persistent barriers to equitable outcomes. Thus, there is a need of actionable policy measures to promote agri-tech adoption in India to ensure that technological growth is in sync with environmental sustainability and livelihood security.","author":[{"family":"Haider"},{"family":"Aprajita","given":"Raj"},{"family":"Dharmendra K","given":"Janghel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21868052","URL":"https://doi.org/10.5281/zenodo.21868052","source":"datacite"},{"id":"doi:10.48550/arxiv.2608.06404","type":"manuscript","title":"UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys","abstract":"Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and management response. Modern 3D reconstruction methods perform strongly on generic benchmarks, but rendered appearance may not translate into metrically and agronomically useful geometry in crop fields. We introduce UAV3DCrop, a public benchmark of repeated multi-angle unmanned aerial vehicle (UAV) crop surveys. It contains 88,830 RGB images at $5280 \\times 3956$ pixels, with a ground sampling distance of 3.6-5.8 mm, from 91 scenes spanning corn, soybean, wheat, and oat. Track A evaluates seven scene-optimized methods -- Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) variants -- on held-out views, photogrammetry-referenced depth, and canopy-height recovery. Track B tests four pretrained feed-forward models on zero-shot camera-pose and geometry estimation. The scene-optimized methods rank differently across the three targets: Splatfacto-big leads appearance, whereas Scaffold-GS leads depth and is statistically tied with Splatfacto for canopy height. Among feed-forward models, MapAnything leads on seven of the eight metrics, while the remaining models vary more across crops and fail severely on absolute scale in a way that alignment conceals. Repeated acquisitions reveal further sensitivities that differ by output type and by model, associated with position within the acquisition sequence and with tie-point multiplicity. Current 3D reconstruction methods are therefore not yet interchangeable for agronomic use: no single method wins on appearance, geometry, and canopy height at once, and only one of four feed-forward models recovers usable metric scale. The dataset is publicly available at https://link-dev.github.io/UAV3DCrop/","author":[{"family":"Zhou","given":"Junxiong"},{"family":"Li","given":"Xuechen"},{"family":"Qiu","given":"Chonghao"},{"family":"Qiao","given":"Lang"},{"family":"Jia","given":"Xiaowei"},{"family":"Yang","given":"Qi"},{"family":"Zhang","given":"Chishan"},{"family":"Yin","given":"Leikun"},{"family":"You","given":"Nanshan"},{"family":"Kumar","given":"Vipin"},{"family":"Mulla","given":"David"},{"family":"Yang","given":"Ce"},{"family":"Jin","given":"Zhenong"},{"family":"Liu","given":"Licheng"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2608.06404","URL":"https://doi.org/10.48550/arxiv.2608.06404","source":"datacite"},{"id":"doi:10.5281/zenodo.19641925","type":"article-journal","title":"AI Integrated Smart Farming Platform","abstract":"This work presents an AI Integrated Smart Farming Platform designed to enhance agricultural productivity and sustainability through the use of advanced machine learning and data-driven technologies. The platform integrates multiple components, including crop recommendation, soil analysis, weather prediction, and resource optimization, to support informed decision-making for farmers. The system leverages historical and real-time data to provide intelligent insights such as optimal crop selection, irrigation planning, and yield prediction. By combining artificial intelligence with scalable web technologies, the platform aims to reduce dependency on traditional farming practices and improve efficiency, accuracy, and profitability in agriculture. Additionally, the platform focuses on accessibility and usability, enabling farmers and stakeholders to interact with the system through an intuitive interface. This research contributes to the development of smart agriculture solutions by demonstrating how AI can be effectively applied to address real-world farming challenges and promote sustainable agricultural practices.","author":[{"family":"Gauda","given":"Ganesh"},{"family":"Hingu","given":"Sahil"},{"family":"Deshmukh","given":"Siddhesh"},{"family":"Gupta","given":"Aryan"},{"family":"Gupta","given":"Jahanvi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19641925","URL":"https://doi.org/10.5281/zenodo.19641925","source":"datacite"},{"id":"doi:10.5281/zenodo.19641924","type":"article-journal","title":"AI Integrated Smart Farming Platform","abstract":"This work presents an AI Integrated Smart Farming Platform designed to enhance agricultural productivity and sustainability through the use of advanced machine learning and data-driven technologies. The platform integrates multiple components, including crop recommendation, soil analysis, weather prediction, and resource optimization, to support informed decision-making for farmers. The system leverages historical and real-time data to provide intelligent insights such as optimal crop selection, irrigation planning, and yield prediction. By combining artificial intelligence with scalable web technologies, the platform aims to reduce dependency on traditional farming practices and improve efficiency, accuracy, and profitability in agriculture. Additionally, the platform focuses on accessibility and usability, enabling farmers and stakeholders to interact with the system through an intuitive interface. This research contributes to the development of smart agriculture solutions by demonstrating how AI can be effectively applied to address real-world farming challenges and promote sustainable agricultural practices.","author":[{"family":"Gauda","given":"Ganesh"},{"family":"Hingu","given":"Sahil"},{"family":"Deshmukh","given":"Siddhesh"},{"family":"Gupta","given":"Aryan"},{"family":"Gupta","given":"Jahanvi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19641924","URL":"https://doi.org/10.5281/zenodo.19641924","source":"datacite"},{"id":"doi:10.5281/zenodo.17246460","type":"article-journal","title":"Artificial Intelligence in Smart Agriculture: Disease Detection and Yield Prediction in Strawberry Cultivation","abstract":"The paper refers to the need for innovative technologies in agriculture due to global population growth and limited natural resources. It highlights smart farming tools such as sensors, robotics, UAVs and artificial intelligence for monitoring crops and improving efficiency. Strawberry cultivation, as a high value and perishable crop, is presented as an ideal case for applying AI technologies. A systematic literature review based on the PRISMA 2020 protocol examined studies from 2015 to 2025 using Scopus and Web of Science. The results show growing interest after 2019, with emphasis on RGB and hyperspectral cameras, soil sensors and AI-based disease detection and yield prediction.","author":[{"family":"Bitakou","given":"Effrosyni"},{"family":"Kotzabasaki","given":"Marianna"},{"family":"Nychas","given":"Konstantinos"},{"family":"Psiroukis","given":"Vasilis"},{"family":"Demestichas","given":"Konstantinos"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.17246460","URL":"https://doi.org/10.5281/zenodo.17246460","source":"datacite"},{"id":"doi:10.5281/zenodo.17246459","type":"article-journal","title":"Artificial Intelligence in Smart Agriculture: Disease Detection and Yield Prediction in Strawberry Cultivation","abstract":"The paper refers to the need for innovative technologies in agriculture due to global population growth and limited natural resources. It highlights smart farming tools such as sensors, robotics, UAVs and artificial intelligence for monitoring crops and improving efficiency. Strawberry cultivation, as a high value and perishable crop, is presented as an ideal case for applying AI technologies. A systematic literature review based on the PRISMA 2020 protocol examined studies from 2015 to 2025 using Scopus and Web of Science. The results show growing interest after 2019, with emphasis on RGB and hyperspectral cameras, soil sensors and AI-based disease detection and yield prediction.","author":[{"family":"Bitakou","given":"Effrosyni"},{"family":"Kotzabasaki","given":"Marianna"},{"family":"Nychas","given":"Konstantinos"},{"family":"Psiroukis","given":"Vasilis"},{"family":"Demestichas","given":"Konstantinos"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.17246459","URL":"https://doi.org/10.5281/zenodo.17246459","source":"datacite"},{"id":"doi:10.5281/zenodo.19439533","type":"article-journal","title":"Integrating New Frontier Digital Twins Technology in Smart Agriculture Revolution","abstract":"The effects of climate change on agriculture are very profound, including food security and the financial stability of developing countries. Thus, Artificial Intelligence (AI), Internet of Things (IoT), and Digital Twins (DTs) are significant in changing agriculture to a data-enabling, real-time system to develop crop management, high productivity, and climate mitigation. Such technologies are useful in predicting the time of droughts and scheduling the irrigation timetable based on climatic changes, and also in deciding on the appropriate crop rotation within a particular area. AI and IoT may be combined to create DTs to facilitate climate-resilient precision farming. This technology embraces agricultural workplaces, livestock surveillance, crop harvesting, crop protection, and predictive maintenance systems. It also changes how agriculture is practised by examining huge amounts of information to predict the impact of climate change. Precision agriculture is an AI-driven technology that uses micro-localised applications, which are informed by synthetic sensory data, drones, and satellite data. Whereas Smart agriculture combines AI, Big Data Analytics, IoT, and DT to collect, unite, and interpret information from many sources. With AI-powered models, future weather conditions, insects, and disease outbreaks are predictable, allowing for early intervention and increased crop production. Such insights culminate in better allocation of resources, optimisation of agricultural activities, and high farm productivity amidst climate change. As a consequence, the DT technology can be a game-changer in the field of agriculture in the future. In this study, DT in conjunction with IoT sensors and AI models has been explained conceptually and potentially as useful in precision agriculture to adjust to the rise in climate change by anticipating droughts, optimising irrigation, and enhancing crop control through real-time data analysis.","author":[{"family":"Jatoi","given":"Imran"},{"family":"Rahu","given":"Mushtaque"},{"family":"Memon","given":"Nimra"},{"family":"Aurangzaib","given":"Muhammad"},{"family":"Oad","given":"Urooj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19439533","URL":"https://doi.org/10.5281/zenodo.19439533","source":"datacite"},{"id":"doi:10.5281/zenodo.19439532","type":"article-journal","title":"Integrating New Frontier Digital Twins Technology in Smart Agriculture Revolution","abstract":"The effects of climate change on agriculture are very profound, including food security and the financial stability of developing countries. Thus, Artificial Intelligence (AI), Internet of Things (IoT), and Digital Twins (DTs) are significant in changing agriculture to a data-enabling, real-time system to develop crop management, high productivity, and climate mitigation. Such technologies are useful in predicting the time of droughts and scheduling the irrigation timetable based on climatic changes, and also in deciding on the appropriate crop rotation within a particular area. AI and IoT may be combined to create DTs to facilitate climate-resilient precision farming. This technology embraces agricultural workplaces, livestock surveillance, crop harvesting, crop protection, and predictive maintenance systems. It also changes how agriculture is practised by examining huge amounts of information to predict the impact of climate change. Precision agriculture is an AI-driven technology that uses micro-localised applications, which are informed by synthetic sensory data, drones, and satellite data. Whereas Smart agriculture combines AI, Big Data Analytics, IoT, and DT to collect, unite, and interpret information from many sources. With AI-powered models, future weather conditions, insects, and disease outbreaks are predictable, allowing for early intervention and increased crop production. Such insights culminate in better allocation of resources, optimisation of agricultural activities, and high farm productivity amidst climate change. As a consequence, the DT technology can be a game-changer in the field of agriculture in the future. In this study, DT in conjunction with IoT sensors and AI models has been explained conceptually and potentially as useful in precision agriculture to adjust to the rise in climate change by anticipating droughts, optimising irrigation, and enhancing crop control through real-time data analysis.","author":[{"family":"Jatoi","given":"Imran"},{"family":"Rahu","given":"Mushtaque"},{"family":"Memon","given":"Nimra"},{"family":"Aurangzaib","given":"Muhammad"},{"family":"Oad","given":"Urooj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19439532","URL":"https://doi.org/10.5281/zenodo.19439532","source":"datacite"},{"id":"doi:10.5281/zenodo.19413425","type":"article-journal","title":"Design and Development of FarmGuard System Based on Microcontroller","abstract":"Microcontroller -Based farmGuard system Agriculture faces frequent crop loss due to the entry of animals and birds into farm fields. Traditional Protection methods such as manual guarding, scarecrows, or simple fencing are often ineffective, time consuming and costly. This Project Proposes a microcontroller-Based farmGuard syste m an automated and low-cost solution made to monitor agricultural land and prevent crop losses. The system uses ESP32 microcontroller as the main control unit connected with sensors to detect unwanted movement near farm boundaries. When birds are detected the system activates actions such as ultrasonic sound, alarm speakers and rotating reflective device to safely scare them away .It can also send real time alerts to farmer through mobile networks. This system helps farmer’s increase crop protection by protecting Plants during important growth stages. It is low-cost, energy-efficient, and can be used on small and large farms.","author":[{"family":"More","given":"Vishakha"},{"family":"Tadakhe","given":"Prachi"},{"family":"Badekar","given":"Shraddha"},{"family":"Mrrrdodake"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19413425","URL":"https://doi.org/10.5281/zenodo.19413425","source":"datacite"},{"id":"doi:10.5281/zenodo.19413424","type":"article-journal","title":"Design and Development of FarmGuard System Based on Microcontroller","abstract":"Microcontroller -Based farmGuard system Agriculture faces frequent crop loss due to the entry of animals and birds into farm fields. Traditional Protection methods such as manual guarding, scarecrows, or simple fencing are often ineffective, time consuming and costly. This Project Proposes a microcontroller-Based farmGuard syste m an automated and low-cost solution made to monitor agricultural land and prevent crop losses. The system uses ESP32 microcontroller as the main control unit connected with sensors to detect unwanted movement near farm boundaries. When birds are detected the system activates actions such as ultrasonic sound, alarm speakers and rotating reflective device to safely scare them away .It can also send real time alerts to farmer through mobile networks. This system helps farmer’s increase crop protection by protecting Plants during important growth stages. It is low-cost, energy-efficient, and can be used on small and large farms.","author":[{"family":"More","given":"Vishakha"},{"family":"Tadakhe","given":"Prachi"},{"family":"Badekar","given":"Shraddha"},{"family":"Mrrrdodake"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19413424","URL":"https://doi.org/10.5281/zenodo.19413424","source":"datacite"},{"id":"doi:10.48550/arxiv.2603.08580","type":"manuscript","title":"SmartGraphical: A Human-in-the-Loop Framework for Detecting Smart Contract Logical Vulnerabilities via Pattern-Driven Static Analysis and Visual Abstraction","abstract":"Smart contracts are fundamental components of blockchain ecosystems; however, their security remains a critical concern due to inherent vulnerabilities. While existing detection methodologies are predominantly syntax-oriented, targeting reentrancy and arithmetic errors, they often overlook logical flaws arising from defective business logic. This paper introduces SmartGraphical, a novel security framework specifically engineered to identify logical attack surfaces. By synthesizing automated static analysis with an interactive graphical representation of contract architectures, SmartGraphical facilitates a comprehensive inspection of a contract's functional control flow. To mitigate the context-dependent nature of logical bugs, the tool adopts a human-in-the-loop approach, empowering developers to interpret heuristic warnings within a visualized structural context. The efficacy of SmartGraphical was validated through a rigorous empirical evaluation involving a large dataset of real-world contracts and a large-scale user study with 100 developers of varying expertise. Furthermore, the framework's performance was demonstrated through case studies on high-profile exploits, such as the SYFI rebase failure and farming protocol flash swap attacks, proving that SmartGraphical identifies intricate vulnerabilities that elude state-of-the-art automated detectors. Our findings indicate that this hybrid methodology significantly enhances the interpretability and detection rate of non-trivial logical security threats in smart contracts.","author":[{"family":"Fattahdizaji","given":"Ali"},{"family":"Pishdar","given":"Mohammad"},{"family":"Shukur","given":"Zarina"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2603.08580","URL":"https://doi.org/10.48550/arxiv.2603.08580","source":"datacite"},{"id":"doi:10.6084/m9.figshare.28755101","type":"article-journal","title":"AGRICULTURA INTELIGENTE (<i>SMART FARMING</i>): UM CONCEITO DE GESTÃO HOLÍSTICA DE PESSOAS, RECURSOS NATURAIS, USO DA TERRA, BIODIVERSIDADE E SISTEMAS DE PRODUÇÃO SUSTENTÁVEL DE ALIMENTOS","abstract":"Nos últimos anos, o rápido desenvolvimento econômico levou a um aumento da população, e as mudanças associadas na estrutura de consumo e concentração populacional nos megacentros urbanos trouxeram impacto e desenvolvimento sem precedentes no uso da terra cultivada. Essa transformação nas formas espaciais, como a quantidade e a estrutura da terra cultivada, e adaptação do sistema de cultivo, modo de manejo e capacidade de produção. O setor agrícola está muito atrás de outros setores na taxa de aceitação tecnológica para automação e controle de sistemas agrícolas. A maioria das práticas agrícolas ultrapassadas ou convencionais mal alcançou o efeito desejado em relação ao rendimento maximizado ou ao custo mínimo de produção. Cientistas e formuladores de políticas classificam a agricultura inteligente como uma solução ganha-ganha para diversos desafios, como produtividade agrícola, segurança alimentar global e impactos ambientais da agricultura. Assim, inspecionar a decisão de adotar a tecnologia agrícola ganhou interesse entre os estudiosos nas últimas décadas. Por exemplo, do ponto de vista das nações desenvolvidas, algumas tecnologias foram examinadas e os fatores de aceitação foram determinados. No entanto, a compreensão do fenômeno é necessária para promover a adoção de alta tecnologia em diferentes sistemas agrícolas.","author":[{"family":"Agapito","given":"Luiz"},{"family":"Vanhaverbeke","given":"Wim"},{"family":"Mahdad","given":"Maral"},{"family":"Weil","given":"Steffi"},{"family":"Sarries","given":"Gabriel"},{"family":"Furlan","given":"Gustavo"},{"family":"Patriani","given":"Tainá"}],"issued":{"date-parts":[[2025]]},"DOI":"10.6084/m9.figshare.28755101","URL":"https://doi.org/10.6084/m9.figshare.28755101","source":"datacite"},{"id":"doi:10.5281/zenodo.19217392","type":"article-journal","title":"Livestock Monitoring System Using IOT","abstract":"This paper presents an IoT-based livestock monitoring system designed to improve animal health management through real-time tracking and smart technology. The system continuously monitors important health indicators such as body temperature, heart rate, and environmental conditions like humidity. Sensors attached to the animals collect data and send it to a microcontroller, which processes the information efficiently. The processed data is transmitted to a cloud platform using wireless communication. Farmers can easily access live updates through a mobile application from anywhere. If any unusual changes in health parameters are detected, the system immediately sends alert notifications. This enables quick response and helps prevent serious diseases. The solution reduces the need for constant manual supervision on farms. It also helps maintain digital records for better long-term analysis. By providing early detection and timely action, the system reduces livestock loss and improves productivity. The use of IoT technology makes farm management more organized and data-driven. Overall, the proposed system offers a practical and cost-effective approach to modern livestock farming.","author":[{"family":"Patil","given":"Dr"},{"family":"Ghadage","given":"Aditi"},{"family":"Mulani","given":"Muskan"},{"family":"Patil","given":"Sakshi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19217392","URL":"https://doi.org/10.5281/zenodo.19217392","source":"datacite"},{"id":"doi:10.5281/zenodo.19217391","type":"article-journal","title":"Livestock Monitoring System Using IOT","abstract":"This paper presents an IoT-based livestock monitoring system designed to improve animal health management through real-time tracking and smart technology. The system continuously monitors important health indicators such as body temperature, heart rate, and environmental conditions like humidity. Sensors attached to the animals collect data and send it to a microcontroller, which processes the information efficiently. The processed data is transmitted to a cloud platform using wireless communication. Farmers can easily access live updates through a mobile application from anywhere. If any unusual changes in health parameters are detected, the system immediately sends alert notifications. This enables quick response and helps prevent serious diseases. The solution reduces the need for constant manual supervision on farms. It also helps maintain digital records for better long-term analysis. By providing early detection and timely action, the system reduces livestock loss and improves productivity. The use of IoT technology makes farm management more organized and data-driven. Overall, the proposed system offers a practical and cost-effective approach to modern livestock farming.","author":[{"family":"Patil","given":"Dr"},{"family":"Ghadage","given":"Aditi"},{"family":"Mulani","given":"Muskan"},{"family":"Patil","given":"Sakshi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19217391","URL":"https://doi.org/10.5281/zenodo.19217391","source":"datacite"},{"id":"doi:10.26188/31847401","type":"article-journal","title":"Trusted sources of advice in carbon farming and emissions management: Insights for building trust to support change","abstract":"This report presents the findings of a project that investigated farmers’ trusted sources of advice on emissions management and carbon farming through a qualitative research design, including individual consultations with 49 farmers and 22 advisers across different States and farm types, and a review of peer reviewed literature on farmers’ trust in advice related to climate-smart/net zero agriculture.We found that farmers’ engagement with emissions management and carbon farming varies widely from actively involved to skeptical. Many farmers are in an information seeking phase rather than actively seeking advice for implementation. Those in this phase want to ask questions and have those questions answered through independent sources. We also identify how trusted sources of advice are aligned to different decisions in carbon farming and emissions management. They include independent (fee-for-service) agronomists, consultants, research institutions, state government agencies, farmer organisations, local natural resource management (NRM) or Landcare groups, industry organisations and carbon project companies. Trust in advice or information sources was influenced by three main factors:• perceived independence• scientific backing/expertise• practical farming experience and understanding of local conditions.Trust was also linked to an alignment in values between the adviser/advisory organisation and the farmer, and long-term farmer-adviser relationships. See full report for details","author":[{"family":"Nettle","given":"Ruth"},{"family":"Kenny","given":"Sean"},{"family":"Reichelt","given":"Nicole"},{"family":"Major","given":"Jason"},{"family":"Tang","given":"Yidan"},{"family":"Ting Valerie Neui","given":"Yu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.26188/31847401","URL":"https://doi.org/10.26188/31847401","source":"datacite"},{"id":"doi:10.26188/31847401.v1","type":"article-journal","title":"Trusted sources of advice in carbon farming and emissions management: Insights for building trust to support change","abstract":"This report presents the findings of a project that investigated farmers’ trusted sources of advice on emissions management and carbon farming through a qualitative research design, including individual consultations with 49 farmers and 22 advisers across different States and farm types, and a review of peer reviewed literature on farmers’ trust in advice related to climate-smart/net zero agriculture.We found that farmers’ engagement with emissions management and carbon farming varies widely from actively involved to skeptical. Many farmers are in an information seeking phase rather than actively seeking advice for implementation. Those in this phase want to ask questions and have those questions answered through independent sources. We also identify how trusted sources of advice are aligned to different decisions in carbon farming and emissions management. They include independent (fee-for-service) agronomists, consultants, research institutions, state government agencies, farmer organisations, local natural resource management (NRM) or Landcare groups, industry organisations and carbon project companies. Trust in advice or information sources was influenced by three main factors:• perceived independence• scientific backing/expertise• practical farming experience and understanding of local conditions.Trust was also linked to an alignment in values between the adviser/advisory organisation and the farmer, and long-term farmer-adviser relationships. See full report for details","author":[{"family":"Nettle","given":"Ruth"},{"family":"Kenny","given":"Sean"},{"family":"Reichelt","given":"Nicole"},{"family":"Major","given":"Jason"},{"family":"Tang","given":"Yidan"},{"family":"Ting Valerie Neui","given":"Yu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.26188/31847401.v1","URL":"https://doi.org/10.26188/31847401.v1","source":"datacite"},{"id":"doi:10.5281/zenodo.18953134","type":"article-journal","title":"Agriculture 6.0: Leveraging AI, IoT, Machine Learning, and Blockchain for a Sustainable Future","abstract":"The Internet of Things (IoT) and smart computing technologies have transformed every facet of the twenty-first century. There are numerous applications for these technologies, ranging from real-time crop conditions, water quality, and soil moisture monitoring to the use of drones to support responsibilities like bug application. An era of agriculture 6.0, sometimes referred to as sustainable and smart agriculture, has been ushered in by the broad integration of modern Information Technology (IT) and traditional agriculture. Smart agriculture addresses automation and intelligence in agriculture. However, information security issues cannot be ignored, given how contemporary digital technology has advanced agriculture. The article starts by giving a summary of the advantages, disadvantages, and difficulties of agriculture's progress from 1.0 to 6.0. In addition to identifying problems and presenting the demands and future opportunities in agriculture, this study concentrated on layered architectural design. Furthermore, we suggested a thorough overview for agriculture 1.0–6.0 that incorporates fog computing, blockchain technology, IoT, AI, ML, and software-defined networking.","author":[{"family":"Rahu","given":"Mushtaque"},{"family":"Khilji","given":"Waqas"},{"family":"Ayaz","given":"Azeem"},{"family":"Memon","given":"Sanjha"},{"family":"Jatoi","given":"Imran"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18953134","URL":"https://doi.org/10.5281/zenodo.18953134","source":"datacite"},{"id":"doi:10.5281/zenodo.18999795","type":"article-journal","title":"Agriculture 6.0: Leveraging AI, IoT, Machine Learning, and Blockchain for a Sustainable Future","abstract":"The Internet of Things (IoT) and smart computing technologies have transformed every facet of the twenty-first century. There are numerous applications for these technologies, ranging from real-time crop conditions, water quality, and soil moisture monitoring to the use of drones to support responsibilities like bug application. An era of agriculture 6.0, sometimes referred to as sustainable and smart agriculture, has been ushered in by the broad integration of modern Information Technology (IT) and traditional agriculture. Smart agriculture addresses automation and intelligence in agriculture. However, information security issues cannot be ignored, given how contemporary digital technology has advanced agriculture. The article starts by giving a summary of the advantages, disadvantages, and difficulties of agriculture's progress from 1.0 to 6.0. In addition to identifying problems and presenting the demands and future opportunities in agriculture, this study concentrated on layered architectural design. Furthermore, we suggested a thorough overview for agriculture 1.0–6.0 that incorporates fog computing, blockchain technology, IoT, AI, ML, and software-defined networking.","author":[{"family":"Rahu","given":"Mushtaque"},{"family":"Khilji","given":"Waqas"},{"family":"Ayaz","given":"Azeem"},{"family":"Memon","given":"Sanjha"},{"family":"Jatoi","given":"Imran"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18999795","URL":"https://doi.org/10.5281/zenodo.18999795","source":"datacite"},{"id":"doi:10.5281/zenodo.19059616","type":"article-journal","title":"Design and Implementation of an Automated Poultry Farm System","abstract":"Automation in poultry farming is crucial to satisfy the increasing demand for eggs while maintaining quality, hygiene, and cost-effectiveness. Conventional poultry farming techniques demand ongoing manual supervision of environmental and operational factors like temperature, humidity, lighting, feeding, watering, and egg harvesting. This document details the creation and implementation of a Smart Egg Poultry Farm Automation System featuring automated feed delivery, water management, egg gathering, gas monitoring, and environmental regulation. The system employs sensors, microcontrollers, mechanical transmission systems, and solar energy assistance to establish a semi-automated poultry facility. The testing of the prototype showed acceptable performance and enhanced productivity.","author":[{"family":"Kharat","given":"Aditya"},{"family":"Bagal","given":"Rahul"},{"family":"Patil","given":"Akshay"},{"family":"Thorat","given":"Pranav"},{"family":"Patil","given":"Ajinkya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19059616","URL":"https://doi.org/10.5281/zenodo.19059616","source":"datacite"},{"id":"doi:10.5281/zenodo.19059617","type":"article-journal","title":"Design and Implementation of an Automated Poultry Farm System","abstract":"Automation in poultry farming is crucial to satisfy the increasing demand for eggs while maintaining quality, hygiene, and cost-effectiveness. Conventional poultry farming techniques demand ongoing manual supervision of environmental and operational factors like temperature, humidity, lighting, feeding, watering, and egg harvesting. This document details the creation and implementation of a Smart Egg Poultry Farm Automation System featuring automated feed delivery, water management, egg gathering, gas monitoring, and environmental regulation. The system employs sensors, microcontrollers, mechanical transmission systems, and solar energy assistance to establish a semi-automated poultry facility. The testing of the prototype showed acceptable performance and enhanced productivity.","author":[{"family":"Kharat","given":"Aditya"},{"family":"Bagal","given":"Rahul"},{"family":"Patil","given":"Akshay"},{"family":"Thorat","given":"Pranav"},{"family":"Patil","given":"Ajinkya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19059617","URL":"https://doi.org/10.5281/zenodo.19059617","source":"datacite"},{"id":"doi:10.5281/zenodo.18978811","type":"article-journal","title":"Smart Fencing System for Protecting Farming Land","abstract":"Abstract: In today’s world the entire farming sectors has facing serious security challenges since long in context with in the from animal intrusion. As the development is going on, the incidents of theft and damage in farming land increases because of human jealousy. In the world of modernization, the traditional fencing system has also steps towards the smart electrical fencing system, which is based on automation. The couplement of IoT (Internet of Things), A.I (Artificial Intelligence) and ML (Machine Learning) has proven a dynamic shift in securing farm land. The SAPS (Stand Alone Power Supply) produce electric energy from RES (Renewable Energy Source). The integration of electronics devices with these technologies make this smart security an upper advantage in this segment. The devices or instruments that leverages the system are intelligent sensors, communication modules system, different types of cameras (day night mode of operation), hooters, lighting system, automatically trigger alarms. In addition to this, the system should have face recognizer system so that it can recognize invaders or restrict unauthorized entry. The smart fencing must put generate electric shock and warms the invaders. The smart farming system must send alert the farmers via mobile application or sms. This smart solution not only strengthens the safety of crops and livestock but also reduces the need for manual patrolling, thereby promoting sustainable and efficient farm management. The proposed system offers a cost-effective and scalable approach to securing rural properties using modern technology. Thus, it protect the farmer land in their absence and work as quick responder.","author":[{"family":"Sahwal","given":"Amod"},{"family":"Bhanjadeo","given":"Subhashree"},{"family":"Virnave","given":"Shantanu"},{"family":"Soni","given":"Kunal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18978811","URL":"https://doi.org/10.5281/zenodo.18978811","source":"datacite"},{"id":"doi:10.5281/zenodo.18978810","type":"article-journal","title":"Smart Fencing System for Protecting Farming Land","abstract":"Abstract: In today’s world the entire farming sectors has facing serious security challenges since long in context with in the from animal intrusion. As the development is going on, the incidents of theft and damage in farming land increases because of human jealousy. In the world of modernization, the traditional fencing system has also steps towards the smart electrical fencing system, which is based on automation. The couplement of IoT (Internet of Things), A.I (Artificial Intelligence) and ML (Machine Learning) has proven a dynamic shift in securing farm land. The SAPS (Stand Alone Power Supply) produce electric energy from RES (Renewable Energy Source). The integration of electronics devices with these technologies make this smart security an upper advantage in this segment. The devices or instruments that leverages the system are intelligent sensors, communication modules system, different types of cameras (day night mode of operation), hooters, lighting system, automatically trigger alarms. In addition to this, the system should have face recognizer system so that it can recognize invaders or restrict unauthorized entry. The smart fencing must put generate electric shock and warms the invaders. The smart farming system must send alert the farmers via mobile application or sms. This smart solution not only strengthens the safety of crops and livestock but also reduces the need for manual patrolling, thereby promoting sustainable and efficient farm management. The proposed system offers a cost-effective and scalable approach to securing rural properties using modern technology. Thus, it protect the farmer land in their absence and work as quick responder.","author":[{"family":"Sahwal","given":"Amod"},{"family":"Bhanjadeo","given":"Subhashree"},{"family":"Virnave","given":"Shantanu"},{"family":"Soni","given":"Kunal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18978810","URL":"https://doi.org/10.5281/zenodo.18978810","source":"datacite"},{"id":"doi:10.5281/zenodo.18957595","type":"article-journal","title":"Automated Irrigation and Nutrient Fertilization System for Sustainable Agriculture","abstract":"Abstract This study presents an automatic irrigation and fertilization system designed to provide a smart, real-time, and cost-effective solution for modern agriculture. The system integrates soil moisture sensors, an Arduino Uno microcontroller, a water pump, and fertilizer dispensing valves to maintain optimal soil conditions. Soil moisture is continuously monitored, and irrigation is activated only when required, reducing water wastage and ensuring proper hydration. A programmed fertilization module delivers precise nutrient quantities, minimizing human error and preventing over-fertilization associated with conventional manual practices. A functional prototype was developed and evaluated under controlled conditions. Experimental results showed nearly a 40% reduction in irrigation cycles compared to manual methods, demonstrating significant improvement in water-use efficiency. Fertilizer distribution was more uniform, leading to healthier root systems, improved soil structure, and enhanced crop quality. Data analysis revealed a strong correlation between automated water–nutrient management and improved plant growth. The study further evaluates system affordability, scalability, and suitability for small and medium-scale farmers, particularly in rural and resource-limited regions. The modular and low-cost design allows customization based on crop type, soil characteristics, farm size, and climatic conditions. Future enhancements include integration of IoT, GSM modules, and mobile applications for remote monitoring and predictive analysis.","author":[{"family":"Pawar","given":"Kumudini"},{"family":"Hattikar","given":"Snehal"},{"family":"Pawar","given":"Anjali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18957595","URL":"https://doi.org/10.5281/zenodo.18957595","source":"datacite"},{"id":"doi:10.5281/zenodo.18957596","type":"article-journal","title":"Automated Irrigation and Nutrient Fertilization System for Sustainable Agriculture","abstract":"Abstract This study presents an automatic irrigation and fertilization system designed to provide a smart, real-time, and cost-effective solution for modern agriculture. The system integrates soil moisture sensors, an Arduino Uno microcontroller, a water pump, and fertilizer dispensing valves to maintain optimal soil conditions. Soil moisture is continuously monitored, and irrigation is activated only when required, reducing water wastage and ensuring proper hydration. A programmed fertilization module delivers precise nutrient quantities, minimizing human error and preventing over-fertilization associated with conventional manual practices. A functional prototype was developed and evaluated under controlled conditions. Experimental results showed nearly a 40% reduction in irrigation cycles compared to manual methods, demonstrating significant improvement in water-use efficiency. Fertilizer distribution was more uniform, leading to healthier root systems, improved soil structure, and enhanced crop quality. Data analysis revealed a strong correlation between automated water–nutrient management and improved plant growth. The study further evaluates system affordability, scalability, and suitability for small and medium-scale farmers, particularly in rural and resource-limited regions. The modular and low-cost design allows customization based on crop type, soil characteristics, farm size, and climatic conditions. Future enhancements include integration of IoT, GSM modules, and mobile applications for remote monitoring and predictive analysis.","author":[{"family":"Pawar","given":"Kumudini"},{"family":"Hattikar","given":"Snehal"},{"family":"Pawar","given":"Anjali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18957596","URL":"https://doi.org/10.5281/zenodo.18957596","source":"datacite"},{"id":"doi:10.48346/imist.prsm/ajlp-gs.v9i1.62102","type":"article-journal","title":"GNSS-Driven Digital Agriculture and Private Sector Engagement to Link Rural Smallholder Farmers with Modern Markets in African Countries. Insights from Kigali City, Rwanda.","abstract":"Context and background Agriculture remains a cornerstone of economic development in many African countries, supplying food for the population and raw materials for industry. However, despite its vital role, rural smallholder farmers who constitute a majority of agricultural producers continue to face considerable challenges in accessing modern markets. Their produce often remains unsold or delayed at the farm level due to limited market connections, inadequate infrastructure, and a lack of technological integration. As urbanization rapidly transforms peri-urban and rural landscapes in developing countries, the intersection of agricultural productivity, food security, and urban planning becomes increasingly critical. The encroachment of urban arable land due to urban sprawl further exacerbates these issues, threatening both rural livelihoods and food security in cities. Goal and Objectives: This study aims to investigate how the adoption of digital agriculture technologies, particularly those powered by Global Navigation Satellite Systems (GNSS), combined with proactive private sector engagement, can serve as a bridge to connect smallholder farmers in rural areas to modern markets. Specifically, the study aimed to document recent smart technologies adopted in agriculture and private sector engagement to link smallholder farmers with modern market; to explore community perspectives on Digital Agriculture employed to connect Smallholder farmers to modern market; and to recommend future digital agriculture and private sector engagement to link smallholder farmers to modern market. Methodology: By enhancing access to buyers, optimizing agricultural practices, and facilitating real-time data sharing, these digital tools offer a pathway to elevate smallholder productivity and economic outcomes. Specifically, the research focuses on insights drawn from Kigali City, Rwanda a country actively pursuing smart agriculture solutions. A mixed-methods research design was adopted for this study, employing both qualitative and quantitative approaches within a case study framework. Kigali was selected as a representative case due to its advanced urban planning initiatives and ongoing efforts to integrate digital solutions in agriculture. Data collection involved structured and semi-structured interviews with key stakeholders. Respondents included 50 rural smallholder farmers and a city-level agronomist responsible for agricultural projects in Kigali. The interviews were designed using a combination of open- and close-ended questions to elicit detailed responses on current practices, perceived challenges, and opportunities related to smart agriculture and market accessibility. Results: The findings reveal a strong consensus among participants on the transformative potential of digital agriculture. An overwhelming majority (97%) of smallholder farmers affirmed that the use of digital technologies such as satellite-based mapping, weather forecasting tools, mobile-based agricultural extension services, and online market platforms could significantly enhance their farming efficiency and market access. Farmers reported that such tools allowed them to shift from labor-intensive practices to more informed, strategic decision-making in crop cultivation and sales. Furthermore, the agronomist interviewed corroborated these findings, emphasizing that GNSS-enabled tools and other precision agriculture technologies can benefit both small-scale and large-scale farmers. He highlighted that these innovations not only support better resource management and yield forecasting but also play a crucial role in linking rural producers with urban consumers and international markets. The ability to showcase available harvests, quantities, and locations in real time can dramatically improve the visibility of smallholder produce, reduce post-harvest losses, and stimulate private investment in rural agriculture. The study also explores the implications of urbanization for a","author":[{"family":"Mihigo","given":"David"},{"family":"Wasiu Akande","given":"Ahmed"},{"family":"Mpemba Lukenangula","given":"John"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48346/imist.prsm/ajlp-gs.v9i1.62102","URL":"https://doi.org/10.48346/imist.prsm/ajlp-gs.v9i1.62102","source":"datacite"},{"id":"doi:10.5281/zenodo.18918973","type":"article-journal","title":"AI-POWERED PERSONAL FARMING ASSISTANT","abstract":"Agriculture is vital for human survival, yet farmers face many challenges like unpredictable weather, plant diseases, poor resource use, and a lack of timely expert advice. Traditional farming often depends on manual observations and slow decisions, which can hurt crop yields and increase financial risks. Limited access to technology makes it harder for farmers to adopt modern, data-driven methods. The AI-Powered Personal Farming Assistant aims to change traditional farming into a smart, tech-driven environment. It is a digital platform that uses artificial intelligence, image processing, and real-time data analysis to help farmers manage crops and make decisions. The system provides instant disease detection, weather-based farming advice, soil condition analysis, and tailored crop guidance through an easy-to-use web or mobile app. One key innovation is AI-based disease identification. Farmers can upload images of plant leaves to get accurate predictions and treatment suggestions. The assistant also provides smart irrigation tips, fertilizer recommendations, and seasonal crop planning using predictive analytics. By combining automation with farming knowledge, the platform decreases reliance on manual consultations and boosts farming efficiency. For farmers, the AI-Powered Personal Farming Assistant acts as a trustworthy digital advisor that improves productivity, reduces crop loss, and encourages sustainable practices. For the agricultural sector, it marks progress toward precision agriculture and smart farming technologies. Overall, this system connects traditional farming with modern artificial intelligence, helping to increase crop yields, optimize resources, and empower farmers.","author":[{"family":"Mahankale","given":"Mr"},{"family":"Shaikh","given":"Mr"},{"family":"Pagare","given":"Mr"},{"family":"Parjane","given":"Mr"},{"family":"Parkhe","given":"Mr"},{"family":"Darode","given":"Mr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18918973","URL":"https://doi.org/10.5281/zenodo.18918973","source":"datacite"},{"id":"doi:10.5281/zenodo.18918974","type":"article-journal","title":"AI-POWERED PERSONAL FARMING ASSISTANT","abstract":"Agriculture is vital for human survival, yet farmers face many challenges like unpredictable weather, plant diseases, poor resource use, and a lack of timely expert advice. Traditional farming often depends on manual observations and slow decisions, which can hurt crop yields and increase financial risks. Limited access to technology makes it harder for farmers to adopt modern, data-driven methods. The AI-Powered Personal Farming Assistant aims to change traditional farming into a smart, tech-driven environment. It is a digital platform that uses artificial intelligence, image processing, and real-time data analysis to help farmers manage crops and make decisions. The system provides instant disease detection, weather-based farming advice, soil condition analysis, and tailored crop guidance through an easy-to-use web or mobile app. One key innovation is AI-based disease identification. Farmers can upload images of plant leaves to get accurate predictions and treatment suggestions. The assistant also provides smart irrigation tips, fertilizer recommendations, and seasonal crop planning using predictive analytics. By combining automation with farming knowledge, the platform decreases reliance on manual consultations and boosts farming efficiency. For farmers, the AI-Powered Personal Farming Assistant acts as a trustworthy digital advisor that improves productivity, reduces crop loss, and encourages sustainable practices. For the agricultural sector, it marks progress toward precision agriculture and smart farming technologies. Overall, this system connects traditional farming with modern artificial intelligence, helping to increase crop yields, optimize resources, and empower farmers.","author":[{"family":"Mahankale","given":"Mr"},{"family":"Shaikh","given":"Mr"},{"family":"Pagare","given":"Mr"},{"family":"Parjane","given":"Mr"},{"family":"Parkhe","given":"Mr"},{"family":"Darode","given":"Mr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18918974","URL":"https://doi.org/10.5281/zenodo.18918974","source":"datacite"},{"id":"doi:10.5281/zenodo.18891489","type":"article-journal","title":"Dataset: Soil, Climate and Remote Sensing Data for Olive Yield Estimation in Andalusia (2017–2023)","abstract":"This dataset supports the manuscript: \"An Integrated Smart Farming Framework for Olive Groves: Linking Soil, Climate and Remote Sensing Data for Yield Estimation\". The dataset integrates soil properties derived from SoilGrids, Sentinel-2 NDVI time series, agroclimatic variables (temperature, precipitation and growing degree days), and olive production records for olive parcels located in Córdoba (Andalusia, Spain). The dataset covers the period 2017–2023 and includes parcel-level information, soil descriptors, climate indicators, NDVI time series and yield metrics used in the study. The data were used to analyse relationships between soil properties, canopy dynamics derived from Sentinel-2 NDVI, hydro-thermal indicators and olive biomass and oil yield.","author":[{"family":"Tarquis","given":"Ana"},{"family":"Gutiérrez-Cabrera","given":"Rosa"},{"family":"Borondo","given":"Javier"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18891489","URL":"https://doi.org/10.5281/zenodo.18891489","source":"datacite"},{"id":"doi:10.5281/zenodo.18891490","type":"article-journal","title":"Dataset: Soil, Climate and Remote Sensing Data for Olive Yield Estimation in Andalusia (2017–2023)","abstract":"This dataset supports the manuscript: \"An Integrated Smart Farming Framework for Olive Groves: Linking Soil, Climate and Remote Sensing Data for Yield Estimation\". The dataset integrates soil properties derived from SoilGrids, Sentinel-2 NDVI time series, agroclimatic variables (temperature, precipitation and growing degree days), and olive production records for olive parcels located in Córdoba (Andalusia, Spain). The dataset covers the period 2017–2023 and includes parcel-level information, soil descriptors, climate indicators, NDVI time series and yield metrics used in the study. The data were used to analyse relationships between soil properties, canopy dynamics derived from Sentinel-2 NDVI, hydro-thermal indicators and olive biomass and oil yield.","author":[{"family":"Tarquis","given":"Ana"},{"family":"Gutiérrez-Cabrera","given":"Rosa"},{"family":"Borondo","given":"Javier"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18891490","URL":"https://doi.org/10.5281/zenodo.18891490","source":"datacite"},{"id":"doi:10.5281/zenodo.21940826","type":"article-journal","title":"Raspberry Pi based Automated Garden Sprinkler System with  Integrated Weather, Humidity, and Soil Moisture Monitoring","abstract":"Abstract - This study presents the design, development, and evaluation of a Raspberry Pi–based automated garden irrigation system integrating soil moisture sensors, humidity and temperature monitoring, and weather forecast data to achieve precision water management. The system leverages capacitive soil moisture probes, DHT22/AHT20 environmental sensors, rain detection modules, and a weather API to inform threshold-based irrigation control logic. Hardware includes a Raspberry Pi 4 microcontroller, opto-isolated relay modules, and 12 V DC solenoid valves, supported by an IP65-protected power and plumbing infrastructure. Software, written in Python, collects real-time sensor data, predicts rainfall, and schedules watering during optimal periods while skipping cycles during precipitation or forecasted rain. Field trials were conducted over five weeks on loam soil divided into Automated Irrigation (AI) and Manual Control (MC) plots. Baseline data from Week 1 (MC only) were compared to Weeks 2–5 (AI active). Results indicate a 33–34% reduction in water usage, 35% increase in soil moisture stability, 81% labor savings, and complete elimination of overwatering incidents. AI plots also showed improved plant health, with increases in height, leaf count, and greenness index. High system uptime (98–99%) demonstrated operational reliability. The findings confirm that IoT-enabled automated irrigation can significantly enhance water efficiency, crop vitality, and operational sustainability, with a short payback period. Key Words: Automated irrigation, Raspberry Pi, IoT agriculture, water efficiency, LeenaBOT, soil moisture control, precision farming.","author":[{"family":"Kanade","given":"Prakash"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21940826","URL":"https://doi.org/10.5281/zenodo.21940826","source":"datacite"},{"id":"doi:10.5281/zenodo.21940827","type":"article-journal","title":"Raspberry Pi based Automated Garden Sprinkler System with  Integrated Weather, Humidity, and Soil Moisture Monitoring","abstract":"Abstract - This study presents the design, development, and evaluation of a Raspberry Pi–based automated garden irrigation system integrating soil moisture sensors, humidity and temperature monitoring, and weather forecast data to achieve precision water management. The system leverages capacitive soil moisture probes, DHT22/AHT20 environmental sensors, rain detection modules, and a weather API to inform threshold-based irrigation control logic. Hardware includes a Raspberry Pi 4 microcontroller, opto-isolated relay modules, and 12 V DC solenoid valves, supported by an IP65-protected power and plumbing infrastructure. Software, written in Python, collects real-time sensor data, predicts rainfall, and schedules watering during optimal periods while skipping cycles during precipitation or forecasted rain. Field trials were conducted over five weeks on loam soil divided into Automated Irrigation (AI) and Manual Control (MC) plots. Baseline data from Week 1 (MC only) were compared to Weeks 2–5 (AI active). Results indicate a 33–34% reduction in water usage, 35% increase in soil moisture stability, 81% labor savings, and complete elimination of overwatering incidents. AI plots also showed improved plant health, with increases in height, leaf count, and greenness index. High system uptime (98–99%) demonstrated operational reliability. The findings confirm that IoT-enabled automated irrigation can significantly enhance water efficiency, crop vitality, and operational sustainability, with a short payback period. Key Words: Automated irrigation, Raspberry Pi, IoT agriculture, water efficiency, LeenaBOT, soil moisture control, precision farming.","author":[{"family":"Kanade","given":"Prakash"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21940827","URL":"https://doi.org/10.5281/zenodo.21940827","source":"datacite"},{"id":"doi:10.5281/zenodo.21902575","type":"article-journal","title":"HILL SPROUT KANGRA STRAWBERRY LEAF DATSET BY AVINASH SAHRMA","abstract":"The Strawberry Leaf Disease Image Dataset, copyrighted by Avinash Sharma, is a real-world image dataset developed for research and applications in deep learning, computer vision, and automated strawberry leaf disease detection. The dataset consists of approximately 8790 images of strawberry leaves captured from real plants at Hill Sprout Farms, Palampur, Himachal Pradesh, India. The dataset represents three major categories of strawberry leaves: Healthy Leaves – Images of strawberry leaves showing normal and healthy growth without visible disease symptoms. Leaf Scorch – Images showing characteristic symptoms of strawberry leaf scorch. Leaf Blight – Images representing strawberry leaves affected by leaf blight. A key feature of this dataset is that the images were captured under real-world agricultural conditions rather than being collected exclusively in controlled laboratory environments. The photographs were taken in natural daylight under different atmospheric and environmental conditions, resulting in variations in illumination, shadows, leaf orientation, and image appearance. The dataset also preserves the natural backgrounds and surrounding farm environment, making it more representative of conditions encountered during practical field-level disease identification.","author":[{"family":"Sharma","given":"Avinash"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21902575","URL":"https://doi.org/10.5281/zenodo.21902575","source":"datacite"},{"id":"doi:10.5281/zenodo.21902576","type":"article-journal","title":"HILL SPROUT KANGRA STRAWBERRY LEAF DATSET BY AVINASH SAHRMA","abstract":"The Strawberry Leaf Disease Image Dataset, copyrighted by Avinash Sharma, is a real-world image dataset developed for research and applications in deep learning, computer vision, and automated strawberry leaf disease detection. The dataset consists of approximately 8790 images of strawberry leaves captured from real plants at Hill Sprout Farms, Palampur, Himachal Pradesh, India. The dataset represents three major categories of strawberry leaves: Healthy Leaves – Images of strawberry leaves showing normal and healthy growth without visible disease symptoms. Leaf Scorch – Images showing characteristic symptoms of strawberry leaf scorch. Leaf Blight – Images representing strawberry leaves affected by leaf blight. A key feature of this dataset is that the images were captured under real-world agricultural conditions rather than being collected exclusively in controlled laboratory environments. The photographs were taken in natural daylight under different atmospheric and environmental conditions, resulting in variations in illumination, shadows, leaf orientation, and image appearance. The dataset also preserves the natural backgrounds and surrounding farm environment, making it more representative of conditions encountered during practical field-level disease identification.","author":[{"family":"Sharma","given":"Avinash"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21902576","URL":"https://doi.org/10.5281/zenodo.21902576","source":"datacite"},{"id":"doi:10.5281/zenodo.20624608","type":"article-journal","title":"Multi-Agent System Architecture for Energy Optimization in Precision Agriculture in the Algerian Sahara","abstract":"Abstract This paper proposes a Multi-Agent System (MAS) architecture designed to enhance energy optimization in precision agriculture within the Algerian Sahara. The increasing demand for sustainable agricultural practices in arid and semi-arid regions requires intelligent systems capable of managing scarce resources, particularly water and energy, while maintaining crop productivity. Wireless Sensor Networks (WSNs), when integrated with MAS frameworks, offer a distributed and adaptive solution for real-time monitoring and decision-making in smart irrigation systems. The proposed architecture leverages autonomous agents responsible for sensing, communication, coordination, and actuation processes to optimize irrigation scheduling and reduce unnecessary energy consumption. Each agent operates based on local environmental data such as soil moisture, temperature, humidity, and solar radiation, while also collaborating with other agents to ensure global system efficiency. The system is particularly tailored to the harsh climatic conditions of the Algerian Sahara, where water scarcity and high evaporation rates significantly challenge traditional irrigation methods. Simulation-based evaluation indicates that the MAS approach improves energy efficiency, reduces water consumption, and enhances system responsiveness compared to conventional centralized irrigation control systems. The results highlight the potential of distributed intelligent systems in supporting sustainable agriculture in extreme environments. Keywords :Multi-Agent System, Wireless Sensor Networks, Smart Irrigation, Energy Optimization, Precision Agriculture, Algerian Sahara","author":[{"family":"Bendjima","given":"Mostefa"},{"family":"Kourtiche","given":"Ikram"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20624608","URL":"https://doi.org/10.5281/zenodo.20624608","source":"datacite"},{"id":"doi:10.5281/zenodo.20624607","type":"article-journal","title":"Multi-Agent System Architecture for Energy Optimization in Precision Agriculture in the Algerian Sahara","abstract":"Abstract This paper proposes a Multi-Agent System (MAS) architecture designed to enhance energy optimization in precision agriculture within the Algerian Sahara. The increasing demand for sustainable agricultural practices in arid and semi-arid regions requires intelligent systems capable of managing scarce resources, particularly water and energy, while maintaining crop productivity. Wireless Sensor Networks (WSNs), when integrated with MAS frameworks, offer a distributed and adaptive solution for real-time monitoring and decision-making in smart irrigation systems. The proposed architecture leverages autonomous agents responsible for sensing, communication, coordination, and actuation processes to optimize irrigation scheduling and reduce unnecessary energy consumption. Each agent operates based on local environmental data such as soil moisture, temperature, humidity, and solar radiation, while also collaborating with other agents to ensure global system efficiency. The system is particularly tailored to the harsh climatic conditions of the Algerian Sahara, where water scarcity and high evaporation rates significantly challenge traditional irrigation methods. Simulation-based evaluation indicates that the MAS approach improves energy efficiency, reduces water consumption, and enhances system responsiveness compared to conventional centralized irrigation control systems. The results highlight the potential of distributed intelligent systems in supporting sustainable agriculture in extreme environments. Keywords :Multi-Agent System, Wireless Sensor Networks, Smart Irrigation, Energy Optimization, Precision Agriculture, Algerian Sahara","author":[{"family":"Bendjima","given":"Mostefa"},{"family":"Kourtiche","given":"Ikram"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.20624607","URL":"https://doi.org/10.5281/zenodo.20624607","source":"datacite"},{"id":"doi:10.5281/zenodo.20638252","type":"article-journal","title":"Multi-Agent System Architecture for Energy Optimization in Precision Agriculture in the Algerian Sahara","abstract":"Abstract This paper proposes a Multi-Agent System (MAS) architecture designed to enhance energy optimization in precision agriculture within the Algerian Sahara. The increasing demand for sustainable agricultural practices in arid and semi-arid regions requires intelligent systems capable of managing scarce resources, particularly water and energy, while maintaining crop productivity. Wireless Sensor Networks (WSNs), when integrated with MAS frameworks, offer a distributed and adaptive solution for real-time monitoring and decision-making in smart irrigation systems. The proposed architecture leverages autonomous agents responsible for sensing, communication, coordination, and actuation processes to optimize irrigation scheduling and reduce unnecessary energy consumption. Each agent operates based on local environmental data such as soil moisture, temperature, humidity, and solar radiation, while also collaborating with other agents to ensure global system efficiency. The system is particularly tailored to the harsh climatic conditions of the Algerian Sahara, where water scarcity and high evaporation rates significantly challenge traditional irrigation methods. Simulation-based evaluation indicates that the MAS approach improves energy efficiency, reduces water consumption, and enhances system responsiveness compared to conventional centralized irrigation control systems. The results highlight the potential of distributed intelligent systems in supporting sustainable agriculture in extreme environments. Keywords :Multi-Agent System, Wireless Sensor Networks, Smart Irrigation, Energy Optimization, Precision Agriculture, Algerian Sahara","author":[{"family":"Bendjima","given":"Mostefa"},{"family":"Kourtiche","given":"Ikram"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.20638252","URL":"https://doi.org/10.5281/zenodo.20638252","source":"datacite"},{"id":"doi:10.5281/zenodo.20810790","type":"article-journal","title":"AgroIntel: An Intelligent District-Aware Framework for Crop Recommendation and Fertilizer Optimization","abstract":"Abstract - Agriculture continues to be a principal means of earning a living for a significant portion of the global population. Crop suitability depends on multiple variables such as soil The rising demand for food production, combined with changing fertility, climatic conditions, rainfall patterns, temperature, climatic conditions and declining soil fertility, has created the need humidity, and regional agricultural practices. Traditional for intelligent agricultural decision-support systems. Farmers decision-making methods often rely on personal experience, often face difficulties in selecting appropriate crops and managing local knowledge, and expert consultations. While these soil nutrients due to variations in environmental conditions and approaches have supported farming activities for many years, insufficient access to expert guidance. To address these challenges, they may not always provide accurate recommendations under this paper presents AgroIntel, a district-aware smart decision- changing environmental conditions. Variations in weather support system for precision crop selection and soil nutrient patterns, soil degradation, and evolving agricultural demands management. The proposed system utilizes soil nutrient parameters, climatic attributes, and district-specific agricultural have increased the need for intelligent and data-driven decision- information to generate personalized recommendations. To support systems. support accurate crop selection, a Random Forest classification approach is implemented, leveraging soil nutrient composition The rapid evolution of Artificial Intelligence (AI) and Machine and weather-related attributes such as NPK content, temperature, Learning (ML) have opened new opportunities for transforming humidity, rainfall, and soil pH. To improve recommendation agricultural practices. Advanced machine learning algorithms relevance, district-level filtering is applied using regional facilitate the analysis of vast amounts of agricultural cultivation patterns. The framework also includes a fertilizer information to improve farming outcomes. and identify hidden advisory module that identifies nutrient deficiencies and suggests relationships among environmental factors that influence crop appropriate corrective measures. Furthermore, multilingual text growth. These capabilities enable the development of and voice support are incorporated to enhance accessibility for farmers from diverse linguistic backgrounds. Experimental intelligent recommendation systems capable of supporting evaluation demonstrates that the proposed framework provides farmers in enhancing decision-making processes By utilizing reliable crop recommendations and practical nutrient predictive analytics, These systems can enhance crop yield, management guidance. The system contributes toward sustainable optimize resource utilization, and support sustainable agriculture by facilitating evidence-based decision-making and agricultural practices..","author":[{"family":"Muragod","given":"Soumya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20810790","URL":"https://doi.org/10.5281/zenodo.20810790","source":"datacite"},{"id":"doi:10.5281/zenodo.20810791","type":"article-journal","title":"AgroIntel: An Intelligent District-Aware Framework for Crop Recommendation and Fertilizer Optimization","abstract":"Abstract - Agriculture continues to be a principal means of earning a living for a significant portion of the global population. Crop suitability depends on multiple variables such as soil The rising demand for food production, combined with changing fertility, climatic conditions, rainfall patterns, temperature, climatic conditions and declining soil fertility, has created the need humidity, and regional agricultural practices. Traditional for intelligent agricultural decision-support systems. Farmers decision-making methods often rely on personal experience, often face difficulties in selecting appropriate crops and managing local knowledge, and expert consultations. While these soil nutrients due to variations in environmental conditions and approaches have supported farming activities for many years, insufficient access to expert guidance. To address these challenges, they may not always provide accurate recommendations under this paper presents AgroIntel, a district-aware smart decision- changing environmental conditions. Variations in weather support system for precision crop selection and soil nutrient patterns, soil degradation, and evolving agricultural demands management. The proposed system utilizes soil nutrient parameters, climatic attributes, and district-specific agricultural have increased the need for intelligent and data-driven decision- information to generate personalized recommendations. To support systems. support accurate crop selection, a Random Forest classification approach is implemented, leveraging soil nutrient composition The rapid evolution of Artificial Intelligence (AI) and Machine and weather-related attributes such as NPK content, temperature, Learning (ML) have opened new opportunities for transforming humidity, rainfall, and soil pH. To improve recommendation agricultural practices. Advanced machine learning algorithms relevance, district-level filtering is applied using regional facilitate the analysis of vast amounts of agricultural cultivation patterns. The framework also includes a fertilizer information to improve farming outcomes. and identify hidden advisory module that identifies nutrient deficiencies and suggests relationships among environmental factors that influence crop appropriate corrective measures. Furthermore, multilingual text growth. These capabilities enable the development of and voice support are incorporated to enhance accessibility for farmers from diverse linguistic backgrounds. Experimental intelligent recommendation systems capable of supporting evaluation demonstrates that the proposed framework provides farmers in enhancing decision-making processes By utilizing reliable crop recommendations and practical nutrient predictive analytics, These systems can enhance crop yield, management guidance. The system contributes toward sustainable optimize resource utilization, and support sustainable agriculture by facilitating evidence-based decision-making and agricultural practices..","author":[{"family":"Muragod","given":"Soumya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20810791","URL":"https://doi.org/10.5281/zenodo.20810791","source":"datacite"},{"id":"doi:10.17632/n4fbk86t9k.2","type":"article-journal","title":"Leakage-aware evaluation of satellite machine learning for district-scale crop yield forecasting: silage maize in Türkiye","abstract":"This record contains the data and code for a leakage-aware evaluation of satellite machine learning applied to district-scale silage-maize yield forecasting in the TR22 South Marmara region of Türkiye (Balıkesir and Çanakkale provinces). The dataset is a fully balanced panel of 30 districts over nine growing seasons (2017–2025), giving 270 district-year observations with no missing values. Predictors combine four Sentinel-2 vegetation indices (NDVI, EVI, NDRE, GNDVI), each summarised by seasonal mean, maximum and 90th percentile at 10 m and aggregated to 60 m district values, with five ERA5-Land meteorological variables. The response variable is district silage-maize yield from Turkish Statistical Institute records. Because district polygons contain substantial non-cropland area, the extraction is provided under four specifications: no cropland mask (the reference), an annual Dynamic World cropland mask, a static ESA WorldCover mask, and an unmasked variant using an alternative temporal reduction order for sensitivity analysis. The code covers the full pipeline: Google Earth Engine extraction, district harmonisation against the yield series, model fitting under contrasting validation regimes (random k-fold, spatial-block, leave-one-district-out, leave-one-year-out), variance decomposition, coordinates-only attribution, district-blocked bootstrap inference, and figure generation. Version 2 supersedes version 1 and should be used in preference to it. Version 1 contains a cropland mask described in the methods but not applied in the extraction, two numerically ill-conditioned EVI features, a temporal reduction performed on the aggregation grid rather than at source resolution, a validation design labelled leave-one-district-out that in fact grouped districts into five folds, and three mis-specified inferential procedures. CHANGELOG.md in this version itemises all twelve differences. Version 1 remains archived for provenance but its EVI columns are not reproducible.","author":[{"family":"Aldag","given":"Mustafa"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/n4fbk86t9k.2","URL":"https://doi.org/10.17632/n4fbk86t9k.2","source":"datacite"},{"id":"doi:10.17632/n4fbk86t9k","type":"article-journal","title":"Leakage-aware evaluation of satellite machine learning for district-scale crop yield forecasting: silage maize in Türkiye","abstract":"This record contains the data and code for a leakage-aware evaluation of satellite machine learning applied to district-scale silage-maize yield forecasting in the TR22 South Marmara region of Türkiye (Balıkesir and Çanakkale provinces). The dataset is a fully balanced panel of 30 districts over nine growing seasons (2017–2025), giving 270 district-year observations with no missing values. Predictors combine four Sentinel-2 vegetation indices (NDVI, EVI, NDRE, GNDVI), each summarised by seasonal mean, maximum and 90th percentile at 10 m and aggregated to 60 m district values, with five ERA5-Land meteorological variables. The response variable is district silage-maize yield from Turkish Statistical Institute records. Because district polygons contain substantial non-cropland area, the extraction is provided under four specifications: no cropland mask (the reference), an annual Dynamic World cropland mask, a static ESA WorldCover mask, and an unmasked variant using an alternative temporal reduction order for sensitivity analysis. The code covers the full pipeline: Google Earth Engine extraction, district harmonisation against the yield series, model fitting under contrasting validation regimes (random k-fold, spatial-block, leave-one-district-out, leave-one-year-out), variance decomposition, coordinates-only attribution, district-blocked bootstrap inference, and figure generation. Version 2 supersedes version 1 and should be used in preference to it. Version 1 contains a cropland mask described in the methods but not applied in the extraction, two numerically ill-conditioned EVI features, a temporal reduction performed on the aggregation grid rather than at source resolution, a validation design labelled leave-one-district-out that in fact grouped districts into five folds, and three mis-specified inferential procedures. CHANGELOG.md in this version itemises all twelve differences. Version 1 remains archived for provenance but its EVI columns are not reproducible.","author":[{"family":"Aldag","given":"Mustafa"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/n4fbk86t9k","URL":"https://doi.org/10.17632/n4fbk86t9k","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33040562.v1","type":"article-journal","title":"<b>PlantCity: A comprehensive image based on multi crop leaves in Pakistan</b>","abstract":"Cite Paper: Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130paper link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data were collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the development of deep learning models for automated disease classification and captures a range of environmental factors, including high temperatures that can exacerbate disease symptoms. It utilizes smartphone-based computer vision to facilitate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33040562.v1","URL":"https://doi.org/10.6084/m9.figshare.33040562.v1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33040562.v2","type":"article-journal","title":"<b>PlantCity: A comprehensive image based on multi crop leaves in Pakistan</b>","abstract":"Cite Paper: Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130paper link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data were collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the development of deep learning models for automated disease classification and captures a range of environmental factors, including high temperatures that can exacerbate disease symptoms. It utilizes smartphone-based computer vision to facilitate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33040562.v2","URL":"https://doi.org/10.6084/m9.figshare.33040562.v2","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33040562","type":"article-journal","title":"<b>PlantCity: A comprehensive image based on multi crop leaves in Pakistan</b>","abstract":"Cite Paper: Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130paper link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data were collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the development of deep learning models for automated disease classification and captures a range of environmental factors, including high temperatures that can exacerbate disease symptoms. It utilizes smartphone-based computer vision to facilitate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33040562","URL":"https://doi.org/10.6084/m9.figshare.33040562","source":"datacite"},{"id":"doi:10.5281/zenodo.21852099","type":"article-journal","title":"Reproducibility compendium for an acquisition-aware audit framework in plant image benchmarks","abstract":"This version-specific reproducibility compendium accompanies the manuscript “Image-level splitting yielded consistently more favorable cross-validation estimates than did acquisition-group isolation in two public weed-image benchmarks: a paired fixed-cohort audit.” It contains the complete project-generated fixed-cohort out-of-fold prediction layer, paired fold assignments, grouping metadata, analysis code, source data underlying figures and tables, validation records, and checksums. DeepWeeds and MFWD source-image archives, upstream pretrained weights, and trained checkpoints are not redistributed. Dataset-specific evidence layers and uncertainty units must not be pooled into a cross-dataset statistical effect. Post-publication correction (2026-08-09): manuscript-facing title and caption text, Figure 1 scope labels, release-status documentation, and dependent checksum manifests were synchronized. No OOF predictions, fold assignments, grouping metadata, numerical results, or analysis algorithms were changed.","author":[{"family":"Chen","given":"Dinghao"},{"family":"Li","given":"Li"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21852099","URL":"https://doi.org/10.5281/zenodo.21852099","source":"datacite"},{"id":"doi:10.5281/zenodo.21831226","type":"article-journal","title":"GreenCalculus — UK Spend-Based GHG Intensity by SIC 2007 Industry Section (ONS)","abstract":"Greenhouse gas intensity for 18 UK industry sections in kg CO2e per pound ofGROSS VALUE ADDED, from the ONS Atmospheric Emissions framework, 5 June 2026release. Ranges from 2.71 for agriculture to 0.01 for information andcommunication — a 271-fold spread, which means sector selection dominates aspend-based estimate far more than the precision of the spend figure. The denominator is value added, NOT invoice value. Gross value added is anindustry's output minus what it bought in to produce that output, so applyingthese intensities directly to a supplier invoice understates the result by asector-specific margin. This matters when combining sources: US EPA spend-basedfactors are published per dollar of purchaser price, which is the invoice basis,and the two are not interchangeable. Three sections are absent and that is the source's position, not an omission.ONS marks K (financial and insurance) and L (real estate) as \"low\" — defined inthe source as \"a low figure but not a real zero\" — in every published year, andtreats U (extra-territorial bodies) as negligible. Section J (information andcommunication) is carried at its 2023 value because 2024 is also marked \"low\";each row carries its own reference year. AR5 GWP-100 per the DEFRA and Ricardo convention. UK residence basis — emissionsattributed to UK-resident economic units wherever they occur. Supports GHGProtocol Scope 3 spend-based estimation and PCAF data quality score 4.they occur. Supports GHGProtocol Scope 3 spend-based estimation and PCAF data quality score 4. Live page:https://greencalculus.com/data/uk-sic-spend-based-ghg-intensity/ API:https://greencalculus.com/wp-json/greencalculus/v1/ons-sic-factors Contains public sector information licensed under the Open Government Licence v3.0.","author":[{"family":"Say","given":"Jeremiah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21831226","URL":"https://doi.org/10.5281/zenodo.21831226","source":"datacite"},{"id":"doi:10.5281/zenodo.21831227","type":"article-journal","title":"GreenCalculus — UK Spend-Based GHG Intensity by SIC 2007 Industry Section (ONS)","abstract":"Greenhouse gas intensity for 18 UK industry sections in kg CO2e per pound ofGROSS VALUE ADDED, from the ONS Atmospheric Emissions framework, 5 June 2026release. Ranges from 2.71 for agriculture to 0.01 for information andcommunication — a 271-fold spread, which means sector selection dominates aspend-based estimate far more than the precision of the spend figure. The denominator is value added, NOT invoice value. Gross value added is anindustry's output minus what it bought in to produce that output, so applyingthese intensities directly to a supplier invoice understates the result by asector-specific margin. This matters when combining sources: US EPA spend-basedfactors are published per dollar of purchaser price, which is the invoice basis,and the two are not interchangeable. Three sections are absent and that is the source's position, not an omission.ONS marks K (financial and insurance) and L (real estate) as \"low\" — defined inthe source as \"a low figure but not a real zero\" — in every published year, andtreats U (extra-territorial bodies) as negligible. Section J (information andcommunication) is carried at its 2023 value because 2024 is also marked \"low\";each row carries its own reference year. AR5 GWP-100 per the DEFRA and Ricardo convention. UK residence basis — emissionsattributed to UK-resident economic units wherever they occur. Supports GHGProtocol Scope 3 spend-based estimation and PCAF data quality score 4.they occur. Supports GHGProtocol Scope 3 spend-based estimation and PCAF data quality score 4. Live page:https://greencalculus.com/data/uk-sic-spend-based-ghg-intensity/ API:https://greencalculus.com/wp-json/greencalculus/v1/ons-sic-factors Contains public sector information licensed under the Open Government Licence v3.0.","author":[{"family":"Say","given":"Jeremiah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21831227","URL":"https://doi.org/10.5281/zenodo.21831227","source":"datacite"},{"id":"doi:10.5281/zenodo.19662664","type":"article-journal","title":"Data Science-Driven Agricultural Yield Prediction System","abstract":"Crop yield forecasting is increasingly important for farmers facing uncertainties such as varying rainfall patterns and fluctuating soil nutrient levels. This study proposes a data-driven system that utilizes historical crop data, soil nutrient parameters, and weather conditions to predict agricultural yield with improved accuracy. Four machine learning models—Linear Regression, Decision Tree, Random Forest, and Long Short-Term Memory (LSTM)—were evaluated to capture both static and time-series characteristics of the data. Among these, the Random Forest model demonstrated superior performance due to its ability to model complex interactions between soil nutrients, rainfall, and temperature. Additionally, K-means clustering was applied to categorize soil types, and SHAP (SHapley Additive exPlanations) analysis was used to interpret the contribution of individual features in the prediction process. The proposed system provides practical insights that can assist farmers, particularly in regions like Podili, in making informed decisions regarding irrigation and fertilizer usage, ultimately enhancing agricultural productivity.","author":[{"family":"Nakkina","given":"Surya"},{"family":"Vutukuru","given":"Haneesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19662664","URL":"https://doi.org/10.5281/zenodo.19662664","source":"datacite"},{"id":"doi:10.5281/zenodo.19662665","type":"article-journal","title":"Data Science-Driven Agricultural Yield Prediction System","abstract":"Crop yield forecasting is increasingly important for farmers facing uncertainties such as varying rainfall patterns and fluctuating soil nutrient levels. This study proposes a data-driven system that utilizes historical crop data, soil nutrient parameters, and weather conditions to predict agricultural yield with improved accuracy. Four machine learning models—Linear Regression, Decision Tree, Random Forest, and Long Short-Term Memory (LSTM)—were evaluated to capture both static and time-series characteristics of the data. Among these, the Random Forest model demonstrated superior performance due to its ability to model complex interactions between soil nutrients, rainfall, and temperature. Additionally, K-means clustering was applied to categorize soil types, and SHAP (SHapley Additive exPlanations) analysis was used to interpret the contribution of individual features in the prediction process. The proposed system provides practical insights that can assist farmers, particularly in regions like Podili, in making informed decisions regarding irrigation and fertilizer usage, ultimately enhancing agricultural productivity.","author":[{"family":"Nakkina","given":"Surya"},{"family":"Vutukuru","given":"Haneesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19662665","URL":"https://doi.org/10.5281/zenodo.19662665","source":"datacite"},{"id":"doi:10.5281/zenodo.17730719","type":"article-journal","title":"AgriField-Manipur: Smart Farming Dataset (Synthetic v2025.1)","abstract":"The AgriField-Manipur Dataset (v2025.1) is a realistic hybrid dataset created to support smart farming, AI research, and IoT-based agricultural development for the valley farming ecosystem of Manipur, India.It contains daily time-series measurements of temperature, humidity, soil moisture, soil pH, rainfall, and crop suitability parameters across multiple valley districts. Although the dataset is synthetically generated at field level due to limited direct sensor availability and operational constraints, all parameter ranges, seasonal behaviour, and soil characteristics are based on verified agricultural references, including: Regional climatology (IMD, NASA POWER) Soil reports and advisories (ICAR-NEH, Manipur Agriculture Department) Crop agronomy and best practices (FAO and ICAR standards) This design ensures that the dataset reflects realistic environmental behaviour, seasonal variation, and district-level differences found in valley agriculture of Manipur. The dataset also includes generator code, allowing reproducibility, custom simulation, and further scaling based on research needs. It is suitable for: Smart farming and IoT platform prototyping Machine learning systems for crop suitability, irrigation, soil analysis, and pest/disease risk Benchmarking, simulation, and academic instruction in precision agriculture","author":[{"family":"Elangbam","given":"Bony"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.17730719","URL":"https://doi.org/10.5281/zenodo.17730719","source":"datacite"},{"id":"doi:10.5281/zenodo.18009822","type":"article-journal","title":"AgriField-Manipur: A Hybrid Constraint-Based Dataset for Agricultural Decision Support in Data-Scarce Valley Regions (Version 2)","abstract":"AgriField-Manipur (Version 2) is a simulated field-level agricultural dataset designed to support machine learning and decision-support research in data-scarce valley agricultural regions, with a focus on the Manipur valley in North-East India. The dataset provides daily time-series observations for simulated agricultural field plots, generated using a hybrid framework that combines rule-based agronomic constraints with stochastic variability. Although synthetic, all variables are bounded by agro-climatic, soil, and crop-physiological references, supporting agronomic plausibility and internal consistency. The dataset comprises 94,900 records, where each record represents a single day of observation for a simulated field plot. It includes environmental variables (temperature, humidity, rainfall), soil indicators (soil moisture, soil type, pH), relative macronutrient indices (N, P, K), crop identity, and downstream decision-support outputs. These outputs include a continuous crop suitability score, a binary suitability classification, and rule-based advisory indicators for irrigation, fertilizer application, and pest or disease risk. The dataset covers five valley districts of Manipur (Imphal East, Imphal West, Thoubal, Bishnupur, and Kakching), spans the period from 1 December 2024 to 30 November 2025, and supports 52 crops relevant to Manipur valley agriculture. Geographic coordinates are provided at an approximate district level to preserve privacy while enabling spatial analysis. Version 2 represents the publication-aligned release of the dataset and is intended for research, model development, and prototyping of agricultural decision-support systems in data-scarce environments. This dataset is synthetic but agronomically grounded and should not be interpreted as direct field measurements. Advisory outputs are generated using expert-defined rules and are provided for research purposes only.","author":[{"family":"Elangbam","given":"Bony"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18009822","URL":"https://doi.org/10.5281/zenodo.18009822","source":"datacite"},{"id":"doi:10.5281/zenodo.19603296","type":"article-journal","title":"TRANSFORMING AGRICULTURE WITH AI-POWERED SMART DRONES","abstract":"This paper introduces an AI-driven smart drone framework for precision agriculture, integrating computer vision, machine learning, and sensor technology to enable real-time crop monitoring and disease detection. By transitioning from manual methods to automated, site-specific interventions for water and chemical application, the system significantly optimizes resource use. Comparative analysis demonstrates that this framework enhances productivity and cost-efficiency while promoting environmental sustainability through reduced wastage. Key Points Technology Integration: Combines UAVs (drones) with computer vision and machine learning for automated field analysis. Precision Management: Enables targeted application of pesticides, fertilizers, and water, reducing chemical usage by an estimated 30–35%. Health Diagnostics: Provides early and accurate identification of crop diseases and nutritional deficiencies compared to traditional visual inspection. Operational Efficiency: Significantly reduces labor dependency and manual error through real-time aerial data processing. Economic & Green Impact: Improves Return on Investment (ROI) over time and fosters sustainable farming by minimizing the environmental footprint of agricultural chemicals.","author":[{"family":"Giri","given":"Aryan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19603296","URL":"https://doi.org/10.5281/zenodo.19603296","source":"datacite"},{"id":"doi:10.5281/zenodo.19603295","type":"article-journal","title":"TRANSFORMING AGRICULTURE WITH AI-POWERED SMART DRONES","abstract":"This paper introduces an AI-driven smart drone framework for precision agriculture, integrating computer vision, machine learning, and sensor technology to enable real-time crop monitoring and disease detection. By transitioning from manual methods to automated, site-specific interventions for water and chemical application, the system significantly optimizes resource use. Comparative analysis demonstrates that this framework enhances productivity and cost-efficiency while promoting environmental sustainability through reduced wastage. Key Points Technology Integration: Combines UAVs (drones) with computer vision and machine learning for automated field analysis. Precision Management: Enables targeted application of pesticides, fertilizers, and water, reducing chemical usage by an estimated 30–35%. Health Diagnostics: Provides early and accurate identification of crop diseases and nutritional deficiencies compared to traditional visual inspection. Operational Efficiency: Significantly reduces labor dependency and manual error through real-time aerial data processing. Economic & Green Impact: Improves Return on Investment (ROI) over time and fosters sustainable farming by minimizing the environmental footprint of agricultural chemicals.","author":[{"family":"Giri","given":"Aryan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19603295","URL":"https://doi.org/10.5281/zenodo.19603295","source":"datacite"},{"id":"doi:10.5281/zenodo.19592685","type":"article-journal","title":"Precision Farming and Health Monitoring in Agric-Workers using Wearable AI Devices","abstract":"This paper introduces a smart precision farming system with wearable health monitoring to optimise the productivity of agriculture and guarantee the safety of agri-workers. The study attempts to combat the weaknesses of conventional agricultural systems that tend to overlook real-time observation of physiological status of workers like stress and fatigue. This was designed in a layered Internet of Things architecture to allow real time transmission and analysis of continuous data over wearable sensors and environmental sources. The dataset used to develop a model was WESAD, and preprocessing, such as normalisation, filtering, and segmentation, were used to enhance the quality of the data and guarantee the high level of the extractions of the features. The model was an Artificial Neural Network (ANN) that was applied with the help of TensorFlow and Keras in order to distinguish between agri-worker conditions of stress, fatigue, and neutral. Results obtained from the independent test dataset demonstrated strong predictive capability, achieving 94.2% accuracy (95% CI: ±1.8%), 92.7% precision (±2.1%), 91.8% recall (±2.3%), and 92.2% F1‑score (±2.0%). Comparison with baseline models showed that the proposed ANN outperformed Support Vector Machine (SVM), Random Forest (RF), and Long Short‑Term Memory (LSTM) networks. Additionally, simulation across 100-time windows produced an overall system accuracy of 96% with an average response time of 1.2seconds, confirming real-time efficiency and consistency. The results show that the implementation of Artificial Intelligence alongside wearable sensors offers a dependable and scalable method of continuously tracking the wellbeing of agri-workers. The proposed system could help improve the early identification of stress‑related disorders, facilitate prompt intervention, and enable safer, more efficient, and sustainable agricultural methods. though field validation with actual agricultural workers remains necessary.","author":[{"family":"Adigwe","given":"Anthony"},{"family":"Ojene","given":"Cornelius"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19592685","URL":"https://doi.org/10.5281/zenodo.19592685","source":"datacite"},{"id":"doi:10.5281/zenodo.19592684","type":"article-journal","title":"Precision Farming and Health Monitoring in Agric-Workers using Wearable AI Devices","abstract":"This paper introduces a smart precision farming system with wearable health monitoring to optimise the productivity of agriculture and guarantee the safety of agri-workers. The study attempts to combat the weaknesses of conventional agricultural systems that tend to overlook real-time observation of physiological status of workers like stress and fatigue. This was designed in a layered Internet of Things architecture to allow real time transmission and analysis of continuous data over wearable sensors and environmental sources. The dataset used to develop a model was WESAD, and preprocessing, such as normalisation, filtering, and segmentation, were used to enhance the quality of the data and guarantee the high level of the extractions of the features. The model was an Artificial Neural Network (ANN) that was applied with the help of TensorFlow and Keras in order to distinguish between agri-worker conditions of stress, fatigue, and neutral. Results obtained from the independent test dataset demonstrated strong predictive capability, achieving 94.2% accuracy (95% CI: ±1.8%), 92.7% precision (±2.1%), 91.8% recall (±2.3%), and 92.2% F1‑score (±2.0%). Comparison with baseline models showed that the proposed ANN outperformed Support Vector Machine (SVM), Random Forest (RF), and Long Short‑Term Memory (LSTM) networks. Additionally, simulation across 100-time windows produced an overall system accuracy of 96% with an average response time of 1.2seconds, confirming real-time efficiency and consistency. The results show that the implementation of Artificial Intelligence alongside wearable sensors offers a dependable and scalable method of continuously tracking the wellbeing of agri-workers. The proposed system could help improve the early identification of stress‑related disorders, facilitate prompt intervention, and enable safer, more efficient, and sustainable agricultural methods. though field validation with actual agricultural workers remains necessary.","author":[{"family":"Adigwe","given":"Anthony"},{"family":"Ojene","given":"Cornelius"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19592684","URL":"https://doi.org/10.5281/zenodo.19592684","source":"datacite"},{"id":"doi:10.5281/zenodo.19569916","type":"article-journal","title":"Enhanced Explainable AI-Based Crop Yield Prediction and Advisory System","abstract":"This research presents an advanced Explainable AI-based crop yield prediction and advisory system developed for precision agriculture. The system utilizes the XGBoost algorithm to achieve high prediction accuracy and integrates SHAP-based interpretability techniques to provide transparent and understandable insights into model decisions. The model analyzes key agricultural parameters such as soil nutrients (Nitrogen, Phosphorus, Potassium), temperature, humidity, pH, and rainfall to predict crop yield effectively. In addition to prediction, the system generates actionable recommendations for farmers, helping them optimize crop productivity and manage soil health efficiently. The developed system includes an interactive dashboard interface and automated PDF report generation, making it practical for real-world agricultural applications. This approach bridges the gap between artificial intelligence and farmer usability by transforming complex predictions into clear and actionable insights.","author":[{"family":"Gandu","given":"Deepthi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19569916","URL":"https://doi.org/10.5281/zenodo.19569916","source":"datacite"},{"id":"doi:10.5281/zenodo.19569917","type":"article-journal","title":"Enhanced Explainable AI-Based Crop Yield Prediction and Advisory System","abstract":"This research presents an advanced Explainable AI-based crop yield prediction and advisory system developed for precision agriculture. The system utilizes the XGBoost algorithm to achieve high prediction accuracy and integrates SHAP-based interpretability techniques to provide transparent and understandable insights into model decisions. The model analyzes key agricultural parameters such as soil nutrients (Nitrogen, Phosphorus, Potassium), temperature, humidity, pH, and rainfall to predict crop yield effectively. In addition to prediction, the system generates actionable recommendations for farmers, helping them optimize crop productivity and manage soil health efficiently. The developed system includes an interactive dashboard interface and automated PDF report generation, making it practical for real-world agricultural applications. This approach bridges the gap between artificial intelligence and farmer usability by transforming complex predictions into clear and actionable insights.","author":[{"family":"Gandu","given":"Deepthi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19569917","URL":"https://doi.org/10.5281/zenodo.19569917","source":"datacite"},{"id":"doi:10.48416/ijsaf.v31i1.694","type":"article-journal","title":"Alternative Food Networks and Green Infrastructures","abstract":"Urbanisation, growing population pressure, and extreme weather conditions all contribute to food insecurity. In greenhouse farming, vegetables are harvested in a controlled environment, resulting in high-quality production with minimum resources. Such green infrastructures have also become promising in urban areas and non-arable lands. In this paper, I focus on community-based greenhouses in the Netherlands, which are primarily managed by volunteers and local residents, and on their varied conceptualisations of food production and innovation. I argue that these Alternative Food Networks are not homogeneous, and that their polymorphism reflects an intrinsic diversity in both organisational cultures and materiality. Despite this diversity, these green infrastructures converge in their emphasis on producing high-quality food and prioritising the management of nature and biodiversity, rather than any reliance on mechanical manipulation. My research involves conducting primary research studies, based on a mixed-method approach combining the use of surveys, semi-structured interviews, observational studies, and site visits around the Netherlands. I posit that community-based greenhouses constitute a hands-on agricultural practice that relies heavily on trust and on fluidity between consumers and producers. This fluidity is enacted through the interconnected roles and knowledge circulation within the greenhouse ecosystem. Understanding technology in use, experiential expertise – which often contains tacit components –, and a knowledge base that is critical to the effective operation of the greenhouse as a system, are integral to this innovative approach to agriculture. The paper examines the role of smart technologies and the emergence of visions in facilitating this ecosystem, while highlighting the vital interplay between growers and consumers in reimagining food production and sustainability.","author":[{"family":"Lyu","given":"Meilin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48416/ijsaf.v31i1.694","URL":"https://doi.org/10.48416/ijsaf.v31i1.694","source":"datacite"},{"id":"doi:10.5281/zenodo.19484433","type":"article-journal","title":"INNOECOFOOD Project Newsletter Issue 3","abstract":"The last six months of 2025 marked an important phase in the progress of the INNOECOFOOD project as partners across Africa and Europe continue to advance innovations for sustainable aquaculture and circular bioeconomy solutions. In this issue, we highlight the steady progress in the construction and operationalization of ECOHUBs in Egypt, Ghana, Kenya, and Tanzania, which are being established as centers for production, research, training, and community engagement powered by renewable energy and supported by AI and IoT technologies. These facilities are expected to play a central role in demonstrating climate-smart aquaculture and innovative food production systems. This edition also presents key updates from our work packages, showcasing the scientific and technological milestones achieved so far. Significant advances have been made in optimizing spirulina strains for sustainable production, scaling up insect farming for feed and food applications, and testing innovative fish diets that incorporate spirulina and black soldier fly as alternatives to fishmeal. In parallel, partners have made progress in developing value-added products such as biscuits, bhajia and nutrient bars using fish, spirulina, and insect ingredients, demonstrating the practical application of circular bioeconomy principles.","author":[{"family":"Africa","given":"Food"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19484433","URL":"https://doi.org/10.5281/zenodo.19484433","source":"datacite"},{"id":"doi:10.5281/zenodo.19484434","type":"article-journal","title":"INNOECOFOOD Project Newsletter Issue 3","abstract":"The last six months of 2025 marked an important phase in the progress of the INNOECOFOOD project as partners across Africa and Europe continue to advance innovations for sustainable aquaculture and circular bioeconomy solutions. In this issue, we highlight the steady progress in the construction and operationalization of ECOHUBs in Egypt, Ghana, Kenya, and Tanzania, which are being established as centers for production, research, training, and community engagement powered by renewable energy and supported by AI and IoT technologies. These facilities are expected to play a central role in demonstrating climate-smart aquaculture and innovative food production systems. This edition also presents key updates from our work packages, showcasing the scientific and technological milestones achieved so far. Significant advances have been made in optimizing spirulina strains for sustainable production, scaling up insect farming for feed and food applications, and testing innovative fish diets that incorporate spirulina and black soldier fly as alternatives to fishmeal. In parallel, partners have made progress in developing value-added products such as biscuits, bhajia and nutrient bars using fish, spirulina, and insect ingredients, demonstrating the practical application of circular bioeconomy principles.","author":[{"family":"Africa","given":"Food"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19484434","URL":"https://doi.org/10.5281/zenodo.19484434","source":"datacite"},{"id":"doi:10.5281/zenodo.19248288","type":"article-journal","title":"CLIMATE VARIABILITY AND SMALLHOLDER FARMING SYSTEMS: A STUDY OF AGRICULTURAL ADAPTATION IN AHMEDABAD DISTRICT, GUJARAT","abstract":"Increasing variability in rainfall and temperature has become a major challenge for agricultural communities, particularly in regions where farming depends heavily on monsoon rainfall. In India, smallholder farmers constitute a major share of the agrarian economy, and their dependence on monsoon-based cultivation exposes them significantly to climate stress. This study examines the effects of climate variability on agricultural productivity, income stability, and livelihood security among smallholder farmers residing near Ahmedabad, Gujarat. The research adopts a mixed-method case study approach combining quantitative and qualitative data. Primary data were collected from 120 farmers across four agro-climatic talukas—Sanand, Bavla, Viramgam, and Dholka—using structured questionnaires and interviews. Secondary climate data on rainfall, temperature, and extreme weather events from 2014 to June 2025 were analyzed. The results show intensifying climate fluctuations characterized by delayed monsoon onset, concentrated rainfall events, extended dry spells, and increasing heatwave frequency. These climatic disruptions reduced yields of cotton, cumin, bajra, castor, and wheat while increasing input costs, pest infestation, and dependence on irrigation. Consequently, household income declined, outstanding debt rose, and nearly half of the farming households reported supplemental migration. Adaptation strategies included crop diversification, drought-resistant seeds, micro-irrigation, crop insurance, and non-farm work; however, the coping mechanisms remain insufficient for long-term resilience. The study concludes that climate variability exacerbates agricultural vulnerability, emphasizing the need for climate-smart practices, localized institutional support, reliable crop insurance, and accessible weather advisory services to safeguard the livelihoods of smallholder farmers.","author":[{"family":"Dani","given":"Ca"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19248288","URL":"https://doi.org/10.5281/zenodo.19248288","source":"datacite"},{"id":"doi:10.5281/zenodo.19248287","type":"article-journal","title":"CLIMATE VARIABILITY AND SMALLHOLDER FARMING SYSTEMS: A STUDY OF AGRICULTURAL ADAPTATION IN AHMEDABAD DISTRICT, GUJARAT","abstract":"Increasing variability in rainfall and temperature has become a major challenge for agricultural communities, particularly in regions where farming depends heavily on monsoon rainfall. In India, smallholder farmers constitute a major share of the agrarian economy, and their dependence on monsoon-based cultivation exposes them significantly to climate stress. This study examines the effects of climate variability on agricultural productivity, income stability, and livelihood security among smallholder farmers residing near Ahmedabad, Gujarat. The research adopts a mixed-method case study approach combining quantitative and qualitative data. Primary data were collected from 120 farmers across four agro-climatic talukas—Sanand, Bavla, Viramgam, and Dholka—using structured questionnaires and interviews. Secondary climate data on rainfall, temperature, and extreme weather events from 2014 to June 2025 were analyzed. The results show intensifying climate fluctuations characterized by delayed monsoon onset, concentrated rainfall events, extended dry spells, and increasing heatwave frequency. These climatic disruptions reduced yields of cotton, cumin, bajra, castor, and wheat while increasing input costs, pest infestation, and dependence on irrigation. Consequently, household income declined, outstanding debt rose, and nearly half of the farming households reported supplemental migration. Adaptation strategies included crop diversification, drought-resistant seeds, micro-irrigation, crop insurance, and non-farm work; however, the coping mechanisms remain insufficient for long-term resilience. The study concludes that climate variability exacerbates agricultural vulnerability, emphasizing the need for climate-smart practices, localized institutional support, reliable crop insurance, and accessible weather advisory services to safeguard the livelihoods of smallholder farmers.","author":[{"family":"Dani","given":"Ca"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19248287","URL":"https://doi.org/10.5281/zenodo.19248287","source":"datacite"},{"id":"doi:10.5281/zenodo.19204116","type":"article-journal","title":"Federated Learning for Predictive Agriculture: A Privacy- Preserving Approach to Crop Disease Detection","abstract":"The growing adoption of smart farming technologies has led to the generation of large volumes of agricultural data, particularly for crop health monitoring and disease prediction. However, concerns over data privacy and ownership hinder the development of centralized machine learning models in agriculture. This paper proposes a novel framework that leverages Federated Learning (FL) to enable collaborative crop disease detection across multiple farms without sharing raw data. Each participating farm trains a local model on its proprietary image or sensor dataset, and only the model updates are aggregated to form a global model. This decentralized approach preserves data privacy while still leveraging the benefits of collective learning. We evaluate the proposed framework using benchmark plant disease datasets and simulate its deployment on edge devices typical in rural areas. The results demonstrate that federated learning achieves competitive accuracy compared to centralized models while offering robust privacy guarantees. This research paves the way for scalable, privacy-preserving AI solutions in precision agriculture, especially for low-resource and data-sensitive farming communities.","author":[{"family":"Sathwik","given":"Prof"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19204116","URL":"https://doi.org/10.5281/zenodo.19204116","source":"datacite"},{"id":"doi:10.5281/zenodo.19204117","type":"article-journal","title":"Federated Learning for Predictive Agriculture: A Privacy- Preserving Approach to Crop Disease Detection","abstract":"The growing adoption of smart farming technologies has led to the generation of large volumes of agricultural data, particularly for crop health monitoring and disease prediction. However, concerns over data privacy and ownership hinder the development of centralized machine learning models in agriculture. This paper proposes a novel framework that leverages Federated Learning (FL) to enable collaborative crop disease detection across multiple farms without sharing raw data. Each participating farm trains a local model on its proprietary image or sensor dataset, and only the model updates are aggregated to form a global model. This decentralized approach preserves data privacy while still leveraging the benefits of collective learning. We evaluate the proposed framework using benchmark plant disease datasets and simulate its deployment on edge devices typical in rural areas. The results demonstrate that federated learning achieves competitive accuracy compared to centralized models while offering robust privacy guarantees. This research paves the way for scalable, privacy-preserving AI solutions in precision agriculture, especially for low-resource and data-sensitive farming communities.","author":[{"family":"Sathwik","given":"Prof"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19204117","URL":"https://doi.org/10.5281/zenodo.19204117","source":"datacite"},{"id":"doi:10.5281/zenodo.19114902","type":"article-journal","title":"Sociological Perspectives on Disruptive Innovation: The Role of Co-Design in Agriphotovoltaics Adoption Among Farmers","abstract":"This book chapter considers technological advancements, especially in eco-friendly domains, that have significantly heightened social awareness, making community-driven participation essential. Disruptive innovations, as defined by Bower and Christensen (1995), have the power to transform entire sectors, but theirsuccess hinges on comprehensive societal understanding and acceptance. To overcome potential skepticism, it is increasingly vital to involve communities in the awareness and adoption of these innovations from the outset. Ramirez (2013) underscored the role of social networks in agricultural technology adoption, while Rose and Chilvers (2018) emphasized the importance of inclusive, responsible innovation in the era of smart farming. As energy and climate challenges intensify, theurgent need to engage all societal sectors in embracing new technologies becomes clear, particularly for solutions like agri-photovoltaics.The Horizon Europe REGACE Project exemplifies this by designing participation models that actively involve farmers in the development of agri-photovoltaic technologies. By prioritizing early and meaningful farmer involvement through different participatory techniques (interviews, open space technologies, world cafés), the project ensures that technological innovation is not imposed from the top down, but rather co-developed with the future users. This participatory approachtransforms the construction of technological innovation into a collaborative process, fostering a deeper awareness of the environmental sustainability of these actions (Antonucci, Sorice, Volterrani 2022, 2024). Recent studies (Spanaki, Sivarajah, Fakhimi Despoudi &amp; Irani, 2022) have shown that the agricultural sector benefits significantly from such community-driven support, ensuring a thorough understanding of the impact and a fair distribution of economic and social value.Referring to a global context dominated by the perspective of contentious politics, especially in the farming policy arena, this paper discusses the initial outcomes of farmer participation from five partner states in the REGACE project, analyzing the potential risks and benefits of this social- technological collaboration in the field of agriphotovoltaics, with a focus on the impact of farmers ‘participation in the technology co-design early stages. The first findings of the Project highlight thecritical role of bottom-up community participation in ensuring the successful adoption and integration of innovative agricultural technologies, due to the direct and active involvement in the technology co-design.","author":[{"family":"Antonucci","given":"Maria"},{"family":"Volterrani","given":"Andrea"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19114902","URL":"https://doi.org/10.5281/zenodo.19114902","source":"datacite"},{"id":"doi:10.5281/zenodo.19114903","type":"article-journal","title":"Sociological Perspectives on Disruptive Innovation: The Role of Co-Design in Agriphotovoltaics Adoption Among Farmers","abstract":"This book chapter considers technological advancements, especially in eco-friendly domains, that have significantly heightened social awareness, making community-driven participation essential. Disruptive innovations, as defined by Bower and Christensen (1995), have the power to transform entire sectors, but theirsuccess hinges on comprehensive societal understanding and acceptance. To overcome potential skepticism, it is increasingly vital to involve communities in the awareness and adoption of these innovations from the outset. Ramirez (2013) underscored the role of social networks in agricultural technology adoption, while Rose and Chilvers (2018) emphasized the importance of inclusive, responsible innovation in the era of smart farming. As energy and climate challenges intensify, theurgent need to engage all societal sectors in embracing new technologies becomes clear, particularly for solutions like agri-photovoltaics.The Horizon Europe REGACE Project exemplifies this by designing participation models that actively involve farmers in the development of agri-photovoltaic technologies. By prioritizing early and meaningful farmer involvement through different participatory techniques (interviews, open space technologies, world cafés), the project ensures that technological innovation is not imposed from the top down, but rather co-developed with the future users. This participatory approachtransforms the construction of technological innovation into a collaborative process, fostering a deeper awareness of the environmental sustainability of these actions (Antonucci, Sorice, Volterrani 2022, 2024). Recent studies (Spanaki, Sivarajah, Fakhimi Despoudi &amp; Irani, 2022) have shown that the agricultural sector benefits significantly from such community-driven support, ensuring a thorough understanding of the impact and a fair distribution of economic and social value.Referring to a global context dominated by the perspective of contentious politics, especially in the farming policy arena, this paper discusses the initial outcomes of farmer participation from five partner states in the REGACE project, analyzing the potential risks and benefits of this social- technological collaboration in the field of agriphotovoltaics, with a focus on the impact of farmers ‘participation in the technology co-design early stages. The first findings of the Project highlight thecritical role of bottom-up community participation in ensuring the successful adoption and integration of innovative agricultural technologies, due to the direct and active involvement in the technology co-design.","author":[{"family":"Antonucci","given":"Maria"},{"family":"Volterrani","given":"Andrea"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19114903","URL":"https://doi.org/10.5281/zenodo.19114903","source":"datacite"},{"id":"doi:10.14279/depositonce-23801","type":"article-journal","title":"Smart microgrids and agriculture in the global energy transformation discourse: a model for the Maghreb countries","abstract":"In agriculture, smart microgrids offer innovative solutions to energy challenges, enabling more sustainable and reliable power supply for farming operations. This dissertation investigates sustainable farming through decentralized energy systems, emphasizing the opportunities and barriers within the Water-Energy-Food (WEF) nexus approach in Maghreb’s energy transformation. It addresses four fundamental research questions: 1) What are the potential benefits and challenges of integrating renewable energy resources into the WEF nexus? 2) How can a demand-side management approach be effectively modelled and applied to a microgrid farm in Morocco? 3) What are the broader implications of macro models for microgrid connections in Morocco on the WEF nexus? 4) What are the implications and business models of microgrid applications in agriculture, particularly within the context of Algerian farms? To answer these questions, this dissertation moves between global, national, and local levels, reflecting on the existing interdependencies and potential feedback loops as the integration of renewable energy resources into agricultural practices evolves. An interdisciplinary methodology is employed, combining quantitative and qualitative research frameworks. This includes the use of modelling, case studies, surveys, literature reviews, and statistical data analysis. This comprehensive approach allows for a multifaceted examination of the drivers and barriers to integrating renewable energy into agriculture and offers robust policy recommendations to facilitate this transition. The dissertation systematically describes and quantifies the scenario space for renewable energy integration into the WEF nexus, evaluates key opportunities and barriers, and proposes policy responses and strategies to enhance sustainable farming through decentralized energy systems. It makes significant contributions to the literature on sustainable agriculture, renewable energy integration, and the WEF nexus by advancing the understanding of current developments and trends in these areas, providing projections that consider complex demand and supply interactions, and introducing novel methodologies for assessing the impacts of renewable energy integration on agricultural practices. In conclusion, this work aims to improve the understanding of the effects of renewable energy integration on the WEF nexus and to develop policy recommendations that support sustainable agricultural practices. By addressing the unique challenges and opportunities in Algeria and Morocco, this dissertation offers valuable insights for policymakers and practitioners aiming to foster sustainable development through innovative energy solutions.","author":[{"family":"Agadi","given":"Redha"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14279/depositonce-23801","URL":"https://doi.org/10.14279/depositonce-23801","source":"datacite"},{"id":"doi:10.5281/zenodo.19093053","type":"article-journal","title":"Impact of Technological Intervention in Milk Production","abstract":"This study investigates the impact of technological interventions on milk production efficiency and sustainability. Traditional dairy farming faces numerous challenges, including low productivity, high labour costs, and inconsistent milk quality. With the rapid advancement of automation, artificial intelligence (AI), Internet of Things (IoT), and smart farming tools, there is increasing interest in their potential to address these challenges. In this research, we examine the application of automated milking systems, AI-driven monitoring, and sensor-based technologies in enhancing operational efficiency and improving milk quality. The results indicate a significant improvement in milk yield, with a reduction in labour costs and improved milk quality parameters such as somatic cell count and fat content. These findings highlight the transformative potential of these technologies in the dairy industry, suggesting that their wider adoption could lead to more sustainable and cost-effective dairy farming practices. The study also provides valuable insights into the future of precision agriculture and the increasing role of digital tools in agriculture. The research underscores the importance of technological integration for dairy farmers and outlines future avenues for technological advancements in dairy farming.","author":[{"family":"Sharma","given":"Dr"},{"family":"Kumari","given":"Rolly"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19093053","URL":"https://doi.org/10.5281/zenodo.19093053","source":"datacite"},{"id":"doi:10.5281/zenodo.19093052","type":"article-journal","title":"Impact of Technological Intervention in Milk Production","abstract":"This study investigates the impact of technological interventions on milk production efficiency and sustainability. Traditional dairy farming faces numerous challenges, including low productivity, high labour costs, and inconsistent milk quality. With the rapid advancement of automation, artificial intelligence (AI), Internet of Things (IoT), and smart farming tools, there is increasing interest in their potential to address these challenges. In this research, we examine the application of automated milking systems, AI-driven monitoring, and sensor-based technologies in enhancing operational efficiency and improving milk quality. The results indicate a significant improvement in milk yield, with a reduction in labour costs and improved milk quality parameters such as somatic cell count and fat content. These findings highlight the transformative potential of these technologies in the dairy industry, suggesting that their wider adoption could lead to more sustainable and cost-effective dairy farming practices. The study also provides valuable insights into the future of precision agriculture and the increasing role of digital tools in agriculture. The research underscores the importance of technological integration for dairy farmers and outlines future avenues for technological advancements in dairy farming.","author":[{"family":"Sharma","given":"Dr"},{"family":"Kumari","given":"Rolly"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19093052","URL":"https://doi.org/10.5281/zenodo.19093052","source":"datacite"},{"id":"doi:10.5281/zenodo.19017256","type":"article-journal","title":"SMART AGRICULTURE MONITORING USING INTERNET OF THINGS TECHNOLOGY","abstract":"Agriculture has been an indispensable element of every nation for an extended period. Plant cultivation can be approached from both a scientific and an artistic perspective. Modern farming has to change if it wants to keep up with the rapidly developing technology world. An essential part of smart farming is the Internet of Things. With the help of IoT sensors, crucial information on agricultural areas can be gathered. Connecting wireless sensor networks, gathering data from sensors in various locations, and communicating the data via a wireless protocol allows the monitoring of agricultural activity made possible by the Internet of Things (IoT). Using the NodeMCU platform, the intelligent agricultural gadget is controlled by the Internet of Things. A DC engine powers the gadget, which also has sensors for temperature, humidity, and wetness. This device measures the relative humidity and moisture content of the air. When the water level drops below a certain threshold, which is controlled by the system, self-watering begins. Variations in temperature are required for the display to work. The IoT gives weather reports that include the current date and time in addition to the temperature and precipitation totals. The individual commodities being cultivated determine whether temperature regulation is viable.","author":[{"family":"Transformation","given":"Emerging"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19017256","URL":"https://doi.org/10.5281/zenodo.19017256","source":"datacite"},{"id":"doi:10.5281/zenodo.19017257","type":"article-journal","title":"SMART AGRICULTURE MONITORING USING INTERNET OF THINGS TECHNOLOGY","abstract":"Agriculture has been an indispensable element of every nation for an extended period. Plant cultivation can be approached from both a scientific and an artistic perspective. Modern farming has to change if it wants to keep up with the rapidly developing technology world. An essential part of smart farming is the Internet of Things. With the help of IoT sensors, crucial information on agricultural areas can be gathered. Connecting wireless sensor networks, gathering data from sensors in various locations, and communicating the data via a wireless protocol allows the monitoring of agricultural activity made possible by the Internet of Things (IoT). Using the NodeMCU platform, the intelligent agricultural gadget is controlled by the Internet of Things. A DC engine powers the gadget, which also has sensors for temperature, humidity, and wetness. This device measures the relative humidity and moisture content of the air. When the water level drops below a certain threshold, which is controlled by the system, self-watering begins. Variations in temperature are required for the display to work. The IoT gives weather reports that include the current date and time in addition to the temperature and precipitation totals. The individual commodities being cultivated determine whether temperature regulation is viable.","author":[{"family":"Transformation","given":"Emerging"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19017257","URL":"https://doi.org/10.5281/zenodo.19017257","source":"datacite"},{"id":"doi:10.5281/zenodo.19016817","type":"article-journal","title":"Federated Learning for Predictive Agriculture: A Privacy- Preserving Approach to Crop Disease Detection","abstract":"The growing adoption of smart farming technologies has led to the generation of large volumes of agricultural data, particularly for crop health monitoring and disease prediction. However, concerns over data privacy and ownership hinder the development of centralized machine learning models in agriculture. This paper proposes a novel framework that leverages Federated Learning (FL) to enable collaborative crop disease detection across multiple farms without sharing raw data. Each participating farm trains a local model on its proprietary image or sensor dataset, and only the model updates are aggregated to form a global model. This decentralized approach preserves data privacy while still leveraging the benefits of collective learning. We evaluate the proposed framework using benchmark plant disease datasets and simulate its deployment on edge devices typical in rural areas. The results demonstrate that federated learning achieves competitive accuracy compared to centralized models while offering robust privacy guarantees. This research paves the way for scalable, privacy-preserving AI solutions in precision agriculture, especially for low-resource and data-sensitive farming communities.","author":[{"family":"Sathwik","given":"Chebrolu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19016817","URL":"https://doi.org/10.5281/zenodo.19016817","source":"datacite"},{"id":"doi:10.5281/zenodo.19016818","type":"article-journal","title":"Federated Learning for Predictive Agriculture: A Privacy- Preserving Approach to Crop Disease Detection","abstract":"The growing adoption of smart farming technologies has led to the generation of large volumes of agricultural data, particularly for crop health monitoring and disease prediction. However, concerns over data privacy and ownership hinder the development of centralized machine learning models in agriculture. This paper proposes a novel framework that leverages Federated Learning (FL) to enable collaborative crop disease detection across multiple farms without sharing raw data. Each participating farm trains a local model on its proprietary image or sensor dataset, and only the model updates are aggregated to form a global model. This decentralized approach preserves data privacy while still leveraging the benefits of collective learning. We evaluate the proposed framework using benchmark plant disease datasets and simulate its deployment on edge devices typical in rural areas. The results demonstrate that federated learning achieves competitive accuracy compared to centralized models while offering robust privacy guarantees. This research paves the way for scalable, privacy-preserving AI solutions in precision agriculture, especially for low-resource and data-sensitive farming communities.","author":[{"family":"Sathwik","given":"Chebrolu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19016818","URL":"https://doi.org/10.5281/zenodo.19016818","source":"datacite"},{"id":"doi:10.6084/m9.figshare.31611781","type":"article-journal","title":"The local food paradox: why sustainable food advocates resist controlled environment agriculture","abstract":"Smart farms use advanced technologies to grow crops indoors without soil, offering environmental benefits such as reduced transportation distances and lower water consumption. However, consumers who prefer local food may resist these products. This study examines this ‘local food paradox’ among South Korean consumers. We surveyed 1,247 consumers and used latent class analysis to identify distinct consumer groups based on their technology acceptance, resistance to food technology, and local food values. Three groups emerged: Technology Enthusiasts (37.0%), who strongly support smart farming due to its perceived safety and efficiency benefits; Conflicted Moderates (25.0%), who hold mixed views balancing technological advantages against traditional values; and Tradition-Oriented Skeptics (38.0%), who prioritize terroir and authenticity and reject smart farm products despite their environmental advantages. Interestingly, consumers who frequently purchase organic food or shop at farmers’ markets were more likely to belong to the skeptical group, confirming the local food paradox: those most committed to sustainable food consumption may resist the most environmentally efficient production method. Prior experience with smart farm products, environmental concern, and health consciousness also significantly influenced group membership. These findings suggest that expanding the smart farm market requires tailored communication strategies. For technology-oriented consumers, emphasizing innovation and safety is effective. For tradition-oriented consumers, messaging should focus on freshness and community connections rather than technical features. This study contributes to understanding why sustainable food technology faces consumer resistance rooted not in fear of novelty, but in deeper conflicts over what constitutes authentic food.","author":[{"family":"You","given":"Jae"},{"family":"Choi","given":"Jong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.31611781","URL":"https://doi.org/10.6084/m9.figshare.31611781","source":"datacite"},{"id":"doi:10.6084/m9.figshare.31611781.v1","type":"article-journal","title":"The local food paradox: why sustainable food advocates resist controlled environment agriculture","abstract":"Smart farms use advanced technologies to grow crops indoors without soil, offering environmental benefits such as reduced transportation distances and lower water consumption. However, consumers who prefer local food may resist these products. This study examines this ‘local food paradox’ among South Korean consumers. We surveyed 1,247 consumers and used latent class analysis to identify distinct consumer groups based on their technology acceptance, resistance to food technology, and local food values. Three groups emerged: Technology Enthusiasts (37.0%), who strongly support smart farming due to its perceived safety and efficiency benefits; Conflicted Moderates (25.0%), who hold mixed views balancing technological advantages against traditional values; and Tradition-Oriented Skeptics (38.0%), who prioritize terroir and authenticity and reject smart farm products despite their environmental advantages. Interestingly, consumers who frequently purchase organic food or shop at farmers’ markets were more likely to belong to the skeptical group, confirming the local food paradox: those most committed to sustainable food consumption may resist the most environmentally efficient production method. Prior experience with smart farm products, environmental concern, and health consciousness also significantly influenced group membership. These findings suggest that expanding the smart farm market requires tailored communication strategies. For technology-oriented consumers, emphasizing innovation and safety is effective. For tradition-oriented consumers, messaging should focus on freshness and community connections rather than technical features. This study contributes to understanding why sustainable food technology faces consumer resistance rooted not in fear of novelty, but in deeper conflicts over what constitutes authentic food.","author":[{"family":"You","given":"Jae"},{"family":"Choi","given":"Jong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.31611781.v1","URL":"https://doi.org/10.6084/m9.figshare.31611781.v1","source":"datacite"},{"id":"doi:10.5281/zenodo.18897144","type":"article-journal","title":"DEEP LEARNING–BASED EARLY DETECTION OF PLANT DISEASES FOR SUSTAINABLE SMART GARDENING","abstract":"Early detection of plant diseases is really important for keeping crops healthy and helping people garden in away that's good for the environment. In the few years there have been a lot of advances in artificial intelligenceespecially deep learning that have made it possible to use pictures to automatically diagnose plant diseases.Usually people have to look at the plants by hand and use their knowledge to figure out what is wrong whichcan take a time and is not always accurate. This can be a problem for people who have gardens or farms in cities.So there is a need for systems that can find plant diseases on and do it correctly. This study is a way to use deeplearning to find plant diseases early which can help people garden in a smart and sustainable way. We usedsomething called neural network models, which were trained on pictures of plant leaves to tell the differencebetween healthy and diseased plants. We did some things to the pictures to make the models work better likemaking them smaller normalizing them and adding data. We then checked how well the system worked bylooking at things like how accurate it was how precise it was and its recall and F1-score. Other studies haveshown that deep learning models can be very good at figuring out what is wrong with plants when they aretrained on a lot of pictures. The results show that deep learning models are much faster and more reliable thanlooking at plants by eye. If we can use these systems in gardening platforms we can catch diseases early reducethe number of crops that are lost and help people take care of their plants in a way that is good for theenvironment. This study is part of a group of research, on using artificial intelligence in farming and shows howdeep learning can help. Plant diseases are a problem and using deep learning to detect plant diseases can make abig difference.","author":[{"family":"Sodikova","given":"Zakhro"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18897144","URL":"https://doi.org/10.5281/zenodo.18897144","source":"datacite"},{"id":"doi:10.5281/zenodo.18897145","type":"article-journal","title":"DEEP LEARNING–BASED EARLY DETECTION OF PLANT DISEASES FOR SUSTAINABLE SMART GARDENING","abstract":"Early detection of plant diseases is really important for keeping crops healthy and helping people garden in away that's good for the environment. In the few years there have been a lot of advances in artificial intelligenceespecially deep learning that have made it possible to use pictures to automatically diagnose plant diseases.Usually people have to look at the plants by hand and use their knowledge to figure out what is wrong whichcan take a time and is not always accurate. This can be a problem for people who have gardens or farms in cities.So there is a need for systems that can find plant diseases on and do it correctly. This study is a way to use deeplearning to find plant diseases early which can help people garden in a smart and sustainable way. We usedsomething called neural network models, which were trained on pictures of plant leaves to tell the differencebetween healthy and diseased plants. We did some things to the pictures to make the models work better likemaking them smaller normalizing them and adding data. We then checked how well the system worked bylooking at things like how accurate it was how precise it was and its recall and F1-score. Other studies haveshown that deep learning models can be very good at figuring out what is wrong with plants when they aretrained on a lot of pictures. The results show that deep learning models are much faster and more reliable thanlooking at plants by eye. If we can use these systems in gardening platforms we can catch diseases early reducethe number of crops that are lost and help people take care of their plants in a way that is good for theenvironment. This study is part of a group of research, on using artificial intelligence in farming and shows howdeep learning can help. Plant diseases are a problem and using deep learning to detect plant diseases can make abig difference.","author":[{"family":"Sodikova","given":"Zakhro"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18897145","URL":"https://doi.org/10.5281/zenodo.18897145","source":"datacite"},{"id":"oa:W4409376493","type":"article-journal","title":"Land Inequality, Farm Size, and Productivity: Insights From Peruvian Agriculture","abstract":"ABSTRACT This paper investigates the analogous land inequality and farm size‐productivity relationships, focusing on agricultural total factor productivity (TFP) rather than partial productivity measures. Using a panel of 268 Peruvian districts over a 5‐year period (2015–2019), I implement a system generalized method of moments (GMM) estimation framework, which adapts to the presumed data‐generating process and structure of the panel while tackling the critical issue of simultaneity bias. The regression output supports both relationships, with a 0.6% increase in agricultural TFP for every one‐percentage point reduction of the land Gini coefficient or a one‐hectare decrease in average farm size. Moreover, an assessment of the potential impact of land quality heterogeneity and measurement error reveals that neither issue appears to bias the results. Finally, the role of rural reform is discussed, emphasizing the need to weigh the moral considerations of equal opportunity to land of the land‐poor against the legitimate property rights of the land‐rich on a case‐by‐case basis.","author":[{"family":"Borrero","given":"Hernán"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1111/agec.70036","URL":"https://doi.org/10.1111/agec.70036","source":"openalex"},{"id":"oa:W4411793436","type":"article-journal","title":"Sustainable Agricultural Development under the Influence of Technology: A Case Study of Bihar","abstract":"Achieving “Zero Hunger,” one of the core Sustainable Development Goals (SDGs) adopted by the United Nations in 2015, necessitates transformative changes in agricultural systems through sustainable practices and resilient technologies. This study examines the influence of farm technologies and supporting infrastructure on agricultural value-added(GVA) in Bihar, a predominantly agrarian and economically underdeveloped state in India, utilizing time series data from 2000 to 2024. Employing advanced econometric models, dynamic simulations, and impulse response analyses, the research identifies key structural drivers and constraints of agricultural growth in the region. Technological advancement is shown to be a primary driver, with mechanization, improved seed varieties, multi-cropping, and agroforestry practices significantly enhancing land productivity. Capital stock investment exhibits a direct and positive elasticity (0.59%), with its impact persisting up to eight years before diminishing, underscoring the need for periodic reinvestment. Mechanization alone accounts for a 32% contribution to GVA, signalling a transition toward labour-saving technologies. Arable land expansion and sustainable practices also play a pivotal role, contributing 21% to agricultural GVA. Conversely, irrigation infrastructure and chemical fertilizers reveal mixed or negative short-term effects, likely due to inefficient application or ecological constraints. Variables such as labour, credit, forest area, and energy consumption are found to be statistically insignificant. The findings advocate for capital lifecycle management, precision farming, sustainable land use, targeted input application, and credit system reform. The study concludes that an integrated, evidence-based policy framework is essential to ensure sustained agricultural productivity, environmental stewardship, and the long-term realization of SDG-2 in Bihar.","author":[{"family":"Sinha","given":"Jitendra"},{"family":"Sinha","given":"Anurodh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55121/nc.v4i1.385","URL":"https://doi.org/10.55121/nc.v4i1.385","source":"openalex"},{"id":"oa:W4406289929","type":"article-journal","title":"AI in agriculture: Smart greenhouses and indoor farming systems","abstract":"This comprehensive article examines the transformative impact of artificial intelligence on modern indoor agriculture, focusing on key technological advancements in smart greenhouse management and controlled environment agriculture. The article explores critical areas, including precision environmental control, nutrient management in hydroponic systems, plant health monitoring and disease management, harvest optimization, quality control, and energy management with sustainability practices. AI-driven solutions have revolutionized traditional farming approaches by integrating deep learning algorithms, computer vision systems, and IoT sensor networks, enabling unprecedented levels of automation, resource efficiency, and crop yield optimization. Implementing these technologies has significantly improved agricultural metrics, from disease detection and prevention to harvest timing and quality assessment, while substantially reducing operational costs and environmental impact.","author":[{"family":"Payili","given":"Praveen"}],"issued":{"date-parts":[[2025]]},"DOI":"10.30574/ijsra.2025.14.1.0054","URL":"https://doi.org/10.30574/ijsra.2025.14.1.0054","source":"openalex"},{"id":"oa:W4407145146","type":"article-journal","title":"High-Precision Multi-Class Object Detection Using Fine-Tuned YOLOv11 Architecture: A Case Study on Airborne Vehicles","abstract":"The widespread adoption of airborne vehicles, including drones and UAVs, has brought significant advancements to fields such as surveillance, logistics, and disaster response. Despite these benefits, their increasing use poses substantial challenges for real-time detection and classification, particularly in multi-class scenarios where precision and scalability are essential. This paper proposes a high-performance detection framework based on YOLOv11, specifically tailored for identifying airborne vehicles. YOLOv11 integrates innovative features, such as anchor-free detection and enhanced attention mechanisms, to deliver superior accuracy and speed. The proposed framework is tested on a comprehensive airborne vehicle dataset featuring diverse conditions, including variations in altitude, occlusion, and environmental factors. Experimental results demonstrate that the fine-tuned YOLOv11 model exceeds the performance of existing models. Additionally, its ability to operate in real-time makes it ideal for critical applications like air traffic management and security monitoring.","author":[{"family":"Albalawi","given":"Nasser"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14569/ijacsa.2025.01601113","URL":"https://doi.org/10.14569/ijacsa.2025.01601113","source":"openalex"},{"id":"doi:10.5281/zenodo.21408205","type":"article-journal","title":"MULTI-PURPOSE AGRICULTURAL ROBOTIC VEHICLE","abstract":"This project focuses on the development of a multipurpose agricultural robotic vehicle designed to automate essential farming tasks. The system is capable of performing operations such as seed sowing, irrigation, and pesticide spraying using a microcontroller and sensor-based setup. It can be controlled remotely or operate autonomously, ensuring accurate and efficient field operations. The robot reduces human effort, saves time, and improves resource utilization. Overall, it offers a cost-effective and practical solution to enhance productivity in modern agriculture. (Abstract)","author":[{"family":"Mankal","given":"Dr"},{"family":"Rakshita","given":"G"},{"family":"Patil","given":"Shradha"},{"family":"Biradar","given":"Pragati"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21408205","URL":"https://doi.org/10.5281/zenodo.21408205","source":"datacite"},{"id":"doi:10.5281/zenodo.21408206","type":"article-journal","title":"MULTI-PURPOSE AGRICULTURAL ROBOTIC VEHICLE","abstract":"This project focuses on the development of a multipurpose agricultural robotic vehicle designed to automate essential farming tasks. The system is capable of performing operations such as seed sowing, irrigation, and pesticide spraying using a microcontroller and sensor-based setup. It can be controlled remotely or operate autonomously, ensuring accurate and efficient field operations. The robot reduces human effort, saves time, and improves resource utilization. Overall, it offers a cost-effective and practical solution to enhance productivity in modern agriculture. (Abstract)","author":[{"family":"Mankal","given":"Dr"},{"family":"Rakshita","given":"G"},{"family":"Patil","given":"Shradha"},{"family":"Biradar","given":"Pragati"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21408206","URL":"https://doi.org/10.5281/zenodo.21408206","source":"datacite"},{"id":"doi:10.5281/zenodo.21551251","type":"article-journal","title":"Tree Leaves Based Disease Prediction and Fertilizer Recommendation Using Deep Learning Algorithm","abstract":"Tree health is critical for maintaining ecological balance and sustaining diverse ecosystems. Early detection of diseases affecting tree leaves can aid in timely intervention and mitigation efforts. This paper proposes a novel approach to tree disease prediction based on deep learning, specifically the VGG16 convolutional neural network architecture and focuses on analyzing high-resolution images of tree leaves to determine whether they are healthy or infected with a specific disease. The methodology entails gathering a large dataset of images of tree leaves from various species and disease types. To improve the model's robustness and generalization, data preprocessing techniques such as image resizing, normalization, and augmentation are used. For feature extraction, the pre-trained VGG16 model is used, and the top layers are tailored to the tree disease prediction task. To improve its performance, the proposed model goes through rigorous training and validation processes. To assess the model's effectiveness in disease classification, metrics such as accuracy, precision, recall, and F1 score are used. The study's goal is to develop a dependable and efficient tool for arborists, foresters, and environmentalists to quickly identify and treat tree diseases. The findings of this paper provide advance precision agriculture and environmental monitoring by providing a scalable and automated solution for early tree disease detection. Furthermore, the paper investigates potential applications in real-world scenarios, fostering sustainable practices for global ecosystem preservation.","author":[{"family":"Maheshwari","given":"R"},{"family":"Banumathy","given":"D"},{"family":"Thiyagarajan","given":"P"},{"family":"Dhayalan","given":"RD"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5281/zenodo.21551251","URL":"https://doi.org/10.5281/zenodo.21551251","source":"datacite"},{"id":"doi:10.5281/zenodo.21551252","type":"article-journal","title":"Tree Leaves Based Disease Prediction and Fertilizer Recommendation Using Deep Learning Algorithm","abstract":"Tree health is critical for maintaining ecological balance and sustaining diverse ecosystems. Early detection of diseases affecting tree leaves can aid in timely intervention and mitigation efforts. This paper proposes a novel approach to tree disease prediction based on deep learning, specifically the VGG16 convolutional neural network architecture and focuses on analyzing high-resolution images of tree leaves to determine whether they are healthy or infected with a specific disease. The methodology entails gathering a large dataset of images of tree leaves from various species and disease types. To improve the model's robustness and generalization, data preprocessing techniques such as image resizing, normalization, and augmentation are used. For feature extraction, the pre-trained VGG16 model is used, and the top layers are tailored to the tree disease prediction task. To improve its performance, the proposed model goes through rigorous training and validation processes. To assess the model's effectiveness in disease classification, metrics such as accuracy, precision, recall, and F1 score are used. The study's goal is to develop a dependable and efficient tool for arborists, foresters, and environmentalists to quickly identify and treat tree diseases. The findings of this paper provide advance precision agriculture and environmental monitoring by providing a scalable and automated solution for early tree disease detection. Furthermore, the paper investigates potential applications in real-world scenarios, fostering sustainable practices for global ecosystem preservation.","author":[{"family":"Maheshwari","given":"R"},{"family":"Banumathy","given":"D"},{"family":"Thiyagarajan","given":"P"},{"family":"Dhayalan","given":"RD"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5281/zenodo.21551252","URL":"https://doi.org/10.5281/zenodo.21551252","source":"datacite"},{"id":"doi:10.5281/zenodo.21550606","type":"article-journal","title":"Optimizing IoT Networks in Smart Agriculture Using Probabilistic Models and Machine Learning Algorithms","abstract":"This study aims to enhance the performance of Internet of Things (IoT) networks in smart agriculture by integrating probabilistic models and machine learning algorithms. The research addresses the need for efficient, reliable, and scalable IoT infrastructures to support precision farming and sustainable agricultural practices in increasingly complex and data-intensive farming environments. A multi-faceted approach was employed, combining probabilistic modeling and machine learning techniques. IoT sensor networks were simulated using real-world agricultural data, supplemented by a small-scale field deployment. Bayesian networks and Hidden Markov Models were applied to capture system dynamics, while Random Forest, Support Vector Machines, and Long Short-Term Memory networks were used for pattern recognition and predictive analytics. Network performance was evaluated using metrics including latency, throughput, packet loss rate, energy efficiency, scalability, reliability, and data accuracy. The integrated approach significantly improved IoT network performance in agricultural settings. Key improvements include: 25% reduction in latency, 35% increase in throughput, 60% decrease in packet loss rate, 30% improvement in energy efficiency, and 6.5% increase in data accuracy. Adaptive routing algorithms, informed by machine learning predictions, were particularly effective in managing network load during peak agricultural seasons, reducing latency by 18% during these periods. The study relied primarily on simulations and limited field trials. Comprehensive real-world implementation across diverse agricultural environments and larger scale deployments is necessary to fully validate the findings. The research did not address potential cybersecurity challenges in optimized IoT networks, which remains an important area for future investigation.","author":[{"family":"Yadav","given":"Ramsagar"},{"family":"Manshahia","given":"Mukhdeep"},{"family":"Chaudhary","given":"MP"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5281/zenodo.21550606","URL":"https://doi.org/10.5281/zenodo.21550606","source":"datacite"},{"id":"doi:10.5281/zenodo.21550607","type":"article-journal","title":"Optimizing IoT Networks in Smart Agriculture Using Probabilistic Models and Machine Learning Algorithms","abstract":"This study aims to enhance the performance of Internet of Things (IoT) networks in smart agriculture by integrating probabilistic models and machine learning algorithms. The research addresses the need for efficient, reliable, and scalable IoT infrastructures to support precision farming and sustainable agricultural practices in increasingly complex and data-intensive farming environments. A multi-faceted approach was employed, combining probabilistic modeling and machine learning techniques. IoT sensor networks were simulated using real-world agricultural data, supplemented by a small-scale field deployment. Bayesian networks and Hidden Markov Models were applied to capture system dynamics, while Random Forest, Support Vector Machines, and Long Short-Term Memory networks were used for pattern recognition and predictive analytics. Network performance was evaluated using metrics including latency, throughput, packet loss rate, energy efficiency, scalability, reliability, and data accuracy. The integrated approach significantly improved IoT network performance in agricultural settings. Key improvements include: 25% reduction in latency, 35% increase in throughput, 60% decrease in packet loss rate, 30% improvement in energy efficiency, and 6.5% increase in data accuracy. Adaptive routing algorithms, informed by machine learning predictions, were particularly effective in managing network load during peak agricultural seasons, reducing latency by 18% during these periods. The study relied primarily on simulations and limited field trials. Comprehensive real-world implementation across diverse agricultural environments and larger scale deployments is necessary to fully validate the findings. The research did not address potential cybersecurity challenges in optimized IoT networks, which remains an important area for future investigation.","author":[{"family":"Yadav","given":"Ramsagar"},{"family":"Manshahia","given":"Mukhdeep"},{"family":"Chaudhary","given":"MP"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5281/zenodo.21550607","URL":"https://doi.org/10.5281/zenodo.21550607","source":"datacite"},{"id":"doi:10.48350/183550","type":"article-journal","title":"Stress tolerance in entomopathogenic nematodes: Engineering superior nematodes for precision agriculture.","abstract":"Entomopathogenic nematodes (EPNs) are soil-dwelling parasitic roundworms commonly used as biocontrol agents of insect pests in agriculture. EPN dauer juveniles locate and infect a host in which they will grow and multiply until resource depletion. During their free-living stage, EPNs face a series of internal and environmental stresses. Their ability to overcome these challenges is crucial to determine their infection success and survival. In this review, we provide a comprehensive overview of EPN response to stresses associated with starvation, low/elevated temperatures, desiccation, osmotic stress, hypoxia, and ultra-violet light. We further report EPN defense strategies to cope with biotic stressors such as viruses, bacteria, fungi, and predatory insects. By comparing the genetic and biochemical basis of these strategies to the nematode model Caenorhabditis elegans, we provide new avenues and targets to select and engineer precision nematodes adapted to specific field conditions.","author":[{"family":"Maushe","given":"Dorothy"},{"family":"Ogi","given":"Vera"},{"family":"Divakaran","given":"Keerthi"},{"family":"Verdecia Mogena","given":"Arletys"},{"family":"Himmighofen","given":"Paul"},{"family":"Machado","given":"Ricardo"},{"family":"Towbin","given":"Benjamin"},{"family":"Ehlers","given":"Ralf"},{"family":"Molina","given":"Carlos"},{"family":"Parisod","given":"Christian"},{"family":"Robert","given":"Christelle"}],"issued":{"date-parts":[[2023]]},"DOI":"10.48350/183550","URL":"https://doi.org/10.48350/183550","source":"datacite"},{"id":"doi:10.48350/177971","type":"article-journal","title":"Towards evolutionary predictions: Current promises and challenges.","abstract":"Evolution has traditionally been a historical and descriptive science, and predicting future evolutionary processes has long been considered impossible. However, evolutionary predictions are increasingly being developed and used in medicine, agriculture, biotechnology and conservation biology. Evolutionary predictions may be used for different purposes, such as to prepare for the future, to try and change the course of evolution or to determine how well we understand evolutionary processes. Similarly, the exact aspect of the evolved population that we want to predict may also differ. For example, we could try to predict which genotype will dominate, the fitness of the population or the extinction probability of a population. In addition, there are many uses of evolutionary predictions that may not always be recognized as such. The main goal of this review is to increase awareness of methods and data in different research fields by showing the breadth of situations in which evolutionary predictions are made. We describe how diverse evolutionary predictions share a common structure described by the predictive scope, time scale and precision. Then, by using examples ranging from SARS-CoV2 and influenza to CRISPR-based gene drives and sustainable product formation in biotechnology, we discuss the methods for predicting evolution, the factors that affect predictability and how predictions can be used to prevent evolution in undesirable directions or to promote beneficial evolution (i.e. evolutionary control). We hope that this review will stimulate collaboration between fields by establishing a common language for evolutionary predictions.","author":[{"family":"Wortel","given":"Meike"},{"family":"Agashe","given":"Deepa"},{"family":"Bailey","given":"Susan"},{"family":"Bank","given":"Claudia"},{"family":"Bisschop","given":"Karen"},{"family":"Blankers","given":"Thomas"},{"family":"Cairns","given":"Johannes"},{"family":"Colizzi","given":"Enrico"},{"family":"Cusseddu","given":"Davide"},{"family":"Desai","given":"Michael"},{"family":"Van Dijk","given":"Bram"},{"family":"Egas","given":"Martijn"},{"family":"Ellers","given":"Jacintha"},{"family":"Groot","given":"Astrid"},{"family":"Heckel","given":"David"},{"family":"Johnson","given":"Marcelle"},{"family":"Kraaijeveld","given":"Ken"},{"family":"Krug","given":"Joachim"},{"family":"Laan","given":"Liedewij"},{"family":"Lässig","given":"Michael"},{"family":"Lind","given":"Peter"},{"family":"Meijer","given":"Jeroen"},{"family":"Noble","given":"Luke"},{"family":"Okasha","given":"Samir"},{"family":"Rainey","given":"Paul"},{"family":"Rozen","given":"Daniel"},{"family":"Shitut","given":"Shraddha"},{"family":"Tans","given":"Sander"},{"family":"Tenaillon","given":"Olivier"},{"family":"Teotónio","given":"Henrique"},{"family":"De Visser","given":"JAGM"},{"family":"Visser","given":"Marcel"},{"family":"Vroomans","given":"Renske"},{"family":"Werner","given":"Gijsbert"},{"family":"Wertheim","given":"Bregje"},{"family":"Pennings","given":"Pleuni"}],"issued":{"date-parts":[[2023]]},"DOI":"10.48350/177971","URL":"https://doi.org/10.48350/177971","source":"datacite"},{"id":"doi:10.48350/188791","type":"article-journal","title":"From microbiome composition to functional engineering, one step at a time.","abstract":"SUMMARYCommunities of microorganisms (microbiota) are present in all habitats on Earth and are relevant for agriculture, health, and climate. Deciphering the mechanisms that determine microbiota dynamics and functioning within the context of their respective environments or hosts (the microbiomes) is crucially important. However, the sheer taxonomic, metabolic, functional, and spatial complexity of most microbiomes poses substantial challenges to advancing our knowledge of these mechanisms. While nucleic acid sequencing technologies can chart microbiota composition with high precision, we mostly lack information about the functional roles and interactions of each strain present in a given microbiome. This limits our ability to predict microbiome function in natural habitats and, in the case of dysfunction or dysbiosis, to redirect microbiomes onto stable paths. Here, we will discuss a systematic approach (dubbed the N+1/N-1 concept) to enable step-by-step dissection of microbiome assembly and functioning, as well as intervention procedures to introduce or eliminate one particular microbial strain at a time. The N+1/N-1 concept is informed by natural invasion events and selects culturable, genetically accessible microbes with well-annotated genomes to chart their proliferation or decline within defined synthetic and/or complex natural microbiota. This approach enables harnessing classical microbiological and diversity approaches, as well as omics tools and mathematical modeling to decipher the mechanisms underlying N+1/N-1 microbiota outcomes. Application of this concept further provides stepping stones and benchmarks for microbiome structure and function analyses and more complex microbiome intervention strategies.","author":[{"family":"Burz","given":"Sebastian"},{"family":"Causevic","given":"Senka"},{"family":"Dal Co","given":"Alma"},{"family":"Dmitrijeva","given":"Marija"},{"family":"Engel","given":"Philipp"},{"family":"Garrido-Sanz","given":"Daniel"},{"family":"Greub","given":"Gilbert"},{"family":"Hapfelmeier","given":"Siegfried"},{"family":"Hardt","given":"Wolf"},{"family":"Hatzimanikatis","given":"Vassily"},{"family":"Heiman","given":"Clara"},{"family":"Herzog","given":"Mathias"},{"family":"Hockenberry","given":"Alyson"},{"family":"Keel","given":"Christoph"},{"family":"Keppler","given":"Andreas"},{"family":"Lee","given":"Soon"},{"family":"Luneau","given":"Julien"},{"family":"Malfertheiner","given":"Lukas"},{"family":"Mitri","given":"Sara"},{"family":"Ngyuen","given":"Bidong"},{"family":"Oftadeh","given":"Omid"},{"family":"Pacheco","given":"Alan"},{"family":"Peaudecerf","given":"François"},{"family":"Resch","given":"Grégory"},{"family":"Ruscheweyh","given":"Hans"},{"family":"Sahin","given":"Asli"},{"family":"Sanders","given":"Ian"},{"family":"Slack","given":"Emma"},{"family":"Sunagawa","given":"Shinichi"},{"family":"Tackmann","given":"Janko"},{"family":"Tecon","given":"Robin"},{"family":"Ugolini","given":"Giovanni"},{"family":"Vacheron","given":"Jordan"},{"family":"Van Der Meer","given":"Jan"},{"family":"Vayena","given":"Evangelia"},{"family":"Vonaesch","given":"Pascale"},{"family":"Vorholt","given":"Julia"}],"issued":{"date-parts":[[2023]]},"DOI":"10.48350/188791","URL":"https://doi.org/10.48350/188791","source":"datacite"},{"id":"doi:10.7910/dvn/vtpo4u","type":"article-journal","title":"2020 - CSA Monitoring: Olopa Climate-Smart Village (Guatemala)","abstract":"&lt;p align=\"justify\"&gt;This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Olopa Climate Smart Village (Guatemala) in February 2020.&lt;/p&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;br&gt; &lt;ul&gt; &lt;li&gt;Adoption of CSA practices and technologies, as well as access to climate information services and &lt;li&gt;their related impacts at household level (and farm level, in selected sites). &lt;/ul&gt; &lt;br&gt; This framework proposes standard Descriptive Indicators to track changes in: &lt;br&gt; &lt;ul type=\"circle\"&gt; &lt;li&gt; 5 enabling dimensions that might affect adoption patterns, &lt;/li&gt; &lt;li&gt;a set of 6 CORE indicators at Household level to assess perceived effects of CSA practices on Food Security, Productivity, Income and Climate vulnerability and &lt;/li&gt; &lt;li&gt;4 CORE indicators on Gender aspects (Participation in decision-making, Participation in implementation, Access/control over Resources and work time). &lt;/li&gt; &lt;li&gt;At farm level, 7 CORE indicators are suggested to determine farms CSA performance, as well as synergies and trade-offs among the three pillars This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real- time. &lt;/li&gt; &lt;/ul&gt; &lt;br&gt; The framework responds to three main research questions: &lt;br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt;Within each CSV community, who adopts which CSA technologies and practices and what are their motivations, enabling/constraining factors?&lt;/li&gt; &lt;li value=\"2\"&gt;What are the gender-disaggregated perceived effects of CSA options on farmers’ livelihood (agricultural production, income, food security, food diversity and adaptive capacity) and on key gender dimensions (participation in decision-making, participation in CSA implementation and dis-adoption, control and access over resources and labour)?&lt;/li&gt; &lt;li value=\"3\"&gt;How does CSA perform at farm level, and what synergies and trade-offs exist (whole farm model analysis)? &lt;/li&gt; &lt;/ol&gt; &lt;br&gt; &lt;p align=\"justify\"&gt;The survey questionnaire is structured around different thematic modules (M1A Demographic, M1B Farming system, M2 Climate events, M3, Climate Information Services, M4 Food Security, M5 CSA practices) whose questions allow assessing standard CSA metrics and the specific indicators associated with the research questions 1 and 2. Data required for assessing farm level CSA performance are collected through the Farm, the Crop and the Animals Calculator modules. &lt;/p&gt;","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Jarvis","given":"Andy"},{"family":"Andrieu","given":"Nadine"},{"family":"Martínez- Barón","given":"Deissy"},{"family":"Martínez-Salgado","given":"Jesus"},{"family":"Lopez","given":"Claudia"}],"issued":{"date-parts":[[2020]]},"DOI":"10.7910/dvn/vtpo4u","URL":"https://doi.org/10.7910/dvn/vtpo4u","source":"datacite"},{"id":"doi:10.7910/dvn/syifeo","type":"article-journal","title":"2021- IFAD-UE/CCAFS CSA Monitoring: Kaffrine Climate-Smart Village (Senegal)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Kaffrine Climate Smart Village (Senegal) in February 2021 &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; (Note that this 3d. question was not addressed in this specific Basona Werana 2021 monitoring, as farm level data were not collected) &lt;/br&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions. &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labor, Decision making and control on CSA generated income). &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frecuency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; At farm level, 7 CORE indicators &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core indicators are used to determine the CSA performance of the farms as well as synergies and trade-offs among the three pillars (productivity, adaptation and mitigation, via farm model analysis). &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. The survey questionnaire is structured around different thematic modules. &lt;/br&gt; &lt;br&gt; For the West Africa i","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Ouedraogo","given":"Mathieu"},{"family":"Zougmoré","given":"Robert"},{"family":"Laderach","given":"Peter"},{"family":"Sall","given":"Moussa"}],"issued":{"date-parts":[[2021]]},"DOI":"10.7910/dvn/syifeo","URL":"https://doi.org/10.7910/dvn/syifeo","source":"datacite"},{"id":"doi:10.7910/dvn/osntkt","type":"article-journal","title":"2020 - CSA Monitoring: Santa Rita Climate-Smart Village (Honduras)","abstract":"&lt;p align=\"justify\"&gt;This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Santa Rita Climate Smart Village (Honduras) in February 2020. &lt;/p&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;br&gt; &lt;ul&gt; &lt;li&gt; Adoption of CSA practices and technologies, as well as access to climate information services and &lt;li&gt; their related impacts at household level (and farm level, in selected sites). &lt;/ul&gt; &lt;br&gt; This framework proposes standard Descriptive Indicators to track changes in: &lt;br&gt; &lt;ul type=\"circle\"&gt; &lt;li&gt;5 enabling dimensions that might affect adoption patterns, &lt;/li&gt; &lt;li&gt;a set of 6 CORE indicators at Household level to assess perceived effects of CSA practices on Food Security, Productivity, Income and Climate vulnerability and &lt;/li&gt; &lt;li&gt;4 CORE indicators on Gender aspects (Participation in decision-making, Participation in implementation, Access/control over Resources and work time). &lt;/li&gt; &lt;li&gt;At farm level, 7 CORE indicators are suggested to determine farms CSA performance, as well as synergies and trade-offs among the three pillars.&lt;/li&gt; &lt;/ul&gt; &lt;br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real- time. &lt;br&gt; The framework responds to three main research questions: &lt;br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt;Within each CSV community, who adopts which CSA technologies and practices and what are their motivations, enabling/constraining factors?&lt;/li&gt; &lt;li value=\"2\"&gt;What are the gender-disaggregated perceived effects of CSA options on farmers’ livelihood (agricultural production, income, food security, food diversity and adaptive capacity) and on key gender dimensions (participation in decision-making, participation in CSA implementation and dis-adoption, control and access over resources and labour)?&lt;/li&gt; &lt;li value=\"3\"&gt;How does CSA perform at farm level, and what synergies and trade-offs exist (whole farm model analysis)? &lt;/li&gt; &lt;/ol&gt; &lt;br&gt; The survey questionnaire is structured around different thematic modules (M1A Demographic, M1B Farming system, M1D Financial Services, M2 Climate events, M3, Climate Information Services, M4 Food Security, M5 CSA practices) whose questions allow assessing standard CSA metrics and the specific indicators associated with the research questions 1 and 2. Data required for assessing farm level CSA performance are collected through the Farm, the Crop and the Animals Calculator modules.","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Andrieu","given":"Nadine"},{"family":"Jarvis","given":"Andy"},{"family":"Martínez- Barón","given":"Deissy"},{"family":"Martínez-Salgado","given":"Jesus"},{"family":"Alvarez-Espinosa","given":"Osman"}],"issued":{"date-parts":[[2020]]},"DOI":"10.7910/dvn/osntkt","URL":"https://doi.org/10.7910/dvn/osntkt","source":"datacite"},{"id":"doi:10.7910/dvn/hvun1u","type":"article-journal","title":"2021- IFAD-UE/CCAFS CSA Monitoring: Fakara Climate-Smart Village (Niger)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Fakara Climate Smart Village (Niger) in February 2021 &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; (Note that this 3d. question was not addressed in this specific Basona Werana 2021 monitoring, as farm level data were not collected) &lt;/br&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions. &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labor, Decision making and control on CSA generated income). &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frecuency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; At farm level, 7 CORE indicators &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core indicators are used to determine the CSA performance of the farms as well as synergies and trade-offs among the three pillars (productivity, adaptation and mitigation, via farm model analysis). &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. The survey questionnaire is structured around different thematic modules. &lt;/br&gt; &lt;br&gt; For the West Africa imple","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Ouedraogo","given":"Mathieu"},{"family":"Zougmoré","given":"Robert"},{"family":"Laderach","given":"Peter"},{"family":"Tougiani","given":"Abasse"}],"issued":{"date-parts":[[2021]]},"DOI":"10.7910/dvn/hvun1u","URL":"https://doi.org/10.7910/dvn/hvun1u","source":"datacite"},{"id":"doi:10.7910/dvn/f5ez7b","type":"article-journal","title":"2019 - CSA Monitoring: Kaffrine Climate-Smart Village (Senegal)","abstract":"&lt;p align=\"justify\"&gt;This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Kaffrine Climate Smart Village (Senegal) in November 2019. &lt;/p&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;br&gt; &lt;ul&gt; &lt;li&gt;adoption of CSA practices and technologies, as well as access to climate information services and &lt;li&gt;their related impacts at household level and farm level &lt;/ul&gt; &lt;br&gt; This framework proposes standard Descriptive Indicators to track changes in: &lt;br&gt; &lt;ul type=\"circle\"&gt; &lt;li&gt;5 enabling dimensions that might affect adoption patterns, &lt;/li&gt; &lt;li&gt;a set of 5 CORE indicators at Household level to assess perceived effects of CSA practices on Food Security, Productivity, Income and Climate vulnerability and &lt;/li&gt; &lt;li&gt;4 CORE indicators on Gender aspects (Participation in decision-making, Participation in implementation, Access/control over Resources and work time). &lt;/li&gt; &lt;li&gt;At farm level, 7 CORE indicators are suggested to determine farms CSA performance, as well as synergies and trade-offs among the three pillars. &lt;/li&gt; &lt;/ul&gt; &lt;br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. &lt;br&gt; The framework responds to three main research questions: &lt;br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt;Within each CSV community, who adopts which CSA technologies and practices and what are their motivations, enabling/constraining factors? &lt;/li&gt; &lt;li value=\"2\"&gt;What are the gender-disaggregated perceived effects of CSA options on farmers’ livelihood (agricultural production, income, food security, food diversity and adaptive capacity) and on key gender dimensions (participation in decision-making, participation in CSA implementation and dis-adoption, control and access over resources and labour)? &lt;/li&gt; &lt;li value=\"3\"&gt;How does CSA perform at farm level, and what synergies and trade-offs exist (whole farm model analysis)? &lt;/li&gt; &lt;/ol&gt; &lt;br&gt; &lt;p align=\"justify\"&gt;The survey questionnaire is structured around different thematic modules (M1A Demographic, M1B Farming system, M1C Financial services, M2 Climate events, M3, Climate Information Services, M4 Food Security, M5 CSA practices) whose questions allow assessing standard CSA metrics and the specific indicators associated with the research questions 1 and 2. Data required for assessing farm level CSA performance are collected through the Farm, the Crop, the animals and the Tree Calculator modules. &lt;/p&gt;","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Andrieu","given":"Nadine"},{"family":"Jarvis","given":"Andy"},{"family":"Ouedraogo","given":"Mathieu"},{"family":"Zougmoré","given":"Robert"},{"family":"Mamadou","given":"Fall"},{"family":"Adeyemi","given":"Chabi"}],"issued":{"date-parts":[[2020]]},"DOI":"10.7910/dvn/f5ez7b","URL":"https://doi.org/10.7910/dvn/f5ez7b","source":"datacite"},{"id":"doi:10.7910/dvn/ellgkb","type":"article-journal","title":"2021- CSA Monitoring: Hoima Climate-Smart Village (Uganda)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Hoima Climate Smart Village (Uganda) in October 2021. &lt;/br&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;/br&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;/br&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions). &lt;/li type=\"circle\"&gt; &lt;/br&gt; &lt;/ul&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labour, Decision making and control on CSA generated income). &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frequency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; At farm level, 7 CORE indicators &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core indicators are used to determine the CSA performance of the farms as well as synergies and trade-offs among the three pillars (productivity, adaptation and mitigation, via farm model analysis). &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;/ol&gt; This integrated framework (Bonilla-Findji et al 2021).is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time &lt;/br&gt; &lt;br&gt; The survey questionnaire is structured around different thematic modules (M1A Demographic, M1B Farming system, M1C Financial services, M2 Climate events, M3, Climate Information Services, M4 Food Security, M5 CSA practices; Farm Calculator,","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Andrieu","given":"Nadine"},{"family":"Läderach","given":"Peter"},{"family":"Recha","given":"John"},{"family":"Ambaw","given":"Gebermedihin"},{"family":"Kakeeto","given":"Ronald"}],"issued":{"date-parts":[[2022]]},"DOI":"10.7910/dvn/ellgkb","URL":"https://doi.org/10.7910/dvn/ellgkb","source":"datacite"},{"id":"doi:10.7910/dvn/a9smp1","type":"article-journal","title":"2021- CSA Monitoring/Midline: Santa Rita Climate-Smart Village (Honduras)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the “adjusted” implementation (see Note below) of the standard “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Santa Rita Climate-Smart Village (Honduras) in August-September 2021 &lt;/br&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;/br&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;/br&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; (Note that this 3d. question was not addressed in this specific 2021 monitoring, as farm level data were not collected) &lt;/br&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions). &lt;/li type=\"circle\"&gt; &lt;/br&gt; &lt;/ul&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labour, Decision making and control on CSA generated income). &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frequency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. The survey questionnaire is structured around different thematic modules. &lt;/br&gt; &lt;br&gt; For the Latin America implementation, some slight changes were made to specific modules of the questionnaire, related to site-specific data collection needs: &lt;/br&gt; &lt;/br&gt; &lt;ul style= \"list-style-type: square\"&gt; &lt;li&gt; In the demographic module (M1A): Five additional questions coming from the CCAFS Baseline/Midline questionnaire were added (HHG","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Martínez-Barón","given":"Deissy"},{"family":"Martínez-Salgado","given":"Jesus"},{"family":"Alvarez-Espinosa","given":"Osman"}],"issued":{"date-parts":[[2022]]},"DOI":"10.7910/dvn/a9smp1","URL":"https://doi.org/10.7910/dvn/a9smp1","source":"datacite"},{"id":"doi:10.7910/dvn/73lca6","type":"article-journal","title":"2021- CSA Monitoring/Midline: Olopa Climate-Smart Village (Guatemala)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the “adjusted” implementation (see Note below) of the standard “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Olopa Climate-Smart Village (Guatemala) in August-September 2021 &lt;/br&gt; &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;/br&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;/br&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; (Note that this 3d. question was not addressed in this specific 2021 monitoring, as farm level data were not collected) &lt;/br&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions). &lt;/li type=\"circle\"&gt; &lt;/br&gt; &lt;/ul&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labour, Decision making and control on CSA generated income). &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frequency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. The survey questionnaire is structured around different thematic modules. &lt;/br&gt; &lt;br&gt; For the Latin America implementation, some slight changes were made to specific modules of the questionnaire, related to site-specific data collection needs: &lt;/br&gt; &lt;/br&gt; &lt;ul style= \"list-style-type: square\"&gt; &lt;li&gt; In the demographic module (M1A): Five additional questions coming from the CCAFS Baseline/Midline questionnaire were added (HHGT60;","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Martínez-Barón","given":"Deissy"},{"family":"Martínez-Salgado","given":"Jesus"},{"family":"Lopez","given":"Claudia"},{"family":"Guevara","given":"Melvin"}],"issued":{"date-parts":[[2022]]},"DOI":"10.7910/dvn/73lca6","URL":"https://doi.org/10.7910/dvn/73lca6","source":"datacite"},{"id":"doi:10.7910/dvn/2tkdpe","type":"article-journal","title":"2021- IFAD-UE/CCAFS CSA Monitoring: Cinzana Climate-Smart Village (Mali)","abstract":"&lt;p align=\"justify\"&gt; This dataset contains the files produced in the implementation of the “Integrated Monitoring Framework for Climate-Smart Agriculture” in the Cinzana Climate Smart Village (Mali) in February 2021 &lt;br&gt; This monitoring framework developed by CCAFS is meant to be deployed annually across the global network of Climate-Smart Villages to gather field-based evidence by tracking the progress on: &lt;/br&gt; &lt;ul&gt; &lt;li&gt; adoption of CSA practices and technologies, as well as access to climate information services and &lt;/li&gt; &lt;li&gt; their related impacts at household level and farm level &lt;/li&gt; &lt;/ul&gt; The CSA framework allows to address three key research questions: &lt;/br&gt; &lt;ol&gt; &lt;li value=\"1\"&gt; Who within each CSV community adopts which CSA technologies and practices and which are their motivations, enabling factors? To which extent farmers access and use climate information services? &lt;/li value=\"1\"&gt; &lt;li value=\"2\"&gt; Which is the gender-disaggregated perceived effects of CSA options on farmers’ livelihood, agricultural, food security and adaptive capacity, and on key gender dimensions (participation in decision making, participation in CSA implementation and dis-adoption, control and access over resources and labour). &lt;/li value=\"2\"&gt; &lt;li value=\"3\"&gt; Which are the CSA performance, synergies and trade-offs found at farm level? &lt;/li value=\"3\"&gt; &lt;br&gt; (Note that this 3d. question was not addressed in this specific Basona Werana 2021 monitoring, as farm level data were not collected) &lt;/br&gt; &lt;br&gt; The CSA framework proposes a small set of standard Core Indicators linked to the research questions, and Extended indicators covering aspects related to the enabling environment. At household level (17 Core indicators): &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core Uptake indicators (they track CSA Implementation and adoption drivers; CSA dis-adoption and drivers; Access to climate information services and agro-advisories, Capacity to use them and constraining factors). &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; 10 Core Outcome indicators (they track farmers perceptions on the effects of CSA practices on their Livelihoods, Food Security and Adaptive Capacity and on Gender dimensions. &lt;/li type=\"circle\"&gt; &lt;li type=\"circle\"&gt; Those include namely: CSA effect on yield/production, on Income, on Improved Food Access and Food Diversity, on Vulnerability to weather related shocks and on Changes in agricultural activities induced by access to climate information. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; Four are Gender related Outcome indicators (Decision-making on CSA implementation or dis-adoption, Participation in CSA implementation, CSA effect on labor, Decision making and control on CSA generated income). &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; An additional set of complementary Extended indicators allows to determine and track changes in enabling conditions and farmers characteristics such as: Livelihood security, Financial enablers, Food security, Frecuency of climate events, Coping strategies, Risk Mitigation Actions, Access to financial services and Training, CSA Knowledge and Learning. &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; At farm level, 7 CORE indicators &lt;/br&gt; &lt;br&gt; &lt;ul&gt; &lt;li type=\"circle\"&gt; 7 Core indicators are used to determine the CSA performance of the farms as well as synergies and trade-offs among the three pillars (productivity, adaptation and mitigation, via farm model analysis). &lt;/li type=\"circle\"&gt; &lt;/ul&gt; &lt;/br&gt; &lt;br&gt; This integrated framework is associated with a cost-effective data collection App (Geofarmer) that allowed capturing information in almost real time. The survey questionnaire is structured around different thematic modules. &lt;/br&gt; &lt;br&gt; For the West Africa imple","author":[{"family":"Bonilla-Findji","given":"Osana"},{"family":"Eitzinger","given":"Anton"},{"family":"Ouedraogo","given":"Mathieu"},{"family":"Zougmoré","given":"Robert"},{"family":"Laderach","given":"Peter"},{"family":"Dembélé","given":"Siaka"}],"issued":{"date-parts":[[2021]]},"DOI":"10.7910/dvn/2tkdpe","URL":"https://doi.org/10.7910/dvn/2tkdpe","source":"datacite"},{"id":"doi:10.5167/uzh-226081","type":"article-journal","title":"Opportunities of 5G Mobile Technology for Climate Protection in Switzerland","abstract":"5G mobile networks are intended to meet the increasing requirements placed on mobile communications. Producing and operating 5G infrastructure causes direct effects on greenhouse gas (GHG) emissions. Meanwhile, 5G is expected to support applications that contribute to GHG abatement. We investigated (i) the GHG footprint of 5G infrastructure, and (ii) the GHG abatement potential of four 5G-supported use cases (i.e., flexible work, smart grids, automated driving and precision farming) for Switzerland in 2030. Our results show that 5G infrastructure is expected to cause 0.018 Mt CO2 e/year. Per unit of data transmitted, 5G is expected to cause 85% less GHG emissions in 2030 than today’s 2G/3G/4G network mix. The four 5G-supported use cases have the potential to avoid up to 2.1 Mt CO2 e/year; clearly more than the predicted GHG footprint of 5G infrastructure. The use cases benefit especially from ultra-low latency, the possibility to connect many devices, high reliability, mobility, availability and security provided by 5G. To put 5G at the service of climate protection, measures should be taken in two fields. First, the GHG footprint of 5G should be kept small, by installing only as much 5G infrastructure as required, running 5G with electricity from renewable energy sources, and decommissioning older network technologies once 5G is widely available. Second, the GHG abatements enabled by 5G-supported use cases should be unleashed by creating conditions that target GHG reductions and mitigate rebound effects. The final outcome depends largely on the political will to steer the development into the direction of a net GHG reduction.","author":[{"family":"Bieser","given":"Jan"},{"family":"Salieri","given":"Beatrice"},{"family":"Hischier","given":"Roland"},{"family":"Hilty","given":"Lorenz"}],"issued":{"date-parts":[[2023]]},"DOI":"10.5167/uzh-226081","URL":"https://doi.org/10.5167/uzh-226081","source":"datacite"},{"id":"doi:10.6084/m9.figshare.27315924","type":"article-journal","title":"Compendium of Youth and Women Engagement in Economic and Entrepreneurial Activities in Northeast Nigeria","abstract":"The Compendium of Youth and Women Engagement in Economic and Entrepreneurial Activities in Northeast Nigeria is a detailed documentation of the Feed the Future Nigeria Integrated Agriculture Activity. This USAID-supported initiative began on July 19, 2019, aiming to restore economic stability in Northeast Nigeria after the Boko Haram insurgency. The Activity engaged vulnerable populations in farming with climate-smart agriculture, good agronomic practices (GAP), nutrition-sensitive interventions, and entrepreneurship. It focuses on long-term economic growth, emphasizing youth and women while building resilience in the region's agricultural systems. The project works in collaboration with public and private sectors to improve market systems, services, and nutrition in the conflict-affected states of Adamawa, Borno, Gombe, and Yobe","author":[{"family":"Quadri","given":"Shakiru"},{"family":"Silwal","given":"Prakash"},{"family":"Faleti","given":"Olukayode"},{"family":"Archibong","given":"Bassey"},{"family":"Luwa","given":"Sini"},{"family":"Ali","given":"Aishatu"},{"family":"Jibrilla","given":"Adamu"},{"family":"Boniface","given":"Godwin"}],"issued":{"date-parts":[[2024]]},"DOI":"10.6084/m9.figshare.27315924","URL":"https://doi.org/10.6084/m9.figshare.27315924","source":"datacite"},{"id":"doi:10.14279/depositonce-15610","type":"article-journal","title":"Comprehensive Review on Climate Control and Cooling Systems in Greenhouses under Hot and Arid Conditions","abstract":"This work is motivated by the difficulty of cultivating crops in horticulture greenhouses under hot and arid climate conditions. The main challenge is to provide a suitable greenhouse indoor environment, with sufficiently low costs and low environmental impacts. The climate control inside the greenhouse constitutes an efficient methodology for maintaining a satisfactory environment that fulfills the requirements of high-yield crops and reduced energy and water resource consumption. In hot climates, the cooling systems, which are assisted by an effective control technique, constitute a suitable path for maintaining an appropriate climate inside the greenhouse, where the required temperature and humidity distribution is maintained. Nevertheless, most of the commonly used systems are either highly energy or water consuming. Hence, the main objective of this work is to provide a detailed review of the research studies that have been carried out during the last few years, with a specific focus on the technologies that allow for the enhancement of the system effectiveness under hot and arid conditions, and that decrease the energy and water consumption. Climate control processes in the greenhouse by means of manual and smart control systems are investigated first. Subsequently, the different cooling technologies that provide the required ranges of temperature and humidity inside the greenhouse are detailed, namely, the systems using heat exchangers, ventilation, evaporation, and desiccants. Finally, the recommended energy-efficient approaches of the desiccant dehumidification systems for greenhouse farming are pointed out, and the future trends in cooling systems, which include water recovery using the method of combined evaporation–condensation, as well as the opportunities for further research and development, are identified as a contribution to future research work.","author":[{"family":"Soussi","given":"Meriem"},{"family":"Chaibi","given":"Mohamed"},{"family":"Buchholz","given":"Martin"},{"family":"Saghrouni","given":"Zahia"}],"issued":{"date-parts":[[2022]]},"DOI":"10.14279/depositonce-15610","URL":"https://doi.org/10.14279/depositonce-15610","source":"datacite"},{"id":"doi:10.14279/depositonce-15641","type":"article-journal","title":"Digital Transformation in Smart Farm and Forest Operations Needs Human-Centered AI: Challenges and Future Directions","abstract":"The main impetus for the global efforts toward the current digital transformation in almost all areas of our daily lives is due to the great successes of artificial intelligence (AI), and in particular, the workhorse of AI, statistical machine learning (ML). The intelligent analysis, modeling, and management of agricultural and forest ecosystems, and of the use and protection of soils, already play important roles in securing our planet for future generations and will become irreplaceable in the future. Technical solutions must encompass the entire agricultural and forestry value chain. The process of digital transformation is supported by cyber-physical systems enabled by advances in ML, the availability of big data and increasing computing power. For certain tasks, algorithms today achieve performances that exceed human levels. The challenge is to use multimodal information fusion, i.e., to integrate data from different sources (sensor data, images, *omics), and explain to an expert why a certain result was achieved. However, ML models often react to even small changes, and disturbances can have dramatic effects on their results. Therefore, the use of AI in areas that matter to human life (agriculture, forestry, climate, health, etc.) has led to an increased need for trustworthy AI with two main components: explainability and robustness. One step toward making AI more robust is to leverage expert knowledge. For example, a farmer/forester in the loop can often bring in experience and conceptual understanding to the AI pipeline—no AI can do this. Consequently, human-centered AI (HCAI) is a combination of “artificial intelligence” and “natural intelligence” to empower, amplify, and augment human performance, rather than replace people. To achieve practical success of HCAI in agriculture and forestry, this article identifies three important frontier research areas: (1) intelligent information fusion; (2) robotics and embodied intelligence; and (3) augmentation, explanation, and verification for trusted decision support. This goal will also require an agile, human-centered design approach for three generations (G). G1: Enabling easily realizable applications through immediate deployment of existing technology. G2: Medium-term modification of existing technology. G3: Advanced adaptation and evolution beyond state-of-the-art.","author":[{"family":"Holzinger","given":"Andreas"},{"family":"Saranti","given":"Anna"},{"family":"Angerschmid","given":"Alessa"},{"family":"Retzlaff","given":"Carl"},{"family":"Gronauer","given":"Andreas"},{"family":"Pejakovic","given":"Vladimir"},{"family":"Medel-Jimenez","given":"Francisco"},{"family":"Krexner","given":"Theresa"},{"family":"Gollob","given":"Christoph"},{"family":"Stampfer","given":"Karl"}],"issued":{"date-parts":[[2022]]},"DOI":"10.14279/depositonce-15641","URL":"https://doi.org/10.14279/depositonce-15641","source":"datacite"},{"id":"doi:10.6084/m9.figshare.12249485.v1","type":"article-journal","title":"Bi-objective optimization of multi-server intermodal hub-locationallocation problem in congested systems modeling and solution .pdf","abstract":"A new multi-objective intermodal hub-location-allocation problem is modeled in this paper in which both the origin and the destination hub facilities are modeled as an M/M/m queuing system. The problem is being formulated as a constrained bi-objective optimization model to minimize the total costs as well as minimizing the total system time. A small-size problem is solved on the GAMS software to validate the accuracy of the proposed model. As the problem becomes strictly NP-hard, an MOIWO algorithm with an efficient chromosome structure and a fuzzy dominance method is proposed to solve large-scale problems. Since there is no benchmark available in the literature, an NSGA-II and an NRGA are developed to validate the results obtained. The parameters of all algorithms are tuned using the Taguchi method and their performances are statistically compared in terms of some multi-objective metrics. Finally, the entropy-TOPSIS method is applied to show that MOIWO is the best in terms of simultaneous use of all the metrics.","author":[{"family":"Seifbarghy","given":"Mehdi"},{"family":"Kahag","given":"Mahdi"},{"family":"Niaki","given":"Seyed"},{"family":"Zabihi","given":"Sina"}],"issued":{"date-parts":[[2020]]},"DOI":"10.6084/m9.figshare.12249485.v1","URL":"https://doi.org/10.6084/m9.figshare.12249485.v1","source":"datacite"},{"id":"oa:W3198518056","type":"article-journal","title":"Development of High-tech Agriculture in the Context of Industrialization and Urbanization: The Case of Vietnam","abstract":"The aim of this article is to assess the importance and development of high-tech agriculture in Vietnam under the context of industrialization and urbanization. Due to pressure from international economic integration and climate change in recent years, high-tech agriculture seems to be an affordable direction for Vietnam to renovate the agricultural sector. Although high-tech agriculture has existed in different locals and sub-sectors of agriculture such as crop, livestock, and aquaculture, and Vietnam has obtained initial achievements in adopting high-tech agriculture, this country has to face a number of challenges related to land, credit, information technology, and human resources in the process of developing high-tech agriculture. Lastly, policies are recommended to facilitate the development of high-tech agriculture in Vietnam.","author":[{"family":"Nguyen","given":"Anh"},{"family":"Cuong","given":"Tran"},{"family":"Huyen","given":"Vu"}],"issued":{"date-parts":[[2021]]},"DOI":"10.31817/vjas.2020.3.3.01","URL":"https://doi.org/10.31817/vjas.2020.3.3.01","source":"openalex"},{"id":"doi:10.1007/s11119-026-10377-y","type":"article-journal","title":"Web services for non-target area assessment and economic benchmarking in precision spraying","abstract":"Abstract This paper presents optimised web services for automatic assistance systems designed for precision pesticide application. By automating the planning, application, documentation and evaluation stages of the pesticide application process, the study seeks to ease the workload on farmers, supporting practical implementation of precision spraying workflows. Specifically, the study addresses two complementary developments: (1) the optimisation of the assistance system through enhancement of an existing geodata-based web service for improved identification of non-target areas, and (2) the development of an automated economic benchmarking web service that enables farmers to assess the economic performance of pesticide application strategies. Validation of the LiDAR-based component using 25 sample plots and 2,400 validation points yielded an overall accuracy of 93.5% and a Cohen’s kappa of 0.816, while the economic benchmarking service was technically validated using a simulated network of 44 test fields. Together, these developments provide a technical basis for improved environmental planning and structured economic assessment in precision spraying. This study presents the development and technical validation of two web services for precision spraying decision support. It does not yet evaluate long-term on-farm adoption effects under operational conditions.","author":[{"family":"Karpinski","given":"Isabella"},{"family":"Nordheim","given":"Stephan"},{"family":"Perić","given":"Zvonimir"},{"family":"Golla","given":"Burkhard"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10377-y","URL":"https://doi.org/10.1007/s11119-026-10377-y","source":"crossref"},{"id":"doi:10.71026/ls.2025.02005","type":"article-journal","title":"Design and Validation of Wireless Soil Monitoring System for Precision Crop Management","abstract":"Precision crop management is essential for optimizing agricultural productivity and sustainability. This study presents the development of a multi-parameter soil wireless sensor monitoring system designed for real-time data collection to support precision agriculture. The system consists of sensor nodes that measure key soil parameters such as moisture, temperature, electrical conductivity (EC), pH, and nutrient levels (Nitrogen, Phosphorus, and Potassium). These sensor nodes, built with Arduino and Dragino LoRa Shields, communicate wirelessly via LoRa technology to a central gateway based on an ESP32 microcontroller. The gateway processes and forwards the collected data to a cloud server using the MQTT protocol. The cloud server, hosted on a Raspberry Pi, integrates InfluxDB for time-series data storage and Grafana for real-time data visualization, enabling farmers to access soil health information remotely. This architecture is optimized for low power consumption, long-range communication, and scalability, making it suitable for large agricultural fields. The system provides a cost-effective and efficient tool for monitoring soil conditions, enhancing resource management, and promoting sustainable farming practices by improving crop yield and reducing environmental impact.","author":[{"family":"Chanthaboury","given":"Thephalak"},{"family":"Panthongsy","given":"Phosy"},{"family":"Panyanouvong","given":"Nouanchanh"},{"family":"Lakanchanh","given":"Donekeo"},{"family":"Khongsomboon","given":"Khamphong"},{"family":"Thongphanh","given":"Phutsavanh"},{"family":"Southisombath","given":"Phouthong"},{"family":"Sengaloun","given":"Deth"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71026/ls.2025.02005","URL":"https://doi.org/10.71026/ls.2025.02005","source":"crossref"},{"id":"doi:10.1109/icaiss61471.2025.11041903","type":"article-journal","title":"A Data-Driven Crop Recommendation System with Explainable AI for Precision Agriculture","abstract":"In this paper, we presented a crop recommendation system for precision agriculture that is based on the machine learning models providing crop recommendations based on the environmental and soil context. Introducing Explainable AI (XAI) in the designed system using LIME, we hope to enhance the level of trust to its recommendations through the understanding of the process which goes into each of them by the farmers. This has been made possible by the system’s architecture that consists of backend in Flask and frontend in React. The system was subjected to a rigorous assessment of its reliability and efficiency once developed to obviate measurement errors and ensure its effectiveness and efficiency. Moreover, the feedback on the integration of XAI also reveals an enhancement of interpretability by demonstrating the explanations of such features as pH of the soil, temperature, and moisture of the soil to have a positive effect to the system. Besides improving the chances of accurate crop yields estimation, this approach enables an accurate assessment of farming inputs with regards to sustainability.","author":[{"family":"Karthik","given":"Moduguri"},{"family":"Nandini","given":"Ankenapalle"},{"family":"Vedha","given":"Pochamreddy"},{"family":"Latha","given":"AR"},{"family":"Sungheetha","given":"Akey"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icaiss61471.2025.11041903","URL":"https://doi.org/10.1109/icaiss61471.2025.11041903","source":"crossref"},{"id":"doi:10.1109/icicv64824.2025.11085980","type":"article-journal","title":"Enhancing Precision Agriculture: Deep Learning for Rice Leaf Disease Identification","abstract":"Although rice is a major crop in many countries, its stability depends on the ongoing health test to ensure food supply and develop permanent growing practices. Economic security and higher agricultural output are the outcomes of early disease detection of rice plant leaves. A deep learning architecture that combines the extractive and computationally efficient MobileNet network with DenseNet, EfficientNetV2 and ResNet50 networks for accurate classification aids in the diagnosis of rice leaf disease. Advanced enrichment metal pictures that undergo preprocessing with contrasting growth and noise reduction are essential for increased resistance of the model. Action may be taken by farmers before the diseases deteriorate thanks to the broad detection of the diseases of the plant, including a bacterial blight paired with explosion and brown spot. The performance assessment compares various architectural effectiveness using tough criteria, F1-score, accurate, recall and accuracy. The integration of deep learning technology brings major plant pathology improvements which allow sustainable practices and yield improvement and secure the food supply against disease threats.","author":[{"family":"Kadiri","given":"Padmaja"},{"family":"Manne","given":"Nikita"},{"family":"Katyayani","given":"Valipireddy"},{"family":"Prasad","given":"Achyutha"},{"family":"Kumar","given":"YR"},{"family":"Kumar","given":"Besta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icicv64824.2025.11085980","URL":"https://doi.org/10.1109/icicv64824.2025.11085980","source":"crossref"},{"id":"doi:10.1109/smartagrisusy68475.2025.11466880","type":"article-journal","title":"An Integrated Federated Learning and Blockchain Architecture for Model Adoption in Precision Livestock Systems","abstract":"Federated learning (FL) deployments in agricultural environments face two critical challenges, such as intermittent connectivity in rural areas and the lack of transparent governance of shared models. This paper proposes an Internet of Things (IoT)-Federated Learning-Blockchain architecture explicitly designed for intermittent, offline-capable operation (an “offline-first” approach) to address those challenges. In this system, IoT-enabled smart feeders equipped with RFID readers and load cells collect individual feed intake and weight data, which are transmitted to Raspberry Pi edge nodes for local processing and model updating. These edge nodes generate daily local models to correct measurement errors in feed intake estimations, and the resulting updates are aggregated at a gateway node using weighted FedAvg, even when one or more clients are temporarily offline. To ensure verifiability and trust, the aggregated models and metadata are recorded in a permissioned blockchain. Experimental simulations with three Raspberry Pi edge nodes, utilizing synthetic vectors to represent model parameters, confirmed that the architecture maintains operational continuity in the presence of client dropouts. At the same time, blockchain storage guarantees immutable traceability of model artifacts. Compared to conventional FL approaches, the proposed architecture achieves resilient performance in the presence of connectivity losses and provides robust end-to-end model governance. Blockchain integration further enhances the system by enabling verifiable and tamper-proof model storage with minimal latency remaining under 3.5 seconds per round, well within the operational needs of livestock data collection. This integration represents a novel contribution toward scalable, transparent, and resilient digital infrastructures for precision livestock farming.","author":[{"family":"Garro","given":"Ricardo"},{"family":"Wilson","given":"Cara"},{"family":"Pordomingo","given":"Anibal"},{"family":"Wibowo","given":"Santoso"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/smartagrisusy68475.2025.11466880","URL":"https://doi.org/10.1109/smartagrisusy68475.2025.11466880","source":"crossref"},{"id":"doi:10.33545/2664844x.2025.v7.i6c.453","type":"article-journal","title":"A study on applications of artificial intelligence in precision farming","abstract":"Precision farming, a data-driven approach to agriculture, leverages Artificial Intelligence (AI) to enhance efficiency, sustainability, and productivity. AI technologies, including machine learning, computer vision, and the Internet of Things (IoT), play a crucial role in real-time monitoring, predictive analytics, and automated decision-making. AI-driven systems analyze vast datasets from satellite imagery, drones, and soil sensors to optimize irrigation, fertilization, and pest control, reducing resource wastage while maximizing crop yields. The integration of AI-powered autonomous machinery and robotics further enhances precision, enabling targeted interventions with minimal human intervention. Machine learning models assist in disease prediction and early detection, allowing farmers to take preventive measures, thereby minimizing crop losses. Additionally, AI-powered climate forecasting helps mitigate risks associated with unpredictable weather patterns, improving resilience in agriculture. Technologies such as deep learning aid in weed detection and precision spraying, reducing the excessive use of herbicides and promoting environmental sustainability. Recent advancements in AI-powered decision-support systems offer tailored recommendations based on historical and real-time farm data, ensuring resource-efficient, cost-effective, and sustainable farming practices. The integration of AI in precision agriculture not only enhances crop quality and productivity but also promotes sustainable farming methods, reducing environmental degradation. As AI continues to evolve, its role in precision farming will be crucial in addressing global food security challenges and fostering a more resilient agricultural ecosystem.","author":[{"family":"Kohli","given":"Kriti"},{"family":"Parmar","given":"Kshitij"},{"family":"Maisnam","given":"Guneshori"},{"family":"Sharma","given":"Saurabh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/2664844x.2025.v7.i6c.453","URL":"https://doi.org/10.33545/2664844x.2025.v7.i6c.453","source":"crossref"},{"id":"doi:10.1109/icaitech66481.2025.11387542","type":"article-journal","title":"Real-Time Visual Detection of Water Leaks in Irrigation Networks Using Deep Learning: A Smart Solution for Precision Agriculture","abstract":"Rapid and accurate detection of water leaks is a critical challenge for preserving increasingly scarce water resources and ensuring sustainable irrigation. Traditional monitoring approaches for water networks, often based on manual inspections or localized sensors, face limitations in terms of cost, accuracy, and responsiveness. Recent advances in computer vision and deep learning open new perspectives for automated monitoring and for automating this process. In this work, we propose a water leak detection system based on the YOLOv11 model, designed to be lightweight and fast, capable of visually identifying areas with anomalies such as water flows or infiltrations in real time. The model was trained using real annotated images via Roboflow, covering diverse conditions. It achieves excellent results, with strong performance in accuracy, recall, and detection precision, outperforming several traditional detection methods reported in related studies. These results demonstrate the relevance of the proposed approach for automated and intelligent water management in agricultural contexts.","author":[{"family":"Ouadjih","given":"Khaldi"},{"family":"Slaoui-Hasnaoui","given":"Fouad"},{"family":"Georges","given":"Semaan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaitech66481.2025.11387542","URL":"https://doi.org/10.1109/icaitech66481.2025.11387542","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i1.11831","type":"article-journal","title":"PERTUMBUHAN DAN PRODUKSI CABAI MERAH KERITING PADA PENGAPLIKASIAN PGPR MELALUI PENERAPAN CITRA TERMAL UNTUK MENDETEKSI PENYAKIT LAYU FUSARIUM","abstract":"Tanaman cabai merah (Capsicum annuum L.) merupakan komoditas hortikultura yang banyak dibudidayakan karena memiliki nilai ekonomis tinggi. Teknologi pertanian 4.0 mulai digunakan untuk pengembangan metode deteksi dini penyakit tanaman, salah satunya penyakit layu fusarium yang bisa di deteksi menggunakan kamera termal. Pengendalian penyakit layu Fusarium dalam penelitian ini menggunakan formulasi PGPR. Penelitian ini bertujuan untuk mengetahui keefektifan PGPR dalam menekan penyakit layu fusarium terhadap pertumbuhan dan produksi tanaman cabai merah keriting serta mengetahui potensi kamera termal dalam mendeteksi penyakit layu fusarium. Penelitian ini menggunakan Rancangan Kelompok Lengkap Teracak faktor tunggal, yaitu pemberian PGPR dengan taraf yaitu P0 (dosis 0 ml), P1 (dosis 100 ml) dan P2 (dosis 200 ml). Hasil penelitian menunjukan bahwa pemberian PGPR tidak berpengaruh nyata terhadap komponen pertumbuhan yaitu tinggi tanaman dan jumlah daun, serta komponen produksi yaitu umur berbunga, jumlah buah, umur panen dan bobot buah. Namun, PGPR dapat mengurangi insidensi penyakit (P1, 40.74%) dan menekan keparahan penyakit (P2, 37.03%). Perlakuan yang mengalami penurunan jumlah daun tertinggi akibat penyakit layu fusarium adalah P0 dengan rataan akhir jumlah daun 390 helai. Kamera termal dapat mendeteksi suhu tanaman dan objek yang dideteksi dengan jelas sehingga dapat diketahui perbedaan suhu antar perlakuan yang menunjukan tingkat infeksi penyakit pada tanaman.","author":[{"family":"Arifah","given":"Dina"},{"family":"Budiman"},{"family":"Risnawati"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35760/jpp.2025.v9i1.11831","URL":"https://doi.org/10.35760/jpp.2025.v9i1.11831","source":"crossref"},{"id":"doi:10.1016/j.procs.2025.04.151","type":"article-journal","title":"Comparative Study of Plant Leaves Detection for Precision Agriculture using Machine Learning Techniques","abstract":"Crop production is an important factor in a country’s economic growth. The production of plants is greatly reduced by plant illnesses, which further decrease the quality of plants while charging farmer’s funds. The different section of a plant exhibit symptoms of plant diseases, however leaves are the most frequently seen area for spotting an infection. Extensive studies are conducted to perform precision agriculture and aid in the premature identification of phytopathology’s. This paper shows the comparative analysis for identifying healthy & unhealthy plant leaves images. The proposed methodology is a multi-step process tends to select optimal subset of features using nature inspired algorithm such as Binary Bat Algorithm (BBA), Whale Optimization Algorithm (WOA), and Particle Swarm Optimization (PSO). These features are utilized in classification method such as Artificial Neural Networks (ANN) and Support Vector Machine (SVM) for predictive analysis. The findings show that obtained result analysis is efficient and determines the predictive analysis.","author":[{"family":"Churamani","given":"Aishwarya"},{"family":"Singh","given":"Aakanksha"},{"family":"Sengar","given":"Ayushman"},{"family":"Bhandari","given":"Pratush"},{"family":"Vijh","given":"Surbhi"},{"family":"Kumar","given":"Sumit"},{"family":"Shahid","given":"Amaan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.procs.2025.04.151","URL":"https://doi.org/10.1016/j.procs.2025.04.151","source":"crossref"},{"id":"doi:10.1016/j.procs.2025.04.316","type":"article-journal","title":"A Relative Analysis for Plant Disease Detection with AI-Driven Techniques: Optimizing Precision Agriculture","abstract":"Vegetable crops play a vital role in ensuring global food security but are highly susceptible to a wide range of diseases, posing serious challenges to sustainable agriculture. Early and accurate detection of these diseases is essential for maintaining crop health and maximizing yields. In this research, four advanced deep learning models such as EfficientNetB0, InceptionV3, DenseNet121, and MobileNetV2 are evaluated focusing on their ability to identify plant diseases from images. EfficientNetB0 stood out as the top-performing model, achieving a validation accuracy of 96.4% and excelling across key metrics such as precision (94%), recall (96%), and F1-score (94.8%). Its success lies in its compound scaling method, which optimizes the model’s depth, width, and resolution, making it both accurate and efficient. MobileNetV2, though less accurate at 92.3%, is a solid alternative for environments with limited computational resources. InceptionV3 and DenseNet121 performed reasonably well, but their accuracy and training efficiency fell short compared to EfficientNetB0. Overall, EfficientNetB0 proved to be the most balanced and reliable model, offering strong performance and adaptability. Its ability to detect diseases accurately, while minimizing false positives, makes it well-suited for practical applications in agriculture. The efficiency of the model allows it to be deployed directly in the field using low-power devices, providing farmers with real-time disease detection capabilities. This work contributes to the growing field of technology enhanced agriculture by offering a reliable solution for early disease detection, ultimately improving crop protection and ensuring sustainable agricultural practices.","author":[{"family":"As","given":"Al"},{"family":"Al-Mahruqi","given":"Ali"},{"family":"Suresh","given":"Uma"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.procs.2025.04.316","URL":"https://doi.org/10.1016/j.procs.2025.04.316","source":"crossref"},{"id":"doi:10.1109/aistemedu67077.2025.11403916","type":"article-journal","title":"Using the Internet of Drones for Smart Agriculture Monitoring on Precision Manufacturing Empowered Framing","abstract":"The integration of drones into agricultural practices has transformed modern farming by enabling real-time monitoring and data-driven decision-making, enhancing efficiency and crop productivity. However, traditional agricultural monitoring methods often face challenges such as limited coverage, delayed data collection, and inefficient resource management. To address these issues, this study proposes the Drone-Agri Framework (DAF), which combines IoT sensor fusion with a swarm intelligence algorithm for smart agriculture monitoring. DAF enables coordinated drone operations, real-time sensing, and intelligent data analysis, ensuring precise monitoring of crop health, soil conditions, and environmental factors. By leveraging IoT-enabled drones and swarm intelligence, the framework enhances predictive analytics, reduces manual intervention, and optimizes resource allocation in precision manufacturing-empowered farming. Experimental evaluations demonstrate that the proposed method significantly improves monitoring accuracy, response time, and overall crop yield compared to conventional approaches. These findings highlight the potential of DAF to advance sustainable and efficient smart agriculture practices.","author":[{"family":"Kumar","given":"Amit"},{"family":"Ojha","given":"Varun"},{"family":"Kumar","given":"Anup"},{"family":"Krishnamoorthy","given":"Ramkumar"},{"family":"Dash","given":"Subhaprada"},{"family":"Rgokulnath"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/aistemedu67077.2025.11403916","URL":"https://doi.org/10.1109/aistemedu67077.2025.11403916","source":"crossref"},{"id":"doi:10.1109/icimtech67074.2025.11265213","type":"article-journal","title":"Detecting Rice Leaf Diseases with YOLOv8: A Scalable Solution for Precision Agriculture","abstract":"The issue of rice leaf diseases is a concern in food security within farming countries such as Indonesia. The conventional methods of inspection are usually tedious and filled with errors, making it preferable to incorporate a deep learning methodology. This study presents a novel implementation of YOLOv8 for rice disease classification using a hybrid dataset of 3,078 annotated images, combining public data and real-field samples from Kandri Village, Central Java, Indonesia. The targeted diseases include Brown Spot, Bacterial Leaf Blight, Leaf Smut, and Blast. Two variants of YOLOv8, YOLOv8n and YOLOv8s, were evaluated using F1-Score and mAP@50. It is conclusive that YOLOv8s outperformed YOLOv8n by achieving an F1-Score of 91.8% and mAP@50 of 84.2%. This can be attributed to the increased accuracy and deeper detection capabilities of the model. With the results of the confusion matrix analysis, it was confirmed there were high rates of accuracy concerning the dominant classes while having difficulties distinguishing the lesser represented diseases. Despite these limitations, the integration of diverse data sources and the real-time detection capability of YOLOv8s demonstrate its novel potential as a practical tool for field-ready rice disease detection.","author":[{"family":"Putri","given":"Angeline"},{"family":"Go","given":"Cindy"},{"family":"Hartono","given":"Sugiarto"},{"family":"Wicaksana","given":"Nico"},{"family":"Reyes","given":"Ian"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icimtech67074.2025.11265213","URL":"https://doi.org/10.1109/icimtech67074.2025.11265213","source":"crossref"},{"id":"doi:10.1016/j.procs.2025.12.041","type":"article-journal","title":"Smart technologies in precision agriculture: an overview","abstract":"In response to the increasing impact of climate change and the growing global population, sustainable and efficient agricultural practices are nowadays more critical than ever. This document aims to investigate the state of the art of connection technologies and sensors used in precision agriculture. Through a structured literature review, the main types of connectivity were identified, along with the main sensors used for each, their pros and cons, and their documented uses. Findings highlight the crucial role of Wireless Sensor Networks and Internet of Things connectivity for real-time agricultural monitoring. Multiple sensors, including optical, thermal, biometric, and air quality sensors, enable precise crop and livestock management. Real-world applications, such as smart irrigation, automated harvesting, and livestock health monitoring, demonstrate how these technologies can improve decision-making and resource efficiency. While acknowledging challenges such as high initial costs and the need for infrastructure, this study underscores the potential for agriculture to become more resilient, data-driven, and sustainable. Finally, the paper proposes a matrix in which the main uses cases found in literature are classified according to open versus closed field, long versus short application range and type of connectivity involved.","author":[{"family":"Mambrioni","given":"Marco"},{"family":"Tebaldi","given":"Letizia"},{"family":"Lysova","given":"Natalya"},{"family":"Volpi","given":"Andrea"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.procs.2025.12.041","URL":"https://doi.org/10.1016/j.procs.2025.12.041","source":"crossref"},{"id":"doi:10.1109/ictest64710.2025.11042416","type":"article-journal","title":"Federated Learning Based Crop Disease Detection in Precision Agriculture","abstract":"Crop diseases significantly impact agricultural productivity, necessitating early and accurate detection to minimize yield loss and enhance sustainability. This study presents a federated learning-based framework for detecting diseases in staple crops such as rice, wheat, and potatoes. By integrating deep learning models like MobileNetV2 and InceptionV3 within a federated learning setup, the proposed framework addresses limitations of traditional methods while preserving data privacy. A dataset of 4,500 images, spanning three crops each with two diseases and one healthy category, was used to improve model robustness and accuracy. Federated learning with MobileNetV2 achieved an accuracy rate of 97.00% by effectively identifying diseases of potato, wheat and rice. The framework’s advanced feature extraction and transfer learning capabilities enable efficient and real-time disease detection. The experimental results highlight the potential of federated learning to support sustainable agriculture and global food security by reducing crop losses and adapting to diverse local conditions while preserving data privacy.","author":[{"family":"Biju","given":"VG"},{"family":"Shihabudeen","given":"H"},{"family":"Devabalaji","given":"KR"},{"family":"Latheef","given":"MMA"},{"family":"Thomas","given":"Tenny"},{"family":"Mali","given":"Goutam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ictest64710.2025.11042416","URL":"https://doi.org/10.1109/ictest64710.2025.11042416","source":"crossref"},{"id":"doi:10.1109/sensors59705.2025.11330430","type":"article-journal","title":"RF-Powered Batteryless Plant Movement Sensor for Precision Agriculture","abstract":"Precision agriculture demands non-invasive, energy-efficient, and sustainable plant monitoring solutions. In this work, we present the design and implementation of a lightweight, batteryless plant movement sensor powered solely by radio frequency (RF) energy. This sensor targets Controlled Environment Agriculture (CEA) and utilizes inertial measurement units (IMUs) to monitor leaf motion, which correlates with plant physiological responses to environmental stress. By eliminating the battery, we reduce the ecological footprint, weight, and maintenance requirements, transitioning from lifetime-based to operation-based energy storage. Our design minimizes circuit complexity while enabling flexible, adaptive readout scheduling based on energy availability and sensor data. We detail the energy requirements, RF power transfer considerations, integration constraints, and outline future directions, including multi-antenna power delivery and networked sensor synchronization.","author":[{"family":"Cappelle","given":"Jona"},{"family":"Mulders","given":"Jarne"},{"family":"Goossens","given":"Sarah"},{"family":"Reher","given":"Thomas"},{"family":"Perre","given":"Liesbet"},{"family":"Strycker","given":"Lieven"},{"family":"Poel","given":"Bram"},{"family":"Callebaut","given":"Gilles"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/sensors59705.2025.11330430","URL":"https://doi.org/10.1109/sensors59705.2025.11330430","source":"crossref"},{"id":"doi:10.1002/9781394386451.ch16","type":"article-journal","title":"Remote Assessments and Aerial Imaging Using UAV for Disaster Management and Precision Agriculture with Immediate Response – A Case Study","abstract":"Advancement in Remote Sensing (RS) and Geographic Information System (GIS) allows non-destructive and timely observation of particular events. Precise and timely assessment of natural disasters such as earthquakes, landslides, forest fires, and volcanic eruptions is essential in giving an operational challenge for the research community. Unmanned Aerial Vehicles (UAVs) play a major role in remote sensing, which provides a feasible, accurate, and safe tool for analyzing the impacts of natural disasters and agriculture in real time. The sensor nodes and various imaging techniques are utilized to access the geographic information using UAVs and monitor the environmental consequences across different management practices. This chapter analyzes the use of various Machine Learning (ML) algorithms with the integration of UAVs to fetch valuable insights from the target field and provide accurate information. This helps the scientific community to extrapolate disaster management and reduce the risk of physical onsite inspection of humans. Also, it can reduce the human errors in physical inspection and predict the diseases at earlier stages. The insights detection of the captured images and the prediction model results are analyzed by categorizing them into worst, average, and best cases to understand the challenging real-world situation. The outcome of this study is to provide a framework for developing an autonomous decision-making system to fully automate the process that is used to get the hazardous and agricultural field assessment effectively and reduce the human errors and risks in physical inspection.","author":[{"family":"Karunanithy","given":"Kalaivanan"},{"family":"Velusamy","given":"Bhanumathi"},{"family":"Prasanth","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394386451.ch16","URL":"https://doi.org/10.1002/9781394386451.ch16","source":"crossref"},{"id":"doi:10.1109/iccams65118.2025.11234011","type":"article-journal","title":"Integration of Multi-Dimensional Geospatial Data for Crop Recommendation and Precision Agriculture","abstract":"Precision agriculture represents a paradigm shift in farming methodologies, leveraging geospatial technologies to optimize crop selection and management practices. This paper presents AgroVision, an integrated approach to crop recommendation systems utilizing multi-dimensional geospatial datasets including Normalized Difference Vegetation Index (NDVI), soil physicochemical parameters, and meteorological variables. The methodology encompasses acquisition of satellite imagery from MODIS using Google Earth Engine, soil data from ISRIC SoilGrids, and climatological parameters from NASA POWER datasets. These heterogeneous data streams undergo rigorous preprocessing, normalization, and integration prior to implementation within a multi-criteria decision support framework. The developed system demonstrates significant efficacy in generating spatially-explicit crop suitability maps with validation accuracy of 95.9% across diverse agro-ecological zones. Comparative analysis reveals a 23% improvement in prediction accuracy over traditional methods and potential yield improvements of 18-27% when recommendations are implemented. This research contributes to agricultural sustainability by enabling data-driven decision-making that optimizes resource utilization while maximizing productivity and economic returns, thereby addressing critical challenges in contemporary agricultural systems.","author":[{"family":"Manikandan","given":"Sidharth"},{"family":"Daivajna","given":"Tejal"},{"family":"Saha","given":"Soumyadeep"},{"family":"Reddyelicherla","given":"Sivananda"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iccams65118.2025.11234011","URL":"https://doi.org/10.1109/iccams65118.2025.11234011","source":"crossref"},{"id":"doi:10.1109/isriti68345.2025.11393349","type":"article-journal","title":"IoT-Based Precision Irrigation System for Real-time Calculation of VPD, ETo and Crop Water Requirements in Sustainable Agriculture","abstract":"This work develops an IoT-based precision irrigation platform for papaya (Carica papaya L., ‘Holland’ variety) in Eastern Thailand where coastal influences and heterogeneous canopies create strong microclimatic gradients. In-orchard sensors (air temperature, relative humidity, solar radiation, wind, rainfall) stream data via MQTT to a backend that computes vapor pressure deficit (V PD), reference evapotranspiration (ETo, FAO Penman–Monteith) and crop evapotranspiration $\\left({E{T_c} = {K_c}\\widehat {E{T_o}}}\\right)$ using a phenology-based constants Kcschedule. A rainfall-effectiveness rule Peff= min{αP, ETc} prevents over-crediting intense showers. A web application converts depth (mm) to liters per tree and runtime given the emitter configuration and provides operational guidance. A case example from Chanthaburi illustrates the end-to-end workflow such as $\\widehat {E{T_o}} = 7.025{\\text{mm}}$, Kc= 1.72 (Month 6) is ETc= 12.083 mm day−1with daily rainfall of 3.00 mm and canopy radius r = 1 m (Acanopy= 3.1416 m2), the net irrigation requirement is (12.083 − 3.00) × 3.1416 = 28.54 L tree−1day−1. The architecture and examples demonstrate an actionable IoT-to-decision pipeline that increases fidelity to orchard microclimate, anchors recommendations in stage-specific papaya physiology and delivers user-facing set points that are simple to apply in the field.","author":[{"family":"Srinil","given":"Phaitoon"},{"family":"Sreekajon","given":"Jakkrapan"},{"family":"Thongnim","given":"Pattharaporn"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/isriti68345.2025.11393349","URL":"https://doi.org/10.1109/isriti68345.2025.11393349","source":"crossref"},{"id":"doi:10.1002/ird.3095","type":"article-journal","title":"Smart Irrigation Control System in Precision Agriculture With Jubatus Climber Algorithm Optimized Distributed BiLSTM","abstract":"ABSTRACT Agricultural productivity is crucial for population growth, but 83% of India's water usage is due to unplanned consumption. To address this, smart agriculture, which uses Internet of Things (IoT) technologies for efficient water management, is essential. Smart irrigation control is crucial for addressing water waste and promoting agricultural growth. To make agriculture smart, automation and IoT technologies emerged with the deep learning algorithms used in the research. Despite advancements, existing research models have drawbacks, including limited accuracy in predicting moisture content and inefficient resource utilization. To address the drawbacks of the existing techniques, a novel approach named distributed bidirectional long short‐term memory optimized with the Jubatus classifier algorithm (JCA‐DiBiLSTM) for automatic irrigation control is proposed. The proposed method integrates BiLSTM networks with a distributed computing architecture, enhancing predictive accuracy by capturing complex temporal dependencies in moisture content data. Additionally, the Jubatus classifier algorithm (JCA) optimizes the model parameters, improving the overall prediction performance. By leveraging JCA‐DiBiLSTM, significant advantages are observed in predicting the moisture content of agricultural land. The model demonstrates enhanced accuracy, outperforming traditional methods and mitigating over‐ or under‐irrigation risks. Furthermore, JCA‐DiBiLSTM ensures an accuracy and specificity of 94% and minimizes the mean square error (MSE) to 5.5 while maximizing the sensitivity to 94%.","author":[{"family":"Amune","given":"Amruta"},{"family":"Pande","given":"Himangi"},{"family":"Musale","given":"Vinayak"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/ird.3095","URL":"https://doi.org/10.1002/ird.3095","source":"crossref"},{"id":"doi:10.71443/9789349552364-10","type":"article-journal","title":"Machine Vision and AI Algorithms for Sorting Grading and Quality Analysis in Post Harvest Processing","abstract":"The integration of machine vision and artificial intelligence (AI) algorithms has revolutionized post-harvest processing in agriculture, enhancing the efficiency, accuracy, and scalability of sorting, grading, and quality assessment systems. Machine vision, utilizing high-resolution imaging technologies and AI-driven algorithms, offers a non-destructive and automated approach to analyzing agricultural products, ensuring consistent quality and minimizing waste. This chapter explores the fundamentals of machine vision systems, including key components such as imaging devices, lighting systems, and preprocessing techniques, alongside the advanced AI models used for defect detection, quality grading, and defect prediction. Special emphasis is placed on machine learning algorithms, including deep learning models, that drive improvements in detection accuracy by learning from vast datasets. The chapter also examines the integration of multispectral, hyperspectral, and thermal imaging technologies, which enhance the detection of internal and external quality attributes. Practical applications and case studies in sorting fruits, vegetables, and grains are presented to demonstrate the significant impact of machine vision and AI on reducing labor costs, improving product quality, and minimizing food waste. Challenges such as environmental variability and system calibration are addressed, alongside future trends and the potential for AI and machine vision to further optimize agricultural processing. The continuous advancements in these technologies are paving the way for a more sustainable and efficient future in post-harvest operations.","author":[{"family":"Patil","given":"Shrishail"},{"family":"Sonawane","given":"Vijay"},{"family":"Mohan","given":"Shivale"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-10","URL":"https://doi.org/10.71443/9789349552364-10","source":"crossref"},{"id":"doi:10.1109/icpeev67897.2025.11291333","type":"article-journal","title":"Advanced Computational Models for Precision Agriculture: Deep and Reinforcement Learning for Predictive Soil Nutrient Management","abstract":"This research introduces an advanced framework for precision agriculture that integrates deep learning (DL) with reinforcement learning (RL) for predictive soil nutrient management. By leveraging real-time data from IoT sensors in conjunction with high-resolution satellite-derived indices, the system provides accurate estimations of essential soil nutrients. The proposed approach achieved over 93% accuracy in predicting nitrogen, phosphorus, and potassium levels, validated through statistical significance testing to ensure robustness. In addition to improving crop yield and resource efficiency, the framework demonstrates practical feasibility by addressing challenges such as model latency, computational demand, and deployment in low-connectivity rural environments. This dual emphasis on predictive accuracy and real-world scalability positions the model as a promising solution for sustainable agricultural resource management.","author":[{"family":"Nagendra","given":"Pidugu"},{"family":"Reddy","given":"Ch"},{"family":"Reddy","given":"KP"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icpeev67897.2025.11291333","URL":"https://doi.org/10.1109/icpeev67897.2025.11291333","source":"crossref"},{"id":"doi:10.1109/stcr62650.2025.11019514","type":"article-journal","title":"Real-Time Pest Detection System Using Efficientnet Deployed On Raspberry Pi For Precision Agriculture","abstract":"A real-time pest classification system is developed for this study with the help of Efficient Net architecture for precision as well as for resource efficiency. The hardware setup includes a Raspberry Pi 4 Model B, 4 GB RAM, DC-to-DC Buck Converter (3A voltage regulator), 5MP Raspberry Pi Camera Module, and 16×2 LCD module. The system architecture includes a 12V adapter powering a buck converter that supplies the 5V needed for the Raspberry Pi and a VNC viewer that is used to access and execute the application remotely over a Wi-Fi connection. The model was pre-trained, and the stored model is utilized in the memory card using the transfer learning methods to optimize computation. Images are taken and preprocessed using the Raspberry Pi Camera Module and resized into a 50×50 resolution. However, robust model generalization is enhanced by using data augmentation techniques such as random rotations, flips, and even brightness adjustments. The architecture of the proposed training pipeline uses an EfficientNet model set with a batch size of 32, Adam optimizer, and a learning rate of 0.001. Thus, training is performed for 15 epochs, at the end of which the model attains a classification accuracy of 93.5%The LCD module presents the classification result, and also sends the prediction to the cloud-based server through API. The proposed system is a scalable low-cost solution for precision agriculture that would empower stakeholders in real-time detection of pests while minimizing crop loss. This paper demonstrates the system's effectiveness in a resource-constrained environment, leading to future enhancements including dataset expansion and edge AI deployment for localized decision-making.","author":[{"family":"Devi","given":"RSS"},{"family":"Cowshik","given":"E"},{"family":"Vishnu","given":"GL"},{"family":"Kaarthi","given":"PCR"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/stcr62650.2025.11019514","URL":"https://doi.org/10.1109/stcr62650.2025.11019514","source":"crossref"},{"id":"doi:10.1109/icpeev67897.2025.11291281","type":"article-journal","title":"An AI-Driven Framework for Precision Pest Detection and Sustainable Management in Agriculture","abstract":"This research creates a fresh artificial intelligence framework which transforms pest management practices in agriculture while emphasizing creativity and framework development. The core novelty emerges from the integration of specific data-driven techniques, particularly the application of convolutional neural networks (CNNs) and transfer learning models like ResNet and VGG, for highprecision pest identification and classification. This framework moves beyond traditional approaches because it eliminates the requirement for multiple hardware tests through its use of existing high-resolution drone imagery coupled with real-time monitoring systems. The framework's development occurs through a multi-stage process. The framework uses CNNs to extract hierarchical features from multispectral and hyperspectral images which enables accurate detection of pest infestations. Pre-trained models are applied with transfer learning to reduce dependency on large labelled datasets and improve adaptability across different agricultural environments. The framework includes predictive analytics and real-time monitoring as its second component to deliver dynamic pest management solutions. Timely interventions become possible through this system which reduces crop damage and improves resource utilization. Its demonstrated flexibility lies in the framework's ability to scale across varying crop types and geographical regions, showing robustness without the need for retraining or hardware modification. By advancing specific AI algorithms and leveraging dronebased agricultural datasets, the framework contributes a novel, data-centric strategy to the growing field of precision pest management.","author":[{"family":"Kumar","given":"Siliveru"},{"family":"Reddy","given":"Ch"},{"family":"Reddy","given":"KP"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icpeev67897.2025.11291281","URL":"https://doi.org/10.1109/icpeev67897.2025.11291281","source":"crossref"},{"id":"doi:10.1109/icecst66106.2025.11307618","type":"article-journal","title":"PrO-MSConvNet: Progression Optimized IoT-Based Precision Agriculture Using Morphable Schema Convolution Network","abstract":"Precision agriculture arrived as a new method of farming using IoT to enable data-driven and real-time decision-making. The intersection of sensor networks and analytics has enabled crop and environmental condition monitoring, resource optimization, and increased sustainability. Despite these advances, conventional models are not capable of handling large volumes of heterogenous agricultural data, leading to inefficient resource allocation and inconsistent crop yields. The need for adaptive and intelligent solutions has grown in response to these limitations. This research proposes PrO-MSConvNet: Progression Optimized IoT-Based Precision Agriculture Using Morphable Schema Convolution Network, a robust methodology that begins with real-time data collection from IoT-enabled sensors measuring soil moisture, temperature, humidity, and crop growth. These inputs are transmitted through Wi-Fi, Zigbee, or LoRaWAN, depending on the scale and connectivity needs of the farm. The data is processed using a Morphable Schema Convolution Network (MSConvNet), which employs deformable convolution and pooling layers, as well as specialized regularizers, to model complex agricultural patterns and make preliminary predictions. These outputs are further refined by the Progression Optimizer (PrO), which dynamically fine-tunes recommendations for irrigation, fertilization, and pesticide application through multi-agent evolutionary optimization. The proposed system achieves 99.5 % accuracy in predictive modeling, 99.8 % efficiency in resource allocation, 99.3 % yield estimation accuracy, 99.6 % disease identification accuracy, and 99.7 % recommendation precision. In conclusion, PrO-MSConvNet offers a significant advancement in IoT-based smart farming by enhancing productivity and sustainability through precise and adaptive resource management strategies.","author":[{"family":"Mathew","given":"Achsah"},{"family":"Kannagi","given":"L"},{"family":"Sandhiya","given":"R"},{"family":"Rosy","given":"NA"},{"family":"Sakthivel","given":"M"},{"family":"Malathi","given":"K"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icecst66106.2025.11307618","URL":"https://doi.org/10.1109/icecst66106.2025.11307618","source":"crossref"},{"id":"doi:10.1016/j.dib.2025.111727","type":"article-journal","title":"SPAS-Dataset-BD: Dataset for smart precision agriculture system in Bangladesh","abstract":"Precision agriculture harnesses data-driven techniques to optimize crop production, resource use, and sustainability. However, low-income countries like Bangladesh face a shortage of localized, high-quality datasets that reflect regional agroclimatic conditions and cropping practices. To address this gap, we present SPAS-Dataset-BD, a robust dataset compiled through a hybrid approach: secondary extraction from the Bangladesh Bureau of Statistics (BBS) 2022 Yearbook and primary on-field surveys of 223 farmers across ten diverse districts. The dataset comprises 4191 records over 73 crop types, with 12 agronomic and environmental features, including underrepresented species. Robustness is demonstrated via threshold-based missing-value handling (<5 % deletion, targeted imputation), hash-based deduplication, and cross-validation against official statistics. We illustrate potential applications, in machine learning (73-class crop classification, yield forecasting) and IoT-driven irrigation scheduling. SPAS-Dataset-BD's scale, methodological transparency, and contextual richness make it a valuable resource for precision agriculture research and policy-making in South Asia.","author":[{"family":"Chowdhury","given":"Rup"},{"family":"Nur","given":"Fernaz"},{"family":"Islam","given":"Muhammad"},{"family":"Islam","given":"Md"},{"family":"Das","given":"Prapti"},{"family":"Afridi","given":"Arafat"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.dib.2025.111727","URL":"https://doi.org/10.1016/j.dib.2025.111727","source":"europepmc"},{"id":"doi:10.1109/rcsm67767.2025.11507329","type":"article-journal","title":"Solar-Powered NPK Detection System for Precision Agriculture","abstract":"This paper presents a low cost solar powered NPK detection system for real time soil nutrient monitoring in precision agriculture. The prototype combines an ion selective electrochemical NPK sensor, an Arduino Nano microcontroller, and RS485 based Modbus RTU communication, providing on site measurements of nitrogen, phosphorus, and potassium. Nutrient values are displayed on a compact OLED interface, while a small photovoltaic array with lithium-ion storage enables fully off grid operation. Field experiments across multiple soil types show an average agreement of about 93% with laboratory analyses. A detailed component cost analysis indicates a total hardware cost between 2500 and 3500 INR, making the system accessible to small scale farmers. By reducing dependence on laboratory testing and providing immediate feedback at the field, the proposed platform supports more informed fertilizer management and improved crop productivity in resource constrained environments.","author":[{"family":"Ramalakshmi","given":"Eliganti"},{"family":"Goli","given":"Vijay"},{"family":"Chinta","given":"Venkata"},{"family":"Nagini","given":"Y"},{"family":"Inturi","given":"Srujana"},{"family":"Reddi","given":"Sowmya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/rcsm67767.2025.11507329","URL":"https://doi.org/10.1109/rcsm67767.2025.11507329","source":"crossref"},{"id":"doi:10.1109/icesc65114.2025.11212546","type":"article-journal","title":"A Novel Smart Vision Hybrid Classifier for Mango Leaf Disease Precision Agriculture Revolution","abstract":"The prevention of economic loss and assurance of crop quality in agriculture heavily relies on faster, more timely, and accurate identification of leaf diseases that affect mango trees. In this study, a new method of automatic detection and classification of mango tree diseases that combines image processing methods with a sophisticated classification approach is proposed. The proposed method comprises several image preprocessing methods that include adaptive contrast enhancement, modified color space image, and multi-level noise elimination, to extract discriminable features from the leaf images. The feature extraction methodology utilized a hybrid texture–color descriptor from a deep learning approach. An entirely new lightweight but fast and powerful classification method–Hybrid Attention-Optimized Deep Ensemble Classifier (HAODEC)–that is made up of convolutional neural networks (CNNs) is proposed. The model was trained and validated on a customized dataset of infected mango leaves and healthy mango leaf images and achieved a promising classification success of $98.96 \\%$, which was far better than previously used comparative models. The research habits show great promise for real-time identification of mango diseases, with a strong promise to develop automated implementations for plant health monitoring strategies and smart farming actions in real-time.","author":[{"family":"Ashwini","given":"A"},{"family":"Menaka","given":"D"},{"family":"Prathaban","given":"Banu"},{"family":"Anusuya","given":"S"},{"family":"Preemi","given":"G"},{"family":"Ancy","given":"AA"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icesc65114.2025.11212546","URL":"https://doi.org/10.1109/icesc65114.2025.11212546","source":"crossref"},{"id":"doi:10.23939/pa2025.01.001","type":"article-journal","title":"Аналіз використання Google Earth Engine для визначення змін агроландшафтів за даними Sentinel-2","abstract":"Мета дослідження полягала в апробації технології визначення змін агроландшафтів за даними супутникових знімків Sentinel-2 із використанням інструментів Google Earth Engine (GEE) на прикладі території Жовківської територіальної громади Львівської області. Основне завдання – виявити зміни земного покриву за період 2017–2024 років, визначити їх масштаби та тенденції. Дослідження проводилося з урахуванням потреб моніторингу землекористування та динаміки земного покриву, що є важливими завданнями для забезпечення сталого розвитку сільських територій. Методи дослідження ґрунтувалися на використанні колекції даних Sentinel-2 Level-2A (Surface Reflectance), які пройшли атмосферну корекцію за два часові періоди. Робота виконувалася у середовищі платформи Google Earth Engine шляхом розробки власних скриптів для автоматизації процесів. Основні етапи включали: попереднє опрацювання даних (маскування хмар, створення композитів, обрізання зображень), розрахунок спектральних індексів (NDVI, NDWI, NDBI), візуалізацію результатів, контрольовану класифікацію з використанням алгоритму Random Forest та оцінку її точності на основі матриці помилок. Результати дослідження свідчать про значні зміни у структурі агроландшафтів за досліджуваний період. Виявлено збільшення площ водних об’єктів, забудованих територій та сільськогосподарських угідь, а також скорочення площ лісів і луків. Такі трансформації узгоджуються з регіональними тенденціями: розвитком аквакультур, урбанізацією та інтенсифікацією сільського господарства. Класифікація показала високу точність, що підтверджує ефективність використання GEE у задачах моніторингу землекористування. Разом з тим виявлено обмеження у застосуванні окремих індексів: NDBI недостатньо чітко розрізняє забудову та оголений ґрунт, NDWI може помилково ідентифікувати водні об’єкти на піщаних ділянках. Найбільш чутливим до помилок класифікації виявився клас луків, а також ділянки, вкриті плівками чи агроволокном. Практична значущість. Розроблений підхід може бути використаний для створення систем моніторингу агроландшафтів на регіональному рівні, оперативного виявлення змін у землекористуванні та планування заходів зі збереження природних ресурсів. Використання платформи GEE забезпечує доступність технології без значних фінансових витрат і спеціалізованого обладнання.","author":[{"family":"Бабій","given":"Л"},{"family":"Заяць","given":"І"},{"family":"Степа","given":"Ю"}],"issued":{"date-parts":[[2025]]},"DOI":"10.23939/pa2025.01.001","URL":"https://doi.org/10.23939/pa2025.01.001","source":"crossref"},{"id":"doi:10.1109/decon67170.2025.11447788","type":"article-journal","title":"A Hybrid AI Approach for Precision Agriculture: Combining Time-Series Analysis with Large Language Models","abstract":"Selection of crop is important decision in agriculture which impacts profitability and sustainability. Farmers and land owners often face this challenges in choosing best crops in variable factors like climate conditions, fluctuating market prices, and other financial constraints. This project presents the design of hybrid approach(LLM and ML) which helps in Multi-Criteria Decision Support System (MCDSS) in crop selection by integrating multiple data sources based on trends. Traditional decision making approaches are experience-based, which makes them inefficient in handling complex, dynamic data patterns. To address these limitations and constraints, this system uses predictive models to estimate profit projections for viable crops under given conditions and also making use of Large Language Model (LLM) to synthesize complex outputs into natural language recommendations and supporting realtime, context-aware query resolution through a chatbot. This application aims to help in decision accuracy, improve the return on investment (ROI) in agriculture sector.","author":[{"family":"Patil","given":"Kiran"},{"family":"Arunachalam","given":"Manasha"},{"family":"Srichandra","given":"Ippatapu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/decon67170.2025.11447788","URL":"https://doi.org/10.1109/decon67170.2025.11447788","source":"crossref"},{"id":"doi:10.1109/optima67660.2025.11380291","type":"article-journal","title":"Optical Sensor Networks for Precision Agriculture: High-Speed Data Transmission and Remote Crop Monitoring","abstract":"Precision agriculture is more and more relying on the dense sensing and an immediate analytics to streamline irrigation, application of fertilizers, and diseases. Our suggested optical sensor network (OSN) architecture provides an integration of a fiber-based distributed sensors network with high-speed WDMPON/RoF transport and edge/cloud analytics. We demonstrate that sub-millisecond per-hop latencies, reduced energy-per-bit at upper sampling rates, and robust, non-invasive crop early warning by using optical spectroscopy, hyperspectral/ thermal UAV, and OPTRAM-based soil-moisture retrieval are all possible using field inspired simulations and models based on literature. Findings are reflected by current developments in SAR/optical fusion and UAV electro-optical systems of crop mapping and stress sensing, with future scalable, dual-purpose (sensing + transport) agricultural photonic infrastructure","author":[{"family":"Maratovich","given":"Aliev"},{"family":"Veeraiah","given":"Vivek"},{"family":"Gupta","given":"Ankur"},{"family":"Dhabliya","given":"Dharmesh"},{"family":"Ahamad","given":"Shahanawaj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/optima67660.2025.11380291","URL":"https://doi.org/10.1109/optima67660.2025.11380291","source":"crossref"},{"id":"doi:10.1109/lciot64881.2025.11118613","type":"article-journal","title":"Current and Future Perspectives on Drone-Based Computer Vision for Precision Agriculture","abstract":"In recent years, drones with computer vision systems integrated with IoT frameworks have transformed precision agriculture by enabling efficient data collection, real-time analysis, and connectivity for autonomous or supervised operations and applications. These systems contribute to developing the Internet of Things (IoT) by creating a seamless network of interconnected devices that share and analyze data, fostering innovation in remote monitoring, automation, and decision-making processes. By bridging physical systems with digital intelligence, they drive advancements in data-driven agriculture while expanding the capabilities of the IoT in diverse environmental and operational settings. This paper presents perspectives on drone-based computer vision techniques applied to precision agriculture, focusing on multidimensional data acquisition, processing, and analysis methods. Challenges and future directions are discussed.","author":[{"family":"Basso","given":"Maik"},{"family":"Guimaraes","given":"Carlos"},{"family":"Rosa","given":"Artur"},{"family":"Pereira","given":"Pedro"},{"family":"Freitas","given":"Edison"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/lciot64881.2025.11118613","URL":"https://doi.org/10.1109/lciot64881.2025.11118613","source":"crossref"},{"id":"doi:10.1109/medcom67532.2025.11404937","type":"article-journal","title":"YOLO-Based Multi-Class Crop and Weed Detection for Precision Agriculture Under Real-World Field Conditions","abstract":"In precision agriculture, precise and real-time identification of crops and weeds species is necessary to reduce herbicides, lower the cost of operation, and enhance the output. The traditional dichotomous crop-weed dichotomous classification systems do not generalize in a real-life agricultural context, especially when two or more types of crops, and different weed species are grown within the same field. The proposed study presents a powerful YOLO-based multi-class detection system that will be able to detect many types of crops and weed in changing environmental factors. The study provides a diversified, field-measured data set with different light, soil, and occlusion conditions and implements augmentation strategies at the highest level to make the models more robust. The performance of three variants of YOLO was assessed in three metrics mAP, precision, recall, and F1-score, and the speed of real-time inference. YOLOv9 was found to have a better mAP at 0.5 of 95.4, 74.6 at 0.5:0.95, and F1-score of 92.3. The model was tested in deployment on edge devices like Jetson Xavier NX and Google Coral TPU and has been validated as being able to be used in real-time on-field to manage weeds. The suggested framework has a great contribution to the multi-class detection performance, providing a scalable and viable solution to sustainable precision agriculture.","author":[{"family":"Dhumale","given":"Anuradha"},{"family":"Pandey","given":"Shraddha"},{"family":"Lakkamraju","given":"Vishnu"},{"family":"Srivastava","given":"Satyajee"},{"family":"Maurya","given":"Sudhanshu"},{"family":"Tabbassum","given":"Saziya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/medcom67532.2025.11404937","URL":"https://doi.org/10.1109/medcom67532.2025.11404937","source":"crossref"},{"id":"doi:10.1016/j.aiia.2025.03.005","type":"article-journal","title":"A new tool to improve the computation of animal kinetic activity indices in precision poultry farming","abstract":"Precision Livestock Farming (PLF) emerges as a promising solution for revolutionising farming by enabling real-time automated monitoring of animals through smart technologies. PLF provides farmers with precise data to enhance farm management, increasing productivity and profitability. For instance, it allows for non-intrusive health assessments, contributing to maintaining a healthy herd while reducing stress associated with handling. In the poultry sector, image analysis can be utilised to monitor and analyse the behaviour of each hen in real time. Researchers have recently used machine learning algorithms to monitor the behaviour, health, and positioning of hens through computer vision techniques. Convolutional neural networks, a type of deep learning algorithm, have been utilised for image analysis to identify and categorise various hen behaviours and track specific activities like feeding and drinking. This research presents an automated system for analysing laying hen movement using video footage from surveillance cameras. With a customised implementation of object tracking, the system can efficiently process hundreds of hours of videos while maintaining high measurement precision. Its modular implementation adapts well to optimally exploit the GPU computing capabilities of the hardware platform it is running on. The use of this system is beneficial for both real-time monitoring and post-processing, contributing to improved monitoring capabilities in precision livestock farming. • Image analysis can be utilised to monitor and analyse the behaviour of individual hens in real time. • The manuscript presents a study on the optimization of kinetic indices based on object tracking techniques. • Conducting object detection in parallel with the YOLOv11n deep neural network improves GPU utilisation. • This tool reduces computational demands and benefits real-time monitoring and post-processing tasks.","author":[{"family":"Carraro","given":"Alberto"},{"family":"Pravato","given":"Mattia"},{"family":"Marinello","given":"Francesco"},{"family":"Bordignon","given":"Francesco"},{"family":"Trocino","given":"Angela"},{"family":"Xiccato","given":"Gerolamo"},{"family":"Pezzuolo","given":"Andrea"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.aiia.2025.03.005","URL":"https://doi.org/10.1016/j.aiia.2025.03.005","source":"crossref"},{"id":"doi:10.1109/icoiics67115.2025.11390212","type":"article-journal","title":"Iot-Based Smart Irrigation Model for Precision Agriculture Using ESP8266 and Soil Moisture Analysis","abstract":"Water management is one of the biggest challenges in agriculture today. Many farmers still follow fixed irrigation schedules without checking the actual needs of the soil or the weather. This often causes water wastage or overwatering, which can harm both crops and the environment. To tackle this problem, we introduce a smart irrigation system that makes watering crops easier and more efficient. The system uses affordable microcontrollers like ESP32/ESP8266 along with sensors that measure soil moisture, temperature, humidity, rainfall, and soil pH. It can work automatically or be controlled by farmers through a mobile app or a web platform. With the help of machine learning, the system studies past data and current field conditions to decide the right amount of water required. Farmers also receive regular soil health updates and instant alerts whenever something unusual happens. In addition, the system keeps track of water flow, prevents overirrigation, and detects pump failures. It is compatible with both drip and sprinkler methods, making it useful for different types and sizes of farms. Overall, this smart irrigation system is affordable, easy to use, and scalable. It helps farmers save water, reduce labor, improve crop yield, and move towards more sustainable farming practices.","author":[{"family":"Bhalerao","given":"Tejaswini"},{"family":"Bansude","given":"Shravani"},{"family":"Bartake","given":"Saraswati"},{"family":"Pardeshi","given":"Kalpana"},{"family":"Pandit","given":"Dipti"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icoiics67115.2025.11390212","URL":"https://doi.org/10.1109/icoiics67115.2025.11390212","source":"crossref"},{"id":"doi:10.1109/iscon65210.2025.11341243","type":"article-journal","title":"Advanced Precision Agriculture: Unifying CNNs &amp; Random Forests for Robust Rice Disease Detection","abstract":"This study introduces a cutting-edge disease classification model that has been specifically created for rice crops. The model makes use of a hybrid methodology that blends Convolutional Neural Networks (CNNs) with a Random Forest classifier. The efficiency of the model is examined across five separate disease classes, which are Bacterial Leaf Blight, Rice Blast, Sheath Blight, Brown Spot, and Tungro Disease. The results of this evaluation demonstrate remarkable precision, recall, and F1-Score values, all of which exceed 96.43%. The assessment is made more comprehensive by the incorporation of support values, which indicate the instances for each class, in addition, to support proportion values that range from 0.19 to 0.21. This work evaluates the rice illness classification model using a dataset of 4286 photos. 97.06% total accuracy is impressive. When it comes to Macro Average, Weighted Average, and Micro Average measures, the model constantly achieves remarkable accuracy, reaching an overall accuracy of 97.06%. This demonstrates that the model is capable of robust generalization. These results demonstrate that the model is reliable over a wide range of datasets and show the potential of the approach to automate disease diagnosis in precision agriculture. It is important to note that the research makes a substantial contribution to the incorporation of modern machine learning algorithms, attaining an amazing total accuracy of almost 99%. The findings of this study represent a significant contribution to the field, as they highlight the practical application of artificial intelligence in the process of revolutionizing agricultural management and ensuring the safety of food supplies around the world.","author":[{"family":"Kaushik","given":"Priyanka"},{"family":"Kumar","given":"Bura"},{"family":"Ali","given":"Mohd"},{"family":"Haldorai","given":"Anandakumar"},{"family":"Jangra","given":"Preeti"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iscon65210.2025.11341243","URL":"https://doi.org/10.1109/iscon65210.2025.11341243","source":"crossref"},{"id":"doi:10.1109/icesc65114.2025.11212543","type":"article-journal","title":"IoT-Enabled Weather Monitoring System for Precision Agriculture and Smart Farming Decisions","abstract":"Agriculture is heavily influenced by weather conditions, and timely, data-driven decisions can significantly enhance crop yield and resource efficiency. This project proposes an IoT-based weather station designed to assist farmers in making informed agricultural decisions. The system employs an ESP32 microcontroller connected to various environmental sensors including temperature, pressure, humidity, soil moisture, and light intensity sensors. These sensors collect real-time field data, which is transmitted via Wi-Fi to the Blynk cloud platform. Using the Blynk mobile app, farmers can monitor live environmental conditions remotely, enabling them to optimize irrigation, fertilizer usage, and crop planning. The system is powered by a sustainable energy source such as a solar-powered battery, ensuring field operability without dependency on grid power. Agriculture encounters low yields and wastages of resources because of little or no timely weather and soil information. Its enhances an IoT-linked solar-powered weather station with real-time monitoring to enhance the efficiency of crop planning and realization of precision farming. The integration of real-time monitoring and mobile alerts supports preventive action against unfavourable conditions such as drought or excessive Overall, the system provides a low-cost, scalable, and smart solution to empower precision agriculture and sustainable farming practices.","author":[{"family":"Sasikala","given":"S"},{"family":"Bharatula","given":"BSD"},{"family":"Roja","given":"N"},{"family":"Sanjeevini","given":"E"},{"family":"Shanmathy","given":"K"},{"family":"Sharmila","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icesc65114.2025.11212543","URL":"https://doi.org/10.1109/icesc65114.2025.11212543","source":"crossref"},{"id":"doi:10.56025/ijaresm.2025.1304252240","type":"article-journal","title":"Leveraging Machine Learning for Precision Agriculture: A Crop Yield Prediction and Recommendation System","abstract":"Machine learning (ML) is transforming agriculture by enhancing crop production, reducing waste, and optimizing resources through data-driven decision-making. This study explores ML applications, analysing challenges and opportunities in integrating ML models with farm data and real-time IoT sensors. Evaluating 15 ML algorithms, the research proposes a novel feature combination scheme-enhanced algorithm, improving predictive accuracy. Experimental results show that modifying labels significantly impacts data analysis. Bayes Net achieved the highest accuracy (99.59%), followed by Naive Bayes Classifier (99.46%). These findings highlight ML’s potential in aiding farmers with crop growth, disease detection, soil health, and irrigation management. ML also boosts agricultural production while reducing costs. Integrating ML with IoT data enables precision agriculture, strengthening infrastructure and sustainability. ML-driven solutions enhance food security by improving crop yield predictions and mitigating climate and resource risks. Challenges include data quality, model interpretability, and integration with existing practices. Collaboration among researchers, agronomists, and developers is crucial for refining ML models. This study underscores ML’s role in shaping sustainable farming and calls for further research on algorithm refinement, data collection, and farmer-friendly applications. By optimizing agricultural processes, ML fosters smart farming and digital transformation. Its integration with traditional methods can create resilient, efficient, and sustainable agricultural systems, benefiting global food production and economic stability.","author":[{"family":"Kumari","given":"Shivani"},{"family":"Kumar","given":"Aman"},{"family":"Ray","given":"Ranjana"},{"family":"Kumar","given":"Shubham"},{"family":"Sen","given":"Sayan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.56025/ijaresm.2025.1304252240","URL":"https://doi.org/10.56025/ijaresm.2025.1304252240","source":"crossref"},{"id":"doi:10.1109/chilecon66915.2025.11476216","type":"article-journal","title":"A Hailo-Accelerated System for Precision Agriculture: Real-Time on-Board YOLO Inference on a Drone Platform","abstract":"Precision agriculture demands real-time solutions for detecting pests and nutritional deficiencies, a task where cloud-based systems falter due to latency and connectivity issues in rural settings. This paper introduces an intelligent agriculture system based on edge computing, designed for on-board deployment on unmanned aerial vehicles (UAVs). The methodology involved building a platform with a Raspberry Pi 5 and a Hailo-8L AI accelerator. On this hardware, we implemented and benchmarked two models, YOLOv8s and YOLOv10s, which were trained on a custom dataset of agricultural anomalies and then compiled for edge deployment. Their performance was evaluated in two scenarios: operating exclusively on the Raspberry Pi's CPU and utilizing the Hailo-8L hardware accelerator. Key findings reveal that hardware acceleration yields a significant performance increase. Specifically, the system achieves a throughput of up to 27.3 frames per second (FPS)-a 13fold improvement-while reducing inference latency by 91.4 % (from 403.7 ms to 34.7 ms) compared to CPU-only processing. This optimization also reduces the main processor's load from$\\sim 99 \\%$to less than 18 %, ensuring thermal stability. The main contribution of this work is providing a robust, quantitative benchmark that validates the viability of this low-power, highperformance architecture, offering a scalable and autonomous solution for real-time agricultural monitoring directly in the field.","author":[{"family":"Vergara","given":"Bárbara"},{"family":"Fernández-Campusano","given":"Christian"},{"family":"Kaschel","given":"Hector"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/chilecon66915.2025.11476216","URL":"https://doi.org/10.1109/chilecon66915.2025.11476216","source":"crossref"},{"id":"doi:10.1109/iccit68739.2025.11491780","type":"article-journal","title":"NextSeed: An IoT Based Precision Agriculture System for Soil Analysis and Crop Recommendation","abstract":"Agriculture is an important sector for the economy and food security of Bangladesh, which is facing several challenges due to climate change, lack of cultivable land and inadequate access to advanced farming technologies. To overcome the above challenges, this paper proposes NextSeed, which is an IoT based precision agriculture system that integrates realtime soils monitoring with machine learning for intelligent crop suggestion. The system uses a 7-in-1 soil sensor to measure NPK nutrients, pH, moisture, temperature and electrical conductivity, and some environmental sensors for rainfall, water level and atmospheric conditions. Data goes through anomaly detection before the cloud processing where a Naive Bayes classifier performs 99.77% accuracy in crop prediction. The system also offers fertilizer recommendations and allows automated irrigation control depending on soil conditions and water availability. NextSeed helps to cover significant gaps in solutions on the market by providing integrated automation that combines soil nutrition analysis with crops prediction and water management for agricultural decision support.","author":[{"family":"Rakib","given":"Md"},{"family":"Alam","given":"Md"},{"family":"Das","given":"Dabasis"},{"family":"Bashir","given":"Golam"},{"family":"Rahman","given":"Md"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccit68739.2025.11491780","URL":"https://doi.org/10.1109/iccit68739.2025.11491780","source":"crossref"},{"id":"doi:10.1109/dasa68193.2025.11499136","type":"article-journal","title":"EfficientNetB4-Based Deep Learning Approach for Accurate Classification of Maize Leaf Diseases in Precision Agriculture","abstract":"This research leverages the EfficientNetB4 architecture, known for its high accuracy and computational efficiency, to classify maize leaf diseases into four categories: Crown Rust, Gray Leaf Spot, Blight, and Healthy. For this study, a pre-processed and augmented dataset of 4,188 maize leaf images from Kaggle was used to improve the model’s performance. To achieve a balanced assessment, the data were partitioned into training (70%), validation (15%), and testing (15%). The model achieved an overall accuracy of 85.26% on the test set, and all class F1-scores were high, which means that the model is quite reliable. However, the confusion matrix showed that there was strong classification since there was some misclassification in Gray Leaf Spot. This work shows how deep learning can be applied in the management of diseases in agriculture. Future work will include collecting more data, integrating disease detection into mobile applications, and integrating explainable AI to provide recommendations for precision farming. This new system has the potential to transform sustainable maize farming.","author":[{"family":"Jangra","given":"Shinnu"},{"family":"Sehgal","given":"Sweety"},{"family":"Kumar","given":"Jasvinder"},{"family":"Mohanty","given":"Jayashree"},{"family":"Saini","given":"Yashasvi"},{"family":"Singla","given":"Manish"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/dasa68193.2025.11499136","URL":"https://doi.org/10.1109/dasa68193.2025.11499136","source":"crossref"},{"id":"doi:10.1109/iceteg66194.2025.11473226","type":"article-journal","title":"A Comprehensive Review of Smart Agriculture: Integrating AI, IoT and Precision Farming","abstract":"Modern agriculture faces complex challenges that demand innovative solutions. This literature survey on smart agriculture technologies explores the collective findings from various papers, shedding light on the transformative role of tech- nological interventions in agriculture. To enhance agricultural practices, the selected studies converge on integrating cutting- edge technologies, including Wireless Sensor Networks (WSN), machine learning algorithms, artificial intelligence (AI), and the Internet of Things (IoT). The synthesis of this article under- scores the significant strides made in optimizing soil monitoring, nutrient analysis, and overall farm management, providing a brief overview of the critical components and outcomes of the selected studies, illustrating the profound impact of technology on advancing smart agriculture. This smart agriculture review also discussed precision agriculture in rural areas with opportunities and challenges. Through a comprehensive analysis, this article aims to offer insights into the evolving landscape of agricultural technology and its implications for sustainable and efficient farming practices.","author":[{"family":"Dai","given":"Guowei"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iceteg66194.2025.11473226","URL":"https://doi.org/10.1109/iceteg66194.2025.11473226","source":"crossref"},{"id":"doi:10.1109/smap66932.2025.00013","type":"article-journal","title":"Sensor-Driven Ensemble Learning for Crop Recommendation and Disease Prediction in Precision Agriculture","abstract":"Agriculture plays a vital role in ensuring global food security, yet it faces growing challenges from climate change, resource limitations, and increasing demand. This paper presents an ensemble learning framework that leverages Internet of Things (IoT) sensor data for crop recommendation and plant disease prediction in precision agriculture. Environmental parameters including temperature, humidity, rainfall, soil pH, and nutrient levels are modeled using Random Forest, Neural Networks, and Logistic Regression classifiers. Experimental evaluation on a publicly available dataset shows that Random Forest achieves superior performance, reaching 89.20% accuracy and the highest F1-score, outperforming baseline models in robustness and interpretability. The integration of Apache Spark enables scalable and near real-time analysis, making the approach suitable for practical deployment. By combining ensemble learning with sensor-driven environmental monitoring, the proposed framework supports sustainable, interpretable, and data-driven agricultural decision-making for farmers, researchers, and policymakers.","author":[{"family":"Vonitsanos","given":"Gerasimos"},{"family":"Economopoulou","given":"Emmanouela"},{"family":"Sioutas","given":"Spyros"},{"family":"Kanavos","given":"Andreas"},{"family":"Mylonas","given":"Phivos"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/smap66932.2025.00013","URL":"https://doi.org/10.1109/smap66932.2025.00013","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i1.13037","type":"article-journal","title":"PERBEDAAN INTENSITAS NAUNGAN DAN VARIETAS TERHADAP SERANGAN HAMA DAN PENYAKIT PADA TANAMAN STROBERI (Fragaria L)","abstract":"Pengembangan stroberi di dataran rendah Indonesia masih terbatas, tetapi bisa menjadi peluang untuk memperluas area budidaya stroberi. Budidaya stroberi di dataran rendah akan menghadapi tantangan baru, terutama serangan hama dan penyakit. Penelitian ini bertujuan untuk mengetahui pengaruh perbedaan intensitas naungan dan varietas terhadap serangan hama dan penyakit tanaman stroberi di dataran rendah. Penelitian ini menggunakan Rancangan Kelompok Lengkap Teracak (RKLT) Tersarang dengan dua faktor. Faktor utama terdiri atas empat taraf yaitu kontrol (P3), naungan 55% (P1), naungan 65% (P2), dan naungan 75% (P4). Faktor tersarang terdiri atas tiga varietas stroberi, yaitu varietas California (R1), varietas Mencir (R2), dan varietas Sweet Charlie (R3). Dengan demikian, terdapat 12 kombinasi perlakuan dengan 4 ulangan, masing-masing ulangan terdiri atas 3 sampel tanaman sehingga diperoleh total 144 tanaman. Hasil menunjukkan bahwa hama yang menyerang tanaman stroberi meliputi ulat grayak, ulat penggulung daun, belalang, kutu putih, sedangkan penyakit yang menyerang meliputi embun tepung, dan busuk buah. Naungan 75% meningkatkan kerusakan daun tertinggi akibat hama pada kontrol sebesar 8.2%, varietas Mencir lebih rentan akibat kerusakan buah dibanding Sweet Charlie sebesar 0.14%. Terdapat korelasi positif antara intensitas cahaya dan suhu udara terhadap intensitas serangan hama dan penyakit, namun kelembaban udara menunjukkan korelasi negatif dengan serangan hama dan penyakit.","author":[{"family":"Istianah"},{"family":"Kalsum","given":"Ummu"},{"family":"Ramdan","given":"Evan"},{"family":"Warip"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35760/jpp.2025.v9i1.13037","URL":"https://doi.org/10.35760/jpp.2025.v9i1.13037","source":"crossref"},{"id":"doi:10.1109/emergin67762.2025.11450659","type":"article-journal","title":"Precision Agriculture Through Spectral Signatures: An Integrated Evalaution of NDVI, EVI, GCI AND NDWI for Stress Detection","abstract":"Crop health monitoring is an essential element of sustainable food security and agriculture. Conventional field-based methods of monitoring tend to be slow and spatially limited, therefore scalable, efficient alternatives are necessary. The article discusses a spectral analysis technique with the central vegetation indices - NDVI (Normalized Difference Vegetation Index), GCI (Green Chlorophyll Index), EVI (Enhanced Vegetation Index), MSI (Moisture Stress Index), and NDWI (Normalized Difference Water Index) to quantify vegetation health, chlorophyll density, water stress, and water condition. Using multispectral reflectance measurements, each index was calculated, plotted, and analyzed to deduce suitable patterns under different vegetation conditions. The method allows for vegetation classification into very healthy, moderately healthy, stressed, and barren groups with normalized thresholds and color maps. Comparative examination indicates how indices react differently to certain plant attributes. The study illustrates a flexible, data-driven approach to preventive crop health diagnostics and lays the groundwork for more sophisticated decision-support systems in precision agriculture. The findings show the viability of extensive vegetation monitoring by spectral index analysis and confirm the application of composite indices in multi-dimensional aspects of plant health detection.","author":[{"family":"Tripathi","given":"Ayush"},{"family":"Yadav","given":"Vanshika"},{"family":"Chauhan","given":"Tanishq"},{"family":"Abidi","given":"Ali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/emergin67762.2025.11450659","URL":"https://doi.org/10.1109/emergin67762.2025.11450659","source":"crossref"},{"id":"doi:10.33545/26633582.2025.v7.i2a.197","type":"article-journal","title":"IoT-Powered smart agriculture: Innovations in precision farming and sustainability","abstract":"Agriculture is one of the most vital sectors for human existence, as it provides the essential resource for survival food. In India, agriculture is not only a means of sustenance but also a cornerstone of the national economy. However, many farmers still rely heavily on traditional and indigenous farming practices, which often limit productivity and efficiency. With the rapid advancement of technology, particularly in areas such as the Internet of Things (IoT), automation, and precision farming, there is a tremendous opportunity to modernize agricultural practices. By adopting smart and innovative technologies, farmers can save time, reduce costs, optimize resource utilization, and improve yields. Yet, despite a growing global and national population, agricultural productivity continues to decline due to environmental, climatic, and resource challenges. If these issues are not addressed through technological integration, humanity may face significant difficulties in sustaining food production and ensuring long-term survival.","author":[{"family":"Kumar","given":"Rajinder"},{"family":"Kaur","given":"Charanjeet"},{"family":"Kaur","given":"Manpreet"},{"family":"Sharma","given":"Sahil"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/26633582.2025.v7.i2a.197","URL":"https://doi.org/10.33545/26633582.2025.v7.i2a.197","source":"crossref"},{"id":"doi:10.1109/icpcsn65854.2025.11036078","type":"article-journal","title":"Comparative Analysis of YOLOv11 and YOLOv12 for Automated Weed Detection in Precision Agriculture","abstract":"This paper presents a comparative analysis of YOLOv11 and YOLOv12 for automated weed detection in precision agriculture. The primary objective is to assess both models' detection accuracy, generalization ability, and reliability using a custom-annotated dataset of sesame crop and weed images. YOLOv11, known for its faster inference speed, demonstrates higher mAP@0.5 in straightforward detection scenarios. However, YOLOv12 outperforms in challenging conditions due to its advanced architectural enhancements, including attention mechanisms and improved feature pyramids. This study highlights the trade-off between computational efficiency and robust detection, offering insights into choosing the optimal object detection model for real-time agricultural applications.","author":[{"family":"Shaik","given":"Abdul"},{"family":"Kandula","given":"Ajay"},{"family":"Tirumalasetti","given":"Gnana"},{"family":"Yendluri","given":"Baladithya"},{"family":"Kalluri","given":"Hemantha"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icpcsn65854.2025.11036078","URL":"https://doi.org/10.1109/icpcsn65854.2025.11036078","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i1.12468","type":"article-journal","title":"RESPON TANAMAN CABAI KATOKKON (Capsicum chinense Jacq.) AKIBAT PUPUK NPK DAN KOMPOS AMPAS TEBU PADA TANAH ALUVIAL","abstract":"Meskipun cabai katokkon (Capsicum chinense Jacq.) merupakan salah satu produk hortikultura yang memiliki potensi ekonomi yang cukup besar, namun belum banyak ditanam oleh petani Indonesia. Penelitian ini bertujuan untuk mendapatkan kombinasi perlakuan yang paling tepat untuk pertumbuhan dan produktivitas cabai katokkon di tanah aluvial serta interaksi antara pupuk NPK dengan kompos dari limbah tebu. Lokasi penelitian dilaksanakan pada tanggal 6 Maret sampai dengan 5 Juni 2024 di Jalan Sepakat II, Gang. Racana Untan, Pontianak Tenggara, Kalimantan Barat. Metode yang digunakan adalah Rancangan Acak Lengkap (RAL) faktorial dua faktor. Tahap awal, dosis pupuk NPK (A) yang diberikan adalah a1 = 100 kg/ha, a2 = 200 kg/ha, dan a3 = 300 kg/ha. Tahap kedua, dosis kompos ampas tebu (N) diberikan sebanyak tiga taraf, yaitu n1 = 10 ton/ha, n2 = 20 ton/ha, dan n3 = 30 ton/ha. Berdasarkan hasil penelitian, perkembangan dan hasil cabai katokkon pada tanah aluvial dipengaruhi oleh interaksi antara pupuk NPK dan kompos ampas tebu. Untuk meningkatkan jumlah buah per tanaman dan berat buah per tanaman cabai katokkon pada tanah aluvial, kombinasi yang paling berhasil dan efisien adalah pemberian pupuk NPK 300 kg/ha dan kompos ampas tebu 10 ton/ha.","author":[{"family":"Vera"},{"family":"Ramadhan","given":"Tris"},{"family":"Hendarti","given":"Indri"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35760/jpp.2025.v9i1.12468","URL":"https://doi.org/10.35760/jpp.2025.v9i1.12468","source":"crossref"},{"id":"doi:10.1016/j.compag.2025.110523","type":"article-journal","title":"Precision monitoring of rice nitrogen fertilizer levels based on machine learning and UAV multispectral imagery","abstract":"Rice is the primary food crop globally, and effective nitrogen fertilizer management is essential for optimizing yield while minimizing environmental impact. This study integrated unmanned aerial vehicle (UAV) imagery with multispectral imaging and machine learning (ML) methods to classify nitrogen levels (N levels) in rice fields. Experimental fields with various N levels (underfertilized, optimal fertilization, and overfertilized) were imaged in 2020 and 2021 by using UAVs. The captured images underwent geometric and spectral corrections, and rice pixel segmentation was performed using a decision tree classifier, which achieved a recall of 95.3 % and an overall accuracy of 88.8 %. N level classification was performed by extracting 16 spectral and structural features from the images, including color space transformations, vegetation indices, and canopy coverage. These features were input to support vector machine (SVM) and k nearest neighbors (KNN) models, and feature selection methods were applied to improve performance. The SVM model outperformed the KNN model, particularly in Period II, achieving an overall accuracy of 90.0 % when the chi-square feature selection method was applied. The Red Edge Ratio Vegetation Index and canopy coverage were the most informative features for classification. The integration of UAV-based multispectral imagery and ML in this study enhanced nitrogen classification accuracy and scalability. The method provides a data-driven approach for precision agriculture and sustainable fertilization management.","author":[{"family":"Yang","given":"Ming"},{"family":"Hsu","given":"Yu"},{"family":"Chen","given":"Yi"},{"family":"Yang","given":"Chin"},{"family":"Li","given":"Kai"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.compag.2025.110523","URL":"https://doi.org/10.1016/j.compag.2025.110523","source":"crossref"},{"id":"doi:10.1201/9781003637264-2","type":"article-journal","title":"Introduction to Multimodal Data Analysis in Precision Farming","abstract":"Precision farming enhances the agricultural productivity and resource utilization by examining the multimodal data from multiple sources, including remote sensing, Internet of Things (IoT) sensors, meteorological data, soil health measurements, and crop monitoring devices. However, some of the concerns, such as data heterogeneity, noise, redundancy, interoperability issues and real-time processing limits, will prevent successful adoption. This chapter works into the advanced methods of machine learning (ML), deep learning (DL), computer vision and geospatial analytics to help solve these issues and deliver accurate decision-making solutions. It emphasizes techniques like sensor fusion, hyperspectral imaging, and AI-based prediction models for better crop production estimation, irrigation automation, disease detection, and pest management system. Furthermore, this chapter discusses the ethical and security considerations which are related to agricultural data management and investigates the current developing trends, i.e. blockchain for safe data sharing, edge computing for real-time analytics and AI-powered decision-support systems. Recent advanced improvements in cloud-based platforms and high-performance computers have also enabled large-scale data aggregation and real-time monitoring for the precision agriculture. Adoption of these technologies is critical for the creation of resilient and adaptive agricultural systems capable of effectively responding to the climate change and global food demand. By combining data science with agronomy, this multimodal data analysis in precision farming will have the potential to transform current agriculture, which ensures sustainability, optimizing resource usage and improving food security.","author":[{"family":"Rana","given":"Navjot"},{"family":"Dahiya","given":"Pankaj"},{"family":"Mehta","given":"Swati"},{"family":"Ladohia","given":"Shivanshu"},{"family":"Sameeksha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003637264-2","URL":"https://doi.org/10.1201/9781003637264-2","source":"crossref"},{"id":"doi:10.1109/aece67531.2025.11386705","type":"article-journal","title":"Web-Based Application to Predict Plant Disease Using Deep Learning for Precision Agriculture","abstract":"The current reliance on manual examination to detect diseases in plants is not effective, subjective, and too slow to deal with the high menace in the world food supply and the agricultural earnings posed by these diseases. This paper addresses the issue with the help of deep learning and specifically a customized Convolutional Neural Network (CNN) that can recognize plant diseases based on leaf images automatically and accurately. It was trained on large dataset of 87,000 photos in 38 categories with a remarkable validation accuracy of 96.66. The combination of this AI system with webbased technologies to perform real-time inferences proves that the given approach can help to increase the rates of disease detection, streamline the process of pesticide application, and make agricultural practices more sustainable.","author":[{"family":"Kapoor","given":"Sattwic"},{"family":"Srivastava","given":"Sarthak"},{"family":"Raj","given":"Namrata"},{"family":"Padhy","given":"Sasmita"},{"family":"Kumar","given":"Naween"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/aece67531.2025.11386705","URL":"https://doi.org/10.1109/aece67531.2025.11386705","source":"crossref"},{"id":"doi:10.1109/icaaic64647.2025.11330381","type":"article-journal","title":"Machine Learning Approaches for Precision Crop Water Estimation: A Comparative Analysis","abstract":"This paper addresses the dynamic water requirements of crops throughout their lifecycle, which are often neglected by traditional irrigation systems, and proposes a scalable smart irrigation solution that uses machine learning models for precision in crop water estimation. It utilizes meteorological data and the Penman-Monteith equation to calculate reference evapo-transpiration(ETo) further corrected by crop-specific coefficients (Kc), to give an accurate estimation of the required amount of water. The authors consider several machine learning models, this article focuses on LSTM networks since they are good at dealing with temporal dependencies. To enhance dataset diversity and reduce overfitting, we employed a genetic algorithm (GA) for data augmentation. GA parameters included a population size of 50, 100 generations, crossover rate of 0.8, and mutation rate of 0.05. The fitness function preserved seasonal autocorrelation patterns. Similar GA-based augmentation methods have been applied in irrigation modeling. Results show that the proposed LSTM model is better compared to other approaches, showing high accuracy with significant improvements in prediction reliability. In conclusion, this study provides a comprehensive framework for optimizing water use efficiency and suggests the potential of ML-powered smart irrigation systems in solving global water issues and promoting the adoption of precision agriculture practices","author":[{"family":"Singh","given":"Nikita"},{"family":"Jeganathan","given":"Nitesh"},{"family":"Vidhani","given":"Pratham"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaaic64647.2025.11330381","URL":"https://doi.org/10.1109/icaaic64647.2025.11330381","source":"crossref"},{"id":"doi:10.1109/gitcon65266.2025.11377119","type":"article-journal","title":"Drone-Assisted Precision Agriculture with Hybrid Machine Learning Models for Sustainable Farming","abstract":"Precision agriculture experiences difficulties in effective crop monitoring and resource management due to restricted real-time data analysis and the generalised use of inputs. This study presents a drone-assisted, hybrid machine learning framework that combines Convolutional Neural Networks (CNN) and Extreme Gradient Boosting (XGBoost) for sustainable agriculture. Aerial footage of high resolution obtained from drones is analysed for feature extraction and classification to evaluate crop health and suggest specific treatments. The suggested method significantly boosts accuracy and operating efficiency relative to baseline models such as SVM, KNN, and Decision Trees. The hybrid CNN+XGBoost model attained an accuracy of 96.4%, precision of 95.1%, recall of 94.7%, and an AUC of 0.982 through attentive model training and validation utilising datasets from Kaggle. The results confirm the system's capacity to accurately identify stressed vegetation. The suggested framework, in contrast to standard models, integrates environmental and economic characteristics, facilitating sustainable input utilisation. This research enhances machine learning applications in agriculture while providing a scalable and resource-efficient solution. The integration of drone technology with advanced analytics facilitates the emergence of next-generation smart farming systems. Future enhancements encompass real-time analytics, multi-spectral sensor integration, and adaptive learning to generalise across different agro-climatic zones.","author":[{"family":"Singh","given":"Davinder"},{"family":"Reddy","given":"PCP"},{"family":"Devayani","given":"G"},{"family":"Poongothai","given":"S"},{"family":"Suganthi","given":"G"},{"family":"Babu","given":"GC"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/gitcon65266.2025.11377119","URL":"https://doi.org/10.1109/gitcon65266.2025.11377119","source":"crossref"},{"id":"doi:10.7160/aol.2025.170101","type":"article-journal","title":"Precision Crop Farming Framework for Small-Scale Rainfed Agriculture Using UAV RGB High-Resolution Imagery","abstract":"This paper presents a precision crop farming framework developed for small-scale rainfed agriculture using unmanned aerial vehicle (UAV) red, green, and blue (RGB) high-resolution imagery. The aim is to enhance farm management by providing precise spatial and temporal information in heterogeneous farming systems in Botswana's semi-arid regions. The precision crop farming framework integrates UAVs and Global Navigation Satellite System (GNSS) data, introducing new vegetation indices and employing machine learning algorithms for high-accuracy crop and land use analysis. The framework comprises four components: data collection, applications, data processing, and users. Methods included UAV data acquisition, global navigation satellite system geo-referencing, and machine learning classification. Results demonstrated high spatial resolution and classification accuracy, providing actionable insights into crop conditions, planting patterns, and farm variability. The precision crop farming framework is a tool for improving agricultural productivity and sustainability, providing a foundation for efficient, data-driven farm management practices.","author":[{"family":"Bolo","given":"Basuti"},{"family":"Zlotnikova","given":"Irina"},{"family":"Mpoeleng","given":"Dimane"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7160/aol.2025.170101","URL":"https://doi.org/10.7160/aol.2025.170101","source":"crossref"},{"id":"doi:10.3390/su18010249","type":"article-journal","title":"AI, Precision Agriculture and Tourism for Sustainable Regional Development: The Case of the Aegean Islands and Crete, Greece","abstract":"Artificial Intelligence plays an exponentially growing role in producing data-driven policy insights. In this policy-oriented case study, AI technology is examined as a necessary coordination node through evidence-based and data-enhanced policies, which can efficiently balance the processes of different and possibly competing sectors, such as agriculture and tourism. The focus is on the NUTS 1 region of the Aegean Islands and Crete (EL4) in Greece. The analysis aims to create a viable and resilient ecosystem of environmental, economic and social sustainability through innovation. Applying a “Growth Pole Theory” approach, key public administration frameworks like the European Interoperability Framework (EIF) and TAPIC (Transparency, Accountability, Participation, Integrity, Capacity) governance framework are discussed and analysed to structure the AI deployment and policy considerations for sustainable development. The paper argues in favour of AI’s transformative potential across both the agriculture and tourism sectors.","author":[{"family":"Lotsis","given":"Sotiris"},{"family":"Georgousis","given":"Ilias"},{"family":"Papakostas","given":"George"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/su18010249","URL":"https://doi.org/10.3390/su18010249","source":"crossref"},{"id":"doi:10.19103/as.2025.152.16","type":"article-journal","title":"Developments in site-specific (SS) nutrient management systems for precision agriculture","abstract":"In agriculture, SS nutrient management systems have emerged as pivotal tools for enhancing productivity and sustainability. These systems, grounded in the principles of precision agriculture, aim to tailor nutrient application to the unique characteristics of individual field zones, ensuring optimal resource use and profit maximization while mitigating environmental impacts. The adoption of SS nutrient management represents a departure from traditional uniform application methods, trying to address the spatial and temporal variability inherent in landscapes. By integrating advanced technologies such as crop sensors, models, and machine learning, these systems provide farmers with the tools to make data-driven decisions that balance economic gains with environmental stewardship. This chapter explores the advancements, challenges, and applications of SS nutrient management. It delves into their economic considerations, technological developments, and potential to impact agriculture globally. The goal is to present an overview of how these systems can support sustainable and profitable farming in diverse systems.","author":[{"family":"Arnall","given":"DB"},{"family":"Sharma","given":"S"},{"family":"Sharry","given":"R"},{"family":"Balboa","given":"GR"},{"family":"Fiorellino","given":"NM"},{"family":"Kafle","given":"A"},{"family":"Lewis","given":"K"},{"family":"Reed","given":"V"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2025.152.16","URL":"https://doi.org/10.19103/as.2025.152.16","source":"crossref"},{"id":"doi:10.1163/9789004725232_174","type":"article-journal","title":"Effect of urban relative vegetation cover on peri-urban Medfly population: an Ecoinformatics analysis","abstract":"Urban habitats, characterized by diverse land uses and warmer climates, offer insect pests such as the Mediterranean fruit fly (Ceratitis capitata) favourable conditions, often leading to pest migration into nearby agricultural plots. This study explored the influence of settlement features on C. capitata populations in citrus orchards in Israel. Using large-scale monitoring data and settlement databases, the impact of proximity to settlements and specific settlement characteristics on C. capitata abundance was analyzed. Results show that settlements promote pest presence, with varying effects depending on settlement features. These findings emphasize the need to incorporate urban characteristics into pest management strategies to enhance control and reduce pesticide use.","author":[{"family":"Katz","given":"C"},{"family":"Ben-Yosef","given":"M"},{"family":"Goldshtein","given":"E"},{"family":"Cohen","given":"Y"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_174","URL":"https://doi.org/10.1163/9789004725232_174","source":"crossref"},{"id":"doi:10.19103/as.2024.152.16","type":"article-journal","title":"Developments in site-specific (SS) nutrient management systems for precision agriculture","abstract":"In agriculture, SS nutrient management systems have emerged as pivotal tools for enhancing productivity and sustainability. These systems, grounded in the principles of precision agriculture, aim to tailor nutrient application to the unique characteristics of individual field zones, ensuring optimal resource use and profit maximization while mitigating environmental impacts. The adoption of SS nutrient management represents a departure from traditional uniform application methods, trying to address the spatial and temporal variability inherent in landscapes. By integrating advanced technologies such as crop sensors, models, and machine learning, these systems provide farmers with the tools to make data-driven decisions that balance economic gains with environmental stewardship. This chapter explores the advancements, challenges, and applications of SS nutrient management. It delves into their economic considerations, technological developments, and potential to impact agriculture globally. The goal is to present an overview of how these systems can support sustainable and profitable farming in diverse systems.","author":[{"family":"Arnall","given":"DB"},{"family":"Sharma","given":"S"},{"family":"Sharry","given":"R"},{"family":"Balboa","given":"GR"},{"family":"Fiorellino","given":"NM"},{"family":"Kafle","given":"A"},{"family":"Lewis","given":"K"},{"family":"Reed","given":"V"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2024.152.16","URL":"https://doi.org/10.19103/as.2024.152.16","source":"crossref"},{"id":"doi:10.19103/as.2025.0152.16","type":"article-journal","title":"Developments in site-specific (SS) nutrient management systems for precision agriculture","abstract":"In agriculture, SS nutrient management systems have emerged as pivotal tools for enhancing productivity and sustainability. These systems, grounded in the principles of precision agriculture, aim to tailor nutrient application to the unique characteristics of individual field zones, ensuring optimal resource use and profit maximization while mitigating environmental impacts. The adoption of SS nutrient management represents a departure from traditional uniform application methods, trying to address the spatial and temporal variability inherent in landscapes. By integrating advanced technologies such as crop sensors, models, and machine learning, these systems provide farmers with the tools to make data-driven decisions that balance economic gains with environmental stewardship. This chapter explores the advancements, challenges, and applications of SS nutrient management. It delves into their economic considerations, technological developments, and potential to impact agriculture globally. The goal is to present an overview of how these systems can support sustainable and profitable farming in diverse systems.","author":[{"family":"Arnall","given":"DB"},{"family":"Sharma","given":"S"},{"family":"Sharry","given":"R"},{"family":"Balboa","given":"GR"},{"family":"Fiorellino","given":"NM"},{"family":"Kafle","given":"A"},{"family":"Lewis","given":"K"},{"family":"Reed","given":"V"}],"issued":{"date-parts":[[2026]]},"DOI":"10.19103/as.2025.0152.16","URL":"https://doi.org/10.19103/as.2025.0152.16","source":"crossref"},{"id":"doi:10.3390/agriengineering7120431","type":"article-journal","title":"Vegetation Indices from UAV Imagery: Emerging Tools for Precision Agriculture and Forest Management","abstract":"Unmanned Aerial Vehicles (UAVs) have become essential instruments for precision agriculture and forest monitoring, offering rapid, high-resolution data collection over wide areas. This review synthesizes global advances (2015–2024) in UAV-derived vegetation indices (VIs), combining bibliometric and content analyses of 472 peer-reviewed publications. The study identifies key research trends, dominant indices, and technical progress achieved through RGB, multispectral, hyperspectral, and thermal sensors. Results show an exponential growth of scientific output, led by China, the USA, and Europe, with NDVI, NDRE, and GNDVI remaining the most widely applied indices. New indices such as GSI, RBI, and MVI demonstrate enhanced sensitivity for stress and disease detection in both crops and forests. UAV-based monitoring has proven effective for yield prediction, water-stress evaluation, pest identification, and biomass estimation. Despite significant advances, challenges persist regarding illumination correction, soil background influence, and limited forestry applications. The paper concludes that UAV-derived vegetation indices—when integrated with machine learning and multi-sensor data—represent a transformative approach for the sustainable management of agricultural and forest ecosystems.","author":[{"family":"Peticilă","given":"Adrian"},{"family":"Iliescu","given":"Paul"},{"family":"Dinca","given":"Lucian"},{"family":"Popa","given":"Andy"},{"family":"Murariu","given":"Gabriel"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriengineering7120431","URL":"https://doi.org/10.3390/agriengineering7120431","source":"crossref"},{"id":"doi:10.1163/9789004725232_136","type":"article-journal","title":"Enhancing seeding efficiency using a computer vision system to monitor furrow quality in real-time","abstract":"Effective seed sowing is hindered by challenges such as residue accumulation, low soil temperatures, and hair pinning (crop residue pushed in the trench by the furrow opener), which obstruct optimal trench formation. In this study, a novel computer vision-based method was developed to evaluate row cleaner performance. Multiple air seeders were equipped with a video acquisition system to capture trench conditions after row cleaner operation. The captured data were used to develop a segmentation model that analyzed key elements such as soil, straw, and machinery. Using the results from the segmentation model, an objective method was developed to quantify row cleaner performance. The results demonstrated the potential of this method to improve row cleaner selection and enhance seeding efficiency.","author":[{"family":"Rai","given":"S"},{"family":"Slichter","given":"R"},{"family":"Dalal","given":"A"},{"family":"Sharda","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_136","URL":"https://doi.org/10.1163/9789004725232_136","source":"crossref"},{"id":"doi:10.46335/ijies.2025.10.7.12","type":"article-journal","title":"Machine Learning-Driven Identification of Cotton Leaf Diseases for Precision Agriculture","abstract":"In this study, we propose a machine learningbased method for automatic detection of cotton leaf diseases based on Random Forest classifier.Other features extracted are color based (RGB) and texture based (GLCM) that helps a lot in increasing the classification accuracy.It yielded a 92.5% accuracy rate, which indicates that combining these features was the right way to go! Class imbalance and similar looking diseases were tackled using data augmentation.Further work comprises applying deep learning techniques and IoT real-time based monitoring for precision agriculture.Our findings underline the power of machine learning for better diagnosis of cotton diseases and for achieving a sustainable economy.","author":[{"family":"Patil","given":"Tushar"},{"family":"Pandey","given":"Sanjay"},{"family":"Duche","given":"Ravindra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.46335/ijies.2025.10.7.12","URL":"https://doi.org/10.46335/ijies.2025.10.7.12","source":"crossref"},{"id":"doi:10.1163/9789004725232_169","type":"article-journal","title":"QDrip: a QGIS-based tool for the spatial layout and cost minimization of drip irrigation subunits","abstract":"The design of a drip irrigation subunit requires at least two steps: spatial layout and optimization of its elements. Recently, several researchers have used heuristic methods combined with hydraulic simulation programs for the optimization problem. However, these methods often rely on separate tools for spatial layout and optimization, increasing complexity and costs. In this paper, QDrip, a QGIS plugin that integrates spatial layout and optimization using a genetic algorithm to select commercial pipes and minimize costs is presented. The functionality of QDrip is demonstrated in a vineyard irrigation system in Beire, Spain, where it significantly reduced design costs and increased adaptability in an easy, precise and fast way.","author":[{"family":"Barberena","given":"I"},{"family":"Campo-Bescós","given":"MA"},{"family":"Casalí","given":"J"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_169","URL":"https://doi.org/10.1163/9789004725232_169","source":"crossref"},{"id":"doi:10.3390/agriculture15030227","type":"article-journal","title":"Applications of Raspberry Pi for Precision Agriculture—A Systematic Review","abstract":"Precision agriculture (PA) is a farm management data-driven technology that enhances production with efficient resource usage. Existing PA methods rely on data processing, highlighting the need for a portable computing device for real-time, infield decisions. Raspberry Pi, a cost-effective multi-OS single-board computer, addresses this gap. However, information on Raspberry Pi’s use in PA remains limited. This review consolidates details on Raspberry Pi versions, sensors, devices, algorithm deployment, and PA applications. A systematic literature review of three academic databases (Scopus, Web of Science, IEEE Xplore) yielded 84 (as of 22 November 2024) articles based on four research questions and screening criteria (exclusion and inclusion). Narrative synthesis and subgroup analysis were used to synthesize the results. Findings suggest Raspberry Pi can be a central unit to control sensors, enabling cost-effective automated decision support for PA, particularly in plant disease detection, site-specific weed management, plant phenotyping, biomass estimation, and irrigation systems. Despite focusing on these areas, further research is essential on other PA applications such as livestock monitoring, UAV-based applications, and farm management software. Additionally, Raspberry Pi can be used as a valuable learning tool for students, researchers, and farmers and can promote PA adoption globally, helping stakeholders realize its potential.","author":[{"family":"Joice","given":"Astina"},{"family":"Tufaique","given":"Talha"},{"family":"Tazeen","given":"Humeera"},{"family":"Igathinathane","given":"C"},{"family":"Zhang","given":"Zhao"},{"family":"Whippo","given":"Craig"},{"family":"Hendrickson","given":"John"},{"family":"Archer","given":"David"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15030227","URL":"https://doi.org/10.3390/agriculture15030227","source":"crossref"},{"id":"doi:10.1163/9789004725232_036","type":"article-journal","title":"Automated single-row multi-fan sprayer optimization for efficient spray application in modern apple orchards","abstract":"An autonomous single-row multi-fan sprayer was optimized and evaluated for spray applications in a Washington V-trellised apple orchard. Sonic anemometers quantified the air volume passing through the sprayed row to optimize upper and lower fan speeds. Replicated trials were then conducted to quantify the effect of two application rates (935 and 748 l/ha) and two travel speeds (2.2 and 1.3 m/s) upon canopy deposition (ng/cm2) and both aerial and ground drift (ng/cm2) in two adjacent downwind rows. Treatments with similar speed showed comparable deposition with differences attributed to rate and canopy zones. Drift in adjacent rows was relatively low. Optimizing fan speed, especially as machine speed changes, and fan angle is critical to obtaining more even spray distribution.","author":[{"family":"Hoheisel","given":"GA"},{"family":"Bhalekar","given":"DG"},{"family":"Gorthi","given":"S"},{"family":"Khot","given":"LR"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_036","URL":"https://doi.org/10.1163/9789004725232_036","source":"crossref"},{"id":"doi:10.70965/pbnsei-eb.2025.21","type":"article-journal","title":"An agentic Multi-Agent Platform for Precision Agriculture","abstract":"NeerVaani is a platform that uses AI technology to help Indian farmers the right way.This technology is for farmers.Developed as an advanced multi-agent system on Google Vertex AI, the system integrates multiple modules such as crop recommendation, market forecasting, irrigation scheduling, disease diagnosis, and government scheme navigation.The Smart Irrigation Scheduler is designed to optimize water use dynamically by integrating soil, weather, and crop information.The Crop-Doctor agent on Vertex AI Vision uses transfer learning to diagnose farmer-uploaded plant diseases and generate structured reports of severity and treatment.Knowledge graphs, semantic search, and event-driven workflows use Firestore for data management.The core algorithms include reinforcement learning with human feedback (RLHF), Prophet for time-series forecasting, Google Earth Engine for geospatial analytics, and linear programming for resource optimization.The system is scalable and modular.It is also secure.Further, it offers multi-lingual support.This means that farmers can interact in the dialect of the region.NeerVaani acts as your personal agronomist and scheme navigator.Offering farmers world-class, data-driven, sustainable agriculture solutions that enhance their efficiency, resilience, and assured prosperity.","author":[{"family":"Singh","given":"Raj"},{"family":"Sarkar","given":"Sauradeep"},{"family":"Ghosh","given":"Prithiraj"},{"family":"Narayan","given":"Unnati"},{"family":"Mishra","given":"Sneha"},{"family":"Maiti","given":"Ananjan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70965/pbnsei-eb.2025.21","URL":"https://doi.org/10.70965/pbnsei-eb.2025.21","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7257-0.ch015","type":"article-journal","title":"A Vision for the Future","abstract":"Precision agriculture is undergoing a fundamental paradigm shift, driven by the fusion of AI, autonomous robotics, advanced sensing, digital twins, and biotechnology. This chapter outlines the creation of integrated, data-driven ecosystems to enhance productivity, resource efficiency, and climate resilience. It details enabling technologies—from hyperspectral imaging and biodegradable sensors to AI platforms and nano-enabled inputs—and analyzes the architecture of interoperable farm systems. Socio-economic dimensions, equitable access, and environmental sustainability are examined alongside scalable implementation pathways for all farm types. Critical research gaps in AI generalizability, robotic coordination, and adoption strategies are identified. The trajectory points toward adaptive, fully connected, and self-optimizing farming systems that harmonize food security with ecological stewardship.","author":[{"family":"Shinwari","given":"Afnan"},{"family":"Hameed","given":"Salma"},{"family":"Akhter","given":"Md"},{"family":"Hassan","given":"Faiz"},{"family":"Sani","given":"Ayesha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-7257-0.ch015","URL":"https://doi.org/10.4018/979-8-3373-7257-0.ch015","source":"crossref"},{"id":"doi:10.3389/frobt.2025.1696483","type":"article-journal","title":"Food's future: sustainability and agricultural robotics.","abstract":"Our global food system faces growing challenges such as population growth, climate change, resource constraints, and food loss. This set of threats has begun to erode the stability of food security efforts and challenge the long-term sustainability goals outlined by global organizations. To respond effectively, the sector needs concrete and forward-looking innovations that reflect the objectives of the Sustainable Development Goals (SDGs) of the United Nations (UN), especially the commitment in Goal 2 to eliminate hunger. In this study, we examine how agricultural robotics can support the shift toward more resilient and sustainable food systems, particularly in areas where classical methods are under strain. It brings together perspectives from technology, sustainability, and policy, aiming to bridge broad global priorities with everyday realities faced in local contexts. To structure the discussion in a concise way, our analysis is framed around five different, yet interrelated, dimensions. First, we use a crisis-framing perspective to explain why food system reform has become urgent and to show how these pressures align with key SDG priorities. The second dimension outlines a simple taxonomy that groups agricultural robots according to their domain and intended function while also highlighting ongoing technical issues such as interoperability. The next dimension examines how robotics is being amalgamated with precision farming tools, Internet of Things (IoT) platforms, artificial intelligence (AI), and big data systems. Collectively, these technologies facilitate more autonomous field operations and support faster, data-driven decision making. The sustainability dimension evaluates how these technologies affect environmental, economic, and social outcomes in the agricultural sector. This comprehensive review highlights several potential advantages, such as reduced chemical inputs, improved water efficiency, improvements in soil quality, more efficient use of labor, and new employment opportunities in rural and remote areas. In the final dimension, this study turns to global case studies, drawing comparative insights between developed nations such as Australia and the United States, and emerging economies including Brazil, India, and China. Across these diverse contexts, agricultural robotics consistently demonstrate the capacity to boost productivity, reduce waste, and make more efficient use of resources. It is apparent that these gains extend beyond the farm, contributing to environmental stewardship and broader socio-economic development. Yet, the path to widespread adoption is far from straightforward. Farmers and policymakers alike confront persistent barriers: the high upfront costs of robotic systems, gaps in technical expertise, difficulties in ensuring interoperability across platforms, and pressing ethical questions around data governance and automation. Overcoming these challenges is not simply a technical exercise; it is a prerequisite for realizing the full promise of robotics in reshaping global food systems for a more sustainable future.","author":[{"family":"Nleya","given":"Sindiso"},{"family":"Ndlovu","given":"Siqabukile"},{"family":"Velempini","given":"Mthulisi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3389/frobt.2025.1696483","URL":"https://doi.org/10.3389/frobt.2025.1696483","source":"europepmc"},{"id":"doi:10.5423/ppj.rw.01.2026.0004","type":"article-journal","title":"Artificial Intelligence-Driven Plant Disease Detection and Diagnosis: A Comprehensive Review of Deep Learning Approaches, Multimodal Sensing Technologies, and Future Perspectives in Precision Agriculture.","abstract":"Plant diseases remain a major threat to global food production, causing significant yield losses and economic impact worldwide. Early and precise disease detection is crucial for effective crop management, yet conventional diagnostic approaches are often slow, labor-intensive, and rely on specialized expertise that may not be widely accessible. Recent advances in artificial intelligence (AI), particularly deep learning–based image analysis, offer scalable and automated solutions for plant disease recognition. This review critically examines forty-one peer-reviewed studies published between 2008 and 2025, selected following PRISMA guidelines from major scientific databases. We summarize key methodological developments, including convolutional neural networks, vision transformers, transfer and few-shot learning, and multimodal sensing approaches, highlighting their reported performance and limitations. Although many models achieve high accuracy in controlled datasets, their effectiveness often decreases under real-field conditions due to environmental variability, limited training data, and practical deployment constraints. We discuss existing challenges and propose future research directions, emphasizing improved robustness in field environments, development of lightweight and explainable models suitable for edge deployment, and integration with precision agriculture systems. This review aims to guide the design of reliable, practical, and scalable AI-driven plant disease detection strategies.","author":[{"family":"Ghimire","given":"Surakshya"},{"family":"Lamsal","given":"Rajan"},{"family":"Sankuratri","given":"Anvesh"},{"family":"Lakkarsu","given":"Pradeep"},{"family":"Vutla","given":"Sairam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5423/ppj.rw.01.2026.0004","URL":"https://doi.org/10.5423/ppj.rw.01.2026.0004","source":"europepmc"},{"id":"doi:10.21203/rs.3.rs-6589718/v1","type":"article-journal","title":"Precision Agriculture using Machine Learning and Deep Learning Algorithms: A Comprehensive Study","abstract":"Abstract Farming has evolved from the basic irrigation techniques used in ancient river valley civilizations to the sophisticated Precision Agriculture of today. It plays an important role in the advancement of human society. This paper explores the use of Machine Learning and Deep Learning algorithms in Precision Agriculture, an essential task in agriculture that helps ensure a stable food supply and improves the efficiency of food production. Despite advances in Precision Agriculture and the widespread adoption of Machine Learning and Deep Learning algorithms, a comprehensive review that systematically addresses the challenges of data quality, model interoperability, and multisource data integration in Precision Agriculture is still lacking. We aim to bridge this gap by analyzing more than 100 related studies. We focus on applying several Machine Learning and Deep Learning algorithms, such as Artificial Neural Networks, Support Vector Machines, Convolutional Neural Networks, Random Forests, etc. We use a comparative analysis methodology to identify key features influencing Precision Agriculture, such as temperature, rainfall, remote sensing data, soil types, etc. Our findings highlight continuous challenges in standardizing data protocols and developing Explainable AI models that can be generalized across diverse agricultural conditions. The key takeaway is that integrating IoT with real-time data processing can significantly improve agricultural resilience and efficiency. Future research should focus on refining robust models and expanding multisource data integration to address these challenges effectively.","author":[{"family":"Mahin","given":"Md"},{"family":"Adnan","given":"Md"},{"family":"Khondoker","given":"Rahamatullah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21203/rs.3.rs-6589718/v1","URL":"https://doi.org/10.21203/rs.3.rs-6589718/v1","source":"europepmc"},{"id":"doi:10.20944/preprints202505.0558.v1","type":"manuscript","title":"An Innovative Process Chain for Precision Agriculture Services","abstract":"In this research, an innovative design is set up for regular provision of precision agriculture services, within the framework of fertilization consultancy. The central node of the chain is a geographic information system (GIS), while a 5x5m point grid is the information carrier. Decision-making is supported by machine learning algorithms developed with training of the collected big data. Potential data sources include soil samples, satellite data, yield maps, and agronomic information; while the produced maps are directed to a commercial farm management information system (FMIS) for visualization and storage and -in parallel- to variable-rate technologies (VRT) for the applications. In a large degree, the process chain is automated with Python programming language. The service has been tested exhaustively under true field conditions before is has entered the market.","author":[{"family":"Karydas","given":"Christos"},{"family":"Iatrou","given":"Miltiadis"},{"family":"Mourelatos","given":"Spiros"}],"issued":{"date-parts":[[2025]]},"DOI":"10.20944/preprints202505.0558.v1","URL":"https://doi.org/10.20944/preprints202505.0558.v1","source":"europepmc"},{"id":"doi:10.20944/preprints202506.1371.v1","type":"manuscript","title":"Variable Rate Nitrogen Application in Wheat Based on UAV Derived Fertilizer Maps and Precision Agriculture Technologies","abstract":"Variable-rate nitrogen (VR-N) application allows farmers to optimize nitrogen (N) input site-specifically within field boundaries, enhancing both economic efficiency and environmental sustainability. In this study, VR-N technology was applied to durum wheat in two small-scale commercial fields (3–4 ha each) located in distinct agro-climatic zones of Thessaly, central Greece. A real-time VR-N application algorithm was used to calculate N rates based on easily obtainable near real-time data from unmanned aerial vehicle (UAV) imagery, tailored to the crop’s actual needs. VR-N implementation was carried out using conventional fertilizer spreaders equipped to read prescription maps. Results showed that VR-N reduced N input by up to 50% compared to the conventional uniform rate N (UR-N) application, with no significant impact on wheat yield or grain quality. In one of the fields, VR-N led to a yield increase of 7.2%, corresponding to an economic gain of €164 ha⁻¹, while in the second field—where growing conditions were less favorable—no significant yield advantage was observed. Environmental benefits were also notable. The carbon footprint (CF) of the wheat crop was reduced by 6. 4% to 22.0%, and residual soil nitrate (NO3¯) levels at harvest were 13% to 36% lower in VR-N zones compared to UR-N zones. These findings suggest a decreased risk of NO3¯ leaching and ground water contamination. Overall, the study supports the viability of VR-N as a practical and scalable approach to improve N use efficiency (NUE) and reduce the environmental impact of wheat cultivation which could be readily adopted by farmers.","author":[{"family":"Tsitouras","given":"Alexandros"},{"family":"Noulas","given":"Christos"},{"family":"Liakos","given":"Vasilios"},{"family":"Stamatiadis","given":"Stamatis"},{"family":"Tziouvalekas","given":"Miltiadis"},{"family":"Qin","given":"Ruijun"},{"family":"Evangelou","given":"Elefterios"}],"issued":{"date-parts":[[2025]]},"DOI":"10.20944/preprints202506.1371.v1","URL":"https://doi.org/10.20944/preprints202506.1371.v1","source":"europepmc"},{"id":"doi:10.1163/9789004725232_086","type":"article-journal","title":"Precision weeding in sugar beet farming: UAV monitoring of robotic systems","abstract":"Weeding robots are revolutionizing sugar beet farming. The performance of these systems is typically evaluated based on weed control efficacy (WCE), crop damage, and herbicide savings. While robots demonstrate WCE comparable to conventional methods, optimizing their performance requires improvements in crop and weed detection, reduced crop damage, and identification of critical operational timings. This study employed high-resolution RGB UAV imagery to evaluate seven robotic weeding strategies by tracking plant status pre- and post-weeding. Results showed that UAV-based analyses effectively identified strategies with the highest crop losses (up to 8%). However, UAV-based statistical analysis closely matched traditional scoring methods in differentiating weeding strategies. These findings underscore the potential of UAV technology as a powerful tool for evaluating and optimizing weed control systems contributing indirectly to the reduction of fungicide use.","author":[{"family":"Barreto","given":"A"},{"family":"Koops","given":"D"},{"family":"Fritsch","given":"T"},{"family":"Ungru","given":"A"},{"family":"Yamati","given":"FRI"},{"family":"Paulus","given":"S"},{"family":"Mahlein","given":"AK"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_086","URL":"https://doi.org/10.1163/9789004725232_086","source":"crossref"},{"id":"doi:10.1016/j.compag.2025.110479","type":"article-journal","title":"Development of a Machine vision system for apple bud thinning in precision crop load management","abstract":"Thinning is a critical practice in apple orchard management, directly influencing crop load and fruit quality. To assist automated crop load management, a machine vision system for apple bud detection was developed to be integrated with robotic platforms. The system employed a Kinect Azure sensor for real-time bud detection and branch diameter measurement, utilizing a YOLOv8-based object detection model trained and evaluated across multiple datasets. The evaluation identified the best-performing model by balancing precision, recall, and robustness in the complex and unstructured environments of apple orchards. Several training configurations were assessed, with the selected setup demonstrating a strong balance between precision (68 %), recall (55 %), F1-score (61 %), and mean average precision (mAP: 59 %) across diverse and unstructured orchard environments. This configuration, trained on a combination of FLIR and Kinect Azure data, was chosen for deployment due to its robustness and compatibility with the Kinect Azure sensor in real-world applications. Two proposed imaging methods for branch diameter measurement were validated against manual caliper-based measurements, with statistical analysis revealing no significant differences (p = 0.98). These findings confirm the semi-automated methods as reliable and labor-efficient alternatives for field applications. Additionally, the bud counting algorithm demonstrated accurate tracking and counting of apple buds, effectively avoiding omissions and duplications in real orchard settings. This study underscores the potential of vision systems to revolutionize apple bud thinning, providing a strong foundation for the development of fully automated solutions in precision orchard management.","author":[{"family":"Pawikhum","given":"Kittiphum"},{"family":"Yang","given":"Yanqiu"},{"family":"He","given":"Long"},{"family":"Heinemann","given":"Paul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.compag.2025.110479","URL":"https://doi.org/10.1016/j.compag.2025.110479","source":"crossref"},{"id":"doi:10.1007/s11119-024-10216-y","type":"article-journal","title":"Detecting spatial variation in wild blueberry water stress using UAV-borne thermal imagery: distinct temporal and reference temperature effects","abstract":"The use of thermal-based crop water stress index (CWSI) has been studied in many crops in semi-arid regions and found as an effective method in detecting real-time crop water status of commercial fields remotely and non-destructively. However, to our knowledge, no previous studies have validated the usefulness of CWSI in a temperate crop like wild blueberries. Additionally, the temporal changes of the water status estimation model has not been well-studied. In this multi-year study, Unoccupied Aerial Vehicle (UAV)-borne thermal imageries were collected in 2019, 2020, and 2021 to test the temporal effects and the impact of different approach-based reference temperatures (Twₑₜ, wet reference temperature; Tdᵣy, dry reference temperature) on leaf water potential (LWP) estimation models using CWSI in two large adjacent wild blueberry fields in Maine, United States. We found that different sampling dates have a significant impact on LWP estimation models using CWSISE (statistical Twₑₜ and empirical Tdᵣy reference) and CWSISS (statistical Twₑₜ and statistical Tdᵣy reference). Further, CWSIBB calculated with bio-indicator-based Twₑₜ and Tdᵣy reference was found more effective (r² = 0.79) in estimating LWP in 2021, compared to the CWSISE and CWSISS approaches in 2019 (r² = 0.34 & r² = 0.36), 2020 (r² = 0.38 & r² = 0.44) and 2021 (r² = 0.43 & r² = 0.46). CWSIBB -LWP model-based crop water status maps show high variation in the crop water status of wild blueberries, even in an evenly irrigated field, suggesting the potential of UAV-borne thermal cameras to detect real-time crop water status within the field, with the CWSIBB calculated from bio-indicator-based references being more reliable. Our results could be used for precision irrigation to increase the overall water use efficiency and profitability of wild blueberry production.","author":[{"family":"Barai","given":"Kallol"},{"family":"Wallhead","given":"Matthew"},{"family":"Hall","given":"Bruce"},{"family":"Rahimzadeh-Bajgiran","given":"Parinaz"},{"family":"Meireles","given":"Jose"},{"family":"Herrmann","given":"Ittai"},{"family":"Zhang","given":"Yong"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-024-10216-y","URL":"https://doi.org/10.1007/s11119-024-10216-y","source":"crossref"},{"id":"doi:10.21203/rs.3.rs-8430416/v1","type":"article-journal","title":"Advanced Crop Recommendation: AI Approaches for Precision Agriculture","abstract":"Abstract Agriculture​‍​‌‍​‍‌​‍​‌‍​‍‌ serves as an instance where data-driven technologies are employed to tackle issues that arise from soil degradation, climate change, and incorrect crop selection, etc. Through accurate crop prediction, farmers can select the best crop that suits the soil and thus, more yield will be obtained and the farm will not lose its vitality.This research paper focuses on developing a crop prediction model using Machine Learning and Deep Learning algorithms such as Support Vector Machine (SVM), Naïve Bayes, and Bidirectional Long Short-Term Memory (BiLSTM). By analyzing the soil along with other factors (Nitrogen (N), Phosphorus (P), Potassium (K), pH, Moisture, Temperature, Humidity), the system determines the crop that can yield the maximum output. SVM and Naïve Bayes are selected as baseline machine learning models to compare because they are very efficient and capable of handling multi-class classification, whereas BiLSTM is used to uncover the deeper temporal patterns in soil and environmental data.BiLSTM outperformed other models on almost all the datasets used and is regarded as being superior to traditional machine learning methods because it handles the sequential data in both directions.The findings indicate that integrating soil analytics with advanced modeling significantly increases the accuracy of the models, makes better crop planning possible, and helps in the conservation of natural resources in agriculture.Finally, such a framework, therefore, provides a dependable, scalable, and smart manner of catering to the farmers' needs and leading them to the right decisions in terms of crop selection.","author":[{"family":"Hugar","given":"Deepa"},{"family":"Madagouda","given":"Basavaraj"},{"family":"Patil","given":"Shivanand"},{"family":"Kulkarni","given":"Sanjeev"},{"family":"Jainapure","given":"Swati"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21203/rs.3.rs-8430416/v1","URL":"https://doi.org/10.21203/rs.3.rs-8430416/v1","source":"europepmc"},{"id":"doi:10.5194/egusphere-egu26-1082","type":"article-journal","title":"Deep Learning Based Soil Moisture Downscaling Framework for Precision Agriculture in Data-Scarce Regions","abstract":"High-resolution soil moisture (SM) information is critical for irrigation decision-making, crop modelling, flood and drought prediction, and water resources management. However, satellite products only provide coarse-resolution data that cannot capture farm-scale spatial variability influenced by factors such as soil heterogeneity, topography, and anthropogenic activities. While downscaling methods offer a potential solution, they currently struggle in data-scarce regions, such as India, where the absence of dense observation networks limits their effectiveness. In this study, we present an irrigation optimisation framework that downscales satellite-derived soil moisture (SM) data to field-scale root zone soil moisture (RZSM) to support data-driven irrigation decision-making in Nashik District, Maharashtra, India. Utilising a Convolutional Long Short-Term Memory (ConvLSTM) network, we integrated sparsely located in-situ data from ground-based sensors with remote sensing predictors, including precipitation, vegetation indices, land surface temperature, and terrain attributes. The ConvLSTM architecture captures non-linear spatial and temporal interactions governing the field-scale SM variability. The models achieved strong performance, with Root Mean Square Error (RMSE) values from 0.02 to 0.08 m³/m³, Mean Absolute Error (MAE) values from 0.02 to 0.06 m³/m³, Correlation Coefficient (r) values ranging from 0.79 to 0.92, and Coefficient of Determination (R²) values between 0.61 and 0.88. These results validate the potential of deep learning for accurate field-scale SM estimation without requiring dense ground networks. Building on this, we are currently extending the framework by coupling the ConvLSTM architecture with a farm-scale ecohydrological model. This hybrid approach enables generalised, field-scale mapping at ungauged locations without in-situ sensors, offering a scalable, scientifically grounded solution for precision agriculture in water-stressed regions. This work can support farmers in making informed irrigation decisions and contribute to improved water management practices.","author":[{"family":"Patoo","given":"Usman"},{"family":"Arora","given":"Chetan"},{"family":"Ghosh","given":"Subimal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5194/egusphere-egu26-1082","URL":"https://doi.org/10.5194/egusphere-egu26-1082","source":"crossref"},{"id":"doi:10.2139/ssrn.7213794","type":"manuscript","title":"A Scalable IoT and Fuzzy Logic based approach for Precision Agriculture in Greenhouses","abstract":"To meet the increasing demand for high-quality agricultural products, greenhouses offer a controlled environment that optimizes crop growth. This research aims to design an Internet of Things (IoT) based fuzzy logic control system that delivers optimal greenhouse conditions. With the integration of interdependencies between key parameters like Temperature, humidity, and soil moisture, the system continuously adjusts actuators like fans, heaters, and irrigation systems to provide accurate environmental control. IoT-capable sensor nodes collect real-time environmental data and send it to a cloud platform for monitoring and control. Experiments show the system maintains target setpoints and responds quickly to environmental changes.The proposed system dynamically adjusts greenhouse parameters, improving resource efficiency and reducing water and energy use compared to threshold-based controls.Combining IoT with fuzzy logic enhances decision-making, delivering an efficient, scalable, and sustainable solution for modern greenhouses.","author":[{"family":"Dash","given":"Ashish"},{"family":"Mishra","given":"Rajesh"},{"family":"Panda","given":"Anup"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.7213794","URL":"https://doi.org/10.2139/ssrn.7213794","source":"crossref"},{"id":"doi:10.1002/9781394336364.ch10","type":"article-journal","title":"Case Study on Reinforcement Learning‐Based Decentralized Approach for Precision Agriculture and Environmental Monitoring","abstract":"Precision agriculture and environmental monitoring are necessary to handle the world's resource optimization and sustainability challenges. In this chapter, reinforcement learning (RL) methods are integrated into the development of intelligent systems that can make adaptive decisions in real-time scenarios. The Internet of Things-enabled sensors, cloud-edge computing, and RL algorithms are presented in a combined system architecture to enable effective solutions for agricultural irrigation and environmental monitoring. Deep Q-networks (DQN) and multi-agent RL (MARL) are exploited for algorithmic advances in resource usage, operational efficiency, and environmental impact. The RL approach is used to optimize resource usage, operational efficiency, and environmental impact. The RL-based system in precision agriculture (PA) uses real-time soil moisture, weather, and crop data to develop optimum irrigation schedules that save water and improve yields. A decentralized RL system balances resource consumption to produce accurate and reliable data for decision-making in dynamic environments as part of environmental monitoring. The methodology is demonstrated through case studies, including RL-driven precision drip irrigation in sugarcane farms and RL-based air quality monitoring in urban settings. Through advanced sensor networks, scalable cloud platforms, and data-driven policies, these systems deliver water conservation, pollution control, and sustainability. This opens opportunities for expansion while addressing challenges like data quality, computational complexity, and user adoption. Moreover, a decentralized RL system enables a dynamic balance of resource expenditure through accurate monitoring. The methodology's practicality is illustrated by case studies such as RL-driven precision drip irrigation in sugarcane farms and RL-based air quality monitoring in urban settings.","author":[{"family":"Vijayprasath","given":"S"},{"family":"Raj","given":"RM"},{"family":"Raaj","given":"RS"},{"family":"Manoharan","given":"Ashok"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394336364.ch10","URL":"https://doi.org/10.1002/9781394336364.ch10","source":"crossref"},{"id":"doi:10.1201/9781003507390-18","type":"article-journal","title":"Blockchain and Digital Twin Applications in Precision Agriculture","abstract":"Precision farming is altering the agricultural sector by employing modern methods to maximize crop productivity and minimize resource consumption. This chapter presents an extensive plan for improving agricultural practices by examining the integration of digital twin and blockchain technology in precision agriculture. A decentralized, transparent, and secure platform for data management is offered by blockchain technology, guaranteeing the validity and traceability of agricultural data. Agricultural processes may be replicated and monitored in real time thanks to digital twins, which are virtual copies of actual objects. Farmers can obtain precise control over a range of farming operations, including crop growth forecast and soil health monitoring, by integrating these technologies. Through less waste and resource consumption, this integration promotes sustainability, increases the effectiveness of the supply chain, and makes decision-making easier. The architecture of digital twin and blockchain systems, as well as implementation issues and possible fixes, are covered in this chapter. Additionally provided are case studies and pilot projects that highlight the advantages of this combined approach in precision agriculture. These technologies have the possibility to revolutionize both large- and small-scale farming operations; their scalability and economic consequences are also explored. In the end, this all-encompassing strategy seeks to open the door for more intelligent, effective, and sustainable farming methods, greatly enhancing both environmental preservation and global food security.","author":[{"family":"Kanthavel","given":"R"},{"family":"Venket","given":"SK"},{"family":"Anju","given":"A"},{"family":"Adline","given":"Freeda"},{"family":"Dhaya","given":"R"},{"family":"Vijay","given":"Frank"},{"family":"Fisher","given":"Joseph"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003507390-18","URL":"https://doi.org/10.1201/9781003507390-18","source":"crossref"},{"id":"doi:10.9734/jeai/2025/v47i73640","type":"article-journal","title":"Adoption of Precision Agriculture Technologies in Northern India: A Push-Pull Framework Approach","abstract":"The human population continues to grow steadily with the shrinking resources being used for production situates great challenge against Indian farming system to attain food and environmental security. To counter these twin challenges in the country there is urgent need of application of modern Hi-tech technologies for enhancing the productivity and sustainability of the farming system for long term on scientific basis. Precision farming looks a win-win strategic advancement technology towards improving the potential of agricultural lands to produce crops on sustainable basis and to increase agricultural productivity in the future. However, their adoption, particularly among small and medium-scale farmers in developing nations like India, remains relatively limited. The agriculture and allied sectors are pivotal to the sustainable growth and development of the North Indian state’s economy. It contributes significantly to production, employment and demand generation through various linkages and meets the nutritional requirements of the population. But the sector is currently facing a dilemma as contribution of north Indian states to their state’s GSDP is decreasing which can be attributed to factors like inadequate use of modern technology, indiscriminate use of inputs coupled with improper management practices over a long period. Therefore, the need for focusing on the sustainable use of the inputs and increasing agricultural production has gained prominence in North India. Despite the several initiatives of government through different schemes and Precision Farming Development Centre’s, current status of the precision farming technologies in agriculture regarding its perception and factors influencing its adoption among farmers is not well known in North India. This study investigates the factors influencing the adoption of PFTs among farmers in Northern India through a push-pull framework approach. The present study was purposively conducted in North India. From North India, three states were selected randomly, namely Punjab, Haryana and Himachal Pradesh. Ludhiana, Hisar and Solan districts were purposively selected from each state based on highest number of farmers trained by the Precision Farming Development Centres located in these states. Further, two blocks were selected randomly from each district and from each block, 15 user farmers, who had received PFDC training and adopted at least one precision technology in agriculture or dairy, were selected using snowball sampling and thus, a total of 90 user farmers were surveyed using a structured open-ended interview schedule. Technologies considered included drip irrigation, laser land levelling, variable rate applicators, and automated dairy systems. Findings reveal that pull factors conditions that attract farmers to adopt PFTs play a dominant role. The most influential pull factors included higher yields (86.66%), saving of time and labour (78.89%), and government subsidies (75.55%). Other motivators included improved resource use efficiency, potential for year-round cropping, and environmental benefits. Conversely, push factors limitations of conventional agriculture compelling farmers to shift also significantly impacted adoption decisions. Key push factors included the non-availability of skilled labour (84.44%), low yield under traditional methods (76.66%), high input costs (67.78%), and concerns about product quality and environmental degradation. The study concludes that adoption is influenced by both the attractiveness of precision technologies and the challenges posed by conventional practices. However, adoption remains uneven, especially among smallholders, due to infrastructural, financial, and informational barriers. The findings suggest that policy interventions must address both motivational and structural constraints to facilitate broader adoption of PFTs in India.","author":[{"family":"Chaudhary","given":"Shalini"},{"family":"Meena","given":"Hans"},{"family":"Behera","given":"Jeebanjyoti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jeai/2025/v47i73640","URL":"https://doi.org/10.9734/jeai/2025/v47i73640","source":"crossref"},{"id":"doi:10.1201/9781003498698-2","type":"article-journal","title":"Precision Agriculture for Sustainable Crop Management","abstract":"Agriculture is one of the basic pillars of the global economy, providing food and raw materials needed for survival. However, the food supply is increasingly strained by the need to manage limited resources sustainably. To achieve this, precision agriculture (PA) is a novel model that leverages advanced technologies to improve crop yields, lessen environmental impact, and grow the bottom line of farmers and growers. There are many advantages of smart farming, enhanced agricultural productivity, better knowledge of crop states, damage mitigation, and resource optimization. It employs a methodical approach to execute targeted areas using innovative technologies, such as remote sensing, satellite navigation, and geographic information systems to monitor and assess soil quality, crop health, and pest invasions. It encourages sustainable and effective agricultural practices. Implementation of PA is challenging in low-income regions with limited systems, but this universal deployment is restricted due to the high initial costs, technical limitations, concerns around data privacy, and the requirement for expert knowledge. This chapter examines key milestones and recent technological advancements in PA, including the use of drones, sensors, and machine intelligence. It also delves into the primary challenges hindering the adaptation of this approach and the main concerns associated with these innovations. Financial incentives, technical help, and agricultural education are essential for surmounting barriers to adoption. PA promotes an ecologically friendly, adaptable farming system that can meet future requirements.","author":[{"family":"Zafar","given":"Asma"},{"family":"Ullah","given":"Muhammad"},{"family":"Naseem","given":"Aqsa"},{"family":"Hanif","given":"Aqsa"},{"family":"Adiba","given":"Atman"},{"family":"Javaid","given":"Muhammad"},{"family":"Nargis","given":"Javaria"},{"family":"Fareed","given":"Faiza"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003498698-2","URL":"https://doi.org/10.1201/9781003498698-2","source":"crossref"},{"id":"doi:10.9734/jeai/2025/v47i73591","type":"article-journal","title":"Application of Drones in Precision Agriculture: A Review on Benefits and Challenges","abstract":"The integration of drone technology in precision agriculture is transforming conventional farming practices by enabling data-driven, efficient, and sustainable crop management. This review explores the multipurpose applications of drones, such as crop monitoring, spraying, mapping, soil analysis, irrigation management, and yield estimation. These applications help in reducing labor costs, enhancing input efficiency, and improving productivity through real-time decision-making. Despite their vast potential, the adoption of drones in agriculture faces several challenges including regulatory restrictions, high initial costs, limited battery life, lack of skilled operators, and technical limitations in diverse environmental conditions. The paper critically analyses current advancements, benefits, and technological limitations based on recent research and case studies. It also highlights future prospects of integrating drones with AI, IoT, and GIS for smarter farming systems. The review concludes that while drones hold immense promise for sustainable agriculture, overcoming existing barriers is essential to realize their full-scale deployment and impact.","author":[{"family":"Satish"},{"family":"Shirwal","given":"Sunil"},{"family":"Maheshwari"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jeai/2025/v47i73591","URL":"https://doi.org/10.9734/jeai/2025/v47i73591","source":"crossref"},{"id":"doi:10.4018/979-8-3373-5283-1.ch004","type":"article-journal","title":"Mobile Mapping Systems","abstract":"Mobile Mapping Systems (MMS) are transforming agriculture by integrating advanced sensors, geospatial technologies, and real-time data processing to enhance decision-making. These systems improve productivity, optimize resource use, and support sustainable farming. MMS enables precise mapping of agricultural landscapes, crop health monitoring, and soil analysis, providing valuable insights for smart farming. With increasing demands for sustainable agriculture due to environmental concerns and food security, MMS play a crucial role in addressing these challenges. Their applications range from crop yield prediction to land management and pest detection. This chapter examines MMS architecture, sensor integration, system modelling, and calibration. It also explores the impact of emerging technologies such as AI, machine learning, and cloud computing on MMS functionality. Through case studies and discussions, the chapter highlights current advancements and future trends, offering insights into the evolving role of MMS in modern agriculture.","author":[{"family":"Elbahnasawy","given":"Magdy"},{"family":"Shamseldin","given":"Tamer"},{"family":"Mansour","given":"Ahmed"},{"family":"Alkady","given":"Yasmin"},{"family":"Elashmawi","given":"Walaa"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-5283-1.ch004","URL":"https://doi.org/10.4018/979-8-3373-5283-1.ch004","source":"crossref"},{"id":"doi:10.1201/9781003637264-11","type":"article-journal","title":"Employing Integrated Data to Study the Impact of Climate Change on Agriculture","abstract":"Climate change poses a growing threat to global agriculture, with increasing temperatures, changed precipitation patterns, and growing environmental stressors significantly affecting crop efficiency and food security. Traditional approaches often fall short in capturing the dynamic and multifaceted nature of these climate-agriculture interactions. This study examines the potential of employing integrated data—encompassing satellite imagery, climate projections, soil features, crop simulation productions, and socio-economic indicators—to analyse, model, and respond to the effects of climate change on agricultural systems. Using a systematic literature review based on the PRISMA procedure, this study examines selected publications to find current trends, technologies, and challenges in the application of big data to agricultural climate adaptation. Emphasis is placed on how integrated datasets and advanced analytical techniques, such as geospatial modelling, machine learning, and ensemble simulations, are being used to improve understanding of crop vulnerability, water and soil resource management, and regional adaptation planning. The conclusions highlight the importance of context-specific model calibration, uncertainty quantification, and interdisciplinary methods that combine biophysical and socio-economic dimensions. Persistent challenges remain in standardizing data architectures, ensuring real-time data integration, and translating model outputs into actionable insights. The study concludes by advocating for robust, adaptive, and participatory data outlines supporting evidence-based agricultural plans and climate-resilient farming practices.","author":[{"family":"Gupta","given":"Prateek"},{"family":"Gupta","given":"Priyanka"},{"family":"Sharma","given":"Gitika"},{"family":"Bhavna","given":"Thakur"},{"family":"Vijay","given":"Prakash"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003637264-11","URL":"https://doi.org/10.1201/9781003637264-11","source":"crossref"},{"id":"doi:10.1007/s11119-026-10318-9","type":"article-journal","title":"Integrating stability zones and machine learning for enhanced crop management","abstract":"Abstract Purpose Sustainable agriculture requires both high and stable crop yields. Whilegenotype-environment-management (G×E×M) interactions influence yield stability, implementingsuch understanding into practical applications demands better analytical tools. Yield StabilityZones (YSZ) effectively identify stable and unstable production areas, yet their implementationhas been constrained by data limitations and interpretability challenges. Precision agriculturenow enables the application of YSZ approaches through multi-year yield and management data,while interpretable machine learning (ML) can decode yield drivers into actionable insights. Thisstudy develops a universal framework integrating YSZ and interpretable ML to enhancedecision-making in variable agricultural environments, using citrus production as a case study. Methods Analysis of five-year yield, soil, and rainfall data (2012–2016) from a 250-ha field todevelop an YSZ framework, assess temporal yield stability and interactions by ‘comparing single-year versus multi-year data’ on a real production scenario, and integrate machine learning(decision trees) to promote interpretation of yield factors and support optimized cropmanagement. Results Significant temporal dynamics in soil-yield interactions was found. Single-year assessments fail to capture critical interannual variability in yield drivers. YSZ effectivelydelineated spatially consistent production areas, distinguishing stable high-yielding zones fromunstable regions, while decision trees identified key drivers of yield variability. Conclusion Together, these tools provide a data-driven approach to optimize crop production sustainably.Our methodology bridges a critical gap in crop analytics and offers scalable insights forprecision agriculture under dynamic production systems.","author":[{"family":"Wei","given":"Marcelo"},{"family":"Longchamps","given":"Louis"},{"family":"Colaço","given":"André"},{"family":"Molin","given":"Jose"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10318-9","URL":"https://doi.org/10.1007/s11119-026-10318-9","source":"crossref"},{"id":"doi:10.19103/as.2025.0152.23","type":"article-journal","title":"Developments in precision pasture management systems","abstract":"Pasture management is an important aspect of dairy farming, making up a significant portion of the dairy cow diet in many countries. Where grazing is the primary feed source, it relies on the quantity and nutritive value of grass. Pasture management involves a number of aspects, such as the measurement of pasture quantity and quality. It also increasingly uses data to make grazing management decisions, e.g. in grass allocations, in combination with grass growth predictions in order to refine overall management decisions. This chapter presents an overview of the various technologies used in pasture management with particular focus on new precision technologies.","author":[{"family":"Obrien","given":"B"},{"family":"Hennessy","given":"D"},{"family":"Ruelle","given":"E"}],"issued":{"date-parts":[[2026]]},"DOI":"10.19103/as.2025.0152.23","URL":"https://doi.org/10.19103/as.2025.0152.23","source":"crossref"},{"id":"doi:10.19103/as.2025.152.23","type":"article-journal","title":"Developments in precision pasture management systems","abstract":"Pasture management is an important aspect of dairy farming, making up a significant portion of the dairy cow diet in many countries. Where grazing is the primary feed source, it relies on the quantity and nutritive value of grass. Pasture management involves a number of aspects, such as the measurement of pasture quantity and quality. It also increasingly uses data to make grazing management decisions, e.g. in grass allocations, in combination with grass growth predictions in order to refine overall management decisions. This chapter presents an overview of the various technologies used in pasture management with particular focus on new precision technologies.","author":[{"family":"Obrien","given":"B"},{"family":"Hennessy","given":"D"},{"family":"Ruelle","given":"E"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2025.152.23","URL":"https://doi.org/10.19103/as.2025.152.23","source":"crossref"},{"id":"doi:10.2139/ssrn.6384898","type":"manuscript","title":"Tomato Leaf Disease Detection Using InceptionV3: A CNN-Based Approach for Precision Agriculture","abstract":"Tomatoes play a vital role in agriculture, offering significant nutritional and economic support. Nonetheless, illnesses in tomato plants affect both the quality and quantity. Timely identification of this illness is essential to minimize crop losses. This research suggests employing Convolutional Neural Networks (CNNs) to identify diseases impacting tomato leaf tissue, utilizing a collection of high- resolution images.&lt;br&gt;&lt;br&gt;Data augmentation methods are employed in the training stage to enhance the generalization abilities of the proposed approach. Accuracy, precision, recall, and the F1 score are the evaluation metrics utilized to offer a thorough analysis of the model's effectiveness. The results indicate that the InceptionV3 CNN-based method is effective in precisely diagnosing and classifying diseases impacting tomato leaf tissue. The supplied model shows encouraging potential for real-time disease identification, offering a possible solution for farmers to take preventive actions preemptively; our accuracy rate for the Inception V3 Model is 99.22%.","author":[{"family":"Jain","given":"Dr"},{"family":"Kumari","given":"Ms"},{"family":"Jain","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.6384898","URL":"https://doi.org/10.2139/ssrn.6384898","source":"crossref"},{"id":"doi:10.3390/s26165029","type":"article-journal","title":"A TinyMLOps Pipeline for Coarse-Grained Plant Disease Classification in Precision Agriculture.","abstract":"Identifying plant health conditions is an emerging precision-agriculture and food-security challenge, intensified by deploying deep-learning models on memory- and power-constrained edge devices. We present a TinyMLOps pipeline spanning model design, optimization, quantization, and deployment across diverse edge devices, evaluated under controlled laboratory conditions. Using a dataset derived from the PlantVillage benchmark, 39 fine-grained classes are aggregated into three superclasses: healthy leaf, unhealthy leaf, and no leaves. The resulting system therefore performs plant health-status classification and background filtering rather than diagnosing specific diseases. We train a MobileNet-based convolutional neural network jointly optimized for classification accuracy and computational efficiency, adopting state-of-the-art hyperparameter optimization (HPO) tools. Five models are selected, four from the Pareto Front and one as the biggest evaluated model during HPO, converted to LiteRT and ONNX, and evaluated at float32 and post-training int8 precision on a Raspberry Pi Zero 2 W and an STM32H743ZI microcontroller. At float32, LiteRT is 1.87–2.65× faster than ONNX Runtime on the Raspberry Pi across all five models. Relative to their float32 LiteRT counterparts, the int8 LiteRT models are 2.83–3.67× smaller on disk and 21.3–31.2% faster on the same board, at a cost in F1-score of between 0.0010 and 0.0068. On the microcontroller, only the two smallest models deploy at both precisions; for these, the fully quantized int8 variants are 4.3× faster and 3.85× smaller in MCU flash footprint than the float32 counterparts. The mid-range model fits the 2 MB flash and 1 MB RAM budget only when quantized, while the two largest models exceed it in every configuration tested.","author":[{"family":"Aqasizade","given":"Hossein"},{"family":"Antonini","given":"Mattia"},{"family":"Vecchio","given":"Massimo"},{"family":"Antonelli","given":"Fabio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/s26165029","URL":"https://doi.org/10.3390/s26165029","source":"europepmc"},{"id":"doi:10.1038/s41467-026-70730-7","type":"article-journal","title":"Cellulose-based sensors for decentralized monitoring in precision agriculture.","abstract":"Abstract Modern agriculture requires rapid, affordable tools to monitor crops and soils directly in the field. Cellulose, the structural polymer of plants, is emerging as a versatile foundation for lightweight, biodegradable sensors that measure nutrients, moisture, stress, and disease without laboratory infrastructure. Spanning simple paper assays to flexible wearables, these platforms enable distributed, real-time insight into plant and soil health. As materials engineering converges with digital connectivity, cellulose-based sensors could accelerate the transition toward more data-driven, adaptive, and sustainable agricultural systems.","author":[{"family":"Rayappa","given":"Mirinal"},{"family":"Flauzino","given":"José"},{"family":"Grell","given":"Max"},{"family":"Güder","given":"Firat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1038/s41467-026-70730-7","URL":"https://doi.org/10.1038/s41467-026-70730-7","source":"europepmc"},{"id":"doi:10.3791/73067","type":"article-journal","title":"Harnessing Digital Technologies in the Agro-Food Sector: An IoT-Driven Precision Agriculture Framework for Achieving Sustainable Development Goals.","abstract":"The agro-food industry is quickly digitizing to solve resource restrictions, climate unpredictability, and sustainable food production using Internet of Things (IoT), Artificial intelligence (AI), cloud computing, and data analytics. Due to rigid irrigation schedules and limited field monitoring, traditional agriculture wastes water, reduces crop yield, and harms the environment. The IoT-Driven Precision Agriculture (IoT-PA) system in this paper optimizes agricultural resource use using distributed sensor networks, real-time soil moisture and weather monitoring, and intelligent irrigation control. The proposed platform gathers environmental data, analyses field conditions, and automatically recommends irrigation to maximize crop growth and avoid water waste. Farmers may make data-driven agricultural decisions with continuous monitoring and fast notifications from the framework. The IoT-PA architecture improves irrigation efficiency, agricultural yield, and sustainable resource management compared to traditional farming. Higher agricultural production and efficient water and resource use assist Sustainable Development Goal (SDG) 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) of the United Nations Sustainable Development Goals. The suggested smart agricultural system is scalable and practicable, promoting sustainable food production and environmental conservation.","author":[{"family":"Sakthivel","given":"TG"},{"family":"Ashok","given":"R"},{"family":"Kumar","given":"APS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3791/73067","URL":"https://doi.org/10.3791/73067","source":"europepmc"},{"id":"doi:10.3389/frobt.2026.1732004","type":"article-journal","title":"Osiris&lt;sup&gt;++&lt;/sup&gt;: hierarchical representations for robotic-enabled precision agriculture.","abstract":"There has been significant development in agricultural robotics over the past few years in the pursuit of optimising efficiency and addressing issues such as labour shortages and humans performing hazardous and arduous tasks. Despite this, human–robot interaction in the agricultural sector remains largely unchanged, often requiring technical expertise, which hinders wide-scale adoption. This problem is particularly pronounced in the African context, where limited technical exposure and linguistic diversity pose significant barriers to the adoption of these technologies. While alternative means for human–robot collaboration have been developed, these methods are currently limited to indoor structured environments. In this work, we introduce Osiris++, a flexible approach designed to allow seamless communication between robots and humans on an array of precision agriculture tasks. We validate and evaluate the performance of Osiris++ in real-world agricultural environments, demonstrating that the system can create accurate and useful scene graphs that aid in solving the assigned tasks. This paves the way for the possibility of allowing natural language instructions, including those in African languages, to be issued to robots within the agricultural sector.","author":[{"family":"Mukuddem","given":"Adam"},{"family":"Speed-Andrews","given":"Adam"},{"family":"Maweni","given":"Thabisa"},{"family":"Nanyaro","given":"Imannuel"},{"family":"Sojen","given":"Ritvik"},{"family":"Hsiao","given":"Venny"},{"family":"Amayo","given":"Paul"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/frobt.2026.1732004","URL":"https://doi.org/10.3389/frobt.2026.1732004","source":"europepmc"},{"id":"doi:10.21203/rs.3.rs-9340242/v1","type":"article-journal","title":"Efficient Super-Resolution for Resource-Constrained Precision Agriculture: A Loss Function Optimization Approach","abstract":"Abstract In smart agriculture, vision-based crop monitoring systems require high-quality imagery along with efficient computation and low power consumption to support accurate analysis and real-time decision-making in resource-constrained edge environments. However, in digital image processing, image quality and computational performance present a trade-off, where increasing reconstruction quality typically increases model complexity and resource requirements. This study addresses this challenge by proposing a lightweight super-resolution (SR) approach optimized for real-world edge applications in agriculture. Unlike existing SR methods that rely on complex architectures or synthetic datasets, this work focuses on loss function-level optimization to improve perceptual image quality without increasing computational cost and power consumption, making it applicable to support resource-constrained precision smart agriculture. ESPCN was chosen as the baseline due to its efficiency, and was further optimized by replacing the conventional Mean Squared Error (MSE) loss with L1 loss to improve robustness to noise and lighting variations. Experimental results on a real-world lettuce dataset captured using ESP32-CAM show that the proposed method produces better texture quality in both day and night conditions. Structural evaluation using Laplacian-based edge density and sharpness, supported by statistical analysis, confirmed improved preservation of high-frequency details without additional computational or energy costs. These findings demonstrate that lightweight loss function optimization provides a practical and energy-efficient solution for improving image quality in edge-based agricultural monitoring systems.","author":[{"family":"Khalif","given":"Mhd"},{"family":"Djuana","given":"Tjhwa"},{"family":"Rambung","given":"Richard"},{"family":"Janna","given":"Achmad"},{"family":"Prabowo","given":"Listyo"},{"family":"Hulu","given":"Tirta"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21203/rs.3.rs-9340242/v1","URL":"https://doi.org/10.21203/rs.3.rs-9340242/v1","source":"europepmc"},{"id":"doi:10.3389/fpls.2026.1848455","type":"article-journal","title":"From classical practices to precision agriculture: a multidisciplinary review of tea (&lt;i&gt;Camellia sinensis&lt;/i&gt;).","abstract":"Tea ( Camellia sinensis ) is one of the most widely consumed beverages worldwide and a crop of enduring cultural, economic, and scientific significance. Although many studies has examined cultivation and trade, no previous review has integrated tea’s long-term domestication history with recent advances in precision agriculture and digital technologies. This review addresses that gap by providing a multidisciplinary synthesis that links the historical, biological, agroecological, and technological dimensions of tea production. This review demonstrates that tea productivity and quality are strongly influenced by interactions among genotype, environment, and management practices, while climate variability increasingly disrupts these relationships. At the same time, precision agriculture technologies offer substantial potential to improve disease detection, optimise resource use, and support data-driven decision-making. However, their adoption remains uneven because of high implementation costs, limited accessibility for smallholder farming systems, and challenges related to data infrastructure. Based on this synthesis, we propose that future research and policy should prioritise: (i) the region-specific integration of digital technologies with traditional cultivation practices; (ii) the development of low-cost, scalable technologies suitable for smallholders; and (iii) climate-resilient cultivation strategies adapted to shifting agroecological conditions. These targeted interventions are essential for improving productivity, sustainability, and resilience across the global tea industry.","author":[{"family":"Yildiz","given":"Muhammet"},{"family":"Mert","given":"Mehmet"},{"family":"Mansoor","given":"Sheikh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fpls.2026.1848455","URL":"https://doi.org/10.3389/fpls.2026.1848455","source":"europepmc"},{"id":"doi:10.3390/s26041297","type":"article-journal","title":"AI-Driven Weather Data Superresolution via Data Fusion for Precision Agriculture.","abstract":"Accurate field-scale meteorological information is required for precision agriculture, but operational numerical weather prediction products remain spatially coarse and cannot resolve local microclimate variability. This study proposes a data fusion superresolution workflow that combines global GFS predictors (0.25°), regional station observations from Southern Moravia (Czech Republic), and static physiographic descriptors (elevation and terrain gradients) to predict the 2 m air temperature 24 h ahead and to generate spatially continuous high-resolution temperature fields. Several model families (LightGBM, TabPFN, Transformer, and Bayesian neural fields) are evaluated under spatiotemporal splits designed to test generalization to unseen time periods and unseen stations; spatial mapping is implemented via a KNN interpolation layer in the physiographic feature space. All learned configurations reduce the mean absolute error relative to raw GFS across splits. In the most operationally relevant regime (unseen stations and unseen future period), TabPFN-KNN achieves the lowest MAE (1.26 °C), corresponding to an ≈24% reduction versus GFS (1.66 °C). The results support the feasibility of an operational, sensor-infrastructure-compatible pipeline for high-resolution temperature superresolution in agricultural landscapes.","author":[{"family":"Pihrt","given":"Jiří"},{"family":"Šimánek","given":"Petr"},{"family":"Čepek","given":"Miroslav"},{"family":"Charvát","given":"Karel"},{"family":"Kovalenko","given":"Alexander"},{"family":"Horáková","given":"Šárka"},{"family":"Kepka","given":"Michal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/s26041297","URL":"https://doi.org/10.3390/s26041297","source":"europepmc"},{"id":"doi:10.1038/s41598-026-42151-5","type":"article-journal","title":"Design and implementation of a deep learning framework for automated crop classification and health diagnosis in precision agriculture.","abstract":"This paper presents a three-phase deep learning framework comprising (i) multi-modal data acquisition from drones and satellites, (ii) standardized pre-processing including interpolation for missing temporal data, and (iii) CNN-based feature extraction for real-time health classification. This framework relies on a mathematical model based on neural networks that classifies and detects the condition of agriculture, removing the reliance on manual tasks and subjective diagnosis. This paper focuses on three main aspects of our framework: data acquisition, training and prediction. Data is collected using sensors like drones, cameras, and satellite imagery and is pre-processed to filter out noise and improve quality. The training part uses CNN to learn features from the data and become more meaningful. The prediction part of the task classifies, and diagnoses crop health through the trained model using the features. The framework accuracy for crops such as maize, potato, and wheat has been tested and yielded over 90% accuracy. The novelty of this work resides in the development of a multi-modal deep learning architecture that fuses macro-scale satellite imagery with micro-scale drone and IoT sensor data to improve diagnostic reliability. The framework was validated on a multi-source agricultural dataset using a 70% training, 15% validation, and 15% testing protocol. Experimental results demonstrate an accuracy exceeding 90% for staple crops. Using this framework can increase the visibility and quality of information maintained for crop health and improve the decision-making routine of farmers in real time. Additionally, automation of this process can significantly reduce labor costs and increase productivity per crop. Implementing this framework can contribute to precision agriculture and sustainable management practices.","author":[{"family":"Pal","given":"Atul"},{"family":"Patro","given":"BDK"},{"family":"Chaube","given":"Shshank"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1038/s41598-026-42151-5","URL":"https://doi.org/10.1038/s41598-026-42151-5","source":"europepmc"},{"id":"doi:10.1038/s41598-026-39596-z","type":"article-journal","title":"Strengthening human infrastructure for smart farming through competency-based assessment of extension agents in precision agriculture.","abstract":"The transition to sustainable agricultural systems increasingly depends on the effective adoption of precision agriculture (PA) technologies. In the United States, Extension agents serve as key facilitators of agricultural innovation and play a critical role in supporting farmers through this transition. However, gaps in professional competencies can hinder their ability to promote and implement PA practices. This study conducted a needs assessment among agricultural Extension agents to evaluate perceived importance and organizational support for 13 core competencies essential to PA adoption. Findings revealed that the most significant needs for support from the Cooperative Extension Service included equipment operational skill, strategy execution, and problem-solving. These gaps highlighted that Extension agents perceived persistent gaps in their capacity to promote PA-related competencies. The Cooperative Extension Services must incorporate a balance of technical, operational, and soft skills to enhance Extension agents’ capacity to facilitate the adoption of precision agriculture. The study recommended that Extension systems inventory existing training resources, reallocate efforts, and invest in addressing the identified competency gaps presented in this study. Investing in the competencies needed for Extension agents will prepare them to effectively communicate precision agriculture practices and facilitate the adoption of the rapidly evolving precision agriculture technologies toward sustainable agriculture.","author":[{"family":"Lee","given":"Chin"},{"family":"Orton","given":"Ginger"},{"family":"Oliveira","given":"Luan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1038/s41598-026-39596-z","URL":"https://doi.org/10.1038/s41598-026-39596-z","source":"europepmc"},{"id":"doi:10.3389/fpls.2026.1846319","type":"article-journal","title":"Foliar-applied honokiol exhibits basipetal translocation, offering a strategy for root disease management in precision agriculture systems.","abstract":"Introduction Root diseases in crops are increasingly becoming the most difficult to control due to the challenge of fungicides reaching infection sites. Honokiol, a natural fungicidal product derived from Magnolia officinalis , is primarily biosynthesized in leaves and subsequently translocated to roots to resist pathogen infection. Methods In this study, honokiol applied to the leaves of Polygonatum cyrtonema Hua (PCH) could be transported downward to the roots and exhibited a control effect against root rot disease. Results Subsequent research showed that concentration, temperature, pH, energy inhibitors (DNP, CCCP) and other agents (AgNO 3 , BaCl 2 , CaCl 2 ) significantly affect basipetal translocation of honokiol, suggesting that its translocation from leaves to roots is mediated by transport proteins. The distribution of honokiol in various parts of PCH was found as leaf &amp;gt; stem &amp;gt; root, indicating that honokiol was absorbed by the leaves and transferred to the roots through phloem. Translocation factor root/stem value of honokiol in PCH was more than 1, indicating that honokiol was easy to transfer to the root. Subsequently, four potential transporter proteins, ABCB11, ABCG24, TIP1–2 and PIP1-3, were screened from Arabidopsis thaliana for molecular docking analysis, indicating a significant binding affinity between honokiol and transporter proteins having a binding energy of −12.83 kcal mol -1 , −10.70 kcal mol -1 , −9.38 kcal mol -1 and −10.67 kcal mol -1 , respectively. Discussion Foliar-applied honokiol exhibited pronounced basipetal translocation, efficiently moving from leaves to root tissues where root rot pathogens reside. This systemic redistribution enables targeted delivery of the antifungal compound honokiol to the infection site without direct soil application, minimizing environmental exposure.","author":[{"family":"Cao","given":"Zhangguang"},{"family":"Wei","given":"Guoyu"},{"family":"Khan","given":"Amir"},{"family":"Hu","given":"Anlong"},{"family":"Guo","given":"Zhenxiang"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fpls.2026.1846319","URL":"https://doi.org/10.3389/fpls.2026.1846319","source":"europepmc"},{"id":"doi:10.1002/fsn3.70963","type":"article-journal","title":"High-Performance Deep Learning for Instant Pest and Disease Detection in Precision Agriculture.","abstract":"ABSTRACT Global farm productivity is constantly under attack from pests and diseases, resulting in massive crop loss and food insecurity. Manual scouting, expert estimation, and laboratory‐based microscopy are time‐consuming, prone to human error, and labor‐intensive. Although traditional machine learning classifiers such as SVM, Random Forest, and Decision Trees provide better accuracy, they are not field deployable. This article presents a high‐performance deep learning fusion model using MobileNetV2 and EfficientNetB0 for real‐time detection of pests and diseases in precision farming. The model, trained on the CCMT dataset (24,881 original and 102,976 augmented images in 22 classes of cashew, cassava, maize, and tomato crops), attained a global accuracy of 89.5%, precision and recall of 95.68%, F1‐score of 95.67%, and ROC‐AUC of 0.95. For supporting deployment in edge environments, methods such as quantization, pruning, and knowledge distillation were employed to decrease inference time to below 10 ms per image. The suggested model is superior to baseline CNN models, including ResNet‐50 (81.25%), VGG‐16 (83.10%), and other edge lightweight models (83.00%). The optimized model is run on low‐power devices such as smartphones, Raspberry Pi, and farm drones without the need for cloud computing, allowing real‐time detection in far‐off fields. Field trials using drones validated rapid image capture and inference performance. This study delivers a scalable, cost‐effective, and accurate early pest and disease detection framework for sustainable agriculture and supporting food security at the global level. The model has been successfully implemented with TensorFlow Lite within Android applications and Raspberry Pi systems.","author":[{"family":"Bilal","given":"Muhammad"},{"family":"Shah","given":"Asghar"},{"family":"Abbas","given":"Sagheer"},{"family":"Khan","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/fsn3.70963","URL":"https://doi.org/10.1002/fsn3.70963","source":"europepmc"},{"id":"doi:10.1016/j.dib.2025.112174","type":"article-journal","title":"MoringaLeafNet: A multi-class leaf disease dataset for precision agriculture and deep learning research.","abstract":"Moringa Oleifera, which has outstanding nutritional and health benefits, is prized around the world because its leaves are rich in essential vitamins, antioxidants, and minerals that support digestion, help the immune system, and fight inflammation. Still, growing Moringa can be difficult because diseases such as Yellow Leaf, Bacterial Leaf Spot, and Cercospora Leaf Spot are hard to detect early and spread fast, leading to a lot of damage. These illnesses cause plants to make less yield, so farmers depend on pesticides and spend more, which also damages the environment and their crops. Here, we make available the MoringaLeafNet dataset, including high-quality images of leaves from the Moringa tree affected by different diseases. The images in the dataset, gathered from March to April and August to September 2025, are divided into four classes: Healthy Leaf, Yellow Leaf, Bacterial Leaf Spot, and Cercospora Leaf Spot. We collected images from Sumi Nursery in Madhupur, Tangail, Bangladesh, and Rafin Nursery in Birulia, Savar, Bangladesh, under various weather conditions. To facilitate better use in deep learning, random rotation, flipping, and brightness/contrast adjustments were performed on the data. The dataset will help develop new disease detection systems in agriculture that allow the early recognition of Moringa leaf diseases. It can also support the development of real-time diagnostic systems that provide farmers with timely insights for decision-making.","author":[{"family":"Sa","given":"Preanto"},{"family":"Mhi","given":"Bijoy"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.dib.2025.112174","URL":"https://doi.org/10.1016/j.dib.2025.112174","source":"pubmed"},{"id":"doi:10.1038/s41598-025-16942-1","type":"article-journal","title":"Multiple model visual feature embedding and selection method for an efficient pest classification supporting precision agriculture.","abstract":"Agriculture 5.0 is a principal economic activity in the world with major workforce dependent crops cultivation. An automated system for crops field insect pest identification can help decrease labour, while also improving the speed and precision in compared to manual methods. Less computation and memory systems are getting utilized for remote deployments of classification systems. In this paper, efficient pretrained multiple deep learning models based visual feature extraction and Linear Discriminant Analysis (LDA) based feature selection to provide high efficacy with light resource requirements. This proposed approach also able to handle large number of classes. To achieve this, diverse pest datasets were combined including 9 and 12 classes respectively and the utilized combined dataset contains total 19 classes. Methodology of proposed system included the selection of multiple pretrained models including DenseNet201, EfficientNetB3 and InceptionResNetV2 based on less memory and less parametric requirements. The second last layer of mentioned models have been utilized for selection of features as DenseNet201, EfficientNetB3 and InceptionResNetV2 resulted 1920, 1536 and 4608 accordingly. The extracted features combined and selected using LDA according to the number of classes. At end a basic light dense neural network have been deployed for classification. This makes a low resource and high efficacy pest classification model for higher number of classes. The results obtained by proposed technique are 99.99% Accuracy, 100% validation, 99.99% Recall and negligible Loss. Further the proposed system has been analysed and compared with benchmark approaches including transfer learning and single model feature extraction and selection approach. The main advantage of our proposed hybrid feature selection is that it makes the classification process lighter because it involves selecting relevant features from the existing dataset without training additional models, whereas transfer learning typically involves retraining or fine-tuning pre-existing models, which can be more computationally intensive. Overall the proposed system and approach resulting higher results with lighter process resources that fitted better in the development of domain of precision agriculture.","author":[{"family":"Sb","given":"Bhattacharjee"},{"family":"Sk","given":"Gupta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1038/s41598-025-16942-1","URL":"https://doi.org/10.1038/s41598-025-16942-1","source":"pubmed"},{"id":"doi:10.7717/peerj.19058","type":"article-journal","title":"Advancing medicinal plant agriculture: integrating technology and precision agriculture for sustainability.","abstract":"To strengthen the agriculture sector, it is crucial to combine the efforts of industrialization (field mechanization and fertilizer production), technology (genome editing and manipulation), and the information sector (for the application of current technologies in precision agriculture). The challenge of modern sustainable agriculture is increasing agricultural output while using the least amount of resources and capital expenditure possible and considering the variables contributing to environmental damage. Different environmental factors adversely affect medicinal plant populations, leading to the extinction of these valuable medicinal species. These difficulties drew the attention of the international scientific community to farm sustainability and energy efficiency studies that put forth the idea of precision agriculture (site-specific crop management) in medicinal plants. It is a systems-based method that monitors and responds to changes in intra- and inter-field conditions for environmentally friendly and optimum crop output. Farming systems have significantly benefited from the visualization and morphological analysis of agricultural areas (both open fields and greenhouse experiments) using remote sensing technology, geographic information systems (GIS), crop scouting, variable rate technology (VRT), and Global Positioning System (GPS). These technologies form the backbone of the fourth agricultural technological revolution, Agriculture 4.0. This review concisely summarizes these innovative technologies’ current use and potential future advancements in medicinal plants. The review is intended for researchers, professionals in medicinal plant cultivation, herbal medicine research, crop science, and related fields.","author":[{"family":"Kumar","given":"Vinay"},{"family":"Zadokar","given":"Ashwini"},{"family":"Kumar","given":"Pankaj"},{"family":"Sharma","given":"Rohit"},{"family":"Sharma","given":"Rajnish"},{"family":"Siddiqui","given":"Mohammed"},{"family":"Irfan","given":"Mohammad"},{"family":"Chandora","given":"Rahul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7717/peerj.19058","URL":"https://doi.org/10.7717/peerj.19058","source":"europepmc"},{"id":"doi:10.5281/zenodo.20696354","type":"article-journal","title":"Multi-Modal Integrated CNN–Random Forest Framework for Disease Classification, Argo-Environmental Crop Recommendation, and Yield Prediction","abstract":"Artificial Intelligence (AI) is transforming agriculture by enabling intelligent systems for improved productivity and decision-making. This paper presents a multi-modal framework that integrates Convolutional Neural Networks (CNNs) and Random Forest-based Machine Learning models for crop disease detection, crop recommendation, and yield prediction. The CNN model analyzes leaf images to identify diseases, while Random Forest models use soil and environmental parameters such as NPK values, temperature, humidity, rainfall, pH, and land area for recommendations and yield estimation. Experimental results show 96.85% accuracy in disease detection, 95.6% accuracy in crop recommendation, and an RMSE of 3.92 with an R² score of 0.91 for yield prediction. The integrated framework further improved performance, achieving 96.1% accuracy, RMSE of 3.67, and R² of 0.93. The results demonstrate the effectiveness of multi-modal learning for precision agriculture and support data-driven, sustainable farming practices.","author":[{"family":"Dattatraya","given":"Deshmukh"},{"family":"Mahajan","given":"Jagruti"},{"family":"Jadhav","given":"Dr"},{"family":"Chandane","given":"Pragati"},{"family":"Patil","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20696354","URL":"https://doi.org/10.5281/zenodo.20696354","source":"datacite"},{"id":"doi:10.5281/zenodo.20696355","type":"article-journal","title":"Multi-Modal Integrated CNN–Random Forest Framework for Disease Classification, Argo-Environmental Crop Recommendation, and Yield Prediction","abstract":"Artificial Intelligence (AI) is transforming agriculture by enabling intelligent systems for improved productivity and decision-making. This paper presents a multi-modal framework that integrates Convolutional Neural Networks (CNNs) and Random Forest-based Machine Learning models for crop disease detection, crop recommendation, and yield prediction. The CNN model analyzes leaf images to identify diseases, while Random Forest models use soil and environmental parameters such as NPK values, temperature, humidity, rainfall, pH, and land area for recommendations and yield estimation. Experimental results show 96.85% accuracy in disease detection, 95.6% accuracy in crop recommendation, and an RMSE of 3.92 with an R² score of 0.91 for yield prediction. The integrated framework further improved performance, achieving 96.1% accuracy, RMSE of 3.67, and R² of 0.93. The results demonstrate the effectiveness of multi-modal learning for precision agriculture and support data-driven, sustainable farming practices.","author":[{"family":"Dattatraya","given":"Deshmukh"},{"family":"Mahajan","given":"Jagruti"},{"family":"Jadhav","given":"Dr"},{"family":"Chandane","given":"Pragati"},{"family":"Patil","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20696355","URL":"https://doi.org/10.5281/zenodo.20696355","source":"datacite"},{"id":"doi:10.5281/zenodo.20710497","type":"article-journal","title":"Advances in Horticultural Crop Production and Improvement","abstract":"Horticulture has emerged as one of the most dynamic and rapidly advancing sectors in agriculture, contributing significantly to nutritional security, economic development, environmental sustainability, and livelihood generation. With the growing challenges of climate change, resource degradation, emerging pests and diseases, and increasing food demands, modern horticultural research is witnessing remarkable innovations in genomics, precision agriculture, biotechnology, artificial intelligence, protected cultivation, post-harvest management, and climate-resilient production systems. The present book entitled “ADVANCES IN HORTICULTURAL CROP PRODUCTION AND IMPROVEMENT” is a comprehensive compilation of contemporary topics that reflect the recent scientific developments and future prospects in horticultural crop improvement and management. The chapters included in this volume encompass diverse and interdisciplinary areas such as salt stress management in tomato, precision horticulture, plant growth regulators, genome editing technologies, genetic engineering, omics approaches, GWAS studies, climate-resilient horticulture, AI and machine learning applications, nutrient management, micropropagation innovations, and conservation of horticultural genetic resources. This book aims to serve as a valuable resource for students, researchers, academicians, extension workers, scientists, and professionals working in the field of horticulture and allied sciences. Each chapter has been contributed by experts and scholars with the objective of providing updated scientific knowledge, practical insights, and future research directions. We sincerely hope that this book will contribute meaningfully to the advancement of horticultural sciences and inspire innovative research and sustainable production strategies for future generations.","author":[{"family":"Abhishek"},{"family":"Mavinalli","given":"Santosh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20710497","URL":"https://doi.org/10.5281/zenodo.20710497","source":"datacite"},{"id":"doi:10.5281/zenodo.20710498","type":"article-journal","title":"Advances in Horticultural Crop Production and Improvement","abstract":"Horticulture has emerged as one of the most dynamic and rapidly advancing sectors in agriculture, contributing significantly to nutritional security, economic development, environmental sustainability, and livelihood generation. With the growing challenges of climate change, resource degradation, emerging pests and diseases, and increasing food demands, modern horticultural research is witnessing remarkable innovations in genomics, precision agriculture, biotechnology, artificial intelligence, protected cultivation, post-harvest management, and climate-resilient production systems. The present book entitled “ADVANCES IN HORTICULTURAL CROP PRODUCTION AND IMPROVEMENT” is a comprehensive compilation of contemporary topics that reflect the recent scientific developments and future prospects in horticultural crop improvement and management. The chapters included in this volume encompass diverse and interdisciplinary areas such as salt stress management in tomato, precision horticulture, plant growth regulators, genome editing technologies, genetic engineering, omics approaches, GWAS studies, climate-resilient horticulture, AI and machine learning applications, nutrient management, micropropagation innovations, and conservation of horticultural genetic resources. This book aims to serve as a valuable resource for students, researchers, academicians, extension workers, scientists, and professionals working in the field of horticulture and allied sciences. Each chapter has been contributed by experts and scholars with the objective of providing updated scientific knowledge, practical insights, and future research directions. We sincerely hope that this book will contribute meaningfully to the advancement of horticultural sciences and inspire innovative research and sustainable production strategies for future generations.","author":[{"family":"Abhishek"},{"family":"Mavinalli","given":"Santosh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20710498","URL":"https://doi.org/10.5281/zenodo.20710498","source":"datacite"},{"id":"doi:10.5281/zenodo.21210792","type":"article-journal","title":"Printing technologies for monitoring crop health","abstract":"Agricultural production requires low-cost sensors capable of delivering reliable, high-resolution data across large areas. Rising food demand, limited arable land, and severe soil degradation have accelerated the adsorption of precision agriculture, which relies on real-time monitoring of soil, plant, and environmental conditions. Central to this shift is the development of scalable sensor technologies enabled by advances in materials sciences. Printing techniques, including inkjet, screen, aerosol jet, 3D printing, and direct laser writing, offer versatile routes to fabricate flexible, large area, and plant-integrated sensors. This Review surveys recent progress in printable low-dimensional materials for agricultural sensing, examines their physicochemical properties in relation to sensor performance, and discusses key challenges and future opportunities requiring interdisciplinary integration.","author":[{"family":"Panáček","given":"David"},{"family":"Kupka","given":"Vojtech"},{"family":"Nalepa","given":"Martin"},{"family":"Dědek","given":"Ivan"},{"family":"Alvarez Diduk","given":"Ruslan"},{"family":"Olenik","given":"Selin"},{"family":"Flauzino","given":"José"},{"family":"Zdrazil","given":"Jan"},{"family":"Jakubec","given":"Petr"},{"family":"Zdražil","given":"Lukáš"},{"family":"Spíchal","given":"Lukáš"},{"family":"Sonigara","given":"Keval"},{"family":"Zboril","given":"Radek"},{"family":"Pumera","given":"Martin"},{"family":"Merkoçi","given":"Arben"},{"family":"Wang","given":"Joseph"},{"family":"De Diego","given":"Nuria"},{"family":"Güder","given":"Firat"},{"family":"Otyepka","given":"Michal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21210792","URL":"https://doi.org/10.5281/zenodo.21210792","source":"datacite"},{"id":"doi:10.5281/zenodo.21210793","type":"article-journal","title":"Printing technologies for monitoring crop health","abstract":"Agricultural production requires low-cost sensors capable of delivering reliable, high-resolution data across large areas. Rising food demand, limited arable land, and severe soil degradation have accelerated the adsorption of precision agriculture, which relies on real-time monitoring of soil, plant, and environmental conditions. Central to this shift is the development of scalable sensor technologies enabled by advances in materials sciences. Printing techniques, including inkjet, screen, aerosol jet, 3D printing, and direct laser writing, offer versatile routes to fabricate flexible, large area, and plant-integrated sensors. This Review surveys recent progress in printable low-dimensional materials for agricultural sensing, examines their physicochemical properties in relation to sensor performance, and discusses key challenges and future opportunities requiring interdisciplinary integration.","author":[{"family":"Panáček","given":"David"},{"family":"Kupka","given":"Vojtech"},{"family":"Nalepa","given":"Martin"},{"family":"Dědek","given":"Ivan"},{"family":"Alvarez Diduk","given":"Ruslan"},{"family":"Olenik","given":"Selin"},{"family":"Flauzino","given":"José"},{"family":"Zdrazil","given":"Jan"},{"family":"Jakubec","given":"Petr"},{"family":"Zdražil","given":"Lukáš"},{"family":"Spíchal","given":"Lukáš"},{"family":"Sonigara","given":"Keval"},{"family":"Zboril","given":"Radek"},{"family":"Pumera","given":"Martin"},{"family":"Merkoçi","given":"Arben"},{"family":"Wang","given":"Joseph"},{"family":"De Diego","given":"Nuria"},{"family":"Güder","given":"Firat"},{"family":"Otyepka","given":"Michal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21210793","URL":"https://doi.org/10.5281/zenodo.21210793","source":"datacite"},{"id":"doi:10.20944/preprints202606.1181.v1","type":"manuscript","title":"Transforming Agriculture with Cyber-Physical Systems: An Insight into Future Smart Farming","abstract":"Agriculture is going through transformations by leveraging the advancements in technological practices including the implementation of Cyber-physical systems (CPS), a centralized system encompassing highly integrated computational and physical elements. It consists of the interconnected web of physical elements in the form of wired and/or wireless field sensors (e.g., moisture sensors, temperature sensors, pH sensors, humidity sensors, etc.), and computational and control elements in the form of artificial intelligence enhanced processing algorithms (e.g., machine learning and deep learning models) CPS allows farmers to, manage irrigation, dispense fertilizers and pesticides meticulously, and anticipate crop yield and market demand. Conventional labor-intensive procedures can be eliminated with these technologies, which can automate all crop-growing activities from field preparation to harvesting. The objective of the perspective is to give an insight into CPS in agriculture, their use, implementation, current challenges, and future recommendations while highlighting the benefits of carrying out CPS in agriculture, such as improved efficiency, enhanced productivity, and minimal resource wastage. It discusses key components and technologies involved, such as sensor networks, Internet of Things (IoT) appliances, cloud driven computing, and data analytical frameworks. Furthermore, challenges and limitations of CPS implementation, including high upfront costs, infrastructure requirements, and data privacy concerns, are also discussed. Future directions and research opportunities in precision farming, predictive analytics, and resource allocation optimization are explored.","author":[{"family":"Waseem","given":"Muhammad"},{"family":"Batool","given":"Hamna"},{"family":"Rehman","given":"Tanzeel"},{"family":"Majeed","given":"Yaqoob"},{"family":"Ahmad","given":"Faraz"},{"family":"Syed","given":"Hamid"},{"family":"Nadeem","given":"Tayyaba"}],"issued":{"date-parts":[[2026]]},"DOI":"10.20944/preprints202606.1181.v1","URL":"https://doi.org/10.20944/preprints202606.1181.v1","source":"europepmc"},{"id":"doi:10.21203/rs.3.rs-9430430/v1","type":"article-journal","title":"Deep learning-based detection of strawberry fruit and ripeness in smart farming -- First review of architectures, real-world studies, and challenges","abstract":"Abstract Accurate detection of strawberry fruit and reliable estimation of ripeness are essential for automated harvesting and yield prediction in smart farming. However, real-world environments introduce significant challenges, including occlusion, illumination variability, and high visual similarity between ripeness stages. Deep learning (DL)-based object detection methods have become the dominant approach to address these issues. This paper presents a systematic review of 50 peer-reviewed studies published between 2023 and 2026, focusing specifically on DL-based detection of strawberry fruit and ripeness. The studies are analyzed with respect to dataset characteristics, preprocessing and annotation strategies, model architectures, and evaluation protocols. Our results show a clear dominance of one-stage detectors, particularly the YOLO family (v5–v11), used in 42 of the 50 reviewed works (84%) due to their real-time capabilities. Transformer-based and hybrid CNN–ViT models are gaining attention and show improved performance in complex scenarios, but often at higher computational cost. However, we identify critical methodological issues that affect the validity of reported results. In particular, the improper application of data augmentation prior to dataset splitting --- a practice observed in one-third of the reviewed studies --- poses a significant risk of data leakage and can result in overly optimistic performance estimates. Additional challenges include inconsistent evaluation metrics, limited dataset diversity, and a lack of standardized benchmarks. This review provides a structured overview of current approaches, a critical assessment of existing research practices, and actionable guidance for developing robust, deployment-ready DL solutions for precision agriculture.","author":[{"family":"Jelali","given":"Mohieddine"},{"family":"Gerz","given":"Fabian"},{"family":"Altan","given":"Orhan"},{"family":"Al-Shrouf","given":"Loui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21203/rs.3.rs-9430430/v1","URL":"https://doi.org/10.21203/rs.3.rs-9430430/v1","source":"europepmc"},{"id":"doi:10.1007/s11119-024-10208-y","type":"article-journal","title":"Joint plant-spraypoint detector with ConvNeXt modules and HistMatch normalization","abstract":"Abstract Context Serrated tussock ( Nassella trichotoma ) is a weed of national significance in Australia which offers little to no nutritional value to livestock, and has the potential to reduce carrying capacity and agricultural return of infested pastures. Aims The aim of this study was to adapt existing Convolutional Neural Networks (CNNs) for plant segmentation and spraypoint detection in the challenging environments of pastures. Methods CNNs that were designed for joint plant and stem segmentation in crop fields were repurposed for dual-task applications in pastures. Given the poor performance of these models in complex pasture environments, a new model drawing inspiration from the recently proposed ConvNeXt was developed, tested for its effectiveness on unseen field data, and enhanced with a novel normalization technique, called HistMatch. Key results Experimentation demonstrated that unlike pre-existing models, which were designed for the simpler environments encountered in early-stage crop fields, our model was able to generalize well to growing conditions not seen during training, achieving 0.807 mIoU and 0.796 F1-score for the plant and spraypoint tasks respectively. This is in comparison to pre-existing models, which achieved 0.270 - 0.454 mIoU and 0.073 - 0.496 F1-score for the same tasks. These results were further improved to 0.854 mIoU and 0.806 F1-score using HistMatch normalization. In spite of greater model complexity, our model had a inference time of 15.7 ms which was comparable to pre-existing models, and suitable for real-time applications. Conclusion Models with greater complexity are required for the relatively complex environments encountered in pastures, but this greater complexity need not come at the expense of real time capability. HistMatch normalization can improve model accuracy, and is particularly effective in cases where models are struggling to generalize well to testing conditions that vary significantly from those seen during training. Implications and impacts The successful adaptation and improvement of CNNs for weed management in pastures could significantly reduce the reliance on blanket herbicide application. HistMatch normalization could also be considered for other agricultural applications, including weed management and disease detection in crop fields and orchards.","author":[{"family":"Ford","given":"Jonathan"},{"family":"Sadgrove","given":"Edmund"},{"family":"Paul","given":"David"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-024-10208-y","URL":"https://doi.org/10.1007/s11119-024-10208-y","source":"crossref"},{"id":"doi:10.5958/0976-4615.2024.00030.3","type":"article-journal","title":"Precision Application of Nitrogen by Root Dipping Application as Starter Solution in Chilli (Capsicum annuum L.)","abstract":"To meet the nutritional demand of the vegetable crops, it is essential to supply nutrients throughout their growth period. Supply of nutrients at initial growth stages of plant leads to improved root development thus ultimately enhances nutrient uptake. Application of fertilisers near the plant root zone had been found more beneficial in liquid form as compared to solid applications. Therefore, an experiment was conducted that comprised one control N1 (water dip only) and three concentrations of urea solution viz., N2 (1% urea solution), N3 (2% urea solution) and N4 (3% urea solution) applied as root dip to chilli hybrid i.e., G1 (Arka Gagan) and variety namely G2 (Kashi Anmol). All the treatments were laid out in Factorial Randomized Block Design (FRBD) with three replications. The data observed for all the parameters was found significantly affected with the use of varying concentration of urea solution. All the growth and yield parameters were statistically improved with increased concentration of urea solution from 0 to 3 per cent, while the least days to first flowering (87.50) and days to 50% flowering (94.83) and days to first harvest (112.83) were observed under control treatment. Performance of the hybrid (Arka Gagan-962.1 g/plant) and variety (Kashi Anmol-879.7 g/plant) in terms of yield was improved by 24 % and 19.4% respectively, with the application of 3% urea solution as root dipping as compared to control treatment (water dip).","author":[{"family":"Dutt","given":"Vikram"},{"family":"Singh","given":"Gagandeep"},{"family":"Singh","given":"Gurmehak"},{"family":"Singh","given":"Nirmal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5958/0976-4615.2024.00030.3","URL":"https://doi.org/10.5958/0976-4615.2024.00030.3","source":"crossref"},{"id":"doi:10.5772/intechopen.1014293","type":"article-journal","title":"Climate Change, Insect Dynamics and Precision Adaptive Strategies","abstract":"Insect pest and beneficial insect dynamics have been altered by shifting environmental factors such as rising temperatures, modified patterns of rainfall and humidity, higher CO levels, and more frequent extreme weather events. Precision agricultural techniques can facilitate efficient and adaptive responses to these changes. Indirect effects through host plants and trophic interactions (e.g., phenological mismatch, changes in plant physiology), geographic shifts in pest ranges and invasive species, and direct effects on insects (development, reproduction, survival) are also included. In order to enable early warning and spatially focused interventions, this review chapter additionally addresses monitoring, modeling, and prediction techniques such as DSS, weather data integration, degree-day models, machine learning, and remote sensing. Precision techniques are addressed on the adaptation side, including variable-rate treatments, timing of interventions, breeding for resistance, optimizing beneficial insect populations, and agronomic practices modified for the microclimate. The ultimate goal is to demonstrate how precision data-driven methods may improve agricultural resilience in the face of climate uncertainty, preserve ecosystem services, and reduce food loss.","author":[{"family":"Ishtiaq","given":"Muhammad"},{"family":"Qayyum","given":"Mirza"},{"family":"Sharif","given":"Umer"},{"family":"Ameer","given":"Muhammad"},{"family":"Naeem","given":"Muhammad"},{"family":"Taha","given":"Hasan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5772/intechopen.1014293","URL":"https://doi.org/10.5772/intechopen.1014293","source":"crossref"},{"id":"doi:10.1007/s11119-026-10381-2","type":"article-journal","title":"Economics and adoption perspectives of site-specific weed management: A review","abstract":"Abstract Purpose Site-specific weed management (SSWM) has become recognised as a promising strategy to reduce herbicide use without compromising crop yield. Despite technological advances, the economic viability and adoption of this technology remain uncertain. This review identifies and analyses 27 economic evaluation studies from the past three decades, focusing on methodological frameworks, considered factors, and reported results. Methods Following PRISMA 2020 guidelines, a systematic literature review was conducted across Scopus, Wiley Online, and AgEcon Search to identify economic evaluations of SSWM published between 1990 and 2025. Out of 2,184 initial records, studies were screened manually based on explicit eligibility criteria, requiring an advanced economic analysis (e.g., partial budgeting, bio-economic modelling, or benefit-cost analysis). Due to substantial study heterogeneity, a qualitative synthesis was performed by grouping the final selected literature into thematic clusters based on methodology and technological context. Results Early studies, focused on robust biological modelling, often reported positive outcomes, yet they commonly underestimated or omitted technology and management costs, leading to overestimated profitability. When such costs were included, results were mixed or negative. While recent studies incorporating AI-based precision spraying included technology costs and showed improved profitability, they omitted biological modelling, similarly overestimating benefits. Published break-even analyses indicated that the required farm sizes exceeded the average farm size in countries like Germany, suggesting that widespread adoption might depend on service providers or cooperatives, although such approaches remain unpopular among farmers. Moreover, sensitivity analyses, crucial to simulation modelling, were conducted only in seven studies. Further methodological limitations include, for example, interpolated weed maps or simplified yield-loss functions. Furthermore, environmental and social benefits, core to the SSWM concept, were widely omitted in economic evaluations. Conclusion Despite the increasing availability of commercial solutions, empirical evaluations, particularly under real-world, multi-year conditions, remain scarce. This overview underscores the need for integrative approaches that combine technological advancements with refined bio-economic and ecological models. Informed by policy frameworks, such efforts are essential to balance profitability and sustainability goals, realising the full potential of SSWM in European small- to medium-scale farming systems.","author":[{"family":"Pitsyk","given":"Vladyslav"},{"family":"Pfrombeck","given":"Johanna"},{"family":"Gandorfer","given":"Markus"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10381-2","URL":"https://doi.org/10.1007/s11119-026-10381-2","source":"crossref"},{"id":"doi:10.1016/j.jafr.2025.102422","type":"article-journal","title":"Edge-deployable segmentation and prescription mapping of post-emergence weeds in sugar beet crops for UAV-based precision spraying","abstract":"Weeds significantly challenge sugar beet cultivation by reducing yields and increasing herbicide usage. Conventional broadcast spraying inflates production costs and raises environmental concerns due to chemical overuse. To address these challenges, this study presents a comprehensive deep learning (DL)-based framework for site-specific weed detection and precision herbicide application using UAV-acquired imagery. High-resolution RGB ortho-mosaic data from experimental sugar beet fields were used to train and evaluate multiple semantic segmentation (U-Net, PSPNet, DeepLabv3) and instance segmentation (YOLOv8, Mask R-CNN) models. U-Net, coupled with a ResNet-34 backbone, achieved the highest segmentation accuracy, with IoUs of 0.85 for Sugar beet and 0.72 for weeds. Prescription maps derived from segmented weed cover suggested a theoretical herbicide savings rate of up to 82.88 % compared to conventional uniform spraying. Instance segmentation was also performed using YOLOv8, YOLOv9, YOLO11, and Mask R-CNN to detect weed patches within the crop canopy. YOLOv8 outperformed Mask R-CNN in instance segmentation mAP (0.728 vs. 0.627), while Mask R-CNN achieved higher classification precision. Edge deployment was explored using optimized and quantized YOLOv8 variants, with the YOLOv8-SB model offering real-time inference speeds exceeding 48 FPS. This research demonstrates a scalable and field-deployable approach for weed mapping and precision spraying in dense weed patches, significantly reducing chemical use while enhancing site-specific weed management practices. • A deep learning approach for aerial weed segmentation and localization during the post-emergence growth stage. • Mapping of weeds based on DL segmentation models for real-time weed spraying and removal. • Identifying areas with high weed density is crucial for optimizing herbicide usage.","author":[{"family":"Joy","given":"Jino"},{"family":"Kelvin","given":"Betitame"},{"family":"Howatt","given":"Kirk"},{"family":"Aderholdt","given":"William"},{"family":"Khan","given":"Mohamed"},{"family":"Peters","given":"Thomas"},{"family":"Sun","given":"Xin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.jafr.2025.102422","URL":"https://doi.org/10.1016/j.jafr.2025.102422","source":"crossref"},{"id":"doi:10.1007/s11119-026-10330-z","type":"article-journal","title":"A stochastic frontier approach to nitrogen use and efficiency in soft wheat cultivation","abstract":"Abstract Purpose This study evaluates the impact of nitrogen recommendations provided by a Decision Support Systems (DSS) on soft wheat production and technical efficiency in specialized Italian cereal farms. Methods Employing a Stochastic Frontier Analysis, the research evaluates the relationship between adherence to DSS recommendations and farm performance. The analysis relies on real farm data from the Barilla Farming platform, agrarian year 2022/2023, covering 487 farms and 1,664 fields, including suggested and actual nitrogen applications and observed yields. Results Findings indicate that compliance with DSS recommendations enhances output levels and efficiency, particularly for medium and large farms, whereas deviations, especially over-application, reduce efficiency with potential increase of costs and environmental risks. Notably, small farms maintain efficiency despite lower nitrogen applications, indicating the need for tailored DSS calibration. Results highlight the importance of site-specific nitrogen management strategies to optimize both economic and environmental outcomes. Conclusion While promoting DSS adoption is essential, our findings suggest that ensuring farmers’ compliance with DSS recommendations is equally—if not more—critical to realizing its full benefits. Policymakers and extension services should not only encourage the uptake of DSS but also focus on strategies that enhance farmers’ adherence to recommended practices. Additionally, ensuring the adaptability of DSS to different farm structures is key to maximizing its impact across varying production scales.","author":[{"family":"Cappella","given":"Maria"},{"family":"Caracciolo","given":"Francesco"},{"family":"Blasi","given":"Emanuele"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10330-z","URL":"https://doi.org/10.1007/s11119-026-10330-z","source":"crossref"},{"id":"doi:10.1163/9789004725232_143","type":"article-journal","title":"Studying digital tools for mechanical weeding to better grasp the adoption of precision farming","abstract":"Adoption of precision agriculture (PA) has been widely addressed in the literature but the pathways leading to the adoption or non-adoption of PA are often poorly explored. This study proposed an original approach to understanding and formalizing the diversity of adoption pathways based on the use case of the adoption of precision mechanical weeding (PMW) technologies. A qualitative approach based on 16 semi-structured interviews with experts, farmers and advisors was tested. Identified key adoption pathways were formalized using the personae approach representing fictional people with realistic characteristics. Six personae were identified illustrating that the characteristics of digital tools, the socio-technical environment, agronomic conditions and the decision-maker’s personal story have significant impact on adoption.","author":[{"family":"Ruiz","given":"V"},{"family":"Djafour","given":"S"},{"family":"Pichon","given":"L"},{"family":"Tisseyre","given":"B"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_143","URL":"https://doi.org/10.1163/9789004725232_143","source":"crossref"},{"id":"doi:10.1002/9781394287260.ch20","type":"article-journal","title":"Precision Agriculture with Unmanned Aerial Vehicles","abstract":"The emergence of precision agriculture addresses the growing demand for more proficient and sustainable farming methods. By harnessing advanced tools like unmanned aerial vehicles (UAVs), GPS, remote sensing, and data analytics, precision agriculture enables farmers to manage soil and crops with remarkable precision. UAVs, integrated with automated systems, sensors, and cameras, play a pivotal role in facilitating crop observation and management, thereby improving productivity, ensuring quality, and minimizing labor efforts. Adopting machine learning (ML) and Internet of Things (IoT) technologies further transforms farming by supporting real-time data acquisition, analysis, and decision-making processes. This chapter offers an in-depth exploration of the applications and limitations associated with incorporating UAVs, AI, and IoT into precision agriculture. It examines the design and control systems of UAVs tailored for farming and highlights their specific uses, including crop spraying, health surveillance, and seed dissemination, emphasizing their contribution to eco-friendly agricultural practices.","author":[{"family":"Suresh","given":"S"},{"family":"Boopathi","given":"Sampath"},{"family":"Elayaraja","given":"R"},{"family":"Velmurugan","given":"D"},{"family":"Selvapriya","given":"R"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394287260.ch20","URL":"https://doi.org/10.1002/9781394287260.ch20","source":"crossref"},{"id":"doi:10.3390/agriculture16060663","type":"article-journal","title":"Effectiveness of Mechanical Precision Weed Control in Organically Grown Winter Spelt Wheat","abstract":"Weed competition restricts organic cereal production. In our study on the mechanical control of weeds, classic (tined weeder) and modern machines were used (spring-tined weeder, rotary weeder and camera-guided hoe). The study was conducted in two growing seasons, 2023–2024 and 2024–2025, on an organic farm, with medium-heavy soil in central Poland. Precision weed control included the following treatments: the first pass was done using a precision spring-tined weeder, the second using a rotary weeder, the third using a camera-guided precision hoe, and the fourth using the rotary weeder once more. Precision weed control compared to classic weed control resulted in a 5.5-times lower number of weeds per 1 m2 and an 8.6-times lower weed biomass. Precision weed control resulted in higher yields—in a classic weed control scheme, spelt wheat yielded almost 4.5 t of dehulled grain per ha, and in precision weed control, yields were ca. 10% higher. Grain quality was high—protein content was approximately 14%, gluten content 28.8% and the Zeleny index was 53.8 mL.","author":[{"family":"Tyburski","given":"Józef"},{"family":"Kowalska","given":"Jolanta"},{"family":"Obremski","given":"Kazimierz"},{"family":"Żurek","given":"Marcin"},{"family":"Wojtacha","given":"Paweł"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16060663","URL":"https://doi.org/10.3390/agriculture16060663","source":"crossref"},{"id":"doi:10.1007/s11119-025-10261-1","type":"article-journal","title":"Dynamic approaches to precision irrigation of cotton","abstract":"Abstract Purpose Zones for spatial irrigation management are often assumed to be static, dictated by non- or slowly-changing parameters, including elevation and slope, soil depth, texture and hydraulic properties, and other landscape properties. Sensing allows for the integration of static management zones (MZ) with a dynamic characterization of water status. Temporal remote sensing data, indicating crop status and, particularly, thermal imaging, indicating water status, suggests that, rather than static, dynamic re-zoning within crop seasons could be beneficial to precision water management. Methods MZ delineation and precision irrigation for cotton were evaluated using a variable rate center pivot sprinkler system. The objectives were to evaluate precision management over time with both static and intra-seasonal dynamic zoning. Spatial distribution and irrigation decision-making were re-evaluated on a weekly basis. Irrigation followed commercial best management, based on target values of plant size (growth rate) in the early vegetative growth period and of plant water status (leaf water potential, LWP) in the reproductive and cotton boll production periods. Site-specific decision-making used drone-acquired normalized difference vegetation index as a proxy for crop height and growth rate and a thermal image-based crop water stress index as a proxy for LWP. Results and conclusion Dynamic precision irrigation of cotton based on weekly decisions using the remote sensing products slightly decreased spatial variability while improving water productivity by 12% using static MZs and by 19% using dynamic MZs, compared to commercial uniform irrigation. The costs and benefits of implementing intra-seasonal dynamic zoning are discussed.","author":[{"family":"Ben-Gal","given":"A"},{"family":"Barski","given":"A"},{"family":"Bukris","given":"O"},{"family":"Yasuor","given":"H"},{"family":"Oshaughnessy","given":"SA"},{"family":"Hansen","given":"NC"},{"family":"Peeters","given":"A"},{"family":"Cohen","given":"Y"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10261-1","URL":"https://doi.org/10.1007/s11119-025-10261-1","source":"crossref"},{"id":"doi:10.19103/as.2025.0152.13","type":"article-journal","title":"Developments in controlled traffic farming (CTF) in precision agriculture","abstract":"The farm practice of controlled traffic farming as a means of reducing compaction damage to soils is described and its benefits in terms of crop and soil responses are outlined. Particular benefits are in lowering greenhouse gas emissions both pre-farm gate and on-farm. A case study outlines how the benefits have been put into practice on a farm. Gantry tractors are introduced as a means of improving the efficiency of controlled traffic farming systems and their benefits and shortcomings are summarised. Particular emphasis is placed on their potential to increase the precision of farming operations.","author":[{"family":"Chamen","given":"William"},{"family":"Mcphee","given":"John"},{"family":"Pedersen","given":"Hans"},{"family":"Carter","given":"Lyle"}],"issued":{"date-parts":[[2026]]},"DOI":"10.19103/as.2025.0152.13","URL":"https://doi.org/10.19103/as.2025.0152.13","source":"crossref"},{"id":"doi:10.9734/jeai/2025/v47i23262","type":"article-journal","title":"Harnessing Robotics for Enhanced\tPrecision in Agriculture","abstract":"The inner workings of the Unmanned Aerial Vehicles (UAVs) employed in agriculture consist of navigation sensors, computational techniques, path planning algorithms, and control strategies. Various smart sensors, such as optical sensors, are integrated into automated machines to detect early signs of pest infestation in standing crops. Additionally, UAVs are equipped with different types of sensors required for analyzing crop-related parameters category of agricultural robots. These robots, along with automated machines, are utilized to accomplish precision farming objectives. Autonomous navigation systems. Among the most common sensors are optical ones, including RGB, multispectral, and hyperspectral cameras.","author":[{"family":"Sahu","given":"Manisha"},{"family":"Verma","given":"Ajay"},{"family":"Kuruwanshi","given":"VB"},{"family":"Sahu","given":"Deepika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jeai/2025/v47i23262","URL":"https://doi.org/10.9734/jeai/2025/v47i23262","source":"crossref"},{"id":"doi:10.1007/s11119-026-10383-0","type":"article-journal","title":"Robust automated processing of continuous electrical resistivity measurements for soil texture mapping in support of optimized precision farming","abstract":"Abstract Background Optimized nutrient and water supply is crucial for enhancing crop yields and ensuring environmental sustainability. As a result, sensor-based, high-resolution soil data, which account for in-field soil variability, are becoming increasingly important for effective nutrient and water management. This paper presents research using electrical resistivity methods, which identify variations in electrical soil properties. Methods Utilizing rolling electrodes, the GEOPHILUS sensor platform continuously conducts measurements of resistivity data. Soil resistivity is measured by injecting an electrical current into the ground and recording the resulting potential differences between electrodes, introducing an approach to map the bulk electrical resistivity of soils. The system’s design and technical capabilities enable the collection of these parameters at five different depths, reaching approximately two meters, however, the speed of the moving measuring system produces data with substantial distortions, which is why a data pre-cleaning step is required. The main objective involves resistivity data processing and 1D inversions. We have developed a robust code to evaluate and process the data and make 1D inversion for all soundings. Data preprocessing is performed to enhance the reliability of resistivity measurements, improving their suitability for further analysis. This step includes filtering out noise and identifying any outliers. Multiple data processing algorithms were used to enhance the quality of the original data and make them ready for inversion. Results Correlation analyses between resistivity and soil texture confirmed strong relationships, with higher resistivity linked to coarser soils and lower resistivity associated with finer soils. The findings validate the approach and its effectiveness in capturing subsurface soil properties. Conclusions The developed methodology offers a reliable framework for processing electrical resistivity data, facilitating a more accurate understanding of soil characteristics, which can inform precision farming practices.","author":[{"family":"Roudsari","given":"Mohamad"},{"family":"Bönecke","given":"Eric"},{"family":"Rühlmann","given":"Jörg"},{"family":"Günther","given":"Thomas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10383-0","URL":"https://doi.org/10.1007/s11119-026-10383-0","source":"crossref"},{"id":"doi:10.19103/as.2024.152.13","type":"article-journal","title":"Developments in controlled traffic farming (CTF) in precision agriculture","abstract":"The farm practice of controlled traffic farming as a means of reducing compaction damage to soils is described and its benefits in terms of crop and soil responses are outlined. Particular benefits are in lowering greenhouse gas emissions both pre-farm gate and on-farm. A case study outlines how the benefits have been put into practice on a farm. Gantry tractors are introduced as a means of improving the efficiency of controlled traffic farming systems and their benefits and shortcomings are summarised. Particular emphasis is placed on their potential to increase the precision of farming operations.","author":[{"family":"Chamen","given":"William"},{"family":"Mcphee","given":"John"},{"family":"Pedersen","given":"Hans"},{"family":"Carter","given":"Lyle"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2024.152.13","URL":"https://doi.org/10.19103/as.2024.152.13","source":"crossref"},{"id":"doi:10.19103/as.2025.152.13","type":"article-journal","title":"Developments in controlled traffic farming (CTF) in precision agriculture","abstract":"The farm practice of controlled traffic farming as a means of reducing compaction damage to soils is described and its benefits in terms of crop and soil responses are outlined. Particular benefits are in lowering greenhouse gas emissions both pre-farm gate and on-farm. A case study outlines how the benefits have been put into practice on a farm. Gantry tractors are introduced as a means of improving the efficiency of controlled traffic farming systems and their benefits and shortcomings are summarised. Particular emphasis is placed on their potential to increase the precision of farming operations.","author":[{"family":"Chamen","given":"William"},{"family":"Mcphee","given":"John"},{"family":"Pedersen","given":"Hans"},{"family":"Carter","given":"Lyle"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2025.152.13","URL":"https://doi.org/10.19103/as.2025.152.13","source":"crossref"},{"id":"doi:10.1201/9781003613510-3","type":"article-journal","title":"A Review on Smart Sensors for Precision Farming in Agriculture Using IoT","abstract":"Agriculture, science of growing plants, has greatly evolved over the ages as it has expanded human populations beyond that of hunters and gatherers. The use of Artificial Intelligence and the Internet of Things-based solutions can help to revolutionize farming practices, which is known as precision agriculture. Precision agriculture gives the possibility to monitor the moisture temperature, humidity, pH, and air quality of the soil to enable irrigation that is so accurate as to enable the monitoring of the crop and management of the resources using the smart sensors that can work with the management of the crop productivity, efficient use of the resources, and sustainable practices. Use of IoT systems, edge computers, and aerial platforms such as the assistance of drones enables making decisions faster and in real time, faster data processing. In this chapter, the literature on IoT-based breakthroughs in the agricultural industry has been surveyed and revealed how the technology offers solutions to various problems that affect the world as the demand of food, scarcity of water, and pest infestations. Other gorgeous and intriguing methods – applied in the irrigation and soil management – are artificial neural networks or data mining together in order to optimize between irrigation, soil, and water management. An example of a practical application of smart farming that demonstrates its transformational potential is the smart irrigation system. Thus, as the agriculture productivity grows, the agriculture sector is being transformed by IoT and AI, where sustainable practices are put center stage. These will be important technologies in the negotiation of the projected rise in food demand by the year 2050 and lowering the pressure on natural resources. Therefore, the application of these technologies would result in an efficient, greener, and resiliency future of agriculture.","author":[{"family":"Shastry","given":"Rakshitha"},{"family":"Sinha","given":"Richa"},{"family":"Chethana","given":"HT"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003613510-3","URL":"https://doi.org/10.1201/9781003613510-3","source":"crossref"},{"id":"doi:10.3390/agriculture16010089","type":"article-journal","title":"Technological and Socio-Economic Challenges in the Development of Sensors for Precision Agriculture","abstract":"Field-deployable sensors play an important role in precision agriculture and are used to enable key stakeholders (farmers, agronomists, policy makers, etc.) to make informed decisions about resource management and improve crop yields. Sensor developers must consider technological, economic, and human aspects jointly in order to design a successful sensor. The objective of this review is to describe some of the key strands of each aspect and highlight the need to develop a degree of understanding of all of these aspects in order to create technologies that will be easily and readily adopted. Rather than analyzing each area in depth, we limit our discussion to a few major aspects and try to indicate interdependency and showcase their impact on one another. We hope that this approach will instigate thoughts and ideas and stimulate the co-creation of fit-for-purpose sensors.","author":[{"family":"Saiz","given":"Ernesto"},{"family":"Iqbal","given":"Faiz"},{"family":"Grant","given":"Jack"},{"family":"Korir","given":"Lilian"},{"family":"Ullah","given":"Sami"},{"family":"Radu","given":"Aleksandar"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture16010089","URL":"https://doi.org/10.3390/agriculture16010089","source":"crossref"},{"id":"doi:10.1163/9789004725232_131","type":"article-journal","title":"An active laser-camera scanning system for precision fruit localization in robotic harvesting","abstract":"An active laser-camera scanner (ALACS), mainly consisting of a red line laser, an RGB camera, and a linear motion slide, was designed for robust and precision fruit localization. A dynamic-targeting laser-triangulation method, coupled with a laser line extraction algorithm, was developed for precise depth computation of target fruits. Calibration results showed that ALACS had the maximum localization errors of 0.6 mm, 1.2 mm and 4.0 mm in the x, y and z (depth) directions, respectively, and the average depth error of less than 1 mm for targets at distances between 100 cm and 160 cm. When integrated with a vacuum-based robotic apple harvesting system, ALACS achieved a 95% fruit detachment rate in an orchard picking evaluation.","author":[{"family":"Zhang","given":"K"},{"family":"Chu","given":"P"},{"family":"Lammers","given":"K"},{"family":"Li","given":"Z"},{"family":"Lu","given":"R"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_131","URL":"https://doi.org/10.1163/9789004725232_131","source":"crossref"},{"id":"doi:10.1080/23311932.2026.2620180","type":"article-journal","title":"The role of big data in sustainable agriculture: advancing environmental sustainability in precision farming systems","abstract":"Sustainable agriculture requires production systems that balance food security, environmental integrity, and economic viability. This narrative review examines how big data analytics, when integrated with precision agriculture technologies, can contribute to environmentally sustainable farming systems. Literature published between 2005 and 2025 was identified through Google Scholar, Scopus, Web of Science, IEEE Xplore, and ScienceDirect using targeted keywords related to big data analytics, IoT, and sustainable agriculture. The review synthesizes evidence on applications including site-specific nutrient management, precision irrigation, yield prediction, disease surveillance, and climate risk monitoring. Findings indicate that big data analytics can reduce input use (water, fertilizers, and pesticides) by 15%–40% while maintaining or improving yields, thereby supporting climate change mitigation and resource efficiency. However, adoption remains uneven due to high costs, data governance concerns, infrastructure limitations, and exclusion of smallholder farmers. The review highlights pathways for inclusive implementation through low-cost sensing, cooperative data platforms, public extension services, and supportive policy frameworks. By critically evaluating both opportunities and constraints, this study demonstrates that big data analytics can support sustainable agriculture only when technological innovation is aligned with equity-oriented governance and farmer capacity building.","author":[{"family":"Bist","given":"Dipak"},{"family":"Chapagaee","given":"Pawan"},{"family":"Kunwar","given":"Adhiraj"},{"family":"Khatri","given":"Lokendra"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/23311932.2026.2620180","URL":"https://doi.org/10.1080/23311932.2026.2620180","source":"crossref"},{"id":"doi:10.1002/ps.70319","type":"article-journal","title":"Detection of kochia [Bassia scoparia (L.) A.J. Scott] and waterhemp [Amaranthus tuberculatus (Moq.) J.D. Sauer] in sugarbeet field using hyperspectral imaging and deep learning technologies.","abstract":"Kochia [Bassia scoparia (L.) A.J. Scott] and waterhemp [Amaranthus tuberculatus (Moq.) J.D. Sauer] are among the most aggressive and competitive weed species in sugarbeet production. Their similarity to the crop during early growth stages poses a significant challenge for early identification using conventional imaging techniques. This study aimed to develop and evaluate a hyperspectral imaging based deep learning model capable of distinguishing kochia and waterhemp from sugarbeet under field conditions. Hyperspectral images were acquired and preprocessed to extract spectral and spatial information for classification.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/ps.70319","URL":"https://doi.org/10.1002/ps.70319","source":"pubmed"},{"id":"doi:10.9734/jeai/2025/v47i63497","type":"article-journal","title":"Engineering a Sustainable Battery Powered Shielded Sprayer on Vegetable Crops for Precision Agriculture","abstract":"This study tackles the challenges of pesticide drift and low mechanization in Indian smallholder agriculture by developing a battery-powered, shielded inter-row sprayer tailored for vegetable crops. Designed at CAET, AAU, Godhra, the sprayer was tested on chilly and cabbage crops under various nozzle types, forward speeds, and nozzle heights. The system comprises a DC motor-driven unit with lithium-ion batteries, a 40-liter tank, a 12V diaphragm pump, and an adjustable boom supporting shielded, interchangeable nozzles to minimize off-target drift. Laboratory analysis (as per IS standards) and ImageJ software were used to assess droplet size, density, and homogeneity factor (VMD, NMD, HF). Field trials over 54 plots measured performance indicators such as field capacity, efficiency, and economic viability. The sprayer significantly reduced drift, increased uniform deposition, and improved time and cost efficiency compared to traditional knapsack sprayers. The system demonstrated a high B:C ratio (3.13), making it an affordable and sustainable option for small and marginal farmers. Compared to a knapsack sprayer (₹626/ha), the developed unit cuts application costs (nearly by half). It covers 1 ha in 4.40 hours, whereas the knapsack sprayer requires 11.62 hours (2.5 times longer) highlighting superior time efficiency","author":[{"family":"Rs","given":"Godhani"},{"family":"Gupta","given":"P"},{"family":"Salunkhe","given":"RC"},{"family":"Dabhi","given":"KL"},{"family":"Rangpara","given":"D"},{"family":"Shukla","given":"K"},{"family":"Yoganandi","given":"Y"},{"family":"Thakor","given":"Devrajsinh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jeai/2025/v47i63497","URL":"https://doi.org/10.9734/jeai/2025/v47i63497","source":"crossref"},{"id":"doi:10.3390/agriculture16161755","type":"article-journal","title":"Coaxial Drive–Vacuum System for Maize Precision Seeding","abstract":"In air-suction maize precision seed metering, the power transmission and vacuum air supply are typically routed through separate, non-coaxial paths. This conventional layout leaves transmission components exposed to debris clogging, subjects the seed-metering disc to eccentric torque, and causes non-uniform suction pressure distribution, ultimately degrading seeding consistency. To address these issues, this study proposes a coaxial integrated design in which a servo motor offset from the seed-metering axis drives a hollow rotary support, and the drive output shares the same axis with the central air passage. Bench tests showed that motor-end feedback speed entered the final target-speed ±5% band within 8.0–36.6 ms, with maximum overshoot of 0.15–5.76%. Seed-disc pre-filling reduced the mean unseeded distance at start-up from 83.1 to 10.4 cm (87.5%, p &lt; 0.001). Field verification at target spacings of 15 and 20 cm and measured speeds of 3.0–12.0 km/h produced quality-of-feed indices of 91.74–97.50%. The results demonstrate the functional implementation and operational feasibility of the proposed electric-drive system under the tested conditions.","author":[{"family":"Fang","given":"Huimin"},{"family":"Wang","given":"Jingyi"},{"family":"Lu","given":"Jialu"},{"family":"Zhao","given":"Ruofu"},{"family":"Sheng","given":"Tao"},{"family":"Zhang","given":"Qingyi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16161755","URL":"https://doi.org/10.3390/agriculture16161755","source":"crossref"},{"id":"doi:10.3390/ecsa-12-26539","type":"article-journal","title":"Wireless Soil Health Beacons: An Intelligent Sensor-Based System for Real-Time Monitoring in Precision Agriculture","abstract":"Precision agriculture is a modern technology that focuses on the crop by meeting the specific needs of the field. This research presents the Wireless Soil Health Beacons design that can be used in precision agriculture to enhance the production and real-time monitoring of the soil and field parameters. The proposed system integrates bio and physical sensors into an IoT-enabled Wireless Soil Health Beacons (WSHB) to provide detailed and real-time soil health parameters. The beacons are compact and are powered by solar, which is weather-resistant and interconnected via wireless nodes. A set of beacons will be implanted to capture biological and environmental data. The biosensor module detects key soil microbiological parameters such as nitrogen-fixing microbial activity, soil pathogen presence, and general microbial population shifts indicative of soil fertility and disease conditions. The physical sensor module continuously measures soil moisture levels, temperature, and salinity. The data is passed from the nodes to a processing module, which collects and analyses the critical parameters directly related to plant growth, water management, and fertiliser optimisation. A mobile interface assists the farmers and stakeholders with the required information, such as field maps, real-time soil health indicators, and critical alerts related to drought, salinity stress, or pathogen hotspots. The proposed system forms as a multi-dimensional soil profiling tool capable of supporting precision agriculture. Most existing soil monitoring systems rely on environmental parameters, while the proposed system allows the continuous tracking of ecological and microbial dynamics in the area. The mesh network architecture helps the system to be redundant and enhances the outcomes. The proposed system helps with sustainable agriculture and improves the yields with minimal environmental degradation, enabling an adaptive and precise farm management system.","author":[{"family":"Subramanian","given":"Vijayalakshmi"},{"family":"Joseph","given":"Alwin"},{"family":"Paramasivam","given":"Durgadevi"},{"family":"Tamilselvan","given":"Akilan"},{"family":"Thangavel","given":"Mahesh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/ecsa-12-26539","URL":"https://doi.org/10.3390/ecsa-12-26539","source":"crossref"},{"id":"doi:10.31200/makuubd.1570013","type":"article-journal","title":"Advanced Leaf Disease Detection: Integrating YOLOv9 with Transfer Learning for Precision Agriculture","abstract":"Leaf diseases pose a significant challenge to agriculture, threatening crop health and yield. Effective detection and management of these diseases are critical for sustainable farming. This study introduces a novel method for detecting leaf diseases in agricultural images by leveraging the YOLOv9 model and transfer learning. By integrating YOLOv9 with various deep-learning libraries, our approach achieves a classification accuracy of 98%. Building on this success, we developed a mobile application that provides real-time disease detection using the trained model. A key strength of this method lies in the curated dataset, annotated with disease labels and bounding boxes. This dataset encompasses diverse crops and environmental conditions, ensuring the robustness and versatility of the model. Extensive experiments demonstrate that our approach outperforms conventional methods in both accuracy and efficiency. The resulting mobile application offers farmers and agricultural stakeholders a user-friendly tool for proactive disease management. It enables real-time identification of leaf diseases via a live camera feed, facilitating timely interventions and crop protection. By combining high accuracy with real- time detection, this method can significantly enhance crop productivity and contribute to sustainable agricultural practices.","author":[{"family":"Elhalid","given":"Osama"},{"family":"Dolićanin","given":"Edin"},{"family":"Isık","given":"Ali"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31200/makuubd.1570013","URL":"https://doi.org/10.31200/makuubd.1570013","source":"crossref"},{"id":"doi:10.1163/9789004725232_114","type":"article-journal","title":"Factors influencing random forest soil volumetric water content predictions within a turfgrass field","abstract":"Irrigation of turfgrass in semi-arid regions consumes much freshwater and up to 50% of applications are wasted through spatial and temporal mis-applications. More efficient spatial applications are possible with valve-in-head sprinkler heads and soil volumetric water content (VWC) mapping. This study uses random forests and a time series of National Agriculture Imagery Program (NAIP) imagery (1m pixel) to predict VWC in a sports field at several different times. Several grid surveys of VWC are used to evaluate prediction accuracy. Feature importance identifies the most important wavebands and a jack-knife procedure is used to determine the optimal sample size needed to produce accurate VWC maps.","author":[{"family":"Kerry","given":"R"},{"family":"Ingram","given":"B"},{"family":"Sanders","given":"K"},{"family":"Hansen","given":"N"},{"family":"Hopkins","given":"B"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_114","URL":"https://doi.org/10.1163/9789004725232_114","source":"crossref"},{"id":"doi:10.1002/agj2.70377","type":"article-journal","title":"Midwestern farmers' willingness to engage with precision agriculture technologies and on‐farm precision experimentation","abstract":"Abstract Precision agriculture technologies (PATs) have revolutionized the agriculture industry and provide many benefits to farmers. Among these benefits is the ability to conduct experiments in a process known as on‐farm precision experimentation (OFPE). By conducting these experiments and through collaboration with researchers, crop consultants, and extension agents, farmers can learn site‐specific management practices to better address challenges in their operations. However, adoption rates of these technologies have remained below 50% in the United States. Furthermore, very few studies have explored the factors that influence a farmer's decision to conduct experiments, or their willingness to collaborate with external stakeholders such as researchers, crop consultants, and extension agents. Therefore, the objectives of this study are to measure farmers' perceptions of PATs and OFPE, identify farmer characteristics associated with OFPE, and explore their willingness to engage in collaborative OFPE. Respondents perceive that PATs help them make better decisions for their operations (84.6%), and 96.3% of those who conduct on‐farm experiments use PATs to do so. Operators whose farms are 1,000 acres or larger, who operate on rented acreage, and who adopt PATs are more likely to engage in on‐farm experimentation. While most OFPE is conducted without external engagement, nearly half of respondents are interested in collaborative OFPE. These results may help guide researchers, crop consultants, and extension personnel as they look for opportunities to collaborate with farmers. This collaboration can help address questions of mutual interest and work toward solutions to the economic and environmental challenges facing agriculture.","author":[{"family":"Tibbs","given":"Reagen"},{"family":"Heller","given":"Nicholas"},{"family":"Bullock","given":"David"},{"family":"Boerngen","given":"Maria"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/agj2.70377","URL":"https://doi.org/10.1002/agj2.70377","source":"crossref"},{"id":"doi:10.2174/9798898813963126010013","type":"article-journal","title":"Precision Agriculture, Irrigation Management, and Monitoring using Hyperspectral Remote Sensing and AI","abstract":"Farming is changing rapidly, and new technology is making it easier to grow food in a way that is good for both people and the planet. Hyperspectral remote sensing is one of these game-changers—it lets us see details about crops and soil that we could never spot with the naked eye. When you add Artificial Intelligence (AI) into the mix, you get a powerful combination: hyperspectral cameras collect huge amounts of data, and AI helps make sense of it all. This paper looks at how these two technologies work together to help farmers spot problems early, use resources wisely, and grow healthier crops with less waste. The research work will focus on how this system works, why it is better than old-school methods, and what it could mean for the future of sustainable farming.","author":[{"family":"Singh","given":"Jaswinder"},{"family":"Singh","given":"Rupinder"},{"family":"Singh","given":"Amanpreet"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898813963126010013","URL":"https://doi.org/10.2174/9798898813963126010013","source":"crossref"},{"id":"doi:10.13053/cys-29-2-5738","type":"article-journal","title":"Systematic Literature Review of Generative AI and IoT as Key Technologies for Precision Agriculture","abstract":"This study examines the convergence of Generative Artificial Intelligence (AI) and the Internet of Things (IoT) as key drivers of innovation in Precision Agriculture. It posits that these technologies enable real-time monitoring of critical variables such as soil moisture, temperature, and crop health, as well as early detection of pests and diseases. The main objective, through a systematic review of 74 papers, is to identify the applications, benefits, and challenges of Generative AI and IoT. The Kitchenham (2004) methodology was applied along with the PRISMA flow, ensuring transparency and replicability. Five research questions were formulated focusing on crop types, IoT devices, thematic topics, conceptual evolution, keywords, and international collaboration. Searches were conducted across five databases. From an initial pool of 39,223 references and after applying exclusion criteria, 74 papers were selected for analysis. The findings confirm that Generative AI and IoT have reached a level of maturity in intensive crops and high-value sectors, supported by low-cost architectures and advanced data analytics. However, gaps remain, such as the lack of economic assessments of hybrid platforms and the scarcity of public datasets that hinder the replication of certain studies. This study offers practical and strategic guidance to support the implementation of Generative AI and IoT in precision agriculture.","author":[{"family":"Andrade-Mogollon","given":"Teodoro"},{"family":"Gamboa-Cruzado","given":"Javier"},{"family":"Amayo-Gamboa","given":"Flavio"}],"issued":{"date-parts":[[2025]]},"DOI":"10.13053/cys-29-2-5738","URL":"https://doi.org/10.13053/cys-29-2-5738","source":"crossref"},{"id":"doi:10.1163/9789004725232_126","type":"article-journal","title":"Collaboration between aerial and ground robots for weed detection and removal","abstract":"This paper presents an approach towards the collaboration between aerial and ground robots or autonomous unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) for weed detection and removal. A UAV equipped with a high resolution digital camera was used to collect data from an experimental strawberry plot. The collected data was used to develop machine-learning models to detect weeds in the plot using two different machine-learning architectures that support real-time implementation. The developed algorithms also identify the location of weeds. The location data was then shared with a UGV for weed removal. Accuracies of the machine-learning models in detecting weeds are discussed and experimental results for weed detection and removal are shown.","author":[{"family":"Pham","given":"V"},{"family":"Malladi","given":"B"},{"family":"Moreno","given":"F"},{"family":"Gonzalez","given":"C"},{"family":"Bhandari","given":"S"},{"family":"Raheja","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_126","URL":"https://doi.org/10.1163/9789004725232_126","source":"crossref"},{"id":"doi:10.37396/jsc.v8i2.555","type":"article-journal","title":"Mini Drone-Based Precision Agriculture for Indonesian MSMEs: A Low-Cost AI-Assisted Monitoring System","abstract":"This research introduces a cost-effective drone-based agricultural monitoring system targeted at Indonesia’s smallholder farming enterprises (MSMEs). By leveraging mini drones (DJI Mini 2 SE) and lightweight AI models, farmers can segment land, detect vegetation health, and count crops using simple RGB video analysis. The system utilizes a mobile-to-YouTube private livestream pipeline and performs video processing offline using semantic segmentation (U-Net) and object detection (YOLOvX). The prototype system—tested on a 300m² vegetable plot—shows promising results with over 90% detection accuracy and effective land use visualization. The interface, built with Streamlit, provides real-time insights, affordability, and aligns with Smart City goals of accessibility and sustainability.","author":[{"family":"Hermanus","given":"Davy"},{"family":"Supangkat","given":"Suhono"},{"family":"Hidayat","given":"Fadhil"}],"issued":{"date-parts":[[2025]]},"DOI":"10.37396/jsc.v8i2.555","URL":"https://doi.org/10.37396/jsc.v8i2.555","source":"crossref"},{"id":"doi:10.1007/s11119-025-10258-w","type":"article-journal","title":"Bayesian yield mapping and uncertainty analysis in vineyards using remote sensing data and grape harvester tracking","abstract":"Yield mapping in viticulture is crucial for optimizing vineyard management. However, it remains constrained by limited yield monitoring sensors on grape harvesters and traditional remote sensing methods, which provide deterministic predictions without explicit uncertainty quantification. This study develops and evaluates a Bayesian hierarchical approach for vineyard yield mapping. The model integrates multi-sensor remote sensing and mechanical harvester telemetry data to generate high-resolution, uncertainty-aware yield maps at the farm scale. Over two growing seasons (2022–2023) in a Sicilian vineyard. Normalized difference vegetation index data from unmanned aerial vehicles and Sentinel-2 satellites were combined with telemetry from global navigation satellite systems mounted on a mechanical grape harvester. Multiple model configurations were systematically evaluated using the brms package in R, and sensitivity analyses were performed. The best-performing model selected, based on six evaluation metrics (Bayesian R², RMSE, MAE, MAPE, and ELPD), achieved an R² of 0.83 and RMSE of 0.26 kg/vine on training data, with independent validation showing an R² of 0.78 and RMSE of 0.09. The model effectively captured spatial and temporal yield variations. Specifically, it identified a 15% yield decline in 2023 linked to drought and heat stress, while explicitly quantifying prediction uncertainty. This hierarchical Bayesian approach significantly advances vineyard yield mapping, demonstrating robust generalization potential. Integrating additional data from multiple seasons, different vineyards, and grape cultivars could further enhance predictive accuracy, reduce uncertainty in prediction and improve scalability of the framework. Ultimately, this methodology offers valuable insights for precision viticulture, supporting targeted agronomic management and informed operational decisions.","author":[{"family":"Canicattì","given":"Marco"},{"family":"Ferro","given":"Massimo"},{"family":"Vallone","given":"Mariangela"},{"family":"Orlando","given":"Santo"},{"family":"Catania","given":"Pietro"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10258-w","URL":"https://doi.org/10.1007/s11119-025-10258-w","source":"crossref"},{"id":"doi:10.1016/j.aiia.2025.04.003","type":"article-journal","title":"Assessing particle application in multi-pass overlapping scenarios with variable rate centrifugal fertilizer spreaders for precision agriculture","abstract":"Environmental impacts and economic demands are driving the development of variable rate fertilization (VRF) technology for precision agriculture. Despite the advantages of a simple structure, low cost and high efficiency, uneven fertilizer-spreading uniformity is becoming a key factor restricting the application of centrifugal fertilizer spreaders. Accordingly, the particle application characteristics and variation laws for centrifugal VRF spreaders with multi-pass overlapped spreading needs to be urgently explored, in order to improve their distribution uniformity and working accuracy. In this study, the working performance of a self-developed centrifugal VRF spreader, based on real-time growth information of rice and wheat, was investigated and tested through the test methods of using the collection trays prescribed in ISO 5690 and ASAE S341.2. The coefficient of variation (CV) was calculated by weighing the fertilizer mass in standard pans, in order to evaluate the distribution uniformity of spreading patterns. The results showed that the effective application widths were 21.05, 22.58 and 23.67 m for application rates of 225, 300 and 375 kg/ha, respectively. The actual fertilizer application rates of multi-pass overlapped spreading were generally higher than the target rates, as well as the particle distribution CVs within the effective spreading widths were 11.51, 9.25 and 11.28 % for the respective target rates. Field test results for multi-pass overlapped spreading showed that the average difference between the actual and target application was 4.54 %, as well as the average particle distribution CV within the operating width was 11.94 %, which met the operation requirements of particle transverse distribution for centrifugal fertilizer spreaders. The results and findings of this study provide a theoretical reference for technical innovation and development of centrifugal VRF spreaders and are of great practical and social significance for accelerating their application in implementing precision agriculture. • Performance of variable rate centrifugal fertilizer spreaders is investigated. • Race-track and back-and-forth trajectories for multiple passes perform similarly. • Swath spacing between adjacent passes is recommended as application effective width. • Multi-pass overlapped application is more effective than single pass one. • Average difference between actual and target application rates is <5 %.","author":[{"family":"Yinyan","given":"Shi"},{"family":"Yangxu","given":"Zhu"},{"family":"Xiaochan","given":"Wang"},{"family":"Xiaolei","given":"Zhang"},{"family":"Enlai","given":"Zheng"},{"family":"Yongnian","given":"Zhang"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.aiia.2025.04.003","URL":"https://doi.org/10.1016/j.aiia.2025.04.003","source":"crossref"},{"id":"doi:10.1007/s11119-025-10222-8","type":"article-journal","title":"Stability maps using historical NDVI images on durum wheat to understand the causes of spatial variability","abstract":"Durum wheat (Triticum durum Desf.) yield should be maximized to meet the growing global demand for pasta production. Precision agriculture (PA) could play a pivotal role in reaching this goal by correctly defining management zones (MZ) and optimizing the use of energy inputs. The aim of the work was to understand the relationship between MZ generated from observed yield data and those generated using a time series of Sentinel-derived vegetation indices (i.e. NDVI) obtained from satellite images and soil properties. For this purpose, two field trials of 10 ha each, cultivated with durum wheat, were carried out in Southern Italy. The results suggested a better strategy for defining MZs by merging soil characteristics and temporal NDVI stability maps. The on-the-go technology used for soil resistivity mapping also represented an excellent tool for delineating stable and homogeneous areas within the fields and estimating soil properties. In particular, the soil clay content had a determining effect on the identification of homogeneous yield areas. However, the integration of historical NDVI data helped delineate MZs within each field. To validate this hypothesis, we integrated soil and NDVI data into a linear predictive model to predict grain yield at the field level. Our findings showed a good level of accuracy and a significant improvement in yield simulated values by combining soil with crop data (R² = 0.620; RMSE = 0.425). Further studies are needed to explore the potential of NDVI stability maps into a linear predictive model to predict grain yield at the field level.","author":[{"family":"Romano","given":"E"},{"family":"Fania","given":"F"},{"family":"Pecorella","given":"I"},{"family":"Spadanuda","given":"P"},{"family":"Roncetti","given":"M"},{"family":"Zullo","given":"D"},{"family":"Giuntoli","given":"G"},{"family":"Bisaglia","given":"C"},{"family":"Bragaglio","given":"A"},{"family":"Bergonzoli","given":"S"},{"family":"Vita","given":"PD"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10222-8","URL":"https://doi.org/10.1007/s11119-025-10222-8","source":"crossref"},{"id":"doi:10.1007/s11119-025-10219-3","type":"article-journal","title":"Improving harvester yield maps postprocessing leveraging remote sensing data in rice crop","abstract":"Abstract Precision Agriculture relies significantly on yield data obtained from combine harvesters, which constitutes a pivotal tool for optimizing crop productivity. Despite its potential, challenges in data accuracy persist, necessitating the development of novel automated postprocessing protocols for yield data refinement. In this paper, different automatic postprocessing protocols were evaluated using remote sensing data, specifically Sentinel-2 satellite imagery. Various automatic postprocessing protocols were applied to a dataset spanning 946 hectares over a four-year period. Commercial sensors on combine harvesters acquired the yield data. The analysis included global (field-level) adjustments and local adjustments at a finer scale (40 × 40 m² level), employing interval mean ± n·(standard deviation) calculations. Three n values (1, 1.5, and 2.5) were tested, resulting in thirteen distinct postprocessing variations. Finally, a mean filter was also applied. The results demonstrated that the yield correlation with satellite data increased with the reduction of yield variability at the pixel level (10 m). The best results were obtained using n = 1 with a 3 × 3 mean filter, where Sentinel-2 pixels remained unaffected, and the average Root Mean Square Error (RMSE) during validation was 0.572 t·ha⁻¹. In addition, the geostatistical parameters (coefficient of variation, semivariance, and range within a 10 m pixel) reached optimal values. Finally, the postprocessing uncertainty was determined to be 0.200 t·ha −1 . These results validate the efficacy of a novel postprocessing protocol for refining yield data in rice crops. The integration of pixel-level data from combine harvesters with Sentinel-2 imagery emerges as a promising approach for optimizing crop management, offering valuable insights for the advancement of Precision Agriculture.","author":[{"family":"Fita","given":"D"},{"family":"Rubio","given":"C"},{"family":"Franch","given":"B"},{"family":"Castiñeira-Ibáñez","given":"S"},{"family":"Tarrazó-Serrano","given":"D"},{"family":"Bautista","given":"AS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10219-3","URL":"https://doi.org/10.1007/s11119-025-10219-3","source":"crossref"},{"id":"doi:10.1007/s11119-026-10425-7","type":"article-journal","title":"Dye-based field evaluation of an integrated high-precision smart sprayer for weed control in vegetables","abstract":"Abstract Purpose Weed management in vegetable production systems is increasingly constrained by labor shortages, rising input costs, and the need to reduce herbicide use while avoiding crop injury. Precision, site-specific spraying offers a promising alternative to broadcast application; however, its effectiveness under real field conditions is often limited by unreliable weed detection, sprayer resolution, and timing inaccuracies. This study evaluates an integrated high-precision smart spraying system combining real-time weed detection, plant tracking, and micro-jet spray actuation for selective weed control in vegetable fields. Methods The system employed a YOLOv10-small model trained on a five-season crop-weed dataset (14,186 images and 103,266 annotated plant instances), coupled with a ByteTrack algorithm for spray timing. A micro-jet sprayer equipped with 12 independently controlled nozzles spaced at 1-cm intervals was mounted on a ground-based, robotic platform to target early-stage weeds, and an optimized multithreaded software architecture was implemented for system integration and real-time performance. Following an initial dataset-based crop-weed detection evaluation, the system was tested in a lettuce field plot, a 15-m crop row containing 74 lettuce plants and 174 weeds, to further evaluate plant detection and spraying performance. Blue dye-based fluid was used in the spraying testing of the system at a forward speed of 0.91 km/h. Results Video-based evaluation yielded a detection performance of 80.0% mAP@50. Field spraying tests achieved a weed hit rate of 84.5% and a crop hit rate of 17.6%, representing a substantial improvement over previous system configurations. Conclusion This study demonstrates the benefits of integrating artificial intelligence (AI)-driven detection and tracking with a high-precision sprayer, advancing the practical deployment of intelligent sprayer systems for precision weed management. Effective site-specific weed control still requires further reducing crop contact while improving weeding accuracy, which could be possible by developing more robust weed detection models and incorporating a buffer zone around crops.","author":[{"family":"Deng","given":"Boyang"},{"family":"Lu","given":"Yuzhen"},{"family":"Siemens","given":"Mark"},{"family":"Brainard","given":"Daniel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10425-7","URL":"https://doi.org/10.1007/s11119-026-10425-7","source":"crossref"},{"id":"doi:10.1007/s11119-026-10345-6","type":"article-journal","title":"Conventional management vs. precision viticulture: A comparison of different levels of mechanization and their impact on vineyard profitability","abstract":"Abstract Purpose Viticulture is one of the most input-intensive agricultural sectors, in which the adoption of precision technologies could contribute significantly to reduce environmental impacts and operating costs. Previous studies have primarily focused on technical aspects, often examining individual farm operations or specific technologies using hypothetical data, rather than assessing economic impacts. To fill this research gap, this study evaluates the profitability of adopting varying levels of precision technologies in an Italian vineyard, focusing on two key farming operations - fertilisation and harvesting - using empirical data. Method This study adopted a partial budgeting approach comparing three differently managed vineyards: (a) conventional management (conventional spreader and manual harvest); (b) low-innovative management (VRT spreader and self-propelled harvester); (c) high-innovative management (VRT spreader and selective self-propelled harvester). Results The findings show that high-innovative management achieved the highest profitability value of 10,732.82 € ha − 1 year − 1 , which is twice that of conventional management. This is due to both direct cost savings (-66.1%) and increased revenues (+ 33.6%). However, precision technologies are only economically viable for farms larger than 25.81 ha (high-innovative management) and 16.42 ha (low-innovative management). Conclusion In this context, as the results of this study demonstrate, the provision of public subsidies aimed at reducing the high investment costs could represent a valid instrument to promote the adoption of precision agriculture technologies among winegrowers, thereby reducing the minimum farm size for their adoption. This study enriches the economic literature on precision agriculture technologies, also providing useful insights for winegrowers and policymakers.","author":[{"family":"Testa","given":"Riccardo"},{"family":"Brunori","given":"Gianluca"},{"family":"Galati","given":"Antonino"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10345-6","URL":"https://doi.org/10.1007/s11119-026-10345-6","source":"crossref"},{"id":"doi:10.1007/s11119-025-10291-9","type":"article-journal","title":"Harnessing Sentinel-2 imagery and AgERA5 data using Google Earth Engine for developing chickpea mechanistic growth modeling and pre-harvest empirical yield forecast","abstract":"Abstract Precision Agriculture (PA) adoption by farmers is limited by costs and technological complexity. Google Earth Engine (GEE) is used in large-scale crop research but remains underutilized for PA applications. Crop yield variability is widely studied, yet research advancements increasingly widen the gap to practical use. To address this, a GEE platform was established, harnessing Sentinel-2 and AgERA5 for chickpea mechanistic daily simulation of the Total Above-Ground Dry Biomass (TAGDB) and Grain Dry Biomass (GDB). In addition, Sentinel-2 spectral reflectance was used to train an empirical Random Forest (RF) model on GEE to forecast Grain Yield (GY) two months prior to harvest. Both mechanistic and empirical models were evaluated at field scale using GY data from 68 fields (2021–2024), including sub-field evaluation from eight fields. The mechanistic and empirical RF models achieved sub-field GY performance with a coefficient of determination (R²), root mean square error (RMSE), and relative RMSE of 0.49, 1.49 t ha⁻¹, and 19.89%, and 0.24, 1.15 t ha⁻¹, and 15.35%, respectively. At the field scale, the mechanistic model resulted in 0.43, 0.9 t ha⁻¹, and 19.35%, while the RF model achieved 0.37, 0.83 t ha⁻¹, and 17.85%, respectively. The models performed similarly to studies in other crops but with a key advantage - they can be fully executed within GEE. A companion app was built to support both the mechanistic and empirical models within GEE. Chickpea farmers can use the mechanistic model to examine the spatial progression of TAGDB and GDB, both retrospectively and in a near real time manner. The RF forecast model can then be used to anticipate GY variability prior to harvest. The streamlined design of the mechanistic model, together with the empirical model implemented in GEE and the open-source scripts available on GitHub, supports efficient adaptation to additional crops.","author":[{"family":"Perach","given":"Omer"},{"family":"Sadeh","given":"Roy"},{"family":"Avneri","given":"Asaf"},{"family":"Solomon","given":"Neta"},{"family":"Bonfil","given":"David"},{"family":"Ram","given":"Or"},{"family":"Greenblatt","given":"Harel"},{"family":"Lati","given":"Ran"},{"family":"Herrmann","given":"Ittai"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10291-9","URL":"https://doi.org/10.1007/s11119-025-10291-9","source":"crossref"},{"id":"doi:10.32854/jvfq2k47","type":"article-journal","title":"Potential of Goniometry and Goniophotometry for Precision Agriculture Applications","abstract":"Objective: To review the application of goniometry and goniophotometry as innovative tools for advancing precision agriculture. The primary objective is to synthesize how these techniques contribute to optimizing light interception, enhancing crop yield, and improving land-use efficiency by providing precise data on plant architecture and light dynamics within cultivation systems. Design/methodology/approach: The research employs a systematic review methodology, analyzing existing scientific literature and case studies where goniometry and goniophotometry have been applied in agricultural contexts. Goniometry is used for measuring the angular dispositions of plant elements like leaves and stems, while goniophotometry characterizes light distribution and incidence angles. The approach focuses on integrating data from both techniques to inform adjustments in crop canopy architecture and artificial lighting systems. Results: The review demonstrates that the integration of goniometric and goniophotometric data enables the determination of optimal light incidence angles. This facilitates strategic adjustments to planting layouts and canopy management, leading to significant enhancements in photosynthetic efficiency. Consequently, studies report improvements in overall crop yield and a more efficient use of available land and light resources in diverse cultivation environments, from greenhouses to open fields. Limitations of the study/implications: The primary limitations discussed involve the technical complexity and cost associated with the specialized equipment required for these measurements. Furthermore, the practical implementation of findings can be constrained by the need for specialized knowledge to interpret data and integrate it into existing farm management systems, potentially limiting accessibility for widespread adoption. Findings/Conclusions: Goniometry and goniophotometry are powerful, though underutilized, tools that provide a scientific basis for optimizing agricultural systems. Their application offers significant advantages for enhancing photosynthetic performance and spatial planting efficiency. While challenges related to cost and complexity exist, the potential of these techniques to contribute to more sustainable and productive precision agriculture is substantial, warranting further research and development of user-friendly applications.","author":[{"family":"Reyes-Fernández","given":"Miriam"},{"family":"Posada-Gómez","given":"Rubén"},{"family":"Martínez-Sibaja","given":"Albino"},{"family":"Flores-Estévez","given":"Mario"},{"family":"Bello-Ramírez","given":"Angélica"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32854/jvfq2k47","URL":"https://doi.org/10.32854/jvfq2k47","source":"crossref"},{"id":"doi:10.1163/9789004725232_148","type":"article-journal","title":"Comparing a camera-AI-controlled inter- and intrarow weeding system with a camera-guided inter-row hoe","abstract":"A camera-AI-controlled inter and intrarow weeder (AI-weeder) and a camera-guided inter-row hoe (guided hoe) were compared on two field experiments, during the growing seasons 2022 and 2023. Both systems demonstrated acceptable weed control at the inter-row area (55-85%). The guided hoe consistently outperformed the AI-weeder in the intra-row zone, achieving > 75% control efficacy, resulting comparable to the efficacy of the herbicide reference. The AI-weeder achieved nearly 90% intra-row control with 25% crop damage, on average. The guided hoe ranged between 15 and 90% intra-row weeding efficacy, with maximum 6% crop damage. After two seasons, the guided hoe offers a viable step towards herbicide reduction in sugarbeet farming. The AI-weeder requires further refinement to unlock its full potential.","author":[{"family":"Fuchs","given":"M"},{"family":"Rueda-Ayala","given":"V"},{"family":"Wirth","given":"J"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_148","URL":"https://doi.org/10.1163/9789004725232_148","source":"crossref"},{"id":"doi:10.14719/pst.9306","type":"article-journal","title":"Emerging trends in soil and crop sensing for enhanced data-driven decision making in precision agriculture","abstract":"The integration of advanced soil and crop sensing technologies with data-driven strategies is revolutionising precision agriculture, addressing urgent global challenges such as increasing food demand and sustainability. Recent advancements in both proximal and remote sensing methods, including electromagnetic, optical, thermal and LiDAR systems, are enhancing the ability to assess soil status, moisture levels, nutrient availability and crop development. Moreover, the innovative application of artificial intelligence (AI), machine learning (ML) and the Internet of Things (IoT) is transforming raw sensor data into actionable insights, enabling more efficient irrigation, optimised nutrient management and improved yield prediction. These technologies are improving operational efficiency considerably by limiting the wastage of resources, lowering labour needs and allowing for timely interventions. Notably, multispectral and hyperspectral imaging are being applied for crop health monitoring, AI-driven pest detection and biomass estimation using 3D modelling advancing sustainable, data-driven precision agriculture. However, despite these promising developments, challenges remain, including difficulties in calibration, system interoperability and the high costs associated with implementation. Therefore, this review addresses the need for standardized methodologies, user-friendly tools for farmers and scalable AI solutions to enhance adoption. Ultimately, by aligning cutting-edge technology with practical agricultural needs, these innovations pave the way for more climate-resilient, productive and sustainable smart farming practices.","author":[{"family":"Elavarasan","given":"Vadivel"},{"family":"Kannan","given":"Pandian"},{"family":"Muthumanickam","given":"Dhanaraju"},{"family":"Praneetha","given":"Subramanyam"},{"family":"Prabukumar","given":"Gnanasekaran"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14719/pst.9306","URL":"https://doi.org/10.14719/pst.9306","source":"crossref"},{"id":"doi:10.5513/jcea01/26.2.4327","type":"article-journal","title":"Power requirements for corn silage harvesters and application of precision agricultural techniques: a review","abstract":"The energy requirements of corn silage harvesters and the application of precision agricultural techniques are essential for efficient and productive agricultural practices. The article aims to review previous studies on the energy requirements needed for different corn silage harvesting machines, and on the other hand, to present methods for measuring corn silage productivity directly in the field and monitoring it based on microcontrollers and artificial intelligence techniques. The process of making corn silage is done by cutting green fodder plants into small pieces, so special harvesters are used for this, called corn silage harvesters. The purpose of harvesting corn silage is to efficiently collect and store as many digestible nutrients as possible per unit of land area. The energy required to harvest corn silage is affected by many factors, including crop moisture, cutting lengths, particle size distribution, etc. This requires understanding the energy requirements of the harvesters used in the process. Using micro-sensors, the feed rate into corn silage harvesters is measured based on load cell data. This method helps in understanding the energy consumption and efficiency of the harvester during the feeding process, leading to more efficient and productive operations. On the other hand, artificial intelligence techniques are used to measure core size and cutting length to control machining parameters. We conclude from this review that precision agriculture techniques help farmers understand the efficiency of corn silage harvesters and know silage yield and quality, which helps them make informed decisions regarding energy use and thus obtain high productivity.","author":[{"family":"Al-Sammarraie","given":"Mustafa"},{"family":"Özbek","given":"Osman"},{"family":"Kirilmaz","given":"Hasan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5513/jcea01/26.2.4327","URL":"https://doi.org/10.5513/jcea01/26.2.4327","source":"crossref"},{"id":"doi:10.1163/9789004725232_178","type":"article-journal","title":"Wheat yield forecasting using deep learning: A comparison between unstructured and structured data","abstract":"Deep learning (DL) models can utilise unstructured (pixel-based) data rather than exclusively depending on structured (organised in rows and columns) data, which may enhance the model’s capacity to capture spatial dependencies and non-linear patterns. Two DL models (a fully connected layer model and TabNet) were employed for within-field yield forecasting using structured data, while a 3D-convolutional neural network (3D-CNN) leveraged unstructured data. An extreme gradient boosting (XGBoost) model, a more traditional decision-tree-based ML model, was also utilised to benchmark the DL models. A leave-one-season-out cross-validation (LOSOCV) approach was implemented, considering each field individually where all but one season was used for training, with the final season reserved for forecasting. The results indicated that the 3D-CNN, using limited yet representative unstructured data, surpassed all other models evaluated in this study. By capturing local spatio-temporal patterns, the 3D-CNN achieved the highest Lin’s concordance correlation coefficient (CCC) in three out of four fields. Future work should aim to integrate ancillary data (e.g., management practices) to better capture the underlying complexity at finer scales.","author":[{"family":"Al-Shammari","given":"D"},{"family":"Filippi","given":"P"},{"family":"Poole","given":"S"},{"family":"Han","given":"S"},{"family":"Bishop","given":"TFA"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_178","URL":"https://doi.org/10.1163/9789004725232_178","source":"crossref"},{"id":"doi:10.51583/ijltemas.2025.140500008","type":"article-journal","title":"Cropprecisionguard App: Innovating Sustainability Through Precision Agriculture","abstract":"Abstract: Traditional agriculture practices often rely on generalized pesticide and fertilizer application recommendations, leading to inefficient resource use, increased costs, and environmental degradation. To address these challenges, we app an innovative solution that integrates precision agriculture techniques with ML to optimize farming practices. This work collects and processes data from multiple sources, including Soli Health Cards (SHC), weather patterns, and crop diagnostics such as the Leaf Colour Chart (LCC). By analysing these datasets using advanced algorithms, the system generates precise, actionable recommendations for pesticide and fertilizer application, ensuring sustainable and cost-effective farming. This app also adapts to real-time conditions. For instance, if a farmer's SHC indicates low nitrogen and phosphorus levels, an initial fertilizer recommendation is provided. During the growing season, the farmers can use LCC to monitor nitrogen levels and adjust applications accordingly. If weather forecasts predict heavy rainfall, the system advises delaying fertilizer application to prevent leaching., data-driven insights help farmers maximize crop yield while preserving soil health and minimizing environmental impact. Thus, our proposed Crop Precision Guard App empowers farmers with real-time, adaptive, and science-backed design-making tools, revolutionizing modern agriculture for greater sustainability and productivity","author":[{"family":"Rani","given":"Mrs"},{"family":"Mswetha"},{"family":"Selvanayaki","given":"M"},{"family":"Svivega"}],"issued":{"date-parts":[[2025]]},"DOI":"10.51583/ijltemas.2025.140500008","URL":"https://doi.org/10.51583/ijltemas.2025.140500008","source":"crossref"},{"id":"doi:10.1163/9789004725232_163","type":"article-journal","title":"On-farm experiment to evaluate the yield and quality of smart-irrigated processing tomato","abstract":"Processing tomato (Solanum lycopersicum L.) yield is threatened by soil water availability. This study used an on-farm experiment in Northern Italy over two years (2023–2024) to test the potential irrigation water rationalization of digital tools (soil mapping, soil probe, weather station, decision support system (DSS), satellite imagery) and regulated deficit irrigation (RDI) to rationalise water use for processing tomato production. Four irrigation strategies were compared in a 4-ha field divided into zones based on soil proximal sensing: business-as-usual (T1), data-driven (T2), and RDI induced at initial (T4) and late (T3) fruit ripening. DSS promoted sustainable irrigation water use, with T2 and T3 leading to 17% water savings without significant yield loss. T4 lowered the product marketability. Despite differences in soil characteristics within the field, no interaction effects on yield were found.","author":[{"family":"Burato","given":"A"},{"family":"Cammarano","given":"D"},{"family":"Pentangelo","given":"A"},{"family":"Ronga","given":"D"},{"family":"Parisi","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_163","URL":"https://doi.org/10.1163/9789004725232_163","source":"crossref"},{"id":"doi:10.1109/jrfid.2025.3574759","type":"article-journal","title":"Power Efficient and Long Range Precision Agriculture Monitoring System","abstract":"Precision agriculture, also referred to as precision farming or smart farming, uses technology to improve the efficiency, sustainability and productivity of agricultural practices. Traditional precision agriculture systems often suffer from limited communication range and high power consumption, which restrict their scalability and long term deployment in large scale farms. Furthermore, existing literature lacks integrated solutions that address both range extension and power minimization in precision agriculture monitoring. To bridge this gap, multiple power efficient soil moisture monitoring nodes are deployed in the farm which transmit data using Bluetooth Low Energy (BLE) technology. Also, this paper investigates the power consumption of the entire precision agriculture monitoring system, including both the sensor nodes and the gateway, which has not been addressed in the previous research works. Soil moisture node has a battery lifetime of 114.18 hrs with 620 mAh / 3V battery. The soil moisture data is received by the gateway (receiver) which then sends data to the cloud. Also, Low Noise Amplifier (LNA) is used at the receiver which reduces the packet loss and increases the range of soil moisture monitoring nodes. Additionally, light intensity (VCNL4040), anemometer, temperature and humidity (SHT40) sensors are interfaced with the gateway which sends data to the cloud directly using Global System for Mobile Communication (GSM) technology. Therefore, this paper proposes novel and power-efficient agricultural monitoring device that also acts as a gateway has a battery life of 106.74 hrs with 15600 mAh / 4.2 V battery. Additionally, the mean absolute errors calculated for the soil moisture sensor (ZSSC3123), VCNL4040, SHT40 and anemometer using reference sensors are 0.1, 1.9, 1.33 and 1.42 respectively.","author":[{"family":"Raina","given":"Radhika"},{"family":"Singh","given":"Kamal"},{"family":"Kumar","given":"Suman"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/jrfid.2025.3574759","URL":"https://doi.org/10.1109/jrfid.2025.3574759","source":"crossref"},{"id":"doi:10.3390/informatics12020046","type":"article-journal","title":"Artificial Neural Networks for Image Processing in Precision Agriculture: A Systematic Literature Review on Mango, Apple, Lemon, and Coffee Crops","abstract":"Precision agriculture is an approach that uses information technologies to improve and optimize agricultural production. It is based on the collection and analysis of agricultural data to support decision making in agricultural processes. In recent years, Artificial Neural Networks (ANNs) have demonstrated significant benefits in addressing precision agriculture needs, such as pest detection, disease classification, crop state assessment, and soil quality evaluation. This article aims to perform a systematic literature review on how ANNs with an emphasis on image processing can assess if fruits such as mango, apple, lemon, and coffee are ready for harvest. These specific crops were selected due to their diversity in color and size, providing a representative sample for analyzing the most commonly employed ANN methods in agriculture, especially for fruit ripening, damage, pest detection, and harvest prediction. This review identifies Convolutional Neural Networks (CNNs), including commonly employed architectures such as VGG16 and ResNet50, as highly effective, achieving accuracies ranging between 83% and 99%. Additionally, it discusses the integration of hardware and software, image preprocessing methods, and evaluation metrics commonly employed. The results reveal the notable underuse of vegetation indices and infrared imaging techniques for detailed fruit quality assessment, indicating valuable opportunities for future research.","author":[{"family":"Unigarro","given":"Christian"},{"family":"Hernandez","given":"Jorge"},{"family":"Florez","given":"Hector"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/informatics12020046","URL":"https://doi.org/10.3390/informatics12020046","source":"crossref"},{"id":"doi:10.1163/9789004725232_129","type":"article-journal","title":"Evaluation of a gripper for a dragon fruit harvesting robot","abstract":"Dragon fruit, or pitahaya, is a tropical fruit of growing interest in the European market. This study evaluates two new robot grippers for harvesting pitahayas with a robot with two cutting devices: a vibration blade and pneumatic scissors. Four pneumatically actuated fingers were built to collect the pitahayas. Experiments revealed three main challenges for detaching and collecting dragon fruits: the high weight of each piece, the risk of physical damage at grasping, and the difficult access to the peduncle targeted by the cutter tool. Despite these challenges, over 75% of ripened fruits were successfully detached and collected, with less than 12% of ‘Purple’ fruits sustaining damage. In conclusion, both designs could be a possible solution for a robot harvesting delicate fruits.","author":[{"family":"González-Planells","given":"P"},{"family":"Blanes","given":"C"},{"family":"Beltrán","given":"P"},{"family":"Asenjo","given":"C"},{"family":"Ortiz","given":"C"},{"family":"Rovira-Más","given":"F"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_129","URL":"https://doi.org/10.1163/9789004725232_129","source":"crossref"},{"id":"doi:10.2174/9798898813963126010016","type":"article-journal","title":"Remote Sensing for Precision Agriculture: Optimizing Fertilizer Use through Nutrient Mapping","abstract":"Efficient use of fertilizers is of utmost importance in sustainable agriculture, as it leads to higher crop yields and limits environmental pollution. Fertilizer application in the traditional way usually overapplies or underspends, causing nutrient imbalances, soil degradation, and environmental pollution. A new application of remote sensing technology in precision agriculture is that of accurate and timely measurement of the levels of soil nutrient availability and crop health. Remote sensing combines satellite imagery, drone-based sensors, and spectral analysis to obtain the most accurate mapping, enabling site-specific fertilizer application. By focusing on this data-driven approach, not only is fertilizer use optimized, but crop productivity is increased, costs are reduced, and environmental risks are mitigated. This chapter examines under what conditions remote sensing is used in nutrient mapping, how it is used, and the comparative merits. It also touches on the integration of remote sensing with artificial intelligence, machine learning, and IoT-enabled smart agriculture for better decision-making. Finally, the chapter discusses the challenges of using remote sensing for fertilizer optimization, as well as current trends in digital agriculture, including government initiatives, policies, and frameworks that support e-governance in agricultural practices.","author":[{"family":"Singh","given":"Jaspreet"},{"family":"Singh","given":"Rupinder"},{"family":"Singh","given":"Amanpreet"},{"family":"Singh","given":"Jaswinder"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898813963126010016","URL":"https://doi.org/10.2174/9798898813963126010016","source":"crossref"},{"id":"doi:10.1201/9781003520733-18","type":"article-journal","title":"Climate-smart agriculture","abstract":"The integration of climate-smart agriculture (CSA) with precision agriculture (PA) technology provides an opportunity to increase agricultural productivity, resource-use efficiency, and climate adaptation. This chapter examines the impact of various PA technologies, including Internet of Things (IoT), smart irrigation, Global Positioning System (GPS), remote sensing, and drones, on crop yield, water-use efficiency, and fertilizer-use efficiency relative to typical farming systems. We collected data from a combination of field observations, surveys, and PA technology data and then employed statistical methods to evaluate the efficiency of these precision-farming systems. The results of the study suggest that applying PA can increase crop yield (up to 3,400 kg/ha) and also improve the efficiency of the use of water and other inputs compared to conventional farming practices. However, obstacles to the widespread utilization of these technologies are the substantial initial cost, a deficiency in technical skills, and unequal availability for smallholder farmers. The study suggested developing low-cost alternatives, implementing policy measures, and building alliances to mitigate identified barriers. Future research should focus on accessibility in precision farming for smallholder farmers and study the socioeconomic implications.","author":[{"family":"Katkar","given":"Tejasvini"},{"family":"Pansare","given":"Bhavana"},{"family":"Bathrinath","given":"S"},{"family":"Selvakanmani","given":"S"},{"family":"Deshmukh","given":"Komal"},{"family":"Joshi","given":"Shripad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003520733-18","URL":"https://doi.org/10.1201/9781003520733-18","source":"crossref"},{"id":"doi:10.1163/9789004725232_121","type":"article-journal","title":"Integrating multi-source remote sensing data and machine learning for large-scale sugarcane yield prediction","abstract":"Accurate yield prediction is fundamental for agricultural management, yet existing models often struggle with scalability across regions. This study demonstrates how combining multiple data sources with machine learning can significantly improve sugarcane yield predictions. Using 97 962 field-seasons across multiple countries, an XGBoost-based model was developed, achieving a mean absolute error of 9.94 t/ha (MAPE 16.45%) and R2 of 0.80. The model identified maximum normalized difference red edge values, humidity conditions, and ratoon number as key yield-determining factors. When tested on independent datasets below 2,000 samples, this approach showed consistent improvement over single-user models, reducing prediction error by 1.29 t/ha.","author":[{"family":"Ferraz","given":"C"},{"family":"Serra-Burriel","given":"F"},{"family":"Cabrera","given":"M"},{"family":"Fortes","given":"R"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_121","URL":"https://doi.org/10.1163/9789004725232_121","source":"crossref"},{"id":"doi:10.11591/eei.v14i2.8481","type":"article-journal","title":"Wireless sensor network using nRF24L01+ for precision agriculture","abstract":"Precision agriculture is a strategy for varying inputs and cultivation methods to suit varying soil conditions and agricultural crops. In order to optimize precision agriculture, wireless sensor network (WSN) is suitable to be integrated. In this research, network devices that communicate using nRF24L01+ based WSN was proposed. As a prototype, four sensor nodes were employed to measure the parameters of air temperature and humidity, soil moisture, and power supply voltage. While, a sink node serves to store measurement data locally. The data are sent to the sink node with a mesh network topology and saved in a comma-separated values (CSV) file and local database. Experimental results show that each sensor node can measure all parameters and successfully send data to the sink node every 1 minute without losing the data. The mesh topology can route data transfer automatically. Round trip time (RTT) of each sensor node depends on the distance from each node. Average power consumption of all sensor nodes in send mode is between 84 mW and 90 mW. Meanwhile, in sleep mode, the sensor nodes 1 and 2 consumed around 21-22 mW and the sensor nodes 3 and 4 consumed around 30 mW which are lower than the send mode.","author":[{"family":"Abidin","given":"Zainul"},{"family":"Falah","given":"Raisul"},{"family":"Setyawan","given":"Raden"},{"family":"Wardana","given":"Fitri"}],"issued":{"date-parts":[[2025]]},"DOI":"10.11591/eei.v14i2.8481","URL":"https://doi.org/10.11591/eei.v14i2.8481","source":"crossref"},{"id":"doi:10.1163/9789004725232_069","type":"article-journal","title":"N balance and satellite-based monitoring of selected winter wheat fields in a nitrate vulnerable zone in Switzerland","abstract":"The study was carried out in a nitrate vulnerable zone in central Switzerland. The focus was set on fertilizer application methods and the use of satellite-based remote sensing to monitor crop growth and nitrogen (N) balance in winter wheat over three years. Sentinel-2 satellite imagery was collected for 27 selected winter wheat site-years. Soil mineral N data, along with crop yield and N uptake measurements, were collected to calculate field-specific N surplus. Preliminary results showed a consistent relationship between satellite-based information and crop growth across the monitored site-years, which reflects the variations in N application rates and N uptake by the crop.","author":[{"family":"Argento","given":"F"},{"family":"Ledain","given":"S"},{"family":"Liebisch","given":"F"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_069","URL":"https://doi.org/10.1163/9789004725232_069","source":"crossref"},{"id":"doi:10.1163/9789004725232_051","type":"article-journal","title":"Crude protein as indicator of pasture productivity and quality: Validation of two proximal sensors","abstract":"This study evaluated two complementary proximal sensors (Rising Plate Meter, RPM and active optical sensor, AOS) to obtain a global indicator of pasture quality and productivity, the crude protein, CP (expressed in kg/ha). The experimental work was carried out on a dryland biodiverse and involved sensor measurements, followed by the collection of a total of 144 pasture samples. Sensor measurements (compressed height, HRPM and NDVI) and the results of reference laboratory analysis were used to develop prediction models. The best models between CP and HRPM×NDVI were obtained in the initial and intermediate phases of the cycle (autumn; R2=0.86; and winter; R2=0.74).","author":[{"family":"Serrano","given":"J"},{"family":"Franco","given":"J"},{"family":"Shahidian","given":"S"},{"family":"Serrano","given":"A"},{"family":"Moral","given":"F"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_051","URL":"https://doi.org/10.1163/9789004725232_051","source":"crossref"},{"id":"doi:10.1163/9789004725232_050","type":"article-journal","title":"Estimation of pasture dry matter: comparative study between Rising Plate Meter and Grassmaster probe","abstract":"This study evaluated two expedient electronic sensors: a rising plate meter (RPM), and a “Grassmaster II” capacitance probe (GMII) to estimate pasture dry matter (DM, kg/ha). The sampling process consisted of sensor measurements, followed by pasture collection and laboratory reference analysis. A total of 288 pasture samples were collected throughout the 2023/2024 pasture growing season. The best DM estimation model was obtained based on the measurements carried out in February in the case of GMII probe (R2=0.61) and December 2023 and February 2024 in the case of RPM (R2=0.76). The results open perspectives for other work which would allow the testing, calibration, and validation of these electronic sensors in a wider range of pasture production conditions, to improve their accuracy as decision-making support tools in pasture management.","author":[{"family":"Serrano","given":"J"},{"family":"Franco","given":"J"},{"family":"Shahidian","given":"S"},{"family":"Serrano","given":"A"},{"family":"Moral","given":"F"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_050","URL":"https://doi.org/10.1163/9789004725232_050","source":"crossref"},{"id":"doi:10.47760/ijcsmc.2025.v14i07.008","type":"article-journal","title":"Machine Learning-Driven Soil Health Analysis for Precision Agriculture: Sensor Based Fertilizer Recommendation","abstract":"Optimal application of fertilizer is key in maximizing crop yields with minimal damage to the soil health, yet conventional soil health analysis remain labour intensive, time consuming and inaccessible to many farmers. This study proposes a machine learning-based fertilizer recommendation system utilizing soil nutrient status to improve soil health analysis. A hybrid machine-learning model synthesizing Extreme Gradient Boosting and Random Forest was trained on a dataset containing Agronomical fertilizer recommendations based on Nitrogen, Phosphorous, Potassium, Soil type and crop type. The study evaluated the performance of an RS485-based digital NPK soil sensor in a sub-study by correlating sensor readings with laboratory test results. In 10 samples per soil type, sensor readings were found to be within ±10% of laboratory values, proving their reliability in real-time field measurements. The findings identify the potential for combining ensemble machine learning algorithms with low-cost sensors to offer scalable, real-time, and accurate fertilizer recommendations for smallholder and commercial farmers. The integrated approach supports data-driven agricultural decision-making and opens the way for smart, sustainable nutrient management.","author":[{"family":"Chinembiri","given":"Emmanuel"},{"family":"Chikoore","given":"Rachel"},{"family":"Mupini","given":"Brian"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47760/ijcsmc.2025.v14i07.008","URL":"https://doi.org/10.47760/ijcsmc.2025.v14i07.008","source":"crossref"},{"id":"doi:10.1163/9789004725232_063","type":"article-journal","title":"Enhancing potato yield estimation using vegetative indices, SAR imagery, and terrain data","abstract":"Having an accurate potato yield estimation is of the upmost importance to help improve the agronomic management of plots. The aim of this study was to analyse the relationship between synthetic aperture radar (SAR) images, vegetation indices (VI) derived from the Copernicus network, a high-resolution digital elevation model (DEM) and orthophotos produced with a camera mounted in a plane with the yield of a potato plot. Multiple regression technique, was used to estimate yield, resulting in an equation with an error of 17% and of R2 of 0.59. It is possible to obtain fairly accurate estimates of potato yields with freely available satellite and other information.","author":[{"family":"Pastor","given":"I"},{"family":"Aizpurua","given":"A"},{"family":"Carrasco","given":"A"},{"family":"Legorburu","given":"J"},{"family":"Castro","given":"J"},{"family":"Uribeetxebarria","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_063","URL":"https://doi.org/10.1163/9789004725232_063","source":"crossref"},{"id":"doi:10.1163/9789004725232_115","type":"article-journal","title":"Mitigating soil erosion on agricultural cropland using elevation data in a track planning algorithm","abstract":"This work investigates integrating elevation data into a track-planning algorithm to calculate AB-lines as driving tracks with minimal slope on the field. The paper utilizes a modified version of the CONREC contouring algorithm to facilitate the calculation of level-lines (lines of constant altitude) within the field. A deviation function assesses deviations in driving directions relative to the level-lines of a field. This deviation can determine the average slope of the driving direction. Consequently, the average slopes of various driving directions are compared, allowing the ideal driving direction with the minimal slope to be identified for mitigating erosion effectively. A web application has been developed to implement and demonstrate the proposed algorithm.","author":[{"family":"Kumpf","given":"M"},{"family":"Tauböck","given":"A"},{"family":"Marefatollah","given":"M"},{"family":"Winterspacher","given":"M"},{"family":"Hungendorfer","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_115","URL":"https://doi.org/10.1163/9789004725232_115","source":"crossref"},{"id":"doi:10.1163/9789004725232_076","type":"article-journal","title":"Time series model for predicting the disturbance of lychee canopy by wind field in unmanned aerial spraying system","abstract":"The rotor downwash airflow generated by unmanned aerial spraying systems (UASS) significantly influences the precision of pesticide application on tree canopies. This study proposes a time-series model to analyze the relationship between multi-rotor UASS wind fields and canopy disturbances in lychee trees. Disturbance data were collected using visual and attitude sensors, with disturbance areas and positions extracted via an enhanced frame difference method and sensor data fusion. UASS motion information was obtained using DeepSORT, while recurrent neural networks (RNN) and multi-head attention mechanisms were employed to analyze 1965 time-series datasets. The results revealed that the Informer algorithm outperformed others in predicting disturbance areas with the lowest errors, while the gated recurrent unit (GRU) model demonstrated consistent accuracy in predicting disturbance positions, providing a reliable solution for precise canopy disturbance analysis.","author":[{"family":"Chen","given":"P"},{"family":"Liu","given":"H"},{"family":"Lan","given":"Y"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_076","URL":"https://doi.org/10.1163/9789004725232_076","source":"crossref"},{"id":"doi:10.1163/9789004725232_111","type":"article-journal","title":"Optimizing variable N application to living grass coverage estimated in late autumn or early spring","abstract":"A field experiment was conducted in 2022–2023 and repeated in 2023–2024, estimating plant coverages using digital processing of autumn and spring aerial images to determine fertilizer rates. Three fixed and two variable manure and mineral N rates were applied in early spring and after the first cut. Dry matter yield (DMY) and agronomic efficiency (AE) were evaluated over two seasons. A low or variable N rate based on spring coverage led to DMY and AE comparable to high N rates. Autumn coverage in the second season improved slurry application decisions, offering a valuable tool for grassland management.","author":[{"family":"Stafford","given":"John"},{"family":"Stafford","given":"John"},{"family":"Stafford","given":"John"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_111","URL":"https://doi.org/10.1163/9789004725232_111","source":"crossref"},{"id":"doi:10.1007/s44378-025-00055-2","type":"article-journal","title":"A critical review of how UAVs can transform precision agriculture in the realm of Agroecology","abstract":"The Sustainable Development Goals (SDGs) encompass 17 global goals aimed at fostering a more sustainable and equitable world by addressing socio-economic and environmental challenges, including agriculture. Achieving these goals necessitates the adoption of agro-ecological principles, particularly in sustainable land use and food production, to enhance productivity while reducing reliance on external resources like fertilizers and pesticides. Precision technologies, such as unmanned aerial vehicles (UAVs), play a crucial role in this transformation by enabling site-specific and energy-efficient practices. The integration of UAVs in Precision Agriculture (PA) aligned with agro-ecological principles is pivotal to achieving several SDGs, particularly SDG1, SDG2, SDG3, SDG12, SDG13, and SDG15. UAVs provide real-time, non-destructive, and spatial data on soil nutrients, crop conditions, and yields, thereby improving resource efficiency. However, concerns about environmental impact, technological skill, e-waste, wildlife conflicts, data security, economic disparities, and the lack of standardized protocols pose significant challenges, particularly for small-scale farmers. These challenges are further complicated by potential conflicts with SDGs, such as SDG3, SDG9, SDG10, and SDG12 to SDG16. Although future advancements hold great potential, policymakers must address the issues of small-scale farmers, such as ease of use, cost involvement, and standard regulatory guidelines. This article critically examines the role of UAVs in PA within the agro-ecological framework, exploring their potential to align with the United Nations’ SDGs while addressing the challenges faced by small scale farmers.","author":[{"family":"Narzari","given":"Rumi"},{"family":"Choudhury","given":"Burhan"},{"family":"Singhal","given":"Gaurav"},{"family":"Choudhary","given":"Karun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s44378-025-00055-2","URL":"https://doi.org/10.1007/s44378-025-00055-2","source":"crossref"},{"id":"doi:10.1109/dasa68193.2025.11498850","type":"article-journal","title":"Early-Stage Weed Detection in Sorghum Using Instance Segmentation for Precision Agriculture","abstract":"Weed infestation is a major challenge in sorghum cultivation, as it competes with crops for nutrients, water, and sunlight, leading to significant yield losses if not managed effectively. Traditional manual weed detection and removal methods are time-consuming, labor-intensive, and prone to human error. To address this issue, this study presents a novel instance segmentation–based approach for automated weed identification during the early crop development stages in sorghum fields. Utilizing deep learning techniques, particularly the Mask R-CNN framework, the model is capable of accurately detecting and segmenting weed occurrences among sorghum plants. The dataset used in this study comprises pixel-level annotated images containing broad-leaf weeds, grasses, and sorghum samples. Through careful training and validation, the model achieved a mean Average Precision (mAP) of 87.4%, demonstrating strong detection accuracy across multiple classes. The inference results further confirm the model’s ability to reliably identify diverse weed types under varying field conditions. These findings highlight the potential of the proposed approach to enhance precision agriculture, enabling more efficient weed management that promotes sustainability and higher crop productivity in sorghum farming.","author":[{"family":"Macalisang","given":"Jonel"},{"family":"Alon","given":"Alvin"},{"family":"Reyes","given":"Michelle"},{"family":"Reyes","given":"Ryan"},{"family":"Militante","given":"Sammy"},{"family":"Acoba","given":"Aimee"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/dasa68193.2025.11498850","URL":"https://doi.org/10.1109/dasa68193.2025.11498850","source":"crossref"},{"id":"doi:10.1089/ind.2025.0007","type":"article-journal","title":"Role of Artificial Intelligence Tools in CRISPR-Cas9 Genomic Editing Technique for Precision Agriculture","abstract":"CRISPR-Cas9 is a groundbreaking technology that has revolutionized genetic engineering by allowing precise and efficient genome editing. Despite its potential, the complexity and variability of genomic data present significant challenges. Artificial intelligence (AI) offers powerful tools to enhance CRISPR-Cas9 applications by improving target identification, minimizing off-target effects, optimizing components, and streamlining data analysis. AI tools have significantly enhanced the CRISPR-Cas9 genomic editing technique in precision agriculture, particularly in the area of disease detection and trait improvement. This review explores the various roles that AI plays in advancing CRISPR-Cas9 technology, highlighting current tools and future directions. This review also explores various AI-driven tools and methods that have been developed to optimize CRISPR-Cas9 genomic editing, from target identification to data analysis, off-target prediction, optimizing the efficiency, accuracy, and safety of gene editing, data analysis, and personalized medicine.","author":[{"family":"Saini","given":"Himanshu"},{"family":"Semwal","given":"Ashish"},{"family":"Nanda","given":"Deepak"},{"family":"Juyal","given":"Tripti"},{"family":"Kumar","given":"Naveen"},{"family":"Srivastava","given":"Hritik"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1089/ind.2025.0007","URL":"https://doi.org/10.1089/ind.2025.0007","source":"crossref"},{"id":"doi:10.1007/s11119-026-10338-5","type":"article-journal","title":"Changing perceptions of crop robotics in social media","abstract":"Perception is often key to the success of precision agriculture innovations. Social media is one window into unvarnished expressions of common perceptions. This study investigates how public discourse surrounding crop robotics evolved on X (formerly Twitter) from 2011 to 2024. Using a mixed-method approach, 6964 tweets were analyzed to: (1) understand how the volume of posts about crop robotics have changed, (2) assess the shifts in sentiments and subjectivity expressed about crop robotics in those messages, (3) identify key themes of discourse and (4) assess if a turning point was triggered by the Hands Free Hectare (HFH) demonstrations of using crop robots to achieve practical farming tasks. The analysis shows that 2016–2018 coincided with a marked inflection in the perception of crop robotics. During this period HFH and several other crop robot organizations demonstrated field crop production with autonomous machines. Prior to this period crop robotics was treated as a distant prospect, but after this period it became a current possibility. Tweets about crop robotics were sparse before 2016, increased sharply in 2017–2018, stayed high to 2023. Tweets became more positive and more factual post 2016. These patterns suggests that sight of retrofitted farm machines autonomously accomplishing HFH field tasks helped some people understand that crop robotics is a real, short-term possibility and that this helped change the societal perception of the technology and commercialization potential.","author":[{"family":"Lowenberg-Deboer","given":"James"},{"family":"Huang","given":"Iona"},{"family":"Sarfo","given":"Yaw"},{"family":"Casals","given":"Germán"},{"family":"Franklin","given":"Kit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10338-5","URL":"https://doi.org/10.1007/s11119-026-10338-5","source":"crossref"},{"id":"doi:10.1007/s11119-025-10276-8","type":"article-journal","title":"Experimental design issues associated with classifications of hyperspectral sensing data","abstract":"Abstract Purpose Hyperspectral sensing (remote or proximal) has emerged as a pivotal tool to classify plant materials (seeds, leaves, and whole plants), pharmaceutical products, food items, and many other objects. Thus, hyperspectral sensing is one of the most frequently used technologies in research articles published by this journal, and it was therefore found relevant to address two methodological issues, which (based on Google Scholar searches) appear to be over-looked or ignored in &gt;94% of hyperspectral sensing studies: 1) the \"small N, large P\" problem, when number of spectral bands (explanatory variables, “P”) surpasses number of observations, (“N”) leading to potential model over-fitting, and 2) absence of independent validation data in performance assessments of classification models. Methods Based on simulations of randomly generated data, risks associated with these issues were illustrated. This communication explores and discusses consequences of over-fitting and risks of misleadingly high accuracy that can result from having a large number of variables relative to observations. Moreover, connections of these issues with radiometric repeatability (levels of stochastic noise) are highlighted. A method is proposed wherein a theoretical dataset is generated to mirror the structure of an actual dataset, with the classification of this theoretical dataset serving as a reference. Conclusion By shedding light on important and common experimental design issues, the principal aim is to enhance methodological rigor and transparency in classifications of hyperspectral sensing data and foster improved and effective applications across various science domains, including precision agriculture.","author":[{"family":"Nansen","given":"Christian"},{"family":"Lee","given":"Hyoseok"},{"family":"Mesgaran","given":"Mohsen"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10276-8","URL":"https://doi.org/10.1007/s11119-025-10276-8","source":"crossref"},{"id":"doi:10.1007/s11119-026-10393-y","type":"article-journal","title":"Soil moisture mapping using radio signal strength and gaussian process regression","abstract":"Abstract Background Soil moisture is a key variable in precision agriculture, affecting irrigation management, crop productivity, and water-use efficiency. However, field-scale soil moisture monitoring remains challenging because conventional sensing approaches are often costly and provide limited spatial coverage. This study proposes a simulation-based framework for soil moisture mapping that integrates near-ground radio-frequency (RF) sensing, Gaussian Process Regression (GPR), and adaptive sample selection Methods Received signal strength (RSS) measurements obtained from paired RF sensors were used as path-averaged proxies for soil moisture. GPR was employed to reduce measurement noise and reconstruct spatial soil moisture distributions from sparse ground-truth observations. An error-driven adaptive sampling strategy was developed to identify locations for additional soil moisture measurements under constrained sampling budgets. The framework was evaluated using numerical simulations based on synthetic soil moisture fields with varying levels of spatial variability and measurement noise. Results Simulation results demonstrated that the proposed framework reduced soil moisture estimation error compared with random sampling and conventional GPR interpolation when only a limited number of samples were available. The adaptive sampling strategy improved the efficiency of data collection by prioritizing regions with higher prediction uncertainty. Reconstruction accuracy was influenced by both soil moisture variability and measurement noise, highlighting the importance of sensor quality and field heterogeneity in system performance. Conclusion The study demonstrates the potential of combining RSS-based RF sensing, probabilistic regression, and adaptive sampling for low-cost and scalable soil moisture mapping in precision agriculture. Although the framework was evaluated only under idealized simulation conditions and no field validation was conducted, the results provide proof of concept and support future development, field testing, and extension of the approach for practical agricultural applications.","author":[{"family":"Yu","given":"Hongjun"},{"family":"Muller","given":"Erik"},{"family":"Mcbratney","given":"Alex"},{"family":"Sukkarieh","given":"Salah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10393-y","URL":"https://doi.org/10.1007/s11119-026-10393-y","source":"crossref"},{"id":"doi:10.14445/23497157/ijres-v11i6p104","type":"article-journal","title":"The Impact of Robots in Agriculture for Enhanced Precision in Farming","abstract":"Agriculture, one of the most important industries globally, faces developing challenges, including labor shortages, environmental sustainability, and the need to meet increasing food demands. As an imperative aspect of precision farming, robotics gives revolutionary solutions to those challenges. This paper explores the impact of robots on agricultural production, specializing in greater precision in planting, harvesting, and crop tracking. The paper illustrates how robots can enhance yield, reduce expenses, minimize environmental impact, and sell sustainable farming by incorporating a case study of John Deere's autonomous tractor and Blue River technology's","author":[{"family":"Rao","given":"Bisa"},{"family":"Teja","given":"Martha"},{"family":"Bhargav","given":"Rss"},{"family":"Krishna","given":"Kota"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14445/23497157/ijres-v11i6p104","URL":"https://doi.org/10.14445/23497157/ijres-v11i6p104","source":"crossref"},{"id":"doi:10.32854/5aqn0407","type":"article-journal","title":"Bio-Inspired Optimization of Convolutional Neural Networks for Enhanced Maize Disease Detection in Precision Agriculture","abstract":"Objetivo: El propósito de este estudio es desarrollar un sistema automatizado, basado en imágenes, para la detección temprana de cuatro enfermedades comunes del maíz—Puccinia sorghi, Cochliobolus carbonum, Bipolaris maydis y Exserohilum turcicum—empleando Redes Neuronales Convolucionales optimizadas mediante algoritmos bioinspirados. Diseño/metodología/aproximación: Se utilizó un conjunto de 17,280 imágenes de alta resolución, capturadas en seis etapas de evolución de la enfermedad. Las imágenes fueron preprocesadas mediante normalización, redimensionamiento y aumento de datos. La arquitectura CNN fue entrenada utilizando dos algoritmos metaheurísticos—Spider Monkey Optimization y Squirrel Search Algorithm—para ajustar pesos e hiperparámetros. Se empleó una partición de datos 80/20 (entrenamiento/validación) y se evaluó el desempeño con métricas estándar de clasificación. Resultados: La CNN optimizada con SMO superó en rendimiento al modelo ajustado con SSA, alcanzando una precisión del 95.14% frente al 89.74%. Además, mostró mejores valores en precisión, sensibilidad y puntuación F1, incluso al distinguir síntomas visualmente similares. Limitaciones del estudio/implicaciones: Aunque SMO mejoró significativamente la clasificación, su complejidad computacional podría dificultar su implementación en contextos con recursos limitados. Persisten algunos errores de clasificación entre enfermedades de apariencia semejante, lo que sugiere la necesidad de mejorar la discriminación de características e incorporar conjuntos de datos más amplios y variados. Hallazgos/conclusiones: La combinación de CNN con SMO demuestra ser una solución eficaz y robusta para el diagnóstico automatizado de enfermedades en cultivos de maíz, reduciendo tiempos de análisis y favoreciendo una gestión agrícola más precisa. Se recomienda continuar con el desarrollo de métodos híbridos de optimización para mejorar la escalabilidad y su aplicación en tiempo real dentro de contextos de agricultura de precisión.","author":[{"family":"Fuentes-Huerta","given":"Marco"},{"family":"Sifuentes","given":"Mario"},{"family":"González-González","given":"David"},{"family":"Praga-Alejo","given":"Rolando"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32854/5aqn0407","URL":"https://doi.org/10.32854/5aqn0407","source":"crossref"},{"id":"doi:10.70177/agriculturae.v1i1.916","type":"article-journal","title":"The Precision Agriculture Revolution in Asia: Optimizing Crop Yields with IoT Technology","abstract":"Agriculture in Asia faces challenges in meeting increasing food needs due to population growth. Conventional farming methods are often less efficient and unsustainable. Precision agricultural technology, especially the Internet of Things (IoT), offers solutions to significantly increase farm productivity and efficiency. This research aims to explore the potential application of IoT technology in precision agriculture in Asia and analyze its impact on optimizing crop yields. This research uses a case study approach by analyzing the implementation of IoT technology in precision agriculture in several Asian countries, such as China, India, and Indonesia. Data was collected through interviews with farmers, agricultural experts, related stakeholders, and field observations. Research results show that the application of IoT technology in precision agriculture in Asia provides significant benefits, including (1) monitoring soil conditions, weather, and plant growth in real-time, (2) optimizing the use of fertilizer and irrigation water, (3) early detection of pests and plant diseases, and (4) increasing the efficiency of agricultural management. In addition, this research found that adopting IoT technology still needs to be improved by factors such as limited infrastructure, initial investment costs, and human resource readiness. It can be concluded that IoT technology has great potential in supporting the precision agriculture revolution in Asia. Its implementation can optimize crop yields through more efficient and sustainable agricultural management. However, systematic efforts are needed to overcome challenges in implementing IoT technology in the farming sector, such as infrastructure investment, human resource training, and supporting policies from the government","author":[{"family":"Guilin","given":"Xie"},{"family":"Jiao","given":"Deng"},{"family":"Wang","given":"Yuanyuan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70177/agriculturae.v1i1.916","URL":"https://doi.org/10.70177/agriculturae.v1i1.916","source":"crossref"},{"id":"doi:10.3390/agriculture15232468","type":"article-journal","title":"Adoption and Perception of Precision Technologies in Agriculture: Systematic Review and Case Study in the PDO Wines of Granada, Southern Spain","abstract":"Precision technologies are increasingly relevant in contemporary agriculture, offering tools to enhance efficiency, sustainability, and decision-making. Their adoption is becoming particularly critical among vine-growers in the wine industry, a sector facing market pressures, climate change, and generational shifts. This study combines a systematic literature review with an empirical analysis of the PDO (Protected Designation of Origin) Wines of Granada (Southern Spain) to examine perceptions of precision agriculture technologies at both global and regional scales. The review included 607 articles published between 2015 and 2025 in English (indexed in ISI Web of Knowledge), identifying key factors influencing technology adoption. Using “perception” and “precision agriculture” as search terms, only 97 articles simultaneously addressed both concepts. At the regional level, a case study involving 22 wineries (with 37 stakeholders) in Granada province was conducted, focusing on socioeconomic barriers and environmental conditions such as altitude, climate, and soil type. Results revealed cross-scale consistencies regarding the importance of costs and perceived usefulness of new technologies (e.g., proximal sensors, satellite imagery), but divergences concerning the difficulties in accessing them and their cost. The findings highlight the need for supportive policies, targeted training, and practical demonstrations to facilitate adoption, thereby fostering innovation and sustainability, especially in the wine sector of the province of Granada. Integrating international and local evidence provides a framework for designing regional strategies tailored to promote precision technologies that improve efficiency, quality, and sustainability in wine production.","author":[{"family":"González-Vivar","given":"Jesús"},{"family":"Sobczyk","given":"Rita"},{"family":"Romero-Frías","given":"Esteban"},{"family":"Rodrigo-Comino","given":"Jesús"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15232468","URL":"https://doi.org/10.3390/agriculture15232468","source":"crossref"},{"id":"doi:10.1109/icssas64001.2024.10761044","type":"article-journal","title":"Integrating Cloud Computing and Naive Bayes for Precision Detection and Classification of Sheet and Rill Erosion in Agriculture","abstract":"Sustainable agriculture has significant challenges from sheet and rill erosion for effective techniques. A new way to accurately identify and classifier sheet and rill erosion in agricultural landscapes with the combination of cloud computing and Naïve Bayes. To differentiate between these erosion patterns work proposes a technique that uses ground truth data and high-resolution satellite images. The technique gets results by using the Naïve Bayes algorithm, which is famous for being simple and successful in classification problems. More efficient and accurate and advanced methods by conducting comprehensive experiments and validations. This technology takes use of the scalability and accessibility of cloud computing to conduct erosion risk assessments in real-time, providing agricultural stakeholders with valuable information to enhance soil conservation initiatives. It highlights the revolutionary power of new technology to improve agricultural land management methods and address environmental issues. Sustainable agricultural practices mitigate the adverse implications of soil erosion by offering exact detection and classification of erosion events, which lead to better informed decision-making.","author":[{"family":"Deshpande","given":"Ashish"},{"family":"Raman","given":"Ramakrishnan"},{"family":"Vekariya","given":"Vipul"},{"family":"Mishra","given":"Nilamadhab"},{"family":"Arumugam","given":"Sundaram"},{"family":"Srinivasan","given":"C"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icssas64001.2024.10761044","URL":"https://doi.org/10.1109/icssas64001.2024.10761044","source":"crossref"},{"id":"doi:10.2172/2516744","type":"article-journal","title":"Precision Agriculture using Networks of Degradable Analytical Sensors (PANDAS) (Final Technical Report)","abstract":"Precision agriculture, where sensing of soil, environment and crop conditions are used to precisely synchronize inputs (such as water and fertilizer) to crop needs enhances input use efficiency. This can improve yields and farm profitability while mitigating environmental losses, improving soil carbon content and substantially decreasing energy use for food, feed and fuel crops. Unfortunately, farmers are not yet able to harness the full potential of these management technologies as there is a lack of available management information, and there is therefore a need for sensors that are able to economically measure spatio-temporal variability in soil and crop properties of extremely heterogeneous farm fields precisely at high resolution and at low cost. Real-time, in-situ monitoring of agricultural soil conditions is today carried out using devices that limit the total number of nodes that can be used economically to typically one per acre or less. Higher spatio-temporal resolution sensing would enable more precise agricultural input optimization, with significant benefits to the farmer and the environment. In order to address this issue, this project focused on developing additively manufactured, biodegradable, soil sensors with predicted costs of 100× increase in information density over current solutions for precision farming of row and other crops, and lead to significant reductions in input energy use and provide increased yield for biofuel crops. Over the course of this project the team at the University of Colorado Boulder, University of California Berkeley, and Colorado State University/Kansas State University investigated a wide range of printable biodegradable electronic materials and sensor designs for determining soil moisture and soil nitrate concentration. These efforts expanded the available materials set for printed soil degradable electronic materials, particularly for conductors, enabling high conductivity and stability. Printed soil moisture and nitrate sensors with suitable sensitivity and selectivity were developed and characterized. Low power and passive wireless electronic systems were integrated with the soil sensors, and testing was carried out with completed sensors to understand their functionality under agricultural conditions. Additionally, other sensor types enabled by the biodegradable materials set created during this project, such as soil microbial activity sensors, were also developed and demonstrated. Project outputs include 10 peer reviewed publications, 4 patent applications, 21 technical presentations, 3 PhD thesis, 10 media reports, 8 additional grants worth over $6M, and the formation of 3 start-up companies.","author":[{"family":"Whiting","given":"Gregory"},{"family":"Arias","given":"Ana"},{"family":"Khosla","given":"Raj"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2172/2516744","URL":"https://doi.org/10.2172/2516744","source":"crossref"},{"id":"doi:10.1109/ispacs62486.2024.10868011","type":"article-journal","title":"Implementation of Mini-Greenhouse Based on Precision Agriculture","abstract":"As the saying goes: “Food is the first priority for the people.” Agriculture has been a national priority since ancient times. In recent years, due to the severe impacts of extreme climate and the decline in the agricultural workforce in rural areas, many agricultural challenges have become increasingly urgent. To address these challenges, governments worldwide, including ours, have placed great importance on agricultural issues. One of the key strategies to combat the effects of extreme climate on agriculture is the introduction of greenhouses. In addition to traditional large-scale greenhouses, we implemented a mini-greenhouse based on standardized precision planting, making planting accessible to general users and agriculture to every corner. In our implementation, we use the Raspberry Pi board to automate the control mechanism of the mini-greenhouse. Users can customize the planting environment for different crops by accessing a web page where they can set parameters such as lighting, exhaust fan temperature, and water supply. The mini-greenhouse enables automated and precise planting by using sensors to monitor conditions such as light levels, atmospheric temperature and humidity, as well as soil temperature and moisture. To ensure reliability and future scalability, all sensors adhere to industrial standards and are based on the RS485 Modbus protocol. With this simple mini-greenhouse, built on the principles of precision agriculture, we aim to bring agriculture into everyday households.","author":[{"family":"Cheng","given":"Wei"},{"family":"Chen","given":"Yu"},{"family":"Chen","given":"Tai"},{"family":"Zhuang","given":"Xiang"},{"family":"Chang","given":"Che"},{"family":"Chien","given":"Wei"},{"family":"Wu","given":"Yu"},{"family":"Chen","given":"Robert"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ispacs62486.2024.10868011","URL":"https://doi.org/10.1109/ispacs62486.2024.10868011","source":"crossref"},{"id":"doi:10.1109/bigdata62323.2024.10826124","type":"article-journal","title":"An AI-Driven Architecture for Precision Agriculture: IoT, Machine Learning, and Digital Twin Integration for Sustainable Crop Protection","abstract":"General efficient crop protection in olive orchards is challenged by the need for precise agrochemical application minimizing environmental impact while ensuring effective spray coverage. Conventional approaches often lead to poor spray distribution, heavy off-target losses and a lack of real-time adaptability in variable field conditions. Such findings imply the need for an approach or system that can adjust application parameters dynamically to optimize both effectiveness and sustainability.This paper introduces an advanced AI-driven architecture designed to meet these challenges by integrating Internet of Things (IoT), machine learning, and digital twin technologies. The core of this approach is the development of a Digital Tree, a virtual model of olive trees that accurately simulates and predicts spray distribution and interactions with environmental variables. IoT sensors in the field collect real-time data on spray behavior and field conditions, which machine learning algorithms then process to refine application parameters dynamically. By enabling data-driven, adaptive decision-making, the digital twin supports optimal spray distribution, reduces off-target impact, and enhances environmental sustainability. This integrated solution offers a scalable and replicable methodology for smart agriculture, advancing precision and sustainability in complex agricultural environments.","author":[{"family":"Costa","given":"Gianni"},{"family":"Forestiero","given":"Agostino"},{"family":"Gentile","given":"Antonio"},{"family":"Macrì","given":"Davide"},{"family":"Ortale","given":"Riccardo"},{"family":"Bernardi","given":"Bruno"},{"family":"Cerruto","given":"Emanuele"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/bigdata62323.2024.10826124","URL":"https://doi.org/10.1109/bigdata62323.2024.10826124","source":"crossref"},{"id":"doi:10.58812/wsnt.v2i04.1536","type":"article-journal","title":"Precision Agriculture Technology Innovation in Supporting Food Security in the Era of Industrial Revolution 4.0","abstract":"The Industrial Revolution 4.0 has driven transformative changes in agriculture through the adoption of precision agriculture (PA) technologies, aimed at optimizing resource use and enhancing food security. This study conducts a systematic literature review of 52 Scopus-indexed documents to evaluate the role of these technologies in addressing global food challenges. Key innovations such as IoT, AI, drones, and robotics are highlighted for their contributions to increasing agricultural productivity, ensuring environmental sustainability, and mitigating the effects of climate variability. Despite their potential, barriers such as high implementation costs, technological complexity, and limited access in developing regions hinder widespread adoption. The findings underscore the need for targeted policies, infrastructure development, and inclusive practices to harness PA technologies for food security fully. This study provides valuable insights for researchers, policymakers, and practitioners to foster sustainable agricultural systems.","author":[{"family":"Judijanto","given":"Loso"},{"family":"Wahyuni","given":"Ira"},{"family":"Suryandari","given":"Ratnawati"}],"issued":{"date-parts":[[2025]]},"DOI":"10.58812/wsnt.v2i04.1536","URL":"https://doi.org/10.58812/wsnt.v2i04.1536","source":"crossref"},{"id":"doi:10.1109/cafe63183.2024.11069337","type":"article-journal","title":"A Comprehensive Strategy for Tomato Cultivation Utilizing Precision Agriculture Techniques","abstract":"Tomato cultivation in the Mediterranean region is challenged by numerous factors, including water scarcity, soil degradation, pest and disease pressures, and climate change. Socioeconomic factors, including farmers' aging, demographic issues, and limited access to advanced agricultural technologies, exacerbate these challenges. This paper explores Precision Agriculture (PA) technologies to improve the sustainability and productivity in tomato farming. PA techniques, such as remote and proximal sensing, including hyperspectral imaging, provide real-time monitoring on crop health status, soil conditions, and moisture content levels, enabling farmers to optimize critical management practices regarding irrigation, fertilization, and pest control. Integrating artificial intelligence (AI) and machine learning (ML) with hyperspectral imaging enhances early crop disease detection, reduces the extensive application of pesticide use. Furthermore, advancements in automated harvesting technologies, including robotic systems equipped with sophisticated visual recognition and end-effector mechanisms, offer promising solutions to labor-intensive harvesting processes. This paper presents a comprehensive review of these technologies, highlighting their applications, contribution, and potential impacts on improving the efficiency and sustainability of tomato cultivation in the Mediterranean region. Through the adoption of these innovative approaches, higher yield, better resource management practices, and reduced production costs are expected.","author":[{"family":"Tsakalos","given":"Karolos"},{"family":"Kleitsiotis","given":"Georgios"},{"family":"Tompris","given":"Ioannis"},{"family":"Passias","given":"Athanasios"},{"family":"Stavroulakis","given":"Emmanouil"},{"family":"Tsipas","given":"Evangelos"},{"family":"Rallis","given":"Konstantinos"},{"family":"Fyrigos","given":"Iosif"},{"family":"Pantazi","given":"Xanthoula"},{"family":"Sirakoulis","given":"Georgios"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/cafe63183.2024.11069337","URL":"https://doi.org/10.1109/cafe63183.2024.11069337","source":"crossref"},{"id":"doi:10.2139/ssrn.7254883","type":"manuscript","title":"&lt;div&gt;\n Mountain Precision Agriculture Index: a Review\n&lt;/div&gt;","abstract":"The paper develops the Mountain Precision Agriculture Index realized in 2020 at Oradea University-Doctoral School, Agronomy Specialization (Covaci-Sterpu, 2020). The article points the importance of entrepreneurship development, focusing on precision agriculture index in the mountain area. The reviewed papers show that the implementation of precision farming within an IoT framework in highland regions (ζ9) must be developed with attention to various essential aspects, precisely the elevation of the mountain (ζ1), the gradient of the terrain (ζ2), the mean local altitude (ζ3), signal degradation due to the mountainous topography (ζ4), access to internet connectivity (ζ6), the level of smart technology utilization (ζ7), and the concentration of active ICT businesses in the region (ζ8). The current paper show that ζ9 is dependent of other indices too, respectively the interaction with the intensity of geomagnetic storms or weather shortcomings (ζ5). The paper presents a specific map of the mountain peaks from the European area, highlighting the importance of the altitude in applying the precision agriculture index.","author":[{"family":"Covaci","given":"Brindusa"},{"family":"Covaci","given":"Mihai"},{"family":"Brejea","given":"Radu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.7254883","URL":"https://doi.org/10.2139/ssrn.7254883","source":"crossref"},{"id":"doi:10.1109/icses63760.2024.10910911","type":"article-journal","title":"IoT-Based Precision Agriculture Using Smart Sensors and Cloud Computing for Crop Monitoring and Yield Optimization","abstract":"The Internet of Thingsbased precision agriculture system plans to deliver the finest agricultural productivity by giving real-time monitoring and therefore informed decisions based on data. Data from the different environmental factors like temperature, soil and other aspects are evaluated by smart sensors and then subsequently sent to the AWS Cloud by a central microcontroller. Then, the XGBoost machine learning model is applied to predict agricultural output under several scenarios following all that has been done with the collected data. Hyperparameter tuning gives the best performance while feature selection enhances the accuracy of the model after normalization and preprocessing. The results of experiments give a 98.5% prediction accuracy, which is confirmed by an R-squared value of 0.92 and an error of 0.245. The system utilizes a new method to enhance farm productivity, reduce resource usage, and enable data-driven decisions in real time.","author":[{"family":"Priya","given":"SS"},{"family":"Akilesh","given":"R"},{"family":"Karthikeyan","given":"S"},{"family":"Balasabarish","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icses63760.2024.10910911","URL":"https://doi.org/10.1109/icses63760.2024.10910911","source":"crossref"},{"id":"doi:10.1109/icses63760.2024.10910560","type":"article-journal","title":"Smart Agriculture: Leveraging IoT and Machine Learning in Wireless Sensor Networks for Precision Farming","abstract":"This research explores the challenge of incorporating IoT with Machine Learning (ML) applications to Precision Agriculture, particularly the use of wireless sensors for irrigation control. Information from sensors that monitor key parameters including temperature, humidity, moisture, and water levels are used to forecast water requirements and control pumps. Support vector machine (SVM), Decision tree (DT), Random Forest (RF) and Naïve Bayes (NB) techniques are adopted for the analysis to find out their accuracy levels. It is observed from all the above-performed models that among all, the SVM has the maximum prediction rate of the given dataset and is slightly outperformed by only the DT and RF. The confusion matrix which points to the misclassification patterns of each model gives an insight into identifying the best ML approach for use. The convergence of IoT and ML guarantees flexibility and responsiveness when controlling and designing agricultural systems. It is this approach that has the potential to enhance water resources management as well as address issues precipitated by climate change and growing worldwide food demand.","author":[{"family":"Sheela","given":"MS"},{"family":"Leonid","given":"TT"},{"family":"Aravindhraj","given":"N"},{"family":"Giri","given":"Pallavi"},{"family":"Amer","given":"Ayman"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icses63760.2024.10910560","URL":"https://doi.org/10.1109/icses63760.2024.10910560","source":"crossref"},{"id":"doi:10.1109/metroagrifor66923.2025.11512345","type":"article-journal","title":"A Low-Cost Portable Spectrophotometer for Precision Agriculture based on Hamamatsu C12880MA","abstract":"The use of spectroscopic techniques to monitor plant health is becoming increasingly popular in precision agriculture. In this paper, we present a potential application of the Hamamatsu C12880MA spectrophotometer to study leaf surface reflectance in the spectral range from 350 nm to 850 nm. This instrument was placed near a black cloth to reduce the ambient noise and the leaves placed on the surface and they are illuminated by a lamp. This light is polarized by a polarizer located on Hamamatsu, and the reflected signal is collected by the C12880MA spectrophotometer connected to the ARDUINO UNO R4 microcontroller. From reflectance analyses, through a machine learning MLP (Multi-Layer Perceptron) model, it is possible to trace back to the corresponding pantone color of the leaf, which in turn can provide us with indications about its health status.","author":[{"family":"Leccisi","given":"Mariagrazia"},{"family":"Fina","given":"Federico"},{"family":"Leccese","given":"Fabio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/metroagrifor66923.2025.11512345","URL":"https://doi.org/10.1109/metroagrifor66923.2025.11512345","source":"crossref"},{"id":"doi:10.1007/s11119-026-10398-7","type":"article-journal","title":"A tertiary systematic literature review and experimental evaluation of deep learning models for plant disease detection","abstract":"Abstract Objective Minimizing crop losses through the early detection of plant diseases is vital for enhancing global agricultural efficiency. While deep learning has emerged as a promising solution, a significant gap exists between laboratory performance and practical, in-field utility. This study evaluates this discrepancy through a dual-methodological approach. Methods First, a tertiary systematic literature review was conducted, synthesizing 22 secondary reviews encompassing over 750 unique primary studies to establish the current state of the art. Second, an empirical validation was performed using a VGG16 transfer learning model trained on three distinct dataset types, which vary in scale (small vs. large), environment (laboratory vs. in-field), and condition (raw vs. pre-processed). Results The tertiary review identifies Convolutional Neural Networks, particularly VGG architectures, as the leading model but highlights a critical reliance on private and unrealistic datasets. Furthermore, the analysis reveals that Accuracy, the most common metric, is often insufficient for evaluating the imbalanced datasets typical of the field. Empirical results corroborate these findings, demonstrating that VGG16 performance is highly dependent on dataset characteristics; models perform significantly better on large, pre-processed laboratory data than on realistic in-field datasets. Conclusion These findings suggest that many current models remain inapplicable to real-world agricultural scenarios. To bridge this reality gap, future research must prioritize the development of open-source, standardized, and validated in-field datasets to ensure the reliability and scalability of automated disease detection systems.","author":[{"family":"Bennin","given":"Kwabena"},{"family":"Teeffelen","given":"Dide"},{"family":"Hurst","given":"William"},{"family":"Babur","given":"Önder"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10398-7","URL":"https://doi.org/10.1007/s11119-026-10398-7","source":"crossref"},{"id":"doi:10.1007/s11119-026-10436-4","type":"article-journal","title":"Integrating soil and canopy sensing to map and relate variability in tart cherry orchards","abstract":"Abstract Purpose Evaluate how soil and canopy sensing can map within-block variability in tart cherry orchards and identify indicators robust enough for repeatable management decisions. Methods Soil apparent electrical conductivity (ECa) was mapped in spring 2022 across four commercial tart cherry blocks (8.5–10.5 ha; approximately 3,500 trees per block), followed by canopy sensing in 2023–2024. Canopy structure was measured using unmanned aerial vehicle (UAV) photogrammetry and mobile terrestrial laser scanning (MTLS) using light detection and ranging (LiDAR), and canopy density using mobile ceptometry. Spatial layers were aligned to per-tree grid cells. An August 2025 campaign compared UAV- and LiDAR-derived tree height with ground-truthed height. Results Soil-to-canopy relationships were weak to moderate but consistent within blocks ( r = 0.10–0.40), with strength and direction varying by site conditions. Canopy density was more strongly associated with UAV-derived volume than height. UAV-derived 90th-percentile height best predicted ground-truthed height ( R ² = 0.89; RMSE = 0.34 m), whereas LiDAR showed a weaker relationship and greater error ( R ² = 0.70; RMSE = 0.52 m). Cross-sensor agreement was moderate to strong ( r = 0.41–0.65). Per-tree rankings were stable between years for UAV height and volume. Conclusion Whole-block sensing revealed persistent spatial patterns that could support management-zone delineation. UAV photogrammetry provided accurate canopy metrics, MTLS offered measurements suited to routine orchard operations, ceptometry added seasonal canopy-density information, and ECa provided soil context. Occasional ECa mapping combined with strategically timed UAV surveys and other sensors as needed could reduce redundant sensing while supporting fertilizer evaluation, pruning, and labor allocation.","author":[{"family":"Wedegaertner","given":"Kurt"},{"family":"Black","given":"Brent"},{"family":"Safre","given":"Anderson"},{"family":"Torres-Rua","given":"Alfonso"},{"family":"Cardon","given":"Grant"},{"family":"Yost","given":"Matt"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10436-4","URL":"https://doi.org/10.1007/s11119-026-10436-4","source":"crossref"},{"id":"doi:10.1016/j.inpa.2026.04.007","type":"article-journal","title":"Reinforcement learning guided active crop localization with CNN detectors and an interactive decision dashboard for precision agriculture","abstract":"Accurate crop localization is a foundational requirement for automated field monitoring in precision agriculture, yet conventional one-shot convolutional neural network (CNN) detectors frequently yield misaligned or incomplete bounding boxes under variable illumination, occlusion, complex canopy structures, and heterogeneous plant morphology. To overcome these limitations, we propose a reinforcement learning (RL), guided active crop localization framework that reformulates localization as a sequential decision-making problem, enabling adaptive refinement of initial detector predictions through learned geometric transformations. The framework integrates three CNN backbones, YOLOv12, VGG16, and ConvNeXt-V2, with three deep RL agents (DQN, PPO, and SAC), where the agent state combines visual embeddings, normalized bounding-box coordinates, and detector confidence, and optimization is driven by a continuous ΔIoU reward function. Extensive experiments across nine backbone agent combinations demonstrate that RL-based refinement consistently outperforms static detectors. The YOLOv12 + DQN configuration achieves the highest localization accuracy, with a Mean IoU of 0.969 ± 0.071, a 100% localization success rate (IoU ≥ 0.5), and convergence typically within a single refinement step. In contrast, VGG16 and ConvNeXt-V2 based configurations yield Mean IoU values ranging from 0.60 to 0.75, while requiring substantially higher computational cost. Importantly, the YOLOv12 + DQN model maintains high operational efficiency, completing inference in ≈0.09 s per sample, making it suitable for real-time agricultural applications. Beyond algorithmic performance, we deploy the proposed model within an interactive decision support dashboard that visualizes bounding-box refinement trajectories, Grad-CAM attention dynamics, and class-level localization statistics, facilitating transparent model interpretation and practical adoption by agricultural practitioners. Overall, the proposed RL-guided active localization framework delivers substantial accuracy gains, low-latency performance, and operational interpretability, establishing a scalable and actionable solution for next-generation precision agriculture systems.","author":[{"family":"Kheir","given":"Ahmed"},{"family":"Kolluru","given":"Vinothkumar"},{"family":"Adli","given":"Gerald"},{"family":"Ali","given":"Marwa"},{"family":"Ding","given":"Zheli"},{"family":"Koubaa","given":"Anis"},{"family":"Feike","given":"Til"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.inpa.2026.04.007","URL":"https://doi.org/10.1016/j.inpa.2026.04.007","source":"crossref"},{"id":"doi:10.1007/s11119-025-10260-2","type":"article-journal","title":"Delineation of management zones in clover-grass for site-specific management of subsequent crops","abstract":"Abstract Modern agriculture faces the challenges of food security with increasing world population and the need to protect natural resources. Organic farming is known as more environmentally friendly, but has a deficit of around 80% yield compared to conventional farming due to lower availability of nitrogen (N) fertilizer. Site-specific management based on subfields can improve the use efficiency of nitrogen, but organic agriculture lacks fast dissolving N fertilizer. Spatial differences must therefore even out strategically within the crop rotation. Between 2020 and 2023 a trial for management zone (MZ) delineation was developed on three organically farmed fields located in northwest Germany. The clover-grass period and the subsequent cereal crop were observed. During the clover-grass period, Unmanned Aerial Vehicle (UAV)-based images were recorded for calculation of the normalized difference red edge index (NDRE), which was used to divide the study sites into site-adapted management zones using a fuzzy-C-means clustering algorithm. On each of the three fields, a subfield with high productivity and one with low productivity were identified. The more productive subfield during clover-grass-period also had higher cereal yield on all fields. At one field, the high productive MZ was characterized by lower terrain elevation and higher clay content, while on other fields, the differences in yield might be due to land use history and soil depth. This research shows a promising approach to delineate management zones of clover-grass based on NDRE index and offers the potential of site-specific management withing the crop rotation.","author":[{"family":"Reuter","given":"Tobias"},{"family":"Nahrstedt","given":"Konstantin"},{"family":"Jarmer","given":"Thomas"},{"family":"Broll","given":"Gabriele"},{"family":"Trautz","given":"Dieter"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10260-2","URL":"https://doi.org/10.1007/s11119-025-10260-2","source":"crossref"},{"id":"doi:10.1079/ab.2026.0015","type":"article-journal","title":"A multimodal AI-based decision support framework for precision agriculture: Enhancing accessibility for low literate farmers","abstract":"Abstract Background : Due to limited literacy, smallholder farmers in agriculture in developing regions continue to encounter challenges, hindering their ability to leverage AI-driven and digital technologies. Most of the conventional platforms are dependent on text-based interfaces, excluding low-literate users from accessing essential decision support services. Methods : A multimodal AI framework is proposed in this study that aims at enhancing the usability and accessibility for smallholder farmers in rural regions. Different accessibility features like localized voice prompts, AI-powered advisory modules incorporating computer vision, and culturally adapted iconography and recommendation engines are integrated for crop disease identification, market price forecasting, and fertilizer scheduling. A mixed-method methodology was conducted using ISO 9241-11 usability standards and participatory design methodologies involving 100 farmers (50 illiterate and 50 semi-Illiterate). Results : The results showed obvious improvement in user experience and inclusivity that integrated multimodal interfaces. Cross-task comparative results indicate improved usability, with task success rates of 62% for illiterate and 82% for semi-literate users. The AI modules achieved strong disease detection performance, with an average accuracy of 87.7%. Conclusions : The results showed the effectiveness of the described framework to fill literacy gaps of farmers in the AI agricultural domain.","author":[{"family":"Maqood","given":"Imran"},{"family":"Jan","given":"Sadeeq"},{"family":"Ahmad","given":"Sadique"},{"family":"Alluhaidan","given":"Ala"},{"family":"Anwar","given":"Muhammad"},{"family":"Haq","given":"Qazi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1079/ab.2026.0015","URL":"https://doi.org/10.1079/ab.2026.0015","source":"crossref"},{"id":"doi:10.1007/s11119-026-10326-9","type":"article-journal","title":"Spatial variability in soil characteristics is associated with Vidalia onion pungency and yield","abstract":"Vidalia onions are known globally for their characteristically low pungencies and remain a vital part of the economy in Southeast Georgia, USA, where they are grown. Previous research has shown that variability in soil properties (e.g. soil type, texture, and sulfur concentration) can affect onion pungency. The objectives of this study were to (i) examine the spatial variability in soil properties within four Vidalia onion fields during the 2020 and 2021 growing seasons, and (ii) identify relationships between soil properties and onion yield and flavor profile. Each 10-ha field was intensely sampled, collecting corresponding soil and onion samples. Onion yields ranged from 8 to 66 Mg ha− 1, and while site-year specific relationships were identified in association with yield, these relationships were not consistent across site-years. However, pungency as determined by pyruvic acid content ranges from 0.78 to 6.98 µmol mL− 1 and was positively associated with soil organic matter and pH in both surface and subsurface soil horizons and negatively correlated with the depth to the subsurface claypan. Meanwhile, pungency showed a mixed or nonsignificant relationship to soil sulfur in the surface soil horizons, suggesting sulfur availability is determined by the interaction of soil properties and not absolute soil sulfur content. These results indicate that the physical and chemical differences among soils within individual fields were sufficient to affect nutrient availability and alter onion flavor. Overall, the results of this study point to the utilization of site-specific fertilizer recommendations and management plans to ensure consistency of onion quality in the Vidalia growing region.","author":[{"family":"Jackson","given":"Daniel"},{"family":"Lessl","given":"Jason"},{"family":"Bastos","given":"Leonardo"},{"family":"Levi","given":"Matthew"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10326-9","URL":"https://doi.org/10.1007/s11119-026-10326-9","source":"crossref"},{"id":"doi:10.19103/as.2024.152.23","type":"article-journal","title":"Developments in precision pasture management systems","abstract":"Pasture management is an important aspect of dairy farming, making up a significant portion of the dairy cow diet in many countries. Where grazing is the primary feed source, it relies on the quantity and nutritive value of grass. Pasture management involves a number of aspects, such as the measurement of pasture quantity and quality. It also increasingly uses data to make grazing management decisions, e.g. in grass allocations, in combination with grass growth predictions in order to refine overall management decisions. This chapter presents an overview of the various technologies used in pasture management with particular focus on new precision technologies.","author":[{"family":"Obrien","given":"B"},{"family":"Hennessy","given":"D"},{"family":"Ruelle","given":"E"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2024.152.23","URL":"https://doi.org/10.19103/as.2024.152.23","source":"crossref"},{"id":"doi:10.1007/s11119-026-10333-w","type":"article-journal","title":"Robust Spectral Classification Under Sample Type and Seasonal Variability: A Proximal Remote Sensing Approach for Grapevine Cultivar Discrimination","abstract":"Abstract Purpose The discrimination of grapevine cultivars is an important yet underexploredtopic in precision viticulture. This study evaluated three aspects of grapevinecultivar classification and model training strategies: (1) the influence ofseasonal variability and data collection strategy; (2) model generalisabilityacross sample types; and (3) the combined impact of temporal and sample-typevariation on classification performance. Methods Spectral data from leaf and canopy samples were used to classify six grapevinecultivars: Currant, Merbein, Muscat, Selma Pete, Sugra-39, and Sultana. Elevendataset configurations were evaluated using ten machine learning and deeplearning classifiers. Performance was assessed using F1 score, balancedaccuracy (BACC), Matthews Correlation Coefficient (MCC), and Area Under theReceiver Operating Characteristic curve (AUC). The Sum of Ranking Differences(SRD) method identified the most robust classifiers across training strategies. Results Leaf spectra collected in December—coinciding with the fruit set phenologicalstage—provided the highest classification accuracy. Models showed limitedgeneralisability across data scales (i.e., sample types), with substantialdeclines in accuracy when trained on one type and tested on another. Combiningleaf and canopy spectra in the training data improved performance but remainedlower than when models were trained and tested on the same sample type. SRDanalysis identified Support Vector Machine (SVM) and 1D Convolutional NeuralNetwork (CNN) as the most robust classifiers. SVM models achieved F1 scores of0.67–1.00, BACC of 0.74–0.98, MCC of 0.65–0.90, and AUC values of 0.87–0.94.The 1D CNN models also showed high performance (F1: 0.62–0.98; BACC: 0.79–0.99;MCC: 0.57–0.97; AUC: 0.93–1.00). Conclusion These findings highlight the importance of temporal and sample-typeconsiderations when developing spectral classification models for grapevinecultivars. Overall, the results provide a foundation for a scalable andcommercially viable approach to cultivar mapping, supporting more precisevineyard management.","author":[{"family":"Loggenberg","given":"Kyle"},{"family":"Strever","given":"Albert"},{"family":"Münch","given":"Zahn"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10333-w","URL":"https://doi.org/10.1007/s11119-026-10333-w","source":"crossref"},{"id":"doi:10.51193/ijaer.2025.11611","type":"article-journal","title":"PRECISION AGRICULTURE IN HILLY REGIONS: A BIBLIOMETRIC ASSESSMENT OF GLOBAL RESEARCH TRENDS","abstract":"Mountain farming sustains rural livelihoods but faces challenges from steep terrain, soil erosion, and climate change. Precision Agriculture (PA), using digital tools and remote sensing, offers solutions but remains underexplored in mountain contexts compared to large-scale flatland farming. This study presents a bibliometric analysis of PA research in hilly regions using Web of Science data time span of (2000–2025). The analysis carried out with 42,548 records appeared in search initially and 2111 paper globally on mountain and Precision agriculture has been considered for screening and 490 publications were reviewed and considered for the analysis, since the these were the only article fulfilling the study objective and direction. Results show steady growth peaking in 2021, with Ethiopia and China as leading contributors. Core journals such as Land Degradation &amp; Development and Remote Sensing dominate the field. Keyword analysis reveals three clusters: environmental conservation, technological integration, and socio-economic adoption. However, gaps persist in cost–benefit assessments, adoption studies, and mountainspecific policy frameworks. Overall, PA shows strong potential for sustainable mountain farming, but greater focus on terrain-sensitive, smallholder-centered innovations is needed. To address this gap and to understand the dynamics of PA, the paper the present study conducts a bibliometric analysis of PA related to mountain farming drawing on Web of science data from 2000-2025.","author":[{"family":"Limbu","given":"Namsa"},{"family":"Rizal","given":"Dr"},{"family":"Debnath","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.51193/ijaer.2025.11611","URL":"https://doi.org/10.51193/ijaer.2025.11611","source":"crossref"},{"id":"doi:10.54963/ia.v2i1.2334","type":"article-journal","title":"Soil Nutrient Assessment Using Ion-Selective Electrode-Based Nutrient Analyzer for Precision Agriculture","abstract":"Rapid and accurate soil nutrient assessment is critical for precision agriculture. This study presents a portable and intelligent soil nutrient analyzer based on ion-selective electrodes (ISE) for rapid, on-site estimation of potassium, nitrate, and chloride. Unlike image-based or machine learning approaches that rely on indirect inference, the proposed system directly measures ion activity using electrochemical sensing, ensuring higher reliability under field conditions. The device integrates sensing, signal conditioning, self-calibration using polynomial regression, and wireless data transmission for real-time soil health assessment. A total of 546 soil samples collected from diverse agricultural locations in Dhanbad district, India, were used for validation, with measurements compared against standard laboratory methods including flame photometry and UV-Vis (ultraviolet-visible) spectrophotometry. The developed system achieved high correlation coefficients of 0.994 (potassium), 0.933 (nitrate), and 0.946 (chloride). Statistical evaluation using RMSE (root mean square error), measurement uncertainty, and hypothesis testing confirms the robustness of the calibration model. The study highlights the advantages of direct sensing over image-based prediction methods, particularly in terms of accuracy, environmental robustness, and practical deployment. Limitations related to sensor drift, soil heterogeneity, and field conditions are also discussed. The proposed system provides a scalable and cost-effective solution for precision agriculture and real-time soil monitoring.","author":[{"family":"Mishra","given":"Preity"},{"family":"Chaulya","given":"Swades"},{"family":"Kumari","given":"Anubhuti"},{"family":"Kumar","given":"Naresh"},{"family":"Kumar","given":"Vikash"},{"family":"Rawani","given":"Vijay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.54963/ia.v2i1.2334","URL":"https://doi.org/10.54963/ia.v2i1.2334","source":"crossref"},{"id":"doi:10.3390/agriculture15212296","type":"article-journal","title":"Computer Vision for Site-Specific Weed Management in Precision Agriculture: A Review","abstract":"Weed management is always a challenge in crop production, exacerbated by the issue of herbicide resistance. Excessive herbicide application not only leads to the development of herbicide resistance weeds but also causes environmental problems. In precision agriculture, innovative weed management methods, especially advanced remote sensing and computer vision technologies for targeted herbicide applications, i.e., site-specific weed management (SSWM), have recently drawn a lot of attention. Challenges exist in accurately and reliably detecting diverse weed species under varying field conditions. Significant efforts have been made to advance computer vision technologies for weed detection. This comprehensive review provides an in-depth examination of various methodologies used in developing weed detection systems. These methodologies encompass a spectrum ranging from traditional image processing techniques to state-of-the-art machine and deep learning models. The review further discusses the potential of these methods for real-time applications, highlighting recent innovations, and identifying future research hotspots in SSWM. These advancements hold great promise for further enhancing and innovating weed management practices in precision agriculture.","author":[{"family":"Singh","given":"Puranjit"},{"family":"Zhao","given":"Biquan"},{"family":"Shi","given":"Yeyin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15212296","URL":"https://doi.org/10.3390/agriculture15212296","source":"crossref"},{"id":"doi:10.1007/s11119-025-10292-8","type":"article-journal","title":"Digital mapping of selected soil health indicators from the root zone and their relationship with rainfed corn yield in Texas vertisols","abstract":"Abstract Assessment of spatial variability of soil health indicators (SHI) from the root zone, not just the topsoil, is crucial for precise farm management decisions. We predicted the spatial distribution of soil organic carbon (SOC), inorganic carbon (SIC), total nitrogen (total-N), nitrate nitrogen (NO 3 -N), C: N ratio, phosphorus (PO 4 ), soil pH, and soil moisture (SM) from the root zone using soil samples from 0–15, 15–30, 30–60, 60–90 cm depths, apparent soil electrical conductivity (EC a ), topography, and a random forest (RF) model. The SHI and corn yield relationship was modeled and mapped, and the field was divided into soil health zones (SHZ) which were assessed for their agronomic significance. The RF model performed very well in predicting SM, pH, and SIC (R 2 up to 0.81), whereas PO 4 and total-N were weakly predicted (R 2 &lt; 0.20) based on 30% test data. The EC a and terrain attributes (mrvbf, normht, sagawi, and fdem) were the most important predictors of SHI. The RF model was robust in quantifying the relationship between SHI and corn yield (R 2 = 0.64; RMSE = 0.80 Mt/ha) where SM appeared as the main predictor of yield variations followed by SIC, NO 3 -N, and pH. The field was divided into four SHZs, and yield responses from these zones were different. Results from this study can be useful for farm management decisions such as in soil health monitoring and variable-rate fertilization, and as a reference to future soil health and precision agriculture research.","author":[{"family":"Adhikari","given":"Kabindra"},{"family":"Smith","given":"Douglas"},{"family":"Hajda","given":"Chad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10292-8","URL":"https://doi.org/10.1007/s11119-025-10292-8","source":"crossref"},{"id":"doi:10.4018/979-8-3373-5283-1.ch003","type":"article-journal","title":"Revolutionizing Farming With Agriculture 4.0","abstract":"The emergence of Agriculture 4.0 signifies a pivotal transformation in farming, driven by the adoption of advanced technologies to address essential issues like global food security, environmental sustainability, and climate resilience. This chapter explores deeply the foundational technologies underpinning Agriculture 4.0, including the Internet of Things (IoT), Artificial Intelligence (AI), robotics, big data analytics, and automation. These innovations collectively redefine agricultural methodologies, enhancing efficiency, precision, and sustainability. Furthermore, this chapter presents a case study on smart plant care that demonstrates the practical application of Agriculture 4.0 principles. This system integrates real-time sensor data with ML algorithms to optimize irrigation and plant health. This chapter provides a comprehensive guide to Agriculture 4.0 technologies and strategies, guiding the conversion of traditional farming methods into a resilient, data-oriented, and sustainable enterprise.","author":[{"family":"Mansour","given":"Ahmed"},{"family":"Alkady","given":"Yasmin"},{"family":"Elashmawi","given":"Walaa"},{"family":"Elbahnasaw","given":"Magdy"},{"family":"Shamseldin","given":"Tamer"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-5283-1.ch003","URL":"https://doi.org/10.4018/979-8-3373-5283-1.ch003","source":"crossref"},{"id":"doi:10.33545/26646064.2025.v7.i3c.626","type":"article-journal","title":"Economic viability of precision agriculture technologies for medium-scale wheat growers","abstract":"From an economic angle, precision agriculture promises higher returns through input savings and yield gains, but whether the promise holds for medium-scale wheat growers (10-50 hectares) in India is far from settled. This research assessed the economic viability of five Precision Agriculture (PA) technologies, variable-rate seeding, GPS-guided fertilizer application, drone monitoring, yield mapping, and soil sensors, among 186 wheat growers in Karnataka and Gujarat during 2022-2023. A structured survey collected data on adoption costs, input savings, yield changes, and Benefit-Cost Ratios (BCR). The mean BCR across all PA technologies was 1.34, but this masked wide variation by farm size: BCR exceeded 1.0 (break-even) only above 15 hectares for most technologies. GPS-guided fertilizer had the highest adoption rate (22.3%) and best BCR (1.78), while drone monitoring had the lowest adoption (8.4%) and a BCR of only 0.92, reflecting high equipment costs. A logistic regression found that farm size, education, and access to extension services were the strongest predictors of PA adoption. These results suggest that PA is economically viable for wheat farms above 15 hectares, but smaller operations need cooperative or rental models to achieve positive returns.","author":[{"family":"Shinde","given":"Devendra"},{"family":"Barua","given":"Keshav"},{"family":"Bora","given":"Omkar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.33545/26646064.2025.v7.i3c.626","URL":"https://doi.org/10.33545/26646064.2025.v7.i3c.626","source":"crossref"},{"id":"doi:10.1007/s11119-026-10380-3","type":"article-journal","title":"Using planetscope imagery to evaluate herbicide efficacy in maize (Zea mays) through post-application weed detection","abstract":"Abstract Background Optimizing herbicide efficacy is increasingly critical due to the absence of new herbicide modes of action (MOA) and their widespread overuse. This study developed a satellite-based approach to map herbicide control failures for evaluating efficacy, based on the hypothesis that effective control reduces crop-weeds co-existence and thus spectral-spatial heterogeneity over time, whereas low efficacy increases it. Methods In controlled experimental maize plots (2022–2023), analysis of Unmanned Aerial Vehicle (UAV) multispectral imagery characterized weed-suppression dynamics following application of two herbicides with different MOA. Satellite imagery was processed to select gray-level co-occurrence matrix (GLCM) texture features sensitive to herbicide-induced pixel differences. Features selected were used to compare two satellite-based approaches for mapping herbicide control failures cover (%) across seven commercial maize fields: (i) a rule-based framework and (ii) UAV to satellite upscaling using a Random Forest model. Results Results showed that by 10 days after spraying (DAS), herbicide effects were uniformly expressed in both MOA, enabling separation between damaged and healthy weeds in UAV images. At the satellite scale, Near-Infrared (NIR)-based GLCM variance and mean were the most sensitive indicators of weed suppression. Using these features and Normalized Difference Vegetation Index (NDVI) from 10 and 14 DAS, a rule-based framework showed better performance compared to UAV to satellite upscaling, achieving within field precision and recall of 0.71 both, and between fields agreement with a coefficient of determination (R 2 ) of 0.97 and root mean square error (RMSE) of 1.86 (%). Conclusions These results demonstrate that rule-based GLCM framework provide an effective tool for evaluating herbicide control efficacy using PlanetScope satellite image.","author":[{"family":"Aharon","given":"Shlomi"},{"family":"Lati","given":"Ran"},{"family":"Eizenberg","given":"Hanan"},{"family":"Cohen","given":"Yafit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10380-3","URL":"https://doi.org/10.1007/s11119-026-10380-3","source":"crossref"},{"id":"doi:10.2174/9798898813963126010008","type":"article-journal","title":"Precision Agriculture Practices for Crop Yield Management with AI Models","abstract":"Advanced computational techniques have revolutionized precision agriculture by enabling information-based strategies and forecasting algorithms for optimizing crop yield. This chapter discusses the integration of artificial intelligence models, such as machine learning and deep learning, with precision farming techniques to reduce ecological footprints and increase agricultural productivity. Some of the main topics are the use of Remote Sensing (RS), Geographic Information Systems (GIS), Global Positioning System (GPS), and Internet of Things (IoT) technologies to monitor agricultural productivity, weather patterns, and soil conditions on a continuous basis. AI applications under scrutiny include predictive modelling and optimisation methods for crop productivity forecasting. This chapter further discusses the issues of incorporating AI in agriculture, specifically with regard to data precision, computational power, and economics, while highlighting emerging solutions and future developments. The ultimate target is to exemplify AI's revolutionary capacity to be used in farming activities, aimed particularly at the rising necessity of environmentally responsible food production that would respond to global problems, including climate change and population growth.","author":[{"family":"Ratan","given":"Rishikesh"},{"family":"Singh","given":"Arshdeep"},{"family":"Rawat","given":"Krishna"},{"family":"Monga","given":"Danish"},{"family":"Tripathi","given":"Adarsh"},{"family":"Sinha","given":"Sakshi"},{"family":"Patel","given":"Jyotsana"},{"family":"Goyal","given":"Amish"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898813963126010008","URL":"https://doi.org/10.2174/9798898813963126010008","source":"crossref"},{"id":"doi:10.54963/ia.v2i1.100190","type":"article-journal","title":"Crop Yield Prediction Using Precision Agriculture and Smart Farming Technologies: A Systematic Review and Future Research Trends","abstract":"The use of crop yield predictions is essential in today's agricultural systems as the global food system is facing increased pressures from climate change, soil degradation, and water scarcity. Precision agriculture is based on the development of data-driven solutions for yield forecasting using remote sensors, IoT (Internet of Things) devices, machine learning, and crop growth models. This systematic literature review synthesizes recent research (2020–2025) concerning crop yield prediction by reviewing what types of data are available, factors affecting yield, what predictive models have been developed, and how those models are used in field, regional, and large-scale agricultural situations. This review also demonstrates how climatic and hydroclimatic variability interact with soil properties and management practices to create yield outcomes, while evaluating the accuracy and performance of statistical, machine learning, deep learning, and hybrid modelling approaches. The study concludes that multi-modal data fusion, real-time data assimilation, and hybrid physics/AI modelling approaches improve prediction accuracy and robustness. Ongoing challenges include (but are not limited to) model transferability, the lack of standardized benchmark datasets for model development and evaluation, insufficient real-time integration of multiple types of information to assist in yield prediction, and difficulty in explaining how advanced AI models develop yield predictions. The authors propose a future research agenda based on the findings of this study that will provide a standard multimodal dataset for the development of explainable AI, a scalable edge/cloud architecture for model deployment, and models that can be transferred across crops, climates, and production systems.","author":[{"family":"Safy","given":"Mohammed"},{"family":"Hassan","given":"Mariam"},{"family":"Shaaban","given":"Abdel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.54963/ia.v2i1.100190","URL":"https://doi.org/10.54963/ia.v2i1.100190","source":"crossref"},{"id":"doi:10.21603/2308-4057-2026-2-680","type":"article-journal","title":"Precision agriculture as a viable means of enhancing sustainable agricultural production","abstract":"Effective management of finite resources in precision agriculture requires efficient technologies to generate reliable data about crops, pastures, soil, water sources, climate, pests, diseases, and other variables. These data enable farmers to make informed decisions to enhance efficiency and make their production more sustainable. This review aimed to assess the technological advances in precision agriculture in terms of their benefits, constraints, and potential for sustainable farming practices. A total of 132 scientific papers were selected, analyzed, and discussed to explore the current status and the future of precision agriculture in relation to sustainable development. This review covers technologies utilized in planting, crop monitoring, resource management, decision support systems, and automation. The application of artificial intelligence (AI)-driven technologies, including machine learning, computer vision, and sensor technologies, transforms traditional farming and contributes to resolving its limitations by providing farmers with real-time data and actionable insights. Ethical considerations, data security, and the digital divide are among the key challenges needing attention. Interdisciplinary collaboration is also needed to tackle complex issues associated with the sustainable implementation of advanced technologies, including AI in precision agriculture. Precision agriculture technologies have a transformative impact on traditional farming. The integration of AI contributes to higher productivity and efficiency, as well as long-term sustainability of farming practices, ensuring food security for the growing population.","author":[{"family":"Diakite","given":"Simbo"},{"family":"Kavhiza","given":"Nyasha"},{"family":"Saquee","given":"Francess"},{"family":"Pakina","given":"Elena"},{"family":"Zargar","given":"Meisam"},{"family":"Diarra","given":"Ousmane"},{"family":"Norman","given":"Prince"},{"family":"Traore","given":"Brahima"},{"family":"Samake","given":"Fasse"},{"family":"Daou","given":"Cheickna"},{"family":"Babana","given":"Amadou"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21603/2308-4057-2026-2-680","URL":"https://doi.org/10.21603/2308-4057-2026-2-680","source":"crossref"},{"id":"doi:10.1163/9789004725232_093","type":"article-journal","title":"A new method for satellite-based derivation of site-specific yield potentials of winter wheat for precision farming applications","abstract":"Accurate site-specific yield potential determination is essential for sustainable agricultural practices, enabling efficient resource use and reducing environmental impacts. This study presents a satellite-based method to predict winter wheat yield using a six-year dataset from conventional and organic farming systems. Two models were evaluated: a non-linear support vector machine (SVM) model and a multilinear model with stepwise backward regression. The SVM model demonstrated higher predictive accuracy, with an R2 of 0.80, a MAE of 0.58 t/ha, and an RMSE of 0.79 t/ha, compared to the multilinear model (R2=0.75, MAE=0.69 t/ha). Expanding the dataset to include diverse soils, climates, and growth stages could further enhance model robustness and applicability.","author":[{"family":"Hagn","given":"L"},{"family":"Mittermayer","given":"M"},{"family":"Schuster","given":"J"},{"family":"Leßke","given":"F"},{"family":"Hülsbergen","given":"KJ"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_093","URL":"https://doi.org/10.1163/9789004725232_093","source":"crossref"},{"id":"doi:10.1007/s11119-026-10362-5","type":"article-journal","title":"Evaluating transformer- and CNN-based semantic segmentation models for sunflower inflorescence identification using a UAV RGB orthomosaic","abstract":"Abstract Purpose Monitoring sunflower inflorescence development is critical for yield assessment and precision crop management. While convolutional neural networks (CNNs) have shown promise in UAV-based crop segmentation, the behavior and practical implications of recent vision transformer architectures for inflorescence-level identification and spatial pattern analysis remain insufficiently explored. This study aims to systematically evaluate transformer-based and CNN-based models for sunflower inflorescence detection and to assess their capability for field-scale spatial characterization. Methods A high-resolution UAV orthomosaic was used to evaluate state-of-the-art transformer-based models (SegFormer, Dense Prediction Transformer (DPT), and UPerNet) and CNN-based models (U-Net, DeepLabv3+, and PSPNet). A controlled experimental framework was adopted, in which spatially disjoint training and testing subsets were extracted from the same production field to capture realistic within-field heterogeneity. All models were evaluated using standard performance metrics, including accuracy, precision, recall, F-score, and IoU. Beyond model-level performance comparison, targeted ablation analyses were conducted to examine the influence of key methodological choices, including loss function selection, patch overlap, and data augmentation strategies. In addition, explainable AI analysis (Grad-CAM) and computational cost assessments were performed. Results Among the 15 evaluated model configurations, the DPT model with the Twins-PCPVT-Base encoder achieved the highest segmentation performance (F-score: 0.946, IoU: 0.897) and demonstrated the most stable behavior across validation and spatially disjoint testing subsets. Explainable AI analysis using Grad-CAM revealed distinct attention patterns between transformer- and CNN-based models, while computational cost analysis highlighted trade-offs between segmentation accuracy and efficiency. To enhance agronomic relevance, object-based segmentation outputs were aggregated into field-scale spatial representations using complementary inflorescence-derived indicators describing inflorescence abundance and size. In addition, a weighted head area index (WHAI) was further introduced to integrate count- and area-based information, providing a balanced, image-derived spatial descriptor of within-field variability in inflorescence development. Conclusions Taken together, the results indicate that transformer-based semantic segmentation, when integrated with object-level spatial indicators, enables consistent and interpretable field-scale characterization of within-field variability in sunflower inflorescence development, thereby enhancing the agronomic relevance of UAV-based image analysis for precision agriculture applications.","author":[{"family":"Yildirim","given":"Esra"},{"family":"Colkesen","given":"Ismail"},{"family":"Sefercik","given":"Umut"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10362-5","URL":"https://doi.org/10.1007/s11119-026-10362-5","source":"crossref"},{"id":"doi:10.1007/s11119-025-10242-4","type":"article-journal","title":"Low-cost automated generation of application maps for control of Rumex Obtusifolius in grasslands","abstract":"The majority of newly developed sprayers now feature advanced capabilities, allowing herbicide application with centimeter-level precision, potentially reducing herbicide use by up to 90%. However, accurately identifying the precise locations to spray, known as the application map, remains a significant research challenge. Recently, both commercial providers and research institutions have proposed various drone-based methods for generating application maps. Despite these advancements, practical adoption is limited, primarily due to regulatory constraints and the high costs associated with the technology. A promising approach to increasing the adoption of these technologies lies in the utilization of more cost-effective hardware solutions. In this paper, we introduce and evaluate a novel detection method specifically designed for identifying Rumex obtusifolius (sorrel) and for automatically generating application maps that are compatible with most GNSS-enabled sprayers. To this end, we present a new metric for treatment success, termed the treatment F1-score, and conduct a comparative analysis of the performance of the DJI Mini 2 and the DJI Matrice 350 RTK using our proposed system, achieving treatment F1-scores of 0.61% and 0.65% , respectively. The ability of this system to deliver good performance utilizing significantly less expensive hardware than typically employed in similar applications suggests a potential for broader adoption, particularly given the unexpectedly modest performance gap of only 4 percentage points in the treatment F1-score. Under controlled experimental conditions, we observed reductions in herbicide use of up to 97% without missing any targets. In practical applications within real-world meadows, a 40% reduction in herbicide consumption was achieved with a treatment accuracy of 85% . These findings underscore the substantial potential for future technological advancements. The standalone object detector achieves a mean Average Precision (mAP) of 67.4% and an F1-score of 62%, demonstrating robust performance even on out-of-distribution drone data collected by other researchers. Still, the performance of the object detection algorithm is identified as a critical bottleneck in the system. To facilitate further research and development in this domain, we have made our training dataset available for download.","author":[{"family":"Eichhorn","given":"Frederick"},{"family":"Kneer","given":"Sebastian"},{"family":"Görges","given":"Daniel"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10242-4","URL":"https://doi.org/10.1007/s11119-025-10242-4","source":"crossref"},{"id":"doi:10.1007/s11119-025-10235-3","type":"article-journal","title":"Shared digital agricultural technology on farms in Southern Germany-analysing farm and socio-demographic characteristics in an inter-farm context","abstract":"Abstract Introduction Up till now, digitalisation in agriculture has almost only been discussed in the context of large farms. However, sooner or later, ongoing digitalisation will reach the agricultural sector as a whole. Indeed, even smaller farms can also benefit from the opportunity and make profitable use of digital agricultural technology by adopting inter-farm organisational forms e.g. collaboration between farmers or contractor services. This article seeks to gain a better understanding of the digital transformation process and to validate relevant forecasts by analysing farm and socio-demographic characteristics that have a possible influence on the likelihood of inter-farm use of digital agricultural technology in general and regardless of the organisational form. Methodological approach Univariate analysis approaches and bivariate analysis approaches were selected to describe the sample. A binary regression analysis was used to analyse the results of a written online survey of farmers from southern Germany. The characteristics listed in hypotheses H1 to H10 serve as a theory-based conceptual framework for the statistical analysis within the binary logistic regression model. Results The results of this study are based on a survey sample of 165 farmers, 36.4 % (n=60) of whom use digital agricultural technology on an inter-farm basis. The sample covers n=89 farms from Baden-Württemberg and n=76 from Bavaria. Most of the farmers (87.3 %) considered themselves perfectly capable of using digital technologies confidently after it had been explained to them once (x̅=2.52, s=1.02, scale: 1=completely true to 6=not true at all), with 38.2 % of them using digital agricultural technology across farms, that means they use digital agricultural technology together. Certain factors which can influence the likelihood of inter-farm use of digital agricultural technology in small-scale regions were identified using the binary logistic regression model to analyse the relevant operational and socio-demographic characteristics. Using this methodological approach, eight predictors were identified, three of which have a positive influence on the likelihood of inter-farm use of digital agricultural technology: the availability of two external labourers, the farm's focus on “finishing” or on “other” activities such as taking horses at livery or fattening livestock. Farms that have less than 200 hectares, have no clear succession plan, or whose farm managers are under 30 years old are less likely to use inter-farm digital agricultural technology. Conclusions In this study, several influencing factors were identified that can play a role in the shared use of digital agricultural technology, especially between farmers in small-scale regions in southern Germany. The empirical results obtained from the binary logistic regression show both positive and negative influences on the likelihood of inter-farm use of digital agricultural technology. Forms of cooperation between farmers play a central role in the establishment and use of capital-intensive digital agricultural systems on farms in southern Germany. The study therefore emphasises that the widespread and economical use of digital agricultural technology in small-scale regions can be achieved quickly, especially through established collaborations between farmers and other stakeholders such as machinery rings or agricultural contractors.","author":[{"family":"Gscheidle","given":"Michael"},{"family":"Petersen","given":"Thies"},{"family":"Doluschitz","given":"Reiner"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10235-3","URL":"https://doi.org/10.1007/s11119-025-10235-3","source":"crossref"},{"id":"doi:10.1007/s11119-025-10228-2","type":"article-journal","title":"Forecasting field rice grain moisture content using Sentinel-2 and weather data","abstract":"Abstract Optimizing the timing of rice paddy drainage and harvest is crucial for maximizing yield and quality. These decisions are guided by rice grain moisture content (GMC), which is typically determined by destructive plant samples taken at point locations. Providing rice farmers with predictions of GMC will reduce the time burden of gathering, threshing and testing samples. Additionally, it will reduce errors due to samples being taken from unrepresentative areas of fields, and will facilitate advanced planning of end-of-season drain and harvest timing. This work demonstrates consistent relationships between rice GMC and indices derived from Sentinel-2 satellite imagery, particularly those involving selected shortwave infrared and red edge bands (r=0.84, 1620 field samples, 3 years). A methodology was developed to allow forecasts of grain moisture past the latest image date to be provided, by fusing remote sensing and accumulated weather data as inputs to machine learning models. The moisture content predictions had root mean squared error between 1.6 and 2.6% and $$\\hbox {R}^2$$ of 0.7 with forecast horizons from 0 to 28 days. Time-series grain moisture dry-down predictions were summarized per field to find the optimal harvest date (22% grain moisture), with an average RMSE around 6.5 days. The developed methodology was operationalized to provide rice growers with current and projected grain moisture, enabling data-driven decisions, ultimately enhancing operational efficiency and crop outcomes.","author":[{"family":"Brinkhoff","given":"James"},{"family":"Dunn","given":"Brian"},{"family":"Dunn","given":"Tina"},{"family":"Schultz","given":"Alex"},{"family":"Hart","given":"Josh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10228-2","URL":"https://doi.org/10.1007/s11119-025-10228-2","source":"crossref"},{"id":"doi:10.1163/9789004725232_046","type":"article-journal","title":"Drone-based weed mapping at the species level for precision weed control in maize and tomato fields","abstract":"Accurate weed identification is crucial for effective implementation of precision weed control strategies. This research evaluated several convolutional neural networks and vision transformer models aiming to map nine common weed species in drone-based RGB images collected in earlyseason maize and tomato fields. The Droneweed dataset (>65 000 labels) was used to train, validate and test the models. Swin-T showed most robust performance (98% F1-score) and EfficientNet-B0 the lowest computational cost, though YOLO-v8 achieved superior classification results (97.5% overall accuracy) and better speed-accuracy balance. Consequently, YOLO-v8m detector was applied to generate treatment maps, which reported high potential to reduce herbicide usage by 37% and 43% in both fields, respectively.","author":[{"family":"Mesías-Ruiz","given":"GA"},{"family":"Dorado","given":"J"},{"family":"Castro","given":"AID"},{"family":"Borra-Serrano","given":"I"},{"family":"Peña","given":"JM"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_046","URL":"https://doi.org/10.1163/9789004725232_046","source":"crossref"},{"id":"doi:10.1007/s11119-025-10225-5","type":"article-journal","title":"Box sampling: a new spatial sampling method for grapevine macronutrients using Sentinel-1 and Sentinel-2 satellite images","abstract":"The ability to reduce sampling distance or time is crucial for growers to monitor vineyard nutrients more frequently. Extension specialists often recommend collecting large random samples, but this is frequently overlooked, leading to inaccurate fertilizer recommendations. A novel, one-location square grid area-based sampling method called “box” sampling was developed to capture the overall nutrient distribution within a block, providing guidance for growers on sample collection in vineyards for nutrient monitoring. Box sampling was compared with random and stratified sampling methods at both bloom and veraison for grapevine foliar nitrogen (N%), phosphorus (P%), potassium (K%), magnesium (Mg%), and calcium (Ca%). Box and stratified sampling locations were determined based on Synthetic Aperture Radar (SAR) from Sentinel-1 and Sentinel-2 Normalized Difference Vegetation Index (NDVI) images. SAR and NDVI images were stratified into three variability zones using the k-means + + algorithm. Representative pixels from each zone were sampled using the stratified method, while the junction of these variability zones (30mx30m sampling window) was sampled using the new box method. In 2021 and 2022, these methods were compared against nutrient population parameters in two vineyard blocks. Both methods showed marginal differences in mean, median, and standard deviation, with box sampling consistently capturing a broader range of variations. This was evidenced by the Bhattacharya coefficient, which indicates the overlap between two probability distributions (with values closer to 1 for greater overlap). The coefficient was > 0.80 for N%, P%, and Mg%, and > 0.60 for K% and Ca% at both bloom and veraison. For 14 different commercial vineyards in 2022 and 2023, box sampling accurately captured random nutrient variability for N%, P% and Mg% at both bloom and veraison. However, for K% (at veraison) and Ca% box sampling performed poorly due to high spatial variability. Box sampling reduced the sampling distance and time by 75% compared to random sampling.","author":[{"family":"Trivedi","given":"Manushi"},{"family":"Bates","given":"Terence"},{"family":"Meyers","given":"James"},{"family":"Shcherbatyuk","given":"Nataliya"},{"family":"Davadant","given":"Pierre"},{"family":"Chancia","given":"Robert"},{"family":"Lohman","given":"Rowena"},{"family":"Heuvel","given":"Justine"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10225-5","URL":"https://doi.org/10.1007/s11119-025-10225-5","source":"crossref"},{"id":"doi:10.55248/gengpi.6.0625.2005","type":"article-journal","title":"A Comprehensive Review: How Precision Agriculture is Shaping the Future of Farming in the United States","abstract":"By combining innovative technology which includes Unmanned Aerial Systems (UAS), remote sensing, Global Positioning Systems (GPS), Variable Rate Technology (VRT), and Decision Support Systems (DSS) into conventional agricultural techniques, precision agriculture (PA) is transforming contemporary farming.These developments allow site-specific crop management, best use of inputs, higher production, and less environmental damage.The urgency of sustainable, effective agricultural systems rises as world problems stem from the population increase, climate change, and resource depletion becoming more severe in major economies.Apart from its advantages for production, precision agriculture has acquired momentum in the United States for its possibilities to lower prices, preserve water, and enhance soil quality.Public-private partnerships (PPRs) are fundamental for PA's progress since they help smallholders and resourceconstrained farmers primarily by means of technology development, finance, and distribution.The technological developments underlying PA, the effects on the economy, the adoption environment, and the role of PPPs in scaling innovations are investigated in this review It also looks at the several obstacles to general acceptance including high implementation costs, knowledge gaps, regulatory challenges, data privacy issues, and cultural opposition.Based on current case studies and research, the article presents main ideas and future paths required to overcome these obstacles including policy change, capacity-building activities, and inclusive innovation models: In the end, the analysis emphasizes that, given fair support, precision agriculture has great potential to shape a resilient, profitable, and ecologically sustainable future for American farming.","author":[{"family":"Arayomboa","given":"Tope"},{"family":"Ajiferukea","given":"Oluwafunmilayo"},{"family":"Amusana","given":"Mayowa"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55248/gengpi.6.0625.2005","URL":"https://doi.org/10.55248/gengpi.6.0625.2005","source":"crossref"},{"id":"doi:10.1163/9789004725232_024","type":"article-journal","title":"Metabolic maps from hyperspectral data for precision grape maturation and decision-making","abstract":"This study applied a tomography-like (TL) method to assess the physicochemical properties of grapes in the Douro Wine Region, in the skin, pulp and seed, focusing on soluble solids content (SSC), chlorophyll (CHL), and anthocyanin (ANT). The method demonstrated high accuracy in reconstructing grape tissue characteristics, with Pearson correlation ≥0.97 and low mean square error (≤0.13). Random forest (RF) predicted soluble solids content (SSC), chlorophyll (CHL) in pulp (PU) and anthocyanin (ANT) in seed (SE) with R2≥0.86. Spatial and decision maps revealed the influence of vineyard heterogeneity on grape maturation, aiding site-specific management strategies that enhance harvest quality and align with winemaking objectives.","author":[{"family":"Tosin","given":"R"},{"family":"Rodrigues","given":"L"},{"family":"Santos-Campos","given":"M"},{"family":"Gonçalves","given":"I"},{"family":"Barbosa","given":"C"},{"family":"Santos","given":"F"},{"family":"Martins","given":"R"},{"family":"Cunha","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_024","URL":"https://doi.org/10.1163/9789004725232_024","source":"crossref"},{"id":"doi:10.14232/rard.2024.1-2.17-23","type":"article-journal","title":"The effect of precision agriculture tender on the efficiency of sunflower cultivation","abstract":"By using precision farming systems, we can optimize the use of resources, reducing waste and wastage. The basis of a well-functioning precision agriculture is the immediate and continuous recording of accurate data at the point of cultivation, and then processing and analyzing the data. This requires a change of approach not only by developers and machine manufacturers, but also by farmers, to turn data into decision-support information that can be quickly made available without external assistance. In our work, we aim to provide an economic analysis of the production of sunflower using precision technology. The production of sunflower is studied at an agricultural enterprise whose crop production sector is considered to be at the forefront of the application of precision technologies on a national level. The principle that the more intensive a cropping system, the more advantages there are in using site-specific technology, is fully realized in the enterprise under study. In our work we present the elements of precision technology applied in sunflower production. On this basis, we calculate the costs of cultivation and the income that can be generated. We determine the results with and without subsidies, which can provide information on the actual income-generating capacity.","author":[{"family":"Ferencz","given":"Árpád"},{"family":"Komarek","given":"Levente"},{"family":"Csiba","given":"Anita"},{"family":"Deák","given":"Zsuzsanna"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14232/rard.2024.1-2.17-23","URL":"https://doi.org/10.14232/rard.2024.1-2.17-23","source":"crossref"},{"id":"doi:10.1201/9781003545781-23","type":"article-journal","title":"Deep Learning","abstract":"The burgeoning fields of plant science and agriculture are undergoing a profound transformation driven by the advent of deep learning. This powerful subset of artificial intelligence is enabling researchers to extract unprecedented insights from increasingly large and complex biological datasets, ushering in an era of data-driven discovery and application. This chapter provides a comprehensive review of how deep learning is revolutionizing various aspects of plant research, from high-throughput phenotyping and accurate disease detection to precise yield prediction and insightful genomic analysis. It delves into the specific deep learning architectures and techniques being employed, the types of data utilized, and the tangible impacts on accelerating scientific understanding and developing sustainable agricultural practices. Furthermore, we critically examine the current challenges faced in integrating deep learning into plant science workflows and explore promising future directions that will continue to shape the landscape of plant research in the years to come.","author":[{"family":"Akhtar","given":"Mohd"},{"family":"Saad","given":"Syed"},{"family":"Pandey","given":"Ekta"},{"family":"Kumari","given":"Rinkee"},{"family":"Faizan","given":"Shahla"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-23","URL":"https://doi.org/10.1201/9781003545781-23","source":"crossref"},{"id":"doi:10.2139/ssrn.6967782","type":"manuscript","title":"Application of Machine Learning Models in Precision Agriculture for Crop Diseases Classification","abstract":"The integration of machine learning techniques into modern agriculture has accelerated significantly, enabling more efficient and accurate crop monitoring practices. Deep learning architectures, particularly pre-trained algorithms such as AlexNet, ResNet, VGGNet, and GoogleNet, have demonstrated strong capabilities in precision agriculture applications, including plant disease detection, nutrient assessment, and growth analysis. These applications rely on heterogeneous data sources, ranging from smartphone imagery and UAV-captured images to satellite and sensor data, making analysis both data intensive and computationally challenging. This study introduces a transfer learning based framework that leverages multiple pre-trained models alongside a custom CNN to classify wheat diseases. A dataset comprising over 5,000 images, representing four disease categories and one healthy class, is utilized for training and evaluation. Model performance is assessed using standard metrics such as accuracy, precision, recall, and F1-score. Experimental findings indicate that the ResNet50 based approach achieves superior performance, reaching an accuracy of 93%, highlighting its effectiveness for agricultural disease diagnosis.Proposes a unified transfer learning framework combining pre-trained CNNs and a custom model for wheat disease classification.Utilizes a diverse dataset of 5,000+ images covering multiple disease classes and healthy crops.Demonstrates superior performance of ResNet50, achieving 93% accuracy across evaluation metrics.","author":[{"family":"Patil","given":"Sagar"},{"family":"Reddy","given":"KS"},{"family":"Sutar","given":"Sandeep"},{"family":"Patil","given":"Suchita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.6967782","URL":"https://doi.org/10.2139/ssrn.6967782","source":"crossref"},{"id":"doi:10.5281/zenodo.20453556","type":"article-journal","title":"Spatial Analysis of pH and Salinity in Agricultural Soils in the Province of Pastaza Using Geographic Information Systems (GIS)","abstract":"This repository contains the raw primary data (.csv) supporting the research article \"Spatial Analysis of pH and Salinity in Agricultural Soils in the Province of Pastaza Using Geographic Information Systems (GIS)\". The dataset includes physicochemical laboratory results from 76 surface soil samples (0–20 cm depth) collected across 14 parishes in the province of Pastaza, located in the Ecuadorian Amazon. The data was collected to evaluate the spatial variability of soil properties and to identify edaphic limitations for agricultural production. Data Dictionary (Variables included in the .csv file): · Sample_ID: Unique identifier for each soil sample. · Parish: Administrative parish where the sample was collected. · Crop_System: Representative cropping system at the sampling site. · Altitude: Elevation above sea level (m a.s.l.). · Moisture_Wet_Base: Soil moisture content (%). · pH: Hydrogen ion concentration (1:2.5 soil-water suspension). · Electrical_Conductivity: Soil salinity indicator (mS/cm). · Calcium_Ca: Exchangeable Calcium (meq/100ml). · Magnesium_Mg: Exchangeable Magnesium (meq/100ml). · Sodium_Na: Exchangeable Sodium (meq/100ml). Keywords: Soil Quality, Digital Soil Mapping, Ecuadorian Amazon, Precision Agriculture, Geographic Information Systems (GIS), Soil Acidity.","author":[{"family":"González Rivera","given":"Víctor"},{"family":"Saltos Espín","given":"Rubén"},{"family":"Hidalgo Guerrero","given":"Irene"},{"family":"González Rivera","given":"Martha"},{"family":"Yucailla","given":"Verónica"},{"family":"González Rivera","given":"Isabel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20453556","URL":"https://doi.org/10.5281/zenodo.20453556","source":"datacite"},{"id":"doi:10.5281/zenodo.20453557","type":"article-journal","title":"Spatial Analysis of pH and Salinity in Agricultural Soils in the Province of Pastaza Using Geographic Information Systems (GIS)","abstract":"This repository contains the raw primary data (.csv) supporting the research article \"Spatial Analysis of pH and Salinity in Agricultural Soils in the Province of Pastaza Using Geographic Information Systems (GIS)\". The dataset includes physicochemical laboratory results from 76 surface soil samples (0–20 cm depth) collected across 14 parishes in the province of Pastaza, located in the Ecuadorian Amazon. The data was collected to evaluate the spatial variability of soil properties and to identify edaphic limitations for agricultural production. Data Dictionary (Variables included in the .csv file): · Sample_ID: Unique identifier for each soil sample. · Parish: Administrative parish where the sample was collected. · Crop_System: Representative cropping system at the sampling site. · Altitude: Elevation above sea level (m a.s.l.). · Moisture_Wet_Base: Soil moisture content (%). · pH: Hydrogen ion concentration (1:2.5 soil-water suspension). · Electrical_Conductivity: Soil salinity indicator (mS/cm). · Calcium_Ca: Exchangeable Calcium (meq/100ml). · Magnesium_Mg: Exchangeable Magnesium (meq/100ml). · Sodium_Na: Exchangeable Sodium (meq/100ml). Keywords: Soil Quality, Digital Soil Mapping, Ecuadorian Amazon, Precision Agriculture, Geographic Information Systems (GIS), Soil Acidity.","author":[{"family":"González Rivera","given":"Víctor"},{"family":"Saltos Espín","given":"Rubén"},{"family":"Hidalgo Guerrero","given":"Irene"},{"family":"González Rivera","given":"Martha"},{"family":"Yucailla","given":"Verónica"},{"family":"González Rivera","given":"Isabel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20453557","URL":"https://doi.org/10.5281/zenodo.20453557","source":"datacite"},{"id":"doi:10.5281/zenodo.21552778","type":"article-journal","title":"Cloud-Assisted IoT-Based Monitoring and Evaluation In Agriculture","abstract":"Agriculture is the primary economic activity in many rural areas and emerging nations, and it serves as the economic backbone for many nations. The agricultural industry has come a long way since its humble beginnings, and it is now significantly more complicated and multi-faceted. The problem that challenges agriculture in the modern day is how to provide food for the entire world's population in a fair and equitable manner while also preventing irreversible damage to the natural environment. Farmers' traditional techniques are insufficient to meet the rising demand of food. The agriculture sector faces various challenges such as producing more and better products while enhancing the sustainability through the smart use of natural resources, minimizing environmental harm, and adapting to the climate change. The purpose of introducing information technology into agriculture is to save production costs, improve production efficiency, and accelerate the development of productivity. Geographic information system technology is widely used in agriculture, such as precision agriculture, land resource management, crop yield estimation and monitoring, and soil and water conservation. The characteristic of expert decision-making system is the logical reasoning of knowledge, and the advantage of network is the acquisition of knowledge. In this paper, the agricultural data obtained from the expert database are displayed in the form of a tree list and are used in the process of system design. The geospatial data can be uploaded through the map loading function, find the map path, and easily uploaded by modifying the expert database. Efficient agricultural policies are essential to meeting increasing demand for safe and nutritious food in a sustainable way. While growing demand for food, feed, fuel and fibre presents significant opportunities for agriculture, government policies must address challenges such as increasing productivity growth, enhancing environmental sustainability, including reducing greenhouse gas emissions, and improving adaptation and resilience in the face of climate change and other unforeseen shocks.","author":[{"family":"Nikisha","given":"R"},{"family":"Felsy","given":"C"}],"issued":{"date-parts":[[2023]]},"DOI":"10.5281/zenodo.21552778","URL":"https://doi.org/10.5281/zenodo.21552778","source":"datacite"},{"id":"doi:10.5281/zenodo.21552779","type":"article-journal","title":"Cloud-Assisted IoT-Based Monitoring and Evaluation In Agriculture","abstract":"Agriculture is the primary economic activity in many rural areas and emerging nations, and it serves as the economic backbone for many nations. The agricultural industry has come a long way since its humble beginnings, and it is now significantly more complicated and multi-faceted. The problem that challenges agriculture in the modern day is how to provide food for the entire world's population in a fair and equitable manner while also preventing irreversible damage to the natural environment. Farmers' traditional techniques are insufficient to meet the rising demand of food. The agriculture sector faces various challenges such as producing more and better products while enhancing the sustainability through the smart use of natural resources, minimizing environmental harm, and adapting to the climate change. The purpose of introducing information technology into agriculture is to save production costs, improve production efficiency, and accelerate the development of productivity. Geographic information system technology is widely used in agriculture, such as precision agriculture, land resource management, crop yield estimation and monitoring, and soil and water conservation. The characteristic of expert decision-making system is the logical reasoning of knowledge, and the advantage of network is the acquisition of knowledge. In this paper, the agricultural data obtained from the expert database are displayed in the form of a tree list and are used in the process of system design. The geospatial data can be uploaded through the map loading function, find the map path, and easily uploaded by modifying the expert database. Efficient agricultural policies are essential to meeting increasing demand for safe and nutritious food in a sustainable way. While growing demand for food, feed, fuel and fibre presents significant opportunities for agriculture, government policies must address challenges such as increasing productivity growth, enhancing environmental sustainability, including reducing greenhouse gas emissions, and improving adaptation and resilience in the face of climate change and other unforeseen shocks.","author":[{"family":"Nikisha","given":"R"},{"family":"Felsy","given":"C"}],"issued":{"date-parts":[[2023]]},"DOI":"10.5281/zenodo.21552779","URL":"https://doi.org/10.5281/zenodo.21552779","source":"datacite"},{"id":"doi:10.5281/zenodo.20910822","type":"article-journal","title":"Precision Agriculture: Spotting and Spraying Yellow Defected Plant","abstract":"The agricultural sector plays an important role in the process of economic development of a country. The conventional pesticide spraying method involves uniform spraying of the entire field even when only some plants are infected. This results in pesticide wastage, increased operation costs, and health hazards. Hence, there is a strong need for an automated, precise, and selective spraying of the plants. This project presents a Precision Agriculture System using Drone Technology for Spotting and Spraying Yellow Defected Plants. The proposed system will consist of a quadcopter with a high-resolution camera and an image processing tool. The captured image is processed and compared with various examples, and the suitable control signal is given to the spraying mechanism for the spraying of the defected plant. This selective spraying reduces the waste of pesticides and decreases the environmental impact while ensuring proper care of the plants. This system integrates the Robot Operating System (ROS) for the control and communication, while the OpenCV enable the real time image processing of the defective plant. The drone mechanical build includes with light weight carbon fibre body with high resolution camera and 3D printed custom parts for delicate electronics. Together these components ensure accurate detection and spraying of the defected plants. The proposed system offers several advantages such as reduced 0chemical usage, improved crop yield, lower labour requirements, and enhanced farming efficiency. The future work will focus on the integration of the advanced machine learning models to accurately find the defected plant and enhancing autonomous path planning through ROS for optimized field coverage. This project contributes toward the development of sustainable and intelligent farming solutions in modern precision agriculture.","author":[{"family":"Stefi","given":"AA"},{"family":"Kumar","given":"Mukesh"},{"family":"Mowlisankar"},{"family":"Kumar","given":"Surendhar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20910822","URL":"https://doi.org/10.5281/zenodo.20910822","source":"datacite"},{"id":"doi:10.5281/zenodo.20910823","type":"article-journal","title":"Precision Agriculture: Spotting and Spraying Yellow Defected Plant","abstract":"The agricultural sector plays an important role in the process of economic development of a country. The conventional pesticide spraying method involves uniform spraying of the entire field even when only some plants are infected. This results in pesticide wastage, increased operation costs, and health hazards. Hence, there is a strong need for an automated, precise, and selective spraying of the plants. This project presents a Precision Agriculture System using Drone Technology for Spotting and Spraying Yellow Defected Plants. The proposed system will consist of a quadcopter with a high-resolution camera and an image processing tool. The captured image is processed and compared with various examples, and the suitable control signal is given to the spraying mechanism for the spraying of the defected plant. This selective spraying reduces the waste of pesticides and decreases the environmental impact while ensuring proper care of the plants. This system integrates the Robot Operating System (ROS) for the control and communication, while the OpenCV enable the real time image processing of the defective plant. The drone mechanical build includes with light weight carbon fibre body with high resolution camera and 3D printed custom parts for delicate electronics. Together these components ensure accurate detection and spraying of the defected plants. The proposed system offers several advantages such as reduced 0chemical usage, improved crop yield, lower labour requirements, and enhanced farming efficiency. The future work will focus on the integration of the advanced machine learning models to accurately find the defected plant and enhancing autonomous path planning through ROS for optimized field coverage. This project contributes toward the development of sustainable and intelligent farming solutions in modern precision agriculture.","author":[{"family":"Stefi","given":"AA"},{"family":"Kumar","given":"Mukesh"},{"family":"Mowlisankar"},{"family":"Kumar","given":"Surendhar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20910823","URL":"https://doi.org/10.5281/zenodo.20910823","source":"datacite"},{"id":"doi:10.5281/zenodo.21905416","type":"article-journal","title":"Raster Reflectance Extraction from Orthomosaics in R","abstract":"This R script provides a workflow for extracting spectral reflectance values from orthomosaics (raster files) at specific ground sampling points defined in UTM coordinates. The script loads a multi‑band orthomosaic, converts sampling points to an sf object with the same coordinate reference system, and extracts pixel values for each point across all available bands. The output is a combined table of coordinates and reflectance values, along with optional graphical visualization and basic correlation statistics. This tool supports remote sensing applications in vegetation monitoring, precision agriculture, and environmental mapping, offering a reproducible and efficient alternative to manual point sampling in GIS software.","author":[{"family":"Maciel Dos Santos","given":"Lucas"},{"family":"Santos Lopes","given":"Marcos"},{"family":"Surmani","given":"Carmem"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21905416","URL":"https://doi.org/10.5281/zenodo.21905416","source":"datacite"},{"id":"doi:10.5281/zenodo.21905417","type":"article-journal","title":"Raster Reflectance Extraction from Orthomosaics in R","abstract":"This R script provides a workflow for extracting spectral reflectance values from orthomosaics (raster files) at specific ground sampling points defined in UTM coordinates. The script loads a multi‑band orthomosaic, converts sampling points to an sf object with the same coordinate reference system, and extracts pixel values for each point across all available bands. The output is a combined table of coordinates and reflectance values, along with optional graphical visualization and basic correlation statistics. This tool supports remote sensing applications in vegetation monitoring, precision agriculture, and environmental mapping, offering a reproducible and efficient alternative to manual point sampling in GIS software.","author":[{"family":"Maciel Dos Santos","given":"Lucas"},{"family":"Santos Lopes","given":"Marcos"},{"family":"Surmani","given":"Carmem"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21905417","URL":"https://doi.org/10.5281/zenodo.21905417","source":"datacite"},{"id":"doi:10.1201/9781003527664-3","type":"article-journal","title":"IoT-Based Precision Agriculture with Integrated Security for Smart Farming","abstract":"The rapid advancement of the Internet of Things (IoT) has transformed nearly every industry, including smart farming, moving it from traditional statistical approaches to more data-driven, quantitative methods. These groundbreaking changes are reshaping conventional agricultural practices, offering new opportunities while also presenting significant challenges. This chapter highlights the potential of wireless and IoT sensors in revolutionizing agriculture, as well as the challenges that arise when integrating this technology with existing farming techniques. The adoption of IoT in smart and precision agriculture is not only modernizing traditional farming methods but also addressing issues like animal intrusion and fire hazards, all while making farming more cost-effective. This chapter introduces an IoT-based model aimed at mitigating potential agricultural damages caused by wild animals and adverse weather conditions, providing a proactive solution for safeguarding farms.","author":[{"family":"Haque","given":"Md"},{"family":"Ahmad","given":"Sultan"},{"family":"Sonal","given":"Deepa"},{"family":"Zafar","given":"Aasim"},{"family":"Ali","given":"Aleem"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003527664-3","URL":"https://doi.org/10.1201/9781003527664-3","source":"crossref"},{"id":"doi:10.1016/j.aiia.2025.02.001","type":"article-journal","title":"Precision agriculture technologies for soil site-specific nutrient management: A comprehensive review","abstract":"Amidst the growing food demands of an increasing population, agricultural intensification frequently depends on excessive chemical and fertilizer applications. While this approach initially boosts crop yields, it effects long-term sustainability through soil degradation and compromised food quality. Thus, prioritizing soil health while enhancing crop production is essential for sustainable food production. Site-Specific Nutrient Management (SSNM) emerges as a critical strategy to increase crop production, maintain soil health, and reduce environmental pollution. Despite its potential, the application of SSNM technologies remains limited in farmers' fields due to existing research gaps. This review critically analyzes and presents research conducted in SSNM in the past 11 years (2013–2024), identifying gaps and future research directions. A comprehensive study of 97 relevant research publications reveals several key findings: a) Electrochemical sensing and spectroscopy are the two widely explored areas in SSNM research, b) Despite numerous technologies in SSNM, each has its own limitation, preventing any single technology from being ideal, c) The selection of models and preprocessing techniques significantly impacts nutrient prediction accuracy, d) No single sensor or sensor combination can predict all soil properties, as suitability is highly attribute-specific. This review provides researchers, technical personnel in precision agriculture, and farmers with detailed insights into SSNM research, its implementation, limitations, challenges, and future research directions. • Site-specific nutrient management promotes sustainable and site-specific agricultural practices for better crop yields and environmental health. It is also necessary to address soil variability and improve the accuracy of nutrient prediction technologies. • This review analyzes research on site-specific nutrient management from the past 11 years (2013–2024). • Provides detailed insights to the farmers and research community about the current site-specific nutrient management technologies based on machine learning and deep learning, their utilization and limitations. • Offers future research directions for researchers and technical personnel in precision agriculture.","author":[{"family":"Vullaganti","given":"Niharika"},{"family":"Ram","given":"Billy"},{"family":"Sun","given":"Xin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.aiia.2025.02.001","URL":"https://doi.org/10.1016/j.aiia.2025.02.001","source":"crossref"},{"id":"doi:10.66406/gjab01202463","type":"article-journal","title":"SUSTAINABLE LIVESTOCK MANAGEMENT THROUGH GENOMICS, PRECISION FEEDING, AND ENVIRONMENTAL MONITORING","abstract":"The present paper analyses sustainable cattle management through the composite method that combines genomics, precision feeding, and environmental monitoring. Genomic studies on whole-genome sequencing and genome-wide association studies have identified hereditary traits related to feed efficiency, milk supply and disease resistance, and heritability estimates support selective breeding programs. The precision feeding experiments, which were planned according to the randomized block designs and sensors relying on the Internet of Things, demonstrated significant improvements in the feed ratio and weight gain, a reduction in the level of methane emissions and feed expenses. Meanwhile, environmental monitoring sensors operating in real-time received alterations in temperature, humidity, and emissions, and demonstrated a direct correlation between ecological stressors and animal performance. Spatial mapping also demonstrated how pressure of grazing affects the sustainability of the environment. The qualitative interviews of farmers and livestock managers provided additional information regarding adoption barriers, socio-cultural attitudes, and the usefulness of the application of genomic and precision technologies to real-life situations. This overlapping of quantitative and qualitative information confirmed that sustainable livestock production requires both high-tech genetic and nutritional optimization and a strong correspondence with the experience of the farmers and with ecological reality. The findings indicate that, integrated systems are capable of enhancing production, reducing environmental impact, and enabling socio-economic resilience simultaneously, which make cattle more sustainable.","author":[{"family":"Jan","given":"Abdul"},{"family":"Iqbal","given":"Shahid"},{"family":"Rehman","given":"Atta"},{"family":"Ramish","given":"Syed"}],"issued":{"date-parts":[[2026]]},"DOI":"10.66406/gjab01202463","URL":"https://doi.org/10.66406/gjab01202463","source":"crossref"},{"id":"doi:10.1201/9781003536932-4","type":"article-journal","title":"Drones in Agriculture: Aerial Intelligence for Precision Farming","abstract":"The integration of drones into agriculture has transformed traditional farming, ushering in precision farming. This chapter explores drones as aerial intelligence platforms, enhancing agricultural processes through advanced data collection, analysis, and decision-making. Drones provide farmers with crucial insights into crop health, soil conditions, and water stress via high-resolution imagery, multispectral sensors, and thermal cameras. These capabilities enable targeted interventions, optimizing productivity while reducing costs and environmental impact. The chapter traces the evolution of drones in agriculture, from military use to essential farming tools. Drones now perform tasks like crop monitoring, irrigation management, and pest control, significantly improving efficiency and accuracy. However, challenges such as regulatory compliance, privacy concerns, and data interpretation remain. Addressing these issues requires collaboration among policymakers, researchers, and industry leaders to establish responsible guidelines for drone use. Looking ahead, the chapter examines future trends in drone technology, including autonomous navigation, swarm intelligence, and machine learning, which promise to further enhance agricultural practices. Ultimately, drones are integral to modern agriculture, offering a sustainable approach to farming that boosts yields and conserves resources.","author":[{"family":"Roy","given":"Debasish"},{"family":"Dutta","given":"Suman"},{"family":"Paul","given":"Debashis"},{"family":"Das","given":"Anshuman"},{"family":"Saikia","given":"Nilutpal"},{"family":"Das","given":"Sumanta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003536932-4","URL":"https://doi.org/10.1201/9781003536932-4","source":"crossref"},{"id":"doi:10.4018/979-8-3373-5283-1.ch007","type":"article-journal","title":"Vertical Farming and Hydroponics Leveraging Smart Technologies for Urban Agriculture","abstract":"As urbanization accelerates and arable land becomes increasingly scarce, vertical farming and hydroponics have emerged as innovative solutions for sustainable food production within metropolitan environments. This chapter explores the technological advancements driving vertical farming and hydroponic systems, focusing on the integration of smart technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and cloud-based monitoring. Through IoT-enabled sensors, real-time data on environmental conditions—such as humidity, temperature, and nutrient levels—can be continuously monitored and adjusted for optimal plant growth. AI-driven analytics enhance predictive maintenance and resource optimization, minimizing waste and maximizing yield. Furthermore, automated climate control and LED-based grow lights replicate natural growing conditions, enabling year-round cultivation independent of weather variations. Case studies from global urban farming projects are presented to illustrate the transformative impact of these technologies on food security and sustainability.","author":[{"family":"Jain","given":"Anupriya"},{"family":"Arora","given":"Vansh"},{"family":"Linzara","given":"Hardik"},{"family":"Saraswat","given":"Oshank"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-5283-1.ch007","URL":"https://doi.org/10.4018/979-8-3373-5283-1.ch007","source":"crossref"},{"id":"doi:10.3390/agriculture16131379","type":"article-journal","title":"Nutrition as the Intelligent Nexus: Integrating Precision Farming into Sustainable Ruminant Systems","abstract":"Global agriculture faces a dual imperative: increase food production to meet rising demand while simultaneously reducing environmental impacts and resource inefficiencies. Addressing this challenge requires repositioning ruminant nutrition as the intelligent nexus linking crop and livestock production within Integrated Crop–Livestock Systems (ICLS). In this role, nutrition becomes central to restoring ecological, nutritional, and economic synergies that have been fragmented by decades of agricultural specialization. While ICLS provides the ecological foundation, Precision Livestock Farming delivers the technological and analytical infrastructure necessary to operationalize integration at the individual-animal level. Real-time sensing, Internet of Things platforms, and Artificial Intelligence (AI) enable dynamic monitoring of animal physiology, behavior, and environmental interactions across scales. A key advancement in this evolution is the development of Hybrid Intelligent Mechanistic Models (HIMM), which integrate biologically grounded mechanistic models with data-driven AI approaches. By combining interpretability with adaptive learning, HIMM enhances predictive accuracy, extrapolative capacity, and decision transparency, enabling the creation of digital twins that simulate biological responses before management interventions are implemented. Such architectures extend precision nutrition beyond feed efficiency and methane mitigation to include nutrient density and product quality, thereby linking different ecosystem processes directly to human dietary needs. Integrating nutrition with advanced modeling and monitoring tools can help livestock systems move beyond static “net-zero” benchmarks toward sustainable strategies that are responsive to local production contexts. In this reframed paradigm, nutrition is not merely a production input but the central analytical framework that computationally links biological mechanisms, environmental stewardship, technological innovation, and human health within sustainable ruminant systems.","author":[{"family":"Tedeschi","given":"Luis"},{"family":"Mendes","given":"Egleu"},{"family":"Fernandes","given":"Marcia"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16131379","URL":"https://doi.org/10.3390/agriculture16131379","source":"crossref"},{"id":"doi:10.71443/9789349552364-01","type":"article-journal","title":"Artificial Intelligence Technologies in Sustainable Agriculture Systems","abstract":"The increasing pressures of population growth, climate variability, and resource constraints have created an urgent need for sustainable and efficient agricultural systems. Artificial Intelligence (AI) has emerged as a transformative tool capable of addressing these challenges by enabling data-driven decision-making, predictive analytics, and intelligent automation across the agricultural value chain. This chapter provides a comprehensive analysis of AI technologies and their applications in sustainable agriculture systems, highlighting their role in enhancing crop productivity, optimizing resource utilization, and minimizing environmental impact. Machine learning, deep learning, computer vision, and natural language processing techniques are explored for tasks such as disease and pest detection, yield prediction, and precision farming operations. The integration of AI with Internet of Things (IoT) devices, remote sensing, and big data analytics is examined, demonstrating how real-time data acquisition and adaptive decision-making can improve operational efficiency and resilience. Additionally, the chapter addresses key challenges in implementing AI, including data heterogeneity, algorithmic transparency, infrastructure limitations, and socio-economic disparities, while outlining research gaps and future directions for scalable, climate-smart, and resource-efficient agricultural solutions. The discussion underscores the potential of AI to catalyze a paradigm shift toward sustainable agriculture, fostering global food security and environmental stewardship.","author":[{"family":"Kishanrao","given":"Kakade"},{"family":"Ashok","given":"Zarkar"},{"family":"Uttamrao","given":"Deshmukh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-01","URL":"https://doi.org/10.71443/9789349552364-01","source":"crossref"},{"id":"doi:10.1201/9781003354253-10","type":"article-journal","title":"Nanobiosensors for Precision Farming and Sustainable Agriculture","abstract":"An overview of nanobiosensors for sustainable agriculture and precision farming is given in this chapter. Throughout every single phase of the agricultural product processing, biosensors are introduced during the pregrowth and growth stages, as well as the regulation of the soil, water, air, and feed and several auxiliary stages. A pressing problem is the creation of novel sensors with enhanced properties. The addition of nanoparticles dramatically increases the sensitivity of the system. In these systems, nanostructures are typically used to bridge the nanoscale gap between the converter and the bioreceptor. Nanostructured organic, inorganic, and mixed materials are used in modern sensors. The majority of significant sensors used in agriculture and described in the literature are organic. This chapter discusses nanobiosensors, fabrication techniques, and an analysis of their structural characteristics.","author":[{"family":"Romanovski","given":"Valentin"},{"family":"Zhang","given":"Zhaowei"},{"family":"Akbarisehat","given":"Ali"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003354253-10","URL":"https://doi.org/10.1201/9781003354253-10","source":"crossref"},{"id":"doi:10.2139/ssrn.5088806","type":"manuscript","title":"IoT Based Smart Monitoring System for Enhancing Precision Agriculture and Environmental Farming System","abstract":"The agriculture industry is experiencing enhancement in crop production and efficiency of resource utilization through the use of advanced technologies such as agriculture precision farming. The paper presents a water monitoring and irrigation system that makes use of Internet of Things technologies to solve issues surrounding water scarcity and unproductive manual irrigation practices. This type of system involves the employing of several different sensors, temperature, nutrient concentration and ultrasonic sensors, to be able to monitor parameters such as n-p-k, water level, and temperature. Based on these inputs, the irrigation system is made active whenever crops require a particular amount of water and nutrients and conditions are met. Manual labor is reduced and efficiency elevated. After evaluating experimental results, this system represents an efficient and viable plantation oriented as well as water conserving system. The Prototype introduces a flexible structure that caters for many agricultural uses.","author":[{"family":"Praneeth","given":"Nalobannagari"},{"family":"Kalyan","given":"Kottem"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2139/ssrn.5088806","URL":"https://doi.org/10.2139/ssrn.5088806","source":"crossref"},{"id":"doi:10.1201/9781003613510-5","type":"article-journal","title":"Influence of Internet of Things and Artificial Intelligence in Precision Agriculture of Coffee Crop","abstract":"The new generation of agricultural farms is based on precision agriculture. The precision agriculture promotes the adoption of advanced technologies, enhancing farm productivity, reducing operational costs, and supporting environmental sustainability. However, the influence of the Internet of Things (IoT) and Artificial Intelligence (AI) enhanced the precision agricultural productivity. This chapter brings out the inference of precision agriculture through a case study on coffee leaf disease detection. The convolutional neural networks adopted in the case study predict the diseases and optimize the resource utilization in coffee production.","author":[{"family":"Jagadamba","given":"G"},{"family":"Chayashree","given":"G"},{"family":"Hemavathi"},{"family":"Jayadeva","given":"Varun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003613510-5","URL":"https://doi.org/10.1201/9781003613510-5","source":"crossref"},{"id":"doi:10.55248/gengpi.6.0725.2580","type":"article-journal","title":"Agri Assist: An Ai-Driven Platform For Precision Agriculture","abstract":"Agriculture stands as the foundation of human survival and a key driver of the world's food supply and economic stability, profoundly impacting nearly every aspect of our daily lives.From growing the food, we eat to delivering raw materials for numerous industries, agriculture plays a crucial role in sustaining both livelihoods and the health of societies.However, agricultural production is frequently challenged by a range of problems -notably pests, diseases, poor soil health, climate variability, and a growing scarcity of resources -which collectively undermine both yields and financial stability for farmers.Detecting pests and diseases at their earliest manifestation is a major hurdle; traditionally, this process involves manually inspecting leaves, roots, or other plant components for visible symptoms -a method that is subjective, prone to human error, delayed, and often less accurate.This delayed or erroneous identification can enable pests and diseases to reach catastrophic proportions, spreading rapidly and causing extensive damage to entire fields and subsequent financial losses.Furthermore, fertilizer application -a crucial aspect of agricultural care -frequently relies on approximate judgments instead of data-informed decisions, resulting in overfertilization, soil degradation, financial waste, and poor yields.In many developing and underdeveloped regions, small and medium-sized farmers do not have access to sophisticated sensor networks or extensive technical training due to financial constraints, limited resources, poor connectivity, or low digital literacy, further compounding their vulnerability and preventing them from optimizing their agricultural practices.Without proper intervention, this scenario can undermine food production, diminish profits, and contribute to growing food insecurity -a major concern for the future well-being of societies.To address these longstanding problems, this project introduces Agri Assist -a pure-AI solution designed to aid farmers without requiring extensive physical sensor networks or significant financial investment.Agri Assist utilizes open-source IoT datasets alongside advanced machine learning and deep learning techniques to enable a range of services previously available only through sophisticated sensor-equipped platforms.Our platform strives to make precision agriculture more accessible, sustainable, adaptable, and realistic for farmers across the spectrum -from smallholders to large enterprises -helping them maximize yields while conserving financial resources, reducing reliance on pesticides and fertilizer, preserving soil health, and conserving the environment.Furthermore, by employing multilanguage support and a simplified user-interface, Agri Assist directly addresses linguistic and literacy barriers, ensuring its ability to empower a greater number of users in a way that resonates with their routines, knowledge, and agricultural practices.Ultimately, Agri Assist aims to transform the agricultural landscape by turning data into actionable knowledge -a transformation that holds the potential to feed growing populations, protect natural resources, enable sustainable practices, and foster greater financial stability for farmers and their families.","author":[{"family":"Hemalatha","given":"Mrs"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55248/gengpi.6.0725.2580","URL":"https://doi.org/10.55248/gengpi.6.0725.2580","source":"crossref"},{"id":"doi:10.1016/j.aiia.2025.01.013","type":"article-journal","title":"Advancing precision agriculture: A comparative analysis of YOLOv8 for multi-class weed detection in cotton cultivation","abstract":"Effective weed management plays a critical role in enhancing the productivity and sustainability of cotton cultivation. The rapid emergence of herbicide-resistant weeds has underscored the need for innovative solutions to address the challenges associated with precise weed detection. This paper investigates the potential of YOLOv8, the latest advancement in the YOLO family of object detectors, for multi-class weed detection in U.S. cotton fields. Leveraging the CottonWeedDet12 dataset, which includes diverse weed species captured under varying environmental conditions, this study provides a comprehensive evaluation of YOLOv8's performance. A comparative analysis with earlier YOLO variants reveals substantial improvements in detection accuracy, as evidenced by higher mean Average Precision (mAP) scores. These findings highlight YOLOv8's superior capability to generalize across complex field scenarios, making it a promising candidate for real-time applications in precision agriculture. The enhanced architecture of YOLOv8, featuring anchor-free detection, an advanced Feature Pyramid Network (FPN), and an optimized loss function, enables accurate detection even under challenging conditions. This research emphasizes the importance of machine vision technologies in modern agriculture, particularly for minimizing herbicide reliance and promoting sustainable farming practices. The results not only validate YOLOv8's efficacy in multi-class weed detection but also pave the way for its integration into autonomous agricultural systems, thereby contributing to the broader goals of precision agriculture and ecological sustainability. • Effective weed management enhances cotton productivity and sustainability. • The study evaluates YOLOv8 for multi-class weed detection in U.S. cotton fields. • YOLOv8 shows significant mAP improvements over previous YOLO variants. • Using CottonWeedDet12, YOLOv8 exhibits rapid stabilization for real-time applications.","author":[{"family":"Khan","given":"Ameer"},{"family":"Jensen","given":"Signe"},{"family":"Khan","given":"Abdul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.aiia.2025.01.013","URL":"https://doi.org/10.1016/j.aiia.2025.01.013","source":"crossref"},{"id":"doi:10.1007/s11119-026-10328-7","type":"article-journal","title":"Real-time detection of Rumex and  C. autumnale in grasslands","abstract":"Abstract Purpose This study addresses the challenge of real-time detection of the weeds Colchicum autumnale and Rumex species on grassland sites, which is an inherently difficult problem because the predominantly green weed leaves provide little contrast to the similarly colored vegetation backgrounds. The resulting detector will be integrated into the SELBEWAG tool, a non-chemical, site-specific weed treatment device. Methods We collected and annotated RGB video recordings from grassland sites in Southwest Germany and trained a quantized EfficientDet object detection model, which has been optimized for low latency on edge devices. Results The detection system achieved a mean average precision of 0.606 across both weed types (0.617 for Rumex and 0.595 for C. autumnale ). With an optimal decision threshold, the model demonstrated precision values of 56.0% for C. autumnale and 48.1% for Rumex, with corresponding recall values of 62.1% and 67.1%, respectively. Detection performance was influenced by surrounding vegetation height and weed clustering. Conclusions The developed system provides effective real-time detection of grassland weeds suitable for integration with the SELBEWAG tool. While detection challenges remain, in particular in high vegetation conditions, the approach significantly improves upon area-wide treatment methods by targeting only the necessary area rather than entire fields.","author":[{"family":"Petrich","given":"Lukas"},{"family":"Haußmann","given":"Ingo"},{"family":"Lohrmann","given":"Georg"},{"family":"Stoll","given":"Albert"},{"family":"Schmidt","given":"Volker"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10328-7","URL":"https://doi.org/10.1007/s11119-026-10328-7","source":"crossref"},{"id":"doi:10.71443/9789349552364-12","type":"article-journal","title":"AI Enhanced Drones for Precision Seeding Spraying and Soil Mapping","abstract":"The integration of Artificial Intelligence (AI) with drone technology is transforming modern agriculture, enhancing precision farming practices through optimized seeding, targeted spraying, and real-time soil mapping. AI-powered drones offer a high level of autonomy and efficiency, providing significant advantages in terms of resource conservation, crop yield, and environmental sustainability. These systems utilize advanced machine learning algorithms and real-time data analytics to facilitate decision-making processes that were previously reliant on manual labor and traditional methods. This chapter explores the role of AI-driven drones in improving agricultural productivity, focusing on precision seeding, spraying, and soil health monitoring. It examines the economic and environmental benefits, including cost reduction, increased efficiency, and the minimized environmental footprint of chemical applications. Case studies from diverse agricultural settings illustrate the successful implementation of AI-enhanced drones, highlighting their adaptability in varying terrains and climatic conditions. The chapter also addresses current challenges in AI integration, such as data security, cost barriers, and regulatory hurdles, while outlining future trends in AI-powered agricultural drone technology. The continued development of these systems promises to drive a more sustainable, data-driven, and resilient agricultural ecosystem.","author":[{"family":"Kishanrao","given":"Kakade"},{"family":"Dadpe","given":"Kuldip"},{"family":"Uttamrao","given":"Deshmukh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-12","URL":"https://doi.org/10.71443/9789349552364-12","source":"crossref"},{"id":"doi:10.2139/ssrn.6771197","type":"manuscript","title":"Navigation and sensor fusion for autonomous field robots in precision agriculture: narrative review","abstract":"Autonomous field robots are increasingly used in precision agriculture for monitoring, phenotyping, spraying, and site-specific intervention, yet reliable autonomy remains difficult under vegetation occlusion, uneven terrain, variable illumination, and intermittent communications. This review provides a deployment-oriented synthesis of navigation and sensor-fusion methods for agricultural robots, with emphasis on what is practical under field conditions rather than only in laboratory settings. The literature was examined through a structured narrative-review workflow using Scopus, Web of Science, IEEE Xplore, ScienceDirect, SpringerLink, and related citation tracking, with primary emphasis on studies published between 2015 and 2025. We compare global, local, and hybrid planning methods; motion-control strategies such as PID, Pure Pursuit, and MPC; and localization pipelines that combine GNSS, IMU, LiDAR, cameras, odometry, and SLAM or Kalman-family fusion. Beyond algorithm summaries, the review links method selection to agricultural deployment constraints, including GNSS degradation, dynamic obstacles, compute limits, ROS 2 integration, time synchronization, and coordinate-frame management. The synthesis shows that no single stack is optimal across all crop systems: lightweight GNSS/IMU-based solutions remain attractive in structured open fields, whereas orchards, vineyards, and other occluded environments benefit more from tighter multi-sensor fusion and SLAM-supported localization. Finally, the review distills design guidance for sensing, planning, validation, and digital-twin-supported testing, and identifies research gaps related to robustness, benchmarking, safety, and scalable on-farm deployment.","author":[{"family":"Boros","given":"Norber"},{"family":"Ambrus","given":"Bálint"},{"family":"Nyéki","given":"Anikó"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.6771197","URL":"https://doi.org/10.2139/ssrn.6771197","source":"crossref"},{"id":"doi:10.7490/f1000research.1115949.1","type":"article-journal","title":"Farming with nature: using precision agriculture to rescue arthropod populations and provide ecosystem services","abstract":"Intensive agriculture has resulted in dramatic transformations of the landscape; with natural areas reduced to fragments or eliminated by large in a matrix of crop, livestock, and pasture areas. The expansion of monocultures has been a key driver of biodiversity loss, including insect abundance and richness. This reduction in diversity threatens important ecosystem services, which are provided by beneficial insect functional groups such as pollinators or natural enemies of agricultural pests. This has created a management paradox on conventional farms – a need for insect services, yet conducting farm practices that reduce their presence and benefits. One model that has been proposed to help tackle this farm management paradox is so-called “precision agriculture”; a multi-faceted strategy that includes conversion of marginal lands on farms to a native species-rich tall-grass prairie, which may provide insect habitat and critical food resources. This resource management strategy has been adopted by ALUS Canada with farms around Southern Ontario and is the basis of my study. Field research was undertaken on 13 farms located in Southern Ontario to examine effects of local and landscape factors on the community structure and function of early-season arthropod groups, and ultimately how this influences crop damage. Results show that these prairie grassland borders can increase beneficial arthropod abundance, including natural enemies of many pests. Responses to prairie borders varied across specific functional groups but mainly depended on percent cover of C3 grasses, C4 grasses and forbs. Overall, beneficial arthropod abundance and richness was greater on ALUS farms than on conventional farms which have no prairies and crop leaf damage was 50% lower on ALUS farms with restored prairies. This was driven by an increase in local habitat diversity and resources from prairie grassland borders. This study provides a clear demonstration that precision agriculture which supports ecosystem services, is compatible with, and even increase beneficial arthropods to agricultural landscapes.","author":[{"family":"Dolezal","given":"Aleksandra"},{"family":"Esch","given":"Ellen"},{"family":"Macdougall","given":"Andrew"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7490/f1000research.1115949.1","URL":"https://doi.org/10.7490/f1000research.1115949.1","source":"crossref"},{"id":"doi:10.1155/aia/3836884","type":"article-journal","title":"Precision Agriculture Technologies in Morocco: State of the Art and Exploration of Company Experience","abstract":"The literature has defined the potential benefits of using precision agriculture (PA) technologies (preservation of natural resources, savings on inputs, efficiency of agricultural interventions, etc.). However, the adoption of these innovations remains dependent on factors linked to the farmer, his environment, and, in some cases, the technology itself. Like numerous other countries, Morocco is witnessing the introduction of a number of precision farming tools and techniques. The genesis of this process of diffusion of these innovations prompted us to carry out an exploratory qualitative study through a survey of potential actors in the PA technology market in order to define a state of the art for Morocco. Our survey covered 30 companies offering PA technologies on the Moroccan market. Around 40% of these businesses had been operating since the 1990s, while 20% joined the sector in the 2020s. The interviewees confirmed that climate change, adaptation to international market trends, and domestic market demand are factors that justify the importance of integrating PA technologies into the agricultural sector. Additionally, the analyses highlight that the context of agriculture in Morocco (farm size, farm income, quality of labor, and dependence on state subsidies) presents challenges to the adoption of these new technologies by farmers. The findings and recommendations presented in this study will serve as a reference for policymakers, agricultural machinery manufacturers, and service providers in order to develop interventions adapted to the national context to promote PA.","author":[{"family":"Idier","given":"Hayat"},{"family":"Dehhaoui","given":"Mohammed"},{"family":"Maatala","given":"Nassreddine"},{"family":"Kadi","given":"Kenza"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1155/aia/3836884","URL":"https://doi.org/10.1155/aia/3836884","source":"crossref"},{"id":"doi:10.1007/s11119-025-10227-3","type":"article-journal","title":"Cauliflower centre detection and 3-dimensional tracking for robotic intrarow weeding","abstract":"Mechanical weeding is an important part of integrated weed management. It destroys weeds between (interrow) and in (intrarow) crop rows. Preventing crop damage requires precise detection and tracking of the plants. In this work, a detection and tracking algorithm was developed and integrated on an intrarow hoeing prototype. The algorithm was developed and validated on 12 rows of 950 cauliflower plants. Therefore, a methodology was provided to automatically generate a label based on the crop plants’ Global Navigation Satellite System (GNSS) position during data collection with a robot platform. A CenterNet architecture was adjusted for plant centre detection by comparing different encoder networks and selecting the optimal hyperparameters. The monocular camera projection error of the plant centre detections in pixel to 3D coordinates was evaluated and used in a position- and velocity-based tracking algorithm to determine the timing for intrarow hoeing knife actuation. A dataset of 53k labelled images was created. The best CenterNet model resulted in an F1 score on the test set of 0.986 for detecting cauliflower centres. The position tracking had an average variation of 1.62 cm. Velocity tracking had a standard deviation of 0.008 [Formula: see text] with respect to the robot’s operational target velocity. Overall, the entire integration showed effective actuation of the prototype in field conditions. Only one false positive detection occurred during operation in two test rows of 135 cauliflowers.","author":[{"family":"Willekens","given":"Axel"},{"family":"Callens","given":"Bert"},{"family":"Wyffels","given":"Francis"},{"family":"Pieters","given":"Jan"},{"family":"Cool","given":"Simon"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10227-3","URL":"https://doi.org/10.1007/s11119-025-10227-3","source":"crossref"},{"id":"doi:10.1109/amathe65477.2025.11081252","type":"article-journal","title":"Smart NFT based Hydroponic System for Precision Agriculture using IoT and AI","abstract":"Precision agriculture (PA) presents numerous possibilities to address the growing challenges of sustainability and food security. To develop an effective PA system, it is essential to collect and analyze real-time data using Artificial Intelligence (AI) methodologies. This research integrates the Internet of Things (IoT) and AI within a Nutrient Film Technique (NFT) hydroponic system for the growth of the Holy basil plant. The aim is to create an ideal indoor environment through optimized resource management. This involves establishing an IoT-enabled framework for real-time data collection to monitor $\\mathbf{p H}$, temperature, humidity, and dissolved substances, affecting both artificial conditions and plant growth rates. The AI processes these data to fine-tune the environment and perform the necessary automated adjustments within the PA system. In addition, AI-driven predictive models will anticipate plant growth patterns and ensure a robust crop management system with precise yield predictions. Addressing these areas is crucial for the successful application of IoT and AI in PA systems. The Random Forest machine learning (ML) model predicts the yield in cm with an accuracy of 97%, while XGBoost is used to predict the NPK dosing with an accuracy of 99%.","author":[{"family":"Chetan","given":"R"},{"family":"Asha","given":"CS"},{"family":"Rao","given":"PR"},{"family":"Suresh","given":"Shilpa"},{"family":"Guruprasad"},{"family":"Kumar","given":"Dhanush"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/amathe65477.2025.11081252","URL":"https://doi.org/10.1109/amathe65477.2025.11081252","source":"crossref"},{"id":"doi:10.1109/icesc65114.2025.11212629","type":"article-journal","title":"A Multilingual LLM-Driven Digital Twin Framework for Climate Resilient Precision Agriculture","abstract":"The emergence of smart agriculture is gaining traction in the age of climate change, food insecurity, and unsustainable farming practices. However, existing Agri-tech solutions seldom provide personalized support and assistance to rural Indian farmers, who mostly grapple with linguistic pluralism, weak infrastructure, and low digital literacy. These systems are sorely needed to address challenges like climate variability, offline operability, and native language communication. With great advances in technology, affordably utilizing Digital Twin-type solutions, large language models (LLMs), and multilingual NLP, the challenge is often with their isolation from one another. The current agricultural advisory tools are not sufficiently grounded in real-time sensor data, don’t lend themselves easily to large-scale regional diversity in language, and are steadily urban-portrayed for access through a cloud infrastructure. There are also problems around the hallucination abilities of LLMs and the low interpretability of the recommendations of AI-augmented tools. This paper suggests an LLM-augmented, modular, and multilingual architecture for IoT-driven Digital Twins, agricultural knowledge graphs, and real-time edge AI deployment for explainable and multilingual advisories to smallholder farmers. The system supports more than 10 Indian languages through Whisper and IndicTrans2 and can run offline on edge devices such as Raspberry Pi. It is showcased in the case studies of voiceassisted fertilizer application, climate-smart irrigation, pest detection, and crop rotation optimization. This system demonstrates a significant progression in creating an inclusive, sustainable, and intelligence-driven farming culture in underresourced settings. The field trials in Rhaga, Tamil Nadu, and Maharashtra proved the advisory accuracy of $93.1 \\%$ and BLEU scores exceeding 82 across 12 Indian languages and an average inference latency of 2.3 seconds at the lowest exceeded existing systems in multilingual capability, contextual precision, and offline operability.","author":[{"family":"Alexander","given":"R"},{"family":"Janet","given":"AMV"},{"family":"Sri","given":"RV"},{"family":"Sasirekha","given":"S"},{"family":"Kathyani","given":"Avuduri"},{"family":"Priya","given":"VS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icesc65114.2025.11212629","URL":"https://doi.org/10.1109/icesc65114.2025.11212629","source":"crossref"},{"id":"doi:10.1109/cloudcom67567.2025.11331405","type":"article-journal","title":"HRL-ViT: Human–Robot Collaborative Vision Transformer for AIoT-Enabled Leaf Disease Detection in Precision Agriculture","abstract":"The combination of artificial intelligence and Internet of Things (AIoT) technologies is changing precision agriculture by making it possible to automatically check the health of crops. Early detection of leaf diseases is still important for stopping yield losses, but regular convolutional neural networks (CNNs) often don't work as well when they have to deal with different textures, lighting changes, and noise on the field level. To address these constraints, this study presents HRL-ViT, a Human–Robot Collaborative Learning framework that utilizes Vision Transformers for leaf disease identification. The frame-work merges the global attention feature of Vision Transformers with a human-in-the-loop approach, wherein predictions with low confidence are validated by experts and used to improve the model over time. The system is also made for edge-based AIoT deployment, which lets you analyze data in real time in agricultural settings. Experimental research utilizing both benchmark datasets and field-acquired images demonstrates that HRL-ViT consistently surpasses baseline CNN and Transformer models, attaining superior accuracy, precision, and recall while minimizing false detections. Transformers' attention maps can be visualized to make them even easier to understand, which helps users trust them and make decisions. In general, HRL-ViT shows a lot of promise for use in autonomous robotic platforms. It offers an explainable and scalable way to find diseases in precision agriculture.","author":[{"family":"Champatiray","given":"Chiranjibi"},{"family":"Samal","given":"Sonali"},{"family":"Gadekellu","given":"Thippa"},{"family":"Srivastava","given":"Gautam"},{"family":"Bahubalendruni","given":"Mva"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/cloudcom67567.2025.11331405","URL":"https://doi.org/10.1109/cloudcom67567.2025.11331405","source":"crossref"},{"id":"doi:10.1145/3767624.3767635","type":"article-journal","title":"Design and testing of a high-speed precision hole sowing seed supply device for pelletized rice seed.","abstract":"To solve the limitations of mechanical rice hole sowing seed dispensers, which are bulky and difficult to adapt to the complex terrain, and to fill the technical gap of UAV rice precision hole sowing, this paper proposes a method of applying UAV rice precision hole sowing after pelletizing rice and designs a simple structure and adjustable sowing volume of Pelletized rice seeds (PR) precision hole sowing seed supplying device. The structure and working principle of the seed supply device were described, the main relevant parameters were analyzed and determined, the mechanical model of the seed filling process of PR was constructed, the experimental study of seed supply performance was carried out by taking the number of holes and the rotational speed of the hole wheel as the experimental factors, and the seed breakage rate and the qualified rate of seed supply as the experimental indexes, and the quadratic regression model of the number of holes and the rotational speed of the hole wheel was also established. The test showed that under the conditions of 1-5 perforated wheels and 20-100r/min working speed, the seed breakage rate and qualified rate of PR in the process of seed supply showed an increasing and then decreasing trend with the increase of the number of perforated wheels and the rotational speed; when the rotational speed of the seed discharge wheel is 71r/min and the number of holes is 8, the seed supply stability of the device is better, and its seed breakage rate B is 0.677%, and the seed supply qualification rate \\({Q}_g\\) is 99.21%. The design and test of the pelletized rice high-speed precision rice hole sowing device can provide a reference and basis for the development of the UAV precision rice hole sowing device (UPR).","author":[{"family":"Ma","given":"Qianshu"},{"family":"Li","given":"Tongjie"},{"family":"Jiang","given":"Chunxia"},{"family":"Xu","given":"Donghan"},{"family":"Zhang","given":"Xiaolong"},{"family":"Wang","given":"Qingqing"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1145/3767624.3767635","URL":"https://doi.org/10.1145/3767624.3767635","source":"crossref"},{"id":"doi:10.1109/incsst64791.2025.11210290","type":"article-journal","title":"IoT-Driven Real-Time Soil Health Monitoring for Precision Agriculture Using Bi-Directional Transformer-CNN Models","abstract":"Global population growth has fuelled food consumption for 60 years. The Green Revolution and genetically altered crops addressed this issue. Synthetic fertilisers, herbicides, and GMO seeds improve productivity. Simple treatments may hurt people and the environment. Precision agriculture, a greener method, optimises farming techniques by monitoring soil health, temperature, moisture, and weather. Using data-driven precision agriculture, this study uses a CNNTransformer hybrid model to evaluate soil health. Transformer-based architectures examine sequential data and CNNs extract features. WICL and LFS improve soil parameter estimates and resolve missing data. CNNTranNet outperformed other machine learning methods with $98 \\%$ accuracy. Deep learning and random forest classifiers predicted soil temperature, climate, and moisture content to improve crop selection and production. Tech innovation and environmental conservation must be balanced to maintain agricultural yield. The CNNTranNet model delivers accurate and efficient soil health monitoring for precision agriculture data-driven decision-making. This method can improve food security and sustainability by picking crops by soil type.","author":[{"family":"Bajpai","given":"Chhavi"},{"family":"Ramesh","given":"Cindhe"},{"family":"Aravindhan","given":"K"},{"family":"Prajna","given":"KB"},{"family":"Praveena","given":"S"},{"family":"Sreetharan","given":"V"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/incsst64791.2025.11210290","URL":"https://doi.org/10.1109/incsst64791.2025.11210290","source":"crossref"},{"id":"doi:10.1109/iceconf65644.2025.11379441","type":"article-journal","title":"Soil Moisture-Based Intelligent Irrigation System with IoT and Cloud Computing for Precision Agriculture and Water Conservation","abstract":"The modern global trend towards sustainable agricultures and efficient water resources management enforces smart irrigation systems. This study presents Soil Moisture-Based Intelligent Irrigation System based on loT sensors, cloud computing and AI based prediction model that is used to optimize the use of water in precision agriculture. Majority of which were calibrated volumetric water content (VWC) references to capacitive soil moisture probes that were introduced into agricultural zones and were monitored in real-time. The data provided by loT -enabled microcontrollers (Arduino with LoRa modules) was transmitted to an edge gateway where the signal was enhanced by noise removal and time-series smoothing prior to cloud upload. A Long ShortTerm Memory (LSTM) model was used to anticipate trends in soil moisture by using environmental data including rainfall, humidity, and temperature. Predictions were made and the system operated the solenoid valves in the areas where irrigation was necessary minimizing water wastage and increasing the efficiency. Findings have shown that the system kept the soil moisture level within a range of 2% of target desirable soil moisture levels with an average of 98.7% accuracy in all the irrigation. Water savings of 25-27% relative to manual techniques of irrigation were found using a comparative analysis, and node duty cycling brought in savings of the battery life of the devices of 65-70%. The dashboard on the cloud enabled farm owners to remotely supervise condition in the field, set alarms and operate irrigation. Generally, the idea to combine the incorporation of loT and AI produced significant efficiency gains in irrigation, water savings, and operational stability. This framework has the potential to be implemented across a very large scale in the agricultural sector particularly in water-stressed areas.","author":[{"family":"Jananil","given":"M"},{"family":"Benisha","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iceconf65644.2025.11379441","URL":"https://doi.org/10.1109/iceconf65644.2025.11379441","source":"crossref"},{"id":"doi:10.1109/agro-geoinformatics66479.2025.11136213","type":"article-journal","title":"Adapting Vision-Language Models for Precision Agriculture: A Study on Crop Segmentation based on UAV Remote Sensing Data","abstract":"With increasing global food security challenges, agricultural remote sensing image analysis has become particularly important for improving production efficiency and resource utilization in precision agriculture. However, traditional crop segmentation methods for UAV remote sensing images rely heavily on large amounts of labeled data and specialized deep learning architectures, which pose significant challenges for practical agricultural applications due to high annotation costs and limited model generalization. Although general vision-language models (VLMs) have demonstrated remarkable capabilities in natural image understanding, their effectiveness in processing specialized agricultural remote sensing data, particularly for precise crop segmentation tasks, remains largely unexplored.This research proposes a novel approach that adapts multimodal large language models for crop segmentation in UAV remote sensing images by reformulating the segmentation task as a conversational format. Our method transforms traditional pixel-level segmentation into a text-based coordinate prediction task, where segmentation masks are converted to polygon coordinates and represented in XML format. To address the unique characteristics of agricultural remote sensing data, we designed two types of conversational prompts: general object segmentation and crop-specific segmentation.Methodologically, we introduce a coordinate-to-text conversion strategy that transforms segmentation labels into structured XML tags containing polygon coordinates, enabling VLMs to perform segmentation through natural language generation. We systematically evaluate four state-of-the-art vision-language models (Qwen2-VL-7B, Qwen2.5-VL-7B, LLaVA-1.5-7B, and LLaMA3-LLaVA-Next-8B) using Low-Rank Adaptation (LoRA) fine-tuning techniques that selectively optimize only the language model components while keeping the visual encoders frozen.Experimental validation demonstrates that adapted VLMs can effectively perform crop segmentation tasks with varying degrees of success across different crop types. Qwen2-VL achieves the best overall performance with an F1-score of 49.16% and IoU of 46.61%, significantly outperforming other models. Notably, tobacco segmentation shows superior results (F1: 78.42%, IoU: 75.64%) compared to corn and barley, indicating crop-specific adaptation capabilities. The results reveal that while VLM-based approaches may not yet match specialized segmentation models in absolute accuracy, they offer unique advantages in few-shot learning scenarios and provide a promising foundation for developing more generalizable agricultural remote sensing solutions.","author":[{"family":"Bie","given":"Yuhui"},{"family":"Xu","given":"Guowei"},{"family":"Wang","given":"Yaojun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/agro-geoinformatics66479.2025.11136213","URL":"https://doi.org/10.1109/agro-geoinformatics66479.2025.11136213","source":"crossref"},{"id":"doi:10.1051/e3sconf/202560100022","type":"article-journal","title":"Plantonome: A Cross-Platform Application for Precision Agriculture","abstract":"In recent years, there has been growing interest in leveraging the Internet of Things (IoT) and Artificial Intelligence (AI) technologies for agriculture. A significant challenge for developers in this field is creating applications that provide precise data about plants, facilitating the smart automation of plant management. This paper presents Plantonome, an open-source application developed using the Flutter software development kit (SDK) and the Dart programming language. Designed to integrate with IoT devices, Plantonome quickly and accurately identifies ornamental plant genera or species using the Plant.id API for plant image analysis. The application also utilizes a NoSQL database for storing user data and plant preferences, and it includes a dataset of ornamental plants with details such as name, brightness, temperature, and humidity requirements. The development approach outlined in this paper accelerates the creation process and results in a high-performing application with a flexible user interface and smooth user experience. The application, tested on Android 5.0 (API level 21) or higher, achieved an accuracy of 94.64% for plant identification and received highly positive feedback regarding its functionality, usability, and efficiency. This work offers significant benefits to researchers and startups aiming to develop cross-platform applications that can automate various agricultural tasks, contributing to advancements in smart agriculture.","author":[{"family":"Deroussi","given":"Anass"},{"family":"Madi","given":"Abdessalam"},{"family":"Alihamidi","given":"Imam"},{"family":"Chabou","given":"Zakaria"},{"family":"Addaim","given":"Adnane"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1051/e3sconf/202560100022","URL":"https://doi.org/10.1051/e3sconf/202560100022","source":"crossref"},{"id":"doi:10.1109/citce67565.2025.11360007","type":"article-journal","title":"Soil Moisture Prediction Based on RoPE and Physical Condition Constraints Using Transformer for Precision Agriculture","abstract":"Precise prediction of soil moisture is the foundation of precision agriculture. This paper employs a Transformer deep learning model to achieve soil moisture prediction and addresses the issue of the model producing results that violate physical laws by introducing rotational position encoding and physical condition constraints, thereby enhancing model performance. Rotational position encoding improves the model’s ability to process spatiotemporal soil moisture data, while physical condition constraints impose constraints on the prediction results to ensure they adhere to physical laws, thus improving the accuracy of soil moisture prediction. Compared to traditional Transformer, the proposed SPD-RoFormer model in this paper improves $R^{2}$ by 22.68%, reduces $R M S E$ by 0.4252, decreases $M A E$ by 0.3264, and increases $R P D$ by $\\mathbf{1 0. 5 0 9 4}$. This method effectively resolves the problem of soil moisture predictions easily violating physical laws, enhances the model’s predictive capability, and provides effective assistance in fields such as soil irrigation, agricultural production, and climate prediction.","author":[{"family":"Yang","given":"Hongwei"},{"family":"Jiang","given":"Dongyao"},{"family":"Huo","given":"Mingchao"},{"family":"Han","given":"Xu"},{"family":"Feng","given":"Xin"},{"family":"Zhang","given":"Jing"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/citce67565.2025.11360007","URL":"https://doi.org/10.1109/citce67565.2025.11360007","source":"crossref"},{"id":"doi:10.3390/rs17183227","type":"article-journal","title":"A Spatially Comprehensive Water Balance Model for Starch Potato from Combining Multispectral Ground Station and Remote Sensing Data in Precision Agriculture","abstract":"The measurement of available water for agricultural plants is a crucial parameter for farmers, particularly to plan irrigation. However, an area-wide measurement is often not trivial as there are several inputs and outputs of water into the system. Here, we present a high-resolution, remote sensing-based water balance model for starch potato cultivation, combining multispectral ground station data with UAV and satellite imagery. Over a three-year period (2021–2023), data from Arable Mark 2 ground stations, DJI Phantom 4 MS drones, PlanetScope satellites, and Sentinel-2 satellites were collected in Mecklenburg–Western Pomerania, Germany. The model utilizes NDVI-based crop coefficients (R2 = 0.999) to estimate evapotranspiration and integrates on-farm irrigation and precipitation data for precise water balance calculations. A correlation with reference NDVI observations by Arable Mark 2 systems can be shown for UAV (R2 = 0.94), PlanetScope satellite data (R2 = 0.94), and Sentinel-2 satellite data (R2 = 0.93). We demonstrate the model’s ability to capture intra-site heterogeneity on a precision farming scale. Our spatially comprehensive model enables farmers to optimize irrigation strategies, reducing water and energy use. Although the results are based on sprinkler irrigation, the model remains adaptable for advanced irrigation methods such as drip and subsurface systems.","author":[{"family":"Piernicke","given":"Thomas"},{"family":"Kunz","given":"Matthias"},{"family":"Itzerott","given":"Sibylle"},{"family":"Wenzel","given":"Jan"},{"family":"Pöhlitz","given":"Julia"},{"family":"Conrad","given":"Christopher"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/rs17183227","URL":"https://doi.org/10.3390/rs17183227","source":"crossref"},{"id":"doi:10.1109/ispa67752.2025.00173","type":"article-journal","title":"A Computational Memory Module with Geolocation Query Engine for Precision Agriculture","abstract":"In precision agriculture, the integration of spatial information through Geographic Information System (GIS) plays a crucial role in optimizing agricultural operations. However, the increasing scale of spatial data poses computational challenges to traditional processor-centric solutions used in GIS due to memory limitations: limited memory capacity and low bandwidth. An architecture shift from processor-centric to memory-centric is necessary for modern data-intensive applications. To overcome the memory bottleneck issues, this paper introduces a novel, callable, pipelined solution in Processing Near Memory (PNM) configuration with large memory capacity and high inner bandwidth tailored for memory-intensive precision agriculture applications. The solution leverages a scalable Computational Memory Module (CMM) with a Geolocation Query Engine (GQE), which addresses the k-Nearest Neighbors (kNN) search problem, a fundamental computation used in GIS for various geolocation queries. Our experimental evaluation, conducted on three distinct datasets, showcased the effectiveness of our proposed CMM. These datasets include a substantial Wheat big data set consisting of 17,847 daily trajectories, as well as smaller Paddy and Corn datasets containing 1,634 and$\\text{1, 2 9 0}$daily trajectories, respectively. In these experiments, our CMM consistently achieved an impressive$\\text{9 5 \\%}$and$\\text{9 9 \\%}$average reduction in query times and energy consumption compared to conventional processor-centric approaches, respectively. By efficiently managing large-scale spatial data, the proposed solution empowers precision agriculture, contributing to increased productivity, sustainability, and profitability in modern agricultural practices.","author":[{"family":"Qie","given":"Jinge"},{"family":"Chen","given":"Ying"},{"family":"Zhang","given":"Xiaoqiang"},{"family":"Shen","given":"Yongshuai"},{"family":"Li","given":"Yi"},{"family":"Pan","given":"Jinlong"},{"family":"Zhang","given":"Yunsen"},{"family":"Dai","given":"Jin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ispa67752.2025.00173","URL":"https://doi.org/10.1109/ispa67752.2025.00173","source":"crossref"},{"id":"doi:10.33545/2618060x.2025.v8.i11sf.4300","type":"article-journal","title":"Advancements in GIS for precision agriculture: Enhancing soil management and crop yield prediction","abstract":"Precision agriculture has emerged as a transformative paradigm in modern farming, driven by the integration of Geographic Information Systems (GIS), remote sensing, and data analytics. This review paper critically examines the role of GIS in optimising soil management and enhancing the accuracy of crop yield predictions. We analyse how spatial data infrastructures enable the transition from uniform field management to site-specific interventions, thereby improving resource efficiency and sustainability. The discussion encompasses the application of geostatistics to map soil nutrient variability, the deployment of Variable Rate Technology (VRT) for precise input application, and the use of multi-temporal satellite imagery to monitor crop phenology. Furthermore, we evaluate integrating machine learning algorithms with geospatial datasets to refine yield forecasting models. Special emphasis is placed on the Indian agricultural context, highlighting how GIS interventions address challenges related to small landholdings and climatic variability. The review concludes that while technical and economic barriers persist, the convergence of GIS with emerging technologies such as the Internet of Things (IoT) and Unmanned Aerial Vehicles (UAVs) offers a robust pathway toward global food security and climate-resilient agriculture.","author":[{"family":"Indiakar","given":"Sohail"},{"family":"Nadaf","given":"Bebijan"},{"family":"Deshpande","given":"Niyaz"},{"family":"Deshmukh","given":"Harshada"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/2618060x.2025.v8.i11sf.4300","URL":"https://doi.org/10.33545/2618060x.2025.v8.i11sf.4300","source":"crossref"},{"id":"doi:10.21926/rpse.2502006","type":"article-journal","title":"Simulation Software in the Design and AI-Driven Automation of All-Terrain Farm Vehicles and Implements for Precision Agriculture","abstract":"Precision agriculture depends on the automation and mechanization of agricultural equipment and vehicles in a variety of terrains, which increases productivity and sustainability. This review presents a comparative analysis of significant simulation software used in designing and developing automated agricultural systems, emphasizing their methodologies and significance in advancing farm technology. Artificial intelligence (AI) and machine learning (ML) methods are modeled, optimized, and integrated using key technologies such as MATLAB/Simulink, SolidWorks, ANSYS, AirSim, and Gazebo. The results demonstrate how these technologies improve agricultural automation's real-time decision-making, predictive maintenance, and system accuracy. Case studies illustrate their practical application in simulating all-terrain farm vehicles and specialized implements. The best tools for simulating autonomous navigation are AirSim and Gazebo, although MATLAB/Simulink is particularly adept at system-level AI modeling. This study takes a new approach to improving design, control, and environmental interactions by combining many modeling tools. This makes it easier to make agricultural automation systems that last longer and work better. It is suggested that future studies investigate the relationship between agricultural automation, AI, and simulation in greater detail to propel precision agriculture forward.","author":[{"family":"Padhiary","given":"Mrutyunjay"},{"family":"Roy","given":"Pankaj"},{"family":"Kumar","given":"Kundan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21926/rpse.2502006","URL":"https://doi.org/10.21926/rpse.2502006","source":"crossref"},{"id":"doi:10.1016/j.rineng.2025.104081","type":"article-journal","title":"Critical regions identification and coverage using optimal drone flight path planning for precision agriculture","abstract":"The use of drones in precision agriculture results in better resource management and effective decision making, particularly in the context of saving water resources and increasing crop yield. However, planning the optimal flight path for a drone to cover a given set of irrigation points is a challenging problem. In this paper, a novel method is proposed that combines image processing, data clustering, and heuristic algorithms to solve this problem. A drone-mounted camera is used to capture the multispectral image of a given land area. The proposed approach applies pre-processing steps to refine the collected image data. Contextual information is used to identify the areas of interest in the segmented image and a pool of these points is created. The K-means clustering algorithm is used to group points into clusters based on their proximity. For each cluster, the 2-opt heuristic algorithm is applied to find an approximate solution to the Traveling Salesman Problem (TSP), which minimizes the total distance traveled by the drone within the cluster. Then, the representative point of each cluster is found by computing the mean point and selecting the closest point to it. Finally, the 2-opt algorithm is applied again to connect the representative points of all clusters, thus forming a complete flight path for the drone. The method is evaluated on simulated and real-world data collected by the drone, and the result shows that the proposed approach produces efficient and feasible solutions for drone semantic localization and coverage. The experimental analysis shows 22% and 46% improvement over the basic approach without K-means clustering and a K-means no parallel approach. • Finding the critical growth patterns in the video data. • Finding the regions of interest in the image data. • Finding the different possible regions in the image data. • Generating manual labels for the extracted regions using domain knowledge. • Planning a path to connect all critical regions.","author":[{"family":"Menon","given":"Bharath"},{"family":"Deshpande","given":"Tanmay"},{"family":"Pal","given":"Amrit"},{"family":"Kothandaraman","given":"Saravanan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.rineng.2025.104081","URL":"https://doi.org/10.1016/j.rineng.2025.104081","source":"crossref"},{"id":"doi:10.3390/agriculture15090936","type":"article-journal","title":"An Improved YOLOv8 Model for Detecting Four Stages of Tomato Ripening and Its Application Deployment in a Greenhouse Environment","abstract":"The ripeness of tomatoes is a critical factor influencing both their quality and yield. Currently, the accurate and efficient detection of tomato ripeness in greenhouse environments, along with the implementation of selective harvesting, has become a topic of significant research interest. In response to the current challenges, including the unclear segmentation of tomato ripeness stages, low recognition accuracy, and the limited deployment of mobile applications, this study provided a detailed classification of tomato ripeness stages. Through image processing techniques, the issue of class imbalance was addressed. Based on this, a model named GCSS-YOLO was proposed. Feature extraction was refined by introducing the RepNCSPELAN module, which is a lightweight alternative that reduces model size. A multi-dimensional feature neck network was integrated to enhance feature fusion, and three Semantic Feature Learning modules (SGE) were added before the detection head to minimize environmental interference. Further, Shape_IoU replaced CIoU as the loss function, prioritizing bounding box shape and size for improved detection accuracy. Experiments demonstrated GCSS-YOLO’s superiority, achieving an average mean average precision mAP50 of 85.3% and F1 score of 82.4%, outperforming the SSD, RT-DETR, and YOLO variants and advanced models like YOLO-TGI and SAG-YOLO. For practical deployment, this study deployed a mobile application developed using the NCNN framework on the Android platform. Upon evaluation, the model achieved an RMSE of 0.9045, an MAE of 0.4545, and an R2 value of 0.9426, indicating strong performance.","author":[{"family":"Sun","given":"Haoran"},{"family":"Zheng","given":"Qi"},{"family":"Yao","given":"Weixiang"},{"family":"Wang","given":"Junyong"},{"family":"Liu","given":"Changliang"},{"family":"Yu","given":"Huiduo"},{"family":"Chen","given":"Chunling"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15090936","URL":"https://doi.org/10.3390/agriculture15090936","source":"crossref"},{"id":"doi:10.1016/j.iot.2025.101535","type":"article-journal","title":"Bridging FANETs and MANETs for synchronous data collection in precision agriculture activities using AirPro-FL: An energy aware fuzzy logic routing protocol","abstract":"The use of Flying Ad-hoc Networks (FANETs) in precision agriculture requires the development of advanced routing protocols to manage UAV-specific challenges effectively. This paper presents AirPro-FL, a proactive routing protocol that uses fuzzy logic to optimize UAV performance in precision agriculture tasks. Unlike conventional FANET research, which often relies on stochastic mobility models that do not accurately reflect real-world agricultural missions, AirPro-FL is designed to address these gaps by enhancing UAV cooperation in scanning operations such as crop scouting, crop surveying and mapping, spraying applications, and geofencing. Traditionally, these agricultural activities rely on a single UAV, often resulting in inefficiencies. The UAV’s limited real-time data transmission capabilities, vulnerability to operational failures, and potential mission execution delays contribute to reduced overall effectiveness. The proposed system involving multiple UAVs significantly speeds up mission completion and enables real-time data transfer through the cooperation between FANETs and Mobile Ad-hoc Networks (MANETs). This innovation empowers agricultural stakeholders to make faster and more reliable decisions based on accurate data collection. Simulation results indicate that AirPro-FL consistently achieves the highest Packet Delivery Ratio (PDR) across all scenarios, halves the average end-to-end delay compared to the second-best protocol, and exhibits superior energy efficiency. The protocol’s success in optimizing data collection during scanning operations underscores its broader applicability beyond agriculture, extending to other fields such as environmental monitoring, disaster management, and surveillance, where similar mobility patterns are employed.","author":[{"family":"Kakamoukas","given":"Georgios"},{"family":"Economides","given":"Anastasios"},{"family":"Bibi","given":"Stamatia"},{"family":"Sarigiannidis","given":"Panagiotis"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.iot.2025.101535","URL":"https://doi.org/10.1016/j.iot.2025.101535","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i1.12643","type":"article-journal","title":"PERTUMBUHAN DAN PRODUKSI POHPOHAN (Pilea trinervia Wight.) PADA PEMBERIAN AIR LIMBAH BUDIDAYA IKAN NILEM DENGAN BERBAGAI TINGKAT KEPADATAN","abstract":"Pohpohan (Pilea trinervia Wight) merupakan sayuran indigenous yang memiliki potensial komersial, namun budidayanya masih terbatas. Pemanfaatan air limbah budidaya ikan nilem sebagai sumber nutrisi alternatif dapat mendukung pertumbuhan tanaman ini. Penelitian ini bertujuan untuk mengetahui pertumbuhan dan produksi pohpohan yang disiram dengan air limbah budidaya ikan nilem pada berbagai tingkat kepadatan. Penelitian menggunakan Rancangan Acak Kelompok satu faktor dengan empat perlakuan tingkat kepadatan air limbah, yaitu kontrol (menggunakan nutrisi hidroponik), kepadatan 10, 20, dan 30. Hasil penelitian menunjukan bahwa pemberian air limbah budidaya ikan nilem berpengaruh nyata pada sebagian besar parameter pertumbuhan dan produksi yang diamati, kecuali diameter batang, panjang akar, bobot segar total dan bobot segar akar. Perlakuan kontrol, kepadatan 20, dan kepadatan 30, secara konsisten meningkatkan tinggi tanaman, jumlah daun, jumlah tunas, luas daun, bobot tajuk basah dan bobot tajuk kering dibandingkan dengan kepadatan 10. Tetapi pada kepadatan 10, kepadatan 20 dan kepadatan 30 menunjukkan hasil yang tidak berbeda. Air limbah ikan nilem pada kepadatan 20 dan 30 memiliki kandungan unsur hara yang cukup untuk mendukung kebutuhan pertumbuhan tanaman pohpohan. Air limbah budidaya ikan nilem berpotensi menjadi sumber nutrisi alternatif yang ramah lingkungan untuk mendukung budidaya tanaman pohpohan secara berkelanjutan.","author":[{"family":"Yulianti","given":"Nani"},{"family":"Mumfuni","given":"Fia"},{"family":"Hermawan","given":"Ilham"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35760/jpp.2025.v9i1.12643","URL":"https://doi.org/10.35760/jpp.2025.v9i1.12643","source":"crossref"},{"id":"doi:10.1109/icrteect67512.2025.11448629","type":"article-journal","title":"Smart Farming with IoT and AI: Enhancing Precision Agriculture through Sensor Networks","abstract":"Precision agriculture received a major transformation through the Internet of Things which introduced real-time crop health monitoring capabilities. This article provides an extensive study about smart crop monitoring systems enabled by IoT technology for sustainable precision agriculture. Internet of Things (IoT) together with Artificial Intelligence (AI) guide smart farming through technological improvements that increase operational precision and efficiency in modern agricultural practices. Through this research the study explores how IoT-based sensor networks gather real-time measurements from agricultural parameters which include soil moisture content and temperature measurements along with humidity data and crop health indicators. AI uses analyzed information to deliver predictive evaluations together with automated choices which optimize major agricultural operations including irrigation and fertilization and pest management and production forecasting. Precise agricultural practices gain increased success, environmental protection, and resource management from the combination of IoT and AI systems which allow farmers to base their choices on data. The analysis capabilities of AI help farmers detect diseases early and adapt to climate changes by preventing risks from unanticipated weather patterns. Smart farming addresses increasing global food demands for sustainable production by overcoming privacy concerns and implementation expenses and infrastructure barriers. The combination of IoT with AI creates a transformational force which enables more efficient and environmentally conscious and intelligent agricultural practices. The complete potential of smart farming will remain unreachable without ongoing technological research efforts and innovation to guarantee worldwide food security.","author":[{"family":"Sirisha","given":"Ch"},{"family":"Kumar","given":"HMG"},{"family":"Kishore","given":"GU"},{"family":"Soujanya","given":"Maisa"},{"family":"Drtthirumalaikumari"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icrteect67512.2025.11448629","URL":"https://doi.org/10.1109/icrteect67512.2025.11448629","source":"crossref"},{"id":"doi:10.1109/incet64471.2025.11139861","type":"article-journal","title":"Advanced Detection of Coconut Stem Bleeding Using an Improved YOLOv5 Model for Precision Agriculture","abstract":"Coconut stem bleeding is a critical agricultural challenge threatening the health and productivity of coconut trees, a vital cash crop in tropical regions and a primary source of income for many farming communities. Early and accurate detection is essential to mitigate agricultural losses and promote sustainable farming. This study introduces a novel YOLOv5-based framework for real-time detection of stem bleeding in coconut trees, prioritizing accuracy, scalability, and practicality.The methodology integrates advanced preprocessing techniques like histogram equalization and 2D wavelet transformation with a dataset enhanced using Mosaic data augmentation for improved diversity. Adaptive anchor box calculation and grid sensitivity elimination enhance detection precision and localization accuracy. Adaptive image scaling ensures uniform input dimensions, optimizing inference speed without compromising performance. These innovations address challenges such as object size variability, lighting conditions, and real-time efficiency.The YOLOv5 framework achieved 97% detection accuracy, a mean average precision (mAP) of 96.23%, precision of 87.42%, recall of 95.32%, and an F1-score of 83.65%. Comparative analysis with CNN, VGG16, and traditional image processing highlights its superiority in accuracy and real-time applicability.This framework empowers farmers to implement immediate interventions, reducing disease spread and crop losses. Beyond technical contributions, it offers economic and social benefits by reducing yield losses and management costs, fostering financial resilience for farmers. Its adaptability to other crops underscores its global relevance, setting a benchmark for intelligent, data-driven solutions in precision agriculture.","author":[{"family":"Hiremath","given":"Jayaprada"},{"family":"Karchi","given":"Rashmi"},{"family":"Hiremath","given":"Mrutyunjaya"},{"family":"Patil","given":"Mallangowda"},{"family":"Sivanandan","given":"Sujith"},{"family":"Hiremath","given":"Shantala"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/incet64471.2025.11139861","URL":"https://doi.org/10.1109/incet64471.2025.11139861","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101629","type":"article-journal","title":"Artificial intelligence of things (AIoT) for precision agriculture: applications in smart irrigation, nutrient and disease management","abstract":"Despite the growing global demand for efficient and sustainable agricultural practices, many traditional farming systems still rely on manual decision-making, which can be inefficient and resource intensive. This review comprehensively examines the applications of Artificial Intelligence of Things (AIoT) in three critical domains of precision agriculture, such as smart irrigation, nutrients and disease management. Through the deployment of interconnected sensor networks, edge and cloud computing platforms, and AI algorithms, AIoT systems facilitate site-specific monitoring and control key environmental and crop parameters. In irrigation, AIoT empowers farmers to optimize water distribution through real-time soil moisture sensing, predictive analytics and dynamic irrigation scheduling. Precision nutrient management utilizes unmanned aerial aehicles , soil sensors, and AI-powered data analysis to monitor nutrient availability and inform optimized fertilization strategies, thereby improving nutrients efficiency and reducing environmental degradation. Similarly, AIoT in disease management enhances surveillance and predictive capabilities by integrating sensor data with AI models to early detect abiotic stresses, enabling timely and targeted interventions. Although the significant benefits of AIoT, its implementation faces several challenges. These include high setup costs, data connectivity issues in rural areas, inconsistent sensor reliability, cybersecurity risks, and limited scalability for smallholder farming systems. Additionally, gaps in technical knowledge and infrastructure pose barriers to widespread adoption. However, advancements in 5G technology, edge computing, and sensor miniaturization offer promising avenues for scaling AIoT in agriculture. This review therefore highlights the transformative potential of AIoT in improving climate-smart and sustainable agriculture by converting data into actionable insights to enhance resilience and food security.","author":[{"family":"Bayar","given":"Jalal"},{"family":"Ali","given":"Nawab"},{"family":"Cao","given":"Zhichao"},{"family":"Ren","given":"Yidong"},{"family":"Dong","given":"Younsuk"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101629","URL":"https://doi.org/10.1016/j.atech.2025.101629","source":"crossref"},{"id":"doi:10.1109/ickecs65700.2025.11035106","type":"article-journal","title":"AgriChainSync: A Scalable and Secure Blockchain-Enabled Framework for IOT-Driven Precision Agriculture","abstract":"The advancement of smart farming, a crucial aspect of the Internet of Things (IoT), facilitates data-driven insights to enhance agricultural efficiency. However, the widespread deployment of IoT devices presents notable concerns related to data security and integrity. This paper introduces AgriChainSynch, a robust framework integrating blockchain, IoT, and artificial intelligence (AI) to strengthen the security, privacy, and operational efficiency of smart farming ecosystems. The framework utilizes a distributed ledger system to ensure tamper-proof data management, incorporates a Blockchain Integration Layer (BIL) for scalability, and features a Feedback and Adaptation Module (FAM) for continuous performance enhancement. By leveraging AWS Cloud, ESP32, and Ethereum Rinke by smart contracts, the system is capable of detecting and mitigating security threats in real time. Experimental evaluations demonstrate improvements in network efficiency, data storage optimization, and transaction processing speed. Additionally, the study establishes a link between faster threat response times and increased blockchain transaction success rates. The results underscore the feasibility of integrating blockchain, AI, and IoT to develop secure, scalable, and efficient precision agriculture solutions.","author":[{"family":"Shrihari","given":"MR"},{"family":"Saira","given":"JL"},{"family":"Ajay","given":"N"},{"family":"Mahesh","given":"MR"},{"family":"Manjunath","given":"TN"},{"family":"Merikapudi","given":"Seshaiah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ickecs65700.2025.11035106","URL":"https://doi.org/10.1109/ickecs65700.2025.11035106","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i1.12652","type":"article-journal","title":"SEBARAN SPASIAL TINGKAT KESESUAIAN LAHAN TANAMAN PANGAN PADA BEBERAPA SUB DAERAH ALIRAN SUNGAI (DAS) DI KAWASAN TELUK TOMINI KABUPATEN BOALEMO","abstract":"Penelitian ini bertujuan untuk menentukan sebaran spasial tingkat kesesuaian lahan tanaman pangan pada Sub Daerah Aliran Sungai (DAS) di kawasan Teluk Tomini Kabupaten Boalemo. Data dianalisis dengan teknik pemadanan antara karakteristik dan kualitas lahan dengan kriteria kesesuaian lahan tanaman pangan berdasarkan kerangka kerja FAO serta menggunakan software ArcGis dengan metode maching. Hasil analisis menunjukkan kesesuaian lahan potensial komoditas pangan masing -masing untuk padi sawah kelas S2 (cukup sesuai) seluas 2,368.16 ha (14.37%) dan kelas S3 seluas 14,114.03 (85.63%), jagung kelas S2 seluas 10,338.40 (62%) dan kelas S3 seluas 6,143.80 ha (37.28%), kedelai kelas S2 seluas 13,712.13 (83.19%) dan kelas S3 seluas 2,770.07 ha (16.81%). Ubi kayu kelas S2 (cukup sesuai) seluas 3,901.42 ha (23.67%), kelas S3 seluas 2,532.34 ha (15.36%) dan kelas N seluas 10,048.44 (60.97%). Hasil analisis menyimpulkan bahwa setiap komoditas tanaman pangan di wilayah penelitian didominasi oleh kelas (S3) 85.63% untuk padi sawah, kedelai cukup sesuai (S2) 83.19%, jagung cukup sesuai (S2) 62%, serta kelas tidak sesuai (N) 60.97% untuk komoditas ubi kayu. Sebaran pengembangan komoditas tanaman pangan di wilayah penelitian paling luas diarahkan untuk komoditas jagung dan kedelai dengan luas 54.17%, kedelai seluas 20.95%, jagung kedelai dan ubi kayu 20.07%, kedelai dan ubi 1.97% serta jagung 0.38%.","author":[{"family":"Nurdin"},{"family":"Rahman","given":"Rival"},{"family":"Apriliani","given":"Silvana"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35760/jpp.2025.v9i1.12652","URL":"https://doi.org/10.35760/jpp.2025.v9i1.12652","source":"crossref"},{"id":"doi:10.1109/iciccs65191.2025.10985661","type":"article-journal","title":"Narrow-Band IoT Applications in Precision Agriculture for Real-Time Environmental Monitoring and Crop Management","abstract":"Precision agriculture is transforming traditional farming practices through data-driven approaches that enable more efficient management of resources such as water, nutrients, and pesticides. This study investigates the implementation of a Narrow-Band Internet of Things (NB-IoT) enabled precision agriculture system integrated with a Long Short-Term Memory (LSTM) deep learning model to optimize crop management through real-time environmental monitoring and data-driven decision-making. The system deployed sensors to monitor essential parameters, including soil moisture, temperature, humidity, light intensity, pH, and nutrient levels, enabling continuous data collection. The LSTM model was trained on historical data to predict crop health, irrigation needs, and pest risk, achieving a prediction accuracy of 92% for soil moisture and 89% for pest risk. Results showed that datadriven irrigation adjustments reduced water consumption by 10-13% while increasing crop yield by 10-13%. Real-time nutrient monitoring facilitated targeted fertilization, reducing over-application by 15% and improving resource efficiency. The study demonstrates that an NB-IoT and deep learning approach can significantly enhance crop productivity and sustainability in agriculture. This model offers a scalable and adaptive solution for precision farming, providing actionable insights for optimized resource use and environmental conservation.","author":[{"family":"Nene","given":"Payal"},{"family":"Karthik","given":"S"},{"family":"Velumani","given":"R"},{"family":"Hariprasath","given":"S"},{"family":"Kumar","given":"VA"},{"family":"Kumar","given":"SS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iciccs65191.2025.10985661","URL":"https://doi.org/10.1109/iciccs65191.2025.10985661","source":"crossref"},{"id":"doi:10.1109/iciss63372.2025.11076290","type":"article-journal","title":"Precision Agriculture Enhanced by Spatio-Temporal Attention Model for Real-Time Crop Monitoring and Prediction","abstract":"Modern farming experiences revolutionary changes through precise agricultural methods that use innovative technologies for crop surveillance and harvest output estimation. The research develops a Spatio-Temporal Attention Model which improves both crop real-time monitoring and forecasting capabilities. The model utilizes satellite imagery together with UAV/drone data and weather information together with soil moisture measurements and IoT sensor outputs to detect intricate spatial and temporal relationships which impact crop vitality and yield production. The system integrates Convolutional Neural Networks (CNNs) to extract spatial information alongside Recurrent Neural Networks (RNNs) together with Transformer-based attention mechanisms for handling temporal patterns. The SpatioTemporal Attention Model establishes a 94.8% crop health classification rate and reduces the yield prediction RMSE to 150 kg/ha. The proposed method establishes its superior performance through tests against CNN-RNN and Transformer models which lack attention mechanisms. The model can be used in precision agriculture due to its real-time monitoring function while maintaining an average inference time of 200 ms. The research demonstrates that spatial and temporal attention techniques enable better agricultural choices thus resulting in superior resources optimization alongside higher crop yields.","author":[{"family":"Abraham","given":"Subin"},{"family":"Thomas","given":"Aashish"},{"family":"Ansleen","given":"Sherena"},{"family":"Kumar","given":"Deepak"},{"family":"Rishee","given":"LGP"},{"family":"Senthil","given":"Kirrti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iciss63372.2025.11076290","URL":"https://doi.org/10.1109/iciss63372.2025.11076290","source":"crossref"},{"id":"doi:10.1109/icancs65819.2025.11377227","type":"article-journal","title":"An Enhanced IoT-Based Smart Agriculture System: Future Directions in Precision Farming","abstract":"Smart agriculture, powered by the Internet of Things (IoT), has revolutionized resource optimization and crop yield enhancement. However, challenges such as latency in cloud-dependent systems, data security vulnerabilities, and suboptimal decision-making persist. This paper introduces an integrated IoT framework combining Edge AI for real-time analytics, blockchain for secure data transactions, and predictive modeling to optimize irrigation. A 90-day field experiment evaluated three irrigation regimes (100 %, 60 %, and 30 % of recommended water volume) using LoRaWAN sensors, lightweight LSTM networks, and a Hyperledger Fabric blockchain. Results demonstrated a 22 % reduction in water usage and 12 % higher yield efficiency in the 60 % regime compared to conventional practices, alongside tamper-proof data logging and sub-5-second decision latency. Results were validated statistically using confidence intervals and significance testing, ensuring robustness. The framework's scalability and energy efficiency establish it as a blueprint for sustainable precision agriculture.","author":[{"family":"Reddy","given":"Patlolla"},{"family":"Enugala","given":"Vinay"},{"family":"Prasad","given":"Srinivas"},{"family":"Tiwari","given":"Meher"},{"family":"Akarapu","given":"Sridhar"},{"family":"Siripuri","given":"Kiran"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icancs65819.2025.11377227","URL":"https://doi.org/10.1109/icancs65819.2025.11377227","source":"crossref"},{"id":"doi:10.1109/decon67170.2025.11447956","type":"article-journal","title":"Multi-Stage Weed Detection Using Lightweight Machine Learning Models for Precision Agriculture","abstract":"Precision agriculture aims to enhance crop productivity by enabling weed detection, which adversely affects yield and increases the burden of manual labour. Accurate and timely weed detection is essential for efficient field management. While deep learning models have shown high effectiveness in this domain, their heavy computational demands often make them impractical for real-time use on resource-limited agricultural platforms like drones and edge devices. To overcome this limitation, we propose a multi-stage weed detection framework employing lightweight deep learning models. The framework balances speed and accuracy by integrating YOLOv8n (You Only Look Once Version 8 – Nano) and EfficientDet-D0 for rapid weed localization, followed by MobileNetV3 for refined classification. This modular design supports flexible deployment across diverse field conditions and crop types. The proposed approach achieves high detection accuracy while maintaining low inference latency, allows its integration into real-time precision agriculture systems. Moreover, the framework supports scalable weed identification while minimizing reliance on manual effort and excessive herbicide application, promoting environmentally friendly and economically viable farming methods.","author":[{"family":"Tamilkodi","given":"R"},{"family":"Sujatha","given":"B"},{"family":"Chandu","given":"SESR"},{"family":"Shah","given":"Tirth"},{"family":"Koushik","given":"R"},{"family":"Nandan","given":"Ch"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/decon67170.2025.11447956","URL":"https://doi.org/10.1109/decon67170.2025.11447956","source":"crossref"},{"id":"doi:10.1109/iccams65118.2025.11234592","type":"article-journal","title":"A Multifunctional UAV System for Precision Agriculture and Environmental Monitoring","abstract":"Today, precision agriculture as a modern approach to farming has been aided by advanced technology for optimizing crop management and resource utilization. A multifunctional UAV system for real-time environmental monitoring in agriculture landscapes is presented here. This drone has a Pixhawk flight controller and a variety of environmental sensors from which air quality using the MQ-135, soil moisture, temperature using DHT22, water pollution, and LIDAR-based distance sensors (VL53L0X) would be applied. Moreover, it has an SD card-associated black box for safe data storage, allows solar charging so it can have a much longer mission time, and permits autonomous water landing when necessary for better survivability in emergency situations. The UAV can provide accurate environmental data which could help farmers or environmental agencies in decision making with regards to irrigation, fertilization, or pollution control. The efficiency of capturing accurate sensors data is verified through test results that also show the solar charging-enabled extended mission endurance and miss emergency landings without damage to critical components. The cashless data integrity is ensured with the black box mechanism. The system is also far superior to conventional systems based on ground monitoring in terms of scalability, flexibility, and reduced cost. In the future, research initiatives will focus on developing machine learning algorithms that enable improved navigation and decision-making in a more autonomous fashion, with the real-time capability for dynamic field management. This UAV-based precision agriculture platform thus assures sustainable agriculture by reducing wastages, improving productivity, and preventing environmental degradation.","author":[{"family":"Kashyap","given":"MS"},{"family":"Ravi","given":"Sahana"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iccams65118.2025.11234592","URL":"https://doi.org/10.1109/iccams65118.2025.11234592","source":"crossref"},{"id":"doi:10.1109/itechsecom64750.2025.11307272","type":"article-journal","title":"Drone Based Precision Agriculture Technique to Increase Crop Yield Using Machine Learning","abstract":"The increasing global population, combined with climate variability and finite natural resources, poses significant challenges to modern agriculture. Conventional farming practices are often labor-intensive, inefficient, and lack real-time monitoring of crop health and soil conditions. Precision agriculture has emerged as a solution by integrating advanced technologies such as unmanned aerial vehicles (UAVs), Internet of Things (IoT) sensors, and artificial intelligence (AI). In this work, we propose a drone-based precision agriculture framework that utilizes highre-solution aerial images and cloud-based deep learning pipelines to automate key farm management operations. The system focuses on four main objectives: (i) detecting water scarcity to enable responsive irrigation, (ii) mapping and identifying weeds, (iii) recognizing plant diseases and suggesting appropriate treatments, and (iv) monitoring crop growth to provide accurate yield predictions. The proposed framework aims to improve efficiency, reduce resource wastage, and support data-driven decision-making in agriculture. The proposed system employs a DJI mavic 2 pro UAV equipped with a$\\mathbf{4 K}, 60 \\text{fps}$camera to capture high-resolution imagery during scheduled flights. Captured images are transmitted to the cloud, where advanced machine learning algorithms process them to generate actionable insights. Experimental results demonstrate strong performance, with$\\mathbf{9 4. 3 2 \\%}$accuracy in growth estimation, 97.84% accuracy in weed detection, and 93.87% accuracy in disease identification with recommended treatments. The findings indicate that the framework effectively reduces manual labor, optimizes resource usage, and enhances crop productivity. By delivering real-time insights to farmers through mobile applications, this approach supports data-driven decision-making, promotes sustainable agricultural practices, and contributes to addressing global challenges of food security and resource management.","author":[{"family":"Mahavishnu","given":"VC"},{"family":"Kumar","given":"SK"},{"family":"Pithani","given":"Surya"},{"family":"Cheran","given":"U"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/itechsecom64750.2025.11307272","URL":"https://doi.org/10.1109/itechsecom64750.2025.11307272","source":"crossref"},{"id":"doi:10.1109/icst66402.2025.11512431","type":"article-journal","title":"Development &amp; Validation of a Portable Electrochemical System for Soil NPK Detection in Precision Agriculture","abstract":"India’s agricultural sector is at a turning point, serving as the backbone of the country. Millions of farmers are burdened with deteriorating soil fertility, falling yield trends, and rising costs of cultivation, while the plots of land they depend on are becoming smaller. Most farmers lack inexpensive and timely access to soil testing, so the majority resort to ineffective guesswork to inform their fertilizer application decisions. This uncertainty leads to both overuse and underuse of crop nutrients, wastage of resources, and long- term land degradation. For small and marginal farmers, most of this cycle not only jeopardizes seasonal productivity but also poses a threat to livelihood security. In this situation, sustainable agriculture will secure food production for the future. In pursuit of this vision, we have developed a low-cost, in-situ electrochemical sensor system to facilitate real-time assessment of the three macronutrients in soil: Nitrate (N), Phosphate (P), and Potassium (K). The sensors are outfitted with selective acoustic coating and are based on the methodology of electrochemical impedance spectroscopy, wherein ion interactions in soil lead to negligible resistance and reactance movement, resulting in measurable responses. The sensors are calibrated to standard solutions and tested with soil extracts from previous assessments, exhibiting low-cost, high sensitivity, high accuracy, and reliability. It would provide farmers with an immediate tool to comprehend their soil space, evaluate their fertilizer footprint, and implement precision farming.","author":[{"family":"Rajadhyaksha","given":"Sahil"},{"family":"Koli","given":"Preksha"},{"family":"Patil","given":"Shrut"},{"family":"Dere","given":"Durgesh"},{"family":"Sankhe","given":"Sanskruti"},{"family":"Mapare","given":"Sheetal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icst66402.2025.11512431","URL":"https://doi.org/10.1109/icst66402.2025.11512431","source":"crossref"},{"id":"doi:10.70102/afts.2025.1833.719","type":"article-journal","title":"EDUCATIONAL FOUNDATIONS OF AGRICULTURAL TECHNOLOGIES AND THEIR INFLUENCE ON PRECISION AGRICULTURE AND SUSTAINABILITY PRACTICES","abstract":"Even though agriculture is now one of the most technologically advanced civilian industries, there is still a big gap between the innovations that are available and how they are actually put into practice, particularly in areas where traditional supervision methods are predominant. This study looks at how farmers' ability to implement precision agriculture systems and accomplish sustainable resource management is impacted by the educational underpinnings of agricultural technologies. The proposed Edu-Integrated Precision Irrigation Optimization Method (E-PIO Method), which demonstrates how technical literacy improves automated systems' performance and dependability under actual farming conditions, is at the heart of this study. The E-PIO Method incorporates wireless communication modules connected to an Arduino-based control unit, temperature sensors, rain sensors, and soil-moisture detectors. The system ensures effective and fair distribution throughout a 10-hectare test field by automatically initiating irrigation only when soil-moisture levels drop below predetermined thresholds and resolving water-demand conflicts using a first-detected priority algorithm. The study demonstrates that educational readiness greatly increases the success of precision agriculture technologies by linking the operational logic of the system with farmers' knowledge of embedded systems, sensor networks, and environmental data interpretation. The findings show that farmers with a basic understanding of contemporary agri-tech deploy the system more accurately, interpret field results more accurately, and achieve more reliable sustainability results. Stronger environmental stewardship, less manual intervention, and increased water-use efficiency are all results of improved technical education. This study concludes that educational capacity is a key factor in determining how effectively cutting-edge technologies, such as the E-PIO Method, can improve agricultural productivity and long-term ecological stability.","author":[{"family":"Bobomuratova","given":"Shoira"},{"family":"Zokirov","given":"Kurbonalijon"},{"family":"Jumakulov","given":"Najimiddin"},{"family":"Allamuratov","given":"G'ofur"},{"family":"Ulugbekov","given":"Oybek"},{"family":"Mullajonova","given":"Muhabbat"},{"family":"Turdunov","given":"Avazbek"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70102/afts.2025.1833.719","URL":"https://doi.org/10.70102/afts.2025.1833.719","source":"crossref"},{"id":"doi:10.1049/aie2.70005","type":"article-journal","title":"Integrating IoT With Machine Learning and Deep Learning Models for Precision Soil‐Less Agriculture: A Review","abstract":"ABSTRACT The rising global population, along with the challenges faced by conventional agricultural practices, has intensified the demand for smart agricultural solutions. In modern agriculture, the integration of Internet of things and machine learning‐deep learning has evolved as an irreplaceable force, particularly in the context of soil‐less farming systems. This study aims to explore the potential of IoT and intelligent data‐driven technologies in advancing smart and precise soil‐less agriculture systems and the review commences by scrutinising the basic principles of IoT and its application in soil‐less agriculture. It also emphasises the integration of diverse sensors for real‐time data collection on dynamic environmental and plant parameters. The advantages of IoT and machine learning–deep learning in soil‐less agriculture systems are comprehensively analysed, covering numerous applications. This study also recognises challenges, such as data security and privacy concerns, and interoperability concerns which must be addressed for wider adoption and sustainable growth. Overall, this review paper presents a comprehensive assessment of IoT and ML‐DL in soil‐less agriculture systems. It highlights the potential of these technologies in tackling the key challenges faced by modern soil‐less agricultural systems. Ultimately, these advancements can contribute significantly towards a greener and sustainable future for agriculture.","author":[{"family":"Subeesh","given":"A"},{"family":"Chauhan","given":"Naveen"},{"family":"Kushwaha","given":"NL"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1049/aie2.70005","URL":"https://doi.org/10.1049/aie2.70005","source":"crossref"},{"id":"doi:10.1109/icaft66710.2025.11452904","type":"article-journal","title":"Precision Agriculture Through IoT: Soil and Water Quality Monitoring and Crop Fertilization Guidance","abstract":"Agriculture requires the management of soil and water to increase yield and productivity with minimal environmental impact. Formers lack real time data like pH, moisture, and nutrients leads to improper irrigation and use of fertilizer. Our aim is to develop an IoT system which monitors the water and soil and provides crop specific recommendations for fertilizer. The system contains sensors such as pH, turbidity, moisture, and temperature connected to the microcontroller and stores data. The data is processed and shown in user dashboard and uses machine learning models and fuzzy logic for recommendations. This model helps with resource management and reduce in water and fertilizer useage while improving crop yield. Our approach demonstrate data monitoring and recommendations releted to specific crop.","author":[{"family":"Thind","given":"Harpreet"},{"family":"Nyamagoud","given":"Shivakumar"},{"family":"Nurandevarmath","given":"Sharan"},{"family":"Kohalli","given":"Shreeshail"},{"family":"Kumara","given":"Valmiki"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaft66710.2025.11452904","URL":"https://doi.org/10.1109/icaft66710.2025.11452904","source":"crossref"},{"id":"doi:10.1109/raeeucci63961.2025.11048326","type":"article-journal","title":"IoT-based Precision Agriculture System using LoRa with Enhanced Soil Fertility Prediction and Automated Irrigation","abstract":"Agriculture serves as the backbone of Indian Economy, with more than 50% of the population involved in farming activities. Precision agriculture, driven by advancements in IoT and machine learning, presents groundbreaking opportunities to enhance agricultural productivity and sustainability. This paper introduces an innovative system for soil fertility prediction and irrigation management, combining IoT-based real-time data with predictive analytics. Using real-time data acquisition capabilities, the LoRa-based IoT network system collects vital parameters such as the pH of the soil, its moisture content, the temperature, and even humidity levels. The central component of the system for soil fertility prediction leverages a stacked ensemble machine learning model with a high accuracy of 93.37%, along with techniques such as SMOTE to tackle class imbalance present in the dataset and polynomial-based feature engineering to further boost model performance. An optimized Long Short-Term Memory model is employed for irrigation management, providing accurate irrigation requirements with exceptional accuracy, reaching 99.53%, integrating both current sensor data and weather forecasts. This novel approach marks a major move toward sustainable and efficient farming practices in an increasingly digital world.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/raeeucci63961.2025.11048326","URL":"https://doi.org/10.1109/raeeucci63961.2025.11048326","source":"crossref"},{"id":"doi:10.1504/ijsami.2025.145317","type":"article-journal","title":"Deep learning and machine learning approaches for data-driven risk management and decision support in precision agriculture","abstract":"Modern agriculture grapples with challenges such as unpredictable weather, biosecurity threats, market volatility, evolving regulations, and farmer health concerns. Effectively addressing these issues while maintaining sustainability demands informed decision-making. Data-driven technologies, especially deep learning (DL), emerge as crucial solutions. This study introduces a sustainable multivariate risk management system for precision agriculture, encompassing plant disease detection, weed detection, fire and smoke detection, and crop recommendation modules. Empowering farmers with tools to navigate risks and enhance operational efficiency, the system leverages DL techniques to uncover correlations among diverse risk factors. Enabling well-informed decisions on risk mitigation, this innovative system has the potential to revolutionise precision agriculture, fostering sustainability and profitability. Insights from the study set a benchmark for adopting data-driven, sustainable practices in smart agriculture. Farmers can utilise the system to conduct informed assessments, proactively mitigate crop damage, and redefine their approach to modern agriculture, ensuring improved yields and enhanced monitoring.","author":[{"family":"Mikram","given":"Mounia"},{"family":"Moujahdi","given":"Chouaib"},{"family":"Rhanoui","given":"Maryem"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1504/ijsami.2025.145317","URL":"https://doi.org/10.1504/ijsami.2025.145317","source":"crossref"},{"id":"doi:10.1117/12.3078174","type":"article-journal","title":"Optical systems in UAVs for sustainable development of precision agriculture","abstract":"This article examines modern optical systems integrated into unmanned aerial vehicles (UAVs) and their role in the sustainable development of precision agriculture. The analysis covers sensor types (multispectral, hyperspectral, thermal cameras, LiDAR), their technical characteristics, and advantages over satellite-based systems. The paper presents comparative research results on the accuracy of various optical sensors for crop monitoring, water stress detection, and phytopathology identification. It is shown that the deployment of UAVs with advanced optical systems can increase crop yields by 15-30%, reduce water usage by up to 30%, and decrease pesticide application by up to 35%, which is especially relevant for resource-limited regions. The article discusses technological limitations, such as weather dependency, sensor calibration requirements, and equipment costs. Special attention is given to future directions, including the integration of AI algorithms for automated data interpretation, the development of hybrid systems, and the standardization of data collection protocols. The study concludes that a multidisciplinary approach is essential for scaling up the application of UAV optical systems in the agricultural sector.","author":[{"family":"Tokhtaeva","given":"Zebo"},{"family":"Salomov","given":"Botir"},{"family":"Tadjibaev","given":"Azizbek"},{"family":"Urinov","given":"Sherali"},{"family":"Chulieva","given":"Gulnoza"},{"family":"Tueva","given":"Evgeniya"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1117/12.3078174","URL":"https://doi.org/10.1117/12.3078174","source":"crossref"},{"id":"doi:10.33545/2618060x.2025.v8.i12sh.4542","type":"article-journal","title":"A review of AI and precision farming in Indian agriculture: Innovations, applications, and challenges","abstract":"Precision farming and artificial intelligence (AI) are transforming Indian agriculture by enhancing productivity, optimizing resource use, and ensuring sustainability. With over 58% of the Indian population dependent on agriculture for their livelihood, integrating AI is vital for addressing the sector's challenges. This review explores the integration of AI in precision farming within the Indian context, highlighting current applications such as crop monitoring, soil health management, irrigation management, pest control, and market access. It also discusses the benefits of increased productivity and resource optimization, the challenges of high initial costs and lack of infrastructure, and future prospects involving government initiatives and public-private partnerships. This paper provides a comprehensive understanding of how AI technologies can revolutionize Indian agriculture, contributing to the nation's food security and economic growth. The discussion includes relevant data and case studies to illustrate the impact and potential of AI-driven precision farming.","author":[{"family":"Gautam","given":"Avinash"},{"family":"Verma","given":"Lekh"},{"family":"Gautam","given":"Monika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/2618060x.2025.v8.i12sh.4542","URL":"https://doi.org/10.33545/2618060x.2025.v8.i12sh.4542","source":"crossref"},{"id":"doi:10.1109/netact65906.2025.11188961","type":"article-journal","title":"Precision Agriculture: Forecasting Crop Prices Through Advanced Data Mining and Machine Learning Models","abstract":"It is a challenging undertaking to predict the prices of agricultural products especially in India, where majority of the households are always faced with economic insecurities and variable incomes. Local production is hardly ever predictable and it is the case that extensive importance is assumed to patterns of behavior in the local markets often ruling out any utility of conventional practices. But, the discovery prospects of the unseen information delivered by the background of large agricultural data holds the possibility of inventive exploitation of a more intelligent, data-dense modelling procedure. Data mining determines covert connections and chain tendencies that may be deployed to construct unique anticipatory models that surpass conventional heuristics. We introduce a machine learning approach of SARIMAX as means of predicting the agricultural market prices, namely a time-series prediction method. The model involves prices at past periods and other external inputs, to indicate the intricate seasonality which is experienced in the agricultural crops data and the stochastic characteristics of the same data. The suggested method has phenomenal predictive power, R-squared of 98.36 %, and effectively represented agricultural price volatility that people experience in the real world. We applied data-based solutions to try to improve predictive accuracy and deliver some real-world utility to the user in their decision making. Being able to combine machine learning with data mining is an important step towards Precision Agriculture because predictive intelligence can potentially lead to financial outcomes for the agricultural industry and alleviate the effects of market volatility.","author":[{"family":"Hirapara","given":"Jignesh"},{"family":"Doshi","given":"Milan"},{"family":"Ranpara","given":"Ripal"},{"family":"Ranpariya","given":"Tushar"},{"family":"Khachariya","given":"Haresh"},{"family":"Sadaria","given":"Priti"},{"family":"Solanki","given":"Malaykumar"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/netact65906.2025.11188961","URL":"https://doi.org/10.1109/netact65906.2025.11188961","source":"crossref"},{"id":"doi:10.55627/agribiol.003.01.1067","type":"article-journal","title":"From Sensors to Insights: The Fusion of AI, Edge Computing, and Precision Agriculture","abstract":"Integrating artificial intelligence (AI), with edge computing, and precision agriculture is revolutionizing farming making it more resilient and sustainable. This article focuses on combine positive impact that the merger of these transformative technologies, can have in providing solutions for key challenges such as plant disease detection, resource optimization, and real-time decision-making. AI algorithms enables rapid and precise analysis of massive agricultural data allowing early disease detection and preventive measures to ensure plant health. Concurrently, edge computing gives the power of reduced latency with on spot data processing and solutions provision to the farmers, even in areas with limited coverage. The fusion of these technologies aligns with key UN sustainable development goals (SDGs), by optimizing the use of water, fertilizers, and pesticides, reducing environmental impacts, and mitigating climate change effects. However, the widespread adoption of AI and edge computing in agriculture is constrained by challenges such as hardware limitations, data collection, quality issues, and the need for technical expertise in particular cases. This review explores how these technologies are currently being used in agriculture, their pros, cons, and potential areas for further research and development. Encouraging interdisciplinary collaboration and continuous innovation will be crucial to overcome these challenges, ensuring that AI and edge computing play a central role in securing global food security and promoting climate-resilient farming.","author":[{"family":"Ali","given":"Faizan"},{"family":"Tariq","given":"Waheed"},{"family":"Razzaq","given":"Ali"},{"family":"Rehman","given":"Abdul"},{"family":"Sarfraz","given":"Sohaib"},{"family":"Rajput","given":"Nasir"},{"family":"Ali","given":"Subhan"},{"family":"Fatima","given":"Kaneez"},{"family":"Jameel","given":"Sahar"},{"family":"Liaqat","given":"Nadia"},{"family":"Akash","given":"Zuniara"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55627/agribiol.003.01.1067","URL":"https://doi.org/10.55627/agribiol.003.01.1067","source":"crossref"},{"id":"doi:10.1109/icsima66552.2025.11233274","type":"article-journal","title":"Precision Detection of Small Brown Planthoppers in Agriculture via YOLOv8 Fine-Tuning","abstract":"The research evaluates the quality of the YOLOv8 architecture in terms of its efficiency in the fine-tuning scenario when it comes to detecting small objects, and the Brown Planthopper (BPH) in a farming setting will be considered as the species under research. Clearly identifying minute target classes has remained a big challenge in computer vision due to their low spatial resolution, minimal salient features and sparsity of associated features. Throughout the research, methodologically speaking, the research was conducted in terms of dataset preparation and annotation followed by the training and fine-tuning of the model and the validation performance. As illustrated in the empirical findings, Model (Fined tuned version) performed better on all the metrics when compared to Model A (base-line version). Model B recorded improvements of 8.5 percent in precision, 11 percent in recall, 12 percent in Mean Average Precision (mAP)@0.5 and 41 percent in mAP@0.5 to 0.95. These gains of accuracy are synonymous with better bounding-box localization, greater true-positive identification, and reduced false-positive identification. In combination, the findings support the paramount importance that the high-quality annotation and manual fine-tuning exercise in the local setting has, hence demonstrating the unique benefit of the solutions as compared to the cloud-based automated training to the local small-object detection activities.","author":[{"family":"Luqman","given":"Nur"},{"family":"Ahmad","given":"Izanoordina"},{"family":"Maharum","given":"Siti"},{"family":"Mansor","given":"Zuhanis"},{"family":"Wei","given":"Bo"},{"family":"Kumar","given":"Vikram"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icsima66552.2025.11233274","URL":"https://doi.org/10.1109/icsima66552.2025.11233274","source":"crossref"},{"id":"doi:10.1109/icdsaai65575.2025.11011723","type":"article-journal","title":"AI-Driven IoT-Enabled Precision Agriculture: Optimizing Resource Usage with LoRaWAN and Drone-Based Monitoring","abstract":"To maximize the use of resources and increases crop productivity, this research proposes an end-to-end IOT-based precision agriculture system with real-time data gathering with the assistance of smart sensors, monitoring with drones, and analytics with AI. The system collects data regarding crop health, weather, and soil moisture through LoRaWAN, a low-power long-range network technology. Such information facilitates predictive decision-making regarding pest control, fertilization, and irrigation. Field trials show a 15% increase in crop yield, a 20% decrease in the application of pesticides, and a 25% decrease in water usage, which demonstrates the effectiveness of the system in resolving critical agricultural problems and ensuring sustainability. This research demonstrates how IoT and AI can revolutionize farming practices today.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icdsaai65575.2025.11011723","URL":"https://doi.org/10.1109/icdsaai65575.2025.11011723","source":"crossref"},{"id":"doi:10.3390/agriculture15232482","type":"article-journal","title":"Hyperspectral Sensing and Machine Learning for Early Detection of Cereal Leaf Beetle Damage in Wheat: Insights for Precision Pest Management","abstract":"The cereal leaf beetle (CLB; Oulema melanopus L., Coleoptera: Chrysomelidae) is a serious pest of wheat, capable of causing yield losses of up to 40% through photosynthetic impairment. Early detection and severity assessment are essential for effective and sustainable pest management. This study evaluates the potential of hyperspectral remote sensing (RS) combined with machine learning (ML) for non-invasive detection of CLB-induced stress in winter wheat. Spectral reflectance was measured using a full-range spectroradiometer (350–2500 nm) from flag leaves categorized into four damage levels (healthy, slightly, moderately, and severely damaged). Three input datasets were used for ML classification: full spectral reflectance, a set of 13 vegetation indices (VIs), and outputs of dimensionality reduction technique. CLB stress increased reflectance in the visible range (400–700 nm) and reduced it in the near-infrared (700–1400 nm), consistent with chlorophyll degradation and mesophyll damage. Several VIs, including RIGreen, NDVI750, GNDVI, and NDVI, correlated strongly with damage severity (τ = 0.78–0.81). Among the six ML models tested, Support Vector Machine (SVM) achieved the highest classification accuracy of 90.0% (precision = 0.90, recall = 0.90, F1 = 0.90) across the four severity classes, and achieved 91.9% accuracy at the early-detection threshold. As far as the currently available literature indicates, this study provides one of the earliest quantitative assessments of CLB damage severity based on full-spectrum leaf-level hyperspectral reflectance integrated with ML classification. These findings were obtained under controlled, leaf-level measurement conditions and therefore represent a proof-of-concept; future validation using UAV and satellite platforms is needed to assess performance under operational field variability. Overall, our findings highlight the potential of hyperspectral RS and ML for precision pest monitoring, supporting threshold-based decision-making and more sustainable insecticide use.","author":[{"family":"Skendžić","given":"Sandra"},{"family":"Novak","given":"Hrvoje"},{"family":"Zovko","given":"Monika"},{"family":"Živković","given":"Ivana"},{"family":"Lešić","given":"Vinko"},{"family":"Maričević","given":"Marko"},{"family":"Lemić","given":"Darija"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15232482","URL":"https://doi.org/10.3390/agriculture15232482","source":"crossref"},{"id":"doi:10.1109/hswtech64936.2025.11278142","type":"article-journal","title":"Transforming Precision Agriculture through Deep Learning: CNN Encoder-Decoders and a Hybrid YOLOv8-SAM Solution for Advanced Grape Cluster Segmentation","abstract":"Accurate grape cluster segmentation is crucial for developing automated vineyard harvesting systems and precision agriculture applications. This paper presents a novel hybrid approach combining YOLOv8 object detection with Meta’s Segment Anything Model (SAM) for multi-cluster grape segmentation, alongside comprehensive evaluation of CNN encoder-decoder architectures for single-cluster scenarios. Using the GrapesNet dataset containing over 11,000 diverse vineyard images, we trained and evaluated various segmentation models including U-Net variants with pre-trained encoders, SegNet architectures, and fully convolutional networks (FCNs). The MobileNetV2-UNet achieved superior single-cluster segmentation with mIoU of 0.906 and Dice coefficient of 0.984, demonstrating computational efficiency suitable for resource-constrained agricultural environments. For multi-cluster scenarios involving overlapping grape clusters, our hybrid YOLOv8-SAM approach demonstrated exceptional performance with mIoU of 0.943 and Dice coefficient of 0.970, significantly outperforming traditional CNN-based methods by 4.1% in IoU scores. The hybrid methodology addresses key challenges in agricultural computer vision including variable lighting conditions, cluster occlusion, and complex vineyard backgrounds. Comprehensive ablation studies validate the contribution of each component, while computational analysis demonstrates practical deployment feasibility. The primary contribution lies in demonstrating that foundation models like SAM, when combined with robust object detection, can effectively handle complex agricultural scenes with overlapping grape clusters, advancing automated harvesting and real-time yield estimation technologies for precision viticulture applications.","author":[{"family":"Gyale","given":"Sarish"},{"family":"Singh","given":"Utkarsh"},{"family":"Tekavade","given":"Yashvardhan"},{"family":"Jadhav","given":"Parul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/hswtech64936.2025.11278142","URL":"https://doi.org/10.1109/hswtech64936.2025.11278142","source":"crossref"},{"id":"doi:10.1117/12.3070423","type":"article-journal","title":"Hyperspectral classification of tree species for precision water management in Mediterranean agriculture","abstract":"Effective agricultural water management relies on innovative tools like remote sensing to assess irrigation needs at basin scales. This study, part of the WAter DIgital Twin (WADIT) project, aims to support water balance modeling by precisely identifying tree species using airborne hyperspectral imagery. Conducted at an experimental farm in Valenzano (Southern Italy), the research employs the CASI sensor to acquire high-resolution data of irrigated tree crops (e.g., olive, fig, grapevine). It evaluates supervised classification techniques—Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), and Random Forest (RF)—to map species from hyperspectral images after pre-processing and feature extraction. Results demonstrate exceptional accuracy (up to 99%), enabling detailed hydrological modeling for tailored irrigation strategies. The study advances precision agriculture and sustainable water management in Mediterranean regions, offering a methodological framework for integrating remote sensing into digital twin systems like WADIT to address water scarcity.","author":[{"family":"Guerriero","given":"Andrea"},{"family":"Matarrese","given":"R"},{"family":"Cavone","given":"C"},{"family":"Ottaviano","given":"A"},{"family":"Vivaldi","given":"GA"},{"family":"Ferrara","given":"G"},{"family":"Camposeo","given":"S"},{"family":"Palasciano","given":"M"},{"family":"D'addabbo","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1117/12.3070423","URL":"https://doi.org/10.1117/12.3070423","source":"crossref"},{"id":"doi:10.1109/iraset64571.2025.11008267","type":"article-journal","title":"Computational Efficiency in Precision Agriculture: MobileNetV2 Outperforms State-of-the-Art CNNs for Real-Time Plant Disease Detection","abstract":"This research addresses critical challenges in global agriculture–particularly climate change, soil degradation, and water scarcity–by advancing smart farming technologies. Automated systems powered by computer vision (CV) and deep learning (DL) enable early plant disease detection, delivering faster, more accurate, and more cost-effective solutions than traditional methods. These innovations enhance crop management and food security. We present a comparative analysis of five deep learning architectures (EfficientNetV2, ResNet50, MobileNetV2, Inception-v2, and DenseNet210) for early pathology detection. By employing user-friendly imaging techniques and scalable solutions, this work facilitates widespread farmer adoption. Future efforts will refine these technologies, improve their adaptability across diverse agricultural environments, and integrate them into existing practices to boost productivity, sustainability, and resilience in modern agriculture.","author":[{"family":"Idrissi","given":"Tarik"},{"family":"Rharras","given":"Abdessamad"},{"family":"Saadane","given":"Rachid"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iraset64571.2025.11008267","URL":"https://doi.org/10.1109/iraset64571.2025.11008267","source":"crossref"},{"id":"doi:10.1109/iccc65605.2025.11022832","type":"article-journal","title":"Advancing Sustainability and Productivity: The Role of Precision Agriculture in Vineyards and Olive Groves","abstract":"Precision agriculture has emerged as a vital approach to modern agricultural management, addressing the dual challenge of increasing food production while preserving the environment. Its importance lies in its ability to leverage advanced technologies to optimize productivity, reduce waste, and ensure sustainability, particularly in high-value crops such as vineyards and olive groves. This study explores the application of precision agriculture tools, such as sensors, drones, geolocation systems, and data analytics, in these crops to enhance productivity, improve product quality, and minimize environmental impact. In vineyards, precision viticulture focuses on managing spatial and temporal variability within plots to increase economic performance through higher productivity, superior fruit quality, and reduced production costs. The targeted application of inputs and precise management practices result in resource savings and uniform fruit quality, crucial for producing premium wines. Similarly, in olive groves, technologies enable effective plant health monitoring and early disease detection. At the same time, drones assist in evaluating plant vigor and planning optimal harvest times, ultimately maximizing yield and olive oil quality. By integrating traditional agricultural practices with modern technological advancements, this study anticipates a range of positive outcomes, including reduced resource waste, improved competitiveness in global markets, and strengthened sustainability in production networks. The findings underscore the transformative potential of precision agriculture, offering valuable insights into sustainable agricultural development and setting a pathway for further innovation in the sector.","author":[{"family":"Fernandes","given":"Fernanda"},{"family":"Santos","given":"Murillo"},{"family":"Morais","given":"Maurício"},{"family":"Lima","given":"José"},{"family":"Pereira","given":"Ana"},{"family":"Mercorelli","given":"Paolo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iccc65605.2025.11022832","URL":"https://doi.org/10.1109/iccc65605.2025.11022832","source":"crossref"},{"id":"doi:10.1163/9789004725232_135","type":"article-journal","title":"Decoupling strategy for a heterogeneous multi-robot system for pest detection and treatment","abstract":"This paper presents a multi-robot system for the autonomous detection and treatment of pests. The system comprises two inspection robots, based on commercial electric vehicles, and two treatment robots equipped with electric sprayers. All four robots are fitted with cameras and global navigation satellite system (GNSS) receivers and operate under a cloud-based mission management system. The robots function decoupled, enabling autonomous navigation, real-time pest detection using convolutional neural network (CNN) models, and precision treatment application. The system was validated in Botrytis detection in white grape vineyards, demonstrating accurate path following, continuous image acquisition with an average 20 % overlap, and 95 % detection accuracy with a 30 % false positive rate.","author":[{"family":"Ribeiro","given":"A"},{"family":"Bengochea-Guevara","given":"JM"},{"family":"Andújar","given":"D"},{"family":"Ranz","given":"C"},{"family":"Montes","given":"H"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_135","URL":"https://doi.org/10.1163/9789004725232_135","source":"crossref"},{"id":"doi:10.1109/metroagrifor63043.2024.10948774","type":"article-journal","title":"AI-Driven Soil Moisture Forecasting for Enhanced Precision Agriculture","abstract":"This paper presents the development of a machine learning model aimed at accurately forecasting soil moisture levels, a crucial aspect of precision agriculture. The model leverages data from tensiometers, devices that measure soil water potential, installed in two distinct agricultural areas in Trentino, Italy. Utilizing a Long Short-Term Memory neural network, the model effectively captures and predicts the temporal dynamics of soil moisture. The data, sourced from multiple tensiometers with varying temporal and spatial frequencies, undergoes pre-processing to align sampling times and integrate environmental factors such as air humidity, temperature, and irrigation data. Our results demonstrate the strong trend-following capabilities of the model and an inherent ability to predict when soil moisture values cross critical agronomic thresholds, which is essential for optimizing irrigation schedules. These preliminary findings suggest that the proposed model could be a valuable tool in advancing precision irrigation practices, contributing to more sustainable and efficient agricultural production.","author":[{"family":"Grazieschi","given":"Paolo"},{"family":"Antonelli","given":"Fabio"},{"family":"Vecchio","given":"Massimo"},{"family":"Pincheira","given":"Miguel"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/metroagrifor63043.2024.10948774","URL":"https://doi.org/10.1109/metroagrifor63043.2024.10948774","source":"crossref"},{"id":"doi:10.1201/9781003662839-8","type":"article-journal","title":"Crop classification using deep learning and satellite data for precision agriculture","abstract":"Crop classification plays a vital role in precision agriculture by enabling efficient resource management and improving yield prediction. The advancement of remote sensing technologies has made it possible to obtain high-resolution satellite images from platforms such as Landsat-8 and Sentinel-2, which provide crucial data for identifying different types of crops. This study explores the application of deep learning models, particularly Convolutional Neural Networks (CNNs) and Transfer Learning, to classify crops accurately. This study focuses on pre-processing satellite data, training deep learning models on labelled crop datasets, and measuring various accuracy parameters (like MAE) for classification. The ultimate aim is to produce a comprehensive crop classification map to assist farmers in improving agricultural planning and resource management. The MAE for our different models lied in the range of 660,000 to 670,000.","author":[{"family":"Singh","given":"Gobind"},{"family":"Sharma","given":"Dhruv"},{"family":"Nalwa","given":"Paras"},{"family":"Lata","given":"Kusum"},{"family":"Singh","given":"Simrandeep"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003662839-8","URL":"https://doi.org/10.1201/9781003662839-8","source":"crossref"},{"id":"doi:10.1163/9789004725232_088","type":"article-journal","title":"Estimating yields, using a combination of remote sensing and a simple crop model","abstract":"Grain yields and their variability impact agronomic management decisions, yet accurate yield maps of multiple seasons in a comparable format are often unavailable at farm level. While crop growth models could estimate site-specific yields, they lack sufficient high-resolution input data. This study hypothesized that combining a growth model with satellite imagery-derived vegetation information could generate yield estimations and yield maps. The model was calibrated using field average yield data from 2017–2023 across relevant global cereal growing areas. The model achieved an r2 of 0.771 for training data and 0.443 for test data, demonstrating its potential for accurate yield mapping.","author":[{"family":"Federolf","given":"CP"},{"family":"Reusch","given":"S"},{"family":"Portz","given":"G"},{"family":"Truszkowski-Graw","given":"A"},{"family":"Jasper","given":"J"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_088","URL":"https://doi.org/10.1163/9789004725232_088","source":"crossref"},{"id":"doi:10.1201/9781003593089-5","type":"article-journal","title":"Smart farming system using IoT data and deep learning for precision agriculture","abstract":"India s expanding population and rising food requirements make husbandry essential. So yeah, twiddling up crop yields is principally essential these days. The thing is, conditions thanks to bacteria, stinky fungi, and sneaky contagions are stranding a ton of that eventuality. It s wild how important trouble these little troublemakers can beget for growers. These problems can be managed and dropped by putting into practice effective factory complaint discovery ways. Because machine literacy approaches influence data- driven perceptivity to give effective discovery results, they’re getting extensively utilized for illness identification. Machine literacy- grounded styles are particularly salutary for relating factory conditions, as they deliver precise results acclimatized to specific tasks. This study explores colorful artificial intelligence (AI) ways used in factory illness discovery, using deep literacy and machine literacy approaches. Among these, Deep literacy has come more popular for its capability to enhance discovery delicacy, especially within computer vision operations. The rapid progress of deep literacy has led to its successful perpetration across different fields, demonstrating significant advancements in computer vision and machine literacy tasks. This review evaluates considering the efficacity of machine literacy and deep literacy ways and operations, drawing perceptivity from colorful exploration studies. The findings punctuate the Deep literacy models‘ superiority over conventional machine literacy ways. To minimize crop losses, deep literacy has the eventuality to abused to directly identify splint conditions by examining prints of tormented factory.","author":[{"family":"Gupta","given":"Raunak"},{"family":"Gaur","given":"Khushi"},{"family":"Kushwaha","given":"Ashok"},{"family":"Chowdhary","given":"Mohit"},{"family":"Satpathy","given":"Sambit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003593089-5","URL":"https://doi.org/10.1201/9781003593089-5","source":"crossref"},{"id":"doi:10.1163/9789004725232_099","type":"article-journal","title":"Estimating cover crop biomass from optical satellite images for integration in a PrecisionAg service","abstract":"Cover crops play a critical role in enhancing soil health, preventing erosion, managing nutrients, and mitigating climate change through carbon sequestration. Accurate estimation of cover crop biomass is essential for optimizing agronomic and environmental benefits, especially for largescale precision agriculture applications. Despite their potential, estimating biomass accurately and efficiently over large areas remains a significant challenge. This study explores the use of optical multi-satellite imagery to estimate cover crop biomass through an empirical approach based on satellite-derived biophysical parameters and in-situ data. The aim is to integrate these estimations into a precision agriculture service to provide farmers with a turnkey solution that supports better nitrogen management and low carbon practices.","author":[{"family":"Veloso","given":"A"},{"family":"Biller","given":"C"},{"family":"Wolde-Mikael","given":"M"},{"family":"Ortolan","given":"M"},{"family":"Jacquin","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_099","URL":"https://doi.org/10.1163/9789004725232_099","source":"crossref"},{"id":"doi:10.1163/9789004725232_106","type":"article-journal","title":"Identifying the dominant species in cereal-legume cover crop mixtures with remote sensing for nitrogen fertilization management","abstract":"The relative proportions of cereals and legumes in cover crop mixtures can be used as a proxy of soil available N. At low N, the ability of legumes to fix atmospheric N provides them with a distinctive advantage and they can outcompete the cereals, while at higher N levels, cereals outcompete the legumes. A clover/oat mixture was sown with four nitrogen treatments that significantly affected their relative abundance within the mixture. Machine learning techniques were used to classify the UAV-RGB images into cereal and legume classes. Classification accuracies were 93, 85 and 76% at 64, 77 and 87 days after sowing (DAS), respectively. Clover volume was generally higher in the lower N application rates while cereal volume was greater in the higher application rates, in agreement with biomass results.","author":[{"family":"Futerman","given":"SI"},{"family":"Laor","given":"Y"},{"family":"Eshel","given":"G"},{"family":"Cohen","given":"Y"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_106","URL":"https://doi.org/10.1163/9789004725232_106","source":"crossref"},{"id":"doi:10.1163/9789004725232_064","type":"article-journal","title":"Temporal modelling of grape phenology using a monitoring camera sensor","abstract":"In this study, a daily grape images dataset derived from a set of 7 monitoring cameras (Vinelapse, IMS Laboratory) is presented. Features describing the joint evolution of grape colour, texture and berry sizes were then extracted using image processing. The relevance of a flexible statistical framework (generalized additive model) to model non-linear trends and identify periods of change in the time series is presented. Results show steady changes can be identified at certain periods, while accounting for model uncertainty. This illustrates the potential of daily grape images time series to compare the phenological behaviour of plants within the same vineyard.","author":[{"family":"Rançon","given":"F"},{"family":"Keresztes","given":"B"},{"family":"Pham","given":"VHH"},{"family":"Deshayes","given":"A"},{"family":"Mabrouk","given":"M"},{"family":"Costa","given":"JPD"},{"family":"Germain","given":"C"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_064","URL":"https://doi.org/10.1163/9789004725232_064","source":"crossref"},{"id":"doi:10.14746/quageo-2025-0008","type":"article-journal","title":"Application maps in precision agriculture – grassland production management in Poland","abstract":"This article discusses the topic of the use of application maps in precision agriculture (PA), particularly in the context of grassland management, which accounts for over 21% of utilised agricultural area (UAA) in Poland. New technological developments in the area of smart agriculture (Precision Agriculture, Agriculture 4.0), in terms of sensor technology and information processing, are creating a wide range of data acquisition opportunities to document biological production processes with both high temporal and spatial resolution. That information can be used to rationalise production processes and reduce trade-offs between different environmental services. The technologies that support this kind of research are analyses using satellite imagery, and map-based applications like the system developed in the GRASSAT project are discussed in detail in this article. The developed application provides farmers with information on events using free data from the Copernicus Programme (Sentinel-1, Sentinel-2, ERA5-Land reanalyses). Remote sensing indices, such as the Normalised Difference Vegetation Index (NDVI), Leaf Area Index (LAI), and fresh biomass production volumes, are calculated to show the condition of the green vegetation in the grassland plots. Meteorological risks, such as field freezing, are also presented. The GRASSAT application is available in both desktop and mobile versions.","author":[{"family":"Markowska","given":"Anna"},{"family":"Dąbrowska-Zielińska","given":"Katarzyna"},{"family":"Wróblewski","given":"Konrad"},{"family":"Wyczałek-Jagiełło","given":"Michał"},{"family":"Ziółkowski","given":"Dariusz"},{"family":"Goliński","given":"Piotr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14746/quageo-2025-0008","URL":"https://doi.org/10.14746/quageo-2025-0008","source":"crossref"},{"id":"doi:10.35760/jpp.2025.v9i2.36","type":"article-journal","title":"ANALISIS PERUBAHAN FISIOLOGIS BENIH KEDELAI (Glycine Max L Merill) PADA SUHU DAN LAMA PENYIMPANAN","abstract":"Penelitian ini dilakukan untuk mengetahui pengaruh suhu dan lama penyimpanan terhadap perubahan fisiologis yaitu mengindikasikan turunnya daya berkecambah benih, banyaknya jumlah benih abnormal benih kedelai. Faktor-faktor yang memengaruhinya meliputi asal atau sumber benih, kondisi lingkungan tumbuh, adanya kontaminasi di lapangan, keadaan pada periode antara masa lewat matang hingga sebelum dipanen, tahap pengeringan, penanganan, prosesing, serta cara penyimpanan. Metode yang digunakan adalah eksperimen kuantitatif Rancangan Acak Lengkap (RAL) dengan pola faktorial yaitu faktor A= suhu simpan dan faktor B=lama simpan. Benih yang digunakan adalah varietas Anjasmoro sebanyak 4 kg, berasal dari BALITKABI (Balai Penelitian Tanaman Aneka Kacang dan Umbi). Parameter yang diamati adalah potensi tumbuh (PT), daya berkecambah (DB), kecepatan tumbuh relatif (KcTR), keserampakan tumbuh (KsT), vigor kecambah (VK). Hasil penelitian diketahui bahwa suhu terbaik untuk menjaga kualitas benih kedelai adalah suhu refrigerator (5 0C) karena dapat menjaga kandungan karbohidrat, protein dan lemak. Kandungan biokimia yang terjaga dapat mempertahankan potensi tumbuh, viabilitas kecambah, keserampakan tumbuh (KsT), kecepatan tumbuh dan vigor kecambah benih kedelai.","author":[{"family":"Jasmi"},{"family":"Harahap","given":"EJ"},{"family":"Setyowati","given":"Mita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35760/jpp.2025.v9i2.36","URL":"https://doi.org/10.35760/jpp.2025.v9i2.36","source":"crossref"},{"id":"doi:10.1201/9781003584438-9","type":"article-journal","title":"Augmented Reality in Sustainable Farming: Exploring Use Cases for Precision Agriculture","abstract":"Augmented reality (AR) is revolutionizing the agricultural sector by making precision, efficiency, and sustainability at the core of farming practices. This chapter goes through the AR s transformative power in solving various critical challenges related to agriculture. These include issues of resource optimization, environmental conservation, and increasing productivity. The chapter also examines the role of AR in reducing environmental footprints through targeted interventions, minimizing water and pesticide use, and lowering carbon emissions. Case studies from global farming projects demonstrate the use of AR technology would provide practical benefits related to scaling up in different agricultural scenarios. The findings here should provide a guiding roadmap for researchers, policymakers, and practitioners intent on moving sustainable agriculture forward.","author":[{"family":"Singh","given":"Shivam"},{"family":"Barhate","given":"Riddhi"},{"family":"Kokane","given":"Chandrakant"},{"family":"Deotare","given":"Vilas"},{"family":"Pawar","given":"Pranav"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003584438-9","URL":"https://doi.org/10.1201/9781003584438-9","source":"crossref"},{"id":"doi:10.3920/978-90-8686-549-9_071","type":"article-journal","title":"Wireless sensor networks for precise Phytophthora decision support","abstract":"Precision Agriculture provides the optimal treatment for each production unit that can be distinguished and which can be individually treated in an efficient way. This agricultural practise is based on detailed information on the status of crops and soil. Most of this information focuses on techniques like soil mapping, yield mapping and remote sensing, which cover the spatial domain with more or less spatial resolution. The information is incidentally sampled and is therefore valid at the time the observations are made. Some of the processes like fertilization and especially crop protection require frequent updates in information. Sensor systems that are continuously present can deliver such information. Several research groups and companies are working on the development of “Smart Dust”. “Smart Dust ” stands for a sensor, a processor and a means of communication that will be packaged into a few cubic millimetres in the future. It is expected that these devices will be available in six years at a cost of around one dollar apiece, although downsizing might not have reached the intended level at that time. Such wireless sensor systems can form a dense network and provide the possibility for continuous monitoring of relevant parameters in a dense grid for a reasonable price.","author":[{"family":"Goense","given":"D"},{"family":"Thelen","given":"J"},{"family":"Langendoen","given":"K"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3920/978-90-8686-549-9_071","URL":"https://doi.org/10.3920/978-90-8686-549-9_071","source":"crossref"},{"id":"doi:10.3920/978-90-8686-549-9_073","type":"article-journal","title":"Agricultural robots: an economic feasibility study","abstract":"This paper focuses on the economic feasibility of applying autonomous robotic vehicles compared to conventional systems in three different applications: robotic weeding in high value crops (particularly sugar beet), crop scouting in cereals and cutting grass on golf courses. The comparison is based on a systems analysis and an individual economic feasibility study for each of the three applications. The results showed that in all three scenarios, the robotic applications are more economically feasible than the conventional systems. The high cost of RTK-GPS and the small capacity of the vehicles are the main parameters that increase the cost of the robotic systems.","author":[{"family":"Pedersen","given":"SM"},{"family":"Fountas","given":"S"},{"family":"Have","given":"H"},{"family":"Blackmore","given":"BS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3920/978-90-8686-549-9_073","URL":"https://doi.org/10.3920/978-90-8686-549-9_073","source":"crossref"},{"id":"doi:10.3920/978-90-8686-549-9_100","type":"article-journal","title":"Topographical data for delineation of agricultural management zones","abstract":"The aim of this study was to delineate management zones by using topographical data, and to investigate how these management zones relate to soil parameters and yield. Elevation, as well as soil and yield data, were sampled in the field. Digital elevation models have been created, and the topographical parameters of slope, aspect and drainage area, estimated. Management zones have been delineated by the use of threshold values and filtering. Significant differences between the zones with respect to organic matter, clay content, phosphorus, pH, potassium, magnesium and yield have been found. The results indicate that topographical data can be used delineate agricultural management zones in central Sweden.","author":[{"family":"Pilesjö","given":"Petter"},{"family":"Thylén","given":"Lars"},{"family":"Persson","given":"Andreas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3920/978-90-8686-549-9_100","URL":"https://doi.org/10.3920/978-90-8686-549-9_100","source":"crossref"},{"id":"doi:10.1201/9781003501220-9","type":"article-journal","title":"Industry 5.0 Unveiled, Precision Agriculture Empowered","abstract":"The agricultural sector is undergoing a transformative paradigm shift with the integration of recommendation and prediction systems. These cutting-edge technologies are now crucial in determining how both farmers and sellers make decisions. Stakeholders in the agricultural sector can optimize crop choices, pricing tactics, and general farm management by utilizing data analytics and prediction algorithms. To reveal the diverse uses and effects of these advancements, this study investigates the ramifications of applying recommendation and prediction techniques to farming. In order to better understand the convergence of recommendation and prediction in the agricultural domain, this research explores the creation and deployment of a novel online application. The platform is designed to promote smooth interactions between farmers and merchants, improving the agricultural supply chain’s efficiency and transparency. Farmers are permitted to engage in negotiated agreements with vendors and sell their grown commodities at basic prices determined by the market. In turn, vendors gain from predictive functions that take profitability, seasonal demand, and market conditions into account when making strategic decisions. The paper highlights the privacy-conscious strategy used for creating farming suggestion and prediction systems. The web application has distinct logins for farmers and vendors, with tailored features for each user group. Transparency and accountability are encouraged via a complete dashboard that displays the past transactional data between farmers and merchants. With support for both Marathi and English, the portal serves a wide range of users. By means of this novel application, the study clarifies a noteworthy advancement in the restructuring of agricultural transactions, promoting effectiveness, equity, and financial sustainability for all parties concerned.","author":[{"family":"Rathod","given":"Kaustubh"},{"family":"Rathi","given":"Devesh"},{"family":"Naranje","given":"Sankalp"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003501220-9","URL":"https://doi.org/10.1201/9781003501220-9","source":"crossref"},{"id":"doi:10.1016/j.jafr.2025.102056","type":"article-journal","title":"From Moo to Microbes: Pathways for precision fermentation in recombinant protein production","abstract":"Meeting global protein demands amid climate change, land scarcity, and a projected population of nearly 10 billion by 2050 requires innovative, sustainable approaches. Traditional dairy and beef sectors contribute significantly to greenhouse gas emissions - dairy alone may emit up to 72 kg CO 2 eq per kilogram of milk protein. Precision fermentation (PF) has emerged as an alternative that harnesses genetically engineered microbes (e.g., Trichoderma reesei , yeasts) to produce animal-equivalent proteins, offering potential reductions in resource use and environmental impacts compared to livestock systems. This paper synthesizes existing life cycle assessments (LCAs), technical process data, and national agricultural statistics to compare PF-derived proteins - focusing on β-lactoglobulin (β‐LG) -to conventional dairy in Germany. Four scenarios are modeled: (1) reallocating the nation’s entire sugar production, (2) using only surplus sugar above Planetary Health Diet recommendations, (3) repurposing maize acreage, and (4) extracting sugar from grasslands. Feedstock requirements (sugar, ammonia, minerals) and energy inputs (electricity for fermentation) were combined to estimate per-kilogram land use for PF proteins under each scenario. Results were then benchmarked against dairy-based β‐LG, which has a land footprint of 19-68 m 2 /kg depending on allocation rules. Findings indicate that high-yield sugar crops (e.g., sugar beet, maize) or surplus sugar streams could feasibly produce substantial volumes of PF protein while limiting new land requirements. Grass-based feedstock is also viable, albeit with higher land footprints. Key challenges include ensuring green ammonia supplies, integrating renewable energy, and navigating socioeconomic trade-offs such as farm employment and nutrient cycling. Nonetheless, PF may complement or reduce reliance on traditional animal agriculture, particularly where grazing land or sugar surpluses can be redirected without compromising food security. Further research on feedstock optimization, techno-economic feasibility, and policy frameworks-such as incentives for “green” inputs-will be vital to accelerating PF’s contribution to a more sustainable protein supply.","author":[{"family":"Kossmann","given":"Hanno"},{"family":"Karslioglu","given":"Özlem"},{"family":"Breunig","given":"Peter"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.jafr.2025.102056","URL":"https://doi.org/10.1016/j.jafr.2025.102056","source":"crossref"},{"id":"doi:10.9734/jeai/2026/v48i54254","type":"article-journal","title":"Deficit Irrigation and Precision  Water Management: Climate-Smart  Strategies for Sustainable Agriculture","abstract":"Agriculture accounts for approximately 70% of global freshwater withdrawals, and this proportion rises to over 90% in many arid and semi-arid regions. As the global population approaches 10 billion and climate change intensifies hydrological variability, the imperative to produce more food with substantially less water has never been more urgent. Deficit irrigation (DI) and precision water management (PWM) have emerged as central pillars of climate-smart agriculture (CSA), offering the twin capacity to sustain crop productivity while dramatically reducing water consumption. This review synthesises scientific evidence on the conceptual foundations, technological advancements, agronomic outcomes, and policy implications of DI and PWM within a CSA framework. Strategies encompassing regulated deficit irrigation (RDI), partial root zone drying (PRD), sensor-based scheduling, remote sensing, Internet of Things (IoT)-enabled smart irrigation, and decision support systems are critically evaluated. Evidence from diverse agroecological contexts indicates that well-implemented DI regimes can reduce irrigation water use by 20–50% with minimal yield penalties, particularly when stress is confined to drought-tolerant growth stages. Integration of precision technologies enhances temporal and spatial resolution of irrigation decisions, further improving water productivity. The review also highlights the alignment of DI and PWM with the three pillars of CSA—increased productivity, enhanced adaptation, and mitigation of greenhouse gas emissions. Notwithstanding documented agronomic and environmental co-benefits, several barriers persist, including knowledge asymmetries among smallholder farmers, high initial investment costs for precision technology, and inadequate institutional and policy support. The review identifies critical research gaps, including a need for more long-term field trials, economic analyses in smallholder contexts, and improved crop-model integration with real-time sensing. The article concludes that a convergence of precision technology, adaptive management, and enabling governance can position DI and PWM as transformative climate-smart strategies for sustainable agriculture globally.","author":[{"family":"Jadhav","given":"Suraj"},{"family":"Kamble","given":"Sagar"},{"family":"Patil","given":"Sachin"},{"family":"Raut","given":"Dnyaneshwar"},{"family":"Shende","given":"Sudarshan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/jeai/2026/v48i54254","URL":"https://doi.org/10.9734/jeai/2026/v48i54254","source":"crossref"},{"id":"doi:10.3390/agriculture16141541","type":"article-journal","title":"Economic Performance of Precision and Conventional Maize Production: Comparative Analysis Using Hungarian Farm-Level Data","abstract":"This study evaluates the economic and agronomic performance of precision maize production under drought-stressed conditions using farm-level operational data from Hungary. A 2024 paired-field case study compared a conventionally managed field (46.65 ha) with a precision-managed field (67.61 ha) using variable-rate fertilization and seeding. Data collected via the John Deere Operations Center enabled 10 × 10 m spatial analysis. Results indicate that despite severe moisture limitations, the precision-managed field achieved a 3.85% higher mean yield (6.47 t ha−1) than the conventional system (6.23 t ha−1). The observed economic advantage was associated with a 5.58% reduction in total production costs through site-specific resource allocation. Consequently, net profit increased by 62.98%, rising from 168.95 USD ha−1 to 275.36 USD ha−1. Spatial analysis demonstrated that precision management synchronized economic outputs with inherent site potential, with management zones accounting for 70.70% of profit variance, compared to 53.3% in the conventional field. Regression models confirmed a tighter alignment between NDVI (Normalized Difference Vegetation Index) and profitability in the precision system. These findings suggest that under spatial heterogeneity and climatic stress, precision agriculture enhances economic resilience by mitigating inefficient expenditures, providing a strategic buffer against input costs and climate volatility.","author":[{"family":"Horváth","given":"Dávid"},{"family":"Szabó","given":"Levente"},{"family":"Hadászi","given":"László"},{"family":"Szabó","given":"Emese"},{"family":"Riczu","given":"Péter"},{"family":"Nábrádi","given":"András"},{"family":"Szűcs","given":"István"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16141541","URL":"https://doi.org/10.3390/agriculture16141541","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.101994","type":"article-journal","title":"Farm typologies and precision agriculture technology co-adoption in German agriculture: A combined cluster and network approach","abstract":"Existing research predominantly focuses on individual precision agriculture technologies (PAT) adoption decisions, offering limited insight into how technologies are combined, how adoption intensity varies across farms and which farm and farmer characteristics differentiate adoption patterns. Against this background, this study identifies farm types that reflect different levels of PAT integration based on the adoption intensity of 32 technologies and examines the observed structure of technology co-adoption. Based on a stratified random-sampling process, survey data from 342 German arable farms were collected via computer-assisted telephone interviews between December 2024 and January 2025. We combine cluster analysis and technology-level network analysis to jointly assess farm-level heterogeneity and patterns of technology co-adoption. The results reveal two farm types that differ primarily in overall PAT adoption intensity rather than domain-specific technology specialization, with systematic differences in farm and farmer characteristics between types. Network analysis identifies a stable technological core centered on guidance and application control technologies, which connect multiple technology domains, while robotic technologies represent a structurally distinct cluster within the broader PAT co-adoption network. Overall, the findings are consistent with technological integration logics, with differences reflecting levels of integration rather than divergent strategies. The results offer actionable implications for technology providers, advisory services, and policymakers seeking to support PAT adoption.","author":[{"family":"Michels","given":"Marius"},{"family":"Twietmeyer","given":"Jasper"},{"family":"Musshoff","given":"Oliver"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.101994","URL":"https://doi.org/10.1016/j.atech.2026.101994","source":"crossref"},{"id":"doi:10.1109/metroagrifor63043.2024.10948749","type":"article-journal","title":"From AI Based Object Detection Model to Grape Yield Mapping for Precision Agriculture Applications","abstract":"Yield mapping in vineyards is crucial for agronomic and economic management, allowing for precision operations like pruning, harvesting, fertilization, irrigation, and soil management. This leads to optimized resource use, improved grape quality, and increased productivity. Traditional yield mapping relies on expensive grape harvesters, which can cause grape loss and are not suitable for manually harvested vineyards. This research proposes a low-cost framework combining hardware and computer vision to generate yield variability maps, which can be used to create management zones for precision agriculture applications. The Yolov8 obtained the best performance with an overall precision of 89%. This approach aims to reduce reliance on costly machinery, enhance data accuracy, and make precision agriculture more accessible and effective.","author":[{"family":"Lindo","given":"Nepi"},{"family":"Fiorentini","given":"Marco"},{"family":"Mancini","given":"Adriano"},{"family":"Ledda","given":"Luigi"},{"family":"Pierdicca","given":"Roberto"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/metroagrifor63043.2024.10948749","URL":"https://doi.org/10.1109/metroagrifor63043.2024.10948749","source":"crossref"},{"id":"doi:10.37221/eaef.18.4_261","type":"article-journal","title":"Assessing wheat yield response to soil compaction using machine learning","abstract":"This study evaluated the impact of soil compaction, expressed as bulk density (BD), on spring wheat using field trials with vibratory plate-compacted subplots (BD: 1.17-1.30Mg/m 3 ).Key soil properties, nutrient uptake, and yield were measured under varying BD.PLSR with cross-validation identified key predictors and was compared with MLR/LR for yield modeling.Moderate compaction (BD3: 1.24 Mg/m 3 ) optimized nutrient utilization, producing 173.6 % more yield than highly compacted soil (BD1).The Control subplots (BD: 1.17 Mg/m 3 ) yielded 143.4 % more than BD1.Spatial analysis showed that combined phosphorus-calcium-magnesium dynamics explained 97.2 % of yield variation (R 2 = 0.972).Nutrient maps supported precision fertilization planning, showing that soil compaction significantly affects wheat productivity through multiple pathways.","author":[{"family":"Amanor","given":"Ishmael"},{"family":"Ospina","given":"Ricardo"},{"family":"Noguchi","given":"Noboru"}],"issued":{"date-parts":[[2025]]},"DOI":"10.37221/eaef.18.4_261","URL":"https://doi.org/10.37221/eaef.18.4_261","source":"crossref"},{"id":"doi:10.3390/agriculture15212215","type":"article-journal","title":"Precision Feeding Systems in Animal Husbandry: Guiding Rabbit Farming from Concept to Implementation","abstract":"Precision Feeding Systems (PFS) demonstrate transformative potential in advancing sustainable and efficient production within modern animal husbandry. However, existing research lacks a synthesis of PFS applications in livestock farming and offers little targeted guidance for China’s rapidly growing rabbit industry. The objective of this review is to bridge this gap by synthesizing current knowledge on PFS technologies—including sensor networks, artificial intelligence (AI), automated controls, and data analytics—and providing a structured framework for their implementation in rabbit production. This study selects and analyzes 112 core references, establishing a foundational database for comprehensive evaluation. The key contributions of this work are threefold: first, it outlines the core components and operational mechanisms of PFS; second, it identifies major challenges such as sensor reliability in dynamic environments, data security risks, limited explainability of AI models, and interoperability barriers; and third, it proposes a customized strategy for PFS adoption in rabbit farming, emphasizing phased implementation, cross-system integration, and iterative optimization. The primary outcomes and advantages of adopting such a system include significant improvements in feed efficiency, resource utilization, animal welfare, and waste reduction—critical factors given rabbits’ sensitive digestive systems and precise nutritional needs. Furthermore, this review outlines a future research agenda aimed at developing resilient sensors, explainable AI frameworks, and multi-objective optimization engines to enhance the commercial scalability and sustainability of PFS in rabbit husbandry and beyond.","author":[{"family":"Jiang","given":"Wei"},{"family":"Li","given":"Guohua"},{"family":"Xu","given":"Jitong"},{"family":"Qin","given":"Yinghe"},{"family":"Wang","given":"Liangju"},{"family":"Wang","given":"Hongying"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15212215","URL":"https://doi.org/10.3390/agriculture15212215","source":"crossref"},{"id":"doi:10.1016/j.jafr.2026.102744","type":"article-journal","title":"Research on the scale effects of UAV flight altitude and crop single-plant mapping for precision agriculture","abstract":"Crop single-Plant mapping serves as the core data foundation for precision agriculture management. In response to the problems of remote sensing data discontinuity, difficult sample acquisition, and terrain heterogeneity caused by cloudy, rainy, and foggy weather in Karst mountainous areas, study is based on UAV Multi-flight Altitude(MA) (5m-100m) RGB images to construct 5m, 35m, 65m, 95m, and Multi-flight Altitude Fusion(MAF) tobacco datasets. Combined with eight models such as U-Net, the study systematically explores the variation law of tobacco characteristics with altitude and the scale selection problem for accurate drawing. Research has found that: (1) The characteristics of tobacco show regular changes with Flight Altitude(FA), and the distribution of Digital Number(DN) values of tobacco plants changes from bimodal (5m-65m) to unimodal (70m-100m), with the DN peak increasing from 90 to 142; Texture features gradually weaken, background interference increases, and identification difficulty increases. (2) The accuracy of model identification is significantly negatively correlated with FA (Pearson's r=-0.99, p<0.01), among which U-Net/U-Net++ stability (CV<15%) is significantly better than PSPNet/PAN (CV<45%). There is a significant difference in the adaptability of the model to FA (ANOVA, F=9.41, p=3.2×10 -4 ), with U-Net/U-Net+ having the best overall performance (95m IoU=0.69), and PSPNet showing a failure in feature extraction (66.7% decrease in IoU from 5m to 95m). (3) Through the correlation analysis between FA and model performance, it was found that the MAF dataset can significantly expand the effective identification range of FA (5m-90m), with U-Net/DeepLabV3+(5m), U-Net (35m, 65m), FPN (95m), and LinkNet (MAF) showing the best comprehensive performance. Study adopts a combination of single FA and MAF datasets to systematically analyze the model identification performance under the same FA and cross FA conditions, reveal the optimal spatial scale for crop identification and the model's adaptability to FA, and provide theoretical and technical support for precise agricultural monitoring.","author":[{"family":"Li","given":"Qianxia"},{"family":"Zhou","given":"Zhongfa"},{"family":"Wei","given":"Lai"},{"family":"Ao","given":"Guangyuan"},{"family":"Qian","given":"Yuzhu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.jafr.2026.102744","URL":"https://doi.org/10.1016/j.jafr.2026.102744","source":"crossref"},{"id":"doi:10.5281/zenodo.21904769","type":"article-journal","title":"D1.2 Obstacles and strategies for EU Food Security and independence, and use of digital solutions","abstract":"This document outlines the policy landscape related to agricultural independence and food security, providing the foundation for subsequent NOSTRADAMUS deliverables. It examines the policies, strategies, and practices that support sustainable, resilient, and secure agricultural systems, with particular emphasis on the growing role of digitalisation, data integration, precision agriculture (PA), innovative technologies, and data-driven decision-making. The deliverable addresses the challenges of agricultural independence within the European Union, focusing on reducing dependence on agrochemicals, mitigating the effects of price volatility, and strengthening resilience to external trade pressures. It analyses key EU policy frameworks, including the Common Agricultural Policy (CAP), the European Green Deal, the Farm-to-Fork Strategy, the REPowerEU Initiative, and the One Health Initiative, together with the EU Digital Strategy, the Chemicals Strategy for Sustainability, and Digital Education policies. The priorities identified through this analysis will inform future NOSTRADAMUS activities, particularly those related to data and technological sovereignty, interoperability and compatibility of data collection systems and digital tools, sustainability at farm level, and the socio-economic factors influencing the digitalisation of small-scale farms.","author":[{"family":"Kandel","given":"Giri"},{"family":"Manikas","given":"Ioannis"},{"family":"Poláková","given":"Jana"},{"family":"Varvaris","given":"Ioannis"},{"family":"Hruška","given":"Adam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21904769","URL":"https://doi.org/10.5281/zenodo.21904769","source":"datacite"},{"id":"doi:10.5281/zenodo.21904768","type":"article-journal","title":"D1.2 Obstacles and strategies for EU Food Security and independence, and use of digital solutions","abstract":"This document outlines the policy landscape related to agricultural independence and food security, providing the foundation for subsequent NOSTRADAMUS deliverables. It examines the policies, strategies, and practices that support sustainable, resilient, and secure agricultural systems, with particular emphasis on the growing role of digitalisation, data integration, precision agriculture (PA), innovative technologies, and data-driven decision-making. The deliverable addresses the challenges of agricultural independence within the European Union, focusing on reducing dependence on agrochemicals, mitigating the effects of price volatility, and strengthening resilience to external trade pressures. It analyses key EU policy frameworks, including the Common Agricultural Policy (CAP), the European Green Deal, the Farm-to-Fork Strategy, the REPowerEU Initiative, and the One Health Initiative, together with the EU Digital Strategy, the Chemicals Strategy for Sustainability, and Digital Education policies. The priorities identified through this analysis will inform future NOSTRADAMUS activities, particularly those related to data and technological sovereignty, interoperability and compatibility of data collection systems and digital tools, sustainability at farm level, and the socio-economic factors influencing the digitalisation of small-scale farms.","author":[{"family":"Kandel","given":"Giri"},{"family":"Manikas","given":"Ioannis"},{"family":"Poláková","given":"Jana"},{"family":"Varvaris","given":"Ioannis"},{"family":"Hruška","given":"Adam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21904768","URL":"https://doi.org/10.5281/zenodo.21904768","source":"datacite"},{"id":"doi:10.5281/zenodo.21904525","type":"article-journal","title":"D1.2 Obstacles and strategies for EU Food Security and independence, and use of digital solutions","abstract":"This document's main objective is to outline the policy landscape associated with agricultural independence and food security and to serve as the basis for further project deliverables. To achieve this, the report examines the practices, policies, and strategies that support sustainability, resilience, and food security in agriculture. Increasingly, these efforts rely on digitalisation, data integration, precision agriculture (PA), innovative technologies, and enhanced data use across the agricultural sector. The deliverable addresses the challenges of agricultural independence and food security in the European Union (EU), where agricultural independence refers to reducing reliance on agrochemicals, mitigating the impacts of fluctuating prices, and addressing external trade pressures. EU-level policies and strategies analysed in this report include the Common Agricultural Policy (CAP), the European Green Deal, the Farm-to-Fork Strategy, the REPowerEU Initiative, and the One Health Initiative, encompassing its four pillars of resilience. In addition, the EU Digital Strategy, the Chemicals Strategy for Sustainability, and Digital Education policies are considered. The priorities identified through this analysis will inform subsequent NOSTRADAMUS deliverables, particularly those related to data and technology sovereignty, interoperability and compatibility of digital tools, databases and data collection systems, sustainability at farm level, and the socio-economic factors influencing the digital transformation of European agriculture.","author":[{"family":"Kandel","given":"Giri"},{"family":"Manikas","given":"Ioannis"},{"family":"Poláková","given":"Jana"},{"family":"Hamouz","given":"Pavel"},{"family":"Hruška","given":"Adam"},{"family":"Varvaris","given":"Ioannis"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21904525","URL":"https://doi.org/10.5281/zenodo.21904525","source":"datacite"},{"id":"doi:10.5281/zenodo.21825597","type":"article-journal","title":"THE INTEGRATION OF THE LATEST TECHNOLOGICAL ADVANCEMENTS IN AGRICULTURE. WHAT ARE THEIR EXACT APPLICATIONS AND HOW DO THEY WORK?","abstract":"Agriculture is not only about planting crops and raising animals, it is way more than that. Agriculture is a business which supports human life, provides raw materials and builds strong economies, playing an extremely important role in our livelihoods, even if we may not always notice that. Experts from this sector, however, say that the new global situation asks for a so called \"revolution\" in agriculture. Only in the last two decades, climate changes have been responsible for a productivity decrease of 21% in this business. Moreover, taking into consideration the pandemic and the political situation from the recent years, which led to a raise of the production costs, farmers and entrepreneurs are more and more worried about the way they are going to make their businesses profitable. We should also mention that the worldwide food need is going to be 50% higher in 2050 than in the present. Fortunately, technological advancements come as a solution to these problems. Not only do they have an impact on the production costs, but they also help in reducing pollution around the world. A 2022 Deloitte study in collaboration with the Environmental Defense Fund revealed that the use of technology in agriculture can decrease with 9.8 gigatons the production of carbon dioxide-equivalent emissions (CO2e) between 2020 and 2050, as well as save up to 100 billion US dollars in costs to farmers by 2030. The agricultural technology, also known as \"AgriTech\", promises a more efficient use of equipment and an increase in crop yields, all of these while following a sustainable production plan, generally referred to as \"precision agriculture\".","author":[{"family":"Tabusca","given":"Alexandru"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5281/zenodo.21825597","URL":"https://doi.org/10.5281/zenodo.21825597","source":"datacite"},{"id":"doi:10.70917/ijcisim-2026-4516","type":"article-journal","title":"A Comprehensive Review Of Statistical Methods For Enhancing Performance In Precision Agriculture","abstract":"Even more precision agriculture tools rely on statistical techniques for fruit detection and recognition optimisation. A thorough review of these statistical techniques was built in this paper, and they have been applied to fruit detection systems since 2018 for efficiency, accuracy, and robustness. Thinking about how advanced statistical methods integrate with machine learning algorithms and deep neural networks, we face significant obstacles such as handling imbalanced datasets, improving detection in occluded or dense environments and dealing with variation between fruit size, shape, and species. Statistical methods also enhance data cleaning before use, feature extraction, and model evaluation, leading to faster fruit detection and more accurate results. A review paper is the result of combining ideas from many experts. It should help the development of precision agriculture focused on lower resource usage farther afield and seeing agro-environmental detection systems as equivalent. Now, we discuss solutions to those problems and future trends in statistical methodology. This work aims to set the direction for future precision agriculture research and practice by pointing out how to reduce the computational complexity of detection systems under various agro-environmental conditions.","author":[{"family":"Shriwas","given":"Raviprakash"},{"family":"Helonde","given":"JB"},{"family":"Burade","given":"Prakash"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70917/ijcisim-2026-4516","URL":"https://doi.org/10.70917/ijcisim-2026-4516","source":"crossref"},{"id":"doi:10.62019/yy6fb844","type":"article-journal","title":"LEVERAGING ARTIFICIAL INTELLIGENCE FOR PRECISION AGRICULTURE: APPLICATIONS IN BOTANY","abstract":"Background: The implementation of artificial intelligence (AI) systems in precision agriculture attracts substantial research because they have shown promise in both improving farming operations along yield growth. The research explores AI applications within botany with a specific focus on crop health monitoring and soil analysis alongside weather prediction algorithms accurate decision systems and yield optimization processes. Objectives: This research sets out to establish quantitative correlations between AI-based crop health tracking mechanisms AI-based soil testing approaches AI-provided weather prediction solutions and decision precision and improved crop yield outcomes. This research examines how well AI solutions handle essential agricultural problems. Methods: Researchers used a structured survey instrument to collect data from three groups including farmers and researchers alongside technology professionals among 355 participants. The questionnaire contained rating scale items distributed on a 5-point Likert scale. Team researchers used descriptive statistics alongside the Shapiro-Wilk test and Cronbach's Alpha to analyze the data. Results: All variables exhibited significant deviations from normality according to the Shapiro-Wilk test (p &lt; 0.05) requiring the use of non-parametric analysis techniques. Results showed a Cronbach's Alpha rating of 0.57 which reflects moderate unitary scale consistency within the survey instrument. The research demonstrates how stakeholders experience different levels of interaction with AI systems while revealing gaps in current measurement instruments. Conclusions: The analysis presents clear evidence about how AI technology can boost farming outcomes and yield optimization initiatives in precision agriculture operations. The current research needs better design approaches because it revealed moderate questionnaire reliability and non-normal distribution of data points. Researchers agree that AI systems must deliver customized solutions that address the requirements and obstacles faced by different members of the agricultural community. Future research priorities include developing enhanced data collection procedures together with non-parametric data analysis solutions and solutions to barriers impeding agricultural AI adoption.","author":[{"family":"Majeed","given":"Lubna"},{"family":"Durrani","given":"Faran"},{"family":"Hayat","given":"Shabnam"},{"family":"Nwodom","given":"Nwodom"},{"family":"Gul","given":"Fabia"},{"family":"Wasti","given":"Maria"},{"family":"Rashid","given":"Sadaf"},{"family":"Aman","given":"Asia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.62019/yy6fb844","URL":"https://doi.org/10.62019/yy6fb844","source":"crossref"},{"id":"doi:10.9734/arja/2025/v18i4763","type":"article-journal","title":"Integration of Sprinkler Technology and Precision Irrigation for Enhanced Resource Management in Crop Production: A Review","abstract":"The non-judicious allocation of water resources at the farm level, predominantly through traditional irrigation methods, presents a critical challenge to global sustainability, particularly given that the agricultural sector consumes in excess of 70% of available freshwater. Enhancing application efficiency through the deployment of advanced pressurized techniques, specifically sprinkler irrigation, is an essential strategy for mitigation. This review systematically assesses the evolution of sprinkler technology and its critical convergence with precision irrigation (PI) methodologies. A modified literature exploration, based on PRISMA 2020 guidelines, was used wherein only primary field studies published after 2005 were included and review articles and simulation-only studies were excluded. Citation chaining was additionally used to identify key irrigation engineering papers. Findings confirm that traditional sprinkler systems achieve a remarkable 39% reduction in water consumption and elevate water productivity by over 14.1% when contrasted with surface gravity systems. Furthermore, the technological apex is reached when sprinkler application is coupled with PI automation and sensor integration. Such systems realize an additional 20−30% water saving and contribute to significant crop yield increases, ranging from 20% to 27.5%. Critical technological domains analyzed include the optimization of mechanical systems (Center Pivot and Linear Mover), the innovation in low-pressure hydraulic nozzles, and the development of responsive control systems, such as Model Predictive Control (MPC). The study underscores that future research must prioritize developing easily adoptable, cost-effective advanced control algorithms and refine nozzle hydraulics to reliably minimize wind drift and evaporation losses, which often compromise application efficiency.","author":[{"family":"Pandey","given":"Yogesh"},{"family":"Dadhich","given":"Sushmita"},{"family":"Warsi","given":"Ahmad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/arja/2025/v18i4763","URL":"https://doi.org/10.9734/arja/2025/v18i4763","source":"crossref"},{"id":"doi:10.71143/gc4v7n32","type":"article-journal","title":"Advancements in Precision Agriculture for Maximizing Crop Yield and Minimizing Waste via Innovative Technological Solutions","abstract":"Precision agriculture, a technology-driven approach to farming, integrates GPS, IoT sensors, Variable Rate Technology (VRT), and data analytics to optimize crop yield and resource usage. This study explores the effectiveness of precision agriculture in enhancing productivity and promoting sustainable farming practices by analysing its impact on crop yield, water and fertilizer usage, and environmental metrics. Data was collected through IoT sensors, GPS mapping, and drone-based remote sensing to monitor field conditions, while VRT was used to apply inputs precisely where needed. Comparative analyses between precision and traditional agriculture show a 20% increase in crop yield and a 40% reduction in water and fertilizer usage for fields employing precision techniques. Environmental benefits were also notable, with significant decreases in greenhouse gas emissions and pesticide runoff. Case studies across diverse farming setups and controlled experiments provided further insights into the practical applications and challenges of precision agriculture. While results indicate substantial improvements in efficiency and sustainability, barriers such as high initial costs and technical expertise requirements remain obstacles for broader adoption, particularly among small-scale farmers. Addressing these challenges will require collaborative efforts from policymakers, agricultural organizations, and technology providers to develop accessible and cost-effective solutions. This study concludes that precision agriculture offers a promising path to sustainable, high-yield farming by reducing resource consumption and minimizing environmental impact. However, increased focus on overcoming adoption barriers is essential to make precision agriculture feasible for a wider range of farmers. Further research should continue to optimize these technologies, making them scalable and adaptable to various agricultural contexts worldwide.","author":[{"family":"Rani","given":"Hema"},{"family":"Kakkar","given":"Priyanka"},{"family":"Singh","given":"Devendra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71143/gc4v7n32","URL":"https://doi.org/10.71143/gc4v7n32","source":"crossref"},{"id":"doi:10.1201/9781003662839-80","type":"article-journal","title":"Towards precision agriculture: A review of image segmentation techniques and their future prospects","abstract":"Image segmentation technique is frequently employed in areas such as precision agriculture, facial recognition, and medical image processing. Techniques for segmenting data include CNN-based segmentation based on semi supervised learning, clustering-based segmentation, region and edge-based segmentation and many more. are some of the current picture/image segmentation techniques. These picture segmentation techniques are scrutinized, summarized, and in this study, their advantages and disadvantages are contrasted. Finally, using the combination of these methods, we forecast the future direction of image segmentation.","author":[{"family":"Bagga","given":"Manju"},{"family":"Singh","given":"Tejbir"},{"family":"Walia","given":"Rubika"},{"family":"Neelima"},{"family":"Thakral","given":"Prateek"},{"family":"Sharma","given":"Ravi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003662839-80","URL":"https://doi.org/10.1201/9781003662839-80","source":"crossref"},{"id":"doi:10.22399/ijcesen.5450","type":"article-journal","title":"A Systematic Literature Review of IoT- and AI-Based Intelligent Irrigation Systems for Water Optimization in Precision Agriculture","abstract":"The increasing global demand for water has emphasized the importance of irrigation systems capable of efficiently managing water use in precision agriculture. This paper presents a review of one hundred studies published between 2018 and 2025 that address the application of Internet of Things (IoT) technologies and computational approaches in irrigation management. The reviewed literature describes the use of sensor networks, wireless communication systems data-driven control mechanisms and automated decision-support tools aimed at improving irrigation practices while supporting crop production. The studies are organized according to the technologies and methods employed, including sensor-based data acquisition IoT-enabled monitoring platforms and intelligent irrigation control systems. A hybrid classification is also introduced to describe approaches that combine predictive modelling with adaptive irrigation strategies. Additionally, the reviewed works are discussed with respect to several system-related aspects such as water management objectives system architecture, and application scale. The paper also summarizes commonly used datasets and evaluation metrics reported in the literature and outlines key challenges identified by previous studies including data quality, communication reliability scalability and operational costs. Finally, the review highlights research directions that may contribute to the development of more efficient reliable and sustainable irrigation systems for precision agriculture","author":[{"family":"Zerguine","given":"Nadia"},{"family":"Omar","given":"Aziza"},{"family":"Aliouat","given":"Zibouda"}],"issued":{"date-parts":[[2026]]},"DOI":"10.22399/ijcesen.5450","URL":"https://doi.org/10.22399/ijcesen.5450","source":"crossref"},{"id":"doi:10.1109/sr.2025.3596890","type":"article-journal","title":"Integrating Sensors and Multicriteria Decision Making (MCDM) in Precision Agriculture: A Mini Review","abstract":"As an emerging technology, smart agriculture is drawing increased attention to sensor technology and multicriteria decision-making (MCDM) models. MCDM-based techniques have been employed in various studies to support decision making under sensor-rich conditions, such as crop selection, irrigation, yield prediction, and animal facility management. In this brief review, significant studies involving sensor-based agriculture using MCDM models are discussed. This article also summarizes and identifies the theoretical background of MCDM methods applied in agriculture, as well as common problems in agricultural decision making. It identifies the criteria regularly used in decision making, such as technical efficiency, environmental sustainability, and economic efficiency, based on these works and other relevant literature. This result suggests that MCDM facilitates stakeholders in managing tradeoffs more effectively in uncertain environments and improves decision quality in the precision agriculture field. Recommendations for enhanced real-time integration, a hybrid approach, and consideration of the farmer in the design of decision support systems are also presented in the discussion.","author":[{"family":"David","given":"Dianes"},{"family":"Albahri","given":"OS"},{"family":"Alamoodi","given":"AH"},{"family":"Albahri","given":"AS"},{"family":"Deveci","given":"Muhammet"},{"family":"Sharaf","given":"Iman"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sr.2025.3596890","URL":"https://doi.org/10.1109/sr.2025.3596890","source":"crossref"},{"id":"doi:10.71364/ijfsr.v2i1.8","type":"article-journal","title":"Smart Farming and Precision Agriculture: Leveraging IoT and Data Analytics to Improve Crop Efficiency and Sustainability","abstract":"Smart farming and precision agriculture are modern approaches in the agricultural sector that utilize the Internet of Things (IoT) and data analytics to improve production efficiency and environmental sustainability. This research aims to explore how IoT technology and data analytics are applied in precision agriculture to face global challenges, such as increasing food needs and resource constraints. Qualitative methods are used with a literature study approach or library research, which focuses on the critical analysis of various scientific sources, including journals, reports, and related books. The results show that IoT provides the ability to monitor soil conditions, weather, and crops in real-time through sensors, while data analytics allows for the interpretation of that data for more accurate decision-making. These technologies contribute to more efficient management of resources, such as water and fertilizers, as well as the reduction of environmental impact through precise control of inputs. In addition, the adoption of this technology also has socio-economic implications, such as increasing the productivity of smallholders and supporting agribusiness sustainability. However, challenges such as high initial investment costs and the need for farmer training remain major obstacles. The study concludes that IoT and data analytics have great potential to revolutionize the agricultural sector by creating more efficient, environmentally friendly, and sustainable agricultural practices. Therefore, a policy strategy that supports the adoption of this technology is needed, especially in developing countries.","author":[{"family":"Sumartono","given":"Eddy"},{"family":"Sanjaya","given":"Aditya"},{"family":"Sugiardi","given":"Sigit"},{"family":"Budiasto","given":"Jarot"},{"family":"Ningsih","given":"Yesi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71364/ijfsr.v2i1.8","URL":"https://doi.org/10.71364/ijfsr.v2i1.8","source":"crossref"},{"id":"doi:10.12944/cwe.21.1.3","type":"article-journal","title":"A Comprehensive Review of Sensor Technologies and IoT  Platforms for Precision Agriculture: Indian Context","abstract":"Precision Agriculture (PA) contributes to a paradigm shift from traditional farming towards a data-driven, technology-enabled approach that optimizes resource use and enhances productivity. This review follows a structured narrative review methodology, where literature was collected from databases including Scopus, Web of Science, and Google Scholar using keywords such as “precision agriculture India”, “IoT farming”, and “soil sensors”. Studies were screened based on relevance, recency (post-2015 priority), and applicability to Indian conditions. This review synthesizes the current state of sensor technologies and Internet of Things (IoT) platforms, critically evaluating their applicability within the unique socio-economic and agro-climatic context of Indian agriculture. This paper introduces PA and traces its technological evolution, followed by a detailed analysis of various sensor types—including resistive, capacitive, and advanced spectral sensors—and their specific applications in irrigation and nutrient management. Key findings indicate that capacitive and IoT-enabled sensors offer the best cost–accuracy balance for Indian farms, while adoption barriers remain primarily economic and infrastructural. The review then delves into the architecture of IoT platforms, examining hardware like Arduino and Raspberry Pi, and communication protocols such as Lora WAN and NB-IoT, with a specific focus on smart irrigation systems. A significant portion is dedicated to the implementation challenges in India, including land fragmentation, economic viability, and digital literacy, proposing context-specific solutions. Finally, future directions involving AI, advanced sensing, and policy frameworks have also been proposed in this paper. It also summarizes on developing affordable, scalable, and farmer-centric solutions supported by robust institutional mechanisms with the significant technological potential in India.","author":[{"family":"Patle","given":"Ghanshyam"},{"family":"Ningthoujam","given":"Anita"},{"family":"Yurembam","given":"Ghanashyam"},{"family":"Jhajharia","given":"Deepak"}],"issued":{"date-parts":[[2026]]},"DOI":"10.12944/cwe.21.1.3","URL":"https://doi.org/10.12944/cwe.21.1.3","source":"crossref"},{"id":"doi:10.1007/s11119-025-10231-7","type":"article-journal","title":"Precision mapping and treatment of spring dead spot in bermudagrass using unmanned aerial vehicles and global navigation satellite systems sprayer technology","abstract":"Abstract Spring dead spot is a disease of bermudagrass ( Cynodon dactylon L. Pers) caused by Ophiosphaerella spp ., of fungi which infect the below ground structures of plants, causing damage to the turf canopy. Previous research suggests that precision management strategies based on manually identified disease within unmanned aerial vehicle (UAV) imagery using GIS software and global navigation satellite systems (GNSS)-equipped sprayers can reduce the fungicide required for spring dead spot management. However, this methodology is time consuming and impractical for golf course superintendents. This paper introduces a novel approach to spring dead spot identification utilizing a custom Python script, the Simple Ophiosphaerella Damage Detector (SODD), to identify and record locations of spring dead spot from UAV imagery using basic feature extraction techniques. Initial tests comparing the outputs from SODD to spring dead spot manually identified by researchers on four fairways, comparisons of K-means cluster maps showed similarities ranging between 71 and 88% although incidence counts were inconsistent. Precision treatment methods based on SODD were evaluated across 16 golf course fairways at three locations in Virginia organized as a randomized complete-block design with four replications and four treatment methods; spot and zonal treatments based on SODD identified incidence and density, respectively, compared against full-coverage and non-treated controls. Applications were made with a Toro Multipro5800 with GeoLink GNSS-equipped sprayer in Fall of 2021. Spot and zonal treatment strategies showed similar control to full-coverage applications ( p ≤0.001) while reducing the percentage of the fairways treated by 48% and 52%, respectively ( p ≤0.001). These results highlight the capabilities for SODD as a tool for disease map generation.","author":[{"family":"Henderson","given":"Caleb"},{"family":"Haak","given":"David"},{"family":"Mehl","given":"Hillary"},{"family":"Shafian","given":"Sanaz"},{"family":"Mccall","given":"David"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10231-7","URL":"https://doi.org/10.1007/s11119-025-10231-7","source":"crossref"},{"id":"doi:10.3390/agriculture15151627","type":"article-journal","title":"Dynamic Monitoring and Precision Fertilization Decision System for Agricultural Soil Nutrients Using UAV Remote Sensing and GIS","abstract":"We propose a dynamic monitoring and precision fertilization decision system for agricultural soil nutrients, integrating UAV remote sensing and GIS technologies to address the limitations of traditional soil nutrient assessment methods. The proposed method combines multi-source data fusion, including hyperspectral and multispectral UAV imagery with ground sensor data, to achieve high-resolution spatial and spectral analysis of soil nutrients. Real-time data processing algorithms enable rapid updates of soil nutrient status, while a time-series dynamic model captures seasonal variations and crop growth stage influences, improving prediction accuracy (RMSE reductions of 43–70% for nitrogen, phosphorus, and potassium compared to conventional laboratory-based methods and satellite NDVI approaches). The experimental validation compared the proposed system against two conventional approaches: (1) laboratory soil testing with standardized fertilization recommendations and (2) satellite NDVI-based fertilization. Field trials across three distinct agroecological zones demonstrated that the proposed system reduced fertilizer inputs by 18–27% while increasing crop yields by 4–11%, outperforming both conventional methods. Furthermore, an intelligent fertilization decision model generates tailored fertilization plans by analyzing real-time soil conditions, crop demands, and climate factors, with continuous learning enhancing its precision over time. The system also incorporates GIS-based visualization tools, providing intuitive spatial representations of nutrient distributions and interactive functionalities for detailed insights. Our approach significantly advances precision agriculture by automating the entire workflow from data collection to decision-making, reducing resource waste and optimizing crop yields. The integration of UAV remote sensing, dynamic modeling, and machine learning distinguishes this work from conventional static systems, offering a scalable and adaptive framework for sustainable farming practices.","author":[{"family":"Chen","given":"Xiaolong"},{"family":"Zhang","given":"Hongfeng"},{"family":"Wong","given":"Cora"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15151627","URL":"https://doi.org/10.3390/agriculture15151627","source":"crossref"},{"id":"doi:10.1163/9789004725232_138","type":"article-journal","title":"Crop robots can defy economies of size and make small-scale agriculture economic – or can they?","abstract":"By comparing experience from two autonomously operated strip cropping field trials, obstacles to a labour-efficient use of crop robots in small-scale biodiverse farming systems are described. Despite different approaches, the conclusions from the two trials agree that logistics and the natural environment are main causes of time-inefficiencies. The current state of technology thus does not yet result in autonomous equipment reliably saving labour time relative to conventional equipment in small-scale, diversified systems. Consequently, larger fields are more economical for robot operations so that crop robots, like tractors, are subject to economies of field size.","author":[{"family":"Spykman","given":"O"},{"family":"Gandorfer","given":"M"},{"family":"Lowenberg-Deboer","given":"J"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1163/9789004725232_138","URL":"https://doi.org/10.1163/9789004725232_138","source":"crossref"},{"id":"doi:10.3390/agriculture15242555","type":"article-journal","title":"Precision Farming: Exploring the Challenges and Opportunities for Smallholder Farmers in Chile","abstract":"The objective of this study is to analyse the challenges and opportunities that Precision Farming (PF) offers for agriculture in Chile, highlighting the possibilities it offers for solving agricultural problems as well as the challenges that hinder its application by small- and medium-sized farmers. A qualitative content analysis was conducted on technical government publications and academic publications focused on precision agriculture, which highlighted the elements that hinder the implementation of PF in smaller agricultural systems, i.e., small farmers. The results show that among the main problems that PF can help solve are spring frosts, low product calibre, fruit rot, low sugar content in fruit, and water stress, among others. The solutions that PA could offer, as outlined in the review, are varied and include frost forecasting, crop monitoring, application of inputs, and selection of more drought-tolerant crops, to name a few. On the other hand, another relevant finding is the fact that small farmers face structural difficulties in accessing PF technologies, due to their high cost (technology transfer) but also to the lack of support from state institutions.","author":[{"family":"Orellana","given":"Eva"},{"family":"Gonzalez","given":"Tirza"},{"family":"Álvarez","given":"Alejandro"},{"family":"Fernández-Campusano","given":"Christian"},{"family":"Muñoz","given":"Miguel"},{"family":"Carrasco","given":"Raúl"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15242555","URL":"https://doi.org/10.3390/agriculture15242555","source":"crossref"},{"id":"doi:10.4018/979-8-3373-5283-1.ch006","type":"article-journal","title":"Robotics and Automation in Modern Agriculture","abstract":"The integration of robotics and automation in modern agriculture is transforming the landscape of food production, significantly enhancing efficiency, precision, and sustainability. This chapter explores the revolutionary impact of robotic technologies in harvesting and processing, focusing on the advancements in sensor technology, machine learning, and autonomous systems. Key innovations such as robotic harvesters, automated sorting and processing lines, and precision agriculture tools are examined for their ability to optimize yield, reduce labor dependency, and minimize environmental impact. Furthermore, the chapter discusses the challenges of scalability, cost, and technology adoption, along with emerging trends like swarm robotics and AI-driven decision-making in agriculture.","author":[{"family":"Pandey","given":"Shreya"},{"family":"Kaushik","given":"Kashish"},{"family":"Tewatia","given":"Anjali"},{"family":"Quraishi","given":"Suhail"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-5283-1.ch006","URL":"https://doi.org/10.4018/979-8-3373-5283-1.ch006","source":"crossref"},{"id":"doi:10.1007/s11119-026-10409-7","type":"article-journal","title":"The economic viability of spot-spraying for pesticides: the case of Northwest Germany","abstract":"Abstract Purpose The reliance on pesticides for crop protection poses significant challenges, including biodiversity loss and environmental pollution. Despite the potential of precision farming technologies such as spot-sprayers for reducing pesticide applications, their adoption remains limited. Previous literature on the economic viability of precision spraying is sparse and did not account for relations between technology availability, prices, land use and adoption decisions. Methods We here analyze and compare the economic viability of different types of smart spot-sprayers for site-specific pesticide applications using a mixed-integer linear programming bio-economic farm model. We apply the model to typical cereal and sugar beet farms in North-Western Germany, which is one of the most productive agricultural regions in Europe. In our analysis, we account for key economic and performance parameters of precision sprayers and check the sensitivity of results regarding assumptions on technology and farm characteristics. Results The findings indicate that real-time spot-spraying of herbicides is economically viable for sugar beet farms exceeding 60-172 ha and cereal farms managing 300-400 ha. The large range of results reflects an important challenge for the adoption of spot sprayers. It highlights the sensitivity of economic viability to changes in technology type and performance and pesticide prices, which are often uncertain for farmers in advance. Broadening the use of the spot sprayer to multiple pesticide types and combining smaller and more precise spot-sprayers with broadcast sprayers improves the economic viability. Conclusions Overall, our results underscore the potential of smart spot-sprayers to contribute to sustainable agricultural practices by reducing pesticide use while maintaining profitability for farmers. Based on our results, we discuss how the adoption of these technologies could be facilitated to achieve environmental goals and improve farm economics.","author":[{"family":"Schots","given":"Jens"},{"family":"Kuhn","given":"Till"},{"family":"Möhring","given":"Niklas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10409-7","URL":"https://doi.org/10.1007/s11119-026-10409-7","source":"crossref"},{"id":"doi:10.71443/9789349552364-03","type":"article-journal","title":"IoT and Edge AI Integration for Real Time Monitoring in Precision Farming Environments","abstract":"The integration of Internet of Things (IoT) and Edge Artificial Intelligence (AI) has revolutionized precision agriculture by providing real-time, data-driven insights for optimizing farming practices. As IoT devices proliferate in agricultural environments, the need for robust and scalable systems that can seamlessly handle vast amounts of data becomes critical. This chapter explores the challenges and opportunities presented by large-scale IoT deployments in agriculture, focusing on the role of Edge AI in ensuring real-time processing and decision-making. Key issues such as device heterogeneity, scalability, interoperability, and data security are examined, alongside strategies for effective system integration and validation. The chapter delves into case studies that illustrate the successful deployment of IoT and Edge AI technologies in diverse agricultural settings, highlighting lessons learned and best practices. Furthermore, it outlines future directions for enhancing system efficiency, ensuring secure data transmission, and fostering widespread adoption of these technologies in precision farming. By addressing these challenges, the chapter provides a comprehensive framework for developing and deploying scalable IoT and Edge AI systems that can drive sustainable agricultural practices worldwide.","author":[{"family":"Ranganathan","given":"S"},{"family":"Gangadevi","given":"K"},{"family":"Salam","given":"Niaz"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-03","URL":"https://doi.org/10.71443/9789349552364-03","source":"crossref"},{"id":"doi:10.3390/agronomy15112648","type":"article-journal","title":"Diffusion Probabilistic Models for NIR Spectral Data Augmentation in Precision Agriculture","abstract":"Near-infrared (NIR) spectroscopy is a rapid, non-destructive tool widely used in agriculture, but limited labeled spectra often constrain model robustness. To address this, we propose using denoising diffusion probabilistic models (DDPMs) for NIR data augmentation. Leveraging the SpectraFood leek dataset, a conditional MLP-DDPM was trained to generate realistic synthetic spectra guided by dry matter content. Incorporating 1000 generated spectra into the training set improved the predictive performance of PLSR, RF, and XGBoost models, demonstrating enhanced generalization and robustness. Compared with WGAN, DDPM offered higher stability and fidelity, effectively expanding the calibration space without introducing unrealistic patterns. Future work will explore conditional and hybrid diffusion frameworks, integrating environmental and physiological covariates, and cross-domain spectral transfer, extending the applicability of DDPMs for diverse crops and precision agriculture scenarios.","author":[{"family":"Hu","given":"Changxu"},{"family":"Wang","given":"Huihui"},{"family":"Hou","given":"Pengzhi"},{"family":"Nan","given":"Jiaxuan"},{"family":"Che","given":"Xiaoxue"},{"family":"Wang","given":"Yaqi"},{"family":"Bai","given":"Yangfan"},{"family":"Chen","given":"Bingjun"},{"family":"Miao","given":"Yuyuan"},{"family":"Zhang","given":"Wuping"},{"family":"Li","given":"Fuzhong"},{"family":"Han","given":"Jiwan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agronomy15112648","URL":"https://doi.org/10.3390/agronomy15112648","source":"crossref"},{"id":"doi:10.19103/as.2025.152.09","type":"article-journal","title":"Decision support systems in precision agriculture and conservation","abstract":"Many public and private decision support systems (DSS) are currently developed. The DSS are defined as computer-based platforms to collect, process, and analyze multi-facet data and generate timely and accurate decisions. Modern DSS includes crop, soil, weather observations, real time machine, sensor, economic and market data, advanced analytics, cloud computing and user-friendly recommendations. Two case studies of public DSS are presented. One is a web-based tool to prescribe variable soybean seeding rates using historical yield maps, yield classification, cost of seed and price of grain. The other web-based platform summarizes yield genotypes by geographies and irrigation management and helps growers to choose the right crop genetics for irrigated or rainfed area. Key barriers to the adoption of modern DSS by farmers and stakeholders are discussed. Future DSS will rely on larger and more diverse datasets, more robust machine learning and process-based models, advanced cloud computing, AI and mobile accessible devices.","author":[{"family":"Kyveryga","given":"Peter"},{"family":"Cano","given":"Priscila"},{"family":"Cisdeli","given":"Pedro"},{"family":"Hernández","given":"Carlos"},{"family":"Santiago","given":"Gustavo"},{"family":"Ciampitti","given":"Ignacio"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2025.152.09","URL":"https://doi.org/10.19103/as.2025.152.09","source":"crossref"},{"id":"doi:10.1080/10826068.2026.2693878","type":"article-journal","title":"Precision fermentation and recombinant proteins as enabling technologies for scalable cellular agriculture.","abstract":"Cellular agriculture has emerged as a promising strategy for producing animal-derived food components through controlled biological processes while reducing the environmental and ethical burdens associated with conventional livestock production. Among its enabling technologies, precision fermentation and cultivated-cell systems offer complementary advantages but continue to face challenges related to production costs, scalability, and functional performance. Increasingly, hybrid cellular agriculture approaches combining precision-fermented proteins, cultivated cells, and plant-derived matrices are being explored to overcome these limitations and accelerate commercialization. This review examines recombinant proteins as critical enabling components within these integrated systems. Advances in microbial expression platforms, including prokaryotic hosts such as Escherichia coli and Bacillus subtilis and eukaryotic hosts such as Saccharomyces cerevisiae and Komagataella phaffii , are critically evaluated regarding protein yield, product quality, regulatory suitability, downstream processing, and techno-economic feasibility. Industrial-scale fermentation capacities up to 80,000 L demonstrate the growing potential for large-scale recombinant protein production. Applications of recombinant proteins in edible scaffolds, serum-free culture media, extracellular matrix alternatives, and functional food ingredients are discussed alongside their associated technical and regulatory challenges. Ultimately, recombinant proteins are identified as integrative elements bridging acellular and cell-based production systems, supporting the development of scalable, economically viable, and sustainable cellular agriculture.","author":[{"family":"Jadhav","given":"Neha"},{"family":"Magdum","given":"Aditya"},{"family":"Shinde","given":"Kapil"},{"family":"Nimbalkar","given":"Mansingraj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/10826068.2026.2693878","URL":"https://doi.org/10.1080/10826068.2026.2693878","source":"europepmc"},{"id":"doi:10.32634/0869-8155-2026-405-04-137-143","type":"article-journal","title":"Functional modeling and parametric evaluation of components of an IoT data collection system for precision agriculture","abstract":"The article considers the development of a functional model of an automated IoT monitoring data acquisition and processing system for precision agriculture tasks using the IDEF0 structural analysis methodology. The modeling object is a hardware-software complex including field IoT sensors, data transmission channels, and server processing infrastructure. A context diagram at level A-0 was constructed and decomposition to level A0 was performed, including four functional blocks: primary data acquisition from sensors, preprocessing and aggregation at the edge gateway, wireless data transmission, and server processing with control action generation. A comparative analysis of technical characteristics of three types of IoT sensors (soil moisture sensors, weather stations, UAV multispectral cameras) was conducted by accuracy, polling frequency, and power consumption parameters. Performance evaluation of three data transmission protocols (LoRa, NB-IoT, Wi-Fi) was performed by throughput, range, and latency criteria. Experimental measurements were carried out at 12 farms in Krasnodar Krai during 2019–2024. Results showed that the LoRa protocol provides the optimal ratio of transmission range (up to 11.2 km) and power consumption (42 mA in transmission mode) for field conditions. The average data processing cycle time from sensor to control command generation was 8.3 s. The developed functional model formalizes information flows and control actions in the IoT monitoring system, providing a basis for designing automated systems in agroengineering.","author":[{"family":"Oskin","given":"SP"},{"family":"Kuznetsov","given":"AV"},{"family":"Koneva","given":"NE"}],"issued":{"date-parts":[[2026]]},"DOI":"10.32634/0869-8155-2026-405-04-137-143","URL":"https://doi.org/10.32634/0869-8155-2026-405-04-137-143","source":"crossref"},{"id":"doi:10.1201/9781003536932-3","type":"article-journal","title":"IoT Sensors and Their Applications in Precision Agriculture","abstract":"The integration of Internet of Things (IoT) sensors in precision agriculture has revolutionized modern farming practices. These sensors gather data from diverse environmental and crop- related parameters like soil moisture, temperature, humidity, nutrient levels, crop health indicators, etc., and transmit it wirelessly to centralized platforms. This helps in real-time monitoring and data-driven decision-making in precision agriculture. IoT-based moisture sensors measure soil moisture at multiple depths to fine-tune irrigation schedules and minimize water consumption in precision irrigation systems. Additionally, IoT-enabled weather stations offer precise weather forecasts and monitor microclimatic conditions, enabling farmers to make informed decisions. Crop health monitoring is another critical application of IoT sensors in precision agriculture. Drones equipped with multispectral cameras facilitate in early detection of pest infestations, nutrient deficiencies, and diseases. Coupled with machine learning algorithms, these images yield actionable insights for optimizing crop management practices. Overall, IoT sensors contribute significantly to enhancing productivity, sustainability, and profitability in agriculture. However, several challenges such as data security, interoperability, and scalability must be addressed to fully harness the potential of IoT-enabled precision agriculture systems. This chapter aims to explore potential sensor applications, describe IoT integration layers, discuss prevailing sensing approaches, address common implementation challenges, and explore future prospects in agriculture.","author":[{"family":"Karmakar","given":"Saikat"},{"family":"Roy","given":"Pooja"},{"family":"Mandal","given":"Subrata"},{"family":"Das","given":"Susanta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003536932-3","URL":"https://doi.org/10.1201/9781003536932-3","source":"crossref"},{"id":"doi:10.1016/j.precisioneng.2026.06.004","type":"article-journal","title":"Generic vibration criteria for hand-held precision instruments","abstract":"This paper presents a measurement-based framework for deriving generic hand-arm vibration criteria (HAVC) for the dynamic evaluation, modeling, and simulation of hand-held precision devices. An inertial measurement system captures translational and rotational vibrations in all six degrees of freedom across representative postures, instrument masses, and operators. The dataset is analyzed using unified spatial referencing, power spectral densities, statistical descriptors, and cross-spectral relationships to establish population-level vibration characteristics. The measurements indicate that operator-induced vibration is dominated by low-frequency physiological tremor, shows systematic dependencies on posture and mass, and exhibits minimal cross-axis coupling. Parametric spectral envelopes are fitted to the median spectra and expressed as normalized filters, enabling the synthesis of realistic vibration signals from appropriately scaled white noise. This approach provides simulation-ready disturbance inputs for control design, structural sensitivity analysis, and optomechatronic performance assessment. The proposed HAVC extend the vibration criterion concept from environmental excitation to human-instrument interaction, providing quantitative reference envelopes for the predictive design of hand-held precision systems.","author":[{"family":"Wiesböck","given":"Johannes"},{"family":"Schitter","given":"Georg"},{"family":"Csencsics","given":"Ernst"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.precisioneng.2026.06.004","URL":"https://doi.org/10.1016/j.precisioneng.2026.06.004","source":"crossref"},{"id":"doi:10.1016/j.prmedi.2026.100095","type":"article-journal","title":"Antihyperlipidemic and thrombolytic potential of medicinal plants: Mechanistic insights and precision medicine perspectives","abstract":"Background Hyperlipidemia and thrombosis are major contributors to cardiovascular morbidity and mortality worldwide. Although synthetic antihyperlipidemic and thrombolytic agents are clinically effective, their long-term use is limited by adverse effects and patient intolerance. Medicinal plants offer a promising alternative due to their multitarget pharmacological actions and favorable safety profiles. Objective This review critically evaluates medicinal plants exhibiting antihyperlipidemic and thrombolytic activities, with emphasis on bioactive phytoconstituents, mechanisms of action, and their relevance to precision medicine. Methods A comprehensive literature survey was conducted using databases including PubMed, Scopus, and Google Scholar, focusing on experimental and clinical evidence supporting lipid-lowering and clot-dissolving effects of herbal drugs. Results Multiple plants such as Commiphora mukul , Hibiscus species, Allium sativum , Ocimum sanctum , and Zingiber officinale demonstrate significant antihyperlipidemic and thrombolytic activity through mechanisms including inhibition of cholesterol synthesis, antioxidant effects, platelet aggregation inhibition, and fibrinolysis. Phytochemicals such as flavonoids, polyphenols, saponins, and organosulfur compounds play key roles. Conclusion Medicinal plants represent viable candidates for adjunct or alternative therapy in cardiovascular disorders. Integration of phytotherapy with precision medicine approaches may improve therapeutic outcomes while minimizing adverse effects. However, standardized formulations, mechanistic validation, and controlled clinical trials are essential.","author":[{"family":"Kingre","given":"AG"},{"family":"Ghube","given":"DD"},{"family":"Tathe","given":"PR"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.prmedi.2026.100095","URL":"https://doi.org/10.1016/j.prmedi.2026.100095","source":"crossref"},{"id":"doi:10.5772/intechopen.1015435","type":"article-journal","title":"Integrating Precision Agriculture and Climate-Smart Practices: Data-Driven Pathways to Sustainable and Resilient Food Systems","abstract":"This chapter examines how data-driven technologies in Precision Agriculture (PA) can enhance the goals of Climate-Smart Agriculture (CSA) to achieve sustainable, resilient food systems. It argues that the integration of digital innovation, such as IoT-enabled sensors, drones, satellite imaging, and machine learning, creates new pathways for emission reduction, resource efficiency, and climate adaptation. Through empirical case studies across diverse agroecological regions, the chapter highlights how precision tools support site-specific management, data analytics enables precision in input use, predictive crop management, and risk mitigation under changing climatic conditions. The convergence of Precision Agriculture and Climate-Smart Agriculture represents a shift from productivity-focused farming to resilience-oriented, data-informed agriculture. For instance, Internet of Things (IoT) systems enable real-time monitoring of soil and crop conditions, while remote sensing and Unmanned Aerial Vehicle (UAV) technologies enhance spatial analysis of farm variability. In the same vein, machine learning transforms agricultural data into actionable insights for yield prediction, pest control, and input optimization. These technologies improve nitrogen and water use efficiency, reduce greenhouse gas emissions, and enhance adaptive capacity. However, the adoption of PA-CSA systems is constrained by high costs, limited digital infrastructure, and weak institutional and technical capacity, particularly among smallholder farmers. The discussion situates PA within global sustainability and policy frameworks, emphasising the importance of data governance, digital equity, and institutional support. Finally, it proposes a model of data responsible agriculture where precision technologies not only optimise productivity but also align with climate goals, resilience building, and social inclusion, making agriculture both smarter and more sustainable.","author":[{"family":"Ojo","given":"Ibukun"},{"family":"Bamigboye","given":"Oluwaseun"},{"family":"Edewor","given":"Sarah"},{"family":"Kolawole","given":"Ayorinde"},{"family":"Chike","given":"Ikechukwu"},{"family":"Oladeji","given":"Damilola"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5772/intechopen.1015435","URL":"https://doi.org/10.5772/intechopen.1015435","source":"crossref"},{"id":"doi:10.2139/ssrn.6249306","type":"manuscript","title":"Toward Precision Agriculture: Rapid and Accurate Detection of Citrus Huanglongbing via FT-IR and a Spectral Attention–Guided CNN","abstract":"Early, rapid, and accurate detection methods are critical for the prevention and control of citrus Huanglongbing (HLB). This study proposes an intelligent rapid detection framework for HLB that integrates Fourier Transform Infrared Spectroscopy (FT-IR) with a deep neural network model combining band fusion priors and attention mechanisms. To enhance the feature learning capability of FT-IR, this study designed and developed a CNN-LSTM model (1DConvLSTM-SA) incorporating dual enhancements via band priors and attention mechanisms. The BandMask (BM) module leverages input band prior information to weight and amplify the absorbance at corresponding wavelengths in FT-IR, thereby guiding the model to focus on sensitive bands that are highly correlated with HLB infection characteristics. The self-attention (SA) module further refines deep spectral features. 1DConvLSTM-SA was trained on FT-IR data and achieved outstanding performance, with an accuracy of 94.1% on the independent Tangelo test set and 93.4% on the independent test sets of the other nine citrus varieties. Furthermore, compared with traditional quantitative polymerase chain reaction (qPCR) methods, this approach reduces costs by 67.4% and testing time by 94.8%. It provides an efficient, cost-effective and promising technical solution for rapid HLB diagnosis, underscoring the broad prospects of AI-driven FT-IR spectral analysis in agricultural disease detection.","author":[{"family":"Li","given":"Minyu"},{"family":"Rao","given":"Wenhua"},{"family":"Gao","given":"Shang"},{"family":"Shen","given":"Chao"},{"family":"Lin","given":"Tao"},{"family":"Lou","given":"Binghai"},{"family":"Fan","given":"Guocheng"},{"family":"Jinfeng","given":"Hu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.6249306","URL":"https://doi.org/10.2139/ssrn.6249306","source":"crossref"},{"id":"doi:10.1007/s42452-026-09248-y","type":"article-journal","title":"Leveraging nonlinear deep learning models for intelligent crop recommendation in precision agriculture","abstract":"Abstract For countries with developing economies, agriculture, particularly the farming and livestock business, plays an essential role in their economic growth. Agriculture is the basis of food security and supplies the farming labor and means of subsistence for the population of the city and rural areas. Modern technologies in agriculture ensure timely, informed, and precise decisions concerning agriculture and related sectors along with the seasonal and climatic variations. This paper suggests a method for selecting the right crop that makes use of a number of deep learning-based crop recommendation systems and allows crop selection for a particular area based on soil and climate. The method incorporates various deep learning techniques, including ANNs, CNNs, RNNs, LSTMs, and CRNNs, in crop categorisation. Individual classifier findings are then integrated with an ensemble classifier to create more accurate crop recommendations by leveraging the complicated nonlinear interactions between diverse agro-environmental parameters. The experimental results reveal that the proposed ensemble model outperforms individual deep learning models, with an overall accuracy of 96.95%. The findings indicate that deep learning-based crop recommendation systems can assist farmers optimise crop selection, support crop selection and improve data-driven agricultural decision-making under varying soil and climatic conditions.","author":[{"family":"Tripathy","given":"Swagatika"},{"family":"Rath","given":"Premansu"},{"family":"Adhikary","given":"Dibya"},{"family":"Woldesenbet","given":"Muluken"},{"family":"Paikaray","given":"Bijay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s42452-026-09248-y","URL":"https://doi.org/10.1007/s42452-026-09248-y","source":"crossref"},{"id":"doi:10.35760/jpp.2026.v10i1.271","type":"article-journal","title":"PENGARUH PEMBERIAN KOMPOS TKKS DAN PGPR TERHADAP PERTUMBUHAN DAN HASIL MELON PADA TANAH PMK","abstract":"Tujuan dari penelitian ini adalah untuk mempelajari bagaimana pemberian kompos tandan kelapa sawit kosong (TKKS) Plant Growth Promoting Rhizobacteria (PGPR) berdampak pada pertumbuhan dan produksi tanaman melon pada tanah Podsolik Merah Kuning (PMK). Kegiatan penelitian dilaksanakan di Kecamatan Sintang, Kabupaten Sintang, Kalimantan Barat, pada bulan September sampai Desember 2025. Penelitian disusun menggunakan Rancangan Acak Lengkap (RAL) faktorial dengan dua faktor, yaitu dosis kompos TKKS (10, 20, dan 30 ton ha⁻¹) dan jenis PGPR (tanpa PGPR, PGPR kemasan, serta PGPR dari akar bambu), dengan masing-masing perlakuan diulang tiga kali. Variabel yang diamati meliputi jumlah daun, bobot buah, diameter buah, ketebalan daging buah, tingkat kemanisan buah, bobot kering tanaman, serta serapan hara fosfor (P). Hasil penelitian menunjukkan adanya interaksi antara kompos TKKS dan PGPR terhadap serapan hara P. Pemberian kompos TKKS berpengaruh nyata terhadap jumlah daun, bobot buah, diameter buah, ketebalan daging buah, dan bobot kering tanaman, dengan dosis optimum 30 ton ha⁻¹. Sementara itu, perlakuan PGPR memberikan pengaruh nyata terhadap pertumbuhan vegetatif, beberapa komponen hasil, serta serapan hara fosfor (P), terutama pada PGPR akar bambu. Secara keseluruhan, aplikasi kompos TKKS dan PGPR secara terpisah mampu meningkatkan pertumbuhan dan hasil tanaman melon pada tanah PMK.Top of Form","author":[{"family":"Sandriani","given":"Sesilia"},{"family":"Rianto","given":"Fadjar"},{"family":"Basuni"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35760/jpp.2026.v10i1.271","URL":"https://doi.org/10.35760/jpp.2026.v10i1.271","source":"crossref"},{"id":"doi:10.1201/9781003545781-3","type":"article-journal","title":"Advances in Artificial Intelligence for Plant Systems Biology","abstract":"Advances in artificial intelligence (AI) have significantly transformed plant systems biology, providing novel tools to unravel complex biological processes and address pressing challenges in agriculture and ecology. This chapter highlights the pivotal role of AI in enhancing our understanding of plant genomics, gene networks, and regulatory systems. Applications such as AI-driven genome analysis, metabolic pathway modeling, and transcriptomics are elucidated to demonstrate their impact on decoding intricate biological interactions. Furthermore, the use of AI in high-throughput phenotyping and trait prediction has revolutionized the analysis of plant–environment interactions. By focusing on crop improvement, precision agriculture, and ecosystem studies, this chapter underscores the role of AI in sustainable food production and biodiversity conservation. While exploring the transformative potential of AI, the chapter also addresses inherent challenges, such as data limitations, model transparency, and ethical considerations. Concluding with future directions, it envisions the integration of advanced AI methodologies to further empower plant systems biology, paving the way for a resilient and sustainable agricultural landscape.","author":[{"family":"Sureshkumar","given":"Tharani"},{"family":"Govindarajan","given":"Ramkumar"},{"family":"Jaison","given":"Sarah"},{"family":"Kutty","given":"Sunitha"},{"family":"Samuel","given":"Siva"},{"family":"Devi","given":"Balasundaram"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-3","URL":"https://doi.org/10.1201/9781003545781-3","source":"crossref"},{"id":"doi:10.1007/s11119-025-10263-z","type":"article-journal","title":"Quantity vs. quality: does wheat grain yield or protein content have a greater opportunity for precision management?","abstract":"Abstract Purpose Fields characterised by large within-field variation stand to potentially gain from the differential application of inputs via Site-Specific Crop Management (SSCM). Maps generated from wheat grain yield and protein sensors are revealing considerable spatiotemporal variability within and between fields, farms, and seasons. Yet one of the biggest barriers to the successful adoption of SSCM is an assessment of the magnitude and spatial distribution of variability, and whether this is sufficient to warrant a change from uniform management. This study aimed to compare opportunities for SSCM between wheat grain yield and grain protein content (GPC) using the Opportunity Index (OI), a measure of the magnitude and spatial structure of within-field variability. Methods This research used a database of 86 paired wheat grain yield and protein maps from 70 fields, collected over four seasons (2020–2023) across two farms in northern New South Wales (NSW) and four farms in Western Australia (WA), resulting in 86 field-years of data. The OI was calculated for every yield and protein map, and maps were then classed as having relatively low, medium, or high opportunities for SSCM. To assess which had a greater opportunity within each field, pairwise differences between the OI for yield and GPC were also calculated. Results Overall, results showed that there was a greater opportunity for SSCM for wheat grain yield than for GPC. While both yield and GPC had a similar spatial structure, yield had a greater magnitude of variation within fields. The OI was greater in NSW than in WA, likely due to variable-rate fertiliser applications already being employed in WA, but not in NSW. Conclusion In calculating the OI across a farm or region, the OI ranks fields as to their suitability for SSCM and provides growers with a simple decision-making tool to determine where SSCM practices may be best directed for the stepwise adoption of precision agriculture. However, it does not provide recommendations for management options, and further investigations by the grower/advisor are needed to make SSCM decisions. Future work should include an economic analysis of the opportunities for SSCM with respect to the premium and discount system applied for grain quality in Australia, and more work is needed to better understand the drivers of the differences in the OI between yield and GPC within and between fields, farms, and seasons.","author":[{"family":"Tilse","given":"Mikaela"},{"family":"Bishop","given":"Thomas"},{"family":"Filippi","given":"Patrick"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s11119-025-10263-z","URL":"https://doi.org/10.1007/s11119-025-10263-z","source":"crossref"},{"id":"doi:10.15662/ijeetr.2026.0802223","type":"article-journal","title":"AI-Based Smart Irrigation System for Precision Agriculture using Soil Moisture Prediction and Weather Data","abstract":"Efficient water management is one of the most critical challenges in modern agriculture. Traditional irrigation methods often lead to excessive water consumption and reduced crop productivity due to the lack of real-time monitoring and predictive decisionmaking. This paper proposes a multimodal artificial intelligence framework for precision agriculture that integrates soil moisture prediction, weather forecasting, and intelligent irrigation scheduling. The proposed system utilizes Long Short-Term Memory (LSTM) networks to predict soil moisture levels based on environmental data and historical measurements. A Random Forest model is employed to determine optimal irrigation decisions by combining predicted soil moisture values with weather parameters such as temperature, humidity, and rainfall probability. The framework aims to support data-driven irrigation management that improves water-use efficiency and crop yield. Experimental results demonstrate that the proposed approach provides accurate predictions and reliable irrigation recommendations, making it suitable for smart farming applications","author":[{"family":"Devakirubai","given":"N"},{"family":"Pushpa","given":"N"},{"family":"Jeevitha","given":"J"},{"family":"Mahalakshmi","given":"J"}],"issued":{"date-parts":[[2026]]},"DOI":"10.15662/ijeetr.2026.0802223","URL":"https://doi.org/10.15662/ijeetr.2026.0802223","source":"crossref"},{"id":"doi:10.3389/fagro.2026.1787088","type":"article-journal","title":"Editorial: Innovative technologies and applications of UAV in precision agriculture to mitigate climate change","abstract":"The accelerating impacts of climate change continue to challenge global agriculture, increasing the need for adaptive and sustainable technological solutions. In this context, Unmanned Aerial Vehicles (UAVs) have evolved from experimental tools to key components of precision agriculture, offering advanced capabilities for monitoring, diagnosis, and targeted intervention. This Research Topic explores how UAVs, combined with remote sensing, AI, and operational strategies, can advance climate-smart agriculture. The topic focuses on innovative technologies and UAV applications in precision agriculture for mitigating climate change, highlighting recent advancements.The four contributions in this collection illustrate UAVs' potential to improve resource-use efficiency, enhance plant protection, enable early detection of biotic stress, and support scalable, data-driven decision-making. Together, these studies underline both the versatility of UAV technologies and the need for continued innovation to address environmental variability, operational challenges, and integration with complementary sensing platforms.Regarding UAV for spraying, the: operational variability and deposition efficiency,","author":[{"family":"Martínez-Peña","given":"Raquel"},{"family":"Pardo","given":"Miguel"},{"family":"Poblete-Echeverría","given":"Carlos"},{"family":"Vélez","given":"Sergio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fagro.2026.1787088","URL":"https://doi.org/10.3389/fagro.2026.1787088","source":"crossref"},{"id":"doi:10.65069/smart2120265","type":"article-journal","title":"Selection of Robots in Precision Agriculture Using Multi-Criteria Decision-Making Methods","abstract":"This article is about choosing the best robot for controlling weeds. It uses a special method that combines fuzzy CRITIC and fuzzy CoCoSO to make decisions based on many different factors. The researchers examined six different robots and considered ten criteria, including performance, cost, and environmental impact. They asked experts for their opinions, using a special scale that accounts for uncertainty and different perspectives. The fuzzy CRITIC method was used to determine the importance of each criterion, and then the fuzzy CoCoSO method was applied to rank the robots from best to worst. By considering all these factors, the study aims to identify the optimal robot for weed control. The decision-making process is complex, but this method helps make it clearer and more effective. The results indicate that the autonomous AI-powered robot with laser weed removal represents the best solution due to its superior performance in terms of precision, autonomy, and environmental acceptability. Validation of the results was conducted through comparison with other fuzzy multi-criteria methods (TOPSIS, MARCOS, ARAS, and SAW), revealing a high degree of consistency among the rankings. Additionally, sensitivity analysis based on variations in the weights of the most influential criteria confirmed the robustness of the model, with only limited changes observed in the middle positions of the ranking. The findings are helpful for determining how to choose the right agricultural robots and provide important guidance for decision-makers regarding the use of technology and the advancement of sustainable agriculture. This can support better choices in the digitalization and transformation of farming practices.","author":[{"family":"Nedeljkovic","given":"Miroslav"},{"family":"Đokić","given":"Milorad"},{"family":"Ćosić","given":"Milivoje"}],"issued":{"date-parts":[[2026]]},"DOI":"10.65069/smart2120265","URL":"https://doi.org/10.65069/smart2120265","source":"crossref"},{"id":"doi:10.46481/asr.2026.5.3.590","type":"article-journal","title":"Crop recommendation in precision agriculture: a systematic literature review of methods, trends, and challenges","abstract":"Crop recommendation methods have become an essential component of modern agriculture, helping farmers identify the most suitable crops based on soil, climatic, and environmental conditions. As key applications of precision agriculture, these methods increasingly employ artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), to improve crop prediction, recommendations, productivity, and farming decision-making. This study presents a systematic literature review (SLR) of ML and DL techniques applied to crop recommendation and related agricultural applications. From 183 identified studies, 129 articles published between 2020 and 2026 were carefully selected through a structured screening process for comprehensive analysis. Relevant studies were retrieved from major academic literature databases and publishing platforms, including ScienceDirect, Scopus, SpringerLink, MDPI, Nature, Frontiers, IEEE, Wiley, and Google Scholar. The review used the PRISMA protocol and showed that ensemble learning-based approaches, particularly Random Forest and Extreme Gradient Boosting (XGBoost), are powerful for predictive performance on various agricultural datasets. Traditional ML approaches such as Support Vector Machines, Decision Trees, and k-Nearest Neighbors are still commonly used. At the same time, Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are used for remote sensing and time-dependent agricultural analysis. The most frequently used dataset source is Kaggle, and typical inputs include soil nutrients (NPK), soil pH, weather conditions, and satellite indices such as NDVI and EVI. Many studies have achieved high accuracy, but most are based on static datasets, which reduces their reliability in real-world scenarios. The main research gaps are limited real-time deployment, low integration of multiple data sources, low cross-regional validation, and low model interpretability. The review shows the importance of scalable and explainable AI systems for real applications in agriculture.","author":[{"family":"Oladipe","given":"Ebenezer"},{"family":"Adewumi","given":"Sunday"},{"family":"Kolajo","given":"Taiwo"},{"family":"Agbogun","given":"Joshua"}],"issued":{"date-parts":[[2026]]},"DOI":"10.46481/asr.2026.5.3.590","URL":"https://doi.org/10.46481/asr.2026.5.3.590","source":"crossref"},{"id":"doi:10.61854/rccedia.v1n1.004","type":"article-journal","title":"Innovación en agricultura de precisión: panorama de patentes","abstract":"El objetivo de este estudio fue caracterizar, mediante patentometría, la dinámica tecnológica asociada a la agricultura de precisión a partir de solicitudes internacionales, identificando tendencias temporales, jurisdicciones de protección, solicitantes líderes y áreas técnicas dominantes. Se realizó un estudio observacional de corte transversal (2025) siguiendo las directrices de la OMPI para informes de panorama de patentes. Se consultó Espacenet y se aplicó una estrategia amplia basada en códigos IPC/CPC y filtros textuales en el título o el resumen, con restricción a solicitudes PCT y una ventana entre 2005 y 2025. La depuración redujo 39 996 registros iniciales a 1 497 documentos PCT y a 1 367 documentos posteriores a 2005, lo que sugiere que gran parte del estado de la técnica circula por rutas nacionales y que el subconjunto PCT concentra invenciones con aspiración global. La serie temporal mostró aceleración desde 2013 y un punto de inflexión en 2017; el crecimiento tendencial se respaldó con un CAGR de 7,29 % (de 2014 a 2024), aunque los modelos de pronóstico reflejaron sensibilidad a los últimos años por el desfase de publicación. La protección se concentró en Estados Unidos, China y la vía europea, con un liderazgo fragmentado, una convivencia de universidades y empresas y con un núcleo tecnológico centrado en gestión y soporte a decisiones, sensado remoto e inteligencia artificial y ejecución en el campo. Se concluye que el ámbito se mantiene en expansión y ofrece oportunidades de diferenciación por integración, interoperabilidad y validación operativa.","author":[{"family":"Alvarez","given":"Gabriela"},{"family":"Minchalo","given":"Gisselle"},{"family":"Arevalo","given":"Luis"}],"issued":{"date-parts":[[2026]]},"DOI":"10.61854/rccedia.v1n1.004","URL":"https://doi.org/10.61854/rccedia.v1n1.004","source":"crossref"},{"id":"doi:10.3390/agriculture16030384","type":"article-journal","title":"A Precision Weeding System for Cabbage Seedling Stage","abstract":"This study developed an integrated vision–actuation system for precision weeding in indoor soil bin environments, with cabbage as a case example. The system integrates lightweight object detection, 3D co-ordinate mapping, path planning, and a three-axis synchronized conveyor-type actuator to enable precise weed identification and automated removal. By integrating ECA and CBAM attention mechanisms into YOLO11, we developed the YOLO11-WeedNet model. This integration significantly enhanced the detection performance for small-scale weeds under complex lighting and cluttered backgrounds. Based on the optimal model performance achieved during experimental evaluation, the model achieved 96.25% precision, 86.49% recall, 91.10% F1-score, and a mean Average Precision (mAP@0.5) of 91.50% calculated across two categories (crop and weed). An RGB-D fusion localization method combined with a protected-area constraint enabled accurate mapping of weed spatial positions. Furthermore, an enhanced Artificial Hummingbird Algorithm (AHA+) was proposed to optimize the execution path and reduce the operating trajectory while maintaining real-time performance. Indoor soil bin tests showed positioning errors of less than 8 mm on the X/Y axes, depth control within ±1 mm on the Z-axis, and an average weeding rate of 88.14%. The system achieved zero contact with cabbage seedlings, with a processing time of 6.88 s per weed. These results demonstrate the feasibility of the proposed system for precise and automated weeding at the cabbage seedling stage.","author":[{"family":"Wang","given":"Pei"},{"family":"Chen","given":"Weiyue"},{"family":"Niu","given":"Qi"},{"family":"Li","given":"Chengsong"},{"family":"Yang","given":"Yuheng"},{"family":"Li","given":"Hui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16030384","URL":"https://doi.org/10.3390/agriculture16030384","source":"crossref"},{"id":"doi:10.1201/9781003545781-4","type":"article-journal","title":"Integrating AI with Plant Functional Genomics","abstract":"The advances in artificial intelligence (AI) have revolutionized plant functional genomics research to the extent of enabling high-resolution and large-scale analysis of complex molecular data. This chapter explores the integration of AI techniques such as deep learning, generative modeling, and transfer learning into plant transcriptomics, proteomics, and phenomics research. New applications such as AI-aided spatial transcriptomics, gene function prediction across species, and hypothesis-free discovery with generative models are discussed with special focus. This chapter discusses how these AI-focused approaches facilitate functional annotation of genes, decipher tissue-specific expression patterns, and accelerate the discovery of regulatory networks in non-model and crop species. Representative case studies on Arabidopsis root datasets, high-throughput imaging strategies, and transformer-based architectures illustrate the potential of AI to uncover biological complexities with unprecedented resolution and predictive accuracy. Bridging computational intelligence with experimental biology, this integrative platform holds the promise of a revolutionary platform for data-driven plant science and next-generation crop improvement.","author":[{"family":"Manoj","given":"Mani"},{"family":"Manikantan","given":"Pappuswamy"},{"family":"Lakshmi","given":"Jayakrishnan"},{"family":"Amar","given":"Tanav"},{"family":"Harshitha","given":"Kathivel"},{"family":"Prabhu","given":"Jeyabal"},{"family":"Robert","given":"Asirvatham"},{"family":"Anand","given":"Arumugam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-4","URL":"https://doi.org/10.1201/9781003545781-4","source":"crossref"},{"id":"doi:10.4018/979-8-2600-0888-1.ch002","type":"article-journal","title":"Towards Sustainable Irrigation","abstract":"Smart irrigation systems integrating Artificial Intelligence (AI) and Internet of Things (IoT) technologies are revolutionizing water management in agriculture. A typological classification is displayed covering classical algorithms (KNN, SVM, Random Forest), deep learning (CNN, LSTM), crossbreed models, reinforcement learning, and transfer learning approaches. These models are assessed based on expectation precision, water-saving execution, taking a toll, scalability, and versatility. The come-about appears that whereas classical models are cost-effective and simple to convey, profound learning and hybrid strategies offer prevalent exactness and vigor. Support learning and exchange learning to illustrate promising flexibility and asset optimization capabilities. Despite these advances, challenges remain in terms of sending fetched sensors with unwavering quality and versatility over assorted agrarian settings.","author":[{"family":"Mougare","given":"Safae"},{"family":"Abouelmehdi","given":"Karim"},{"family":"Saadaoui","given":"Hassan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-2600-0888-1.ch002","URL":"https://doi.org/10.4018/979-8-2600-0888-1.ch002","source":"crossref"},{"id":"doi:10.1007/s44163-026-00896-y","type":"article-journal","title":"An IoT-driven machine learning system for real-time smart crop recommendation and optimization in precision agriculture","abstract":"Agriculture is essential to global food security and sustainable development. The use of machine learning (ML) and Internet of Things (IoT) has the potential to enhance crop production and improve resource management through enhanced precision agriculture. This article describes a smart crop recommender system developed to support both ML-based decision making and real-time environmental sensing. At the core of the system is a capacitive soil moisture sensor and a temperature-humidity sensor interfaced using an Arduino Nano. Using a nRF24L01 transceiver employing the 2.4 GHz Enhanced Shock Burst (ESB) protocol, the sensor information can be wirelessly transmitted. Data collected from the sensors are sent to an ESP32 module that posts the information to the Blynk web application through Wi-Fi, allowing real-time remote access. As the data source for the crop recommender model, the Blynk application provides the data needed to perform data analysis on the various ML algorithms (Random Forest, Bagging, Decision Tree, Gradient Boosting, and Enhanced Gaussian Naive Bayes [EGNB]) to determine the most suitable type of crop based on the current soil and environmental conditions. Based on the analysis, the EGNB model showed superiority with an accuracy of 99.55% with respect to precision, recall, and F1-score. This system provides an economically viable and expandable approach to smart agricultural practices, which integrates cutting-edge machine-learning modelling with digital tools for obtaining data in real-time (IoT). These capabilities allow users to receive and utilize actionable, data-driven guidance in real time when making decisions about crop production.","author":[{"family":"Sawant","given":"Nitish"},{"family":"Kumar","given":"Anuj"},{"family":"Pant","given":"Sangeeta"},{"family":"Kotecha","given":"Ketan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s44163-026-00896-y","URL":"https://doi.org/10.1007/s44163-026-00896-y","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7257-0.ch008","type":"article-journal","title":"Predicting and Managing Crop Health Through Artificial Intelligence and IoT","abstract":"In this chapter, the author discusses the paradigm shift in modern agriculture that is motivated by the need to have sustainable food production and the use of resources efficiently through smart farming. Smart farming combines IoT, AI, ML, big data analytics, drones, and robotics and is used to increase productivity and environmental sustainability. Making sense of data is turning real-time sensor data into actionable insights in order to monitor the conditions of soil, crop development, weather conditions, and the health of livestock. Precision farming allows for the process of irrigating, fertilizing, pest control, and harvesting, which minimizes the amount of inputs wasted. Experiment results demonstrate machine learning algorithms as the best classifiers using the precision, recall, accuracy and F1-score that play a key role in getting smarter farming to work. The model is stable, as the accuracy of disease detection is 98.26% and validation outcomes are more proficient. Agriculture 5.0 will encourage transparency, efficiency, and the use of less water, energy, and chemicals.","author":[{"family":"Tushar"},{"family":"Jaiswal","given":"Pooja"},{"family":"Shrivastava","given":"Prabhat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-7257-0.ch008","URL":"https://doi.org/10.4018/979-8-3373-7257-0.ch008","source":"crossref"},{"id":"doi:10.1201/9781003546702-14","type":"article-journal","title":"Integration of AI with Precision Agriculture for Targeted Pest Control","abstract":"The integration of artificial intelligence (AI) with precision agriculture has revolutionized targeted pest control by enabling early pest detection, predictive analytics, and precise pesticide application. With AI-driven technologies, such as remote sensing, IoT, drones, and machine learning models, it is possible to monitor crop health and pest population in real-time, minimizing the relevant use of chemicals and environmental impact. These technologies can facilitate proactive management policies, enhance crop productivity, reduce the cost of inputs and encourage eco-sustainable farming. This chapter covers AI-based pest detection system, autonomous robots, and data analytics to enhance the decision-making process, which ensures efficient solutions to pest control that are accurate and environmental-friendly. Focusing on the future of the possibility, the chapter shows the continuing innovations and obstacles to using AI to manage pests as a key to sustainable agriculture and world food security.","author":[{"family":"Hameed","given":"Akhtar"},{"family":"Ali","given":"Subhan"},{"family":"Aslam","given":"Hafiz"},{"family":"Alam","given":"Muhammad"},{"family":"Ali","given":"Faizan"},{"family":"Binyamin","given":"Rana"},{"family":"Rafiq","given":"Muhammad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003546702-14","URL":"https://doi.org/10.1201/9781003546702-14","source":"crossref"},{"id":"doi:10.3390/electronics15122502","type":"article-journal","title":"An Intelligent Cloud-Integrated Electronic Nose System for Non-Destructive Fruit Ripeness Monitoring in Precision Agriculture","abstract":"Precision in estimating the ripeness of fruits is critical in quality control and minimizing losses in supply chains of agricultural produce following harvesting. Conventional ripeness assessment techniques tend to be destructive, time-consuming and unsuited to monitoring in real-time. In order to avoid these drawbacks, this research suggests a cloud-integrated smart electronic nose (E-nose) system to predict fruit ripeness in a non-destructive and real-time manner. The system uses a low-priced, non-selective gas sensor array with an ESP8266-based Internet of Things (IoT) board to record volatile organic compound (VOC) signatures released at various maturation phases of fruits. The obtained sensor data will be sent to a cloud server to be preprocessed centrally and classified using machine learning, thus reducing the computational needs at the edge. There is a collection of 953 samples of the unripe, ripe, and rotten stages of banana under controlled conditions. Several supervised machine learning algorithms are tested, and methods of ensemble boosting proved to be more effective. The Light Gradient Boosting Machine (LightGBM) is the most accurate in terms of classification of 96.50% and weighted F1-score of 96.49%. The confusion matrix analysis shows that the majority of misclassifications are observed among the neighboring stages of ripeness, indicating the gradual biochemical changes. The system is practically applicable as visualization of the predicted ripeness levels occurs in real time via a mobile application. The suggested model provides a scalable, low-cost, and smart solution to precision agriculture, which can allow efficient, automated, and non-destructive measurement of fruit quality.","author":[{"family":"Kumar","given":"Dharmendra"},{"family":"Jain","given":"Vibha"},{"family":"Mishra","given":"Ashutosh"},{"family":"Shrestha","given":"Rakesh"},{"family":"Sahlabadi","given":"Mahdi"},{"family":"Rajput","given":"Navin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/electronics15122502","URL":"https://doi.org/10.3390/electronics15122502","source":"crossref"},{"id":"doi:10.1201/9781003545781-12","type":"article-journal","title":"Artificial Intelligence Approaches in Plant Digital Multiple Omics","abstract":"The artificial intelligence (AI) integration in plant digital multiple omics has transformed plant research by increasing data assessment, explanation, and predictive modeling. AI-driven applications, encompassing deep learning (DL) and machine learning (ML), enable the extraction of impactful insights from large-scale genomic, proteomic, phenomic, metabolomic, and transcriptomic datasets. These technologies facilitate correct trait choice, gene expression analysis, and stress tolerance prediction, thereby increasing crop advancement programs. AI models, such as recurrent neural networks and convolutional neural networks (CNNs), have been successfully used for accurate breeding and high-throughput phenotyping. Furthermore, incorporative AI frameworks permit a systems biology strategy and bridge gaps among omics layers to elucidate complicated plant-climate interactions. Current innovations in AI-assisted image analysis and natural language processing further increase digital farming by yield forecasting and automating disease detection. Despite its revolutionized potential, AI applications in plant multiple omics pose problems such as limited annotated datasets, data heterogeneity, and the requirement for standardized computational frameworks. Determining these constraints needs interdisciplinary cooperation between agronomists, data scientists, and biologists. Future AI-driven multi-omics applications promise to develop climate-resilient crops, improve agricultural sustainability, and increase food security through automated decision-making and predictive analytics. Future studies should focus on producing AI-powered, multi-omics platforms based on clouds with organized data-sharing protocols to increase reproducibility and interoperability in plant sciences.","author":[{"family":"Mobeen","given":"Maida"},{"family":"Umar","given":"Aftab"},{"family":"Akram","given":"Javeria"},{"family":"Aziz","given":"Robina"},{"family":"Ghafar","given":"Muhammad"},{"family":"Raza","given":"Qasim"},{"family":"Fatima","given":"Samreen"},{"family":"Majeed","given":"Muhammad"},{"family":"Shahzad","given":"Umbreen"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-12","URL":"https://doi.org/10.1201/9781003545781-12","source":"crossref"},{"id":"doi:10.1201/9781042004607-95","type":"article-journal","title":"Revolutionizing Agriculture by Integrating AI, Block Chain, IOT and Cloud for Precision and Sustainable Farming","abstract":"Agriculture face several challenges such as resource inefficiency, climate variability, lack of real time monitoring, supply chain and market challenges that impact productivity, sustainability, and profitability. These challenges highlight the need for AI, Block chain, IOT and Cloud based solution to enable smart, data-driven, and sustainable farming practices. To address these challenges, this research paper reflects an overview of smart agriculture system that integrate with AI, Block chain, IOT AND Cloud Technology to enhance efficiency and sustainability in farming practices. This system utilizes IOT-enabled sensors deployed in field to collect the real time data including temperature, humidity and soil moisture. This data is transmitted and saved in the cloud based server where AI-driven analytics optimize irrigation, predict crop disease and potential threats, and automate farm management. Additionally, AN AI chat bot provides farmers with real time insights, new farming techniques and guidance on organic and sustainable farming practices fostering environmental conservation. Block chain ensures data integrity, transparency and secure transaction, enabling traceability by providing decentralized and tampers- proof record keeping of agricultural activities. By leveraging cloud computing, farmers can access real time insights from any location, allowing for scalable and cost-effective precision farming. This work focuses how integration of these advanced technologies improves crop yields, optimizes resource consumption, and promotes sustainability. The digital transformation in agriculture can bridge the gap between traditional farming and modern advancements in agriculture fostering a data-driven, efficient, and resilient agriculture ecosystem also discussed here.","author":[{"family":"Singh","given":"Arya"},{"family":"Singh","given":"Arpita"},{"family":"Dheer","given":"Getaansha"},{"family":"Kapoor","given":"Nirman"},{"family":"Rajput","given":"Anupama"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781042004607-95","URL":"https://doi.org/10.1201/9781042004607-95","source":"crossref"},{"id":"doi:10.1201/9781003773801-83","type":"article-journal","title":"A Novel Hybrid Approach for Foreground Extraction in Precision Agriculture","abstract":"Modernizations in precision agriculture have transformed data analyses and crop management strategies. It redefines the farming practices, enhancing productivity and sustainable resource management. Foreground segmentation is crucial to empower the exact identification for the accurate crop analysis and other significant elements in agricultural practices. This work involves the unsupervised approach combined with the pretrained network UNet, VGG16, ResNet50 followed by the clustering method K Means and DBSCAN to extract the foreground regions from plant images. Furthermore Class Activation Mapping were employed to generate heatmaps to highlight the area of high importance assisting in accurate segmentation. The result revealed that this collaborated work brings the output with the accuracy and F1 score above 70%for the complex maize weed dataset, and above 85%for crop weed detection dataset and crop weed field images dataset.","author":[{"family":"Revathy","given":"MB"},{"family":"Kavitha","given":"J"},{"family":"Rani","given":"PAJ"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003773801-83","URL":"https://doi.org/10.1201/9781003773801-83","source":"crossref"},{"id":"doi:10.1021/acsmaterialslett.6c00076","type":"article-journal","title":"Ultrasensitive Biopolymer−MOF Composite-Based Pressure Sensor for Data-Driven Precision Agriculture","abstract":"Abstract Plants continuously experience subtle mechanical stimuli from growth, fruit loading, and environmental stress, yet decoding these biomechanical signals remains difficult due to the lack of soft, biocompatible, and sensitive sensing materials. Herein, we report a chitosan−metal-organic framework (CS−MOF) composite as an ultrasensitive capacitive pressure sensor for precision agriculture. Incorporating MOF within a chitosan matrix creates a network with enhanced dielectric modulation and tunable compressibility, collectively improving mechanocapacitive transduction. The CS−MOF composite exhibits high pressure sensitivity (4.58 kPa−1, 0−5 kPa), rapid response/recovery times (200 ± 5/220 ± 3 ms), and excellent durability over 2000 cycles. Integrated onto tomato plants (Solanum lycopersicum), the sensor enables noninvasive monitoring of fruit growth and branch deformation via wireless IoT coupling, showing a strong correlation between capacitance changes and fruit mass accumulation (R2 = 0.95, p &amp;lt; 0.001). This work highlights biopolymer−MOF hybrids as promising platforms for sustainable, data-driven agriculture.","author":[{"family":"Mansoor","given":"Sheikh"},{"family":"Iqbal","given":"Shahzad"},{"family":"Abbas","given":"Zahir"},{"family":"Kang","given":"Ho"},{"family":"Akram","given":"Waseem"},{"family":"Chung","given":"Yong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1021/acsmaterialslett.6c00076","URL":"https://doi.org/10.1021/acsmaterialslett.6c00076","source":"crossref"},{"id":"doi:10.59429/ace.v9i3.6019","type":"article-journal","title":"An Ensemble Machine Learning-Based Data-Centric Framework for Agrochemical Optimization in Precision Agriculture for Sustainable Farming","abstract":"Precision agriculture is an important application scenario for chemical engineering to carry out the clean production and sustainable resource use. In this paper, we propose an explainable data-centric ensemble machine learning framework for the optimization of agrochemical (fertilizer and pesticide) inputs based on utilizing their input efficiency and reducing environmental pollution based on chemical engineering aspects. We utilize the multiple source agricultural data (soil N, P, K, pH, temperature, humidity and rainfall) to make it possible for the precise application and site-specific planting adaptation of agrochemicals. Integrating three models including Logistic Regression, Support Vector Machine, Decision Tree, we utilize the Voting Classifier and Stochastic Gradient Boosting (SGB) to implement the classification. Together with controlled noise addition and cross validation that utilize data-centric methods, the Voting Classifier performs the best accuracy 90.7% with perfect score balance between precision, recall and F1-score. SHAPley Additive ExPlanations (SHAP) and permutation feature importance methods are adopted for model interpretation and illustrate the dominant features are rainfall, humidity and nitrogen that are consistent with agricultural chemical transport and nutrient conversion process. The framework can be further used for VRT systems to realize automated and quantitative inputs and reduce input of fertilizer and pesticides; soil and water pollution is limited, resource use efficiency is high. A generalized, interpretable and engineering-practical framework is proposed which is important for the chemical engineering application of clean production in precision agriculture.","author":[{"family":"Mishra","given":"Padma"},{"family":"Doshi","given":"Kinjal"},{"family":"Jadhav","given":"Rupali"},{"family":"Vipat","given":"Rashmi"},{"family":"Ved","given":"Niki"}],"issued":{"date-parts":[[2026]]},"DOI":"10.59429/ace.v9i3.6019","URL":"https://doi.org/10.59429/ace.v9i3.6019","source":"crossref"},{"id":"doi:10.18488/cras.v13i2.5015","type":"article-journal","title":"The climate-driven evolution of farm machinery technologies: Resilience, precision, and policy in global and Indian agriculture","abstract":"The study examines the critical role of climate change in reshaping agricultural mechanization, emphasizing the adoption of Climate-Smart Agriculture (CSA) technologies to enhance operational resilience, optimize resource use, and mitigate sectoral emissions. It particularly focuses on smallholder-dominated regions, such as India, where institutional frameworks are central to technology adoption. A comprehensive review and synthesis of global and Indian literature on climate impacts, mechanization trends, and institutional models was conducted. The analysis integrates environmental stressors, thermal extremes, hydrological volatility, and reduced operational windows, with the technological evolution of CSA, including Artificial Intelligence (AI), Internet of Things (IoT), and autonomous machinery. Socioeconomic constraints, landholding fragmentation, and collective access mechanisms, such as Custom Hiring Centers (CHCs) and Farmer-Producer Organizations (FPOs), were examined to evaluate adoption feasibility. Climate change imposes both operational and structural challenges that conventional machinery cannot meet. Advanced CSA technologies, leveraging data-driven precision and autonomous capabilities, are essential for maintaining timeliness and efficiency under extreme conditions. In India, the smallholder landscape necessitates institutionalized collective access models, which effectively bridge the gap between high-cost climate-smart equipment and limited farmer resources. Integrated policy support, innovative financing, and local technical capacity building are identified as critical enablers for successful adoption. The findings underscore the need for coordinated strategies combining technology, institutional innovation, and capacity development to achieve scalable climate adaptation in agriculture. Policymakers, researchers, and industry stakeholders must prioritize multifunctional, resource-efficient machinery alongside sustainable institutional frameworks to ensure resilience in smallholder-dominated systems.","author":[{"family":"Paul","given":"Ayan"},{"family":"Verma","given":"Pooja"},{"family":"Machavaram","given":"Rajendra"}],"issued":{"date-parts":[[2026]]},"DOI":"10.18488/cras.v13i2.5015","URL":"https://doi.org/10.18488/cras.v13i2.5015","source":"crossref"},{"id":"doi:10.1186/s13007-026-01556-z","type":"article-journal","title":"DAPR-AM-Net: an end-to-end smart farming system powered by dual-attention progressive refinement and adaptive MixUp for explainable tomato leaf disease classification and forecasting.","abstract":"Vision-based crop disease diagnosis plays a pivotal role in smart agriculture, yet challenges such as complex field backgrounds, high intra-class similarity of lesion morphology, and severe data imbalance continue to impede model stability and interpretability. To address these issues, this study proposes DAPR-AM-Net, an intelligent diagnostic framework for tomato leaf diseases that integrates dual-attention progressive refinement with adaptive MixUp. The method introduces four key innovations: (1) a Dual Attention Fusion Mechanism (DAFM) that jointly leverages channel-wise and spatial attention to enhance lesion-related texture, color, and structural cues while suppressing background noise via the CBAM module, thereby directing the network's focus toward pathogenic regions; (2) an Adaptive MixUp with Attention-Aware Sampling (AMAAS) module that dynamically adjusts sample mixing ratios according to attention maps, effectively improving discrimination in complex boundary areas; (3) a Progressive Feature Refinement with Dual Attention (PFR-DA) module that incrementally optimizes deep feature representations through cross-hierarchical information flows; and (4) an Imbalance-Aware Multi-Objective Optimization (IAMOO) strategy that adaptively modulates loss weights based on category distribution to strengthen recognition of minority disease classes. On our self-constructed Tomato-DD dataset, DAPR-AM-Net achieves superior performance across all major metrics-including an accuracy of 99.73%, precision of 99.73%, recall of 99.74%, and an F1-score of 99.73%-outperforming current state-of-the-art approaches. On the full Plant-Village dataset, the model achieves 99.85% accuracy, 99.78% precision, 99.84% recall, and a 99.81% F1-score, while maintaining a compact model size of only 4.72 M parameters. Multi-level interpretability analyses corroborate the transparency and reliability of the model's inference process. Additionally, we developed an end-to-end smart agriculture platform powered by DAPR-AM-Net. Overall, DAPR-AM-Net provides a forward-looking yet practical solution for high-accuracy and strongly interpretable disease diagnosis in smart agriculture scenarios, demonstrating both methodological innovation and real-world applicability.","author":[{"family":"Wang","given":"Ran"},{"family":"Yu","given":"Xiao"},{"family":"Lu","given":"Lina"},{"family":"Chen","given":"Cong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1186/s13007-026-01556-z","URL":"https://doi.org/10.1186/s13007-026-01556-z","source":"europepmc"},{"id":"doi:10.71443/9789349552364-13","type":"article-journal","title":"Big Data Analytics and AI for Crop Rotation Planning and Sustainable Land Use","abstract":"The growing pressures of climate change, soil degradation, and food security demands have heightened the need for innovative agricultural practices that balance productivity with sustainability. This chapter explores the transformative role of Big Data analytics and Artificial Intelligence (AI) in optimizing crop rotation planning and promoting sustainable land use. By leveraging real-time data from diverse sources such as soil sensors, satellite imagery, and weather forecasts, AI-driven systems can develop precise, adaptive crop rotation strategies that enhance soil health, mitigate environmental risks, and improve overall farm productivity. The chapter delves into the integration of AI models that predict long-term soil health impacts, optimize resource use, and provide dynamic crop rotation recommendations based on real-time environmental conditions. Emphasizing the importance of data standardization, quality assurance, and predictive analytics, the chapter outlines key challenges and opportunities in implementing these technologies at scale. It also discusses the potential of AI and Big Data to foster climate change adaptation in agriculture, ensuring that farming systems remain resilient to evolving environmental challenges. The integration of these technologies into sustainable land management practices promises to reshape the future of agriculture, enabling both increased food production and environmental preservation.","author":[{"family":"Tiwari","given":"Nidhi"},{"family":"Thanikasalam","given":"A"},{"family":"Vandarkuzhali","given":"T"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-13","URL":"https://doi.org/10.71443/9789349552364-13","source":"crossref"},{"id":"doi:10.1109/isacc65211.2025.10969205","type":"article-journal","title":"Smart Agriculture: Enhancing Crop and Weed Detection Using MobileNetV2 for Autonomous Farming Systems","abstract":"Agriculture is vital to food security and economic stability, but weeds reduce crop yields by competing for sunlight, water, and nutrients. Manual weeding and herbicides are often ineffective and environmentally harmful. This study presents an autonomous weeding robot that utilizes MobileNetV2 for real-time crop and weed detection, leveraging its lightweight architecture for efficient performance on devices like the NVIDIA Jetson Nano. The system achieves 85% accuracy, a 0.72 IoU score, and 25 FPS processing speed, with field tests showing detection accuracy of up to 90% in ideal conditions. By reducing herbicide use and improving resource efficiency, this approach supports sustainable agriculture, with future advancements such as multispectral imaging and pest detection further enhancing its role in precision agriculture.","author":[{"family":"Ma","given":"Sutharson"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/isacc65211.2025.10969205","URL":"https://doi.org/10.1109/isacc65211.2025.10969205","source":"crossref"},{"id":"doi:10.1109/iciee63403.2024.10920455","type":"article-journal","title":"Evaluation of Internet Connection Reconfiguration for Reliable Monitoring and Treatment of Toraja Lada Katokkon Smart Farming","abstract":"This study evaluates the internet transmission performance in smart farming in Lembang Madandan, Tana Toraja Regency, focusing on how router distance affects download speed, upload speed, and latency. The greenhouse cultivates Lada Katokkon plants, valuable yet sensitive to environmental conditions, necessitating IoT technology for monitoring and control. Data were collected at distances ranging from 1 to 20 meters under loaded and unloaded conditions. Results showed that the download speed fluctuated significantly with values ranging from 4.3 Mbps to 12 Mbps, upload speed varied between 1 Mbps and 3.1 Mbps, unloaded latency ranged from 0 ms to 49 ms, and loaded latency ranged from 304 ms to 995 ms. These variations indicate that distance significantly affects network performance. Optimizing device placement, adding access points, and using repeaters or extenders are recommended to improve signal strength and connection stability. Limitations include specific greenhouse conditions and measurement range. Further studies should explore other environmental factors and test network optimization strategies. Implementing these strategies is expected to enhance IoT system operation, boost productivity, and sustainability in smart agriculture, and ensure better management of Lada Katokkon plants.","author":[{"family":"Pineng","given":"Martina"},{"family":"Palantei","given":"Elyas"},{"family":"Areni","given":"Intan"},{"family":"Wardi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iciee63403.2024.10920455","URL":"https://doi.org/10.1109/iciee63403.2024.10920455","source":"crossref"},{"id":"doi:10.51583/ijltemas.2025.140400115","type":"article-journal","title":"Agrovision: Smart Solutions for Modern Farming.","abstract":"Abstract: AgroVision is a mobile-centric artificial intelligence- driven platform, particularly designed to enhance the efficiency and sustainability of contemporary agriculture operations, specif- ically focusing on small-scale farmers in resource-constrained areas. AgroVision offers personalized crop prescriptions using soil pH, moisture, and nutrient levels, as well as for weed and crop detection through the YOLOv8 algorithm. In contrast to hardware-locked proprietary agricultural innovations, AgroVi- sion can execute seamlessly on mobile devices via a Flutter app, allowing farmers to take pictures of their fields and input soil data directly. From this analysis, the insights provided by AgroVision are tailored to the user so that decisions can be made regarding maximized crop yield, deepening ecological impact, and ecological footprint minimization. While the development team faced challenges with low computational power and a lack of varied training data, they were still able to robustly optimize the models and apply data augmentation techniques to guarantee consistent system performance across different operational scenarios. Focused on bridging the accessibility gap for precision farming technologies and fostering data-driven practices in agriculture, AgroVision addresses gaps related to sustained and inclusive agricultural advancement.","author":[{"family":"More","given":"Kunal"},{"family":"Ghongade","given":"Vishvesh"},{"family":"Asodekar","given":"Chinmay"},{"family":"Palkar","given":"Prof"},{"family":"Mandlik","given":"Shreyash"}],"issued":{"date-parts":[[2025]]},"DOI":"10.51583/ijltemas.2025.140400115","URL":"https://doi.org/10.51583/ijltemas.2025.140400115","source":"crossref"},{"id":"doi:10.32832/jurma.v9i1.2446","type":"article-journal","title":"Melon Hydroponic Cultivation Based on Smart Farming Technology to Improve the Creative Economy","abstract":"Indonesia is an agricultural country that has a variety of agricultural commodities that can be developed in the horticulture sector. One of the agricultural products that comes from horticulture commodities and has a high selling value is melon. Rejosari Village is a developing village in Kudus Regency and has a large rice field area of ​​60% of the total area. This is utilized by Rejosari Village to implement a hydroponic melon farm program as an effort to support the SDGs of food security and sustainable agriculture in Indonesia. One of the problems faced in the hydroponic melon cultivation process in Rejosari Village is the lack of appropriate technology in the cultivation process and the lack of optimal utilization of the melons produced. The methods used in this community service activity are preparation, implementation, and evaluation. The results of this community service activity are the application of smart farming technology, the formation of a mini greenhouse, the existence of the Paguyuban Melon group, an increase in the productivity of smart farming businesses by 20%, and an increase in efficiency and effectiveness in hydroponic melon cultivation.","author":[{"family":"Nurviyani","given":"Erly"},{"family":"Permadi","given":"Pria"},{"family":"Agustina","given":"Atni"},{"family":"Purwaningrum","given":"Jayanti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32832/jurma.v9i1.2446","URL":"https://doi.org/10.32832/jurma.v9i1.2446","source":"crossref"},{"id":"doi:10.1109/i-coste68047.2025.11467551","type":"article-journal","title":"Solar-Powered IoT-Based Smart Farming Model (SPISFM)","abstract":"The Solar-Powered IoT-Based Smart Farming Model (SPISFM) represents an innovative solution to key agricultural inefficiencies, including excessive water consumption, high operational energy costs, and insufficient crop heath assessment by utilizing sustainable solar energy and advanced IoT enabled sensor system thus promoting green environment. The system incorporates distributed photovoltaic power generation, smart irrigation automation, and mobile-based real-time management for data-centric agricultural decision-making. The system employs soil moisture sensors and microcontroller-operated irrigation valves to deliver water precisely, when necessary, complemented by CCTV imaging with embedded machine learning. Through net metering, surplus photovoltaic output exported to the national grid, ensuring zero dependence on conventional fossil energy and enabling CO2-free irrigation. The SPISFM represents a sustainable, adaptable, and resource-efficient strategy aligned to the demands of modern farming.","author":[{"family":"Naeem","given":"Md"},{"family":"Ruma","given":"Kamrunnahar"},{"family":"Sultana","given":"Shakila"},{"family":"Anjum","given":"Nafiza"},{"family":"Barua","given":"Moumita"},{"family":"Islam","given":"Md"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/i-coste68047.2025.11467551","URL":"https://doi.org/10.1109/i-coste68047.2025.11467551","source":"crossref"},{"id":"doi:10.1109/icicnct66124.2025.11233075","type":"article-journal","title":"Smart Farming System for Plant Disease Detection using Optimized Spectral Domain Reconstruction Graph Neural Network","abstract":"The practice of cultivating the soil, growing crops and keeping livestock is referred to as farming. An essential component of a nation's economic growth is agriculture. Farming accounts for around 58 % of a nation's main source of income. Up until now, farmers have used traditional farming methods. These methods took a lot of time and were less productive since they were imprecise. By accurately identifying actions that taken at appropriate time, precise farming contributes to increased output. Precision farming includes forecasting the weather, evaluating the soil, suggesting crops to be grown, and figuring out how much fertilizer and pesticides are necessary. In this manuscript, Smart Farming System for Plant Disease Detection using Optimized Spectral Domain Reconstruction Graph Neural Network (SFS-PDD-SDRGNN) is proposed. Initially real time input data is gathered from IoT sensors. Then, input data is fed into preprocessing stage. In preprocessing, Regularized Bias aware Ensemble Kalman Filtering (RBAEKF) is utilized to remove noise and normalize data. After preprocessing, preprocessed data is fed to Spectral Domain Reconstruction Graph Neural Network (SDRGNN) for plant disease detection as fungal infection and nutrient deficiency. To enhance accuracy, the Arctic Tern Optimization Algorithm (ATOA) is utilized to optimize SDRGNN weight parameters and ensuring precise plant disease detection. The proposed SFS-PDD-SDRGNN method is executed in Python and evaluated utilizing performance metrics like accuracy, detection rate, recall, precision, computation time. The proposed method attains$23.41 \\%, 25.29 \\%$and 24.35 % higher accuracy;$25.41 \\%, 24.29 \\%$and 27.35 % higher precision;$\\mathbf{2 3. 4 1 \\%, ~} \\mathbf{2 2. 2 9 \\%}$and$\\mathbf{2 5. 3 5 \\%}$higher recall when analyzed with existing techniques.","author":[{"family":"Rani","given":"LF"},{"family":"Deepa","given":"N"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icicnct66124.2025.11233075","URL":"https://doi.org/10.1109/icicnct66124.2025.11233075","source":"crossref"},{"id":"doi:10.15662/ijeetr.2026.0802121","type":"article-journal","title":"Data-Driven Smart Farming and Personalized Diet Advisory System","abstract":"Smart agriculture systems leverage machine learning techniques to enhance crop productivity and resource efficiency. This system integrates sensor data such as soil moisture, temperature, humidity, and nutrient levels to monitor real-time field conditions. Machine learning models analyze historical and real-time data to predict crop yield, detect plant diseases, and recommend optimal irrigation and fertilization schedules. By automating decision-making, the system minimizes water usage, reduces fertilizer waste, and improves overall farm management Weather forecasting data is also incorporated to support proactive farming decisions and reduce climate-related risks. The proposed approach enables early detection of crop stress and pest infestation, allowing timely intervention. In addition, the system includes an image-based analysis module where farmers can upload images of fruits or vegetables to identify the produce and estimate its nutritional values such as vitamins, minerals, and caloric content using computer vision and deep learning techniques. Furthermore, the system personalizes nutritional recommendations based on the user’s health conditions, including diabetes, obesity, or nutrient deficiencies. By linking dietary advice to specific health needs and the quantity of produce consumed, it supports better health management alongside sustainable farming. Farmers and consumers receive actionable insights through a user-friendly interface, supporting both production and post-harvest decision-making This intelligent system promotes sustainable farming practices, enhances food quality awareness, improves health outcomes, and increases overall profitability. Overall, the machine learning-based smart agriculture system provides a comprehensive and reliable solution to address modern agricultural and dietary challenges.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.15662/ijeetr.2026.0802121","URL":"https://doi.org/10.15662/ijeetr.2026.0802121","source":"crossref"},{"id":"doi:10.1016/j.procs.2025.03.233","type":"article-journal","title":"IoT-Driven Smart Farming with Machine Learning for Sustainable Food Systems","abstract":"Integrating the Internet of Things (IoT) and machine learning (ML) technologies in agriculture, commonly called smart farming, is revolutionizing the sector by enhancing productivity, efficiency, and sustainability. This paper explores the application of IoT-driven smart farming using machine learning for sustainable agricultural practices. The system introduces an efficient Soil Moisture Detection System utilizing IoT Technology, revolutionizing modern farming practices. By continuously monitoring crucial parameters such as soil moisture, temperature, and humidity in real-time, the system ensures seamless data transmission to a centralized server. Additionally, integrating motion detection capabilities enhances security measures and promptly alerts farmers to environmental changes. The dataset consisting of 100,000 rows is generated to facilitate the development and training of five ML models to predict soil moisture trends. Decision Trees achieved an accuracy rate of 99.98%, while Random Forests achieved 99.99%. The integration of these predictive models empowers farmers with actionable insights for precise irrigation scheduling and optimal crop yield optimization. These models provide actionable insights for precise irrigation scheduling and optimal crop yield optimization. Field tests have confirmed the efficacy of this approach, demonstrating significant improvements in irrigation efficiency and subsequent crop yields. Thus, the proposed system represents a substantial advancement in leveraging the synergistic potential of IoT and ML technologies to foster sustainable agricultural practices.","author":[{"family":"Murgod","given":"Sanjana"},{"family":"Kabbur","given":"Tanushree"},{"family":"Matte","given":"Bibijan"},{"family":"Mujumdar","given":"Vaibhav"},{"family":"Raikar","given":"Meenaxi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.procs.2025.03.233","URL":"https://doi.org/10.1016/j.procs.2025.03.233","source":"crossref"},{"id":"doi:10.54314/jssr.v7i4.2330","type":"article-journal","title":"INOVASI SMART FARMING OPTIMALISASI BAWANG MERAH HIDROPONIK BERBASIS IOT DAN MACHINE LEARNING","abstract":"Desa Berastagi memiliki potensi sumber daya alam yang luar biasa, dan masyarakatnya terdiri dari mayoritas petani dan didukung oleh BUMD. Namun, desa ini masih menerapkan pertanian konvensional dan belum menerapkan teknologi seperti IOT untuk meningkatkan produksi hasil pertanian dan ketersediaan pangan lokal untuk menggantikan komoditas pangan impor dengan usaha pertanian cerdas atau smart farming 4.0. Dalam penelitian ini, target yang diharapkan dari M&amp;A adalah untuk menghasilkan lebih banyak hasil pertanian lokal Melalui penggunaan teknologi modern, kualitas dan kuantitas hasil panen ditingkatkan. Selain itu, teknologi ini dapat mengubah pertanian, menghasilkan sistem pertanian pintar. Pertanian cerdas menggabungkan kekuatan perangkat Internet of Things (IoT), sensor, analisis data, dan pembelajaran mesin. Selanjutnya, penulis menganalisis algoritma pembelajaran yang diawasi dengan K-Nearest neighbor digunakan dalam layanan web karena mengungguli algoritma lainnya dengan akurasi 94% dan AUC Score 0,90","author":[{"family":"Putra","given":"Purwa"},{"family":"Julham","given":"Julham"},{"family":"Nurlinda","given":"Nurlinda"},{"family":"Dhitisari","given":"Indri"}],"issued":{"date-parts":[[2025]]},"DOI":"10.54314/jssr.v7i4.2330","URL":"https://doi.org/10.54314/jssr.v7i4.2330","source":"crossref"},{"id":"doi:10.1109/idicaiei61867.2024.10842707","type":"article-journal","title":"IoT-based Smart Solution for Furrow Farming","abstract":"This paper presents the development and implementation of an advanced irrigation system integrating soil moisture sensors and solenoid valves to create a flexible and efficient irrigation framework. The system is designed to detect and respond to specific moisture thresholds in each furrow, ensuring optimal water distribution. When the sensors detect adequate moisture levels, the solenoid valves are deactivated, and the irrigation system shuts down sequentially to prevent water wastage. With farm-wide connectivity, users can remotely monitor, update, and activate the system as needed, allowing for precise control and customization based on varying farm sizes and water requirements. This automated irrigation system promotes sustainable farming practices by optimizing crop growth through precise water management, minimizing wastage, and enhancing overall productivity. This innovative solution empowers farmers with real-time control by bridging the gap between technology and agriculture, leading to more efficient and productive farming operations.","author":[{"family":"Banode","given":"Somesh"},{"family":"Desuwar","given":"Shruti"},{"family":"Tambe","given":"Sujal"},{"family":"Thakre","given":"Prasheel"},{"family":"Kalbande","given":"Kamlesh"},{"family":"Chore","given":"Nitin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/idicaiei61867.2024.10842707","URL":"https://doi.org/10.1109/idicaiei61867.2024.10842707","source":"crossref"},{"id":"doi:10.47134/jees.v3i3.1154","type":"article-journal","title":"Integrating Climate-Smart Strategies into Farming Systems: Implications for Sustainability and Resilience","abstract":"Global agriculture faces the dual challenge of feeding a projected 10 billion people by 2050 while mitigating substantial greenhouse gas emissions and adapting to severe climate vulnerabilities. While Climate-Smart Agriculture (CSA) addresses these pressures, most research examines single practices in isolation, missing the critical interactions of whole-farm integration. This study synthesizes existing evidence on integrating multiple climate-smart strategies, identifies knowledge gaps regarding multi-practice adoption, and evaluates the implications for long-term agricultural sustainability and resilience. A Systematic Literature Review (SLR) was conducted, analyzing 38 peer-reviewed articles, official government reports, and institutional publications published between 2013 and 2026 using thematic analysis. Modern farming requires an integrated approach that combines sustainable intensification, conservation agriculture, agroforestry, and integrated water management. Bundling these practices enhances soil carbon sequestration and buffers against extreme weather. However, adoption is severely restricted by top-down mandates, inadequate extension services, and a massive global climate financing deficit. Technical innovations remain ineffective without localized adaptability and matching socio-economic reforms. Achieving genuine climate resilience demands transitioning from isolated technical fixes to a unified farming system framework. Policymakers must support this shift through innovative carbon market financing, secure land tenure, and decentralized digital extension services, while future research prioritizes multidimensional impact evaluations to ensure permanent sustainability","author":[{"family":"Mamasao","given":"Moseb"},{"family":"Guro","given":"Aldrees"},{"family":"Mama","given":"Rasmiah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.47134/jees.v3i3.1154","URL":"https://doi.org/10.47134/jees.v3i3.1154","source":"crossref"},{"id":"doi:10.2174/9798898812102125030011","type":"article-journal","title":"Smart Cities: Urban Planning and Infrastructure Management","abstract":"The Internet of Things (IoT) can access certain subsets of data for the creation of several digital services, while also integrating a wide range of diverse and heterogeneous end systems in a transparent and seamless manner. This chapter examines innovative solutions to key challenges in smart cities, with an emphasis on ambient noise assessment, air quality monitoring (E-nose system), and smart parking management systems (SPMS). Utilizing servo motors, smartphone apps, and sensors, the SPMS combines Internet of Things technology to maximize parking space distribution, improve user experience, and raise total parking efficiency. An E-nose air quality monitoring system with a sensor array based on the ESP32 can identify gas pollutants, dust, and CO2. Techniques for processing data, such as threshold alarms and median computation, provide precise and prompt air quality monitoring. Additionally, a noise monitoring system with a Gaussian filter and sound level sensors is demonstrated. The proposed analysis demonstrates how IoT-based solutions may be used to enhance sustainability, manage urban infrastructure more effectively, and improve people's quality of life in smart cities.","author":[{"family":"Chaudhary","given":"Aanchal"},{"family":"Pandey","given":"Harsh"},{"family":"Yadav","given":"Ayush"},{"family":"Singh","given":"Vaibhav"},{"family":"Singh","given":"Nishant"},{"family":"Mohapatra","given":"Hitesh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2174/9798898812102125030011","URL":"https://doi.org/10.2174/9798898812102125030011","source":"crossref"},{"id":"doi:10.55606/jpkmi.v5i2.8232","type":"article-journal","title":"Pengembangan Desa Smart Farming Melalui Inovasi Pupuk Organik Cair","abstract":"The liquid organic fertilizer (POC) production training in Ngadirejo Village, Widang Subdistrict, Tuban Regency, was conducted to reduce farmers’ dependence on chemical fertilizers and promote sustainable agriculture. The program actively engaged farmers through lectures, hands-on practice, discussions, and skill evaluations. POC was produced from local organic waste such as water hyacinth, banana corms, moringa leaves, cow urine, and fish meal, fermented for 14–30 days. The final product contains complete nutrients to improve soil fertility and crop productivity while being environmentally friendly. The training results indicated an increase in community knowledge and skills to independently produce POC. This innovation has the potential to support smart farming practices and enhance farmers’ welfare.","author":[{"family":"Aninditatama","given":"Bhaga"},{"family":"Setiawan","given":"Agus"},{"family":"Mutia","given":"Agus"},{"family":"Ramadhan","given":"Firjatullah"},{"family":"Ardiansyah","given":"Anita"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55606/jpkmi.v5i2.8232","URL":"https://doi.org/10.55606/jpkmi.v5i2.8232","source":"crossref"},{"id":"doi:10.71143/r5sbb313","type":"article-journal","title":"Smart Agriculture: Leveraging IoT and Machine Learning for Sustainable Farming","abstract":"The increasing global demand for food, along with the challenges posed by climate change and limited natural resources, calls for a shift from conventional farming to more intelligent, data-centric methods. This study investigates the use of Internet of Things (IoT) devices, cloud computing, and Machine Learning (ML) algorithms to support sustainable agricultural practices. A dataset containing 10,001 entries—including variables such as environmental conditions, soil nutrients, and crop data—was analysed to forecast crop yield. Multiple regression models were tested, with the Random Forest Regressor delivering the highest accuracy at 98.48%, significantly outperforming baseline models like Linear Regression, which scored 76.42%. The integration of cloud services facilitates scalable, real-time data handling and allows efficient processing of sensor data alongside predictive modelling. This research highlights the effectiveness of ensemble learning methods and connected infrastructure in delivering actionable insights for precision agriculture. In order to increase productivity and ensure sustainable resource use, the suggested framework encourages more intelligent choices in areas such as crop planning, soil management, and yield enhancement.","author":[{"family":"Gupta","given":"Vidhi"},{"family":"Singh","given":"Ridhima"},{"family":"Mishra","given":"Divas"},{"family":"Sexena","given":"Pratha"},{"family":"Kapoor","given":"Navnika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71143/r5sbb313","URL":"https://doi.org/10.71143/r5sbb313","source":"crossref"},{"id":"doi:10.21474/jncs01/133","type":"article-journal","title":"EDGE INTELLIGENCE FOR SMART AGRICULTURE: AN ARTIFICIAL INTELLIGENCE FRAMEWORK FOR PRECISION FARMING AND SUSTAINABLE CROP MANAGEMENT","abstract":"The rapid growth of the global population has intensified the demand for sustainable agricultural practices capable of increasing crop productivity while minimizing environmental impact. Conventional farming techniques often rely on manual observation and generalized resource allocation, leading to inefficient utilization of water, fertilizers, pesticides, and energy. Recent advances in Artificial Intelligence (AI), Edge Computing, and the Internet of Things (IoT) have enabled intelligent precision agriculture systems that provide real-time monitoring and autonomous decision-making. Edge Intelligence, which combines AI with distributed edge devices, processes agricultural data closer to its source, reducing communication delays and dependence on cloud infrastructure. This paper presents a comprehensive review of Edge Intelligence applications in smart agriculture and proposes an AI-enabled precision farming framework integrating IoT sensors, unmanned aerial vehicles (UAVs), machine learning, computer vision, and edge computing. The framework aims to improve crop health monitoring, irrigation management, pest detection, soil analysis, and yield prediction while reducing operational costs and environmental impact. The paper also discusses current challenges, security considerations, and future research directions. The findings indicate that Edge Intelligence has significant potential to transform modern agriculture by enabling efficient, scalable, and sustainable farming practices.","author":[{"family":"Brooks","given":"Nathan"},{"family":"Kareem","given":"Aisha"},{"family":"Petrova","given":"Elena"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21474/jncs01/133","URL":"https://doi.org/10.21474/jncs01/133","source":"crossref"},{"id":"doi:10.9734/jeai/2026/v48i94435","type":"article-journal","title":"Organic and Natural Farming for Climate-smart Agriculture","abstract":"Organic and natural farming are increasingly promoted as responses to the coupled crises of climate change, soil degradation and input dependence. Yet their climate-smart credentials are frequently asserted from labels or individual practices rather than evaluated across productivity, adaptation and mitigation, with food-system and distributional effects made explicit. This critical narrative review synthesises peer-reviewed evidence published from 1990 to 5 June 2026, with earlier foundational material retained where necessary. It distinguishes regulated organic agriculture from heterogeneous natural-farming movements and evaluates both through a climate-smart framework. Organic systems generally enhance soil biological activity, on-farm biodiversity and input-use efficiency, and they can improve water regulation and yield stability where rotations, cover crops, organic amendments and diversified habitats are well designed. They also avoid most synthetic nitrogen fertiliser and pesticide inputs. These advantages do not translate automatically into lower climate impacts: average yield gaps, uncertain additionality and permanence of soil carbon, manure-related nitrous oxide, nutrient import dependence and land-use displacement can offset field-level gains. Evidence for natural farming is promising but geographically concentrated, especially in India; recent farm studies report competitive yields, lower purchased-input costs and biodiversity benefits, whereas modelling warns of nutrient constraints during large-scale conversion. The decisive unit of analysis is therefore the farming system in its landscape, dietary and nutrient-cycling context, not the production label. Climate-smart transitions should combine practice bundles with outcome-based measurement, region-specific nutrient budgets, safeguards against leakage, farmer-centred learning and policies that reward public goods without shifting risk to labour-constrained or resource-poor households. The review concludes that organic and natural farming can make substantial contributions to climate-smart agriculture, but only conditionally and as components of broader food-system transformation.","author":[{"family":"Narwal","given":"Kunal"},{"family":"Singh","given":"Dharmender"},{"family":"Sharma","given":"Akanksha"},{"family":"Walia","given":"Akanksha"},{"family":"Yadav","given":"Vicky"},{"family":"Yadav","given":"Kapil"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/jeai/2026/v48i94435","URL":"https://doi.org/10.9734/jeai/2026/v48i94435","source":"crossref"},{"id":"doi:10.1109/icima64861.2025.11073971","type":"article-journal","title":"IoT-Enabled Smart Farming: Harnessing LoRa Technology for Sustainable Agriculture","abstract":"The present-day speed of Internet of Things (IoT) technology development delivers real-time monitoring and decision-making features to precision agriculture. This research seeks to establish an IoT-smart farming system built around LoRa (Long Range) technology to create more efficient resource management while maintaining sustainable farming routines. The LoRaWAN-based sensor network distributed across different topographical areas measured environmental parameters such as soil moisture and temperature, humidity. The obtained sensor data was sent through LoRa gateways to establish real-time processing at a cloud server. The radio signals maintained peak power levels in open agricultural fields yet they faced minor reductions in receiving strength in dense farmland regions. Experimental data revealed that LoRa established reliable communication which delivered -70 dBm average RSSI in open fields coupled with -85 dBm RSSI in dense crop areas as well as achievement of over 90% data transmission success across a 5 km distance using minimal power. Results from experiments proved that LoRa technology establishes dependable long-distance transmission while using minimal energy.","author":[{"family":"Kalaivanan","given":"T"},{"family":"Sethuraman","given":"Priya"},{"family":"Abirami","given":"B"},{"family":"Rajkumar","given":"L"},{"family":"Sathish","given":"A"},{"family":"Ali","given":"Guma"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icima64861.2025.11073971","URL":"https://doi.org/10.1109/icima64861.2025.11073971","source":"crossref"},{"id":"doi:10.38035/jsmd.v3i4.704","type":"article-journal","title":"Smart Coffee Farming: Inovasi IoT dan AI untuk Produktivitas Perkebunan Kopi","abstract":"Sektor pertanian memiliki peran penting dalam perekonomian nasional, khususnya komoditas kopi yang berkembang sejak diperkenalkan oleh Belanda di Indonesia. Di Jawa Barat, perkebunan kopi seperti di Manglayang umumnya dikelola secara tradisional dan bergantung pada kondisi cuaca serta ketersediaan air. Produktivitas kopi sering menurun akibat tiga faktor utama: pengolahan benih yang tidak terkontrol sehingga rentan jamur, distribusi irigasi yang tidak merata saat musim kemarau, serta gangguan hama dari hewan liar. Solusi yang dapat diterapkan adalah pertanian berbasis Internet of Things dan Artificial Intelligence, seperti sensor kelembaban tanah untuk pembibitan, drone untuk pemetaan irigasi, serta sistem pengenalan hewan untuk pengendalian hama. Teknologi ini mampu meningkatkan efisiensi, monitoring, dan produktivitas perkebunan secara berkelanjutan.","author":[{"family":"Risanti","given":"Rini"},{"family":"Amijaya","given":"Hasanah"},{"family":"Oktavia"},{"family":"Fajar","given":"Ganjar"},{"family":"Nurhidayat","given":"Yayat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.38035/jsmd.v3i4.704","URL":"https://doi.org/10.38035/jsmd.v3i4.704","source":"crossref"},{"id":"doi:10.1109/icosec67334.2025.11459642","type":"article-journal","title":"SmartCrop Hub AI-Powered Farming, Crop Planning &amp; Community Platform","abstract":"Agriculture continues to face challenges such as crop diseases, inefficient fertilizer usage, unpredictable weather conditions, and limited access to expert guidance. This paper introduces an AI-powered Smart Farming Assistant that integrates deep learning, machine learning, and large language models via Open Router APIs to provide farmers with real-time decision support. The Smart Farming Assistant acts as a unified platform bringing together multiple modules. Plant disease detection employs image-based models to identify infections, while fertilizer recommendations enhance nutrient utilization and minimize environmental impact. Seasonal crop planning enables farmers to choose the most suitable crops based on soil and climate conditions. A multilingual chatbot provides personalized advice. A farmer community forum encourages knowledge sharing and collaboration among peers. Crop rotation planning helps maintain soil health and support sustainable practices over time. The AI farm guide supplies step-by-step instructions for effective farm management in an easy-to-follow format. Integrated weather forecasting provides insights into potential climate changes. An expense tracker aids in financial monitoring for informed decision-making. Finally, Clerk-based user authentication ensures secure access and personalized services, creating a dependable digital environment for farmers’ operations.","author":[{"family":"Kalaiarasi","given":"P"},{"family":"Junaid","given":"Shaik"},{"family":"Shaikshavali","given":"Mulla"},{"family":"Kumar","given":"Chintapalli"},{"family":"Lavanya","given":"Nusum"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icosec67334.2025.11459642","URL":"https://doi.org/10.1109/icosec67334.2025.11459642","source":"crossref"},{"id":"doi:10.3844/jcssp.2025.2337.2348","type":"article-journal","title":"Assessing the Usability of IoT-Based Smart Farming for Sustainable Organic Agriculture","abstract":"This study evaluates the usability of an IoT-based smart farming system developed to support organic agriculture in Thailand. Many small-scale farmers still spend considerable time manually monitoring soil conditions and managing irrigation, often without access to practical technology. This slows farm operations and makes efficient water use more difficult. To address these challenges, the system was designed with wireless soil-moisture sensors that collect real-time data and automatically control irrigation. It operates in automatic mode during the day and allows manual control at night through a mobile app. The aim is to reduce daily workload, conserve water, and improve decision-making on the farm. Usability was assessed using the System Usability Scale (SUS). Twenty organic farmers in Thailand participated in the evaluation after using the system under real working conditions. The results showed an average SUS score of 86, which is considered excellent and reflects a high level of user satisfaction. The findings suggest that this type of smart farming system can be a valuable tool for small-scale organic farmers. It provides a simple and accessible way to adopt agricultural technology without requiring advanced technical skills. By making irrigation easier and more efficient, the system supports sustainable practices and helps farmers manage their time and resources more effectively.","author":[{"family":"Suttidee","given":"Arisaphat"},{"family":"Sriboonlue","given":"Pankom"},{"family":"Tongnamtiang","given":"Sompoch"},{"family":"Lakkham","given":"Varitha"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3844/jcssp.2025.2337.2348","URL":"https://doi.org/10.3844/jcssp.2025.2337.2348","source":"crossref"},{"id":"doi:10.36227/techrxiv.177138881.15794631/v1","type":"article-journal","title":"Farm-Scale Autonomous Welfare Monitoring in Smart Livestock Farming: A Systematic Review of Robotics and Multimodal AI with an Emphasis on the Lab-to-Farm Deployment Gap","abstract":"While breakthroughs in autonomous robotics and multimodal artificial intelligence (AI) promise continuous, realtime monitoring for precision livestock farming, their practical on-farm application faces significant limitations, revealing a critical \"lab-to-farm\" deployment gap that is rooted in fundamental challenges to the embodied AI community: poor model generalization, simulation-to-real fragility, and the absence of standard validation benchmarks. This review highlights today's state of the art in order to understand and bridge the gap. Using a pool of over 900 reviewed articles, we selected 33 studies from 2021 to 2025 to propose recommendations for adopting farm-scale autonomous monitoring. Our review reveals that 67% of robotics research relies on simulation, with no validation in dynamic farm environments. Based on this finding, we propose a technical roadmap focused on three pillars: 1) the use of Generative AI for data standardization and sim-to-real adaptation; 2) the adoption of a \"Leave-One-Farm-Out\" protocol for rigorous field validation; and 3) the development of Edge-Native systems. Furthermore, we define a Standardized Welfare Insight Schema to facilitate the creation of reproducible datasets, thus enabling the development of truly robust models for livestock welfare.","author":[{"family":"Toure","given":"Francois"},{"family":"Diallo","given":"Abdoulaye"},{"family":"Boukadoum","given":"Mounir"}],"issued":{"date-parts":[[2026]]},"DOI":"10.36227/techrxiv.177138881.15794631/v1","URL":"https://doi.org/10.36227/techrxiv.177138881.15794631/v1","source":"crossref"},{"id":"doi:10.70882/josrar.2025.v2i3.57","type":"article-journal","title":"Smart Farming for Groundnut Yield Prediction Using IoT and Machine Learning","abstract":"The integration of IoT in agriculture has revolutionized crop production by enhancing productivity, quality, and efficiency while reducing labor costs and boosting farmer income. IoT sensors provide precise data on environmental, soil, and plant factors, critical for predicting crop yields. In this study, groundnut crops were cultivated in 20 pots and monitored using IoT devices over 120 days, generating 480 data instances. Parameters like temperature, soil moisture, and nutrients (nitrogen, phosphorus, potassium) were measured to track growth metrics. Machine learning models Multi-Layer Perceptron (MLP), K-Nearest Neighbors (KNN), and Random Forest (RF) were developed using bagging techniques to predict yield and model growth rates based on NPK levels. Model performance was evaluated using R-squared, MAE, RMSE, and RMSLE metrics. For yield prediction, KNN outperformed RF and MLP with the highest R-squared (0.87), lowest MAE (2.1033), and lowest RMSE (2.0119), while MLP performed worst. Conversely, in modeling growth rates influenced by NPK, MLP excelled with the highest R-squared (0.52), lowest MAE (1.3499), MSE (2.7220), RMSE (1.6498), and an exceptionally low RMSLE (0.0024). Overall, KNN was the top performer for yield prediction, followed by RF and MLP, whereas MLP was superior for growth rate predictions. This highlights the potential of IoT and machine learning in advancing agricultural intelligence.","author":[{"family":"Bala","given":"Abdullahi"},{"family":"Olanrewaju","given":"Oyenike"},{"family":"Echobu","given":"Faith"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70882/josrar.2025.v2i3.57","URL":"https://doi.org/10.70882/josrar.2025.v2i3.57","source":"crossref"},{"id":"doi:10.3390/proceedings2026134058","type":"article-journal","title":"FIWARE-Powered Smart Farming: Integrating Sensor Networks for Sustainable Soil Management","abstract":"Digital transformation in agriculture addresses key challenges such as climate change, water shortages, and sustainable production. Precision agriculture technologies rely on the Internet of Things (IoT) sensor networks, analytics, and automated systems to manage resources efficiently and increase productivity. Fragmented infrastructures and vendor-specific platforms lead to unintegrated data silos that obstruct regional solutions. This paper will emphasize FIWARE, an open-source, standard-based platform that can be integrated with existing agricultural sensors in municipalities or regions. FIWARE takes all these disparate sensors (soil probes, weather stations, and irrigation meters) and integrates them into a single real-time information system, providing a set of decision support tools to the user to facilitate adaptive irrigation. Case studies show the benefits of FIWARE, including water savings, reduced runoff, better decision-making, and improved climate resilience.","author":[{"family":"Hitiris","given":"Christos"},{"family":"Gkola","given":"Cleopatra"},{"family":"Vergados","given":"Dimitrios"},{"family":"Karamerou","given":"Vasiliki"},{"family":"Michalas","given":"Angelos"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/proceedings2026134058","URL":"https://doi.org/10.3390/proceedings2026134058","source":"crossref"},{"id":"doi:10.1109/iciscois62701.2026.11447556","type":"article-journal","title":"MobileNetV2 Model for Multiclass Tomato Disease Prediction Using Blended Dataset for Smart Farming","abstract":"Agriculture remains a cornerstone of Namibia's economy, yet small-scale crop farmers continue to face significant productivity losses due to late or inaccurate diagnosis of plant diseases. Tomato, a major crop in the country's semi-arid regions, is highly susceptible to fungal and bacterial infections that spread rapidly under local climatic conditions. Manual inspection is labor-intensive, subjective, and ineffective for largescale monitoring. In the literature, many studies have used highquality datasets to train deep learning models. However, these datasets are not real-time and rarely reflect Namibia's specific atmospheric and climatic conditions. To address this challenge, this study uses a blended dataset combining the PlantVillage Tomato Leaf Dataset from Kaggle with real-time images collected from small farms in oshana region of Namibia. The study further investigates a resource-efficient and reliable deep learning model, namely MobileNetV2, for multiclass Tomato plant disease classification. The performance of the proposed MobileNetV2 model is compared with VGG16 and ResNet50 architectures, all trained and fine-tuned using the blended dataset. Their performance is evaluated based on overall prediction accuracy and computational efficiency. Experimental results demonstrate that the proposed MobileNetV2-based multiclass classification model achieved the highest accuracy of over 90 % with significantly lower computational resources. The proposed method showed rapid inference that can enable mobile deployment for on-field crop monitoring.","author":[{"family":"Anatolia","given":"Iita"},{"family":"Sesham","given":"Srinu"},{"family":"Abisai","given":"Mateus"},{"family":"Gideon","given":"Kenneth"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iciscois62701.2026.11447556","URL":"https://doi.org/10.1109/iciscois62701.2026.11447556","source":"crossref"},{"id":"doi:10.9734/ajaar/2026/v26i3715","type":"article-journal","title":"Agriculture 5.0: AI-Enabled Smart Farming with Advanced Monitoring  and Pest Management","abstract":"Agriculture 5.0 is a paradigm shift whereby modern technologies (robotics, artificial intelligence (AI), and the Internet of Things (IoT) are utilised to improve productivity, sustainability, and resiliency in various agricultural domains. This is an integrated solution that not only focuses on traditional crop production but also on horticulture, livestock, fisheries, and agroforestry systems, which allows management of a farm in an integrated manner. Integration of intelligent sensors, autonomous machines, and data-oriented decision support provides the possibility to monitor the state of soil, water, and weather in real-time, which will result in increased efficiency of resource utilisation. Also, AI-based imaging and machine learning algorithms make it possible to detect insect pests and plant diseases early and precisely to support precision-based interventions and mitigate the need to use chemical inputs. Climate-smart practices also include minimising environmental effects and protecting biodiversity, as well as improving adaptive capacity to climate variability, which are also promoted by Agriculture 5.0. The integration of digital technologies and connected platforms will guarantee the availability of data integration and predictive analytics, as well as informed decision-making on farm and regional levels. In addition, automation and robotics minimise labour reliance and enhance efficient and consistent operations in farms. Agriculture 5.0 can bring transformations in the current farming sector despite the hurdles associated with it, including the cost of initial investment, complications of data management, and the use of technical expertise. It is also bringing about the possibilities of sustainable, efficient, and resilient agricultural systems by combining technological innovation with ecological principles that will address the food security challenges of the world.","author":[{"family":"Das","given":"Nilotpal"},{"family":"Mandal","given":"Argha"},{"family":"Sarkar","given":"Meghna"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/ajaar/2026/v26i3715","URL":"https://doi.org/10.9734/ajaar/2026/v26i3715","source":"crossref"},{"id":"doi:10.31289/agr.v7i2.8480","type":"article-journal","title":"Respon Perkembangan Buah pada Tanaman Semangka terhadap Pemberian Asam Humat sebagai Dasar Budidaya Smart Farming","abstract":"Kecukupan nutrisi dalam tanah menjadi faktor penting dalam mendapatkan hasil panen terbaik. Penerapan metode smart farming membantu mengidentifikasi kondisi tanah yang berpengaruh pada kebutuhan nutrisi tanaman. Tujuan dari penelitian pendahuluan ini adalah mengetahui respon perkembangan buah terhadap dosis penambahan asam humat, sehingga dapat dijadikan acuan dasar untuk data penerapan metode smart farming pada budidaya tanaman semangka di lahan sub optimal Desa Kumendung. Penelitian menggunakan faktor pemberian asam humat empat konsentrasi berbeda (0, 2, 4, 6, dan 8 g/L) dengan varietas semangka Amara dan Seri F1. Pengamatan meliputi pengukuran terhadap tinggi tanaman (21 hst), berat buah (kg), volume buah (cm3) dan nilai total kandungan gula (Brix). Hasil penelitian menunjukkan bahwa pemberian asam humat secara signifikan berpengaruh terhadap berat dan total gula buah. Perbedaan dosis tidak berpengaruh signifikan terhadap volume dan tinggi tanaman, ditunjukkan dengan hasil uji ANOVA nilai R square respon tinggi tanaman, berat, volume dan total gula buah secara berturut-turut adalah 0,231, 0,644, 0,383 dan 0,547. Angka tersebut menjelaskan bahwa peningkatan dosis asam humat tidak memberikan perubahan nyata pada hasil panen buah semangka. Dengan demikian, penggunaan asam humat sebagai suplemen hara tanah dapat diminimalisir dengan pemberian dosis paling rendahnya yaitu 2 g/L. Kata kunci: asam humat, smart farming, semangka","author":[{"family":"Sakinah","given":"Ni'mawati"},{"family":"Bariyyah","given":"Khoirul"},{"family":"Hadi","given":"Ahmad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31289/agr.v7i2.8480","URL":"https://doi.org/10.31289/agr.v7i2.8480","source":"crossref"},{"id":"doi:10.1109/icwt66752.2025.11181816","type":"article-journal","title":"IoT-Based Smart Water Quality Monitoring System for Sustainable Koi Fish Farming","abstract":"Temperature and pH levels are critical parameters for assessing water quality in fish ponds, particularly in koi fish ponds. Koi fish are ornamental fish with high market prices, and maintaining optimal water quality is crucial for their successful cultivation. When the water quality is ideal, the fish can grow and thrive at their best. This system enables koi fish breeders to easily monitor and control water quality, allowing real-time adjustments through a smartphone to maintain the water within specific parameters.After testing, the system can automatically regulate temperature and pH levels if they deviate from the set parameters. Additionally, during sensor calibration, the temperature and pH sensors showed average errors of 0.96% and 1.08%, respectively. The average communication delay via MQTT was 0.7 seconds.","author":[{"family":"Pramudita","given":"Resa"},{"family":"Abdallah","given":"Zidan"},{"family":"Iglesias","given":"Andre"},{"family":"Rizqulloh","given":"Muhammad"},{"family":"Sartika","given":"Nike"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icwt66752.2025.11181816","URL":"https://doi.org/10.1109/icwt66752.2025.11181816","source":"crossref"},{"id":"doi:10.1016/j.procs.2026.07.161","type":"article-journal","title":"Analyzing the level of adoption of smart farming on potential users using extended UTAUT","abstract":"Smart farming integrates technology with agricultural knowledge to enhance efficiency and sustainability. However, adoption remains low in areas like Surabaya and Kediri due to limited digital literacy, infrastructure, and lack of youth involvement. This study analyzes factors affecting smart farming adoption using the extended UTAUT model. A quantitative approach was applied with 180 respondents, and data were analyzed using Structural Equation Modelling (SEM). Results show that effort expectancy, social influence, facilitating conditions, and intention to use significantly influence adoption. The findings offer theoretical insight and practical recommendations to support inclusive adoption among conventional farmers and emerging smart farming communities.","author":[{"family":"Sakti","given":"Mohammad"},{"family":"Hidayati","given":"Sri"},{"family":"Hidayat","given":"Alifiansyah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.procs.2026.07.161","URL":"https://doi.org/10.1016/j.procs.2026.07.161","source":"crossref"},{"id":"doi:10.35631/jistm.937023","type":"article-journal","title":"THE EFFECT OF INTEGRATING IOT SYSTEM IN THE SMART FARMING OF RED ONION (ALLIUM CEPA)","abstract":"Smart farming is pivotal in advancing agriculture, offering innovative solutions to optimize crop yields and monitor plant growth. This study proposes the use of the Internet of Things (IoT) in smart farming to determine the optimal watering interval for red onions (Allium cepa). The system incorporates Arduino technology, utilizing a water pump and humidity sensor for automated irrigation. Three watering schedules were tested: 8, 12, and 18 hours. The results indicate that an 8-hour interval yielded the highest growth (3.5 ± 1.20 cm) within three weeks, followed by 12 hours (3.4 ± 1.33 cm) and 18 hours (2.0 ± 0.67 cm). Factors such as soil type, nutrition, and environmental conditions may influence these outcomes. Future work, including greenhouse cultivation, is suggested to enhance data precision and agricultural productivity.","author":[{"family":"Chong","given":"Yu"},{"family":"Suhaimi","given":"Mimi"},{"family":"Adnan","given":"Nurulakidah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35631/jistm.937023","URL":"https://doi.org/10.35631/jistm.937023","source":"crossref"},{"id":"doi:10.35760/ik.2025.v30i3.87","type":"article-journal","title":"Smart Agriculture Prototype : An IoT - Controlled System for Lightning and Nutrient Management in Dragon Fruit Farming","abstract":"Perkembangan teknologi mendorong sektor pertanian untuk beradaptasi menuju sistem yang lebih cerdas, efisien, dan terintegrasi. Buah naga salah satu komoditas bernilai ekonomi tinggi, membutuhkan pengelolaan intensitas cahaya, kelembapan dan pemberian nutrisi secara teratur agar dapat tumbuh optimal. Penelitian ini merancang prototipe sistem otomatis berbasis Internet of Things (IoT) yang berfungsi mengendalikan penerangan dan pemberian nutrisi. Sistem dikembangkan menggunakan mikrokontroler ESP32-S3 yang terhubung dengan sensor BH1750 untuk pengukuran intensitas cahaya serta modul RTC DS3231 untuk penjadwalan pemberian nutrisi. Seluruh komponen dikendalikan melalui relay dan dapat dipantau secara real-time menggunakan Telegram Bot. Hasil pengujian menunjukkan bahwa lampu otomatis menyala pada intensitas cahaya 26,08 lux dan mati pada 265,60 lux, sedangkan pompa nutrisi bekerja otomatis setiap dua hari sekali pada pukul 09.14 selama 5 detik. Data pemantauan dan status perangkat berhasil dikirim secara real-time melalui Telegram, menunjukkan bahwa sistem ini efektif dalam meningkatkan efisiensi dan akurasi perawatan tanaman buah naga.","author":[{"family":"Marliza","given":"Nana"},{"family":"Hasim","given":"Nursabilah"},{"family":"Arifatno","given":"Deny"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35760/ik.2025.v30i3.87","URL":"https://doi.org/10.35760/ik.2025.v30i3.87","source":"crossref"},{"id":"doi:10.35791/cocos.v15i4.57637","type":"article-journal","title":"PENGARUH SMART FARMING TERHADAP KADAR HARA TANAH PADA LAHAN PERTANIAN DAMPINGAN PT. TIRTA INVESTAMA  PABRIK AIRMADIDI DI DESA TUMALUNTUNG","abstract":"Permasalahan ketersediaan pangan seperti kelangkaan bahan pokok pangan menjadi persoalan yang sering diperbincangkan. Hal tersebut berkaitan dengan problem atas isu ketahanan pangan di ranah nasional maupun global. Sebagai kunci utama ketahanan pangan, sektor pertanian di Indonesia perlu ditingkatkan agar ketersediaan den kualitas pangan terjaga. Teknis penerapan sistem sertifikasi proses produksi pertanian yang menggunakan teknologi maju ramah lingkungan dan berkelanjutan telah digaungkan oleh pemerintah maka untuk meningkatkan pengelolaan dan produksi pertanian masa kini dengan perubahan teknologi ke arah transformasi digital dari segi pengembangan maupun pemanfaatan teknologi, Smart Farming dipilih sebagai alternatif pada produk inovasi teknologi pertanian berguna untuk memudahkan petani dalam melakukan pekerjaan yang lebih efisien, terukur, dan terintegrasi. Hasil penelitian menunjukkan bahwa kegiatan dari Sistem Smart Farming dapat membantu mencukupi kebutuhan hara tanah sehingga sejalan dengan harapan menanggulangi kelangkaan pangan. Kata kunci: Ketahanan pangan, Smart farming, Unsur hara, Sistem irigasi cerdas, Teknologi pertanian ABSTRACT The problem of food availability, such as the scarcity of basic food ingredients, is an issue that is often discussed. This is related to the problem of food security issues in the national and global realm. As the main key to food security, the agricultural sector in Indonesia needs to be improved so that food availability and quality are maintained. The technical implementation of a certification system for agricultural production processes that uses advanced environmentally friendly and sustainable technology has been proposed by the government, so to improve current agricultural management and production with technological changes towards digital transformation in terms of development and use of technology, Smart Farming was chosen as an alternative product Agricultural technology innovation is useful for making it easier for farmers to carry out work that is more efficient, measurable and integrated. This research proves that activities from the smart farming system can help meet the nutrient needs of the soil so that it is in line with the hope of overcoming food scarcity. Keywords: Food security, Smart farming, Nutrients, Smart irrigation systems, Agricultural technology","author":[{"family":"Kamil","given":"Wisye"},{"family":"Luntungan","given":"Emmy"},{"family":"Tindage","given":"Jorly"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35791/cocos.v15i4.57637","URL":"https://doi.org/10.35791/cocos.v15i4.57637","source":"crossref"},{"id":"doi:10.1115/1.4071725","type":"article-journal","title":"Integration of Smart Components in Poultry Farming: A Critical Review on Lighting, Sensing, and Automation Technologies","abstract":"Abstract While the world population is increasing faster than ever, food consumption and demand are also increasing. To meet this fast-growing food demand, poultry and livestock industries, as well as the food processing industry, are expanding rapidly. In addition to the food industry, overall industrialization is advancing with state-of-the-art technologies, particularly artificial intelligence. With recent advancements in science and technology, every sector is adopting state-of-the-art technologies to improve performance at an affordable cost. Different sectors of agriculture are embracing the remarkable technological advancements offered by science. While these technological advancements offer innovations and opportunities, they also continue to produce new challenges. For instance, the extended industrialization of the modern era demands a continuous, uninterrupted supply of power, requiring energy-efficient, sustainable technologies so that maximum technological advantage can be achieved with the least energy use. This article focuses solely on modernizing poultry farming and explores the existing technologies for poultry lighting, sensing, and automation, highlighting their shortcomings. First, recent innovations in lighting technology and the effect of lighting on poultry birds are reviewed, followed by an analysis of poultry-specific lighting technologies along with numerous lighting fixtures, their unique features, and performance parameters. In the latter part, various sensing and automation technologies currently used in the poultry industry have been elaborated. Moreover, the technological gaps and future needs for poultry lighting, sensing, and automation are explicitly presented.","author":[{"family":"Islam","given":"Md"},{"family":"Arik","given":"Mehmet"},{"family":"Rahman","given":"Md"},{"family":"Rehman","given":"Tanzeel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1115/1.4071725","URL":"https://doi.org/10.1115/1.4071725","source":"crossref"},{"id":"doi:10.1109/csitss67709.2025.11295857","type":"article-journal","title":"AgriTech: A Multi-Functional UGV for Smart and Sustainable Farming","abstract":"Agriculture remains a primary source of livelihood for nearly 50% of India's population, contributing significantly to the nation's GDP. However, traditional farming methods are labor-intensive, time-consuming, and increasingly inefficient due to labor shortages. This paper presents the design and development of “AgriTech,” a multi-functional Unmanned Ground Vehicle (UGV) engineered to enhance agricultural productivity through automation. The UGV performs essential tasks such as ploughing, seed sowing, pesticide spraying, and grass cutting, while also offering real-time video surveillance capabilities. Controlled remotely via mobile application using the Blynk platform and powered by a lead-acid battery, the system integrates key components including a Node-MCU microcontroller, relay modules, and an ESP32 camera. The UGV allows farmers to monitor and operate the system in both autonomous and manual modes, improving efficiency and reducing manual labor requirements. The proposed solution addresses key challenges in modern agriculture by promoting sustainability, optimizing operational time, and reducing costs, thus advancing toward a smart and resilient farming future.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/csitss67709.2025.11295857","URL":"https://doi.org/10.1109/csitss67709.2025.11295857","source":"crossref"},{"id":"doi:10.1109/icic68054.2025.11309530","type":"article-journal","title":"Ensemble Voting for Robust Model Predictive Control in a Greenhouse Smart Farming IoT","abstract":"Smart Farming, based on the Internet of Things (IoT), has emerged as a key sector in the digital transformation of agriculture. However, several previous studies have highlighted the research challenges that robustness is an issue in achieving precision agriculture in smart farming. The purpose objective of this study is to develop a predictive model of actuator status using the ensemble voting method, which integrates four classification algorithms: random forest (RF), k-nearest neighbor (KNN), gradient boosting (GB), and extreme gradient boosting (XGBoost), to enchance the accuracy and consistency of predictive control system application. We extracted agricultural data from the IoT system, which covers more than 37,000 data points and 13 environmental parameters, obtained from Kaggle. We used the Pearson correlation coefficient (PCC) to explain and simplify the complex relationships between sensors and actuators in an IoT smart agriculture greenhouse. The test results showed that the model performed better than the individual models, with an accuracy value of 0.9973 and the lowest standard deviation. These findings indicate that the ensemble application provides accurate predictions for the status of fan actuators, irrigation systems, and water storage pumps. We conclude that the soft voting method in an ensemble can improve the performance of certain models and strengthen the generalization ability of complex Internet of Things (IoT) systems.","author":[{"family":"Septian","given":"Ardika"},{"family":"Putrada","given":"Aji"},{"family":"Wicaksono","given":"Ryan"},{"family":"Reskyadita","given":"Feddy"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icic68054.2025.11309530","URL":"https://doi.org/10.1109/icic68054.2025.11309530","source":"crossref"},{"id":"doi:10.36227/techrxiv.174440944.41197873/v1","type":"article-journal","title":"Internet of Things-Based Smart Precision Farming in Soilless Agriculture: Opportunities and Challenges for Global Food Security","abstract":"The rapid growth of the global population and the continuous decline in cultivable land pose significant threats to food security. This challenge worsens as climate change further reduces the availability of farmland. Soilless agriculture, such as hydroponics, aeroponics, and aquaponics, offers a sustainable solution by enabling efficient crop cultivation in controlled environments. The integration of the Internet of Things (IoT) with smart precision farming improves resource efficiency, automates environmental control, and ensures stable and high-yield crop production. IoT-enabled smart farming systems utilize real-time monitoring, data-driven decision-making, and automation to optimize water and nutrient usage while minimizing human intervention. This paper aims to explore the opportunities and challenges of IoT-based soilless farming. It also highlights its role in sustainable agriculture, urban farming, and global food security. These advanced farming methods ensure greater productivity, resource conservation, and year-round cultivation. However, these methods also face challenges such as high initial investment, technological dependency, and energy consumption. Through a comprehensive study, bibliometric analysis, and comparative analysis, this research highlights current trends and research gaps. It also outlines future directions for researchers, policymakers, and industry stakeholders to drive innovation and scalability in IoT-driven soilless agriculture. By highlighting the benefits of vertical farming and Controlled Environment Agriculture (CEA)-enabled soilless techniques, this paper supports informed decision-making to address food security challenges and promote sustainable agricultural innovations.","author":[{"family":"Dutta","given":"Monica"},{"family":"Gupta","given":"Deepali"},{"family":"Tharewal","given":"Sumeg"},{"family":"Goyal","given":"Deep"},{"family":"Sandhu","given":"Jasminder"},{"family":"Kaur","given":"Manjit"},{"family":"Alzubi","given":"Ahmad"},{"family":"Alanazi","given":"Jazem"}],"issued":{"date-parts":[[2025]]},"DOI":"10.36227/techrxiv.174440944.41197873/v1","URL":"https://doi.org/10.36227/techrxiv.174440944.41197873/v1","source":"crossref"},{"id":"doi:10.1109/iccit68739.2025.11490357","type":"article-journal","title":"Smart Farming for Bangladesh: An IoT and Machine Learning-Based Crop Advisory System","abstract":"Agriculture is vital to Bangladesh's economy, yet farmers face challenges in selecting suitable crops, fertilizers, and understanding soil types due to the need for specialized expertise. This paper presents an IoT and machine learning-based Crop Advisory System to address these issues by automating crop recommendation, fertilizer prediction, and soil type classification. Using an ESP32 microcontroller, the system collects real-time data on environmental and soil parameters (NPK, temperature, humidity, rainfall, pH, soil texture, moisture) via sensors. Six machine learning models-Logistic Regression, K-Nearest Neighbors, Support Vector Classifier, Naïve Bayes, Decision Tree, and Random Forest-are trained on Kaggle datasets, with preprocessing and VGG16 feature extraction for soil type classification. In addition to the initial train-test evaluation, model robustness was validated using 5 -fold stratified cross-validation, with results reported as mean ± standard deviation. The crop recommendation task achieved consistently high cross-validated performance (e.g., RF:$0.9959 \\pm 0.0027$; NB:$0.9945 \\pm 0.0018$), while Logistic Regression and ensemble methods remained strong for fertilizer prediction (e.g., RF:$0.9821 \\pm 0.0264$). Soil type classification showed moderate but stable performance (LR: 0.660$\\pm 0.009$), reflecting dataset limitations. An Android application, integrated with Firebase for real-time data retrieval, provides user-friendly interfaces for farmers to access predictions. This system enhances agricultural decision-making, offering a scalable solution for precision farming in Bangladesh.","author":[{"family":"Akther","given":"Tasmin"},{"family":"Uddin","given":"Md"},{"family":"Rahman","given":"Mohammad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccit68739.2025.11490357","URL":"https://doi.org/10.1109/iccit68739.2025.11490357","source":"crossref"},{"id":"doi:10.1109/iccces62661.2026.11436654","type":"article-journal","title":"IoT-Enabled Distributed Smart Farming System using Lora","abstract":"This paper presents an IoT-enabled distributed smart farming system that enhances agricultural productivity through automation, real-time monitoring, and data-driven decision-making. The system integrates multi-depth soil moisture, temperature, humidity, pH, nutrient (NPK), and environmental sensors with LoRa-based long-range communication to provide reliable, low-power connectivity across large farms. A central Arduino Mega acts as the controller, aggregating data from distributed nodes and executing rule-based logic for irrigation, safety, and environmental management. Data is transmitted via GSM to a cloud dashboard, where farmers can monitor field conditions, analyze historical trends, and remotely control actuators. Automated irrigation ensures precise water delivery, reducing wastage while promoting root health. Safety modules monitor electrical parameters and environmental hazards, providing rapid fail-safe responses. Field deployment demonstrated >95% communication reliability over 2 km and up to 45% water savings compared to timer-based irrigation. The system's modular, solar-powered design ensures scalability, sustainability, and adaptability. Future integration of machine learning models, such as LSTM networks, will enable predictive irrigation scheduling and proactive equipment maintenance.","author":[{"family":"Naik","given":"Pradeep"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccces62661.2026.11436654","URL":"https://doi.org/10.1109/iccces62661.2026.11436654","source":"crossref"},{"id":"doi:10.1109/ictest64710.2025.11042280","type":"article-journal","title":"Smart Farming: Improving Disease Detection in Pepper Leaves Using AI and Image Processing","abstract":"Smart farming leverages advanced technologies to enhance crop monitoring, disease detection, and precision agriculture, ensuring higher productivity and sustainability. Early identification of plant diseases is crucial for minimizing yield loss and optimizing intervention strategies. This study presents an AI-driven disease detection system for pepper plants, integrating image processing and machine learning techniques to enable automated crop health assessment. The proposed framework begins with data collection from agricultural fields or institutional repositories. Captured images undergo pre-processing to enhance contrast and reduce noise, followed by feature extraction using Discrete Wavelet Transform with Haar wavelet compression. Extracted features are analyzed using an Artificial Neural Network classifier, employing the back-propagation algorithm to differentiate between healthy and diseased leaves. This AI-powered approach enhances disease identification accuracy, supporting real-time monitoring and smart decision-making for farmers. By integrating machine learning with precision agriculture, the system contributes to efficient farm management, reduced chemical usage, and sustainable farming practices, paving the way for next-generation smart farming solutions.","author":[{"family":"Koushik","given":"Varun"},{"family":"Sahu","given":"Umesh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ictest64710.2025.11042280","URL":"https://doi.org/10.1109/ictest64710.2025.11042280","source":"crossref"},{"id":"doi:10.1201/9781003685364-62","type":"article-journal","title":"Towards smarter farming: advanced neural architectures for leaf disease identification","abstract":"Improve plant leaf disease classification with the use of user-friendly apps and advanced deep learning models. We include the Xception model into the SE-SK-CapResNet architecture, which merges CapsNet and ResNet for strong feature extraction and classification, to enhance the accuracy of diagnosis on a variety of plant leaf disease datasets. The YOLO series of models enables rapid identification of abnormalities in agricultural operations in real-time. To improve accessibility and safeguard sensitive agricultural data, we built a web-based front-end app with Flask and implemented secure user authentication. The improved system is a trustworthy and easily available tool for agricultural disease control, according to experimental data, as it performs better at classification and localization.","author":[{"family":"Murty","given":"Pilla"},{"family":"Manasa","given":"V"},{"family":"Bhavyasri","given":"T"},{"family":"Rajesh","given":"S"},{"family":"Hussain","given":"S"},{"family":"Haswanth","given":"K"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003685364-62","URL":"https://doi.org/10.1201/9781003685364-62","source":"crossref"},{"id":"doi:10.34151/jurtek.v18i1.5229","type":"article-journal","title":"Sistem Smart Farming Cabai dengan Rule-Based System Node-RED dan Berbasis Internet of Things","abstract":"This study aims to design and implement a Smart farming system based on the Internet of Things (IoT) using a Rule-Based System (RBS) approach for the cultivation of Japlak chili at Dafrot Farm, Tasikmalaya Regency. The research adopts a Research and Development (R&amp;D) method consisting of literature review, needs analysis, system design, hardware and software development, as well as system testing and evaluation. The system is developed using an ESP32 microcontroller and equipped with DHT11, DS18B20, YL-69 soil moisture sensor, and MH-RD rain sensor. Node-RED serves as the core platform for data processing and rule-based decision-making using IF-THEN logic. Data is transmitted via the MQTT protocol and monitored in real-time through the IoT MQTT Panel application. The research findings indicate that the system can accurately monitor environmental parameters and provide appropriate automatic responses to certain conditions, such as low soil moisture or rainfall. The water pump is activated automatically when soil moisture drops below 60% under clear weather conditions and is deactivated when moisture exceeds 68% or rain is detected. In addition to the automatic mode, manual control is also available via the dashboard and mobile application. The system demonstrated stable and responsive performance during field observation.","author":[{"family":"Fajriyati","given":"Azkiya"},{"family":"Sugeng","given":"Ajeng"},{"family":"Rizqulloh","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.34151/jurtek.v18i1.5229","URL":"https://doi.org/10.34151/jurtek.v18i1.5229","source":"crossref"},{"id":"doi:10.52436/1.jutif.2024.5.5.2728","type":"article-journal","title":"HORTICULTURE SMART FARMING FOR ENHANCED EFFICIENCY IN INDUSTRY 4.0 PERFORMANCE","abstract":"Chili peppers and papayas are important horticultural commodities in Indonesia with high economic value. To enhance productivity and efficiency in cultivating these crops, the application of Smart Farming technology is crucial. This study evaluates the use of image processing and artificial intelligence in the pre-harvest and post-harvest processes for chili peppers and papayas. For the pre-harvest process, data from 50 images of ripe chili peppers on the plant were used. The counting of ripe chilies was performed using HSV color segmentation with two masking processes, resulting in an average accuracy of 82.58%. In the post-harvest phase, 30 images of papayas, consisting of 10 images for each ripeness category—unripe, half-ripe, and ripe—were used. Papaya ripeness classification was carried out using the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel and parameters C = 10 and γ = 10-3, achieving perfect classification accuracy of 100% for all categories. This study underscores the significant potential of Industry 4.0 technologies in enhancing agricultural practices and efficiency in the horticultural sector, providing important contributions to optimizing chili pepper and papaya production.","author":[{"family":"Arifin","given":"Nurhikma"},{"family":"Insani","given":"Chairi"},{"family":"Milasari","given":"Milasari"},{"family":"Rasyid","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.52436/1.jutif.2024.5.5.2728","URL":"https://doi.org/10.52436/1.jutif.2024.5.5.2728","source":"crossref"},{"id":"doi:10.26877/e-dimas.v17i1.24953","type":"article-journal","title":"Optimalisasi Potensi Kelompok Wanita Tani Indah Lestari Sumberjo melalui Edukasi Smart Farming Berbasis AI","abstract":"Kelompok Wanita Tani (KWT) Indah Lestari menghadapi berbagai kendala dalam mengelola kegiatan pertanian, antara lain rendahnya literasi teknologi, keterbatasan sarana digital, dan minimnya pendampingan teknis dalam penerapan sistem pertanian modern. Kondisi ini menghambat peningkatan produktivitas dan efisiensi pertanian di tingkat rumah tangga, terutama dalam menghadapi tantangan perubahan iklim dan kebutuhan akan sistem pertanian yang lebih adaptif. Sebagai solusi, dilaksanakan kegiatan pengabdian masyarakat yang berfokus pada edukasi Smart Farming berbasis Artificial Intelligence (AI). Program ini bertujuan meningkatkan literasi teknologi dan keterampilan digital anggota KWT dalam memanfaatkan aplikasi AI untuk deteksi dini hama dan penyakit tanaman, monitoring pertumbuhan, serta rekomendasi pemupukan sesuai kebutuhan tanaman lokal seperti kangkung, sawi, padi, bayam, jagung, dan cabai. Kegiatan dilaksanakan pada bulan September 2025 di Desa Sumberjo, Kecamatan Polman, Kabupaten Polewali Mandar, dengan melibatkan 20 anggota KWT Indah Lestari dan penyuluh pertanian kecamatan sebagai pendamping. Metode meliputi presentasi interaktif, pelatihan praktik penggunaan aplikasi AI sederhana, serta evaluasi partisipatif untuk menilai peningkatan pemahaman peserta.Hasil menunjukkan peningkatan signifikan: lebih dari 90% peserta memahami konsep Smart Farming, 85% mampu menjelaskan fungsi aplikasi AI, dan 80% yakin dapat menggunakannya secara mandiri. Selain itu, 95% peserta menyadari manfaat teknologi pertanian, dan 75% bersedia mengadopsi inovasi digital secara bertahap. Untuk keberlanjutan dan peningkatan dampak kegiatan, disarankan dilakukan pendampingan rutin guna memperkuat kemampuan peserta dalam menggunakan aplikasi AI. Materi pelatihan dapat diperluas pada pengolahan data tanaman dan optimasi pemupukan berbasis AI, serta penerapan teknologi secara bertahap pada lahan kecil agar manfaatnya berkelanjutan dan nyata bagi petani.","author":[{"family":"Arifin","given":"Nurhikma"},{"family":"Milasari","given":"Milasari"},{"family":"Astinawaty","given":"Astinawaty"}],"issued":{"date-parts":[[2026]]},"DOI":"10.26877/e-dimas.v17i1.24953","URL":"https://doi.org/10.26877/e-dimas.v17i1.24953","source":"crossref"},{"id":"doi:10.1109/icmsci67830.2026.11469231","type":"article-journal","title":"A CNN-Based Smart Farming Robot for Plant Disease Detection and Crop Management","abstract":"Agribusiness, the backbone of many countries' economy, has many challenges posed by plant diseases that may compromise the yield and quality of the produce. The disease detection approaches that have been in use are time-consuming and inaccurate as they depend on human vision. The paper describes the design and implementation of an autonomous smart farming robot for the detection of chilli plant diseases. The proposed method uses a hybrid architecture for image classification with the inclusion of an InceptionResNetV2 model for the detection of diseases in chilli plants. The idea is to use pictures of leaves to figure out if a chilli plant has a disease. We are looking at five kinds of diseases in chilli plants: Healthy, Leaf Curl, Leaf Spot, Whitefly and Yellowish diseases. We are using a system that combines different ways of looking at pictures to see if a chilli plant is sick. This system uses something called an InceptionResNetV2 model to look at the leaves and find diseases in chilli plants. Using leaf image classification for chilli plants will really help us find out what is wrong, with the plant. This method will make it a lot easier to detect leaf diseases in chilli plants. Experimental results for 50 epochs indicate that the approach is highly precise and would be an optimal solution for the detection of leaf diseases in chilli plants.","author":[{"family":"Suseendhar","given":"P"},{"family":"Saravanan","given":"S"},{"family":"Ganapathy","given":"BM"},{"family":"Ramkumar","given":"A"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icmsci67830.2026.11469231","URL":"https://doi.org/10.1109/icmsci67830.2026.11469231","source":"crossref"},{"id":"doi:10.55824/jpm.v3i5.448","type":"article-journal","title":"Pengembangan Budidaya Pakcoy dengan Metode Smart Farming Kelompok Pertanian Gandasuli Gumilir, Komunitas Dampingan PT. SBI Pabrik Cilacap","abstract":"Smart farming merupakan pendekatan pertanian modern yang memanfaatkan teknologi informasi dan komunikasi untuk meningkatkan efisiensi dan hasil produksi pertanian. Smart farming 4.0 yang berbasis kecerdasan buatan akan mendorong dan meningkatkan penghasilan petani pakcoy gandasuli rw 14 gumilir. Kegiatan ini bertujuan untuk mengkaji penerapan metode smart farming pada budidaya pakcoy (Brassica rapa), khususnya pada komunitas dampingan PT Solusi Bangun Indonesia Pabrik Cilacap yaitu kelompok pertanian Gandasuli Gumilir. Dalam penelitian ini kami menganalisis berbagai aspek budidaya pakcoy mulai dari pemilihan benih, penanaman, perawatan, hingga panen, serta bagaimana teknologi smart farming dapat diterapkan untuk mengoptimalkan setiap tahapan tersebut. Petani dapat bercocok tanam tanpa bergantung pada musim melainkan melalui mekanisasi. Proses penanaman hingga pemanenan dapat dilakukan secara akurat mulai dari tenaga kerja, waktu tanam hingga proses pemanenan. Beberapa teknologi smart farming seperti blockchain yang dapat memfasilitasi ketertelusuran rantai pasok produk pertanian untuk pertanian off farm modern, agri drone sprayer (drone penyemprotan pestisida dan pupuk cair), drone surveilans (drone untuk pemetaan lahan), sensor tanah dan cuaca, sistem irigasi cerdas (irigasi pintar), Ruang Pertanian. Beragamnya tingkat pendidikan petani, umur petani dan minat masyarakat terhadap pertanian, serta mahalnya peralatan teknologi smart farming menjadi kendala terbesar bagi petani dalam menerapkan smart farming. Kementerian pertanian telah melaksanakan pilot project penerapan smart farming di beberapa lokasi di Indonesia. Kementerian Pertanian juga perlu mengambil peran dengan membuat roadmap smart farming. Proyek Strategis Pemerintah pada tahun 2020 hingga 2024 melalui food estate yang dibangun bersama korporasi petani dapat mendukung penerapan smart farming secara masif.","author":[{"family":"Prastya","given":"Andika"},{"family":"Fauzi","given":"Muhammad"},{"family":"Nurochman","given":"Budi"},{"family":"Prasadi","given":"Oto"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55824/jpm.v3i5.448","URL":"https://doi.org/10.55824/jpm.v3i5.448","source":"crossref"},{"id":"doi:10.1109/itechsecom64750.2025.11307642","type":"article-journal","title":"An IoT Precision Farmbot for Smart Turmeric Farming","abstract":"This paper outlines the design and development of the Intelligent IoT Agriculture Solution - Turmeric Precision FarmBot, a cyber-physical system for the optimization of turmeric cultivation. The system architecture includes an ESP32 microcontroller as the main processing element and connects the same with digital temperature-humidity sensors (DHT22), capacitive moisture probes for soil moisture measurement, and a smoke detector module. Motorized movement and actuation are powered by rechargeable lithiumion batteries. A double-layered communication system is employed, consisting of local real-time monitoring and actuation enabled by the Blynk IoT platform and remote access enabled by an embedded HTTP web server running on the ESP32. The system allows for closed-loop irrigation scheduling based on sensor inputs, autonomous locomotion for field access, and safety handling by hazard perception. Experimental validation in controlled turmeric fields shows a water-saving effectiveness of up to 35%, a reduction in manual labor by up to 40%, and pre-emergent hazard reporting with a latency of under 3 seconds. The proposed FarmBot presents an extensible framework to precision farming with IoTtechnology by effectively integrating low-cost embedded devices and cloud-aided decision support towards sustainability, resource effectiveness, and operational ruggedness in turmeric cultivation.","author":[{"family":"Radhika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/itechsecom64750.2025.11307642","URL":"https://doi.org/10.1109/itechsecom64750.2025.11307642","source":"crossref"},{"id":"doi:10.33395/sinkron.v9i1.14255","type":"article-journal","title":"Embedded Smart Farming System  for Soil and Hydroponic Planting Media  Based on The Internet of Things","abstract":"Smart agricultural technology by applying the internet of things (IoT) purposes to make farmers' work more efficient due to the automation system and assist farmers in monitoring the condition of their agricultural land. The focus of discussion in this research is the application of smart agriculture system technology that uses the concept of embedded systems for soil and hydroponic planting media. This system applies an automation system for water irrigation and fertilizer irrigation using four tanks, namely a water source, a water irrigation tank, a fertilizer tank, and a water circulation system in hydroponics. The system is also equipped with weather monitoring based on temperature, rainfall, and light intensity. Other parameters contained in this system are soil pH, water pH, TDS, fertilizer availability, and irrigation pump status. The monitoring system based on the Android application displays all parameters and the status of the devices used.","author":[{"family":"Rifka","given":"Silfia"},{"family":"Ramiati","given":"Ramiati"},{"family":"Dewi","given":"Ratna"},{"family":"Khair","given":"Ummul"},{"family":"Setiawan","given":"Herry"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33395/sinkron.v9i1.14255","URL":"https://doi.org/10.33395/sinkron.v9i1.14255","source":"crossref"},{"id":"doi:10.3389/fsufs.2025.1687446","type":"article-journal","title":"Driving mechanism of Internet use on vegetable farmers’ smart farming adoption","abstract":"Smart farming (SF) is an important driving force for promoting the development of agricultural modernization. Internet use plays a key role in promoting farmers’ adoption of SF. Based on survey data from 603 rural households in Jiangxi Province, this study employs a binary Probit model and a mediating effect model to explore the impact and mechanism of Internet use on farmers’ adoption behavior of SF. The findings show that (1) Internet use significantly promotes farmers’ adoption of SF, and the conclusion still holds after conducting robustness tests through replacing the explained variable, subsample regression, and a placebo test. (2) Risk attitude and economic cost play a mediating role in the promotion of farmers’ adoption of SF by Internet use, with the proportions of their mediating effects accounting for 8.56 and 6.81%, respectively. Government incentives play a positive moderating role in the process of Internet use, affecting farmers’ adoption behavior of SF. (3) Internet use is more effective in significantly promoting the adoption of SF among farmers in younger age groups and with higher education levels. Based on this, the government should strengthen Internet infrastructure construction in major vegetable-producing areas to lower the thresholds for vegetable farmers’ Internet usage. It should conduct SF-related training via Internet platforms to help farmers improve their risk attitudes and reduce their economic costs, and implement government subsidy policies linked to Internet usage and SF. Meanwhile, it should provide support for innovation pilots integrating Internet usage and SF to younger and highly educated vegetable farmers, and develop simplified Internet usage tools for elderly and less educated vegetable farmers—all so as to highlight the promotional role of Internet usage in vegetable farmers’ adoption of SF.","author":[{"family":"Wu","given":"Zanzan"},{"family":"Chen","given":"Chao"},{"family":"Xu","given":"Mingyu"},{"family":"Li","given":"Lianying"},{"family":"Hu","given":"Weinan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fsufs.2025.1687446","URL":"https://doi.org/10.3389/fsufs.2025.1687446","source":"crossref"},{"id":"doi:10.1109/autocom64127.2025.10956508","type":"article-journal","title":"Enabling Smart Farming with IoT and Sensor Networks: Case Studies from Developing Countries","abstract":"Smart Farming with IOT and Sensor Networks is an advanced technology that enables traditional farmers to reduce waste and introduce intelligence in measuring the productivity of crops. The papers show how deploying IOT and sensor networks has contributed to enhancing productivity, reducing costs, and sustainability through a few successful case studies spanning regions under development. IOT and Sensor Networks for Agriculture: Low-cost sensors and communication devices with data analytics help collect and analyze real-time information from farms. Along with weather forecasts, soil analysis, and other useful insights, it helps farmers take technocratic actions, eventually allowing them to use their resources better. IOT and sensor networks are particularly useful in developing countries, where small-scale farmers often cannot access modern technologies and information. Farmers using IOT systems for drip irrigation can use their mobile phones to control watering remotely and thus increase water efficiency significantly, as was the case in India. Leveraging sensor networks to advance precision farming has successfully grown crops with higher yields and less fertilizer use in Africa. Using IOT and sensor networks in the application layer can significantly enhance food security, diminish ecological footprint, and foster sustainable agricultural practices, particularly in developing countries. The world has a later taste of the benefits that would eventuate in one dark-haired roommate becoming somewhat more bearded and less university student-like than ever before; there is still much research to come on this technology, which could change the face (not beard)of global agriculture - improving livelihoods for millions upon million small-scale farmers.","author":[{"family":"Garg","given":"Mohan"},{"family":"Parui","given":"Souvik"},{"family":"Kandhari","given":"Harsimrat"},{"family":"David","given":"Roshita"},{"family":"Naval","given":"Preeti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/autocom64127.2025.10956508","URL":"https://doi.org/10.1109/autocom64127.2025.10956508","source":"crossref"},{"id":"doi:10.26562/ijirae.2025.v1209.02","type":"article-journal","title":"Smart Crop Selection: A Machine Learning Approach for Seasonal Farming","abstract":"Agriculture is the backbone of the economy, but unpredictable climate conditions pose significant challenges to crop production. Our Smart Crop Selection System addresses this issue by analyzing soil and climate data to provide farmers with accurate, seasonal recommendations. Leveraging Random Forest and XGBoost algorithms, the system considers key parameters like soil nutrients, pH, temperature, humidity, and rainfall. A user-friendly web interface offers interactive visualizations, enabling farmers to make informed decisions. Real-time model training ensures continuous improvement, adapting to new data and climate patterns. Our system outperforms traditional approaches, empowering farmers with reliable, data-driven insights to optimize crop yields. By providing accurate crop recommendations, our system helps farmers adapt to changing climate conditions, enhancing agricultural productivity and sustainability. This innovative approach has the potential to transform agricultural decision-making, promoting sustainable farming practices and improving farmers' livelihoods. With its robust performance and user-centric design, our system is poised to make a significant impact in the agricultural sector, supporting farmers in making data-driven decisions for better crop yields and resource allocation. This leads to improved productivity and sustainability.","author":[{"family":"Shafi","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.26562/ijirae.2025.v1209.02","URL":"https://doi.org/10.26562/ijirae.2025.v1209.02","source":"crossref"},{"id":"doi:10.1109/etcom66606.2025.11437117","type":"article-journal","title":"Digital Twin for Predictive Modelling in Smart Farming Based on Ensemble Neural Network Algorithm","abstract":"The convergence of Digital Twin (DT), Internet of Things (IoT), and Artificial Intelligence (AI) presents a transformative opportunity for precision agriculture. Although promising, the application of virtual replicas of digital twins that enable bidirectional data flow between physical and digital entities remains nascent in this domain. This work proposes a novel DT framework for smart irrigation that uses a cloudbased EnergyPlus architecture and the Decision Support System for Agricultural Technology Transfer (DSSAT). The core of this framework is an advanced predictive model that utilizes embedded real-time sensor data (soil, weather, and crop) from agricultural fields. The model performs two critical functions: univariate time series forecasting of rainfall and multivariate forecasting of quarterly crop yield. A hybrid AI architecture, combining Gated Recurrent Units (GRU) with Bidirectional Long Short-Term Memory (BiLSTM) networks (GRU-BiLSTM), is developed to achieve high fidelity predictions. Empirical evaluation confirms the superiority of the model over existing benchmarks, achieving an accuracy of 98%, a precision of 97%, a recall of 99%, and an F1 score of 99%. This research validates the efficacy of integrating a sophisticated AI forecasting model within a DT environment, offering a powerful decision support tool for farmers to optimize irrigation strategies and improve agricultural productivity.","author":[{"family":"Bharatula","given":"Sita"},{"family":"Prasad","given":"PB"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/etcom66606.2025.11437117","URL":"https://doi.org/10.1109/etcom66606.2025.11437117","source":"crossref"},{"id":"doi:10.9734/jabb/2025/v28i82712","type":"article-journal","title":"Smart Irrigation Systems Using the Internet of Things: Applications in Farming Systems","abstract":"Water management in agriculture has been transformed by smart irrigation systems that use the Internet of Things (IoT) to maximize resource use and boost crop yields. IoT-based irrigation, which reduces waste and improves sustainability in the face of growing water scarcity, combines sensors, actuators and real-time data analytics to deliver accurate water flow. The use of IoT in agriculture is reviewed in this paper, which also covers AI-driven decision-making algorithms and communication technologies like LoRa, Zigbee and Wi-Fi. In agriculture, IoT has been widely employed in agriculture to enable better farming and redefine conventional practices. Some of the necessary applications include monitoring crops, monitoring livestock, automation of the supply of water through real-time data, promotion of optimal water consumption and wastage minimization. Furthermore, increased agricultural yields, cost savings and water conservation are just a few benefits of using IoT in irrigation systems. Research also claimed that when compared to traditional methods, IoT-based irrigation systems can save up to 30% on water usage. IoT-based irrigation has drawbacks despite its benefits, including costly upfront costs, complicated technology and cyber security threats. The use of self-powered sensors, AI-powered predictive irrigation and blockchain-enhanced data security are some of the upcoming trends. Smart irrigation systems have the ability to transform precision agriculture and guarantee both environmental preservation and food security by removing implementation obstacles. Future research should focus on enhancing interoperability among IoT devices, improving decision-making algorithms and developing cost-effective solutions for small-scale farmers. With continuous innovation and widespread adoption, IoT-driven smart irrigation has the potential to address global food security concerns while preserving water resources, creating a more sustainable and technologically advanced agriculture industry.","author":[{"family":"Ojha","given":"Rohit"},{"family":"Manvir"},{"family":"Fayaz","given":"Asma"},{"family":"Kaundal","given":"Munish"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jabb/2025/v28i82712","URL":"https://doi.org/10.9734/jabb/2025/v28i82712","source":"crossref"},{"id":"doi:10.3390/su17188254","type":"article-journal","title":"Life Cycle Assessment of an Industrial Aquaponics System in Chongqing, China: Environmental Performance and Optimization Strategies","abstract":"Industrial aquaponics systems (IAS) integrate aquaculture and hydroponics in a closed-loop design, offering a promising solution to sustainable protein production. However, their environmental performance remains insufficiently quantified, particularly in China. This study presents one of the first life cycle assessments (LCAs) of a large-scale IAS in Chongqing, based on operational data from a smart facility producing ~114,700 kg of largemouth bass and ~86,500 kg of vegetables annually. The analysis adopts a cradle-to-gate scope with a functional unit of 1 kg of marketable fish and employs the CML-IA method to assess ten midpoint impact categories. Results indicate that fish feed and electricity consumption are the dominant contributors to environmental burdens, particularly in global warming potential, eutrophication, and human toxicity. Scenario and sensitivity analyses reveal that reducing fishmeal content in feed and switching from coal-based electricity to renewable sources can significantly lower impacts. Comparisons with conventional protein sources demonstrate that aquaponics fish outperform pork and beef in most environmental categories when impacts are normalized by nutritional value. This study highlights key environmental hotspots and proposes viable optimization strategies, offering practical insights into the design and operation of climate-smart aquaponics systems. The findings provide a science-based reference for policymakers and practitioners aiming to promote resource-efficient food systems in urban China.","author":[{"family":"Guan","given":"Youbang"},{"family":"Liu","given":"Lian"},{"family":"Chen","given":"Yingyi"},{"family":"Liu","given":"Lirong"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/su17188254","URL":"https://doi.org/10.3390/su17188254","source":"crossref"},{"id":"doi:10.35138/paspalum.v13i2.906","type":"article-journal","title":"Analisis Kelayakan Teknis Dan Finansial Usahatani Paprika Sistem Smart Farming Di P4S Lembang Agri Kabupaten Bandung Barat","abstract":"The Lembang Agri Independent Agriculture and Rural Training Center (P4S) which oversees farmer groups in Pengkolan Village, Cikidang Village, Lembang District, West Bandung Regency produces peppers, including using hydroponic methods supported by a smart farming system. Farming can be said to be sustainable if it is technically and financially feasible. This study aims to analyze technical feasibility, analyze production costs, revenue, income and financial feasibility of pepper farming. The method used in this study is an analytical descriptive quantitative method with qualitative supporting data. Respondents were taken by purposive sampling method. The types of data used are primary data and secondary data. The technical variables of farming are measured by the Guttman scale. Technical feasibility data analysis is descriptive and categorical. Costs and revenues are processed based on the formula of receipts and revenues. Financial feasibility analysis of data processed using R/C Ratio, BEP, and ROI. The results of the research show that the technical feasibility of the location, technology and layout in practice have mostly met the minimum standards of pepper farming with a feasible category (value of 93.54%) technically. The total production cost is IDR 104,730,417/season. Revenue of IDR 360,000,000. Revenue of IDR 255,269,583. R/C Ratio obtained is 3. BEP Production is 1,987 kg/season &gt; average production is 12,000 kg/season. BEP Price IDR 8,727/kg &gt; average selling price IDR 30,000/kg. BEP Revenue is IDR 59,612,255 &gt; average revenue is IDR 360,000,000. Return of investment (ROI) is 35% &gt; from the Bank's interest rate of 6%. Thus, pepper farming in P4S Lembang Agri is profitable and worth pursuing.","author":[{"family":"Lafifauzi","given":"Syufa"},{"family":"Sulandjari","given":"Kuswarini"},{"family":"Mariyani","given":"Siti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.35138/paspalum.v13i2.906","URL":"https://doi.org/10.35138/paspalum.v13i2.906","source":"crossref"},{"id":"doi:10.2174/9798898815462126010005","type":"article-journal","title":"Aerophonic and Hydrophonic Systems using IoT","abstract":"This article presents an IoT-based monitoring and control system for an aeroponic garden. The proposed system is integrated with an Android application, named Aeroponics Monitor, which enables users to remotely monitor plant conditions and control irrigation schedules. Through the application, users can determine when to water the plants and adjust the frequency of monitoring, thereby supporting efficient water usage and precise crop management. This idea for an IoT device has four levels. The app layer, the fog layer, the cloud layer, and the device layer are them. The sensors in the device layer collect information about the things that are being tracked. After that, the fog layer works with the data and sends it to the Firebase and Thingspeak servers. Thingspeak looks at the data from the things being watched in the yard using its IoT analysis tools in the cloud. The test results showed that a lot less water was used than with standard methods, and the vitamin supply was very accurate. This smart farming technology has a lot of potential to make sure everyone has enough food and to help the economy grow in the long run by using less water and better managing nutrients. There are a lot of things that make it work. To make the high-tech small-scale hydroponic system, low-cost parts and sensors were used. This lets the growing of green veggies and seeds be monitored from afar, and the process can be automated. Other factors, like the temperature and electrical conductivity of the nutrition solution, were outside the acceptable ranges. 75% of the cabbage seeds germinated in the experiment that was set up at the start. One of the best things about the suggested hydroponic system is how easy it is to set up and handle. The developed system supports remote monitoring and control without imposing stringent requirements on the user’s technical expertise. Its intuitive design enables users with varying levels of experience to operate the system effectively. Furthermore, the small-scale hydroponic system that was designed and implemented offers a practical solution for small- and medium-sized vegetable growers, facilitating year-round indoor crop production under controlled conditions.","author":[{"family":"Ashokkumar","given":"N"},{"family":"Bharathi","given":"M"},{"family":"Madhu","given":"GC"},{"family":"Nagarajan","given":"P"},{"family":"Balakumaresan","given":"R"},{"family":"Basha","given":"Shaik"},{"family":"Selvaperumal","given":"Sathish"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898815462126010005","URL":"https://doi.org/10.2174/9798898815462126010005","source":"crossref"},{"id":"doi:10.1109/temsconlatam65810.2025.11238529","type":"article-journal","title":"IoT-Driven Smart Management in Broiler Farming: Simulation of Remote Sensing and Control Systems","abstract":"Parameter monitoring and control systems play a key role in industry because they support automation, helping to increase productivity and make better use of resources. These improvements focus on managing environmental factors and handling the complex interactions between multiple inputs and outputs in production. This paper presents an automation system for broiler management, developed through a simulation scenario that uses sensor networks and embedded systems. The system builds a transmission network to monitor and control broiler temperature and feeding by using Internet of Things (IoT) tools, along with a dashboard and a cloud-based database to track progress in broiler operations. This work is expected to guide stakeholders and entrepreneurs in the animal production sector by promoting sustainable practices through simple and low-cost automation. The goal is for them to scale and integrate these recommendations into their existing operations, leading to more efficient decision-making at the management level.","author":[{"family":"Suarez","given":"Sandra"},{"family":"Padilla","given":"VS"},{"family":"Ponguillo-Intriago","given":"Ronald"},{"family":"Espinal","given":"Albert"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/temsconlatam65810.2025.11238529","URL":"https://doi.org/10.1109/temsconlatam65810.2025.11238529","source":"crossref"},{"id":"doi:10.1109/iementech65115.2025.10959551","type":"article-journal","title":"A Brief Review on Smart Farming Technologies for Precision Agriculture","abstract":"Farming sustains the global population, currently over 7.9 billion people. As the population continues to grow, the importance of farming becomes even more critical. This review explores the latest advancements in smart farming technologies and their application in precision agriculture. Smart farming integrates cutting-edge technologies such as the Internet of Things (IoT), artificial intelligence (AI), and big data analytics to enhance agricultural productivity and sustainability. By leveraging these technologies, precision agriculture aims to optimize resource use, reduce environmental impact, and increase crop yields. Various research groups are working on these cutting-edge technologies which is briefly reviewed and discussed here.","author":[{"family":"Raj","given":"Rishav"},{"family":"Ghosh","given":"Arijit"},{"family":"Pal","given":"Amar"},{"family":"Kundu","given":"Soumik"},{"family":"Karmakar","given":"Samit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iementech65115.2025.10959551","URL":"https://doi.org/10.1109/iementech65115.2025.10959551","source":"crossref"},{"id":"doi:10.1109/icaiss68683.2026.11526222","type":"article-journal","title":"Smart Farming: Eggplant Leaf Disease Detection through Fine-Tuned DenseNet201 Deep Learning Model","abstract":"In the majority of developing countries, farmers use eggplant that is readily infected by different diseases that affect leaves. The early and correct detection of these diseases will help in provision of food, sustainable agriculture and cost reduction. A precise fine-tuning of the DenseNet201 and a deep learning methodology allowed scholars to differentiate the eggplant leaves state of a healthy plant, insect pest disease, leaf spot disease, mosaic virus disease, small leaf disease, white mold disease and wilt disease. Overall, 3552 images of open-source Kaggle platform were selected and divided into the following subsets: training, validation and testing: 70, 15 and 15 percent. The given system demonstrated a 86% hit rate with test data and a high score in precision, recall and F1scores on most of the classes. The analysis of the confusion matrices and the training curves show clearly that there is no error rate or the model is firm. Artificial intelligence in plant pathology can help find a faster solution to plant diseases, responsible eating patterns, and fight climate change and hunger. The study satisfies the objectives of sustainable development by contributing to the effectiveness of the farming process, by facilitating the new ideas in the process of finding the solutions and effective use of the resources. The recommended method can enable farmers and other agriculturalists to identify diseases at an earlier age, shift toward low-pesticide practices and achieve greater yields.","author":[{"family":"Kaur","given":"Khushdeep"},{"family":"Kaur","given":"Husanpreet"},{"family":"Kaur","given":"Avneet"},{"family":"Gupta","given":"Varun"},{"family":"Tomar","given":"Shobhit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaiss68683.2026.11526222","URL":"https://doi.org/10.1109/icaiss68683.2026.11526222","source":"crossref"},{"id":"doi:10.1109/icetems66917.2026.11469712","type":"article-journal","title":"AI-Based Crop Disease Prediction and Smart Farming Application","abstract":"AI-based agricultural platform that offers multilingual and data-supported help for sustainable agriculture practices for Indian farmers. The application uses latest technology advancements, which include an API for robust identification of crop diseases for 23 key crops and over 288 crop diseases, a Google Gemini API for accessing market prices, a Hybrid AI model for personalized agricultural recommendations for crops, a Soil Monitoring System, and a Scheme Fetcher for accessing schemes based on location. The application allows Indian farmers to cross the language and literacy barrier because it offers regionbased guidance written in Marathi, Hindi, and English languages. The intelligent and location-aware assistance in this agricultural support solution guaratees its scalability, offline functionality, and improvement as a comprehensive agricultural support system for modernization in Indian farming.","author":[{"family":"Gawande","given":"Prachi"},{"family":"Dhenge","given":"Mohit"},{"family":"Meshram","given":"Servesh"},{"family":"Gajbhiye","given":"Sanket"},{"family":"Pokalwar","given":"Shreyas"},{"family":"Giradkar","given":"Lokesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icetems66917.2026.11469712","URL":"https://doi.org/10.1109/icetems66917.2026.11469712","source":"crossref"},{"id":"doi:10.22266/ijies2025.1231.59","type":"article-journal","title":"A Modular Intelligent Resource Architecture: Enhancing Energy Efficiency in Smart Farming with Edge–Cloud Fusion","abstract":"Smart greenhouse systems utilizing IoT technologies for real-time monitoring and autonomous control have emerged as a response to increasing climate variability.However, conventional architectures suffer from scalability limits, high latency, and excessive energy use.This study introduces a novel Edge Fusion 3-Layer architecture that integrates localized anomaly detection via Probabilistic Neural Networks (PNNs) at the edge with cloud-based decision-making through Adaptive Neuro-Fuzzy Inference Systems (ANFIS).The proposed model employs eventdriven communication to transmit only critical anomalies, thereby conserving energy and improving responsiveness.Simulation results demonstrate that Edge Fusion reduces total energy consumption by up to 45% (809 J at 1000 nodes) and achieves client-and server-side delays below 30 ms, validated through two-way ANOVA with strong explanatory power (R² = 0.775 for energy, R² = 0.748 for server delay).Lifetime analysis further confirms extended sensor operation, particularly at smaller deployment scales.Compared with recent state-of-the-art approaches, including Hybrid PSO + Fuzzy Clustering and ANFIS + DBO optimization, Edge Fusion delivers statistically robust improvements in energy efficiency and responsiveness.These results highlight the framework's potential as a scalable and sustainable solution for smart agriculture in resource-constrained environments.","author":[{"family":"Amiroh","given":"Khodijah"},{"family":"Priyambodo","given":"Tri"},{"family":"Lelono","given":"Danang"}],"issued":{"date-parts":[[2025]]},"DOI":"10.22266/ijies2025.1231.59","URL":"https://doi.org/10.22266/ijies2025.1231.59","source":"crossref"},{"id":"doi:10.21203/rs.3.rs-9781395/v1","type":"article-journal","title":"Multisource Grapevine Phenology Dataset for Smart Farming and AI Modeling","abstract":"Abstract Artificial Intelligence and Machine Learning rely on large, high-quality datasets for accurate and robust models, yet data scarcity remains a major challenge, especially in smart farming. Phenology modeling, a key application, studies how plant biological events relate to climate and seasons. Accurate phenology models improve crop quality, support climate adaptation, and guide decisions such as pesticide use and harvesting, enhancing environmental and economic sustainability. However, agricultural data are highly diverse and heterogeneous, complicating model development. This study presents a proposed georeferenced dataset for Machine Learning-based grapevine phenology prediction across 3 Protected Designations of Origin in Aragón, Spain. Developed by a multidisciplinary team, the dataset combines 9 datasets from 8 sources (including meteorological time series, field phenology observations, and Copernicus Sentinel-2 multispectral imagery) covering the period 2016–2022. It supports both physical and Machine Learning-based phenology modeling and facilitates knowledge extraction in agronomy and plant biology. Its relevance lies in its comprehensive scope, the inclusion of 9 phenological stages, and a rigorous methodology ensuring reproducibility. This framework enables the creation of similar datasets for other regions or crops, advancing smart farming through scalable, data-driven solutions. The open publication of the code further supports this objective. We further anticipate its potential contribution to developing foundation models as well as to the creation of new knowledge in biology and agronomy.","author":[{"family":"Pérez","given":"Francisco"},{"family":"Hoyo-Alonso","given":"Rafael"},{"family":"Labata-Lezaún","given":"Gorka"},{"family":"Barriuso-Vargas","given":"Juan"},{"family":"Ilarri-Artigas","given":"Sergio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21203/rs.3.rs-9781395/v1","URL":"https://doi.org/10.21203/rs.3.rs-9781395/v1","source":"europepmc"},{"id":"doi:10.20944/preprints202501.2285.v1","type":"manuscript","title":"Smart Farming Technologies for Sustainable Agriculture: A Case Study of a Mediterranean Aromatic Farm","abstract":"Consumer interest in medicinal and aromatic herbs is on the rise, with buyers increasingly concerned about the microbiological quality of nutraceutical and aromatic plants. The use of Unmanned Aerial Vehicles (UAVs) and sensor technology allows for high-resolution crop monitoring, particularly in the production of rosemary and sage in Grotte (Italy), Agrigento District. The aim of this study is to evaluate the efficacy of UAV-based time series remote sensing data and multimodal data fusion using RGB and multispectral sensors in rosemary and sage harvesting time individuation and the microbiological quality of these nutraceutical and aromatic plants before and after an innovative an sustainable drying process. The multispectral data were acquired with a DJI multispectral camera mounted on the Unmanned Aerial Vehicle (UAV) Phantom 4. The use of drones in the aromatic plants crops can lead to improved efficiency, productivity, and profitability for farmers and businesses. Italian producers follow strict hygiene regulations to reduce bacterial contamination, particularly during the crucial drying process. A rapid drying method at low temperature using a dryer powered by a photovoltaic Renewable Energy Source (RES) helps preserve the quality of the plants. Real-time monitoring of the drying process is enabled through a system based on wireless sensor networks (WSN), providing valuable data on moisture content, drying rates, and microbial stability. Overall, the innovative use of drones, sensor technology, and renewable energy sources in the production of aromatic herbs like rosemary and sage holds great potential for enhancing crop quality, shelf life, and overall sustainability in the chain food industry.","author":[{"family":"Greco","given":"Carlo"},{"family":"Gaglio","given":"Raimondo"},{"family":"Settanni","given":"Luca"},{"family":"Sciurba","given":"Lino"},{"family":"Ciulla","given":"Salvatore"},{"family":"Orlando","given":"Santo"},{"family":"Mammano","given":"Michele"}],"issued":{"date-parts":[[2025]]},"DOI":"10.20944/preprints202501.2285.v1","URL":"https://doi.org/10.20944/preprints202501.2285.v1","source":"europepmc"},{"id":"doi:10.5281/zenodo.19683153","type":"article-journal","title":"SMART AGRICULTURE: AN INTELLIGENT DECISION SUPPORT SYSTEM WITH ADVANCED MACHINE LEARNING AND EDGE AI","abstract":"Smart agriculture integrates modern digital technologies to enhance farming productivity and sustainability. This paper presents an updated Intelligent Machine Learning-based Decision Support System (IML-DSS) that incorporates Edge AI and Federated Learning for real-time agricultural decision-making. The system predicts crop yield, detects plant diseases, and optimizes resource utilization using multi-source data such as IoT sensors, satellite imagery, and climate databases. Advanced models including ensemble learning, transformer-based architectures, and explainable AI are utilized to process heterogeneous agricultural data. Edge-cloud integration enables low-latency processing and scalability. Experimental validation using recent datasets shows improved prediction accuracy, faster decision-making, reduced environmental impact, and enhanced farmer trust through interpretability. The proposed system contributes significantly to sustainable and data-driven agriculture.","author":[{"family":"Reddy","given":"Mr"},{"family":"Muhlisa","given":"Bolbekova"},{"family":"Farangiz","given":"Anvarova"},{"family":"Sevara","given":"Kamolova"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19683153","URL":"https://doi.org/10.5281/zenodo.19683153","source":"datacite"},{"id":"doi:10.5281/zenodo.19683152","type":"article-journal","title":"SMART AGRICULTURE: AN INTELLIGENT DECISION SUPPORT SYSTEM WITH ADVANCED MACHINE LEARNING AND EDGE AI","abstract":"Smart agriculture integrates modern digital technologies to enhance farming productivity and sustainability. This paper presents an updated Intelligent Machine Learning-based Decision Support System (IML-DSS) that incorporates Edge AI and Federated Learning for real-time agricultural decision-making. The system predicts crop yield, detects plant diseases, and optimizes resource utilization using multi-source data such as IoT sensors, satellite imagery, and climate databases. Advanced models including ensemble learning, transformer-based architectures, and explainable AI are utilized to process heterogeneous agricultural data. Edge-cloud integration enables low-latency processing and scalability. Experimental validation using recent datasets shows improved prediction accuracy, faster decision-making, reduced environmental impact, and enhanced farmer trust through interpretability. The proposed system contributes significantly to sustainable and data-driven agriculture.","author":[{"family":"Reddy","given":"Mr"},{"family":"Muhlisa","given":"Bolbekova"},{"family":"Farangiz","given":"Anvarova"},{"family":"Sevara","given":"Kamolova"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19683152","URL":"https://doi.org/10.5281/zenodo.19683152","source":"datacite"},{"id":"doi:10.5281/zenodo.19314584","type":"article-journal","title":"Intercropping for Climate-Smart Agriculture: Mitigating Risks and Enhancing Resilience","abstract":"Intercropping has become a viable concept in climate-smart agriculture as it is perceived to assist farmers in dealing with production risks in a climate of uncertainty. Farmers can decrease the susceptibility that comes with monocropping by planting two or more crops in the same field, and this will enhance the stability of the main output of the farms. This paper explains the role of intercropping in resilience, including increased yield stability, increased resource-use efficiency, soil health, and ecological control of pests and diseases. It also emphasises how crop diversity is effective to buffer drought, moisture stress and market fluctuations, particularly in the smallholder farming system. Based on recent studies, the article discusses the idea of intercropping as being a situational approach, rather than one that can be universally applied, but rather one that works best when there is a fit between crop combinations, planting systems, and managerial actions to local agroecological parameters. The discussion also highlights that intercropping may be considered to serve people with more climate-smart objectives as it is combined with proper management of soil, nutrients, and extensions. On the whole, the article proposes that intercropping belongs to the most viable and biologically efficient channels of establishing resilience, downside risk reduction, and more stable agricultural production in the face of climate change.","author":[{"family":"Roy","given":"Moumita"},{"family":"Dutta","given":"Subham"},{"family":"Mondal","given":"Debasmita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19314584","URL":"https://doi.org/10.5281/zenodo.19314584","source":"datacite"},{"id":"doi:10.5281/zenodo.19314585","type":"article-journal","title":"Intercropping for Climate-Smart Agriculture: Mitigating Risks and Enhancing Resilience","abstract":"Intercropping has become a viable concept in climate-smart agriculture as it is perceived to assist farmers in dealing with production risks in a climate of uncertainty. Farmers can decrease the susceptibility that comes with monocropping by planting two or more crops in the same field, and this will enhance the stability of the main output of the farms. This paper explains the role of intercropping in resilience, including increased yield stability, increased resource-use efficiency, soil health, and ecological control of pests and diseases. It also emphasises how crop diversity is effective to buffer drought, moisture stress and market fluctuations, particularly in the smallholder farming system. Based on recent studies, the article discusses the idea of intercropping as being a situational approach, rather than one that can be universally applied, but rather one that works best when there is a fit between crop combinations, planting systems, and managerial actions to local agroecological parameters. The discussion also highlights that intercropping may be considered to serve people with more climate-smart objectives as it is combined with proper management of soil, nutrients, and extensions. On the whole, the article proposes that intercropping belongs to the most viable and biologically efficient channels of establishing resilience, downside risk reduction, and more stable agricultural production in the face of climate change.","author":[{"family":"Roy","given":"Moumita"},{"family":"Dutta","given":"Subham"},{"family":"Mondal","given":"Debasmita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19314585","URL":"https://doi.org/10.5281/zenodo.19314585","source":"datacite"},{"id":"doi:10.5281/zenodo.16752416","type":"article-journal","title":"Prediction of Plant Disease with Deep Learning Method","abstract":"With the rapid growth of the global population, the agricultural sector is under increasing pressure to enhance food production and crop health management. One of the critical challenges in this domain is the timely and accurate detection of plant diseases, which, if not addressed promptly, can lead to significant crop losses. Traditional methods of disease identification often require expert analysis and manual inspection, making them inefficient for large-scale agricultural applications. This project introduces an automated plant disease detection system using deep learning, specifically convolutional neural networks (CNNs), to identify diseases from leaf images. The model learns visual features directly from the data, reducing the need for handcrafted features or expert intervention. The system supports real-time disease diagnosis, making it suitable for integration into smart farming platforms. By leveraging AI technology, the proposed method offers a scalable and efficient solution to modern agricultural challenges, contributing to sustainable crop monitoring and food security. The proposed model achieved an accuracy of 89.6% and an F1-score of 0.87 on the test dataset. However, fluctuations in validation accuracy suggest mild overfitting, indicating a need for improved generalization strategies such as enhanced data augmentation or regularization techniques.","author":[{"family":"Fatema","given":"Ms"},{"family":"Ali","given":"Dr"},{"family":"Jadhav","given":"AT"},{"family":"Bhuyar","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.16752416","URL":"https://doi.org/10.5281/zenodo.16752416","source":"datacite"},{"id":"doi:10.5281/zenodo.16604615","type":"article-journal","title":"Lo-Ra WAN Enabled Smart Agriculture System for Real-Time Pest and Crop Health Monitoring","abstract":"A LoRa WAN-Enabled Smart Agriculture System for real-time crop health and pest detection monitoring is presented in this project. In order to measure vital environmental parameters like soil moisture, temperature, pH, and gas emissions suggestive of pest activity, the system incorporates Internet of Things sensors. Large agricultural fields can have scalable deployment thanks to LoRa WAN's low-power, long-range communication capabilities. The system sends the data it collects to a cloud platform for real-time analysis and visualization, giving farmers timely insights to maximize crop yield, minimize pesticide use, and optimize resource usage. This solution exemplifies how cloud integration and the Internet of Things can advance precision agriculture and promote sustainable farming methods.","author":[{"family":"Tmenakadevi"},{"family":"Mgokulnath"},{"family":"Ahariraman"},{"family":"Kjavith"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.16604615","URL":"https://doi.org/10.5281/zenodo.16604615","source":"datacite"},{"id":"doi:10.5281/zenodo.18008488","type":"article-journal","title":"Policy, Governance, and Scaling Up Agroecology in Southeast Asia","abstract":"Abstract Southeast Asia is at the frontline of climate change, biodiversity loss and agrarian transformation. Agroecology is increasingly promoted as a pathway to sustainable, climate-resilient and equitable food systems in the region. Over the past decade, ASEAN and its member states have made important policy moves, culminating in the Policy Guidelines on Agroecology Transitions in ASEAN, adopted by ASEAN Ministers on Agriculture and Forestry (AMAF) in 2024 to guide national and local policy actors in scaling up agroecology. Parallel processes include ASEAN Regional Guidelines on Climate-Smart Agriculture and Sustainable Agriculture, and national frameworks for conservation agriculture and organic farming. At the same time, research reveals that agroecological initiatives in the Mekong region remain fragmented, often project-based and focused on technical practices more than on value chains, governance or social justice. A recent systematic review of agroecological practices in Southeast Asia confirms positive biophysical and economic impacts, but notes limited evidence on social, political and institutional dimensions that are crucial for scaling. This chapter examines how policy and governance arrangements shape the prospects for scaling up agroecology in Southeast Asia. It reviews (1) regional policy frameworks and guidelines; (2) multi-level governance and key networks; (3) evidence on scaling pathways and barriers; and (4) emerging instruments and strategies, including the ASEAN Policy Guidelines, ALiSEA, ASSET and research platforms such as ASEA. It argues that while the region has made major steps in recognizing agroecology at policy level, effective scaling still depends on transforming institutions, metrics and power relations, and on empowering territorial actors to co-design agroecological transitions. Keywords: Agroecology; policy and governance; scaling pathways; climate-resilient agriculture; sustainable food systems; ASEAN; Southeast Asia; multi-level governance; institutional transformation","author":[{"family":"Him","given":"Hun"},{"family":"Leng","given":"Channy"},{"family":"Horn","given":"Sarun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18008488","URL":"https://doi.org/10.5281/zenodo.18008488","source":"datacite"},{"id":"doi:10.17882/109882","type":"article-journal","title":"Physical and biogeochemical marine data of the Smart Bay S. Teresa underwater observatory (Eastern Ligurian Sea, Italy), 2024-2025","abstract":"In July 2024, a preliminary real-time monitoring and transmission system based on wireless underwater networking (IoUT) was implemented in the harbour of La Spezia (Eastern Ligurian Sea) to create an early warning system for temperature increase and to monitor oxygen and pH levels. Currently, the \"Smart Bay Santa Teresa Underwater Observatory\" is equipped with a system of transmission nodes connected to advanced probes, distributed across 12 stations throughout the Gulf. This development, achieved through collaboration with NRPP RAISE and EMBRC-UP projects, aims to detect changes in ocean conditions and marine ecosystems in real time, while also providing comprehensive marine data in support of shellfish farming activities located in this highly impacted coastal area. Physical-chemical data (temperature, dissolved oxygen, pH, conductivity, current, turbidity, chlorophyll) are acquired hourly and transmitted in real time, validated by ENEA with analytical approaches through weekly and monthly measurement campaigns. Biogeochemical parameters are measured analytically (total alkalinity, pH) and derived (pCO2, saturation state, dissolved inorganic carbon) on a weekly and monthly basis, together with high-precision vertical profiles (measured by means of a CTD probe). Data have been measured at five coastal stations: Santa Teresa Bay pier (BayP, 44.081855°N, 9.881658°E) (depth: 1 m) – leisure marina inside the dam Shellfish farming East (ShellFishE, 44.079517°N, 9.873986°E) (depths: 2, 5 and 8 m) – inside the harbour Shellfish farming West (ShellFishW, 44.072206°N, 9.855306°E) (depths: 2, 5 and 8 m) – inside the harbour Portovenere pier (PortovenereP, 44.053812°N, 9.838510°E) (depths: 1 and 2 m) – in the Regional Park and inside the Gulf Portovenere South (PortovenereS, 44.049858°N, 9.840694°E) (depth: 2 m) – in the Regional Park and inside the Gulf This monitoring is conducted within the context of the Smart Bay Santa Teresa collaboration platform. For comprehensive information about the infrastructure, data visualization capabilities, and utilization of observatory-derived data, a dedicated project section has been created on the Smart Bay Santa Teresa website: https://smartbaysteresa.com/en/. This platform serves as a central hub for stakeholder engagement and knowledge dissemination.","author":[{"family":"Bordone","given":"Andrea"},{"family":"Raiteri","given":"Giancarlo"},{"family":"Ciuffardi","given":"Tiziana"},{"family":"Gabrielli","given":"Erica"},{"family":"Lorenzini","given":"Sofia"},{"family":"Becagli","given":"Silvia"},{"family":"Appolloni","given":"Luca"},{"family":"Lombardi","given":"Chiara"}],"issued":{"date-parts":[[2025]]},"DOI":"10.17882/109882","URL":"https://doi.org/10.17882/109882","source":"datacite"},{"id":"doi:10.46254/af07.20260061","type":"article-journal","title":"Optimization and Techno-Economic Assessment of Hybrid Renewable Energy Systems for Precision Agriculture: A Review of Tools, Algorithms, and Sustainability","abstract":"In recent years, precision farming has been leveraging information infrastructure enabled by smart energy use, with designs for irrigation, sensors, automation, and post-harvesting services. In many agricultural regions, it is increasingly clear that, given the high cost of grid extensions and diesel-powered generators, traditional power grids are ill-suited. This corresponds to the rise of hybrid renewable energy systems. This study offers general considerations for optimizing and conducting cost studies of hybrid renewable energy systems in the precision agriculture sector. A comparison of the identified features has been employed to determine which hybrid configurations, their associated control strategies, optimization techniques, and assessment criteria are applicable to a given agricultural application. The summarized results point to a stronger tendency toward cost minimization and a system-oriented, consequently techno-centric design, with disproportionate underuse of explicit and realistic energywatercrop interactions, real-time decision-making, and compensation for socio-economic aspects. The present article argues for a systems approach to solving the problem of sustainable, resilient precision farming, as well as the use of hybrid renewable energy sources and their smart deployment. Keywords Hybrid renewable energy systems, Precision agriculture, Techno-economic analysis, Energy system optimization, Sustainable agriculture","author":[{"family":"Emezirinwune","given":"Michael"},{"family":"Babatunde","given":"Olubayo"},{"family":"Olanrewaju","given":"Oludolapo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.46254/af07.20260061","URL":"https://doi.org/10.46254/af07.20260061","source":"crossref"},{"id":"doi:10.1109/iciics67880.2026.11483558","type":"article-journal","title":"A Comprehensive Precision Agriculture Framework: Automated Plant Disease Identification and Categorization Through Cutting Edge Deep Learning Frameworks","abstract":"The outbreak of plant diseases represents one of the greatest menaces to the world agricultural productivity resulting in a global loss of crops that is estimated at 20-40 per annum. The conventional detection techniques based on visual inspection which is manual are time consuming and subjective. In the current paper, an optimized deep learning architecture to identify and detect plant diseases based on an ensemble of Convolutional Neural Networks (CNNs) will be presented (ResNet-50, DenseNet-121, and EfficientNet-B4). The authors make the contribution in the formulated system of adaptive preprocessing and attention-based feature fusion, weighted ensemble voting, which is developed based on explicit mathematical optimization. Extensive experimental validation of 15 plant species and 38 disease classes on a dataset of 54, 267 images supports a high accuracy of 97.8% and a high precision of 97.3 and a high recall of 97.1, which is a 2.0 percent improvement on existing algorithms with inference times less than 150 ms on edge machines. Ablation studies map the individual contribution of the components in detail, and analysis at the level of the classes indicate a stable detection across the types of diseases. The efficiency of the computations in the framework (model size: 89 MB, energy consumption: about 2.1 kWh per 1000 inferences) allows the implementation in farming scenarios with limited room.","author":[{"family":"Subbarayudu","given":"Jangam"},{"family":"Rafi","given":"DM"},{"family":"Suresh","given":"Juttu"},{"family":"Sumalatha","given":"Sangareddy"},{"family":"Anusha","given":"Muttavarapu"},{"family":"Reddy","given":"Chaduvula"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iciics67880.2026.11483558","URL":"https://doi.org/10.1109/iciics67880.2026.11483558","source":"crossref"},{"id":"doi:10.1109/ictmim68190.2026.11507300","type":"article-journal","title":"Optimizing Crop Selection and Fertilizer Usage with a Hybrid SVM-Genetic Algorithm Framework in Precision Agriculture","abstract":"The concept of precision agriculture emerged in the 1980s as a means to tailor fertilizer rates and mixtures to individual growing sites, with positive results for a wide range of crops and regions. Inadequate baseline data, limited sample methods, lack of site-specific fertilizer recommendations, and a paucity of qualified specialists are agronomic issues; high costs and limited experience are socioeconomic constraints. As a result, adoption remains uneven despite global interest. In order to address these challenges, datasets for crop selection and fertilizer optimisation were cleaned and prepared using data preprocessing. The optimal feature selection was achieved via RFE. A structurally reduced hybrid model that combined a GA and an SVM was used to select the crop and usage of fertilizers, an important measure of crop health and nutrient status. When it came to complicated nonlinear connections, the GA-SVM model achieved an accuracy of 94.69 %, which was higher than rival models. They need to overcome socioeconomic and technical obstacles to disseminate advanced machine learning and precision agriculture, which can increase fertilizer efficiency and crop selection.","author":[{"family":"Ravi","given":"Venkata"},{"family":"Nallathamby","given":"Rachel"},{"family":"Rajamani","given":"Tamilarasi"},{"family":"Abinaya","given":"M"},{"family":"Amrutkar","given":"Nimisha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/ictmim68190.2026.11507300","URL":"https://doi.org/10.1109/ictmim68190.2026.11507300","source":"crossref"},{"id":"doi:10.1109/icrai70912.2026.11551950","type":"article-journal","title":"A CNN-Based Intelligent Framework for Early Plant Stress Detection and Automated Remediation Recommendations in Precision Agriculture","abstract":"Detecting plant stress at the very beginning is of great importance for the sustainability of agricultural production and the optimal use of resources. A new intelligent framework based on CNN is proposed in this paper that not only identifies early plant stress with a very high accuracy but also gives automated, context-sensitive remediation suggestions. Our system uses a specially designed Convolutional Neural Network architecture that is trained on a multimodal dataset consisting of the visible spectrum and other sources. The detection module achieves a stable performance of 83.5 to 84.98% accuracy over several stress categories, which is significantly better than the existing methods in the literature that usually have an accuracy range of 70 to 82%. The next step after detection with 83.5 to 84.98% accuracy is that our integrated recommendation engine quickly generates targeted prescriptive interventions, which are solely based on the type of stress diagnosed. The system provides specific guidance on fertilizer formulations, irrigation adjustments, or pesticide applications through structured knowledge-based mapping for each correctly identified condition from the test dataset. This entire process from detection to prescription demonstrates the possibility of practical deployment at the edge, thereby giving farmers actionable insights directly from visual analysis. Validation through experiments proves the system’s ability to connect automated diagnosis with immediate agricultural recommendations, thus helping precision resource management through timely, data driven interventions.","author":[{"family":"Adden","given":"Muhammad"},{"family":"Zahid","given":"Rizwan"},{"family":"Ain","given":"Noor"},{"family":"Gillani","given":"Hammad"},{"family":"Abid","given":"Urooj"},{"family":"Rehman","given":"Hafiz"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icrai70912.2026.11551950","URL":"https://doi.org/10.1109/icrai70912.2026.11551950","source":"crossref"},{"id":"doi:10.1016/j.agwat.2025.110087","type":"article-journal","title":"Evaluating precision irrigation and nitrogen management for corn using SWAP model under changing humid climates","abstract":"Climate change is expected to alter crop productivity and nitrogen dynamics, yet limited research has quantified how different irrigation strategies can mitigate these impacts, particularly in humid regions where erratic rainfall complicates water and nutrient management. This study employs the agro-hydrological model SWAP to examine the performance of rainfed, calendar, and precision irrigation with both single (1 N) and split (2 N) nitrogen applications. SWAP model calibration and evaluation were conducted using observed volumetric water content across multiple soil depths as well as nitrate concentration data. Corn yield, nitrogen uptake, nitrate leaching, and irrigation water productivity were compared for each integrated irrigation and nitrogen strategy under different climate scenarios. To distinguish the effects of irrigation and nitrogen application strategy, precision irrigation was simulated using both a single nitrogen application (Precision-1N) and a split application (Precision-2N). Results indicated that nitrogen application timing (1 N vs. 2 N) had less of an impact on yields, leaching, and water productivity compared to irrigation strategy. Precision-2N consistently outperformed the Calendar-1N system across all scenarios, with higher yields and nitrogen uptake, and significantly better water productivity. The greatest long-term benefits of the Precision-2N treatment compared to Calendar-1N were observed under Scenario 4, which featured increased rainfall variability without an increase in total precipitation. In contrast, the smallest disparities between the irrigation treatments were observed in climate scenarios where precipitation increased. An analysis of interannual variability demonstrated that the Precision-2N benefits were most pronounced during years with frequent extreme temperature events. These findings reinforce the effectiveness of Precision-2N to achieve a favorable balance between higher yields and reduced NO₃ leaching. • Precision irrigation enhanced yield and WP, reducing nitrate leaching. • Rainfall variability impacted yield and NO₃ leaching more than total rainfall. • Increased precipitation minimized differences between calendar and precision treatment. • Nitrogen timing had less impact than irrigation strategy. • Extreme temperature events limited productivity despite sufficient rainfall.","author":[{"family":"Budhathoki","given":"Suman"},{"family":"Stewart","given":"Ryan"},{"family":"Frame","given":"William"},{"family":"Shortridge","given":"Julie"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.agwat.2025.110087","URL":"https://doi.org/10.1016/j.agwat.2025.110087","source":"crossref"},{"id":"doi:10.46759/iijsr.2026.10201","type":"article-journal","title":"Hyperlocal Precision Agriculture in Deltaic Ecosystems: A Critical Survey of AI, Machine Learning, and Data-Driven Approaches for Crop Intelligence and Decision Support","abstract":"Deltaic agricultural systems are facing more and more stress because of changes in the weather, a lack of water, and more crop diseases. This problem is especially clear in the Cauvery Delta region of Tamil Nadu, India, where limited resources are making it harder and harder for farmers to grow crops. Recent improvements in artificial intelligence (AI), machine learning (ML), and deep learning (DL) have made it possible to create intelligent decision support systems for important agricultural tasks like finding crop diseases, predicting yields, managing irrigation, and giving farmers advice. Even though there has been a lot of progress, current research is still broken up, and there hasn't been much work done to bring it all together through comparative evaluation, systematic taxonomy construction, and finding research gaps across domains. To mitigate this limitation, this survey offers an extensive examination of AI-driven methodologies utilized in deltaic agricultural systems. The research encompasses machine learning (ML), deep learning (DL), and hybrid methodologies within essential agricultural sectors, offering a systematic comparative assessment based on performance, scalability, cost, and practical applicability. Also, a hierarchical taxonomy is created to sort existing systems by methodology, data dependency, and deployment context. This gives a clear picture of the current research trends. The survey also points out important structural problems that make it hard for people to use the technology in the real world. These problems include the lack of decision frameworks that consider the source of water, the difference between controlled experimental datasets and real-world conditions, the lack of region-specific (Tamil-language) advisory systems, and the reliance on hardware-intensive infrastructures. Finally, the paper talks about future research directions that will lead to AI solutions that are integrated, easy to understand, light, and focused on farmers. These directions stress the need for hyperlocal, easy-to-use, and scalable systems to help sustainable precision agriculture in deltaic areas with limited resources.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.46759/iijsr.2026.10201","URL":"https://doi.org/10.46759/iijsr.2026.10201","source":"crossref"},{"id":"doi:10.1117/12.3109435","type":"article-journal","title":"Multispectral drone imaging for field-scale yield variability mapping in precision agriculture","abstract":"Field-scale yield variability is a defining feature of modern crop production, yet many fertilization and irrigation decisions are still made uniformly, ignoring within-field heterogeneity. This study evaluates multispectral drone imaging as a practical tool for mapping yield variability at field scale and for supporting site-specific management decisions. Highresolution multispectral imagery was acquired at key growth stages over commercial cereal fields, processed into calibrated reflectance and vegetation index maps, and linked to georeferenced yield data from combine harvesters. A set of empirical and machine-learning models was developed to relate multispectral metrics to final yield and to delineate stable management zones. Model performance, spatial resolution, positional accuracy and operational requirements were compared with those of satellite-based approaches and traditional scouting. Results show that multispectral drone imaging captures fine-scale yield patterns with sufficient accuracy to inform variable-rate strategies, while remaining compatible with typical farm logistics and digital agriculture platforms.","author":[{"family":"Wang","given":"Mei"},{"family":"Sulimin","given":"Vladimir"},{"family":"Shvedov","given":"Vladislav"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1117/12.3109435","URL":"https://doi.org/10.1117/12.3109435","source":"crossref"},{"id":"doi:10.7160/aol.2026.180203","type":"article-journal","title":"Optimization of Water Use in Precision Agriculture Through IoT-Enabled Multi-Sensor Fusion and Machine Learning-Based Smart Irrigation Scheduling","abstract":"This research presents a smart irrigation system that integrates Internet of Things (IoT) and machine learning (ML) to optimize water usage in agriculture. The system consists of a wireless sensor network that continuously monitors real-time environmental parameters such as soil moisture, temperature, humidity, wind speed, and rainfall. A Node-MCU microcontroller processes sensor data and transmits it to the Thing-Speak cloud for predictive analysis. The system follows a structured irrigation scheduling method, dynamically adjusting water distribution based on sensor feedback and environmental conditions. The proposed irrigation framework integrates an inverted U-shaped structure with a T-shaped hybrid irrigation system, enabling efficient water management through solenoid valves and sub-pipelines. This system, previously developed for sprinkler irrigation, was evaluated using machine learning models to assess its performance based on soil moisture and temperature parameters. In the present study, several machine learning algorithms, including Decision Tree, XG-Boost, Gradient Boosting, and Random Forest, were employed to predict irrigation requirements. The models consider multiple factors, such as soil moisture, rainfall, wind speed, and water availability, to forecast future irrigation demands, thereby facilitating optimal water utilization. Gradient Boosting achieved the highest accuracy (98.38%) and the lowest RMSE (0.1272), while Decision Tree and XG-Boost also performed strongly, with accuracy of 98.24% each. For controlling and monitoring the developed system, an android-based mobile application developed, allowing farmers to monitor and control irrigation remotely. The results demonstrate significant improvements in water conservation, reduced manual intervention, and enhanced crop yield. Future work will focus on refining predictive models, integrating additional environmental factors, and expanding system capabilities for broader adoption in precision agriculture.","author":[{"family":"Kaur","given":"Amritpal"},{"family":"Bhatt","given":"Devershi"},{"family":"Raja","given":"Linesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.7160/aol.2026.180203","URL":"https://doi.org/10.7160/aol.2026.180203","source":"crossref"},{"id":"doi:10.55003/eth.430208","type":"article-journal","title":"An Integrated LoRa-Enabled IoT Sensing System for Precision Agriculture: Design Algorithm and Practical Evaluation","abstract":"Precision agriculture increasingly relies on Internet of Things (IoT) technologies for continuous environmental monitoring; however, practical deployment remains constrained by energy efficiency, long-range communication, and system scalability. This paper presents an integrated IoT-based environmental sensing system that combines multi-parameter sensors with a microcontroller-based node and LoRa based long-range communication through a hardware algorithm co design approach. A lightweight device level algorithm is developed to manage sequential sensing, data validation, compact payload construction, and duty cycled transmission under resource constrained conditions. Experimental evaluations under simulated and representative field conditions demonstrate that sensor measurements remain within acceptable accuracy ranges for precision agriculture, with stable repeatability and limited drift over time. Communication experiments show packet delivery ratios above 90% over extended distances, while scalability analysis confirms reliable multi node operation with moderate latency increase. Energy profiling reveals that duty cycled operation significantly reduces power consumption without substantially degrading communication reliability. Overall, the proposed system provides a practical, energy efficient, and scalable solution for long term environmental monitoring in precision agriculture.","author":[{"family":"Yimyam","given":"Worawut"},{"family":"Ganokratanaa","given":"Thittaporn"},{"family":"Chumuang","given":"Narumol"},{"family":"Ketcham","given":"Mahasak"},{"family":"Boonyopakorn","given":"Pongsarun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55003/eth.430208","URL":"https://doi.org/10.55003/eth.430208","source":"crossref"},{"id":"doi:10.1109/icaect68478.2026.11426055","type":"article-journal","title":"An Application of Precision Agriculture Based on Machine Learning for Prediction of Crop Yield and Fertilizer Recommendation","abstract":"Nowadays, maximizing crop yields while reducing resource use is essential for successful and sustainable farming. Personalized crop and fertilizer suggestions are desperately needed in India's many agricultural regions, and the software helps with that. Based on a variety of environmental elements and soil conditions, our model uses machine learning techniques including logistic regression, random forests, k-nearest neighbours, linear regression, and support vector machines (SVM) to provide farmers unambiguous instructions. Crop databases, which are now accessible on many websites in the agriculture industry, are essential for recommending appropriate crops. Accordingly, farmers may be able to choose crops more effectively if a decision support system analyses the crop dataset using machine learning techniques. Using crop cloud data, global positioning system coordinates, and machine learning algorithms, the project's main objective is to provide farmers with more accurate and practical crop recommendations more rapidly. This comprehensive strategy aims to boost our proposal's legitimacy in light of the particular difficulties presented by India's climate and diversity. Crop history, soil properties, climate data, and fertilizer usage patterns are among the variables that the model takes in. In order to give farmers in various areas real advantages, we worked to develop a range of practical and adaptable goods that might be more effective and beneficial. For the project, a model that gives farmers information on crop planting and selection is required. Through the use of machine learning techniques like Random Forests and SVM, the effort promotes sustainable practices, modernizes agriculture, and increases the overall profitability of Indian agriculture.","author":[{"family":"Bonde","given":"Utkarsha"},{"family":"Koshal","given":"Aryan"},{"family":"Kolhe","given":"Sharvil"},{"family":"Dasarwar","given":"Priya"},{"family":"Dhankar","given":"Praveen"},{"family":"Holey","given":"Shreyas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaect68478.2026.11426055","URL":"https://doi.org/10.1109/icaect68478.2026.11426055","source":"crossref"},{"id":"doi:10.1109/etaact69135.2026.11542186","type":"article-journal","title":"MultiLayer SVM Model for Intelligent Pest Detection and Precision Crop Protection in Smart Agriculture","abstract":"By integrating biological, chemical, and cultural approaches, Integrated Pest Management (IPM) keeps insect populations at economically harmful levels while lowering hazards to public health and the environment. It is an environmentally friendly and sustainable agricultural strategy. In this study, it applies state-of-the-art methods of ML and image processing to the problem of intelligent pest detection and crop protection as it pertains to smart agriculture. Two pest image datasets with 21 pest categories are used in the study. A Multilayer SVM is used to classify the images after they have undergone segmentation, noise reduction, and PCA-LDA feature extraction. With a 96.21% accuracy rate, the model shows that combining machine learning and pest identification allows for accurate and sustainable crop protection in smart agriculture. The study concludes that smart agricultural approaches can be made more sustainable and effective in protecting crops when machine learning and intelligent pest detection.","author":[{"family":"Prasad","given":"SVV"},{"family":"Asrani","given":"Deepak"},{"family":"Asrani","given":"Komal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/etaact69135.2026.11542186","URL":"https://doi.org/10.1109/etaact69135.2026.11542186","source":"crossref"},{"id":"doi:10.3390/agriculture16020156","type":"article-journal","title":"Connection Between the Microbial Community and the Management Zones Used in Precision Agriculture Cultivation","abstract":"In precision agriculture, the delineation of Management Zones (MZs) is essential for optimizing input use efficiency and site-specific nutrient management. MZs are established based on spatial variability derived from remote sensing data—such as Normalized Difference Vegetation Index (NDVI) from satellite or UAV-based imagery—and yield maps collected during harvest. However, the microbial community composition of the soil is often overlooked in MZ delineation. To address this gap, we investigated the soil bacterial community structure across different MZs in an arable field. The zones were delineated using NDVI data, soil profiles were described, and bulk soil samples were collected. Soil physicochemical parameters were analyzed in parallel with 16S rRNA gene amplicon sequencing to characterize bacterial community composition and diversity. The results demonstrated that soil texture and soil organic matter content were the primary drivers influencing bacterial community structure across the field. Moreover, patterns in microbial composition aligned closely with MZ delineations, indicating that microbial profiles could aid in better understanding and supporting the nutrient management practices. Our findings suggest that soil microbiological data can enhance the stability and biological relevance of MZ definitions, thereby improving resource allocation, soil health management, and overall sustainability in precision farming systems.","author":[{"family":"Cserháti","given":"Mátyás"},{"family":"Márton","given":"Dalma"},{"family":"Csorba","given":"Ádám"},{"family":"Farkas","given":"Milán"},{"family":"Almalkawi","given":"Neveen"},{"family":"Hegyi","given":"Ádám"},{"family":"Kriszt","given":"Balázs"},{"family":"Szegi","given":"Tamás"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16020156","URL":"https://doi.org/10.3390/agriculture16020156","source":"crossref"},{"id":"doi:10.3390/agriculture16141508","type":"article-journal","title":"Mechanistic Networks and Precision Intervention Strategies for Feed Intake Control in Sows: Bridging Reproductive Potential, Physiological Homeostasis and Swine Industry Production","abstract":"The reproductive efficiency of modern breeding sows is commonly restricted by a mismatch between high genetic reproductive potential and insufficient voluntary feed intake during critical physiological periods. This review comprehensively examines the physiological, nutritional, and management mechanisms regulating feed intake in sows and their implications for reproductive performance, synthesizing recent advances across neuroendocrine regulation, metabolic signaling, immune-related pathways, and precision feeding strategies. We construct an integrated framework involving three core dimensions: (1) Physiological regulation: the hypothalamic–pituitary–adrenal, hypothalamic–pituitary–gonadal, and hypothalamic–pituitary–spleen axes functionally interact via shared neuroimmune pathways within the hypothalamic–pituitary–immune axis, coordinately regulating feeding patterns and reproductive cyclicity through core hormonal and inflammatory signaling molecules. Perinatal stress induces pro-inflammatory cytokine secretion, activates the intestinal JAK-STAT3 pathway, and upregulates intestinal hepcidin expression, impairing intestinal barrier integrity and triggering persistent inflammation. These peripheral inflammatory signals modulate hypothalamic neuropeptide Y and Proopiomelanocortin expression, forming a negative feedback loop that suppresses feeding behavior. (2) Nutritional regulation: dietary nutrients and specific flavor compounds reshape intestinal satiety signaling, improving piglet growth performance and survival rates, while optimized dietary composition and functional additive supplementation enhance sow feed intake capacity. (3) Management strategies: standardized feeding regimes and optimal rearing environments regulate nutrient digestion and gut hormone secretion. Major knowledge gaps include the translational potential of precision nutrition approaches, biomarker validation for feed intake monitoring, and the scalability of integrated interventions under commercial production conditions. This review provides a multidimensional framework integrating physiological, nutritional, and management strategies to enhance sow feed intake, offering theoretical insights and practical guidance for sustainable pig production.","author":[{"family":"Chai","given":"Haoliang"},{"family":"Zhao","given":"Dexin"},{"family":"Yu","given":"Xilong"},{"family":"Zhang","given":"Shaoshuai"},{"family":"Ji","given":"Fengjie"},{"family":"Peng","given":"Weiqi"},{"family":"Song","given":"Jianlou"},{"family":"Diao","given":"Xinping"},{"family":"Wu","given":"Hongzhi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16141508","URL":"https://doi.org/10.3390/agriculture16141508","source":"crossref"},{"id":"doi:10.1016/j.compag.2025.111302","type":"article-journal","title":"Precision yield estimation and mapping in manual strawberry harvesting with instrumented picking carts and a robust data processing pipeline","abstract":"High-resolution yield maps for manually harvested crops are impractical to generate on commercial scales because yield monitors are available only for mechanical harvesters. However, precision crop management relies on accurately determining spatial and temporal yield variability. This study presents the development of an integrated system for precision yield estimation and mapping for manually harvested strawberries. Conventional strawberry picking carts were instrumented with a Global Positioning System (GPS) receiver, an Inertial Measurement Unit (IMU), and load cells to record real-time geo-tagged harvest data and cart motion. Extensive data were collected in two strawberry fields in California, USA, during a harvest season. To address the inconsistencies and errors caused by the sensors and the manual harvesting process, a robust data processing pipeline was developed by integrating supervised deep learning model with unsupervised algorithms. The pipeline was used to estimate the yield distribution and generate yield maps for season-long harvests at the desired grid resolution. The estimated yield distributions were used to calculate two metrics: the total mass harvested over specific row segments and the total mass of trays harvested. The metrics were compared to ground truth and achieved accuracies of 90.48% and 94.05%, respectively. Additionally, the accuracy of the estimated yield based on the number of trays harvested per cart for season-long harvest was better than 94% achieving a strong correlation (Pearson r = 0.99) with the actual number of counted trays in both fields. The proposed system provides a scalable and practical solution for specialty crops, assisting in efficient yield estimation and mapping, field management, and labor management for sustainable crop production. The dataset and code supporting this study are available at: https://doi.org/10.5061/dryad.v6wwpzh7h and https://github.com/uddhavbhattarai/iCarritoYieldEstimationandMapping.git . • Picking carts record real-time harvest data during manual strawberry harvesting. • Robust data pipeline corrects errors from GPS and manual cart handling. • Scalable, practical yield estimation and mapping at desired resolution. • High yield estimation accuracy (>94%) in season-long harvest.","author":[{"family":"Bhattarai","given":"Uddhav"},{"family":"Arikapudi","given":"Rajkishan"},{"family":"Peng","given":"Chen"},{"family":"Fennimore","given":"Steven"},{"family":"Martin","given":"Frank"},{"family":"Vougioukas","given":"Stavros"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.compag.2025.111302","URL":"https://doi.org/10.1016/j.compag.2025.111302","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102267","type":"article-journal","title":"Ros-AI: An LLM-enhanced scalable multimodal framework for UAV-based rose bloom analysis in precision agriculture","abstract":"Accurate detection of rose blooms is important for nursery management, but it remains challenging due to the tiny size of flowers, their dense clustering, and frequent occlusion in UAV images. This study presents a multimodal framework that combines supervised deep learning, unsupervised computer vision, and large language models (LLMs) to address these challenges. UAV flights collected high-resolution RGB, and multispectral imagery of rose nurseries. Among the supervised methods, a tile-based YOLOv8-m model with sliding-window inference achieved strong validation performance (mAP@0.5 = 0.985, recall = 0.948), confirming the effectiveness of tiling strategies for small-object detection. But these approaches required heavy annotation and GPU resources. To overcome these limitations, we introduced the RGB Bloom Quantifier, an unsupervised algorithm that uses dynamic red-channel thresholding, morphological filtering, and contour analysis. This method achieved 93.1% accuracy while running entirely on CPU hardware, eliminating the need for training data and reducing deployment cost. Bloom counts from both pipelines were integrated with locally deployed LLMs (LLaMA 3 and Gemini), which generated practical recommendations for workforce allocation, irrigation scheduling, fertilizer application, and harvest timing. The results demonstrate that supervised and unsupervised approaches provide complementary strengths: supervised YOLO ensures high accuracy, while the quantifier enables scalable, low-cost deployment. Together with LLM-driven advisory, the framework moves beyond detection to actionable decision support, offering a pathway toward robust, affordable, and field-ready AI systems for precision agriculture.","author":[{"family":"Sundaravadivel","given":"Prabha"},{"family":"Manjunatha","given":"Harshitha"},{"family":"Narasimhamurthy","given":"Kruthik"},{"family":"Borah","given":"Shekhar"},{"family":"Anand","given":"Aryan"},{"family":"Torbert","given":"HA"},{"family":"Knight","given":"Patricia"},{"family":"Tamil","given":"Lakshman"},{"family":"Kumpatla","given":"Siva"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102267","URL":"https://doi.org/10.1016/j.atech.2026.102267","source":"crossref"},{"id":"doi:10.3390/agriengineering8010030","type":"article-journal","title":"Ambrosia artemisiifolia in Hungary: A Review of Challenges, Impacts, and Precision Agriculture Approaches for Sustainable Site-Specific Weed Management Using UAV Technologies","abstract":"Weed management has become a critical agricultural practice, as weeds compete with crops for nutrients, host pests and diseases, and cause major economic losses. The invasive weed Ambrosia artemisiifolia (common ragweed) is particularly problematic in Hungary, endangering crop productivity and public health through its fast proliferation and allergenic pollen. This review examines the current challenges and impacts of A. artemisiifolia while exploring sustainable approaches to its management through precision agriculture. Recent advancements in unmanned aerial vehicles (UAVs) equipped with advanced imaging systems, remote sensing, and artificial intelligence, particularly deep learning models such as convolutional neural networks (CNNs) and Support Vector Machines (SVMs), enable accurate detection, mapping, and classification of weed infestations. These technologies facilitate site-specific weed management (SSWM) by optimizing herbicide application, reducing chemical inputs, and minimizing environmental impacts. The results of recent studies demonstrate the high potential of UAV-based monitoring for real-time, data-driven weed management. The review concludes that integrating UAV and AI technologies into weed management offers a sustainable, cost-effective, mitigate the socioeconomic impacts and environmentally responsible solution, emphasizing the need for collaboration between agricultural researchers and technology developers to enhance precision agriculture practices in Hungary.","author":[{"family":"Hammad","given":"Sherwan"},{"family":"Kovács","given":"Gergő"},{"family":"Milics","given":"Gábor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriengineering8010030","URL":"https://doi.org/10.3390/agriengineering8010030","source":"crossref"},{"id":"doi:10.53894/ijirss.v9i3.11370","type":"article-journal","title":"Precision agriculture for smallholder farmers: Maximizing economics productivity using a machine learning-based water recommendation system","abstract":"This study explores how smallholder farmers in various communities can economically optimize productivity, connectivity, and efficiency using precision agricultural technologies, particularly and sensors. The study can empower many small scale farmers by demonstrating customized applications of precision agriculture tools, thus boosting their ability to maximize resource utilization, reducing risks, and increasing yields. Furthermore, this study developed a machine learning (ML) decision-making system to improve crop yield for smallholder farmers economically in rural South Africa. This system specifically optimises irrigation by detecting soil moisture anomalies and providing recommendations to maintain optimalsoil moisture levels. The optimal range was set for the range of 70 to 80%. The system was trained and modelled using several parameters of soil moisture humidity, atmospheric temperature, soil temperature, and soil moisture. A comparison was carried out using MLmodel and Logistic regression, XGBoost, CatBoost, Gradient Boosting and Support vector 13 machine (SVM). The metrics used were accuracy, F1 Score, Recall, and Precision. The results showed 4 that the XGBoost model performed better than the other four models5 with an accuracy of 0.73, an F1 Score of 0.64, and a recall of 0.73. The Gradient Boosting16 model had the 2nd best result with a precision of 0.79. The findings demonstrated that optimizing irrigation systems, enhanced crop yield could be achieved with better stability.","author":[{"family":"Aroba","given":"Oluwasegun"},{"family":"Rudolph","given":"Michael"},{"family":"Adetunji","given":"Kayode"}],"issued":{"date-parts":[[2026]]},"DOI":"10.53894/ijirss.v9i3.11370","URL":"https://doi.org/10.53894/ijirss.v9i3.11370","source":"crossref"},{"id":"doi:10.3389/fagro.2025.1670380","type":"article-journal","title":"Integrating UAVs, satellite remote sensing, and machine learning in precision agriculture: pathways to sustainable food production, resource efficiency, and scalable innovation","abstract":"Precision agriculture has emerged as a pivotal approach to achieving sustainable food production by integrating advanced technologies such as Unmanned Aerial Vehicles (UAVs), satellite remote sensing, and machine learning. This review examines the synergistic application of these technologies in enhancing agricultural efficiency, resource optimization, and environmental sustainability. UAVs enable high-resolution, real-time monitoring of crop health, soil conditions, and pest infestations, while satellite remote sensing provides scalable, large-scale agricultural data for comprehensive landscape analysis. Machine learning algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs) and Random Forests (RFs), process complex datasets to deliver actionable insights for precision decision-making, such as yield prediction, nutrient management, and irrigation optimization. Case studies demonstrate that integrating UAV and satellite data with machine learning improves crop yield prediction accuracy and resource use efficiency, reducing irrigation costs by 20–25% and nitrogen application by up to 31 kg ha −1 , without compromising productivity. AI-driven disease detection systems have demonstrated high efficacy, with certain models achieving accuracy exceeding 95% in identifying diseases such as Botrytis cinerea in tomatoes, powdery mildew in wheat, and downy mildew in grapes. However, challenges persist, including data processing complexities, high computational demands, and the need for cost-effective, scalable solutions. The findings underscore the transformative potential of these technologies in advancing sustainable agriculture, while emphasizing the necessity for interdisciplinary collaboration, supportive policies such as subsidies for precision agriculture equipment, streamlined regulations for UAV operations, and open data initiatives for satellite imagery, as well as improved accessibility to key technologies including high-resolution multispectral sensors, cloud computing infrastructure, and scalable machine learning platforms for smallholder farmers. This review provides a roadmap for future research and policy development aimed at optimizing food production systems in the face of climate change and growing population demands.","author":[{"family":"Xing","given":"Yingyig"},{"family":"Liu","given":"Xuning"},{"family":"Wang","given":"Xiukang"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fagro.2025.1670380","URL":"https://doi.org/10.3389/fagro.2025.1670380","source":"crossref"},{"id":"doi:10.70177/agriculturae.v3i2.3563","type":"article-journal","title":"ADVANCING CROP PRODUCTION SYSTEMS: INTEGRATING SUPERIOR VARIETIES AND PRECISION AGRICULTURE FOR SUSTAINABLE YIELD ENHANCEMENT","abstract":"Global food demand continues to rise due to population growth, climate variability, and changing consumption patterns, placing increasing pressure on agricultural production systems. Conventional farming practices often struggle to achieve sustainable yield improvement while maintaining resource efficiency and environmental integrity. The integration of superior crop varieties with precision agriculture technologies has emerged as a promising strategy to enhance productivity, optimize input use, and promote sustainable agricultural development. This study aims to evaluate the effectiveness of integrating high-performing crop varieties with precision agriculture approaches in improving crop yield, resource efficiency, and production sustainability. The research focuses on identifying synergistic effects between genetic improvement and site-specific management practices in modern crop production systems. A mixed-methods approach was employed, combining field experiments, secondary agronomic data analysis, and precision farming measurements. Superior crop varieties were assessed under precision-managed conditions using variable-rate fertilization, sensor-based monitoring, and data-driven decision support systems. Yield performance, input efficiency, and environmental indicators were analyzed using descriptive statistics and comparative analysis. Results demonstrate that the combined application of superior varieties and precision agriculture significantly increased crop yields while reducing fertilizer and water inputs. Improved nutrient-use efficiency and yield stability were observed across different growing conditions. The study concludes that integrating genetic advancement with precision agriculture offers a viable pathway for sustainable yield enhancement. This approach supports resilient, efficient, and environmentally responsible crop production systems.","author":[{"family":"Hadi","given":"Pramono"},{"family":"Ferrari","given":"Marco"},{"family":"Romano","given":"Lucia"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70177/agriculturae.v3i2.3563","URL":"https://doi.org/10.70177/agriculturae.v3i2.3563","source":"crossref"},{"id":"doi:10.18535/ijecs/v15i03.5436","type":"article-journal","title":"Plant Leaf Disease Identification For Precision Agriculture Using Deep Learning","abstract":"Agriculture faces ongoing challenges from crop diseases, unpredictable weather, and heavy reliance on chemical pesticides. These factors lower crop productivity and harm environmental sustainability. This paper introduces a smart mobile app that helps with sustainable crop management through deep learning for plant disease detection and 24-hour weather forecasting. The system analyzes leaf images taken by mobile devices to identify plant species and spot diseases early using convolutional neural networks. Real-time weather data is also processed to give accurate forecasts for the next 24 hours. This helps farmers make timely decisions based on current weather. The app suggests suitable organic fertilizers based on plant health and weather forecasts. It determines when pesticides are necessary, focusing on eco-friendly solutions and recommending chemical pesticides only when needed and under favorable weather conditions. The app uses mobile number authentication and keeps a six-month history of user activities, including disease diagnoses, weather forecasts, and advice records. Additionally, follow-up notifications are sent 10 to 20 days after pesticide recommendations to check treatment effectiveness based on farmer feedback. The proposed system aims to cut down chemical use, improve crop yield, and encourage environmentally friendly and data-driven farming practices.","author":[{"family":"Samagna","given":"Avuldhapuram"},{"family":"Snehitha","given":"Badakala"},{"family":"Srilatha","given":"Kadiyam"},{"family":"Kavya","given":"Kamju"},{"family":"Soumya","given":"Karre"},{"family":"Sathish","given":"A"},{"family":"Ramana","given":"BV"}],"issued":{"date-parts":[[2026]]},"DOI":"10.18535/ijecs/v15i03.5436","URL":"https://doi.org/10.18535/ijecs/v15i03.5436","source":"crossref"},{"id":"doi:10.36378/jtos.v9i1.5760","type":"article-journal","title":"An IoT-Based Model for Monitoring Soil pH, Temperature, and Moisture to Support Precision Agriculture","abstract":"Manual measurement of soil pH, temperature, and moisture often produces fragmented field data that are difficult to use for periodic land monitoring. This study developed an Internet of Things-based prototype for monitoring soil conditions to support precision agriculture. The system integrated a soil pH sensor, a waterproof DS18B20 soil temperature sensor, a soil moisture sensor, an ESP32 NodeMCU, Wi-Fi communication, data storage, and a web-based dashboard. The research followed a prototype development model covering requirement analysis, system design, hardware and software implementation, testing, evaluation, and refinement. Field testing was conducted from February to April 2026 at 08:00, 12:00, and 16:00. The results showed that soil pH ranged from 6.47 to 6.70 with an average of 6.58, soil temperature ranged from 21.30°C to 28.61°C with an average of 24.57°C, and soil moisture ranged from 73.67% to 90.00% with an average of 87.71%. Functional testing indicated that the prototype could read, transmit, store, and visualize soil data through the dashboard during operation. The proposed model is feasible as an early-stage monitoring system for data-driven soil management, although future accuracy validation with calibrated instruments is still required.","author":[{"family":"Jaelani","given":"MAQ"},{"family":"Syaputra","given":"Muhammad"},{"family":"Sutomo","given":"Budi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.36378/jtos.v9i1.5760","URL":"https://doi.org/10.36378/jtos.v9i1.5760","source":"crossref"},{"id":"doi:10.1111/itor.70176","type":"article-journal","title":"An application of message routing in intermittent networks to precision agriculture","abstract":"Abstract The widespread adoption of wireless sensor networks (WSN) and Internet of Things in recent years has provided powerful technological tools for the advancement of precision agriculture, a concept in use since the end of the 20th century. The possibility of collecting data and information obtained from the deployment of a WSN that allows the evaluation of different actions and their impact on the production will change the productivity of agricultural and livestock raising activities, particularly in developing countries. In order to collect and process data in real time, properly running the underlying challenged network is critical, especially when the nodes operate on batteries, and their energy demand should be minimized so their active life is maximized. In this case, nodes may operate intermittently in order to extend their lifespan, so the graph representing the network changes over time. In this work, we address the problem of routing messages in intermittent networks arising from such applications. We propose an integer programming formulation for this problem and develop a heuristic based on the minimum‐cost flow problem in networks. We evaluate their computational performances, and we apply the heuristic procedure to a case study coming from the application of WSN in a forced‐drip irrigation lot. Based on our computational experiments, we argue that the use of this heuristic approach provides a simple and effective mechanism to assess different network configurations with agility.","author":[{"family":"Marenco","given":"Javier"},{"family":"Zabala","given":"Paula"},{"family":"Santos","given":"Rodrigo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1111/itor.70176","URL":"https://doi.org/10.1111/itor.70176","source":"crossref"},{"id":"doi:10.62110/sciencein.jist.2026.v14.1606","type":"article-journal","title":"Efficient plant disease detection using reinforced coati optimization algorithm (RCOA) for Precision Agriculture","abstract":"Recent advancement in Artificial Intelligence (AI) have greatly improved their application in agriculture, especially in the identification of plant leaf diseases and in facilitating enhanced decision-making. Detection of plant leaf diseases plays important role for placing crop healthy and assisting farmers to take action on time. However, despite these improvements, they are still challenging to use in the real world. The process can be difficult to analyze plant leaf images because they often have complicated background and different structural patterns. Differences in light, texture, and the way leaves naturally change make things even more complicated, making it hard for automated detection systems to be reliable. Therefore, the paper introduces novel method as Reinforced Coati Optimization Algorithm (RCOA) for determining useful selection of features from a huge set of feature set generated from feature extraction methods. The RCOA algorithm is tested on CEC 2017 Benchmark function suite. Further, the model is trained using Support Vector Machine (SVM) and Multilayer Perceptron (MLP). The outcome depicts that proposed algorithm is providing better outcomes on comparative analysis with state-of-the-art methods.","author":[{"family":"Vijh","given":"Surbhi"},{"family":"Shieh","given":"Chin"},{"family":"Jain","given":"Vishal"},{"family":"Horng","given":"Mong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.62110/sciencein.jist.2026.v14.1606","URL":"https://doi.org/10.62110/sciencein.jist.2026.v14.1606","source":"crossref"},{"id":"doi:10.21474/jnaves01/128","type":"article-journal","title":"PRECISION AGRICULTURE TECHNOLOGIES FOR ENHANCING CROP YIELD AND RESOURCE EFFICIENCY: A COMPREHENSIVE REVIEW","abstract":"The increasing global demand for food, coupled with limited natural resources and climate variability, has created significant challenges for modern agriculture. Precision agriculture has emerged as an innovative approach that utilizes advanced technologies to improve crop productivity while minimizing environmental impacts. Precision agriculture involves the use of Global Positioning Systems (GPS), Geographic Information Systems (GIS), remote sensing, drones, sensors, and data analytics to optimize farm management practices. This review examines the principles, technologies, applications, benefits, and challenges of precision agriculture. The findings suggest that precision farming can enhance crop yields, improve resource-use efficiency, reduce production costs, and contribute to sustainable agricultural development. Despite challenges related to cost and technical expertise, precision agriculture represents a promising pathway toward future food security and environmental sustainability.","author":[{"family":"Bennett","given":"Olivia"},{"family":"Mahmood","given":"Hassan"},{"family":"Deshmukh","given":"Riya"},{"family":"Mensah","given":"David"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21474/jnaves01/128","URL":"https://doi.org/10.21474/jnaves01/128","source":"crossref"},{"id":"doi:10.35760/jpp.2026.v10i1.262","type":"article-journal","title":"COMPARATIVE PERFORMANCE AND GENERALIZATION ANALYSIS OF MOBILENETV1 AND MOBILENETV2 FOR RHIZOME SPICE CLASSIFICATION","abstract":"Indonesia's rich biodiversity includes rhizome spices that are often difficult to distinguish manually due to their similar visual characteristics. This study developed and compared MobileNetV1 and MobileNetV2 for classifying four rhizome spice classes, namely ginger, turmeric, galangal, and aromatic ginger, using a dataset of 1,120 images. MobileNetV1 achieved a training accuracy of 0.9611 at a learning rate of 0.001 in 1,522.65 seconds, whereas MobileNetV2 achieved a higher training accuracy of 0.9823 at a learning rate of 0.0002 in 1,444.20 seconds. While MobileNetV2 demonstrated superior classification performance and faster convergence, MobileNetV1 demonstrated stronger generalization capability, indicated by a smaller train-validation accuracy gap (1.21% vs. 1.80%) and more stable validation performance. Both no-dropout models achieved an accuracy, precision, recall, and F1-score of 0.9642 on the 112-image test set. The two best-performing models were deployed in a Streamlit-based web application. The results demonstrate that MobileNetV2 is preferable when maximizing predictive performance, whereas MobileNetV1 offers greater robustness for relatively small datasets. This study contributes to the development of practical AI-based tools for agricultural and spice-identification applications.","author":[{"family":"Femalea","given":"Najmah"},{"family":"Saputra","given":"Guntur"},{"family":"Delianti"},{"family":"Nurthoyibah","given":"Hilmi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35760/jpp.2026.v10i1.262","URL":"https://doi.org/10.35760/jpp.2026.v10i1.262","source":"crossref"},{"id":"doi:10.65521/intjournalrecadvengtech.v15i1.1741","type":"article-journal","title":"Image-Based Breed Recognition for Cattle and Buffaloes of India: Advancing Precision Agriculture","abstract":"Breed determination plays a very important role in livestock admin, preservations of genetic diversity and optimization of agricultural output within India's extensive bovine sector. Convention identifies approaches relies upon adept examination of substantial properties create a hold-up through the labor - exhaustive nature, incompatible with results, and a vulnerability to a human oversight - computing when it is determine between visually proportional and a hybrid of variation. This can be look into presents an automatic visual classifications architecture by take advantage of a cutting-edge to the Computer Vision technologies and Deep Learn methodologies, particularly for Convolutional Neural Networks (CNNs), to allow reliable and the methodical breed classification of Indian cattle and a buffalo. Our access to contain the development of all-inclusive well - curated an image archive; an application of an modern preprocessing protocols to an separate the subjects and the features identifying characteristics like including coat patterns and horn configurations; Construction of the and advanced architecture to efficient of giving best accurate and predictive performance. This system stands for a practical and inexpensive and time-efficient stand-in for traditional standard assessment of the methods. The technology keep a very promise for a real-world deployment allowing farming producers, enhance veterinary in system, and encouraging familiar decision-making.","author":[{"family":"Yadav","given":"Chandrashekhar"},{"family":"Singh","given":"Sanjeev"},{"family":"Adepwar","given":"Utkarsh"},{"family":"Panday","given":"Ananya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.65521/intjournalrecadvengtech.v15i1.1741","URL":"https://doi.org/10.65521/intjournalrecadvengtech.v15i1.1741","source":"crossref"},{"id":"doi:10.3390/agriculture16111216","type":"article-journal","title":"Design and Operating-Parameter Optimization of a Precision Seeder for Chinese Yam Based on Automatic Seed Distribution and Chain-Driven Metering","abstract":"A precision seeder for elongated Chinese yam seed segments was developed by integrating automatic seed distribution with chain-driven metering. The design was based on measured seed segment properties, including mean length, width, thickness, equivalent diameter, density, moisture content, intrinsic mechanical properties, and seed-seed/seed-steel contact parameters. A seed-layer stress model, sprocket-conveying stability condition, seed-dropping trajectory equation, and plant-spacing equation were used to determine the main structural parameters and to select operating speed, seed-dropping height, and seed-box slope angle as optimization variables. Box–Behnken response surface optimization predicted the best parameter combination as an operating speed of 0.20 m s−1, a seed-dropping height of 0.14 m, and a seed-box slope angle of 26.18°, with predicted qualified-seeding, multiple-seeding, and missed-seeding indices of 86.45%, 5.16%, and 8.40%, respectively. Field validation using the rounded seed-box slope angle of 26° produced mean qualified-seeding, multiple-seeding, and missed-seeding indices of 86.16%, 5.13%, and 8.71%, respectively. The results demonstrate a practical design route for oriented precision seeding of elongated tuber segments.","author":[{"family":"Mu","given":"Jingchao"},{"family":"Zhao","given":"Hongpeng"},{"family":"Zhang","given":"Xiuping"},{"family":"Chen","given":"Lin"},{"family":"Zhao","given":"Xiaoshun"},{"family":"Liu","given":"Tinghui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriculture16111216","URL":"https://doi.org/10.3390/agriculture16111216","source":"crossref"},{"id":"doi:10.4018/979-8-3693-7006-3.ch007","type":"article-journal","title":"Nano-Biochar in Sustainable Agriculture","abstract":"Innovative soil amendment research is driven by the need for sustainable agriculture to provide global food security and reduce environmental damage. Biochar, made from organic feedstocks that promote soil health and sequester carbon. Bulk characteristics may limit its efficacy. Nanotechnology can modify biochar's functioning. Sub-micrometer particle size, large surface area, and unique physicochemical properties make nano-biochar (NBC) a significant breakthrough. Nano-biochar in sustainable agriculture is covered in this chapter. NBC production and characterization are explained, along with its properties compared to regular biochar. In this chapter, we discuss NBC's many uses as a soil conditioner, remediator, agrochemical transporter, and plant stress reducer. A heavy metal contaminated soil remediation case study shows NBC's practicality and efficacy. Finally, the chapter discusses nano-biochar's role in next-generation sustainable agriculture systems.","author":[{"family":"Singh","given":"Omkar"},{"family":"Singh","given":"Shivangi"},{"family":"Shahi","given":"Uday"},{"family":"Singh","given":"Vaishali"},{"family":"Singh","given":"Krishna"},{"family":"Singh","given":"Sakshi"},{"family":"Derdzyan","given":"Tatevik"},{"family":"Sousa","given":"João"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3693-7006-3.ch007","URL":"https://doi.org/10.4018/979-8-3693-7006-3.ch007","source":"crossref"},{"id":"doi:10.1201/9781003662808-14","type":"article-journal","title":"Precision Agriculture: Forecasting Crop Prices through Machine Learning Models","abstract":"Crop price forecasting is difficult but an important step in farming when the prime time of trading crops is an issue since farmers in India usually do not have enough revenues. The existing system of prices is very lopsided since it depends largely on the local markets and on the crop production of the current season, which results in uneven prices of crops in the country. As opposed to the current studies that have been limited to the analysis of crop prices, there is an urgent need to improve experiments in crop production forecasts. Imbalanced production of crops between the different fraternities of the Indian agriculture also adds to the predicaments. To remedy this, it is important to put in place an appropriate Minimum Support Price (MSP) to establish a base price of crops and therefore, stand to relieve poverty in the country. A combination of machine learning and data mining leads to better prediction of the pruning costs and transforms the process of conducting business in the agricultural sector. The use of such advanced technologies gives the farmer an opportunity to gain valuable information about complicated patterns and trends in the vast world of horticultural data. The ability of SARIMAX algorithms to adjust and learn based on the past and real-time data is, therefore, central in the development of more refined findings on the factors that have an influence on pruning costs.","author":[{"family":"Hirapara","given":"Jignesh"},{"family":"Ranpara","given":"Ripal"},{"family":"Doshi","given":"Milan"},{"family":"Mangi","given":"Priyanka"},{"family":"Dineshkumar","given":"Bhagchandani"},{"family":"Choudhury","given":"Koushik"},{"family":"Bhojani","given":"Aarati"},{"family":"Dave","given":"Nehal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003662808-14","URL":"https://doi.org/10.1201/9781003662808-14","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7257-0.ch005","type":"article-journal","title":"Revolutionizing Crop and Soil Monitoring Through IoT-Enabled Farming","abstract":"The integration of Internet of Things (IoT) technologies is transforming agriculture from traditional input-based practices to data-driven, real-time, and automated production systems. IoT platforms integrate advanced sensors, connectivity infrastructures, and edge–cloud computing to continuously monitor soil moisture, nutrient status, pH, temperature, and plant physiological parameters, enabling early detection of biotic and abiotic stresses. When combined with artificial intelligence and machine learning models, heterogeneous data streams are analyzed to optimize irrigation, fertigation, pest management, and overall farm productivity. Automated control systems translate analytical insights into timely agronomic interventions, reducing resource inputs, labor demands, and environmental impacts. Applications span large-scale farms, smallholder systems, and controlled environments, demonstrating improved yield, resource efficiency, and crop quality.","author":[{"family":"Hassan","given":"Dilawar"},{"family":"Tehseen","given":"Nadia"},{"family":"Farid","given":"Urooj"},{"family":"Ehsan","given":"Muhammad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-7257-0.ch005","URL":"https://doi.org/10.4018/979-8-3373-7257-0.ch005","source":"crossref"},{"id":"doi:10.55041/ijsrem58929","type":"article-journal","title":"AI Powered Precision Agriculture Drone System for Crop Health Monitoring and Management","abstract":"ABSTRACT Let’s face it, the old way of walking fields and guessing at crop health just doesn’t cut it anymore. Food security is a growing problem, and farmers need smarter tools. That’s where new AI-powered drone system steps in. It’s built for real work, not just showing off tech for tech’s sake. Here’s how it goes: imagine your fields dotted with small IOT sensors, each one quietly watching over soil moisture and water quality. They’re running on low-cost, programmable ESP32 hardware—nothing fancy, but reliable. Most of the time, the drones stay parked. But the second a sensor picks up trouble—say, a patch of soil gets too dry or water quality drops—the system jumps into action. The drone takes off on its own and heads straight to the problem spot, guided by GPS and the sensor’s alert. Once there, it snaps high-res images of the crops below. No more guesswork—these images go through a machine learning pipeline built with Tensor-Flow and K-eras, using deep Convolutional Neural Networks. The system checks for early signs of yellowing, wilting, or pests—stuff you don’t want to miss. After that, the results and clear, practical advice—like when to water—pop up on a central dashboard. This setup isn’t about replacing farmers; it’s about giving them a break from endless scouting and letting them focus on bigger decisions. By only sending out drones when needed, it saves energy and cuts down costs. Early data shows a 40% faster response to crop diseases and up to 30% better use of resources. In the end, it’s a smart, affordable way to bring precision farming to the people who need it most, making farms more efficient—without all the extra work.","author":[{"family":"Kumara","given":"Manoj"},{"family":"Chandhara","given":"Pavan"},{"family":"Kumarch","given":"Praveen"},{"family":"Kumarch","given":"Sravan"},{"family":"Kumarb","given":"Sunil"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsrem58929","URL":"https://doi.org/10.55041/ijsrem58929","source":"crossref"},{"id":"doi:10.1117/12.3103945","type":"article-journal","title":"Active optical sensing and 3D imaging of materials for robotic precision operations","abstract":"Many jobs in food and agriculture, such as crab meat picking and fruit harvesting, require precise hand-eye coordination and accurate 3D vision for robotic operations. Current RGBD cameras often lack sufficient depth resolution, rendering them unreliable for these tasks. In this presentation, we will introduce an active laser-scanning 3D imaging system developed in our lab that achieves a depth resolution of better than 0.5mm, enabling accurate robotic operations. We will showcase results from tasks like automated crab meat picking and its potential applications in selective harvesting of fruits and vegetables, seed manipulation, and other precision food services. This patented technology offers significant advancements in automated and smart processing for agricultural commodities.","author":[{"family":"Tao","given":"Yang"},{"family":"Ali","given":"Mohamed"},{"family":"Hevaganinge","given":"Anjana"},{"family":"Sadrieh","given":"Faranguisse"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1117/12.3103945","URL":"https://doi.org/10.1117/12.3103945","source":"crossref"},{"id":"doi:10.1007/s11119-026-10367-0","type":"article-journal","title":"Crop robots as potential enablers of economical and biodiversity-smart small-scale farming","abstract":"Abstract Purpose Reducing human labor requirements through crop robots is assumed to positively affect the economy of smaller fields. Strip cropping is a mechanizable approach to creating smaller subfields and increasing biodiversity but currently suffers from economic pressures. To investigate whether robots could present a labor-saving solution in this production system, two strip cropping field labs operated with autonomous equipment are studied. Methods Human labor during tractor and commercial robot operations in a strip cropping setting was documented in southern Germany (2022-2024). Descriptive analyses are complemented by technological progress scenarios. Both observed and scenario data are used to calculate the effect of field and strip size on human labor input. The findings are contextualized with observations from strip cropping trials in the UK that were operated fully autonomously with retrofitted equipment (2023-2025). Results A comparison of the observed tractor and robot data shows that tractors can currently operate a strip cropping system more efficiently than robots. The AgBot crop robot analyzed cannot yet reduce human labor time in a small-scale diversified production system. However, low-threshold technological progress may lead robots’ human time requirements to approach that of tractors. Hybrid autonomous technologies, as used in the UK setting, can address inefficiencies arising from logistics. Conclusion Economies of field size exist for both tractors and robots and can only be overcome at extensive changes to farm infrastructure and legal framework. Logistics and support activities make larger fields more economical. Crop robots should therefore not be assumed to change field structures towards more biodiversity.","author":[{"family":"Spykman","given":"Olivia"},{"family":"Lowenberg-Deboer","given":"James"},{"family":"Gandorfer","given":"Markus"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10367-0","URL":"https://doi.org/10.1007/s11119-026-10367-0","source":"crossref"},{"id":"doi:10.19103/as.2025.0152.09","type":"article-journal","title":"Decision support systems in precision agriculture and conservation","abstract":"Many public and private decision support systems (DSS) are currently developed. The DSS are defined as computer-based platforms to collect, process, and analyze multi-facet data and generate timely and accurate decisions. Modern DSS includes crop, soil, weather observations, real time machine, sensor, economic and market data, advanced analytics, cloud computing and user-friendly recommendations. Two case studies of public DSS are presented. One is a web-based tool to prescribe variable soybean seeding rates using historical yield maps, yield classification, cost of seed and price of grain. The other web-based platform summarizes yield genotypes by geographies and irrigation management and helps growers to choose the right crop genetics for irrigated or rainfed area. Key barriers to the adoption of modern DSS by farmers and stakeholders are discussed. Future DSS will rely on larger and more diverse datasets, more robust machine learning and process-based models, advanced cloud computing, AI and mobile accessible devices.","author":[{"family":"Kyveryga","given":"Peter"},{"family":"Cano","given":"Priscila"},{"family":"Cisdeli","given":"Pedro"},{"family":"Hernández","given":"Carlos"},{"family":"Santiago","given":"Gustavo"},{"family":"Ciampitti","given":"Ignacio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.19103/as.2025.0152.09","URL":"https://doi.org/10.19103/as.2025.0152.09","source":"crossref"},{"id":"doi:10.1201/9781003520733-25","type":"article-journal","title":"Smart soil systems","abstract":"Digital agriculture, precision farming, and soil categorization are all being combined to make Indian agriculture a more sustainable and effective system. This chapter explores how deep learning (DL) and machine learning (ML) approaches are transforming agricultural operations. These technologies optimize crop selection, nutrient management, and irrigation techniques by utilizing image-based soil categorization to offer the best results in a limited time. Precision farming allows farmers to make data-driven decision tailored to fulfill their farms unique needs by utilizing state-of-the-art digital technologies and Internet of Things-enabled platforms. This strategy is further improved by digital agriculture, which minimizes manual work, automates data collecting and analysis, and makes scalable solutions possible across various terrains. The chapter is also highlighting the difficulties and challenges of using these technologies in India, emphasizing the need of smallholder farmers to have easy access to reasonably priced solutions. Additionally, it looks at how combining geographic data with artificial intelligence (AI)-powered systems might boost agricultural productivity, decrease environmental impact, and improve resource efficiency. This chapter imagines a future in which Indian agriculture thrives on innovation, sustainability, and resilience by filling important holes in traditional farming methods.","author":[{"family":"Priya","given":"Madhu"},{"family":"Bhatt","given":"Devershi"},{"family":"Malche","given":"Timothy"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003520733-25","URL":"https://doi.org/10.1201/9781003520733-25","source":"crossref"},{"id":"doi:10.3390/s25061751","type":"article-journal","title":"FFAE-UNet: An Efficient Pear Leaf Disease Segmentation Network Based on U-Shaped Architecture","abstract":"The accurate pest control of pear tree diseases is an urgent need for the realization of smart agriculture, with one of the key challenges being the precise segmentation of pear leaf diseases. However, existing methods show poor segmentation performance due to issues such as the small size of certain pear leaf disease areas, blurred edge details, and background noise interference. To address these problems, this paper proposes an improved U-Net architecture, FFAE-UNet, for the segmentation of pear leaf diseases. Specifically, two innovative modules are introduced in FFAE-UNet: the Attention Guidance Module (AGM) and the Feature Enhancement Supplementation Module (FESM). The AGM module effectively suppresses background noise interference by reconstructing features and accurately capturing spatial and channel relationships, while the FESM module enhances the model’s responsiveness to disease features at different scales through channel aggregation and feature supplementation mechanisms. Experimental results show that FFAE-UNet achieves 86.60%, 92.58%, and 91.85% in MIoU, Dice coefficient, and MPA evaluation metrics, respectively, significantly outperforming current mainstream methods. FFAE-UNet can assist farmers and agricultural experts in more effectively evaluating and managing diseases, thereby enabling precise disease control and management.","author":[{"family":"Wang","given":"Wenyu"},{"family":"Ding","given":"Jie"},{"family":"Shu","given":"Xin"},{"family":"Xu","given":"Wenwen"},{"family":"Wu","given":"Yunzhi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/s25061751","URL":"https://doi.org/10.3390/s25061751","source":"crossref"},{"id":"doi:10.19103/as.2024.152.09","type":"article-journal","title":"Decision support systems in precision agriculture and conservation","abstract":"Many public and private decision support systems (DSS) are currently developed. The DSS are defined as computer-based platforms to collect, process, and analyze multi-facet data and generate timely and accurate decisions. Modern DSS includes crop, soil, weather observations, real time machine, sensor, economic and market data, advanced analytics, cloud computing and user-friendly recommendations. Two case studies of public DSS are presented. One is a web-based tool to prescribe variable soybean seeding rates using historical yield maps, yield classification, cost of seed and price of grain. The other web-based platform summarizes yield genotypes by geographies and irrigation management and helps growers to choose the right crop genetics for irrigated or rainfed area. Key barriers to the adoption of modern DSS by farmers and stakeholders are discussed. Future DSS will rely on larger and more diverse datasets, more robust machine learning and process-based models, advanced cloud computing, AI and mobile accessible devices.","author":[{"family":"Kyveryga","given":"Peter"},{"family":"Cano","given":"Priscila"},{"family":"Cisdeli","given":"Pedro"},{"family":"Hernández","given":"Carlos"},{"family":"Santiago","given":"Gustavo"},{"family":"Ciampitti","given":"Ignacio"}],"issued":{"date-parts":[[2025]]},"DOI":"10.19103/as.2024.152.09","URL":"https://doi.org/10.19103/as.2024.152.09","source":"crossref"},{"id":"doi:10.1016/j.jafr.2026.102984","type":"article-journal","title":"Biologically mediated degradation of metal–organic frameworks for precision agriculture","abstract":"The extensive use of traditional agrochemicals leads to systemic inefficiencies with large proportion of active agrochemicals being lost to leaching, volatilization and photolysis. Precision agriculture needs advanced delivery systems that can match the demand of the crop to the release of agrochemicals. Metal–organic frameworks (MOFs) are emerging as promising platforms for controlled delivery of fertilizers and pesticides in agricultural systems. This review synthesizes the concept of biologically mediated degradation of MOFs, where framework disassembly is governed by biological processes rather than passive mechanisms. Microbial activity, rhizosphere acidification, and plant root exudates play key roles in regulating degradation behavior and nutrient release. These interactions enable enhanced release efficiency in soil environments while maintaining stability under non-biological conditions. Despite these advantages, challenges such as the low large-scale yields (∼27%) continue to limit practical application, and scalable and sustainable synthesis methods, especially aqueous-phase routes, are required. The development of biodegradable and biocompatible MOF systems should also be accompanied to safe soil integration. By aligning material design with biological functionality, MOFs offer a sustainable platform for nutrient management and precision crop protection. • Metal-organic frameworks enable biologically responsive agrochemical release. • Rhizosphere microbes and root exudates trigger controlled MOF degradation. • MOF systems improve nutrient efficiency and reduce agrochemical losses. • Encapsulation enhances UV stability and reduces toxicity to non-target species. • MOFs support precision agriculture and sustainable crop protection.","author":[{"family":"Haidri","given":"Irfan"},{"family":"Qasim","given":"Muhammad"},{"family":"Ullah","given":"Qudrat"},{"family":"Amir","given":"Muhammad"},{"family":"Haider","given":"Waqas"},{"family":"Nguyen","given":"Hien"},{"family":"Promwee","given":"Athakorn"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.jafr.2026.102984","URL":"https://doi.org/10.1016/j.jafr.2026.102984","source":"crossref"},{"id":"doi:10.1201/9781003520733-26","type":"article-journal","title":"Planting the future","abstract":"The progress of modern technology affects every aspect of human endeavor, including agriculture. The digital age, which allows for the widespread use of the internet and mobile devices, has proven beneficial not only to huge enterprises but also to agribusiness owners/farmers. While new tools and technology have always been essential for agricultural operations and food production, the development and use of innovative farming technologies are currently driven by pressing challenges. The most important one is food security: the International Monetary Fund estimates that by 2050, food production will need to rise by 70% to keep up with the world’s population growth. Precision farming, or smart agriculture, is centered on using cutting-edge technology (sensors, big data, satellites, cloud computing, and the Internet of Things) to track, automate, monitor, and analyze agricultural processes. Utilizing these cutting-edge technologies has continued to increase production levels, lessen the labor for farmers, and even lower the cost of agriculture. Smart agriculture is becoming the center of innovation in many developing nations to boost their economies because of its increasing significance and value. Smart farming offers a lot of potential, but there are still issues like high implementation costs, worries about data security, and low digital literacy among farmers. This chapter has outlined the ongoing revolution in digital farming by examining the state of smart agriculture today, its essential technologies, its applications, and the challenges farmers face in the smart farming age, thereby identifying the research gap in the intelligent farming system.","author":[{"family":"Jain","given":"Neelu"},{"family":"Monika"},{"family":"Kumar","given":"Pardeep"},{"family":"Sharma","given":"Manoj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003520733-26","URL":"https://doi.org/10.1201/9781003520733-26","source":"crossref"},{"id":"doi:10.71443/9789349552364-15","type":"article-journal","title":"AI in Climate Smart Agriculture for Risk Mitigation and Adaptation Strategies","abstract":"Climate change poses a significant threat to global agriculture, requiring innovative solutions to enhance resilience and sustainability in farming systems. Artificial Intelligence (AI) has emerged as a transformative tool for addressing climate-related challenges, enabling precise risk mitigation and effective adaptation strategies. This chapter explores the integration of AI in climate-smart agriculture (CSA), focusing on its applications for risk assessment, crop management, and resource optimization. Key AI technologies, including machine learning, computer vision, and predictive analytics, are examined in the context of climate-smart practices, demonstrating their potential to optimize agricultural productivity while minimizing environmental impact. The chapter also addresses critical challenges related to data collection, quality, and accessibility, emphasizing the need for standardized frameworks and robust data infrastructures. Furthermore, ethical and legal considerations, including data privacy and security, are discussed in relation to AI implementation in agriculture. By highlighting the role of AI in improving climate resilience, this chapter provides a comprehensive overview of its potential to revolutionize agricultural practices in the face of changing environmental conditions. The findings underscore the importance of interdisciplinary collaboration in advancing AI-driven solutions for sustainable agriculture, ensuring food security, and mitigating the effects of climate change.","author":[{"family":"Singh","given":"Brajesh"},{"family":"Ramamurthy","given":"M"},{"family":"Suresh","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-15","URL":"https://doi.org/10.71443/9789349552364-15","source":"crossref"},{"id":"doi:10.1007/s11119-026-10413-x","type":"article-journal","title":"Scalable field boundary refinement from satellite time series using deep learning","abstract":"Abstract Purpose Accurate spatial management units are fundamental to precision agriculture because they directly influence crop classification, input optimization, and decision-support systems. However, administrative agricultural parcels often aggregate multiple crop units within a single polygon, introducing structural uncertainty into parcel-based crop mapping and management analytics. This study addresses inaccuracies in existing agricultural parcel boundaries that introduce upstream errors that cascade into downstream analyses, including crop mapping, yield estimation, and decision-support workflows. Consequently, the proposed framework is designed for parcel refinement rather than semantic crop classification. Methods We selected parcel refinement as a polygon-conditioned semantic segmentation problem, leveraging existing parcel geometries to generate more accurate, agronomically coherent management units rather than performing field boundary detection from scratch. Implemented at the national scale in Israel, the framework uses a computationally efficient single-sensor Sentinel-2 time-series approach based on harmonic modeling to generate phenology-aware composites that improve robustness to noise, cloud contamination, and temporal gaps. Geometry-preserving synthetic data augmentation was incorporated to improve boundary learning under limited annotations, and outputs were evaluated using both pixel-level segmentation metrics and polygon-level operational correctness. Results We compared a zero-shot Segment Anything Model (SAM) pipeline with supervised deep learning architectures (U-Net, DeepLabV3, and SegFormer). U-Net achieved the strongest boundary performance (mean IoU = 0.76) and improved polygon-level correctness from 75.16% to 87.8% (absolute gain: 12.64% points; relative improvement: 16.8%). Conclusion The proposed framework provides a scalable pathway to reduce structural uncertainty in agricultural parcel databases and strengthen the spatial foundation of precision agriculture and data-driven agricultural management systems.","author":[{"family":"Edri","given":"Adi"},{"family":"Edan","given":"Yael"},{"family":"Fine","given":"Lior"},{"family":"Rozenstein","given":"Offer"},{"family":"Paz-Kagan","given":"Tarin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10413-x","URL":"https://doi.org/10.1007/s11119-026-10413-x","source":"crossref"},{"id":"doi:10.1201/9781003637264-16","type":"article-journal","title":"Enhancing Agricultural Traceability and Precision Farming with Nanoparticle-Based Biosensors","abstract":"The agricultural sector is vital to human well-being, providing essential resources for the survival and existence of both humans and wildlife. Recent efforts have focused on increasing agricultural yields by conducting extensive research with sensors and nanotechnology. Using sensor data, agricultural products can now be tracked and traced more efficiently from farm to market. The development of advanced biosensors for precision farming is made possible by nanoparticles. This technology improves agricultural sustainability and efficiency by enabling real-time monitoring of plant health and nutrient levels. Proteinoid polymers are being investigated as effective agro-chemical transporters, offering a targeted and regulated method to increase agricultural output while reducing environmental impact. In this book chapter, we provide an overview of the cutting-edge uses of nanosensors in agriculture. We have also emphasized on the effective management of food from farm to market that helps in satisfying the growing demand for food. Our proposed bidirectional LSTM model obtained an accuracy of 98.30% in detecting ethylene and an RMSE value of 0.2621. Furthermore, the challenges and opportunities associated with the use of nanosensors in the field of food safety were briefly addressed. We conclude by highlighting machine learning and artificial intelligence (AI) as tools for food process optimization. These technologies are used in the food industry to increase productivity, reduce waste, and provide personalized customer experiences.","author":[{"family":"Sahoo","given":"Somya"},{"family":"Bulasara","given":"Phani"},{"family":"Sinha","given":"Ankit"},{"family":"Raj","given":"Piyush"},{"family":"Singh","given":"Shreyam"},{"family":"Mishra","given":"Satyam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003637264-16","URL":"https://doi.org/10.1201/9781003637264-16","source":"crossref"},{"id":"doi:10.1007/s11119-026-10359-0","type":"article-journal","title":"Expanding the services of cereal/legume cover crop mixtures: From UAV-RGB species-dominance identification to precision-based pre-plant nitrogen decisions","abstract":"Pre-plant nitrogen (N) fertilization is typically applied uniformly despite within-field variability in soil N availability, particularly following service crops (SC). In legume-cereal SC mixtures, competitive dominance reflects soil N conditions and may serve as an ecological indicator of N availability. This study assessed whether UAV-RGB species dominance mapping can support spatial pre-plant N decisions for a subsequent cash crop. The framework was developed in a controlled plot during one SC season with four N rates (0–120 kg N ha⁻¹) applied to create soil N variability. UAV-RGB imagery was acquired three times during the season and combined with biomass, soil N, and nitrogen nutrition index (NNI) measurements. A legume-to-cereal dominance ratio was derived from classified imagery and linked to NNI to define a threshold for binary pre-plant N decision mapping. The approach was subsequently evaluated in a 20-ha commercial field monitored over two seasons, using UAV imagery and biomass measurements. Soil N availability strongly influenced species dominance: legumes dominated under low N conditions, whereas cereals dominated under higher N levels. In the experimental plot, the dominance ratio derived from mid-season imagery (64–77 days after sowing (DAS)) corresponded with NNI measured later (91 DAS), enabling delineation of areas likely to require or not require pre-plant N fertilization. In the commercial field, classified canopy proportions aligned with measured biomass in both seasons. The experimentally derived threshold distinguished between an N-deficient and N-fertilized seasons, where most subplots required or did not require pre-plant N. These findings demonstrate that UAV-RGB mapping of species dominance in legume-cereal SC mixtures can indicate soil N availability before cash crop establishment. Although agronomic validation of variable-rate pre-plant fertilization was not conducted, the study presents a transferable framework that integrates SC-based soil management with precision nitrogen decision support, using accessible remote sensing tools.","author":[{"family":"Futerman","given":"Simon"},{"family":"Laor","given":"Yael"},{"family":"Eshel","given":"Gil"},{"family":"Aharon","given":"Shlomi"},{"family":"Cohen","given":"Yafit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s11119-026-10359-0","URL":"https://doi.org/10.1007/s11119-026-10359-0","source":"crossref"},{"id":"doi:10.1016/j.snr.2026.100502","type":"article-journal","title":"Machine learning-integrated plant biosensors for precision agriculture: A systematic review of stress detection, pathogen monitoring and smart crop management","abstract":"Plant biosensors combining biological recognition elements with electrochemical, optical and CRISPR based transduction platforms have emerged as robust field deployable tools for the detection of stress biomarkers, pathogens and phytohormones directly within agricultural settings. Sophisticated computational methods are needed to tackle the potential of these devices which generate complex high dimensional data. By following PRISMA guidelines, this systematic review critically assesses the state of the art in machine learning algorithms like deep learning, random forest and time series models. These are used to convert raw biosensor data into actionable agronomic insights that provide early stress prediction, multi analyte classification and real time crop health assessment. The review provides a thorough survey of biosensing platforms including electrochemical, fluorescent, aptamer based, antibody based and multiplexed architectures as well as evaluates their coupling with Internet of Things (IoT) networks and artificial intelligence-based decision systems to enable precision agriculture. Some of the primary challenges are the lack of labelled field datasets, the complexity of making cross-crop models work for all crops and the lack of consistent machine learning benchmarking pipelines for biosensor data, though strategies such as transfer learning, self-supervised learning and data augmentation offer promising paths forward. The review discusses about future chances to put lightweight machine learning models directly into biosensor platforms for edge computing and wearables. This work is in line with the UN SDGs, especially SDG 2, SDG 12 and SDG 13 by integrating biosensor innovation with data-driven analytics for sustainable, climate-resilient agriculture.","author":[{"family":"Sharma","given":"Anchal"},{"family":"Sharma","given":"Madan"},{"family":"Priyadarshi","given":"Himanshu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.snr.2026.100502","URL":"https://doi.org/10.1016/j.snr.2026.100502","source":"crossref"},{"id":"doi:10.3389/fagro.2025.1665444","type":"article-journal","title":"Precision agriculture techniques for optimizing chemical fertilizer use and environmental sustainability: a systematic review","abstract":"Precision agriculture (PA) techniques are critical for optimizing chemical fertilizer use in modern farming. However, a comprehensive synthesis of their effectiveness in enhancing nutrient management and reducing environmental impacts is lacking. This systematic review, following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, analyzes global evidence to evaluate PA’s role in improving fertilizer application practices. Our analysis of 51 peer-reviewed studies reveals that PA significantly enhances nutrient use efficiency and crop yields. Specifically, 37.25% of studies highlight PA-driven technological innovations, while 29.41% document major improvements in nutrient management. These findings confirm that PA promotes sustainable fertilizer utilization and reduces environmental footprints. To realize its full benefits, policymakers must address key challenges to widespread adoption, such as cost barriers, lack of technical expertise, and infrastructure limitations.","author":[{"family":"Cai","given":"Baozhong"},{"family":"Shi","given":"Fang"},{"family":"Geremew","given":"Betelhem"},{"family":"Addis","given":"Amsalu"},{"family":"Abate","given":"Meseret"},{"family":"Dessie","given":"Wubliker"},{"family":"Bayu","given":"Tesfaye"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3389/fagro.2025.1665444","URL":"https://doi.org/10.3389/fagro.2025.1665444","source":"crossref"},{"id":"doi:10.55041/ijsrem57306","type":"article-journal","title":"AI-Integrated Smart Agriculture System Using Autonomous Rover for Precision and Sustainable Farming","abstract":"Abstract— The goal of AI-driven Smart Agriculture through Fully Automated Agricultural Machines (AI-Integrated SMART Agriculture System Using Autonomous Rover for Precision and Sustainable Farming), is to increase yield in traditional agriculture by using integrated technology (AI) and advanced sensors connected to the internet, with the ability to move freely without human operators. By equipping a multi- sensor rover with multiple sensors (moisture, ph, DHT11 temperature, humidity, colour, and many others) and a high- resolution camera module, it will be possible to capture current field conditions, and accurately monitor soil quality, crop growth, and environmental conditions in real-time. The data collected through the rover will give the farmer a complete record of their agricultural activities, which will include the analysis of soil quality, crops' growth and environmental conditions over a period of time. Through the use of a CNN- based (Convolutional Neural network) model, each crop will have its own “leaf disease” detection and stress assessment model to find out if there is an infection and/or nutrient deficiency in the crop as soon as possible, so the farmer can take preventative action before too much time has passed. A K- Nearest Neighbors (KNN)-based and/or many other machine learning models will be used to classify and predict crop yield. In addition to the above, a LLM (Large Language Model)-based advisory system will be integrated to provide the farmer with a summary report of all the information received from the rover, and a recommendation for the most efficient methods of managing their resources (water and nutrients), as well as other general information related to the efficient and sustainable use of water, fertilizers, pesticides, and natural resources in the agricultural environment. In order to guarantee spatial precision and effective field coverage, data can be collected from several zones thanks to the autonomous rover's independent field navigation. This project creates a comprehensive precision agriculture framework that improves decision-making, decreases manual labor, conserves natural resources, and increases overall crop productivity by fusing AI-driven analytics, IoT-enabled sensing, computer vision, and autonomous navigation. This advances sustainable and technology-driven farming. Keywords— Precision Agriculture, Autonomous Rover, Machine Learning, IoT Sensors","author":[{"family":"Bagyalakshmi","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsrem57306","URL":"https://doi.org/10.55041/ijsrem57306","source":"crossref"},{"id":"doi:10.3390/geomatics6040089","type":"article-journal","title":"Geometric and Photogrammetric Assessment of Stratospheric Platform for Precision Agriculture Monitoring: A Multi-Campaign Analysis","abstract":"Remote sensing is widely recognized as a key technology across a wide range of technical and scientific domains, especially in agriculture. Although satellite data have long supported crop monitoring, their limitations in spatial resolution, revisit frequency and cloud coverage have often constrained their applications. High-resolution satellites, available from the beginning of the 2000s, have improved performance, particularly in the field of precision agriculture, but they remain expensive and inflexible. Unmanned Aerial Vehicles perform better in precision agriculture, offering flexibility and high levels of detail; however, their limited operational areas and short endurance flight times constrain their effectiveness. In this evolving landscape, High Altitude Pseudo Satellites (HAPSs), particularly high-altitude balloons, are emerging as a promising new technology that could fill the gaps between satellite and drone remote sensing. These platforms provide large area coverage with high-resolution imagery and long endurance flights at low operational expenses and ease of deployment. This study investigates the operational characteristics, strengths, and geometric limitations of data acquired by the CubeHAPS® platform, a high-altitude pseudo-satellite system, as a prerequisite for its application in precision agriculture. Focusing on experimental campaigns conducted in northern Italy in summer 2024 and 2025, the research characterizes platform stability, image block consistency, and photogrammetric quality through internal metrics. The results demonstrate measurable improvements between the two campaigns, attributed to the introduction of a stabilization system in 2025 and establishing the conditions under which the platform can support reliable photogrammetric reconstruction.","author":[{"family":"Bovio","given":"Lorenza"},{"family":"Miherea","given":"Victor"},{"family":"Fath","given":"Jannis"},{"family":"Boccardo","given":"Piero"},{"family":"Borgogno-Mondino","given":"Enrico"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/geomatics6040089","URL":"https://doi.org/10.3390/geomatics6040089","source":"crossref"},{"id":"doi:10.1016/j.inpa.2026.02.001","type":"article-journal","title":"A dynamic optimization model for precision irrigation of cherry tomato under mechanized cultivation using CatBoost","abstract":"• Correlation analysis revealed key indicators for each growth stage, including growth, photosynthesis, yield and quality. • TOPSIS and ML analyzed the characteristics of phenological periods and the water requirements, building dynamic irrigation models. • The CatBoost demonstrated superior performance (R 2 = 0.913, RMSE = 1.730, MAE = 1.238) among 12 machine learning algorithms. • Raspberry Pi automatic irrigation system with Catboost model increased the yield (16.85%) and IWUE (8.77%) over FAO method. Under mechanized cultivation, systemic modifications to the plant growth environment have profoundly impacted crop water requirements. Despite substantial advances in precision irrigation technologies, existing studies remain inadequate in capturing the dynamics of crop water demand across growth stages and in integrating irrigation management under variable cultivation conditions. In this study, a three-factor randomized split-plot experiment was conducted with two temperature regimes (ambient and ambient +2.3°C), two cultivation modes (wide–narrow and equidistant), and three irrigation levels (75% Ep, 100% Ep, and 125% Ep), yielding twelve treatments. Growth traits were quantified at each growth stage, together with final yield and fruit quality. Stage-specific key indicators were identified using Pearson correlation analysis. Optimal irrigation levels for each growth stage under different cultivation conditions were then determined by multi-objective optimization using the TOPSIS comprehensive evaluation model. Twelve machine-learning algorithms were trained to construct the irrigation decision model, among which CatBoost exhibited the highest predictive accuracy (R 2 = 0.913, RMSE = 1.730, MAE = 1.238). The optimized model was implemented and validated using an automatic irrigation system based on Raspberry Pi. Relative to the FAO-recommended irrigation strategy, the automated system significantly increased yield and irrigation water use efficiency (IWUE) by 16.85% and 8.77%, respectively, reduced fruit acidity by 36.36%, and decreased labor costs. Collectively, these findings provide a robust theoretical basis and practical technical framework for precision automatic irrigation in mechanized cultivation systems under future climate-warming scenarios.","author":[{"family":"Yang","given":"Taiguo"},{"family":"Xu","given":"Sihan"},{"family":"Wang","given":"Rongqun"},{"family":"Wang","given":"Junxing"},{"family":"Jiang","given":"Yu"},{"family":"He","given":"Daiwei"},{"family":"Li","given":"Rui"},{"family":"Zhang","given":"Zhi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.inpa.2026.02.001","URL":"https://doi.org/10.1016/j.inpa.2026.02.001","source":"crossref"},{"id":"doi:10.1016/j.precisioneng.2026.02.012","type":"article-journal","title":"A dual-joint compliant architecture for precision control in robotic neuroendoscopy","abstract":"Neuroendoscopy treats intracranial pathologies through millimeter-scale channels using endoscopes introduced along a straight trajectory from a cranial entry point to the target. The entry point acts as a Remote Center of Motion (RCM), which must remain fixed to follow the surgical plan and avoid damage around the entry point. Existing robotic RCM platforms rely on rigid multi-link structures, increasing complexity and footprint. To mitigate these limitations, we propose a compact dual-joint compliant mechanism for neuroendoscopic manipulation. Building on the Tetra II flexure architecture, we redesigned and optimized the joint for neurosurgical use. The end-effector holder is moved from the central axis to the side to improve visual access, facilitate sterile draping and allow rapid instrument exchange while preserving the RCM constraint. The mechanical design targets directionally uniform stiffness in the working plane while minimizing parasitic RCM displacements. The mechanism uses two identical compliant joints in series, with the connection angle treated as a design variable. For each angle, the response is obtained by analyzing each joint separately in FEM and combining their contributions via rotation matrices. An angular offset of 300° yields near-isotropic stiffness, with a root-mean-square error of 0.90 N/m from an ideal isotropic behavior. A PA12 prototype was tested under 0 . 1 ± 0 . 01 N radial loads. Experimental stiffness differed by ≤ 19% from FEM. The parasitic RCM displacement was 0.032 ± 0.018 mm for a 4.5°shaft rotation, well within the 1 mm neurosurgical tolerance. This dual-joint compliant RCM mechanism offers a practical alternative to conventional rigid-link designs. • Brain endoscopy needs millimetric pivoting to avoid hurting delicate tissue. • Compliant joints keep a stable pivot and remove footprint, friction, wear, backlash. • Dual-compliant joint for robotics neuroendoscopy. • New hybrid methodology for finding stiffness using FEM and rotation matrices.","author":[{"family":"Mariano","given":"Federico"},{"family":"Momi","given":"Elena"},{"family":"Berselli","given":"Giovanni"},{"family":"Jovanova","given":"Jovana"},{"family":"Mattos","given":"Leonardo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.precisioneng.2026.02.012","URL":"https://doi.org/10.1016/j.precisioneng.2026.02.012","source":"crossref"},{"id":"doi:10.3997/2214-4609.202655063","type":"article-journal","title":"Spatial Variability Analysis of Crops Based on the dSAVI Index for Precision Agriculture","abstract":"Summary This paper presents the results of a statistical assessment of the interannual variability of the soil-adjusted vegetation index dSAVI and the evaluation of its relationship with the moisture regime during the early growth stages of agricultural crops. The study was conducted on a production field with an area of 117 ha located in the Ternopil region. The dataset included multispectral Sentinel-2 Level-2A (Surface Reflectance) satellite imagery and the CHIRPS Daily climate dataset for 2023–2025. The methodological approach is based on the use of the dSAVI index, by which the soil background correction coefficient is dynamically determined as a function of NDVI, ensuring adaptive consideration of the proportion of bare soil and vegetation cover density. The analysis was performed for two phenological intervals: the early growth stage (15.05-05.06) and the stage of active vegetative growth of maize (15.06-05.07). Satellite data processing, composite image generation, and index calculation were performed in the Google Earth Engine environment, while spatial analysis and cartographic visualization were carried out in ArcMap. Statistical assessment of the relationships was conducted using the Pearson correlation coefficient. The results indicate pronounced interannual variability of dSAVI values within the study field. In 2025, a decrease in index values was recorded during both analyzed periods. A phase-dependent relationship between dSAVI and precipitation sums was identified: in the early stage, an inverse relationship was observed, whereas during the active growth stage, a positive correlation was detected. These findings confirm the necessity of considering the crop phenological stage when interpreting vegetation indices for crop monitoring and managing spatial heterogeneity in precision agriculture.","author":[{"family":"Buhai","given":"K"},{"family":"Zatserkovnyi","given":"V"},{"family":"Vorokh","given":"V"},{"family":"Mironchuk","given":"T"},{"family":"Shovkoplias","given":"T"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3997/2214-4609.202655063","URL":"https://doi.org/10.3997/2214-4609.202655063","source":"crossref"},{"id":"doi:10.1201/9781003743774-158","type":"article-journal","title":"Smart Next-Gen Approach in Precision Agriculture Using XGBoost-Based Federated Learning for Crop Prediction","abstract":"In India, a significant portion of the population continues to rely on agriculture as their primary source of livelihood. As an agri-rich nation, India is increasingly promoting technology-driven smart farming practices over conventional methods to enhance productivity and sustainability.To address this, we propose a scalable framework that integrates federated learning with an enhanced XGBoost ensemble classifier for crop recommendation based on soil nutrient levels (N, P, K) and other ecological parameters. Extensive simulations conducted on local clients (edge nodes), encompassing 22 crop varieties including lentils and fruits, ensure data privacy by storing only model responses at the global level to achieve model accuracy in terms of precision value 95%, recall score and F1 score 97% and 98% accordingly.","author":[{"family":"Saha","given":"Manab"},{"family":"Saha","given":"Priya"},{"family":"Dholey","given":"Milan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003743774-158","URL":"https://doi.org/10.1201/9781003743774-158","source":"crossref"},{"id":"doi:10.1109/metroagrifor63043.2024.10948867","type":"article-journal","title":"Multispectral Imaging Supervised by Optical Spectrometry for Close Acquisition in Precision Agriculture","abstract":"Satellite and airborne multispectral imaging has shown huge potential for many agricultural applications, primarily for plant indices. Imaging close to plants allows further expansion of this potential, such as early identification of plant disease or sufficient maturity status for harvest. To this aim, the joint use of optical spectrometry and multispectral imaging is shown effective: the most informative spectral bands for a given application can be identified so that the number of filters could be reduced to be mounted on a dedicated multispectral imaging system. To validate the on-field approach, we developed a compact, modular multispectral imaging system equipped with four sensors in the visible and near- IR band, a sensor in the far-IR, and a set of sensors to measure environmental parameters (T, RH, CO2, lux). This system collects only the most informative data needed for specific tasks from which spectral indices or processing methods can be implemented to improve automated analysis also through artificial intelligence approaches.","author":[{"family":"Scutelnic","given":"Dumitru"},{"family":"Muradore","given":"Riccardo"},{"family":"Daffara","given":"Claudia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/metroagrifor63043.2024.10948867","URL":"https://doi.org/10.1109/metroagrifor63043.2024.10948867","source":"crossref"},{"id":"doi:10.1080/15440478.2026.2708455","type":"article-journal","title":"Climate Change Impacts on Worldwide Cotton Productivity and Agricultural Income: Physiological, Econometric, and Precision Agriculture Perspectives","abstract":"Climate change is expected to affect all sectors of the global economy, with agriculture being particularly vulnerable due to its dependence on temperature and precipitation. Cotton is especially sensitive to these changes as its productivity relies on suitable thermal conditions, water availability, and stable reproductive development. This study investigates the effects of climate change on cotton productivity and agricultural income in seven major cotton-producing countries, including Australia, Brazil, China, India, Pakistan, Türkiye, and the United States, over the period 1971-2023. Long-run relationships were examined using the Westerlund cointegration test, country-specific effects were estimated with the Augmented Mean Group (AMG) estimator and verified using Common Correlated Effects (CCE) approach, while short-run dynamics were assessed through the Dumitrescu-Hurlin panel causality test. Results reveal significant long-run relationships between climate variables, cotton productivity, and agricultural income, although the magnitude and direction of these effects vary across countries. In contrast, short-run effects appear limited and heterogeneous. To strengthen the interpretation of the econometric findings, the results are compared with experimental evidence on cotton heat stress and physiological responses. Together, the evidence indicates that climate change influences cotton productivity mainly through temperature-sensitive processes such as photosynthesis, reproductive development, and fiber formation, underscoring the need for country-specific adaptation strategies and climate-resilient agricultural policies.","author":[{"family":"Zuhal","given":"Mustafa"},{"family":"Erkencioglu","given":"Bedriye"},{"family":"Tokel","given":"Dilek"},{"family":"Senol","given":"Celal"},{"family":"Demir","given":"Hacer"},{"family":"Ozyigit","given":"Ibrahim"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/15440478.2026.2708455","URL":"https://doi.org/10.1080/15440478.2026.2708455","source":"crossref"},{"id":"doi:10.1002/cft2.70108","type":"article-journal","title":"Decision‐making factors for variable rate application of seed and fertilizer in precision agriculture systems: A review","abstract":"Abstract Input management practices within precision agriculture systems have enabled grain and oilseed producers to apply agricultural inputs variably, facilitating resource, yield, and profit optimization. Despite significant progress in variable rate technologies, research comparing different methodologies and comprehensive guidelines to assist producers in their decision‐making processes is still lacking. This research article aimed to identify and summarize the suggested decision‐making factors for determining variable seed rates and variable fertilizer applications. A systematic review of the literature from the last 2 decades was conducted, summarizing various approaches within precision agriculture related to variable rate applications in canola ( Brassica napus L.), maize ( Zea mays L.), soybean [ Glycine max (L.) Merr.], and wheat ( Triticum aestivum L.). Findings revealed a wide range of decision‐making factors guiding variable rate applications, from site‐specific soil characteristics to complex data‐driven recommendations. Focus crops were maize and soybean in terms of variable seeding rates, while nitrogen was the only fertilizer source discussed. Most articles appeared to address a single specific decision‐making factor, with limited comparisons drawn between different methods. The results underscore the complexity of variable rate decisions, especially in terms of the influence of weather, highlighting the overarching impact that rainfall has on grain and oilseed production in dryland systems. To maximize the effectiveness of variable rate applications across diverse production systems and justify the initial investment in these technologies, it is essential to develop adaptable, context‐specific guidelines for seed and fertilizer management.","author":[{"family":"Truter","given":"Karen"},{"family":"Delport","given":"Marion"},{"family":"Meyer","given":"Ferdinand"},{"family":"Swanepoel","given":"Pieter"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/cft2.70108","URL":"https://doi.org/10.1002/cft2.70108","source":"crossref"},{"id":"doi:10.33545/26646064.2026.v8.i2b.695","type":"article-journal","title":"Impact of precision nutrient management on yield, quality and economics of rice-based cropping systems","abstract":"Policy statement: national fertilizer subsidy programmes across much of Angola and comparable rice-growing regions continue to promote a single blanket recommended dose regardless of field-specific soil status, a policy this two-season research set out to test against four precision nutrient management approaches that adjust fertilizer application to actual crop and soil need. Five nutrient management strategies, farmer practice (no formal recommendation), blanket recommended dose of fertilizer (RDF), soil test crop response (STCR)-based recommendation, Leaf Color Chart (LCC)-guided nitrogen management, and Nutrient Expert decision-support tool recommendation, were compared for rice grain yield, nitrogen use efficiency, grain quality, and net economic return. The Nutrient Expert-guided treatment produced the highest grain yield at 6.9 t per hectare, exceeding farmer practice by 41% and blanket RDF by 18%, while also delivering the highest nitrogen use efficiency and net economic return among the five approaches tested. Leaf Color Chart-guided management, a considerably simpler and lower-cost precision approach than either STCR or Nutrient Expert, still captured most of the yield and efficiency benefit, reaching 94% of Nutrient Expert's yield and 91% of its net return, suggesting this simpler tool offers a strong practical entry point for precision nutrient management where more sophisticated decision-support tools are not readily accessible. Yield response to nitrogen status, measured through Leaf Color Chart readings, followed a curvilinear rather than linear pattern, with yield gains diminishing and eventually reversing at the highest chart readings, confirming that nitrogen application beyond crop need reduces rather than continues raising yield. These findings challenge blanket fertilizer recommendation policy and support precision nutrient management, even in its simpler and more accessible forms, as a genuinely superior alternative on yield, efficiency, and economic grounds simultaneously.","author":[{"family":"Mbumba","given":"Domingos"},{"family":"Sakala","given":"Esperanca"},{"family":"Cazombo","given":"Joao"},{"family":"Kassoma","given":"Ana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.33545/26646064.2026.v8.i2b.695","URL":"https://doi.org/10.33545/26646064.2026.v8.i2b.695","source":"crossref"},{"id":"doi:10.1109/idciot67589.2026.11455755","type":"article-journal","title":"Interpretable AI Enabled Solutions for Crop Selections, Yield Estimation and Rainfall Analysis in Precision Agriculture","abstract":"The rapid growth of the world's population and the growing need for food security have made modern farming very difficult. Traditional farming methods often don't work well with changes in the environment, low yields and changes in rainfall. In order to solve these limitations this study focuses on the creation of usable artificial intelligence driven solutions for crop selection, yield prediction and rainfall analysis thus enabling precision agriculture. The goal is to give farmers accurate and simple data-driven insights so that they can make important decisions about crop management that are both economical and clear. The suggested method combines a number of machine learning and deep learning models such as Decision Tree, Random Forest, AdaBoost, XGBoost, Support Vector Machine, Gradient Boosting Machine, k-Nearest Neighbors, Artificial Neural Network, Recurrent Neural Network, Long Short-Term Memory and Convolutional Neural Network. To make predictions easier and build trust among those involved clear techniques are used. The framework's test outcomes show that it has a very high prediction accuracy of 98.9% which makes agricultural forecasting much more accurate. The study finds that the combination of advanced algorithms and understanding not only improves predictive performance but also makes it possible for farming practices that are both smart and economical and can adjust to future agricultural needs.","author":[{"family":"Reddy","given":"PPK"},{"family":"Reddy","given":"KS"},{"family":"Reddy","given":"CCV"},{"family":"Vandana","given":"P"},{"family":"Madhusudhan","given":"G"},{"family":"Chandrakala","given":"N"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/idciot67589.2026.11455755","URL":"https://doi.org/10.1109/idciot67589.2026.11455755","source":"crossref"},{"id":"doi:10.33545/26180723.2026.v9.i1i.2989","type":"article-journal","title":"Precision UAV Spraying: Impacts of differential application rates on cotton yield","abstract":"Unmanned Aerial Vehicles (UAVs) offer a promising alternative to conventional ground-based crop management by reducing mechanical damage, soil compaction and inefficiencies in spray application. This study assessed the performance of UAV-based spraying in cotton cultivation compared to traditional hand sprayers, with emphasis on optimizing spray volumes across different crop growth stages. Since cotton crop density increases progressively, constant spray volumes can lead to wastage; therefore, three nutrient application rates (18, 25, and 30 L/ha) and three herbicide application rates (25, 37, and 50 L/ha) were evaluated. Crop growth parameters (plant height and leaf area) and remote sensing indices (NDVI and LAI) were monitored from spraying to harvest, while spray deposition was quantified using Water Sensitive Papers (WSP). The highest yield (205.2 kg) was recorded with 50 L/ha herbicide and 30 L/ha nutrient application. Remote sensing data and growth parameters indicated uniform crop health up to 40 days after sowing (DAS). Beyond this stage, 25 L/ha nutrient application was optimal until 80 DAS, while 30 L/ha was most effective from 80 to 150 DAS due to increased crop density. Overall, the findings demonstrate that UAV spraying enhances yield and efficiency by tailoring application volumes to crop growth stages, with effective post-emergent weed control being critical to maximizing cotton productivity.","author":[{"family":"Hp","given":"Vinodh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.33545/26180723.2026.v9.i1i.2989","URL":"https://doi.org/10.33545/26180723.2026.v9.i1i.2989","source":"crossref"},{"id":"doi:10.33545/2664844x.2026.v8.i3f.1283","type":"article-journal","title":"Optimizing Products with Precision: A Review of Response Surface methodology","abstract":"Response Surface Methodology (RSM) is a powerful statistical tool widely used in optimizing complex processes across various industries, including agriculture, food technology, and biological sciences. This methodology employs mathematical and statistical models to identify the relationships between input variables and output responses, allowing researchers to optimize processes with fewer experimental runs. RSM is particularly effective in experiments involving multiple variables where traditional optimization methods may fail to capture intricate interdependencies. This review explores the fundamentals of RSM, including its design strategies, such as factorial designs and central composite designs, which enable efficient model fitting and optimization. Key applications of RSM in agriculture and horticulture, particularly in optimizing product quality and process efficiency, are discussed. The review also highlights the role of regression modeling in determining functional relationships between variables, and the advantages of second-order models in capturing non-linear behaviors. By presenting a comprehensive overview of RSM, including its application in experimental design, model fitting, and optimization, this paper underscores its importance as a robust tool for enhancing precision and efficiency in scientific and industrial research.","author":[{"family":"Rs","given":"Neethu"},{"family":"Priyanka","given":"BD"},{"family":"Kumar","given":"V"},{"family":"Santhosh","given":"Sreehari"},{"family":"Krishnamurthy","given":"Pradeep"}],"issued":{"date-parts":[[2026]]},"DOI":"10.33545/2664844x.2026.v8.i3f.1283","URL":"https://doi.org/10.33545/2664844x.2026.v8.i3f.1283","source":"crossref"},{"id":"doi:10.1002/9781394336326.ch3","type":"article-journal","title":"Applications of Aerial Aided Edge Computing in Disaster Management and Emergency Response, Environmental Monitoring and Conservation, Precision Agriculture and Crop Management, Infrastructure Inspection and Maintenance, Surveillance, and Public Safety","abstract":"Aerial Aided Edge Computing (AAEC) is an advancement of the technological revolution that incorporates edge computing with Unmanned Aerial Vehicles (UAVs), enabling instant data processing, and making decisions directly at the data collection source. This chapter discovers the AAEC applications and explores the challenges and future directions to gain insights into the role of AAEC across various sectors. AAEC eases the rapid situational awareness and efficient resource allocation in disaster management and emergency response. It provides real-time iconography and data analysis for search and emergency missions, destruction evaluation, and resource dissemination. AAEC enhances environmental monitoring and conservation efforts by providing exhaustive and sustainable Wildlife monitoring, forest well-being, and Contamination levels, facilitating the implementation of proactive conservation strategies. AAEC facilitates advancements in Precision agriculture and crop management to empower the monitoring of crop health, soil assessment, and field monitoring, enabling resource optimization and elevating crop productivity. In Infrastructure inspection and maintenance, the AAEC is integrated with UAVs to ensure prior detection of failures while performing detailed inspections of buildings, roads, and bridges. Ultimately, by employing data processing in real-time and analysis in the surveillance and public safety field, AAEC improves crime detection and prevention, crowd monitoring and traffic management. Transversely, in all these applications, AAEC delivers substantial advantages that include enhanced efficiency, elevated safety, and minimized operational costs.","author":[{"family":"Lakshmi","given":"K"},{"family":"Parvathavarthini","given":"S"},{"family":"Thangavel","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394336326.ch3","URL":"https://doi.org/10.1002/9781394336326.ch3","source":"crossref"},{"id":"doi:10.71026/ls.2026.030104","type":"article-journal","title":"Design of LoRaWAN Network Applying in Organic Greenhouse Farming","abstract":"Organic farming is vital for promoting sustainable agriculture and food safety in Laos. Precision monitoring of environmental parameters within greenhouses is essential to enhance crop productivity and maintain organic standards. This paper presents the design and implementation of a LoRaWAN-based wireless sensor network for environmental monitoring in organic greenhouse farming. The study aims to design a LoRa wireless communication network and develop a high-performance data transmission model by implementing and comparing star and mesh topologies. The designed system consists of 3 sensor nodes (End Nodes) and 1 gateway node, and its performance is tested in both closed and open organic greenhouses. Network performance was evaluated using an Anritsu MS2720T Spectrum Master. Spectrum analysis confirmed stable and viable signal propagation in the 433 MHz band, with a robust signal-to-noise ratio suitable for reliable data transmission. The star topology demonstrated superior performance inside the greenhouse with a 98% Packet Delivery Ratio (PDR) and stable communication at 10 meters, compared to 85% PDR for the mesh topology. These results confirm that the star topology is more reliable for data transmission in the obstructed greenhouse environment, providing a validated model for efficient environmental monitoring in support of sustainable organic farming in Laos.","author":[{"family":"Pathoummalath","given":"Nion"},{"family":"Panthongsy","given":"Phosy"},{"family":"Lakanchanh","given":"Donekeo"},{"family":"Parmanee","given":"Thay"},{"family":"Southisombath","given":"Phouthong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71026/ls.2026.030104","URL":"https://doi.org/10.71026/ls.2026.030104","source":"crossref"},{"id":"doi:10.1016/j.asej.2026.104118","type":"article-journal","title":"Precision agriculture using a low-cost vertical take off and landing tailsitter: Design and performance analysis","abstract":"Unmanned aerial vehicles (UAVs) for precision agriculture face a fundamental design trade-off: multirotor platforms provide hovering capability but suffer from limited endurance, while fixed-wing aircraft offer superior range but require runways incompatible with small agricultural plots.This work presents the design and performance analysis of a low-cost tailsitter architecture, focusing on the novel integration of a frugal, minimalist hardware stack with an energy-optimized flight control system. This unique architecture achieves maximum power efficiency and stability, positioning the platform for widespread, accessible adoption in the precision agriculture domain. Considering this analysis of aircraft where seamless transition from the hover to the forward highlight is done for a niche understanding with the prospective level of flexibility compared with the traditional UAVs. This utility makes this class of UAVs well suited for a wide range of applications, including surveillance, transportation, and farming. Particularly in the agricultural sector there is a huge potential from the adoption of tailsitters with digitization becoming essential for improving agricultural yields. In developing economies, to address the cost barrier this work makes use of lightweight Depron material and off-the-shelf avionics to achieve a total production cost of approximately $140 USD (excluding camera/sensor). This work aims to propose a low-cost tailsitter with a custom flight controller that is power efficient, stable, manoeuvrable for precision farming and the low-cost architecture is a key technical design achievement that enables widespread adoption regardless of region. The present work affirms the aerodynamic design with propulsion efficiency by static analysis and simulation studies, therefore confirming its architectural suitability for precision agriculture. The 970-gram aircraft employs a custom flight controller built based on Teensy 4.1 microcontroller, achieving 3300 Hz control loop rate. Performance analysis indicates that the vehicle is projected to consume significantly less power (3.05 W/min) compared to the power consumption of a quadcopter (6.1 W/min), showcasing power efficiency. Additionally, with a static thrust-to-weight ratio of 1.67:1, the VTOL demonstrates excellent stability and manoeuvrability, enabling extremely short take-off runs and vertical climb-outs.","author":[{"family":"Aswin","given":"R"},{"family":"Reka","given":"SS"},{"family":"Karrthikeyan","given":"K"},{"family":"Venugopal","given":"Prakash"},{"family":"Ponraj","given":"Abraham"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.asej.2026.104118","URL":"https://doi.org/10.1016/j.asej.2026.104118","source":"crossref"},{"id":"doi:10.1109/etaact69135.2026.11541876","type":"article-journal","title":"Smart Indian Farmer Assistant: A Tri-Modal AI Framework for Precision Agriculture Using MobileNetV2, XGBoost, and Multimodal Language Models","abstract":"The agriculture sector of today is at a crossroads and has to tackle a tripartite challenge: delayed pathological diagnosis, empirical treatment, uncertainty regarding crops to be grown, and acute lack of available agronomic knowledge. In this scenario, this paper examines the \"Comprehensive Smartphone-Based System\" designed to serve as a Virtual Agricultural Scientist. The proposed technique is based on the integration of MobileNetV2 for offline disease detection, XGBoost for soil-parameter-based crop recommendation, and Gemini 1.5 Flash for reasoning-based validation. Experimental validation on a dataset of over 54,000 images shows a classification accuracy of 98.24% with an inference latency of only 26 milliseconds. At the same time, the XGBoost model is also able to predict the best crops with an accuracy of 99.65%. In addition, in situations where the confidence in models is not very high, the Gemini model provides opportune \"second opinions,\" correcting errors or resolving ambiguous symptoms in 68% of such cases. Notably, these modules for diagnosis and consultation are designed to function in an offline manner, providing constant support to farmers in conditions of limited connectivity.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/etaact69135.2026.11541876","URL":"https://doi.org/10.1109/etaact69135.2026.11541876","source":"crossref"},{"id":"doi:10.1002/ldr.70502","type":"article-journal","title":"Economic Returns From\n                    <scp>AI</scp>\n                    ‐Driven Precision Agriculture in Degraded Ecosystems: Productivity Effects Measured Using\n                    <scp>UAV</scp>\n                    Remote Sensing","abstract":"ABSTRACT Land degradation has significantly reduced agricultural productivity worldwide, with over half of the world's agricultural land classified as degraded, leading to substantial annual losses. Precision agriculture powered by artificial intelligence (AI) offers a promising solution to rehabilitate degraded ecosystems by optimizing resource use and improving yields sustainably. This study evaluates the economic benefits of AI‐driven precision agriculture, focusing on AI‐based irrigation scheduling and productivity monitoring using unmanned aerial vehicle (UAV) remote sensing with LiDAR. This study proposed a deep neural network–based machine learning framework that integrates high‐frequency UAV campaigns acquiring multispectral and LiDAR data over degraded agricultural plots. These datasets are processed by AI algorithms to estimate crop requirements and optimize irrigation schedules. The model, tested in a conceptual mixed‐farming scenario, employs machine learning techniques, including Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM). Compared to the conventional method, these models show accuracy improvements of 3.2%, 2.7%, and 4.3%, respectively, with Kappa coefficients improving by 0.064, 0.044, and 0.087. The results demonstrate significant productivity gains, with crop yields increasing by 15 to 25, along with notable water savings, leading to improved economic returns. Remote sensing measurements show enhanced vegetation cover and biomass on rehabilitated plots. The study concludes that investment in AI and UAV technology can yield a positive return on investment (ROI) through higher yields and reduced input costs over several growing seasons, based on observations in Shaanxi and Hebei provinces, China.","author":[{"family":"Liang","given":"Min"},{"family":"Nan","given":"Li"},{"family":"Peng","given":"Bi"},{"family":"Bo","given":"Gao"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/ldr.70502","URL":"https://doi.org/10.1002/ldr.70502","source":"crossref"},{"id":"doi:10.3390/agriengineering8080312","type":"article-journal","title":"Mapping the Evolution of Artificial Intelligence in Agriculture: A Large-Scale BERTopic Analysis of Smart Farming, Automation, and Precision Systems (2020–2025)","abstract":"Advances in artificial intelligence (AI) are revolutionizing agriculture through applications in crop monitoring, precision agriculture, automation, and environmental management. With the rapid development of AI in agriculture, there is an increasing need for extensive evaluation to identify emerging trends and potential future directions. This paper provides a descriptive bibliometric and thematic synthesis of 31,452 publications on the application of artificial intelligence in agriculture in Scopus from 2020 to 2025. The trends and structure of topics in the area are analyzed using BERTopic topic modeling alongside thematic synthesis, temporal trend analysis, centrality-density mapping, and evidence synthesis. Six higher-order themes were identified in the analysis, with crop and production intelligence being the most common. Despite the current progress, the topic of crop-related applications of computer vision remains dominant in the research landscape. However, applications in livestock, socio-technical systems, sustainability, and advanced distributed artificial intelligence fall at the periphery of the landscape. Temporal and structural analyses reveal a concentrated research landscape dominated by production-oriented applications, while interdisciplinary and emerging AI domains remain relatively fragmented. The paper also emphasizes the importance of combining transformer-based topic modeling with thematic and structural analysis in multidisciplinary fields. The results have revealed important insights into the direction AI technology is taking in the agricultural sector, underscoring the need for interoperable, explainable, sustainable, and farmer-centered systems for agricultural development.","author":[{"family":"Capilitan","given":"Jobelle"},{"family":"Balbin","given":"Abigael"},{"family":"Matias","given":"Junrie"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriengineering8080312","URL":"https://doi.org/10.3390/agriengineering8080312","source":"crossref"},{"id":"doi:10.3390/su18031178","type":"article-journal","title":"Sustainable Quantification of Urea in Aqueous Solutions and Corn Cultivation Soils Using Raman Spectroscopy: Towards Precision Agriculture and the Reduction of Environmental Impact","abstract":"The reliable quantification of urea in agricultural systems requires methods that combine metrological rigor with low environmental impact. This work develops and validates a micro-Raman method (λ = 532 nm) for the direct determination of urea in aqueous solutions and soils. The method is formally compared with the reference procedure ISO 19746:2017 (HPLC). Calibration, based on the 1000–1200 and 1460–1670 cm−1 windows, showed near-ideal linearity in the 0.25–25% w/w range (r2 = 0.9999). LOD and LOQ values were 0.178 and 0.735% w/w, respectively. Intra- and inter-day accuracy proved adequate for routine use (RSD ≤ 5%). A one-way ANOVA (p = 0.983) confirmed no statistically significant differences between concentrations obtained by micro-Raman and ISO 19746:2017. In the soil matrix, recoveries ranged between 94 and 101, and the contained biases demonstrate good tolerance to matrix effects. Application to maize plots allowed for monitoring urea disappearance at three depths (0–2 cm, 5–7 cm and 10–15 cm) over 90 days. These differentiated areas of rapid surface hydrolysis from more persistent fractions at depth. The Eco-Scale (96), GAPI (pictogram dominated by green areas), and AGREE (0.88) metrics confirm a significantly lower environmental footprint than that of the chromatographic method. The proposed micro-Raman methodology is emerging as a green, fast, and traceable alternative for monitoring urea in fertilizers and agricultural soils.","author":[{"family":"Hernandez-Fernandez","given":"Joaquín"},{"family":"Tejera","given":"Maria"},{"family":"Acosta","given":"Michel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/su18031178","URL":"https://doi.org/10.3390/su18031178","source":"crossref"},{"id":"doi:10.4238/wkfmfn65","type":"article-journal","title":"SPECTRAL ENGINEERING OF PLANT METABOLISM IN  CONTROLLED ENVIRONMENT AGRICULTURE:  MECHANISMS, METABOLIC REPROGRAMMING, AND  PRECISION LIGHTING STRATEGIES","abstract":"Controlled environment agriculture (CEA) is a promising solution to sustainable crop production under growing pressure from climate change, urbanisation and resource constraints. One of the key technological advances in CEA is the application of spectral engineering with programmable light-emitting diode (LED) systems to precisely control plant growth, metabolism, morphology and nutritional quality. The present review critically evaluates the role of spectral environments in modulating plant physiological and biochemical processes with special emphasis on photosynthesis, carbon and nitrogen metabolism, antioxidant responses, secondary metabolite biosynthesis and crop-specific quality parameters. The review discusses the use of dynamic lighting strategies, spectral-spatial optimisation and pre-harvest illumination approaches to boost productivity and phytochemical accumulation in horticultural crops and recent advances in integrating metabolomics, transcriptomics, high-throughput phenotyping, artificial intelligence, deep learning, and digital twin technologies in the context of intelligent environmental control and predictive cultivation systems. Furthermore, current challenges regarding energy consumption, economic feasibility, reproducibility and large-scale implementation of plant factory systems with artificial lighting are critically analysed. The results show that effective spectral engineering demands crop and growth stage specific spectral recipes, rather than universal ones. Further integration of photobiology, computational modelling, smart sensing systems and sustainable energy management will be key to future progress in CEA and to generate adaptive cultivation systems that can improve yield, nutritional quality, stress resilience and resource-use efficiency concurrently. In brief, spectral engineering is a developing multidisciplinary field with great promise for advancing sustainable and intelligent indoor agriculture.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.4238/wkfmfn65","URL":"https://doi.org/10.4238/wkfmfn65","source":"crossref"},{"id":"doi:10.3390/agronomy16050564","type":"article-journal","title":"From Sensing to Intervention: A Critical Review of Agricultural Drones for Precision Agriculture, Data-Driven Decision Making, and Sustainable Intensification","abstract":"Unmanned aerial vehicles (UAVs) are increasingly employed in precision agronomy to support high-resolution monitoring and management of crops; however, the extent to which UAV-derived data can be translated into reliable, scalable, and decision-ready applications remains inconsistent. This review addresses this gap by critically synthesising the recent literature with a specific focus on the end-to-end data pipeline, from acquisition planning and pre-processing to data fusion, analytics readiness, and operational decision support. A systematic analysis of peer-reviewed studies published over the last five years was conducted to evaluate core agronomic applications, including crop health monitoring, precision irrigation, soil and field variability assessment, spraying, and yield prediction, with particular attention to indicators used, validation strategies, and reported agronomic outcomes. The findings indicate that monitoring and diagnostic applications are the most mature and consistently validated, whereas interventional uses and absolute yield prediction remain strongly context-dependent and constrained by operational, methodological, and regulatory factors. Across applications, pipeline robustness, uncertainty management, and reproducibility emerge as more critical determinants of agronomic value than sensor resolution alone. The review further identifies key barriers to scaling, including technical limitations, skills requirements, data integration challenges, and regulatory constraints, and outlines an innovation roadmap distinguishing currently deployable solutions from emerging developments over the next three to five years. Overall, this work provides a decision-oriented framework to support more transparent, validated, and sustainable integration of UAV technologies into modern agricultural systems.","author":[{"family":"Arsenoaia","given":"Vlad"},{"family":"Topa","given":"Denis"},{"family":"Ratu","given":"Roxana"},{"family":"Tenu","given":"Ioan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agronomy16050564","URL":"https://doi.org/10.3390/agronomy16050564","source":"crossref"},{"id":"doi:10.14445/23488549/ijece-v13i4p122","type":"article-journal","title":"Smart Precision Agriculture using IoT Sensing and Machine Learning Analytics for Farming in Mysuru District","abstract":"Precision farming has been found to be a viable solution to the problem of productivity, sustainability, and resource efficiency of the rural agricultural sector in India. In this paper, I introduce a combined Internet of Things (IoT) and Machine Learning (ML)-based precision farming system to be used in real-time monitoring of soil health and predicting crop yields, including a comprehensive case study performed in the Mysuru district of Karnataka, India. One complete set of 557 farm records of 7 taluks in Mysuru, and another 50 comparison records in adjacent districts, were taken, including basic parameters like temperature, humidity, soil pH, soil moisture, light intensity, nutrient level (N, P, K), and yield/acre. A multi-sensor hardware platform (along with a Soil Information System (SIS)) was created together with cloud storage and a mobile-based decision-support application that will allow acquiring data continuously and provide feedback to the farmer. Three machine learning models, Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT), were then trained on the preprocessed data consisting of normalized, imputed, and outlier-treated data to predict yields and compare them. As illustrated in experimental results, the Random Forest model performs better in terms of accuracy of 95.7 percent and a lesser prediction error on the Mysuru dataset compared to the SVM and DT models and models trained on neighboring district data. The results also show that the Mysuru soils have more coherent fertility and moisture retention properties, which make them better at predicting and multi-crop compatibility.","author":[{"family":"Fathima","given":"Noor"},{"family":"Bagali","given":"Mohmad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.14445/23488549/ijece-v13i4p122","URL":"https://doi.org/10.14445/23488549/ijece-v13i4p122","source":"crossref"},{"id":"doi:10.3390/su18157978","type":"article-journal","title":"Bridging Magnetic Field Agriculture and UAV-Based Precision Monitoring: An Integrated Dual-Stream Evidence Synthesis and Conceptual Framework for Field-Scale Validation","abstract":"Magnetic field (MF) technologies have been explored in agriculture since the 1930s, with research activity increasing markedly since 2016. However, they have not achieved mainstream adoption, partly because no MF-specific validated methodology exists for evaluating their effects under realistic field conditions. Unmanned Aerial Vehicle (UAV)-based multispectral sensing represents a potential pathway to address this limitation by providing spatially explicit, non-destructive estimates of key canopy physiological variables at field scale, thereby enabling, for the first time, the systematic evaluation and validation of MF treatment responses under open-field conditions. To realise this potential, however, a common evidential basis must first be established by identifying crop physiological variables that are both consistently modulated by MF treatments and reliably detectable by UAV remote sensing. This study addressed this challenge through a dual-stream evidence synthesis of 216 peer-reviewed publications, comprising 102 studies on MF treatments in agricultural crops and 114 studies on UAV-based multispectral monitoring. Evidence from both research domains was synthesised to identify physiological variables that are simultaneously responsive to MF treatments and detectable through UAV remote sensing. Five direct bridge variables were identified: chlorophyll content, nitrogen use efficiency (NUE)/nitrogen assimilation, above-ground biomass (AGB), leaf area index (LAI), and yield. Chlorophyll content emerged as the strongest bridge variable, combining consistent MF responsiveness with UAV estimation accuracies of up to R2 = 0.90. Based on these findings, a conceptual framework was developed linking MF treatments, UAV-derived vegetation indices, ground-truth measurements, and machine-learning approaches for field-scale validation. The review revealed a complete absence of integration between the two research domains within the reviewed corpus, despite their strong biological and methodological compatibility. The proposed framework is conceptual and remains to be experimentally validated; it provides the first operational pathway for evaluating MF technologies under realistic farming conditions and may support future research on sustainable and digitally enabled crop production systems.","author":[{"family":"Papadopoulos","given":"George"},{"family":"Georgiou","given":"Evgenia"},{"family":"Oikonomou","given":"Antonia"},{"family":"Fountas","given":"Spyros"},{"family":"Bilalis","given":"Dimitrios"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/su18157978","URL":"https://doi.org/10.3390/su18157978","source":"crossref"},{"id":"doi:10.55041/ijsrem57791","type":"article-journal","title":"Enhancing Precision Agriculture Pest Control: A YOLOv10-Based Deep Learning Approach for Insect Detection","abstract":"ABSTRACT Precision Agriculture (PA) leverages advanced technologies to optimize resource use while preserving crop quality and yield. However, pest infestations remain a critical challenge that can undermine these benefits. Recent deep learning frameworks like YOLOv8 have shown promise in real-time insect detection, yet often remain limited to specific insect types or crops. To address this limitation and improve detection accuracy, this work explores an enhanced, generalized approach using the latest YOLOv10 object detection model. We develop and test a YOLOv10-based tool designed to detect any insect category across diverse crops, enabling broader and faster pest monitoring in the field. A comprehensive performance evaluation was conducted on a benchmark insect dataset, demonstrating notable improvements over YOLOv8, including higher mean Average Precision (mAP) scores and faster inference speeds. The findings suggest that YOLOv10's architectural advancements contribute to more robust, scalable, and real-time pest detection, offering significant potential to strengthen pest management strategies within precision agriculture.","author":[{"family":"Kaurav","given":"Arun"},{"family":"Avula","given":"Renuka"},{"family":"Pujitha","given":"B"},{"family":"Srinithin","given":"B"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsrem57791","URL":"https://doi.org/10.55041/ijsrem57791","source":"crossref"},{"id":"doi:10.9734/bji/2026/v30i4896","type":"article-journal","title":"Artificial Intelligence and Plant Nanotechnology in Precision Agriculture: A Critical Appraisal of Smart Nanomaterials, Predictive Modelling and Translational Evidence","abstract":"Precision agriculture is increasingly described as the convergence of two originally separate technological programmes: engineered nanomaterials that act at the plant and soil interface, and computational learning systems that convert agronomic data into management decisions. The claim that these programmes already constitute a single integrated capability has become common in recent literature, yet the evidential basis for that integration has rarely been examined with the scepticism it warrants. This critical narrative review evaluates the strength, consistency and methodological quality of the evidence linking artificial intelligence to plant nanotechnology, and asks where the coupling is demonstrated, where it is merely plausible and where it is rhetorical. Literature was identified through Crossref Metadata Search, PubMed, the Directory of Open Access Journals and targeted searching of publisher and institutional pages, supplemented by backward and forward citation tracing, with all bibliographic records verified through digital object identifier resolution. Four coupling modes are distinguished: nanoscale sensing that generates machine-readable plant signals, data-driven prediction and design of nanomaterial behaviour, stimuli-responsive delivery that actuates algorithmic decisions, and decision integration at field scale. Evidence quality differs sharply among these modes. Supervised models of nanoparticle uptake and plant response now rest on curated datasets and interpretable learning methods, but they inherit descriptor limitations from nano quantitative structure and activity relationship modelling, rely on small and heterogeneous laboratory datasets, and have seldom been validated prospectively. Nanosensors detect defined stress signalling molecules in living tissue with high temporal resolution, yet reports of calibration stability, cross-species transferability and field durability remain scarce. Nano-enabled fertilisers and pesticides show efficiency gains in controlled conditions that are frequently attenuated or unverified in field systems, and comparisons with conventional analogues are often methodologically weak. Environmental fate, soil microbiome effects and life-cycle burdens remain insufficiently characterised to support confident safe-by-design claims. The dominant limitation is not conceptual but infrastructural: the coupling of artificial intelligence to plant nanotechnology is constrained by data scarcity, non-standardised reporting and an unresolved gap between glasshouse demonstration and agronomic deployment. Research priorities are proposed that address prospective validation, standardised nano-agronomic datasets, field-durable sensing and governance of data asymmetry.","author":[{"family":"Awodiran","given":"Festus"},{"family":"Adeyemi","given":"Kareem"},{"family":"Feranmi","given":"Ojedapo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/bji/2026/v30i4896","URL":"https://doi.org/10.9734/bji/2026/v30i4896","source":"crossref"},{"id":"doi:10.56557/jogae/2026/v18i311028","type":"article-journal","title":"Precision Farming for Sustainable and Efficient Agribusiness in India: A Critical Narrative Review with Descriptive Evidence Synthesis","abstract":"India's agricultural economy faces a distinctive precision-farming problem: the technologies that can measure and manage field variability are advancing rapidly, while the institutional conditions needed to convert technical precision into durable farm and agribusiness value remain uneven. This critical narrative review evaluates precision farming as a decision system rather than a collection of devices, with particular attention to Indian smallholder conditions, resource-use efficiency, farm economics, service delivery and environmental performance. Literature published from 1 January 2000 to 14 June 2026 was examined through accessible scholarly indexes, agricultural databases and authoritative Indian institutional sources. The requested descriptive meta-analytical element was implemented as structured comparison of reported effect directions and magnitudes; statistical pooling was not undertaken because interventions, crops, comparators, outcomes and study designs were too heterogeneous for a defensible common effect estimate. The evidence is strongest for scale-compatible practices that translate measurement directly into management, including precision land levelling, sensor- or threshold-guided nitrogen management, drip fertigation and targeted application technologies. These approaches frequently maintain or increase yield while reducing irrigation water or fertiliser requirements, although the magnitude and persistence of benefit are context dependent. By contrast, remote sensing, machine learning and digital advisories have strong diagnostic potential but weaker causal evidence for income or yield gains at scale. Large observational and modelling datasets reveal substantial scope for site-specific management, yet modelled opportunity should not be conflated with realised farmer benefit. India's small and fragmented holdings make capital-intensive ownership models difficult to generalise; custom hiring, farmer collectives and service-based delivery can improve asset utilisation but introduce quality, interoperability and governance requirements. The review concludes that India's most credible pathway is not technology maximalism but frugal, service-enabled precision: reliable measurement, locally calibrated decision rules, affordable execution and independent outcome evaluation. Future research should prioritise multi-season causal trials, whole-farm economics, environmental outcomes, interoperability, data governance and distributional effects across farm sizes, regions and gendered access to services.","author":[{"family":"Bollagani","given":"Divya"},{"family":"Chowdhary","given":"Kuldeep"},{"family":"Shireesha","given":"Chowdula"}],"issued":{"date-parts":[[2026]]},"DOI":"10.56557/jogae/2026/v18i311028","URL":"https://doi.org/10.56557/jogae/2026/v18i311028","source":"crossref"},{"id":"doi:10.1201/9781003545781-18","type":"article-journal","title":"Plant Disease Diagnosis Based on Artificial Intelligence Technologies","abstract":"Plant diseases pose a significant threat to global food security, leading to substantial economic losses and reduced crop yields. Traditional diagnostic methods rely on manual inspection, which is often time-consuming, labor-intensive, and prone to inaccuracies. Recent advancements in artificial intelligence (AI) have revolutionized plant disease diagnosis by enabling automated, precise, and real-time detection. AI-based techniques, including machine learning and deep learning, leverage large datasets and image processing methods to accurately classify plant diseases. Additionally, computer vision and Internet of Things technologies have enhanced disease monitoring through AI-powered mobile applications, drones, and smart sensors. While AI-driven plant disease diagnosis offers numerous advantages, challenges such as data quality, computational costs, and model generalization remain. Future research must focus on improving AI algorithms, developing robust datasets, and integrating real-time monitoring systems to make plant disease diagnosis more efficient and scalable. AI-powered solutions hold immense potential to transform modern agriculture, ensuring sustainable farming practices and enhanced crop protection.","author":[{"family":"Govindarajan","given":"Ramkumar"},{"family":"Sureshkumar","given":"Tharani"},{"family":"Rathinam","given":"Elakkiya"},{"family":"Jaison","given":"Sarah"},{"family":"Kutty","given":"Sunitha"},{"family":"Samuel","given":"Siva"},{"family":"Devi","given":"Balasundaram"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-18","URL":"https://doi.org/10.1201/9781003545781-18","source":"crossref"},{"id":"doi:10.70917/ijcisim-2026-3771","type":"article-journal","title":"Metaverse-Based Precision Agriculture: Integrating IoT, AI, and Data Analytics for Sustainable Development","abstract":"The fast development of digital technologies has changed the contemporary agriculture, making it more precise, data-driven, and sustainable in managing the farm. Nevertheless, farmers continue to experience difficulties in terms of observing the process of soil dynamics, optimization of irrigation, and real-time visualization of the state of the fields, which results in the inefficiency of resources and the instability of yields. In order to overcome these constraints, the study suggests the implementation of a combined metaverse-based precision agriculture system comprising of IoT sensing, artificial intelligence-enhanced prediction, and advanced data analytics. A 6-in-1 agro sensor has been used to collect real-time soil parameters such as pH, EC, moisture, temperature, phosphorus, and potassium and utilize them in a Raspberry Pi IoT platform. The Karnataka soil moisture dataset is then trained through CNN, LSTM and CNN-LSTM models after cleaning, smoothing and normalization to classify and predict soil moisture. The system is represented in an interactive metaverse system as an immersive system to monitor and make decisions. Based on the experimental results, it is concluded that the hybrid CNN-LSTM model is superior and the RMSE, MAE, MAPE and R2 values are 0.142, 0.810, 27.342 and 0.829 respectively, making it a valuable model for sustainable and accurate irrigation management.","author":[{"family":"Rao","given":"Phuke"},{"family":"Sandhu","given":"Ramandeep"},{"family":"Bhujbal","given":"Santosh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70917/ijcisim-2026-3771","URL":"https://doi.org/10.70917/ijcisim-2026-3771","source":"crossref"},{"id":"doi:10.3390/agronomy16141358","type":"article-journal","title":"Precision Agriculture Monitoring and Control System Using In-House-Designed Capacitive Sensors","abstract":"This paper describes the design and implementation of an automated irrigation control system that uses data collected by a wireless sensor network. Each sensor node, built on a custom-designed printed circuit board, includes sensors for light intensity, temperature, and a custom soil moisture sensor. Data is transmitted to a central control node via ESP-NOW, where it is processed and compared with configurable thresholds retrieved from Google Sheets over Wi-Fi. Irrigation is triggered automatically when conditions meet the remotely defined thresholds. A key contribution is the development and testing of a custom soil moisture sensor, with results compared to commercial models. The system supports low-power operation through deep sleep modes, enabling long-term field deployment. The novelty lies in the complete integration of hardware, software, and cloud-based control, providing a flexible and low-cost solution for precision agriculture. The system can be deployed in greenhouses or open fields and serves as a platform for future research in smart irrigation. The fundamental aspect is a very user-friendly solution for any farmer attributable to easy accommodation to the Google Sheets interface, no maintenance cost over the cloud account, and up to 45 days of battery life or a built-in alternative for solar power.","author":[{"family":"Hoței","given":"Ștefania"},{"family":"Marghescu","given":"Cristina"},{"family":"Negroiu","given":"Rodica"},{"family":"Mihăilescu","given":"Bogdan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agronomy16141358","URL":"https://doi.org/10.3390/agronomy16141358","source":"crossref"},{"id":"doi:10.1201/9781003545781-6","type":"article-journal","title":"Artificial Intelligence Approaches for Analyzing and Interpreting Visual Data in Plant Biology","abstract":"The integration of advanced imaging technologies in plant science is reshaping the way we monitor and manage agricultural systems. This chapter explores the significance of image-based data in modern plant science, emphasizing the role of precision agriculture in improving crop health, disease detection, and growth monitoring. It delves into techniques for phenotypic trait extraction, such as automated feature detection and the use of computer vision for analyzing morphological traits. The application of deep learning in disease classification and stress identification enables early detection of both abiotic and biotic stress factors. Moreover, 3D plant modeling, time-series analysis, and multispectral imaging are discussed as powerful tools for assessing plant health and growth dynamics. The chapter also covers the role of data augmentation, synthetic data generation, and transfer learning in enhancing model performance. Additionally, the integration of IoT and robotics in smart farming is explored, highlighting the advancements in autonomous systems and real-time monitoring.","author":[{"family":"Manoj","given":"Mani"},{"family":"Bharath","given":"Manikandan"},{"family":"Dhanushka","given":"Kannan"},{"family":"Nair","given":"Aneesh"},{"family":"Malarvizhi","given":"Marimuthu"},{"family":"Shenbagam","given":"Madhavan"},{"family":"Velayuthaprabhu","given":"Shanmugam"},{"family":"Anand","given":"Arumugam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-6","URL":"https://doi.org/10.1201/9781003545781-6","source":"crossref"},{"id":"doi:10.21474/jnaves01/117","type":"article-journal","title":"PRECISION AGRICULTURE AND ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE CROP PRODUCTION: A REVIEW OF EMERGING TECHNOLOGIES AND FUTURE APPLICATIONS","abstract":"The increasing demand for food, declining natural resources, climate variability, and environmental concerns have accelerated the adoption of advanced technologies in agriculture. Precision Agriculture (PA) and Artificial Intelligence (AI) have emerged as transformative approaches for improving agricultural productivity, resource efficiency, and sustainability. Precision agriculture enables site-specific management of crops using advanced sensing and monitoring technologies, while AI facilitates data-driven decision-making through machine learning, computer vision, and predictive analytics. This review examines the principles of precision agriculture, the role of artificial intelligence in crop production, major technological advancements, benefits, limitations, and future prospects. The review highlights the potential of integrating AI-driven solutions with precision farming systems to enhance food security and environmental sustainability.","author":[{"family":"Ferreira","given":"Lucas"},{"family":"El-Sayed","given":"Amina"},{"family":"Kim","given":"Jonathan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.21474/jnaves01/117","URL":"https://doi.org/10.21474/jnaves01/117","source":"crossref"},{"id":"doi:10.3390/agronomy16111094","type":"article-journal","title":"Harnessing AI for Precision Agriculture: An Integrated System for Vineyard Pathogen and Pest Detection","abstract":"Vineyards are affected by pathogens globally. Some of the most damaging pathogens are Uncinula necator, Plasmopara viticola, and thrips, which affect the plant entirely and threaten the health and productivity of vineyards. To control the emergence and spread of pathogens, early detection is essential. Studies to date focus on visual or molecular detection of pathogens but are limited in terms of scalability, labor intensity, need for equipment and expertise. To tackle these limitations, we propose the early detection of grapevine virus infections using Convolutional Neural Networks on both RGB and thermal infrared imagery captured via a smartphone and an FLIR sensor. To do so, we employ a four-step workflow where we first acquire nearly 500 images detecting symptoms of pathogens, which we then crop in smaller tiles. Then, we use the ArcGIS Train Deep Learning Model tool trained with Single Shot Detector and RetinaNet frameworks to detect image areas showing pathogen presence. Finally, we calculate the IoU score to compare precisions between different tile sizes and frameworks. The results demonstrate that pathogen detection using these models is highly effective, with most images having a IoU score above 0.7. Moreover, 30% of images score a precision of 1.0. The consequences of these findings highlight the importance of early detection of pathogens to better understand their spread and effects on vineyards, which finally contribute to proposing effective management measures.","author":[{"family":"Petre","given":"Ioana"},{"family":"Șandric","given":"Ionuț"},{"family":"Vizitiu","given":"Diana"},{"family":"Sărdărescu","given":"Ionela"},{"family":"Ioniță","given":"Cristian"},{"family":"Dardală","given":"Marian"},{"family":"Bacău","given":"Simona"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agronomy16111094","URL":"https://doi.org/10.3390/agronomy16111094","source":"crossref"},{"id":"doi:10.3390/s26144373","type":"article-journal","title":"A Comparative Benchmark of Real-Time Detectors for Canopy Image-Based Blueberry Detection Toward Precision Orchard Management","abstract":"Computer vision with artificial intelligence (AI) offers a promising tool for blueberry growers to accomplish orchard tasks such as harvest maturity assessment and yield estimation, which otherwise would be labor-intensive and prone to error. However, blueberry detection in natural environments remains challenging due to variable natural lighting, frequent occlusions by leaves and branches, and motion blur due to environmental factors and imaging devices. AI models such as deep learning-based object detectors promise to address these challenges, but they are data-driven, demanding a large-scale, diverse dataset that captures the complexities of real-world orchard conditions. Deployment of these models in practical scenarios often faces limited computing resources, highlighting the importance of achieving the right accuracy/speed/memory trade-off in model selection. This study presents a novel comparative benchmark analysis of advanced real-time object detectors, including YOLO (You Only Look Once) (v8–v12) and RT-DETR (Real-Time Detection Transformers) (v1–v2) families, consisting of 36 model variants, evaluated on a newly curated large dataset for blueberry detection. This dataset contained 661 canopy images collected with smartphones during the 2022–2023 seasons, consisting of 85,879 manually annotated instances (including 36,256 ripe and 49,623 unripe blueberries) that represent a broad range of lighting conditions, occlusions, and fruit maturity stages. Among the YOLO models, YOLOv12m achieved the best accuracy with a mAP@50 of 93.3%, while RT-DETRv2-X obtained a mAP@50 of 93.6%, the highest among all RT-DETR variants. The inference time varied with the model scale and complexity, and the mid-sized models appeared to offer a good balance between accuracy and speed. To further improve fruit detection performance, all models were fine-tuned using Unbiased Mean Teacher-based semi-supervised learning (SSL) with 1644 cross-source unlabeled canopy images acquired from ground-based machine vision platforms. SSL resulted in accuracy improvements of up to 2.0%, with RT-DETR-v2-X achieving the highest mAP@50 of 95.5%. These findings highlight the efficacy of SSL for leveraging cross-domain unlabeled data, although further research is needed to fully exploit its benefits. The curated dataset and developed software programs are publicly available to facilitate further research and practical deployment.","author":[{"family":"Mu","given":"Xinyang"},{"family":"Lu","given":"Yuzhen"},{"family":"Deng","given":"Boyang"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/s26144373","URL":"https://doi.org/10.3390/s26144373","source":"crossref"},{"id":"doi:10.1201/9781003545781-13","type":"article-journal","title":"Uncovering Complicated Plant Biological Networks through the Assistance of Artificial Intelligence Tools","abstract":"Plant biological networks, comprising gene regulatory, protein–protein interaction (PPI), and metabolic pathways, are intricate systems fundamental to understanding plant development and physiology. The advent of artificial intelligence (AI) offers promising tools to unravel these complex networks, allowing for more precise insights into regulatory mechanisms, functional annotation, and multi-omics data integration. This chapter explores how AI techniques, including machine learning and deep learning, are transforming the analysis of plant biological networks. It delves into AI’s role in gene regulatory network inference, PPI predictions, and metabolic network reconstruction and also highlights AI-driven approaches for analyzing spatial and temporal dynamics in plant systems. Through integrative network analysis, AI enables the synthesis of diverse data types, driving advancements in plant biology. Case studies illustrate practical applications of these AI tools, offering valuable perspectives for future research.","author":[{"family":"Charulekha","given":"Kamalakkannan"},{"family":"Girigoswami","given":"Agnishwar"},{"family":"Girigoswami","given":"Koyeli"},{"family":"Manoj","given":"Mani"},{"family":"Pallavi","given":"Pragya"},{"family":"Gowtham","given":"Pemula"},{"family":"Robert","given":"Asirvatham"},{"family":"Anand","given":"Arumugam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-13","URL":"https://doi.org/10.1201/9781003545781-13","source":"crossref"},{"id":"doi:10.22214/ijraset.2026.83480","type":"article-journal","title":"IoT-Based Soil Nutrient Analysis and Crop Recommendation System for Precision Agriculture","abstract":"Agriculture plays a vital role in feeding the growing global population, yet optimizing crop production and resource management remains a significant challenge for farmers. This paper presents a Machine Learning (ML)-enabled Internet of Things (IoT) prototype designed to monitor soil parameters in real time and provide customized crop recommendations. The proposed system integrates four sensors — a JXBS-3001 NPK sensor, an FC-28 soil moisture sensor, a DHT11 temperaturehumidity sensor, and an analog soil pH probe — deployed in the crop field and interfaced with a NodeMCU (ESP8266) microcontroller. Collected data is transmitted to the Ubidots cloud platform via the MQTT protocol. The Random Forest classifier is employed as the primary algorithm, achieving 99.09% test accuracy on the standard Kaggle Crop Recommendation dataset (2,200 samples, 22 crop classes); Logistic Regression, LightGBM, and a Neural Network are evaluated as benchmarks. Recommendations and fertilizer guidance are delivered to the farmer through a web-based dashboard, and a rule-based fertilizer engine maps measured N, P, K deficits to dosage suggestions per crop. The prototype was demonstrated in a working deployment and received first prize at the AURA 2.0 State-Level Project Expo (2023) and first prize at Shark Tank 2.0 (2024).","author":[{"family":"Prajwal","given":"JA"}],"issued":{"date-parts":[[2026]]},"DOI":"10.22214/ijraset.2026.83480","URL":"https://doi.org/10.22214/ijraset.2026.83480","source":"crossref"},{"id":"doi:10.3997/2214-4609.202655104","type":"article-journal","title":"Application of GIS for the Analysis of Yield Monitoring Data in Precision Agriculture","abstract":"Summary The study considers the application of geographic information systems (GIS) for the analysis of yield monitoring data within a production field. The relevance of the work is determined by the need to assess the spatial heterogeneity of indicators characterizing the physical condition of grain products and the conditions of yield formation in precision agriculture technologies. The information base consisted of telemetric data obtained during harvesting by combine harvesters, containing spatially referenced measurements of grain moisture and accompanying technological parameters. The study used the dry matter content indicator (DryMatter, %), which was calculated based on grain moisture values. The data obtained were preliminarily processed to eliminate anomalous measurements and improve the reliability of the analysis. Spatial modelling was performed in a GIS environment with the creation of thematic maps of the DryMatter (%) distribution. To interpret the identified patterns, a digital elevation model was additionally used, which allowed for the analysis of the morphometric characteristics of the field surface. The results of the study indicate the presence of pronounced within-field variability of the DryMatter (%) indicator. The spatial distribution of values exhibits an ordered pattern and demonstrates consistency with the relief features of the territory. The results obtained confirm the feasibility of applying geoinformation analysis for assessing the spatial heterogeneity of technological indicators in precision agriculture technologies.","author":[{"family":"Bohush-Zadnipriana","given":"A"},{"family":"Vorokh","given":"V"},{"family":"Pastushenko","given":"T"},{"family":"Nikolaienko","given":"O"},{"family":"Ilchenko","given":"O"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3997/2214-4609.202655104","URL":"https://doi.org/10.3997/2214-4609.202655104","source":"crossref"},{"id":"doi:10.71026/ls.2025.03004","type":"article-journal","title":"Design of LoRaWAN Network Applying in Organic Greenhouse Farming","abstract":"Organic farming is vital for promoting sustainable agriculture and food safety in Laos. Precision monitoring of environmental parameters within greenhouses is essential to enhance crop productivity and maintain organic standards. This paper presents the design and implementation of a LoRaWAN-based wireless sensor network for environmental monitoring in organic greenhouse farming. The study aims to design a LoRa wireless communication network and develop a high-performance data transmission model by implementing and comparing star and mesh topologies. The designed system consists of 3 sensor nodes (End Nodes) and 1 gateway node, and its performance is tested in both closed and open organic greenhouses. Network performance was evaluated using an Anritsu MS2720T Spectrum Master. Spectrum analysis confirmed stable and viable signal propagation in the 433 MHz band, with a robust signal-to-noise ratio suitable for reliable data transmission. The star topology demonstrated superior performance inside the greenhouse with a 98% Packet Delivery Ratio (PDR) and stable communication at 10 meters, compared to 85% PDR for the mesh topology. These results confirm that the star topology is more reliable for data transmission in the obstructed greenhouse environment, providing a validated model for efficient environmental monitoring in support of sustainable organic farming in Laos.","author":[{"family":"Pathoummalath","given":"Nion"},{"family":"Panthongsy","given":"Phosy"},{"family":"Lakanchanh","given":"Donekeo"},{"family":"Parmanee","given":"Thay"},{"family":"Southisombath","given":"Phouthong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71026/ls.2025.03004","URL":"https://doi.org/10.71026/ls.2025.03004","source":"crossref"},{"id":"doi:10.1109/tccn.2026.3683140","type":"article-journal","title":"Split Learning Over NOMA-Enabled HetNets for Scalable IoT-Based Precision Agriculture","abstract":"The convergence of artificial intelligence (AI) and precision agriculture is driving the rapid deployment of machine learning (ML) models within Internet of Things (IoT) ecosystems. However, traditional centralized ML frameworks pose significant challenges in energy efficiency, communication overhead, and real-time responsiveness, especially in remote agricultural environments. To address these limitations, we propose a novel hierarchical split learning framework enabled by non-orthogonal multiple access (NOMA) and deployed over a heterogeneous network (HetNet) topology. In the proposed system, each geographically distributed low-power edge node equipped with a nano-GPU executes a segment of a common deep neural network (DNN) on locally collected agricultural data and transmits intermediate activations to a central aggregator edge node (AEN), which completes the remaining layers and coordinates the backpropagation process. NOMA enables simultaneous data uploads from multiple sensors over shared frequency resources, improving spectral efficiency and supporting scalability. HetNet-based zone segmentation further enhances resource reuse and system coverage. We formulate a comprehensive optimization problem aimed at minimizing total system energy consumption, accounting for both local computation and wireless communication. To solve it, we develop an efficient distributed solution with proven convergence. Extensive simulation results validate the effectiveness of the proposed framework in reducing energy consumption and transmission delay while maintaining high model accuracy, establishing it as a scalable and sustainable solution for intelligent agricultural systems.","author":[{"family":"Hossain","given":"Mohammad"},{"family":"Sadat","given":"Nazmus"},{"family":"Ansari","given":"Nirwan"},{"family":"Amsaad","given":"Fathi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/tccn.2026.3683140","URL":"https://doi.org/10.1109/tccn.2026.3683140","source":"crossref"},{"id":"doi:10.1002/9781394248711.ch10","type":"article-journal","title":"Smart Crop Health Monitoring and Precision Irrigation with IoT‐Driven Systems","abstract":"This research investigates the development and implementation of an IoT-driven system for smart crop health monitoring and precision irrigation. The study addresses challenges of water scarcity, inefficient irrigation practices, and limited real-time insights into crop conditions by integrating advanced sensor networks, wireless communication, and data analytics. The proposed system employs a suite of environmental and soil sensors to continuously monitor key parameters such as moisture levels, temperature, and nutrient content. Data collected from these sensors is transmitted to a centralized platform where machine learning algorithms analyze crop health and predict irrigation needs. The system dynamically adjusts water distribution based on real-time field conditions, promoting efficient usage and reducing waste. Field experiments and simulations validate the effectiveness of the system in optimizing irrigation schedules and improving crop yield. Furthermore, the study explores the scalability of the IoT framework and its potential integration with other precision agriculture technologies. The outcomes of this research aim to enhance sustainable practices by providing farmers with actionable insights and automated control over irrigation processes, ultimately contributing to resource conservation and increased productivity. This work lays the groundwork for future advancements in smart farming, positioning IoT as a key enabler in the evolution of modern agriculture significantly.","author":[{"family":"Sholapurapu","given":"Prem"},{"family":"Riadhusin","given":"Raami"},{"family":"Praveen","given":"RVS"},{"family":"Boob","given":"Nandini"},{"family":"Singh","given":"Navdeep"},{"family":"Gudainiyan","given":"Jitendra"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394248711.ch10","URL":"https://doi.org/10.1002/9781394248711.ch10","source":"crossref"},{"id":"doi:10.58175/gjret.2026.3.1.0011","type":"article-journal","title":"Application of AI in Precision Soil Quality Assessment for Sustainable Agriculture","abstract":"Soil quality assessment is a critical component of precision agriculture and sustainable land management, as soil physicochemical and fertility-related properties directly influence agricultural productivity and environmental sustainability. Conventional soil evaluation methods are often labor-intensive, time-consuming, and difficult to scale across large agricultural regions. This study aims to develop an accurate, scalable, and interpretable artificial intelligence (AI)–based framework for precision soil quality assessment. A comprehensive secondary soil dataset containing physicochemical and fertility indicators was used to classify soil quality into Good, Medium, and Poor categories. Four AI models—Random Forest, XGBoost, Multilayer Perceptron (MLP), and one-dimensional Convolutional Neural Network (1D-CNN)—were implemented and evaluated using an 80:20 stratified train–test split. Model performance was assessed using accuracy, balanced accuracy, precision, recall, F1-score, confusion matrices, Receiver Operating Characteristic curves, and Precision–Recall curves. Results indicate that deep learning models outperform traditional machine learning approaches, with the MLP achieving the highest accuracy, followed by the 1D-CNN. Explainable AI techniques were applied to identify key soil parameters influencing classification outcomes, enhancing model transparency. The proposed AI-based framework demonstrates strong potential for supporting precision agriculture practices and sustainable soil management.","author":[{"family":"Saleh","given":"Lubaba"},{"family":"Halimuzzaman","given":"Halimuzzaman"},{"family":"Rahman","given":"Mozibur"},{"family":"Rumanuzzaman","given":"Kazi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58175/gjret.2026.3.1.0011","URL":"https://doi.org/10.58175/gjret.2026.3.1.0011","source":"crossref"},{"id":"doi:10.22219/kinetik.v11i3.2700","type":"article-journal","title":"A Memory-Efficient and Gradient-Stable Lightweight ANFIS for Real-Time Humidity Prediction in Precision Agriculture","abstract":"Precision agriculture demands artificial intelligence solutions that are both accurate and deployable on resource-constrained hardware, yet conventional machine learning models require excessive memory while traditional ANFIS architectures suffer from training instability. This study developed a memory-efficient and gradient-stable lightweight Adaptive Neuro-Fuzzy Inference System (ANFIS) for real-time humidity prediction on microcontroller-class devices. The proposed architecture strategically reduced the rule base from 27 to only 4 interpretable fuzzy rules and limited membership functions to two per input, achieving an 85.2% reduction in learnable parameters. A gradient-stable training mechanism was introduced, combining physics-informed parameter initialization with adaptive gradient clipping to prevent gradient explosion. The model was trained and validated using 31,474 real-world greenhouse samples collected over 218 days, with 80% allocated for training and 20% for temporal testing. Experimental results demonstrated that the gradient-stable architecture successfully converged from a catastrophic R² of -64.08 to 0.9148, with a root mean square error of 1.32% and mean absolute error of 1.05%. The model required only 0.211 KB of memory, representing a 99.9% reduction compared to baseline Random Forest models, while achieving inference time of 8.2 milliseconds on Arduino UNO. The system was successfully deployed on three independent hardware modules, maintaining consistent performance with average RMSE of 1.99% over 168 hours of continuous operation. This study concludes that strategic simplification and stability-aware training enable interpretable neuro-fuzzy systems to operate effectively on ultra-low-resource devices, bridging the gap between predictive accuracy and hardware feasibility in embedded agricultural IoT applications.","author":[{"family":"Nurraharjo","given":"Eddy"},{"family":"Utami","given":"Ema"},{"family":"Kusrini","given":"Kusrini"},{"family":"Ariyuana","given":"Kumara"}],"issued":{"date-parts":[[2026]]},"DOI":"10.22219/kinetik.v11i3.2700","URL":"https://doi.org/10.22219/kinetik.v11i3.2700","source":"crossref"},{"id":"doi:10.1201/9781003545781-19","type":"article-journal","title":"AI-Enabled ChatGPT and Large Language Models in Plant Research","abstract":"The revolutionary role of artificial intelligence (AI), specifically ChatGPT and large language models (LLMs) in furthering plant research is explored in this chapter. AI provides innovative solutions that improve productivity and discovery as plant science faces difficulties with data processing, prediction, and administration. The integration of ChatGPT and LLMs in important domains such as environmental modelling, phenotyping, and genomics is examined in this chapter. The chapter demonstrates how these models can help researchers make predictions, evaluate massive datasets, and generate insights at previously unheard-of scales using case studies and current research. This chapter offers a critical viewpoint on how AI is changing the field of plant biology and research methodology by providing a thorough overview of the current and possible future uses.","author":[{"family":"Bano","given":"Wajeeha"},{"family":"Ansari","given":"Lubna"},{"family":"Iqbal","given":"Javed"},{"family":"Fatima","given":"Hareem"},{"family":"Samiullah"},{"family":"Saleem","given":"Aamir"},{"family":"Ahmad","given":"Basir"},{"family":"Abbas","given":"Syed"},{"family":"Abbasi","given":"Banzeer"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003545781-19","URL":"https://doi.org/10.1201/9781003545781-19","source":"crossref"},{"id":"doi:10.1007/s10791-026-09952-8","type":"article-journal","title":"A lightweight deep learning and whale optimization framework for sustainable precision agriculture","abstract":"The changing needs of the modern agriculture require smart and resource saving solutions to such problems as falling productivity, irresponsible use of inputs, and deterioration of the environment. This paper presents a hybrid framework AgriCLWO-Net, which consists of lightweight Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) model along with Whale Optimization Algorithm (WOA) to provide precision agriculture services by sensors integrated Internet of Things (IoT) environments. The suggested model will categorize the health status of crops, optimize irrigation and spreading of fertilizers, and enhance sustainability performance based on spatiotemporal field information. The methodology takes advantage of CNN to perform spatial patterns area recognition based on multisensory stimuli, LSTM to perform temporal relationships in crop and atmospheric patterns, and WOA to tune the hyperparameters and adaptive decision-making. The model was tested against a sample dataset of the Indian agricultural areas including the temperature, soil moisture, humidity, and nutrient measurements. Findings show that the classification accuracy (98.54%), water use efficiency (27.93%), fertilizer reduction (21.64%), and sustainability index increased (0.54 to 0.76) significantly as compared to the existing baseline models.","author":[{"family":"Ramu","given":"SC"},{"family":"Raman","given":"Dugyala"},{"family":"Ramana","given":"Kadiyala"},{"family":"Krishna","given":"Akula"},{"family":"Khan","given":"Arfat"},{"family":"Khan","given":"Shakir"},{"family":"Abdu","given":"Seid"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s10791-026-09952-8","URL":"https://doi.org/10.1007/s10791-026-09952-8","source":"crossref"},{"id":"doi:10.1201/9781003520733-19","type":"article-journal","title":"The impact of variable rate technology (VRT) on soil health and crop yield optimization","abstract":"Variable rate technology (VRT) is a precision agriculture technology that varies agricultural input application according to real-time data, maximizing the use of resources, improving soil health, and increasing crop yield for sustainable farming. This chapter applies a data-driven, geospatial method to measure VRT adoption using remote sensing, Geographic Information System (GIS) mapping, and analysis of soil variability to examine its effects on indicators of soil health and optimization of crop yield across varying agricultural regions. This chapter aims to depict improved soil nutrient balance, reduced input wastage, and improved crop yield reliability. Spatial analysis would be expected to reveal positive relationships between VRT application zones and optimal productivity, promoting site-specific and sustainable soil management approaches. The chapter discovers that VRT enhances crop yield and soil fertility through effective regulation of inputs. Its use promotes sustainable agriculture through environmental minimization, resource conservation, and long-term soil productivity under a range of farm conditions.","author":[{"family":"Dhepe","given":"Amol"},{"family":"Sharma","given":"Swati"},{"family":"Somasekar","given":"J"},{"family":"Manikandan","given":"G"},{"family":"Kizhakethil","given":"Midhun"},{"family":"Salati","given":"Abid"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003520733-19","URL":"https://doi.org/10.1201/9781003520733-19","source":"crossref"},{"id":"doi:10.9734/bpi/asti/v11/7768","type":"article-journal","title":"AI-Driven Precision Agriculture: A Critical Review of Predictive Irrigation, Yield Monitoring, Smart Fertilization, and Supply Chain Integration","abstract":"Artificial intelligence has moved from a peripheral tool to a central organising technology across the crop production cycle, reshaping how water, nutrients, yield information, and post-harvest logistics are managed. This review synthesises recent scholarship on four interlocking domains of artificial-intelligence-enabled precision agriculture: predictive irrigation scheduling, remote sensing and deep-learning-based yield monitoring, variable-rate and sensor-guided fertilization, and blockchain-artificial-intelligence convergence in agri-food supply chains. Machine learning and deep learning models, including random forests, support vector machines, convolutional neural networks, and deep reinforcement learning agents, have demonstrably improved the accuracy of evapotranspiration estimation, soil moisture prediction, and irrigation timing, while unmanned aerial vehicles and satellite-based multispectral imagery paired with convolutional and transformer architectures have advanced early yield forecasting and pest and disease detection. Variable-rate technologies coupled with artificial-intelligence-driven decision-support systems have improved nutrient-use efficiency and reduced environmental externalities associated with uniform fertilizer application, while blockchain ledgers integrated with machine learning forecasting tools have strengthened traceability, food safety assurance, and demand-driven waste reduction across agri-food value chains. Despite these advances, adoption remains markedly uneven: infrastructural, financial, and digital-literacy barriers concentrate benefits among large, well-resourced producers, particularly in high-income regions, while smallholder farmers in low- and middle-income countries risk further marginalisation. The review also identifies persistent methodological limitations, including narrow geographic representativeness of training datasets, weak external validation, and underdeveloped frameworks for data governance and algorithmic accountability. It concludes that realising the productivity, sustainability, and equity potential of artificial intelligence in agriculture depends less on further algorithmic refinement than on coordinated investment in rural digital infrastructure, interoperable data standards, and inclusive policy design.","author":[{"family":"Antonio","given":"Valles"},{"family":"Manuel","given":"Alonzo"},{"family":"Raymundo","given":"Morales"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/bpi/asti/v11/7768","URL":"https://doi.org/10.9734/bpi/asti/v11/7768","source":"crossref"},{"id":"doi:10.70382/mejavs.v8i1.027","type":"article-journal","title":"IOT-DRIVEN HEALTH MONITORING SYSTEMS FOR BROILER AND NOILER CHICKENS: A SMART PRECISION FARMING APPROACH","abstract":"he poultry industry is essential for global food security, with broiler and Noiler chickens being major contributors to meat production. Traditional poultry farming relies on manual monitoring, which is labor-intensive and inefficient. The Internet of Things (IoT) offers a transformative approach by enabling real-time health monitoring, automation, and data-driven decision-making in poultry management. This study evaluates the impact of an IoT-driven health monitoring system on broiler and Noiler chickens' health, growth, and productivity. A total of 100 chickens are divided into two groups: an experimental group housed in IoT-equipped units with automated monitoring and a control group managed using traditional methods. IoT sensors continuously measure critical parameters such as temperature, humidity, ammonia levels, feed intake, and movement. Real-time data analysis enables early detection of diseases, stress, and abnormal behavior, while the control group relies on manual observation. Preliminary results suggest that IoT-driven monitoring improves poultry health by ensuring timely interventions, reducing mortality, and enhancing feed conversion efficiency. Automated environmental controls minimize stress and maximize weight gain. The study also examines the economic benefits of IoT adoption in commercial poultry farms, emphasizing improved productivity and cost savings. This research highlights the potential of IoT-based health monitoring to revolutionize poultry farming, making it more efficient and sustainable. Future studies will integrate artificial intelligence (AI) for predictive analytics to enhance poultry health management and productivity.","author":[{"family":"Banjoko","given":"IK"},{"family":"Adedotun","given":"KJ"},{"family":"Raji","given":"AK"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70382/mejavs.v8i1.027","URL":"https://doi.org/10.70382/mejavs.v8i1.027","source":"crossref"},{"id":"doi:10.1109/icosec67334.2025.11459507","type":"article-journal","title":"IoT based Automated Irrigation System for Aquaponics and Land Farming","abstract":"To monitor essential environmental parameters in real time, an IoT based smart irrigation system is proposed. pH and TDS sensors in aquaponics systems ensure that the water quality maintains itself at ideal levels for fish and plants, encouraging effective nutrient absorption and water recirculation. In land farming, soil moisture and NPK sensors provide precise data to enable precision irrigation and fertilization. Based on threshold-based decision-making and predictive analytics, the system dynamically triggers water pumps and actuators to regulate irrigation cycles. Cloud integration stores and analyzes historical data, enhancing system reliability and optimizing performance through data-driven insights. Real-time remote monitoring enables farmers to control and manage the system from anywhere, ensuring timely intervention and improved operational efficiency. The system’s performance is enhanced by predictive analytics models that forecast soil moisture and plant growth, enabling adaptive irrigation schedules. Fault detection mechanisms ensure system reliability by preventing sensor drift, communication failures, and power disruptions. By addressing challenges such as sensor calibration, power consumption, and system redundancy, this IOT-based irrigation system ensures consistent and accurate operation. It promotes sustainable agriculture by reducing water waste, lowering energy consumption, and improving overall crop health. The integration of IOT technologies in Aquaponics and land farming offers a scalable, efficient, and environmentally friendly solution for modern agricultural practices.","author":[{"family":"Kavitha","given":"M"},{"family":"Basha","given":"CHH"},{"family":"Janani","given":"B"},{"family":"Gopika","given":"BS"},{"family":"Sivamani","given":"S"},{"family":"Senthilkumar","given":"S"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icosec67334.2025.11459507","URL":"https://doi.org/10.1109/icosec67334.2025.11459507","source":"crossref"},{"id":"doi:10.2174/9789815305067125010016","type":"article-journal","title":"IoT-Based Data Security in Smart Farming Systems","abstract":"Data security is crucial when interacting with internet-based networks, clouds, servers, etc. In today’s world, the most prominent percentage of communication is internet-based. Using sensors like temperature and soil moisture sensors, the collected data is encrypted. The electronic gadgets transform the normal text into unintelligible cipher text, which is then stored in the cloud at the transmitting end. The AES128 key and hash code used on the transmitting side are used to decode data on the receiving side. In this process, if any unauthorized person tries to hack the data, they fail to get the original data since the data is in the form of cipher text. The application of IoT and 5G communication technologies introduces smart farming ecosystems to a wide range of cyber security risks and vulnerabilities. This type of cyberattack will cause economic disruption in nations with significant agricultural dependence. Hence, there is a need for data security in smart farming. In this paper, an efficient and easy way to encrypt the data using Cipher text is shown.","author":[{"family":"Dhanush","given":"GS"},{"family":"Bhattacharya","given":"Devadri"},{"family":"Adithya","given":"JM"},{"family":"Kushal","given":"G"},{"family":"Shrisha","given":"MR"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2174/9789815305067125010016","URL":"https://doi.org/10.2174/9789815305067125010016","source":"crossref"},{"id":"doi:10.31764/jmm.v9i2.30036","type":"article-journal","title":"PENERAPAN SMART FARMING MAGGOT BSF DALAM MENDORONG KUALITAS AYAM UNGGUL","abstract":"Abstrak: Desa Karangkobar di Kendal memiliki lingkungan alam yang subur, menjadikannya tempat yang cocok untuk peternakan ayam. Ketersediaan pakan alami, udara bersih, dan kualitas air yang baik mendukung kesehatan ternak. Masalah pada Tini Farm, mitra peternakan mikro dalam program ini, hanya terdapat 6 pekerja berpendidikan dasar. Peternak ayam masih mengandalkan pakan konvensional (pur) yang rendah protein dan berisiko mengandung zat berbahaya. Alternatif seperti maggot BSF memiliki nutrisi tinggi dan ramah lingkungan, tetapi budidayanya terkendala teknologi, media wadah, serta suhu dan kelembaban yang kurang optimal untuk pertumbuhannya. Tujuan pengabdian adalah penerapan smart farming maggot BSF yang meningkatkan kualitas ayam siap dijual dalam 1–3 bulan antara 125-200 ekor ayam per siklus serta keterampilan mitra dalam pemantauan pertumbuhan maggot berbasis IoT. Metode pelaksanaan koordinasi dengan 6 peternak Tini Farm di Desa Karangkobar, konstruksi, praktik, serta pendampingan penggunaan advanced technology maggot cultivation dan automatic feeder berbasis IoT terutama penerapan suhu optimal (30–36°C) dan kelembaban (60–70%). Sosialisasi meliputi instalasi, kontrol suhu dan kelembaban, serta monitoring real-time. Evaluasi dilakukan melalui wawancara serta kuesioner sebanyak 15 pertanyaan, dengan pendampingan lanjutan selama 3–6 bulan. Hasil survei menunjukkan 72,2% masyarakat tertarik mengenai budidaya maggot sedangkan dalam evaluasi lanjutan 60,6% masyarakat mengalami peningkatan produksi dari budidaya maggot BSF. Teknologi ini mampu menekan biaya produksi dan meningkatkan daya saing peternak.Abstract: Karangkobar Village in Kendal has a fertile natural environment, making it an ideal location for poultry farming. The availability of natural feed, clean air, and highwater quality supports livestock health. However, Tini Farm, a micro-scale poultry farming partner in this program, faces several challenges. It only employs six workers with basic education, and the farmers still rely on conventional feed (pur), which is low in protein and may contain harmful substances. Alternative feeds like BSF maggots offer high nutritional value and are environmentally friendly, but their cultivation is limited by technology, container media, as well as suboptimal temperature and humidity conditions. This program aims to implement smart farming using BSF maggots to enhance chicken quality, enabling sales within 1–3 months, producing 125–200 chickens per cycle. It also focuses on improving farmers' skills in IoT-based maggot growth monitoring. Implementation includes coordination with six poultry farmers at Tini Farm, construction, practical training, and assistance in using advanced maggot cultivation technology and IoT-based automatic feeders. Training covers installation, temperature and humidity control, and real-time monitoring. Evaluation involved interviews and a 15-question questionnaire, followed by 3–6 months of additional assistance. Results show 72.2% of the community is interested in maggot farming, with 60.6% increasing production. This technology reduces costs and boosts competitiveness.","author":[{"family":"Pradnya","given":"Irene"},{"family":"Zakia","given":"Maulida"},{"family":"Sukestiyarno","given":"Yohanes"},{"family":"Enjelita","given":"Anggun"},{"family":"Emyu","given":"Dalnius"},{"family":"Maulana","given":"Ivan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31764/jmm.v9i2.30036","URL":"https://doi.org/10.31764/jmm.v9i2.30036","source":"crossref"},{"id":"doi:10.1038/s41598-025-10537-6","type":"article-journal","title":"AI-driven smart agriculture using hybrid transformer-CNN for real time disease detection in sustainable farming","abstract":"Plant diseases pose a significant threat to global food security, with severe implications for agricultural productivity. Early and accurate detection of these diseases is crucial, yet it remains a challenging task, significantly impacting crop yields and food supply chains. Despite the progress in artificial intelligence, particularly deep learning, challenges persist in real-world applications due to environmental noise, varying light conditions, and other complicating factors that hinder detection accuracy. This study introduces the AttCM-Alex model, a novel deep-learning framework designed to boost the detection and classification of plant diseases under challenging environmental conditions. By integrating convolutional operations with self-attention mechanisms, AttCM-Alex effectively addresses the variability in light intensity and image noise, ensuring robust performance. To simulate practical agricultural scenarios, the study employs bilinear interpolation for image dimension adjustment and introduces Salt-and-Pepper noise. Additionally, the model's robustness was evaluated by varying image brightness levels by ±10%, ±20%, and ±30%. Experimental results demonstrate that AttCM-Alex significantly outperforms traditional models, particularly in scenarios involving fluctuating light conditions and noise interference. The model achieved a peak detection accuracy of 0.97 with a 30% increase in image brightness and maintained an accuracy of 0.93 even with a 30% decrease in brightness, highlighting its robustness and reliability. The findings affirm the AttCM-Alex model as a powerful tool for real-world agricultural applications, capable of enhancing disease detection systems' accuracy and efficiency. This advancement not only supports better crop management practices but also contributes to sustainable agriculture and global food security.","author":[{"family":"Zeng","given":"Zhuo"},{"family":"Mahmood","given":"Tariq"},{"family":"Wang","given":"Yu"},{"family":"Rehman","given":"Amjad"},{"family":"Mujahid","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1038/s41598-025-10537-6","URL":"https://doi.org/10.1038/s41598-025-10537-6","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.100839","type":"article-journal","title":"Precision livestock farming usage among a subset of U.S. swine producers: Insights through a structural equation modeling approach","abstract":"There is limited information about which factors influence the use and intention to use Precision Livestock Farming (PLF) technologies in livestock farming. Effective interventions that address the enablers and barriers to using PLF require a theoretical model to identify these factors. We empirically evaluated the Capability Opportunity Motivation Behavior (COM-B) model using US swine producers as a case study. Specifically, we tested the COM-B model as a framework for planning interventions in two behavioral contexts: PLF usage and the intention to use PLF. Our cross-sectional survey involved 53 swine producers from Iowa, Michigan, and North Carolina. Structural Equation Modeling (SEM) was used to specify and test the models. Most participants were male, aged 31–50, with extensive farming experience. Awareness was high for electronic sow feeders (ESF), radio frequency identification (RFID), and weighing scales but lower for other technologies. Over one-third currently use PLF, with many non-users open to future adoption. Capability positively influences PLF usage, while motivation mediates the effect of opportunity, with high costs deterring usage. Effective interventions should address cost concerns and focus on animal welfare to promote efficient, welfare-friendly swine production.","author":[{"family":"Akinyemi","given":"BE"},{"family":"Siegford","given":"JM"},{"family":"Jessiman","given":"L"},{"family":"Turner","given":"SP"},{"family":"Johnson","given":"AK"},{"family":"Akaichi","given":"F"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.100839","URL":"https://doi.org/10.1016/j.atech.2025.100839","source":"crossref"},{"id":"doi:10.58578/yasin.v6i3.10173","type":"article-journal","title":"Development of a Web Extended Reality (WEBXR) Based Smart Farming Simulation Game for Soybean Cultivation","abstract":"Although digital simulation media in agriculture has received considerable scholarly attention, limited research has specifically addressed the development of Web Extended Reality (WebXR)-based smart farming educational simulations to respond to the low regeneration of young farmers. This study aims to design and develop a WebXR-based smart farming simulation game for soybean cultivation as an interactive learning medium accessible through WebXR-enabled browsers and to evaluate its feasibility and user experience. This study employed a Research and Development (R&amp;D) approach using the Multimedia Development Life Cycle (MDLC) model, consisting of concept, design, material collection, assembly, testing, and distribution stages. Data were collected through observations, interviews, and literature review, involving 50 student respondents from Universitas Pendidikan Ganesha through direct application testing. User experience data were obtained using the Game Experience Questionnaire (GEQ), covering In-Game and Post-Game modules. The findings show that all system functions operated properly based on black box testing and that the application was declared highly valid by both content experts (1.00) and media experts (1.00). GEQ results for the In-Game components showed competence at 2.88 (high/good), sensory and imaginative immersion at 2.90 (high/good), flow at 2.37 (moderate/fair), challenge at 2.74 (high/good), tension/annoyance at 1.33 (low), positive affect at 3.21 (very high), and negative affect at 0.43 (very low). The Post-Game components showed positive experience at 3.07 (high/good), negative experience at 0.30 (very low), tiredness at 0.44 (very low), and returning to reality at 0.95 (low). The study concludes that the WebXR-based smart farming simulation game is feasible for broader implementation and effective in providing an immersive, enjoyable, and interactive learning experience for soybean cultivation. These findings contribute to agricultural education technology by demonstrating the potential of WebXR-based simulation games as modern digital learning media to support smart farming literacy and encourage youth engagement in agriculture.","author":[{"family":"Yuniarta","given":"Gede"},{"family":"Sindu","given":"IGP"},{"family":"Aryanto","given":"Kadek"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58578/yasin.v6i3.10173","URL":"https://doi.org/10.58578/yasin.v6i3.10173","source":"crossref"},{"id":"doi:10.1109/ised67359.2025.11405300","type":"article-journal","title":"Agribot: Smart Farming Robot with RFID Navigation for Selective Pesticide Spraying","abstract":"Excessive pesticide usage in conventional farming poses serious health hazards and leads to environmental contamination. This paper presents Agribot, a semi-autonomous ground robot for selective pesticide spraying using RFID-based navigation and lightweight CNN-based weed detection. The system integrates an ESP32 microcontroller, L298N motor driver, ultrasonic sensors, and a smartphone camera for real-time image processing and control. Upon detecting weeds, Agribot automatically halts, activates a localized spraying mechanism, and resumes motion guided by RFID tags without GPS dependence. The proposed model achieved 89% accuracy, 91.2% precision, and an F1-score of 88.7% on a dataset of 6,324 images. Field trials on $\\mathbf{5} \\mathbf{m \\times 3 m}$ plot showed a navigation deviation within $\\pm 8 \\mathrm{~cm}$ and 42% pesticide savings over manual spraying, offering a scalable, low-cost, and safer precision-agriculture solution.","author":[{"family":"Mittapally","given":"Haritha"},{"family":"Bommera","given":"Likith"},{"family":"Karna","given":"Shushruth"},{"family":"Nunsavathu","given":"Gireeshma"},{"family":"Karvanga","given":"Rohit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/ised67359.2025.11405300","URL":"https://doi.org/10.1109/ised67359.2025.11405300","source":"crossref"},{"id":"doi:10.62273/dmuu5863","type":"article-journal","title":"Teaching Case: Smart Poultry Farming Using the Internet of Things, Artificial Intelligence, and Analytics: A Project Management Case","abstract":"Efficient and profitable business operations today rely on the use of advanced technologies.This is particularly evident in managing family farms in the competitive broiler chicken industry.Farmers raising broiler chickens from chick to optimum weight in five weeks require investments in and use of smart farming technologies employing the Internet of Things (IoT), automated monitoring and alerts, artificial intelligence, and machine learning.This case explores these technologies at one family farm in North Georgia to understand how smart technologies and the Internet of Things (IoT) provide an automated workforce and consistent production results.The farm, located in Dawsonville, Georgia, is a large operation raising 200,000 chickens per cycle with a workforce of two.Understanding the application of smart technologies in family business operations aids in meeting world food demand, increasing food quality, and farmer profitability.This case study is used in undergraduate and graduate-level management information systems, analytics, and project management courses to critically evaluate the application of these technologies in creating a more efficient business operation.Teaching notes with suggested guidelines, assignments, and discussions are provided upon request.","author":[{"family":"Mcwilliams","given":"Denise"},{"family":"Mady","given":"Ash"},{"family":"Smatt","given":"Cindi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.62273/dmuu5863","URL":"https://doi.org/10.62273/dmuu5863","source":"crossref"},{"id":"doi:10.55041/ijsrem58769","type":"article-journal","title":"AgroMitra AI: An AI-Based Smart Farming System for Soil Nutrient Analysis","abstract":"Abstract - Agriculture plays a vital role in sustaining the global economy and food supply. However, improper soil nutrient management leads to reduced crop yield and inefficient fertilizer usage. This paper presents the design and implementation of an AgroMitra AI: An AI-Based Smart Farming System for Soil Nutrient Analysis. The system utilizes sensors to measure key soil parameters such as nitrogen (N), phosphorus (P), potassium (K), moisture, temperature, and pH. The collected data is processed using an AI model to predict soil nutrient levels and recommend suitable fertilizers based on crop type. The proposed system integrates ESP32 for real-time data acquisition and wireless communication with a mobile application. Experimental results show improved accuracy in nutrient estimation and optimized fertilizer usage. The system provides a cost-effective and scalable solution for precision agriculture. Key Words: Smart Farming, Soil Nutrients, ESP32, Artificial Intelligence, IoT,","author":[{"family":"Jamdar","given":"RS"},{"family":"Agre","given":"Shubham"},{"family":"Chavan","given":"Pruthviraj"},{"family":"Jadhav","given":"Aditya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsrem58769","URL":"https://doi.org/10.55041/ijsrem58769","source":"crossref"},{"id":"doi:10.1109/iconstem65670.2025.11374887","type":"article-journal","title":"Smart Farming: Harnessing Robotics and Automation for Sustainable Agricultural Practices","abstract":"Innovations in robots, artificial intelligence (AI), and the internet of things (IoT) are transforming precision agriculture and soil resource conservation. The system enables resource optimisation, data-driven decision-making, and environmentally sustainable farming. Because AI enables advanced predictive analysis, farmers may anticipate crop outcomes, identify diseases beforehand, and optimise planting schedules. Real-time crop development, patterns of weather and health of soil monitoring are made measurable by IoT-based sensor networks, which facilitate quicker and more effective farm operations. By introducing autonomous platforms for soil testing, harvesting, and seeding, robotics revolutionizes traditional farm labour while reducing labour costs and increasing operational efficiency. This investigation primary objective is to use robotics, machine learning (ML), and the IoT to forecast yields of crop depends on soil and climate data. The investigation makes use of a Kaggle dataset that has data on 12 different crops. The collection includes vital soil parameters required for the best crop growth as well as important climate variables like temperature, humidity, and rainfall. The goal is to create precise models that can forecast crop production by using sophisticated ML methods and Robotics on this dataset. As a result, this helps farmers maximise their agricultural earnings and make decisions which is informed about management of crop. The findings of this study have important ramifications for the agriculture sector since they support the adoption of sustainable farming methods and offer insightful information about crop yield estimation.","author":[{"family":"Patange","given":"Gajanan"},{"family":"Baral","given":"Debabrata"},{"family":"Bose","given":"Akruti"},{"family":"Shrivastava","given":"Namrata"},{"family":"Subha","given":"L"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iconstem65670.2025.11374887","URL":"https://doi.org/10.1109/iconstem65670.2025.11374887","source":"crossref"},{"id":"doi:10.52151/aet2022464.1607","type":"article-journal","title":"Internet of things (IOT) based smart farming: A futuristic approach","abstract":"The world population has touched 7.9 billion mark and the expected growth is 9 billion by 2050 and 11 billion by 2100 (Muzamil et al., 2022). The rise has coincided with an increase in urbanization and industrialization; triggering rural-urban migration and creating a vacuum in terms of labour workforce in the agricultural sector. Although, a number of technologies were developed in the agricultural sector, however, the sector continues to rely heavily on the manual labour. Agricultural is labour intensive and dangerous occupation after construction and mining owing to its high injury and fatality rates. In India, a report suggested that the agricultural workforce reduced from 54% to 40% in last one decade and can reach to 26% by 2050. This has the propensity to expose the agricultural system to new challenges, jeopardize the existing social order and threaten the food security system.","author":[{"family":"Banday","given":"Rizwan"},{"family":"Muzamil","given":"Mohd"},{"family":"Kumar","given":"Amit"},{"family":"Mohiuddin","given":"Masrat"},{"family":"Kumar","given":"Rohitashw"},{"family":"Rashid","given":"Saqib"}],"issued":{"date-parts":[[2025]]},"DOI":"10.52151/aet2022464.1607","URL":"https://doi.org/10.52151/aet2022464.1607","source":"crossref"},{"id":"doi:10.71302/jamas.v6i1.105","type":"article-journal","title":"Implementasi Smart Farming Berbasis Fuzzy Sugeno untuk Penyiraman dan Pemupukan Otomatis Tanaman Sawi Hijau","abstract":"Sektor pertanian di Indonesia memerlukan pengelolaan penyiraman dan pemupukan yang tepat untuk mendukung pertumbuhan tanaman secara optimal. Namun, sebagian besar petani masih menggunakan metode manual dalam menentukan waktu dan jumlah penyiraman maupun pemupukan, sehingga proses tersebut kurang efisien dan berpotensi menyebabkan ketidaktepatan dalam pemberian air dan nutrisi. Berbagai penelitian sebelumnya umumnya hanya mengembangkan sistem penyiraman otomatis berbasis sensor kelembapan tanah, sedangkan integrasi antara penyiraman otomatis, pemupukan otomatis berdasarkan pH tanah, dan monitoring lingkungan secara real-time masih terbatas. Oleh karena itu penelitian ini mengembangkan sistem yang mengintegrasikan seluruh fungsi tersebut dalam satu platform berbasis Internet of Things menggunakan metode Fuzzy Sugeno. Penelitian ini bertujuan merancang dan mengimplementasikan sistem smart farming berbasis mikrokontroler yang mampu melakukan penyiraman dan pemupukan secara otomatis sesuai dengan kondisi tanaman. Sistem dikembangkan menggunakan mikrokontroler ESP32 yang terhubung dengan jaringan Wi-Fi. Sensor Soil Moisture digunakan untuk mengukur kelembapan tanah sebagai dasar pengendalian penyiraman, sedangkan sensor Soil pH digunakan untuk mengukur tingkat keasaman tanah sebagai acuan pemupukan. Selain itu, sensor DHT11 digunakan untuk memantau suhu udara dan sensor LDR untuk mengukur intensitas cahaya. Seluruh data sensor dikirim ke basis data dan ditampilkan secara real-time melalui dashboard monitoring. Metode Fuzzy Sugeno diterapkan untuk mengolah data kelembapan dan pH tanah sehingga sistem dapat menentukan durasi penyiraman dan pemupukan secara otomatis. Hasil penelitian menunjukkan bahwa sistem yang dikembangkan mampu melakukan penyiraman dan pemupukan secara otomatis berdasarkan kondisi tanah serta menampilkan informasi hasil pembacaan sensor secara real-time melalui dashboard monitoring. Berdasarkan hasil pengujian dapat disimpulkan bahwa sistem Smart Farming berbasis ESP32 dan metode Fuzzy Sugeno berhasil mengintegrasikan penyiraman otomatis, pemupukan otomatis, dan monitoring real-time sehingga mampu memberikan keputusan penyiraman dan pemupukan sesuai kondisi tanah tanaman sawi hijau","author":[{"family":"Hadriansa"},{"family":"Simung","given":"Okky"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71302/jamas.v6i1.105","URL":"https://doi.org/10.71302/jamas.v6i1.105","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101690","type":"article-journal","title":"Deep learning-based holstein face recognition in real-world farming conditions","abstract":"Non-contact biometric identification of cattle using visual facial features is now feasible due to recent advances in computer vision and deep learning. However, the lack of publicly available datasets continues to prevent the development and fair evaluation of robust models. This study attempts to address this gap by proposing Holstein2025, a benchmark dataset of individual cow face images captured using fixed-position side-view surveillance cameras in a commercial dairy farm. Holstein2025 reflects real-world environmental variability and supports both face detection and identification tasks. A systematic evaluation of state-of-the-art backbones and face recognition loss functions was conducted. The final pipeline integrates YOLO11n with an oriented bounding box head for cow face detection and alignment (average precision of 0.995, processing time of 11.2 ms), and a ConvNeXt-Tiny-based face identification network trained with an optimised ArcFace-based loss incorporating two auxiliary terms (accuracy of 0.97, processing time of 0.6 ms per face). Overall, the system runs in real time and achieved a precision of 0.98 in open set testing at a similarity threshold of 0.807. To promote reproducibility and practical application, all code and data are open-sourced and released with this paper.","author":[{"family":"Shu","given":"Hang"},{"family":"Jin","given":"Zhongming"},{"family":"Guo","given":"Gang"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101690","URL":"https://doi.org/10.1016/j.atech.2025.101690","source":"crossref"},{"id":"doi:10.55544/sjmars.icmri.10","type":"article-journal","title":"Next-Generation Farming: Leveraging IoT Sensors for Sustainable Smart Agriculture","abstract":"The agricultural industry in India is losing ground daily, which has an impact on the ecosystem's ability to produce. Resolving the issue is becoming more and more important to revitalize agriculture and return it to a path of higher growth. An extensive agricultural system requires a lot of maintenance, expertise, and supervision. The Internet of Things (IoT) is a network of linked devices that may communicate and receive information via the Internet and perform tasks without the need for human intervention. Increased crop yields are the outcome of the abundance of data analysis parameters provided by agriculture. The modernization of communication and information is facilitated by the use of IoT devices in smart farming. It is reasonable to expect that moisture, minerals, light, and other elements will improve crop development. In this study, we are discussing to development of the agriculture system in India. An advanced version of agriculture for farmers who can grow, develop and cares of the crops. The aim of next-generation agriculture by IOT sensors is to merge intelligent technologies to produce an agricultural environment that is more precise, effective, and sustainable. This system is based on advanced sensor technologies, like weather sensors, temperature sensors, humidity sensors, rainfall, wind, and soil sensors, which monitor temperature, pH, and moisture level. Also, livestock sensors to monitor the health of crops and the movement of pests, insects, and animals Wireless communication technologies such as LPWAN (local power wide area network), including LoRa and NB-IoT, are utilized for data collection and transfer in faraway agricultural areas due to their long-range and low power consumption. Farmers can increase resource use, improve production, and reduce their impact on the environment. To support seamless data collection and transmission in remote agricultural areas, wireless communication technologies such as LPWAN (Low Power Wide Area Network), including LoRa and NB-IoT, are utilized for their low power consumption and long-range capabilities. These technologies enable continuous monitoring and real-time decision-making, allowing farmers to optimize resource use, increase yield, and reduce environmental impact. Overall, next-generation IoT-based agriculture combines sensor data with connectivity and analytics to transform traditional farming into a smart, data-driven practice.","author":[{"family":"Negi","given":"Divyanshu"},{"family":"Verma","given":"Atul"},{"family":"Gaurav"},{"family":"Kumar","given":"Aman"},{"family":"Srivastava","given":"Saurabh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55544/sjmars.icmri.10","URL":"https://doi.org/10.55544/sjmars.icmri.10","source":"crossref"},{"id":"doi:10.1109/icccit62592.2025.10928096","type":"article-journal","title":"AI for Smart Farming: Machine Learning Models for Precision Crop Yield Prediction","abstract":"AI and other advanced technologies are gradually beginning to invade the agriculture sector to serve the increasing demand of the consumers for better methods of food production. A key component of precision agriculture, this work focuses on how to use machine learning models to predict crop yields with high accuracy. Specifically, the nature and volatility of the environmental context – such as the nature and quality of soils, as well as the climatic and water conditions – present a major challenge to the application of the conventional modeling approaches aimed at forecasting productive capacity in agriculture. Still, when comparing, the AI-driven models will allow sorting through much information gathered from different sources, including sensors, satellite imagery, and yield history. This work examines the differences of several machine learning models. Such models are the Random Forests, SVMs, and CNNs and other Deep Learning methodologies respectively. A quality model is evaluated based on scalability, computational performance, and prediction accuracy. Also in scope of the study, there is an opportunity to employ IoT together with data collected with remote sensing to make and provide realtime forecasts and evaluations. By the utilization of the results attained, it is established that the yields expected by the machine learning models are much more precise, which aids in enhancing agricultural decision-making concerning resource utilizing, crop handling, and risk minimization. The purpose of this study is focused on the promotion of the agricultural sustainability and production through the development of the innovative data driven farming practices.","author":[{"family":"Praveen","given":"Rvs"},{"family":"Maindola","given":"Meenakshi"},{"family":"Bhavana","given":"Munugapati"},{"family":"Nijhawan","given":"Ginni"},{"family":"Raju","given":"Hemanth"},{"family":"Bansal","given":"Saloni"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icccit62592.2025.10928096","URL":"https://doi.org/10.1109/icccit62592.2025.10928096","source":"crossref"},{"id":"doi:10.1108/ijqrm-09-2024-0320","type":"article-journal","title":"Empirical investigation of barriers and benefits of smart farming","abstract":"Purpose Smart farming (SF) holds immense potential in making farming viable and improving farmers' livelihoods. However, its adoption is still in the early stages, and the resulting impacts are underexplored. This study investigates the information systems/policy and implementation barriers to the adoption of SF and its implications for various socioeconomic aspects. Design/methodology/approach This survey research used a structured questionnaire to collect data on farm details, farmer characteristics and usage of SF technologies from a sample of 197 farmers based in the State of Karnataka, India. Exploratory factor analysis with principal component extraction is used to validate the proposed questionnaire constructs. Results are analyzed using one-way and two-way ANOVAs and interaction plots. Findings Our study throws light on the benefits and barriers of SF technologies. Advanced SF technologies displayed a significant positive effect on socioeconomic variables compared to startup SF technologies, which displayed no significant effect. Overcoming information systems/policy barriers for adopting startup and advanced SF technologies displayed significant positive effects on farmers' health and net income, whereas overcoming implementation barriers for adopting advanced SF technologies led to improvement in the farmers' gross income. Originality/value Although the technical feasibility of SF has been explored in the literature, its adoption barriers and socioeconomic impacts have been underexplored. To the best of our knowledge, the interaction between different types of barriers and the level of SF adoption has not yet been investigated in the literature. Our study addresses those research gaps using data from a previously underexplored context, viz. developing nations.","author":[{"family":"Narayanamurthy","given":"Gopalakrishnan"},{"family":"Jayanth","given":"RSS"},{"family":"Tortorella","given":"Guilherme"},{"family":"Fogliatto","given":"Flávio"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1108/ijqrm-09-2024-0320","URL":"https://doi.org/10.1108/ijqrm-09-2024-0320","source":"crossref"},{"id":"doi:10.1088/1742-6596/2949/1/012060","type":"article-journal","title":"IoT-based Smart Agriculture System: Design of Farming Diary","abstract":"Abstract Agriculture has played an important role in human society since ancient times, providing livelihoods and contributing signi(icantly to the economy of a country. Nowadays, climate change is increasingly having a direct and profound impact on crop productivity. These changes affect soil nutrients, pests, and water levels. To mitigate these impacts and increase crop productivity, IoT (internet of things) technology has been and is being utilized to transform agricultural cultivation processes not only to improve production methods, and reduce costs but also to ensure traceability and enhance environmental sustainability. In this paper, a smart farming diary is designed and implemented on mobile and web applications based on IoT technology. The system allows farmers to record detailed farming activities, including information on seeds, fertilizers, pesticides, weather, and other factors affecting crops. All data is collected from sensors, and IoT terminal devices for statistics, stored as logs, and analyzed to evaluate the effectiveness of the system.","author":[{"family":"Nguyen-Tat","given":"Thien"},{"family":"Phuc","given":"Kha"},{"family":"Do","given":"Tri"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1088/1742-6596/2949/1/012060","URL":"https://doi.org/10.1088/1742-6596/2949/1/012060","source":"crossref"},{"id":"doi:10.1109/icaaid68975.2025.11358131","type":"article-journal","title":"UAV_LINK: A UAV-Assisted Communication Framework for Smart Farming in Isolated Environments Using Satellite-Based Edge Computing","abstract":"Smart farming in remote areas often suffers from poor connectivity, high communication delays, and limited energy resources, making it difficult to rely on traditional cloud-based systems. To overcome these challenges, we introduce UAV_LINK, a UAV-assisted communication framework that integrates unmanned aerial vehicles (UAVs) with satellite-based edge computing. In this system, UAVs act as intelligent relays between ground IoT devices and satellite layers—mist, edge, and cloud—ensuring that farming data is processed closer to where it is generated. UAV_LINK adapts task offloading decisions in real time by balancing communication delay and execution cost according to each application’s requirements. Simulation results using the SatEdgeSim environment show that UAV_LINK consistently achieves lower end-to-end delay, reduced average energy consumption (especially when the number of satellites is low), lower network usage, and a higher task success rate compared to conventional algorithms such as Round Robin, Trade Off, and Weighted Greedy. These improvements come at the expense of slightly higher CPU utilization, due to the framework’s adaptive optimization process. Overall, UAV_LINK demonstrates that combining UAVs with satellite-edge computing can provide a practical and efficient solution for smart farming in isolated environments, helping bridge the connectivity gap and promote sustainable agricultural operations.","author":[{"family":"Babaghayou","given":"Messaoud"},{"family":"Zaoui","given":"Fatima"},{"family":"Benfriha","given":"Sihem"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaaid68975.2025.11358131","URL":"https://doi.org/10.1109/icaaid68975.2025.11358131","source":"crossref"},{"id":"doi:10.1051/shsconf/202521601022","type":"article-journal","title":"Edge Computing for Real-Time Climate Data Analysis in Smart Farming","abstract":"In modern agriculture, there is a need for precise and timely analysis of climate data for its sustainability. In smart farming, real-time insight is scheduled for the informed decision taking but the traditional ways of data collection and processing does not support such fast and accurate measurements. This study proposes an edge computing-based system to tackle this challenge to minimize the latency by performing the data analysis on the data source, or on the edge. It proposes the integration of edge cloud computing with real-time climate collection so that the condition of dynamic environment can be continuously analyzed. By doing data processing at the edge, latency is reduced and the accuracy of the predictions is improved at the same time, so the farmers are able to take data driven decision when it matters most. Real time datasets coming from sensors of a smart farming setup were used to test the system. The results shows 35% saved data processing latency and 92% of the prediction accuracy in climate conditions and anomalies. Such outcomes allowed the scheduling of effective irrigation and the decision making on crop management, which demonstrated the potential of edge computing to replace conventional farming with more efficient, data based methods.This implementation is to emphasize the edge computing led transformative opportunities for sustainable and productive agriculture by enabling faster and more actionable decision making.","author":[{"family":"Shnain","given":"Ammar"},{"family":"Abed","given":"Z"},{"family":"Annapoorna","given":"Errabelli"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1051/shsconf/202521601022","URL":"https://doi.org/10.1051/shsconf/202521601022","source":"crossref"},{"id":"doi:10.1002/9781394248711.ch13","type":"article-journal","title":"Smart Farming Technologies","abstract":"The convergence of the Internet of Things (IoT), data analytics, and machine learning is transforming contemporary agriculture, resulting in the development of smart farming and precision agriculture. The current review synthesizes results of 24 seminal studies that discuss varied applications of IoT-based technologies across agricultural production. These reports identify improvements in sensor networks, wireless communications, cloud platforms, and data-driven decision-making software that allow for real-time monitoring, efficient irrigation, pest management, and yield forecasting. The application of big data and artificial intelligence has been invaluable in converting raw data into useful information, enhancing farm productivity, sustainability, and profitability. While the potential is clear, scalability, interoperability, data security, infrastructure capacity, and rural adoption obstacles continue to exist. Multiple studies also highlight the need for leveraging geospatial data and wireless sensor networks for improving decision-making accuracy. The combination of smart devices and analytics not only helps in solving food security problems but also supports global initiatives to implement sustainable agriculture and climate resilience. This systematic review serves as a basis for future research and deployment plans, with the aim of overcoming practical limitations and increasing technological resilience in heterogeneous agro-ecosystems.","author":[{"family":"Dilip","given":"R"},{"family":"Nishchitha","given":"MH"},{"family":"Talikoti","given":"Mallika"},{"family":"Kalpavi","given":"CY"},{"family":"Balaraj","given":"Harshini"},{"family":"Tejashwini","given":"N"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394248711.ch13","URL":"https://doi.org/10.1002/9781394248711.ch13","source":"crossref"},{"id":"doi:10.2174/9798898815912126010018","type":"article-journal","title":"Smart Farming with Deep Learning: Enhancing Crop Management through Advanced Image Analysis","abstract":"A type of advanced image processing and data technologies for analysis with promising outcomes is called deep learning, or DL. In addition to being used in many other industries, DL is also being used in agriculture. Because deep learning algorithms provide precise predictions and sophisticated image processing, they have completely changed several industries, particularly agriculture. This study provides a comprehensive overview of study results and publications on deep learning methods for agricultural image processing and prediction and their variations, emphasizing the uses of these networks in weed proof of identity, irrigation administration, disease identification, and crop yield prediction. This work focuses on specific agricultural issues, the model and architecture that were employed, the resources from which the data were gathered, the data preparation process, and the overall operation carried out in compliance with the methodology applied to each investigation project. Additionally, we examine numerous deep learning approaches used in other fields and also contrast them with current methodologies. When it comes to regression and classification performance, deep machine learning performs differently from more traditional methods. Our results show that deep machine learning yields results with excellent accuracy. Compared to conventional photographic processing techniques, these outcomes are far more accurate. In addition to classification tasks, deep learning can be used for yield manufacturing, detection, and disease division.","author":[{"family":"Chaturvedi","given":"Ravi"},{"family":"Mishra","given":"Annu"},{"family":"Nayyar","given":"Poorva"},{"family":"Asthana","given":"Sameer"},{"family":"Shaliyar","given":"Mohd"},{"family":"Singh","given":"Rajneesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898815912126010018","URL":"https://doi.org/10.2174/9798898815912126010018","source":"crossref"},{"id":"doi:10.71443/9789349552364-05","type":"article-journal","title":"AI Based Decision Support Systems for Irrigation Scheduling and Water Resource Optimization","abstract":"The integration of Artificial Intelligence (AI) into water management systems represents a significant advancement in optimizing water usage, enhancing sustainability, and addressing the growing challenges of water scarcity and climate change. AI-based decision support systems (DSS) leverage real-time data, machine learning algorithms, and predictive analytics to improve irrigation scheduling, optimize water allocation, and support decision-making processes in agricultural and urban water systems. Despite the immense potential of AI in revolutionizing water resource management, the adoption of AI technologies in conventional water frameworks faces numerous challenges, including technological, regulatory, and organizational barriers. This chapter explores the critical role of AI in transforming existing water management practices, emphasizing the need for effective communication among stakeholders, comprehensive training programs for water professionals, and robust policy frameworks. By addressing key gaps and opportunities for AI integration, the chapter outlines strategies to ensure equitable and efficient water distribution, enhance water-use efficiency, and promote sustainable practices. Furthermore, it discusses the essential role of government policies and cross-sector collaboration in facilitating the adoption of AI-enabled water management systems. The chapter provides valuable insights into how AI can complement traditional water governance systems, ultimately contributing to the optimization of global water resources in an era of growing environmental and socio-economic pressures.","author":[{"family":"Rajkumar","given":"Kotalwar"},{"family":"Raghavendra","given":"Kulkarni"},{"family":"Upadhye","given":"Nishant"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-05","URL":"https://doi.org/10.71443/9789349552364-05","source":"crossref"},{"id":"doi:10.24014/ijaidm.v8i1.31823","type":"article-journal","title":"Implementation of Fuzzy Logic Method on Plantation Monitoring System in Website-Based Smart Farming","abstract":"The plantation sector is a crucial component of agriculture. However, plantation management faces several challenges, including limited technological integration within agriculture. The adoption of technology in plantations, particularly IoT (Internet of Things)-based monitoring systems, has become a significant trend in recent years. This system is designed to improve the efficiency of Smart Farming, allowing for more optimized management. This study implements the Fuzzy Logic method in a corn plantation monitoring system to address uncertainties and complexities in decision-making. The system integrates hardware and software, enabling real-time monitoring of environmental conditions through a web-based interface. Testing results indicate that the developed system achieves an accuracy level of 97.42%, providing valuable and responsive data to support farmers in decision-making. With this system, farmers can more effectively monitor and manage plantation conditions, potentially increasing productivity and agricultural yield quality.","author":[{"family":"Oktariani","given":"Clara"},{"family":"Nurdin","given":"Ali"},{"family":"Handayani","given":"Ade"}],"issued":{"date-parts":[[2025]]},"DOI":"10.24014/ijaidm.v8i1.31823","URL":"https://doi.org/10.24014/ijaidm.v8i1.31823","source":"crossref"},{"id":"doi:10.12962/j26139960.v9i5.2344","type":"article-journal","title":"Automasi Pengusiran Hama melalui Aplikasi Smart Farming untuk Meningkatkan Produktivitas Pertanian di Desa Krogowanan, Magelang","abstract":"Kabupaten Magelang merupakan salah satu kabupaten dengan produksi padi yang melimpah bahkan melebihi target menjadikannya daerah dengan produksi padi tertinggi di Jawa Tengah. Desa Krogowanan, Kecamatan Sawangan, Magelang merupakan salah satu desa yang berada di Kabupaten Magelang yang memiliki pengembangan komoditas padi terbesar dengan luas lahan sawah mencapai 1756 Ha. Di Desa Krogowanan, praktek pertanian masih didominasi olah pertanian monokultur dan belum banyak memanfaatkan teknologi pertanian modern secara optimal. Pola tanam ini rentan terhadap serangan hama dan belum memanfaatkan teknologi modern dalam budidaya padi mereka. Ketergantungan pada metode tradisional ini tidak hanya meningkatkan risiko kegagalan panen akibat hama tetapi juga membatasi kemampuan petani untuk merespon cepat terhadap gangguan tersebut. Serangan hama wereng coklat yang dapat mengakibatkan kerugian produksi hingga 70% telah menjadi masalah serius di beberapa daerah di Kabupaten Magelang, termasuk Desa Krogowanan. Penanganan yang tidak efektif dan kurangnya penggunaan teknologi dalam pengendalian hama dapat mengurangi kualitas dan kuantitas produksi padi. Berdasarkan latar belakang permasalahan yang telah dijelaskan di atas, Laboratorium Simulasi Sistem Tenaga Listrik Departemen Teknik Elektro ITS berencana untuk melaksanakan pengabdian masyarakat berbasis produk dengan mengimplementasikan sistem smart farming berupa integrasi power supply dan aktuator dengan pengendalian melalui website Internet of Things (IoT). Hal ini bertujuan untuk memudahkan petani untuk monitoring kondisi lahan mereka dari mana saja dan kapan saja untuk mengelola hasil tani menjadi lebih efisien.","author":[{"family":"Aryani","given":"Ni"},{"family":"Penangsang","given":"Ontoseno"},{"family":"Wibowo","given":"Rony"},{"family":"Soeprijanto","given":"Adi"},{"family":"Putra","given":"Dimas"}],"issued":{"date-parts":[[2025]]},"DOI":"10.12962/j26139960.v9i5.2344","URL":"https://doi.org/10.12962/j26139960.v9i5.2344","source":"crossref"},{"id":"doi:10.31764/am.v5i2.36608","type":"article-journal","title":"Agro-Scan: Pemanfaatan Aplikasi Smart Farming Untuk Deteksi Dini Penyakit Daun Padi Berbasis AI sebagai Upaya Digitalisasi Pertanian Presisi","abstract":"Abstract: The decline in rice production yields due to leaf disease outbreaks has become a major issue for the Joint Farmers Group in Kuper Village, Merauke Regency, with harvest yields during 2022–2023 reaching only 40–50% of the previous year. The delay in identifying diseases and the lack of understanding about effective prevention methods resulted in the excessive use of pesticides and chemicals, leading to increased production costs and a decrease in rice quality. The objective of this community service program is to digitalize agriculture with a precision approach by utilizing an AI-based smart farming application to enable the early detection of rice leaf diseases. The method employed is Participatory Action Research (PAR), which includes socialization, farm management training, and technology implementation. The result of this project is the implementation of the Agro-Scan application, an AI and IoT-based smart farming tool that can detect diseases through image analysis and provide real-time control recommendations; based on farmer observations, the yields from the subsequent harvest are expected to potentially achieve three times the previous amount.Abstrak: Permasalahan penurunan hasil produksi padi akibat serangan penyakit daun menjadi persoalan Gabungan Kelompok Tani (Gapoktan) di Kampung Kuper Kabupaten Merauke, dengan hasil panen selama tahun 2022-2023 hanya mencapai 40-50% dari tahun sebelumnya. Keterlambatan dalam mengidentifikasi penyakit dan minimnya pemahaman tentang cara pencegahan yang efektif berakibat pada penggunaan pestisida dan bahan kimia yang berlebihan, yang menyebabkan peningkatan biaya produksi dan penurunan kualitas beras. Tujuan dari program pengabdian masyarakat ini adalah untuk mendigitalisasi pertanian dengan pendekatan presisi melalui pemanfaatan aplikasi pertanian pintar berbasis AI guna mendeteksi secara dini penyakit daun padi. Metode yang digunakan yaitu Participatory Action Research (PAR), yang mencakup sosialisasi, pelatihan manajemen pertanian, serta penerapan teknologi. Hasil dari proyek ini adalah penerapan aplikasi Agro-Scan, yaitu aplikasi pertanian pintar berbasis AI dan IoT yang memungkinkan dapat mendeteksi penyakit melalui analisis gambar dan memberikan rekomendasi pengendalian secara realtime. Dari pengamatan petani, hasil yang diperoleh dari hasil panen nantinya dapat mencapai 3 kali lipat dari sebelumnya.","author":[{"family":"Nggego","given":"Dedy"},{"family":"Anwar","given":"Anwar"},{"family":"Rahayu","given":"Tri"},{"family":"Erwin","given":"Erwin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.31764/am.v5i2.36608","URL":"https://doi.org/10.31764/am.v5i2.36608","source":"crossref"},{"id":"doi:10.1016/j.cose.2025.104790","type":"article-journal","title":"Systematic mapping study to assess security landscape for IoT-based smart farming systems","abstract":"• The paper identifies the current trends in key security technologies for IoT-based smart farming through a systematic mapping study. • The paper assesses the technology readiness level (TRL) of each identified key security solution and the characteristics of a security product identified by ISO/IEC 25010. • Mapping of ISO/IEC 25010 security characteristics and Technology Readiness Level Smart farming systems sit at the intersection between three rapidly and independently advancing fields of IoT, Security, and Machine Learning. Its full realisation has tremendous positive impacts on food production; yet agricultural settings come with unique challenges that inhibit the rapid deployment of such state-of-the-art technologies. In this paper, we systematically study the current state of security for IoT-based smart farming research and development landscape and assess the proposed security solutions through the lens of technology readiness levels (TRL) and ISO/IEC 25010 security product evaluation framework. By analysing forty-eight primary studies, we identified the top security technologies under development, the critical security threats being addressed, and the most popularly used machine learning-based security solutions. Furthermore, we found that most of the ISO/IEC 25010 security characteristics considered by the security solutions are currently below TRL 6, indicating that they are well below the deployment readiness levels. Therefore, we recommend several supporting transitional technologies be developed to move the prototype development towards system validation and deployment to avoid the technology “valley of death”, such as farming-specific intrusion detection public datasets and large-scale IoT agriculture testbeds to validate the interoperability and transparency of security solutions at different layers. This systematic mapping study, together with a TRL assessment and ISO 25010 standard mapping, is the first of its kind, intending to provide a standardised comparison of the current state of security technologies for IoT-based smart farms to define a clear roadmap for future research and development. It provides a common terminology for the multidisciplinary stakeholders of smart farming to distinguish between theoretical security concepts and ready-to-deploy solutions, facilitating crucial decisions for investment, deployment, and commercialisation.","author":[{"family":"Zahid","given":"Farzana"},{"family":"Chen","given":"Xiao"},{"family":"Sohail","given":"Shaleeza"},{"family":"Li","given":"Boyang"},{"family":"Ooi","given":"Melanie"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.cose.2025.104790","URL":"https://doi.org/10.1016/j.cose.2025.104790","source":"crossref"},{"id":"doi:10.21015/vtcs.v13i1.2138","type":"article-journal","title":"AGRITECH: A Smart System for Sustainable Farming","abstract":"Conventional agriculture, which requires human labor and does not use any kind of mechanism, is proved to be very less efficient and cannot meet the growing food requirements of the world. The application of IoT as a means of implementing change toward precision agriculture is presented below. The following paper describes the design of a smart agricultural system using IoT devices, Raspberry Pi, and a set of sensors: soil moisture, humidity, gas, flame, and motion sensors to improve farming. High technologies like drone and image processing are used to check the health of the plant and increase the production during the farming process.The smart system substantially enhances the productivity and utilization of resources by making smart choices. A mobile application can expand the system’s capabilities, data protection, low energy consumption and high reliability. This specific use of IoT makes farming more efficient to enable farmers to grow more crops and make more profits as a positive step towards sustainable farming. From the research, the authors have been able to show how IoT can be implemented in agriculture to facilitate better yield, resource utilization, and its sustainable utilization.The implementation of IoT-based smart agriculture systems significantly enhanced farming efficiency, resource utilization, and crop yield. Results indicate improved decision-making, reduced manual labor, and increased productivity through automated monitoring and mobile-based control.","author":[{"family":"Abdullah"},{"family":"Haque","given":"Hafiz"},{"family":"Ahmad","given":"Nadeem"},{"family":"Aini","given":"Qurat"},{"family":"Saeed","given":"Ali"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21015/vtcs.v13i1.2138","URL":"https://doi.org/10.21015/vtcs.v13i1.2138","source":"crossref"},{"id":"doi:10.1109/icmnwc63764.2024.10872060","type":"article-journal","title":"Intelligent Farming in Rural Areas: CBGRU-Based Smart Agriculture and Precision Solutions","abstract":"Climate-Smart Agriculture (CSA) aims to reduce food insecurity, boost rural economies, and protect the environment. CSA programs sometimes ignore small-scale farmers' demands, who face higher challenges. This research introduces Vulnerable-Smart Agriculture (VSA) to address small-scale farmers' needs and create a sustainable farming framework. The recommended method involves preprocessing, feature selection, and model training. Data cleansing, normalization, and correlation analysis are preprocessing steps. MRMR and CFS are used to select features. The CBGRU architecture trains the model. The CBGRU model outperforms CNN and BiGRU with an average accuracy of 93.60%. High accuracy shows that the VSA strategy meets small-scale farmers' needs through data-driven insights. VSA can cover the CSA gap by including small-scale farmers, according to this research. Strong preprocessing, feature selection, and CBGRU-based model training can boost agricultural production, sustainability, and rural lives.","author":[{"family":"Laxmi","given":"M"},{"family":"Renganathan","given":"K"},{"family":"Sukumar","given":"P"},{"family":"Kaliappan","given":"S"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icmnwc63764.2024.10872060","URL":"https://doi.org/10.1109/icmnwc63764.2024.10872060","source":"crossref"},{"id":"doi:10.55041/ijsrem43767","type":"article-journal","title":"Solar Powered IOT Solution for Smart Farming and Soil Condition","abstract":"The integration of solar power and the Internet of Things (IoT) in agriculture has the potential to revolutionize traditional farming practices by improving efficiency, productivity, and sustainability. This paper presents a solar-powered IoT solution for smart farming, with a primary focus on real-time soil condition monitoring. The system consists of solar-powered IoT sensors deployed in agricultural fields to measure critical soil parameters, including moisture levels, temperature, pH, and nutrient content. These sensors are connected via a low-power wireless network to transmit data to a cloud-based platform. Farmers can access real-time data through a mobile or web application, allowing them to make informed decisions on irrigation, fertilization, and crop management.[3] KEYWORDS- Arduino Uno Micro controller, Solar power, LED display, battery, really, WiFi module,water pump.","author":[{"family":"Kishore","given":"Mr"},{"family":"Karthika","given":"KS"},{"family":"Fasiha","given":"AS"},{"family":"Pravallika","given":"G"},{"family":"Kishore","given":"NV"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55041/ijsrem43767","URL":"https://doi.org/10.55041/ijsrem43767","source":"crossref"},{"id":"doi:10.25124/jnst.v2i2.8749","type":"article-journal","title":"Design And Implementation Of A Cyber Physical System Of A Automated Wheather Station And Agricultural Node In Smart Farming","abstract":"This research focuses on the development of a Cyber-Physical System (CPS) for Smart Farming by integrating an automated weather station with an agricultural node. The automated weather station collects crucial meteorological data, includingtemperature, humidity, rainfall, wind speed, and solar radiation, while the agricultural node monitors soil conditions, nutrient levels, and pest presence. Through seamless wireless communication and cloud-based analytics, the system providesreal-time insights to farmers, enabling informed decision-making regarding irrigation, fertilization, and pest control. Fieldtrials have demonstrated improved crop yield, resource optimization, and reduced environmental impact, showcasing thepotential of this CPS to revolutionize modern agriculture and contribute to sustainable and efficient farming practices. TheAgricultural Node, on the other hand, incorporates various sensors and actuators to monitor and control essential factorssuch as soil moisture, nutrient levels, and pest presence.","author":[{"family":"Komang","given":"Aswin"},{"family":"Priramadhi","given":"Rizki"},{"family":"Darlis","given":"Denny"}],"issued":{"date-parts":[[2025]]},"DOI":"10.25124/jnst.v2i2.8749","URL":"https://doi.org/10.25124/jnst.v2i2.8749","source":"crossref"},{"id":"doi:10.1002/9781394383658.ch1","type":"article-journal","title":"Artificial Intelligence and IoT for Smart Farming","abstract":"Agriculture devotes meaningfully to the economy. Agriculture automation is a large source of concern and is currently being discussed around the globe. The world's population is rapidly increasing, and with it, there is a high demand for food and jobs. The farmers’ conventional techniques were not adequate to meet these targets. Due to this, advanced automated techniques were invented. These new techniques met foodstuff requirements while simultaneously giving work opportunities to a large number of human beings. Agriculture has undergone a transformation as a result of artificial intelligence. This technique has protected crop yields against a diversity of factors like climate change, population growth, labor issues, and food security interests. This chapter's primary goal is to examine the adoption of automation systems in agriculture, such as irrigation, weeding, and spraying, applying sensors and more equipment integrated into robots and drones. These techniques retain water, pesticides, and herbicides while also maintaining soil fertility as well as helping in the powerful usage of the workforce, resulting in expanded output and better quality.","author":[{"family":"Singh","given":"Kshatrapal"},{"family":"Sharma","given":"Yogesh"},{"family":"Shukla","given":"Vijay"},{"family":"Gupta","given":"Dhiraj"},{"family":"Rai","given":"Arun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394383658.ch1","URL":"https://doi.org/10.1002/9781394383658.ch1","source":"crossref"},{"id":"doi:10.33545/2618060x.2025.v8.i11l.4364","type":"article-journal","title":"Adopting climate-smart agronomy practices in vertical farming systems for urban sustainability","abstract":"Climate-smart agronomy practices are critical in addressing the challenges of urban sustainability, especially with the growing global population and the increasing demand for food production in cities. Vertical farming, as an innovative and space-efficient agricultural system, presents a promising solution for urban areas where traditional farming is limited by space, water, and other environmental constraints. This paper explores the adoption of climate-smart agronomy practices in vertical farming systems to enhance urban sustainability. The research investigates the potential of integrating climate-resilient practices, such as efficient water use, renewable energy integration, and optimized crop selection, in vertical farming systems. It also examines the role of technology, such as hydroponics and aeroponics, in enhancing productivity while minimizing the environmental footprint. The results indicate that climate-smart agronomy in vertical farming systems can significantly improve resource efficiency, reduce greenhouse gas emissions, and contribute to food security in urban areas. The paper also highlights the need for policies and institutional frameworks to support the scaling of these practices in urban farming systems. This research underscores the importance of adopting climate-smart agriculture as a cornerstone for sustainable urban development.","author":[{"family":"Santos","given":"Maria"},{"family":"Nguimkeu","given":"Samuel"},{"family":"Petrov","given":"Elena"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/2618060x.2025.v8.i11l.4364","URL":"https://doi.org/10.33545/2618060x.2025.v8.i11l.4364","source":"crossref"},{"id":"doi:10.2174/9798898815462126010004","type":"article-journal","title":"IoT-Driven Soil Analysis and Crop Estimate: Enhancing Precision Agriculture through Progressive Sensor Technologies and Machine Learning","abstract":"The rapid advancement of IoT technologies has opened new avenues for precision agriculture, enabling more effective and maintainable farming practices. This research highlights the transformative budding of IoT-driven soil and crop monitoring in achieving precision farming objectives. This chapter explores methods for detecting soil water content and nutrient levels and proposes an analytical model to recommend appropriate crops based on specific soil conditions. The approach integrates multifunctional soil sensor arrays with advanced spectroscopic sensors to collect realtime data on soil moisture, temperature, pH, and key nutrients such as nitrogen, phosphorus, and potassium. These sensors are connected through a wireless network, transmitting data to a cloud IoT tool for analysis. A predictive model, trained on extensive historical data and validated through pilot tests in various agricultural environments, ensures robust performance across different soil types and conditions. In addition to the challenges faced in data collection and analysis, the research underscores the appropriate machine learning algorithm’s role for accurate crop predictability. The machine learning approaches are tested and provide a comprehensive solution that enhances crop yield and promotes sustainable farming by minimizing water and fertilizer usage. Machine learning approaches were evaluated, with an MLP Classifier achieving a classification accuracy of 98.33% using MinMax scaling and 99.33% with Standard scaling, while a Convolutional Neural Network (CNN) provides a classification accuracy to 98.67%. The proposed method’s scalability and adaptability make it a valuable tool to improve the net productivity of modern agriculture, tackling issues of food security and environmental sustainability. Future developments will focus on integrating AI for advanced analytics and exploring blockchain technology for secure data management, ensuring the reliability of predictive models, and providing farmers with actionable insights for optimizing irrigation, fertilization, and crop selection.","author":[{"family":"Francis","given":"Ambily"},{"family":"Babu","given":"Caren"},{"family":"Johnson","given":"Renoh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898815462126010004","URL":"https://doi.org/10.2174/9798898815462126010004","source":"crossref"},{"id":"doi:10.14719/pst.8325","type":"article-journal","title":"Exploring the factors influencing the adoption of smart farming technologies in agriculture - A bibliometric analysis literature review","abstract":"Smart Farming Technologies (SFTs) play a crucial role in enhancing agricultural productivity, sustainability and resource efficiency. However, a variety of technological, economic, social and policy-related issues influence their adoption. This study uses bibliometric analysis to highlight collaborative efforts in this field, uncover global research trends and investigate the major factors impacting the adoption of SFT. The study uses Visualization of Similarities (VOS) viewer and R studio to perform bibliographic coupling, keyword co-occurrence and citation network analysis using Scopus as the main database. The selection of excellent, peer-reviewed studies is guaranteed via a PRISMA-based methodology. The results show notable differences in adoption rates, with affluent countries making tremendous progress while underdeveloped regions struggle with digital literacy, inadequate infrastructure and budgetary restraints. High upfront expenditures, problems with interoperability, worries about data privacy and farmers' aversion to change are some of the main obstacles. Adoption rates are greatly impacted by social factors, institutional support and governmental regulations, underscoring the necessity of focused interventions. To close the gap between the development of technology and its practical application, the study emphasizes the value of collaborative research, interdisciplinary approaches and policy frameworks. To increase adoption, it is essential to address infrastructure and financial issues, improve farmer training and fortify policy measures. The findings deepen our understanding of the dynamics of smart farming adoption and provide evidence-based suggestions for industry executives, researchers and policymakers. To guarantee extensive SFT implementation and long-term agricultural resilience, future studies should concentrate on localized adoption models, sustainable financing and adaptable regulations.","author":[{"family":"Poorna","given":"Teja"},{"family":"Senthilkumar","given":"M"},{"family":"Manimekalai","given":"R"},{"family":"Saravanan","given":"PA"},{"family":"Vanitha","given":"G"}],"issued":{"date-parts":[[2025]]},"DOI":"10.14719/pst.8325","URL":"https://doi.org/10.14719/pst.8325","source":"crossref"},{"id":"doi:10.48175/ijarsct-29444","type":"article-journal","title":"Smart Poultry Farming with ESP8266: A Comprehensive Review of Monitoring and Automation Approaches","abstract":"Abstract: Poultry farming is a significant component of the agricultural sector, contributing to food security and rural income generation. However, maintaining the health of poultry birds requires constant monitoring of their living conditions, which is challenging with traditional manual methods. These methods are often time-consuming, inconsistent, and prone to human error. This project presents a Smart Poultry Monitoring System based on Arduino microcontroller technology. The system utilizes various sensors, including temperature, humidity, and gas (ammonia) sensors, to monitor the poultry environment in real-time. These sensors are interfaced with an Arduino board, which processes the sensor data and displays it on an LCD screen for easy visibility. Additionally, the system features a buzzer or LED alert mechanism to notify the farmer when any environmental parameter crosses predefined threshold levels. The primary objective of this project is to automate the monitoring process, reduce manual effort, and help maintain a healthy and safe environment for poultry birds. The system is cost-effective, user-friendly, and suitable for small to medium-sized poultry farms, especially in rural areas where advanced solutions like GSM or IoT may not be accessible or affordable. This smart monitoring approach enhances poultry farm management by enabling timely corrective actions, thereby improving bird health, reducing mortality, and increasing overall productivity. Keywords: Health monitoring, Disease alert, Sensors, Temperature and humidity","author":[{"family":"Ghadage","given":"Akash"},{"family":"Gholave","given":"Chandrakant"},{"family":"Devkar","given":"Abhijeet"},{"family":"Naiknavare","given":"MV"}],"issued":{"date-parts":[[2025]]},"DOI":"10.48175/ijarsct-29444","URL":"https://doi.org/10.48175/ijarsct-29444","source":"crossref"},{"id":"doi:10.55041/ijsrem61380","type":"article-journal","title":"Automated Rice Farming: A Sensor-Fused AI–IoT Framework for Smart Water Management","abstract":"Abstract - Water is a key subject to manage in rice agriculture, and especially in Karnataka, where farmers continue to rely on traditional farming methods. Many farmers establish a schedule for watering their rice crop, based on years of farming experience, however, the continual change in weather patterns means that this experience must be taken into consideration along with the changes in weather for the previous year (such as rainfall and temperature increases). The result is that many farmers risk either over-irrigating or under-irrigating their crops. These risks, depending on whether they are too much or too little water, will have negative consequences on their crop yield, the health of the soil, and their overall productivity. This paper describes the use of a smart irrigation system that utilizes IoT sensors and artificial intelligence to assist farmers with their irrigation practices. The smart irrigation system gathers information about the moisture in the soil, temperature, humidity, and water levels in real-time from the farmer's field and uses this information, combined with short term weather predictions from local weather stations, to develop a better understanding of the factors affecting the agricultural industry in that area and how they will continue to be affected. The intelligent irrigation system's goal is not to replace the farmer but to provide the farmer with simple, practical suggestions to help him or her make more informed decisions. The overall objectives of the smart irrigation system are to reduce water usage, decrease the cost of irrigation and improve the efficiency of rice production in light of the changing climate.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsrem61380","URL":"https://doi.org/10.55041/ijsrem61380","source":"crossref"},{"id":"doi:10.1109/iceca66444.2025.11383500","type":"article-journal","title":"Advances in AI for Smart Farming: A Review of Hybrid and Explainable Models for Crop Recommendation and Yield Prediction","abstract":"Smart farming integrates Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) to optimize crop productivity and resource use. By combining soil nutrient (NPK) and pH data with remote-sensing and IoT sensor inputs, modern AI systems generate location-specific recommendations and yield forecasts. This review systematically analyzes recent advances in ML and DL models including Random Forest, Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) architectures applied to crop recommendation and yield prediction. It highlights how hybrid and explainable models improve prediction accuracy and interpretability compared with conventional techniques. The study synthesizes findings from 2016–2025 literature to identify three persistent challenges: data heterogeneity, limited scalability, and lack of model transparency. Emerging approaches such as federated learning, edge computing, and explainable AI are discussed as practical pathways toward interpretable, privacy-preserving smart farming systems. The paper contributes a comparative synthesis of current research trends and outlines design priorities for developing AI frameworks that are not only accurate but also transparent and deployable in real-world agricultural environments.","author":[{"family":"Phull","given":"Labhesh"},{"family":"Kaur","given":"Jasmeet"},{"family":"Nikita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iceca66444.2025.11383500","URL":"https://doi.org/10.1109/iceca66444.2025.11383500","source":"crossref"},{"id":"doi:10.1109/fmec65595.2025.11119362","type":"article-journal","title":"Explainability-Aware Adversarial Threats and Mitigation in Federated Learning Based Anomaly Detection for Cooperative Smart Farming","abstract":"Cooperative Smart Farming (CSF) provides an effective solution to address the evolving needs of smart farming, making precision agriculture more accessible to small-scale farmers. These cooperatives are formal enterprises collectively financed, managed, and operated by member farms, working together for shared benefits. However, CSFs face increased security risks, since a cyberattack on one farm can disrupt the entire network, threatening data integrity and decision-making. Federated Learning (FL) offers a robust solution that enables distributed learning by maintaining a global model across the cloud server and multiple client farms on each edge node, where the global model is trained on the client's model parameter without accessing the client's private data. This paper demonstrates that FL-based network anomaly detection systems in CSF are vulnerable to data poisoning adversarial attacks. We present a novel poisoning attack strategy in which an adversary identifies and exploits the most essential features of the dataset using Explainable AI techniques. Using the Explainability-informed features, the adversary can perform targeted data poisoning attacks using the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks against the trained Convolutional Neural Network (CNN) classifier. Our experimental results indicate that the accuracy of the FL model declines significantly when adversaries poison data by manipulating essential features compared to random perturbations. We also propose a defense mechanism leveraging DistilBERT, a lightweight language model deployed on each local client to mitigate this adversarial attack. Our defense approach effectively filters out poisoned data using cosine similarity, restoring model robustness and accuracy.","author":[{"family":"Praharaj","given":"Lopamudra"},{"family":"Gupta","given":"Maanak"},{"family":"Gupta","given":"Deepti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/fmec65595.2025.11119362","URL":"https://doi.org/10.1109/fmec65595.2025.11119362","source":"crossref"},{"id":"doi:10.1109/aisummit66170.2025.11411202","type":"article-journal","title":"A Hybrid Sensor–Image Framework for Smart Farming Using Deep and Ensemble Learning","abstract":"Smart farming is vital in combating the agricultural challenges that the world faces through the use of sustainable resource management. Unfortunately, most of the current machine learning systems are only capable of handling unimodal data and single-model approaches, which limits their adaptability and scalability. This research introduces a multi-task ensemble-based framework that merges farm image data with IoT sensor streams to improve crop–weed classification and environmental anomaly detection.Visual features are derived from the use of the pre-trained CNNs (ResNet50, VGG16), whereas the sensor data are the parameters like temperature, humidity, CO, LPG, and smoke. The merged feature space is of 4610 dimensions, including statistical descriptors and temporal patterns. Simple models—Logistic Regression, Ridge Classifier, KNN, Random Forest, and Extra Trees—are combined with voting and stacking ensembles, trained with 5-fold stratified cross-validation and normalization-based preprocessing.The innovative method obtains the F1-scores of 0.9667 for multi-class weed–crop classification, 0.9956 for binary crop–weed discrimination, and an accuracy of 0.9889 for anomaly detection, which proves that the ensemble integration of CNN feature vectors and sensor data is a powerful, efficient, and effective approach for precision agriculture.","author":[{"family":"Umamageswaran","given":"J"},{"family":"Ryan","given":"JC"},{"family":"Vasudevan","given":"Shashini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/aisummit66170.2025.11411202","URL":"https://doi.org/10.1109/aisummit66170.2025.11411202","source":"crossref"},{"id":"doi:10.1109/acroset66531.2025.11281312","type":"article-journal","title":"Integrating Explainable AI in Smart Farming for Transparent Crop Recommendation","abstract":"The agricultural industry is experiencing a significant shift with the integration of Artificial Intelligence (AI) and the Internet of Things (IoT), signaling the dawn of a new era in farming. While AI-based systems for crop suggestions and market analysis have shown great potential, their widespread adoption is often limited due to the lack of transparency in many Machine Learning models, which leads to skepticism among farmers and agricultural stakeholders. This study introduces a novel framework that incorporates Explainable AI (XAI) methods into intelligent farming systems. By utilizing historical agricultural data, the system not only delivers reliable crop suggestions and market forecasts but also explains the reasoning behind its outputs in an understandable manner. The approach makes use of models trained on large-scale historical datasets, enhanced with explanation techniques such as LIME, SHAP, and counterfactual analysis to provide real-time, interpretable recommendations. Experimental findings indicate that this system boosts both the precision of its recommendations and the clarity of its decision-making process, ultimately building user trust and encouraging the adoption of precision farming practices.","author":[{"family":"Bairagya","given":"Rishav"},{"family":"Chowdhury","given":"Sagarika"},{"family":"Dey","given":"Priyanka"},{"family":"Das","given":"Arpan"},{"family":"Chatterjee","given":"Tathagata"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/acroset66531.2025.11281312","URL":"https://doi.org/10.1109/acroset66531.2025.11281312","source":"crossref"},{"id":"doi:10.1109/iccrtee64519.2025.11052855","type":"article-journal","title":"Sustainable Farming Through AI and ML: Forecasting Rainfall Patterns for Smart Crop Planning","abstract":"Changes in climate affect rainfall patterns like never before; thus, the accurate prediction of rainfall is necessary for proper agricultural planning so that the farmer may schedule cropping cycles, irrigate, and manage water resources. Machine learning (ML) was implemented in the study to enhance rainfall forecasting and provide environmental consideration for crop recommendation In addition, it would also suggest suitable crops concerning temperature, humidity, soil fertility, and water availability to assist farmers in their decision-making. The research contributes towards some important UNESCO Sustainable Development Goals as follows. SDG 2 (Zero Hunger): Helping farmers make the right crop choices and decisions, in choosing their inputs to yield more from food production. SDG 6 (Clean Water & Sanitation): Improving efficiency in water use through proper irrigation planning. SDG 13 (Climate Action): Having an AI-enabled weather forecast that helps enhance resilience against climate impacts. So, this system using AI plus rainfall prediction through precision agriculture would consider several issues related to crop losses, savings in resource usage, and others that promote sustainable agricultural practices under climate uncertainty.","author":[{"family":"Sk","given":"Hari"},{"family":"Keerthini","given":"Sagili"},{"family":"Tonape","given":"Pavani"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iccrtee64519.2025.11052855","URL":"https://doi.org/10.1109/iccrtee64519.2025.11052855","source":"crossref"},{"id":"doi:10.63824/jtep.v13i2.527","type":"article-journal","title":"INOVASI ELECTRONIC SMART FARMING: SOLUSI TEKNOLOGI TEPAT GUNA DALAM PENGUATAN KETAHANAN PANGAN DI YONIF TERITORIAL PEMBANGUNAN","abstract":"Penelitian ini membahas inovasi Electronic Smart Farming sebagai solusi teknologi tepat guna untuk mendukung penguatan ketahanan pangan di wilayah teritorial Yonif TP. Latar belakang penelitian ini adalah tuntutan modernisasi pertahanan yang memerlukan sistem pertanian presisi, otomatis, dan mandiri energi di lingkungan militer. Tujuan penelitian adalah merancang dan mengintegrasikan lima pilar inovasi elektronika utama, yaitu Solar Powered Smart Aquaculture System, sistem irigasi hidroponik cerdas, teknologi Drone Spraying, Smart Auto-Feeder System, dan sistem Auto Tracking Solar Cell. Metode yang digunakan adalah rekayasa elektronika berbasis mikrokontroler dengan sistem kendali otomatis guna memastikan efisiensi sumber daya yang maksimal. Hasil penelitian menunjukkan bahwa implementasi inovasi ini mampu mentransformasi manajemen lahan menjadi lebih terukur dan efisien. Keunggulan signifikan terlihat pada optimalisasi penyerapan energi surya melalui mekanisme auto tracking yang meningkatkan efisiensi daya, penggunaan drone yang mampu menyelesaikan penyemprotan 1 hektar lahan dalam waktu 10-15 menit, serta penghematan biaya energi hingga 100%. Kesimpulannya, inovasi Electronic Smart Farming ini efektif menjadi solusi teknologi tepat guna bagi Yonif TP dalam mewujudkan kemandirian pangan yang berkelanjutan.","author":[{"family":"Hifni","given":"Muchammad"},{"family":"Putri","given":"Crystal"},{"family":"Cahayaputri","given":"Olivia"}],"issued":{"date-parts":[[2026]]},"DOI":"10.63824/jtep.v13i2.527","URL":"https://doi.org/10.63824/jtep.v13i2.527","source":"crossref"},{"id":"doi:10.53935/jomw.v2024i4.862","type":"article-journal","title":"Smart Farming Revolution: AI-Powered Solutions for Sustainable Growth and Profit","abstract":"The agricultural sector faces numerous challenges, including resource scarcity climate change and economic sustainable concerns. But the opportunities for transforming through artificial intelligence (AI) are immense, enabling optimized resource utilization, higher crop yield, and reduced waste. As the world progresses toward addressing global food security, AI offers a potent answer to bridge the gap between sustainable agriculture and economic viability. The roles of AI driving tools in sustainable farming, and the implications for cost and benefit, are assessed in this study to see how they may ultimately help to more efficiently invest in smallholder and large scale farming. It analyzed AI applications such as accuracy agriculture, predictive analytics and automated decision making systems to show how AI can revolutionize agriculture. They found that AI tools also increase the efficiency with which resources are put to use, reduce environmental impact and enable farming to be profitable, which are all forces for sustainable agriculture in the years ahead. Furthermore, the use of AI solutions encourages innovation in farming processes, opening up possibilities for a better and greener agricultural future.","author":[{"family":"Hossain","given":"Md"},{"family":"Ferdousmou","given":"Jannatul"},{"family":"Khatoon","given":"Rabeya"},{"family":"Saha","given":"Sanchita"},{"family":"Hassan","given":"Mahafuj"},{"family":"Akter","given":"Jahanara"},{"family":"Debnath","given":"Anupom"}],"issued":{"date-parts":[[2025]]},"DOI":"10.53935/jomw.v2024i4.862","URL":"https://doi.org/10.53935/jomw.v2024i4.862","source":"crossref"},{"id":"doi:10.1109/bigdata62323.2024.10825128","type":"article-journal","title":"A Lightweight Edge-CNN-Transformer Model for Detecting Coordinated Cyber and Digital Twin Attacks in Cooperative Smart Farming","abstract":"The agriculture sector is increasingly adopting innovative technologies to meet the growing food demands of the global population. To optimize resource utilization and minimize crop losses, farmers are joining cooperatives to share their data and resources among member farms. However, while farmers benefit from this data sharing and interconnection, it exposes them to cybersecurity threats and privacy concerns. A cyberattack on one farm can have widespread consequences, affecting the targeted farm as well as all member farms within a cooperative. For instance, a de-authentication attack prevents sensors from connecting to the network, obstructing the farming application from receiving real-time data. This disruption obstructs decision-making for all member farms that rely on this data from an attacked farm. Further, farmers have adopted digital twin (DT) technology that facilitates a virtual farm replica that encompasses vital aspects of farming, such as crop cultivation, soil composition and weather conditions. However, it’s critical to acknowledge that attackers can target these digital twins (DTs), potentially disrupting real physical farm operations.In this research, we address existing gaps by proposing a novel and secure architecture for Cooperative Smart Farming (CSF). First, we highlight the role of edge-based DTs in enhancing the efficiency and resilience of agricultural operations. To validate this, we develop a test environment for CSF, implementing various cyberattacks on both the DTs and their physical counterparts using different attack vectors. We collect two smart farming network datasets to identify potential threats. After identifying these threats, we focus on preventing the transmission of malicious data from compromised farms to the central cloud server. To achieve this, we propose a CNN-Transformer-based network anomaly detection model, specifically designed for deployment at the edge. As a proof of concept, we implement this model and evaluate its performance by varying the number of encoder layers. Additionally, we apply Post-Quantization to compress the model and demonstrate the impact of compression on its performance in edge environments. Finally, we compare the model’s performance with traditional machine learning approaches to assess its overall effectiveness.","author":[{"family":"Praharaj","given":"Lopamudra"},{"family":"Gupta","given":"Deepti"},{"family":"Gupta","given":"Maanak"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/bigdata62323.2024.10825128","URL":"https://doi.org/10.1109/bigdata62323.2024.10825128","source":"crossref"},{"id":"doi:10.47001/cjesr/2024.101001","type":"article-journal","title":"Smart Cattle Health Monitoring and Farming Productivity Management Using IOT and CNN","abstract":"The agricultural industry plays a pivotal role in supporting global food security and sustaining economies. Within this industry, cattle farming represent a significant sector, providing essential resources like meat, milk, and other dairy products. However, traditional cattle farming practices often face challenges related to monitoring, managing, and predicting various aspects of cattle health and productivity. In recent years, the advent of technology has opened up new possibilities for transforming traditional farming practices into more efficient, data-driven systems. The integration of smart devices, IoT sensors, machine learning algorithms, and real-time data analytics has paved the way for innovative solutions that can address the limitations of conventional cattle farming. The integrated embedded system proposed in this paper aims to revolutionize cattle farming practices by providing a comprehensive solution to enhance cattle well-being and optimize farming efficiency. It encompasses four crucial areas: real-time monitoring and health management, milk production prediction, artificial insemination scheduling, and disease analysis with first aid recommendations. By utilizing cutting-edge IoT, sensors, machine learning algorithms, and image recognition techniques the system enables farmers to monitor cattle health in real-time, predict milk production accurately, schedule artificial insemination effectively, and promptly identify and manage cattle skin diseases. Overall, the system has archived 91% high accuracy through these advancements, also empowers farmers to make data-driven decisions, ensuring proactive measures to prevent health issues, enhance productivity, and fosters a sustainable and profitable agriculture industry.","author":[{"family":"Abdulmumin","given":"Abdulsalam"},{"family":"Omoniyi","given":"Adekunle"},{"family":"Olorunfemi","given":"Samuel"},{"family":"Olawale","given":"Rashidat"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47001/cjesr/2024.101001","URL":"https://doi.org/10.47001/cjesr/2024.101001","source":"crossref"},{"id":"doi:10.48175/ijarsct-29493","type":"article-journal","title":"Smart Poultry Farming with ESP8266: A Comprehensive Review of Monitoring and Automation Approaches","abstract":"Abstract: Poultry farming is a significant component of the agricultural sector, contributing to food security and rural income generation. However, maintaining the health of poultry birds requires constant monitoring of their living conditions, which is challenging with traditional manual methods. These methods are often time-consuming, inconsistent, and prone to human error. This project presents a Smart Poultry Monitoring System based on Arduino microcontroller technology. The system utilizes various sensors, including temperature, humidity, and gas (ammonia) sensors, to monitor the poultry environment in real-time. These sensors are interfaced with an Arduino board, which processes the sensor data and displays it on an LCD screen for easy visibility. Additionally, the system features a buzzer or LED alert mechanism to notify the farmer when any environmental parameter crosses predefined threshold levels. The primary objective of this project is to automate the monitoring process, reduce manual effort, and help maintain a healthy and safe environment for poultry birds. The system is cost-effective, user-friendly, and suitable for small to medium-sized poultry farms, especially in rural areas where advanced solutions like GSM or IoT may not be accessible or affordable. This smart monitoring approach enhances poultry farm management by enabling timely corrective actions, thereby improving bird health, reducing mortality, and increasing overall productivity.","author":[{"family":"Ghadage","given":"Akash"},{"family":"Gholave","given":"Chandrakant"},{"family":"Devkar","given":"Abhijeet"},{"family":"Naiknavare","given":"MV"}],"issued":{"date-parts":[[2025]]},"DOI":"10.48175/ijarsct-29493","URL":"https://doi.org/10.48175/ijarsct-29493","source":"crossref"},{"id":"doi:10.33545/26164485.2025.v9.i1.n.2079","type":"article-journal","title":"Homoeopathic remedies in enhancing plant growth in climate-smart urban farming systems","abstract":"Climate-smart urban farming systems demand innovative, low-input, and environmentally responsible strategies to enhance crop growth and productivity. In this context, homoeopathic remedies have emerged as a novel bio-stimulant category with the potential to regulate plant physiological responses at ultra-low dilutions. Despite their widespread use in alternative medicine, their scientific application in agriculture remains underexplored, particularly in controlled urban farming environments such as hydroponics, rooftop gardens, and vertical farming structures. This research evaluates the practical capacity of homoeopathic formulations to improve plant Vigor, stress tolerance, and nutrient uptake efficiency within climate-smart frameworks. Previous experimental evidence suggests that ultra-dilute preparations may influence enzymatic activities, seed germination rates, hormonal balance, and root-shoot biomass partitioning under abiotic stress conditions such as salinity, drought, and temperature fluctuations, all of which are common challenges for urban growers. Integrating these remedies may complement resource-efficient technologies, reducing dependence on synthetic fertilizers and supporting circular bioeconomy principles. The objectives of this research include examining physiological and biochemical changes induced by homoeopathic remedies, determining their agronomic performance in nutrient-restricted urban environments, and assessing their role in enhancing resilience against climate-related stressors. The working hypothesis posits that specific homoeopathic dilutions can induce beneficial plant responses, thereby improving growth indices without introducing chemical residues or ecological risks. The research employs controlled experiments in hydroponic and soil-less substrates to monitor growth parameters, nutrient assimilation, chlorophyll stability, water-use efficiency, and yield attributes. Findings from this work are expected to contribute to sustainable agricultural innovations by offering a cost-effective, eco-friendly, and scalable plant growth enhancement strategy compatible with emerging urban farming systems.","author":[{"family":"Vos","given":"Helena"},{"family":"Wilde","given":"Marijn"},{"family":"Vermeer","given":"Saskia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/26164485.2025.v9.i1.n.2079","URL":"https://doi.org/10.33545/26164485.2025.v9.i1.n.2079","source":"crossref"},{"id":"doi:10.1109/esic68176.2026.11495636","type":"article-journal","title":"Smart Farming Using Deep Learning: Detection of Soybean Leaf Disease from UAV-Captured Images","abstract":"Early detection of soybean leaf disease is crucial to preventing yield loss and ensuring sustainable soybean crop production. Traditional farming is often inefficient and heavily dependent on manual labor, leading to lower productivity and inconsistent yields. This study performs a comparative analysis of several state-of-the-art (SOTA) Convolutional Neural Network (CNN) architectures to find the best model for accurately classifying different soybean leaf diseases from remotely sensed images captured by Unmanned Aerial Vehicles (UAVs). The experimental analysis has been conducted in two phases. In the first phase, the original dataset has been used to train five most trending SOTA pretrained CNN architectures, including VGG16, VGG19, ResNet50, InceptionV3, and Xception. In the second phase, the dataset has been enriched using four augmentation techniques, namely random horizontal flipping, rotation, Gaussian blurring, and brightness-contrast adjustments, to increase diversity and enable the models to achieve more generalized performance. Experimental results reveal that, on the original dataset, VGG19 outperforms other models, achieving highest classification accuracy of 98.59 %. This strong performance of VGG19 can be attributed to its simple and uniform architecture, which enables effective feature extraction. On the augmented dataset, ResNet50 outperforms with classification accuracy of 99.15 %, benefiting from its residual block design. These findings demonstrate the effectiveness of deep learning (DL) for reliable and automated detection of soybean leaf diseases from remotely sensed UAV images.","author":[{"family":"Nath","given":"Swarnali"},{"family":"Biswas","given":"Saroj"},{"family":"Majumdar","given":"Sounak"},{"family":"Kumar","given":"Kunal"},{"family":"Acharjee","given":"Tapodhir"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/esic68176.2026.11495636","URL":"https://doi.org/10.1109/esic68176.2026.11495636","source":"crossref"},{"id":"doi:10.1109/csnt64827.2025.10969029","type":"article-journal","title":"Lora-Enabled System for Smart Farming Management and Oversight, Utilizing Wireless Sensor Networks","abstract":"The purpose of this study is to create a LoRa-based smart farming management and surveillance system. Utilizing Wireless Sensor Networks (WSNs) in rural settings, with the aim of replacing the existing technology in agricultural monitoring systems. A dedicated private network server is established and connected to a gateway, which gathers information or signals from the nodes at the end and sends this data to the cloud without the need for routers. This data can then be utilized for various applications by the end users. The system overcomes issues related to communication failures and energy-efficient data transmission. This advanced farming platform enhances the effectiveness of farming methods. The proposed methodology is the application of resources including as water, fertilizers, and pesticides should be optimized in order to achieve maximum efficiency while simultaneously minimizing waste. Farming productivity and sustainability are both significantly improved because of its contribution, notably in terms of the efficient management of resources. And intelligent cities used to improve agriculture—comparing the planned weather station and the numerous developed patents. The technique here is like a cutting-edge, reasonably priced choice for local weather monitoring.","author":[{"family":"Elumalai","given":"J"},{"family":"Kumuthapriya","given":"K"},{"family":"Hema","given":"R"},{"family":"Sundaram","given":"PSS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/csnt64827.2025.10969029","URL":"https://doi.org/10.1109/csnt64827.2025.10969029","source":"crossref"},{"id":"doi:10.4018/979-8-3373-0020-7.ch003","type":"article-journal","title":"Enhancing IoT-Based Smart Irrigation Efficiency Through Optimized Sensor Placement, Noise Elimination, and Incremental Learning","abstract":"Modern agriculture faces challenges requiring innovative solutions to balance productivity with sustainability. Optimizing irrigation is critical, as traditional systems lead to water waste and inefficiencies, necessitating smart technologies. Key advancements include Dual Electromagnetic (DUAL-EM) scanning for soil conductivity mapping, optimizing sensor placement, reducing costs, and ensuring data quality. Noise reduction techniques like Isolation Forest and LOF enhance data reliability, achieving 81.02% accuracy and 0.328 MAE. Incremental learning models such as LightGBM and XGBoost dynamically refine irrigation schedules, optimizing water application under changing conditions. IoT integration with soil sensors, weather stations, and automated valves ensures precise irrigation. These strategies conserve water, reduce costs, and align with environmental goals, transforming farming practices and advancing sustainable agriculture.","author":[{"family":"Chandrappa","given":"Varun"},{"family":"Islam","given":"Nahina"},{"family":"Ashwath","given":"Nanjappa"},{"family":"Shrestha","given":"Pramod"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-0020-7.ch003","URL":"https://doi.org/10.4018/979-8-3373-0020-7.ch003","source":"crossref"},{"id":"doi:10.6084/m9.figshare.26405053","type":"article-journal","title":"Eco-Friendly Intensification and Climate-Resilient Agricultural Systems (EFICAS) for Promoting Sustainable Natural Resources Management in Lao PDR","abstract":"The Lao government has implemented various policies focused on the agricultural sector, particularly commercial crop production, as an effort to overcome economic weakening. Those policies have also been designed to reduce malnutrition and poverty. The current fast growth and expansion of commercial crop production have proven to trigger poverty alleviation in Laos. However, this condition led to the to the attenuation of farming communities, which accounted for 75% of the total population in Laos, raising the indebtedness number of farmer families, increasing the vulnerability of the communities, and sharpening disparities among producers. Recently, besides the increase in climate change influence, agricultural practices in Laos have also faced several economic risks. These economic risks include the intermittent nature of local market monopolies, fluctuation, and price games along the agricultural value chains, and instability of production contract implementation. Since 2014, the Lao government has evaluated the consequences of these agricultural practices based on the exploitation of natural resources and the environment. The Eco-Friendly Intensification and Climate-Resilient Agricultural Systems (EFICAS) project was funded and managed by Centre de Cooperation International en Recherche Agronomique pour le Développement (France International Cooperation Center for Agronomy Research Development, CIRAD) and the European Union Global Climate Change Alliance (EU-GCCA) during 2014-2018. CIRAD partnered with (Department of Agricultural Land Management, DALAM) under Laos Ministry of Agriculture and Forestry (MAF) performed EFICAS together. This project aimed to improve Northern upland community livelihoods, strengthening food security, resilience to climate change, introducing innovative methods, and new intervention approaches to support farmers’ adoption of climate-smart systems based on sustainable agriculture.","author":[{"family":"Prabakusuma","given":"Adhita"}],"issued":{"date-parts":[[2024]]},"DOI":"10.6084/m9.figshare.26405053","URL":"https://doi.org/10.6084/m9.figshare.26405053","source":"datacite"},{"id":"doi:10.5281/zenodo.19279131","type":"article-journal","title":"AgriSmart: AI-Based Smart Farming & Marketplace System","abstract":"Agriculture is a vital sector for economic development, yet it faces challenges such as low productivity, lack of market access, and dependency on intermediaries. To overcome these issues, AgriSmart: AI-Driven Smart Farming and Digital Marketplace System is proposed as an integrated digital solution that utilizes Artificial Intelligence and web technologies. The system combines key features including a digital marketplace, AI-based crop disease detection, chatbot assistance, and a data analytics dashboard. The marketplace allows farmers to directly connect with customers, eliminating middlemen and ensuring fair pricing. The AI-based crop scanner helps in early detection of plant diseases and provides suitable recommendations for treatment. Additionally, the chatbot (AgriBot) offers real-time guidance related to farming practices, weather conditions, and market trends, while the community platform enables knowledge sharing among farmers. The dashboard provides insights into sales and performance, supporting better decision-making. Overall, AgriSmart improves agricultural efficiency, communication, and productivity. It offers a cost-effective, user-friendly, and scalable solution, bridging the gap between traditional farming and modern digital technologies.","author":[{"family":"Vr","given":"Prof"},{"family":"Bandgar","given":"Swapnil"},{"family":"Wadkar","given":"Abhinav"},{"family":"Mangire","given":"Shivrudra"},{"family":"Dhumal","given":"Om"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19279131","URL":"https://doi.org/10.5281/zenodo.19279131","source":"datacite"},{"id":"doi:10.5281/zenodo.19279132","type":"article-journal","title":"AgriSmart: AI-Based Smart Farming & Marketplace System","abstract":"Agriculture is a vital sector for economic development, yet it faces challenges such as low productivity, lack of market access, and dependency on intermediaries. To overcome these issues, AgriSmart: AI-Driven Smart Farming and Digital Marketplace System is proposed as an integrated digital solution that utilizes Artificial Intelligence and web technologies. The system combines key features including a digital marketplace, AI-based crop disease detection, chatbot assistance, and a data analytics dashboard. The marketplace allows farmers to directly connect with customers, eliminating middlemen and ensuring fair pricing. The AI-based crop scanner helps in early detection of plant diseases and provides suitable recommendations for treatment. Additionally, the chatbot (AgriBot) offers real-time guidance related to farming practices, weather conditions, and market trends, while the community platform enables knowledge sharing among farmers. The dashboard provides insights into sales and performance, supporting better decision-making. Overall, AgriSmart improves agricultural efficiency, communication, and productivity. It offers a cost-effective, user-friendly, and scalable solution, bridging the gap between traditional farming and modern digital technologies.","author":[{"family":"Vr","given":"Prof"},{"family":"Bandgar","given":"Swapnil"},{"family":"Wadkar","given":"Abhinav"},{"family":"Mangire","given":"Shivrudra"},{"family":"Dhumal","given":"Om"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19279132","URL":"https://doi.org/10.5281/zenodo.19279132","source":"datacite"},{"id":"doi:10.5281/zenodo.19217795","type":"article-journal","title":"A Comprehensive Survey On IoT And AI-Based Smart Agriculture Systems","abstract":"Smart agriculture has emerged as a key solution to address critical challenges in traditional farming, including inefficient irrigation, excessive resource usage, delayed disease detection, and limited accessibility to modern technologies, especially in rural areas. The integration of the Internet of Things (IoT) and Artificial Intelligence (AI) has enabled data- driven decision-making, real-time monitoring, and automation in agricultural practices. This survey presents a comprehensive review of IoT- and AI-based smart agriculture systems reported in recent literature. Various system architectures, sensing technologies, communication methods, and AI techniques used for irrigation control, crop health monitoring, disease detection, and yield prediction are analyzed and compared. The survey also examines connectivity models, including internet- dependent and offline solutions, power management approaches such as solar-based systems, and user-access mechanisms like mobile applications, SMS alerts, and voice interfaces. Key challenges related to cost, scalability, data reliability, and rural deployment are discussed. Finally, the paper identifies existing research gaps and outlines future directions for developing affordable, scalable, and intelligent smart farming solutions, providing design insights for next- generation agricultural monitoring systems.","author":[{"family":"Khandbahale","given":"Chaitanya"},{"family":"Shaikh","given":"Mohammad"},{"family":"Raut","given":"Arnav"},{"family":"Sonar","given":"Darshan"},{"family":"Pawar","given":"Professor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19217795","URL":"https://doi.org/10.5281/zenodo.19217795","source":"datacite"},{"id":"doi:10.5281/zenodo.19217794","type":"article-journal","title":"A Comprehensive Survey On IoT And AI-Based Smart Agriculture Systems","abstract":"Smart agriculture has emerged as a key solution to address critical challenges in traditional farming, including inefficient irrigation, excessive resource usage, delayed disease detection, and limited accessibility to modern technologies, especially in rural areas. The integration of the Internet of Things (IoT) and Artificial Intelligence (AI) has enabled data- driven decision-making, real-time monitoring, and automation in agricultural practices. This survey presents a comprehensive review of IoT- and AI-based smart agriculture systems reported in recent literature. Various system architectures, sensing technologies, communication methods, and AI techniques used for irrigation control, crop health monitoring, disease detection, and yield prediction are analyzed and compared. The survey also examines connectivity models, including internet- dependent and offline solutions, power management approaches such as solar-based systems, and user-access mechanisms like mobile applications, SMS alerts, and voice interfaces. Key challenges related to cost, scalability, data reliability, and rural deployment are discussed. Finally, the paper identifies existing research gaps and outlines future directions for developing affordable, scalable, and intelligent smart farming solutions, providing design insights for next- generation agricultural monitoring systems.","author":[{"family":"Khandbahale","given":"Chaitanya"},{"family":"Shaikh","given":"Mohammad"},{"family":"Raut","given":"Arnav"},{"family":"Sonar","given":"Darshan"},{"family":"Pawar","given":"Professor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19217794","URL":"https://doi.org/10.5281/zenodo.19217794","source":"datacite"},{"id":"doi:10.5281/zenodo.19203790","type":"article-journal","title":"Creating virtual AI models of digital twins on farms to simulate and predict performance under different climatic conditions.","abstract":"The agricultural sector is undergoing a transformative phase driven by the increasing integration of advanced digital technologies. Digital twin technology has emerged as a cutting-edge innovation capable of revolutionizing precision farming practices by enabling real-time farm simulation and dynamic decision support. Smart farming has introduced agricultural systems that are increasingly autonomous and highly interconnected. A digital twin is a virtual representation of a physical farm system that continuously updates through data streams derived from sensors, machinery, and environmental inputs. This technology facilitates advanced modeling, predictive analytics, and real time optimization of agricultural operations. Digital twin modeling is essential for accurately representing the physical entity, and it provides functional services and meets the requirements of modern farms. This study provides a detailed analysis of the key aspects of ADTs, providing deeper insights into the potential application areas in agriculture, and discusses major implementation challenges. This study explores applications of ADT in controlled environment agriculture, soil and irrigation management, crop monitoring and cultivation support, post-harvest activities, livestock monitoring and management, and agricultural machinery. It provides intelligent, adaptive, and dynamic facility management and farming decision-making suggestions. The contribution of the project is to develop an ecosystem of digital twins that collectively capture the behavior of a greenhouse facility.","author":[{"family":"Kumar","given":"Ashok"},{"family":"Kumar","given":"Arvind"},{"family":"Singh","given":"SR"},{"family":"Yadav","given":"MC"},{"family":"Yadav","given":"Vijay"},{"family":"Bhargava","given":"Govind"},{"family":"Pandaya","given":"Mohit"},{"family":"Yadav","given":"Anupam"},{"family":"Khakre","given":"Alkesh"},{"family":"Jain","given":"Tanisha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19203790","URL":"https://doi.org/10.5281/zenodo.19203790","source":"datacite"},{"id":"doi:10.5281/zenodo.19203791","type":"article-journal","title":"Creating virtual AI models of digital twins on farms to simulate and predict performance under different climatic conditions.","abstract":"The agricultural sector is undergoing a transformative phase driven by the increasing integration of advanced digital technologies. Digital twin technology has emerged as a cutting-edge innovation capable of revolutionizing precision farming practices by enabling real-time farm simulation and dynamic decision support. Smart farming has introduced agricultural systems that are increasingly autonomous and highly interconnected. A digital twin is a virtual representation of a physical farm system that continuously updates through data streams derived from sensors, machinery, and environmental inputs. This technology facilitates advanced modeling, predictive analytics, and real time optimization of agricultural operations. Digital twin modeling is essential for accurately representing the physical entity, and it provides functional services and meets the requirements of modern farms. This study provides a detailed analysis of the key aspects of ADTs, providing deeper insights into the potential application areas in agriculture, and discusses major implementation challenges. This study explores applications of ADT in controlled environment agriculture, soil and irrigation management, crop monitoring and cultivation support, post-harvest activities, livestock monitoring and management, and agricultural machinery. It provides intelligent, adaptive, and dynamic facility management and farming decision-making suggestions. The contribution of the project is to develop an ecosystem of digital twins that collectively capture the behavior of a greenhouse facility.","author":[{"family":"Kumar","given":"Ashok"},{"family":"Kumar","given":"Arvind"},{"family":"Singh","given":"SR"},{"family":"Yadav","given":"MC"},{"family":"Yadav","given":"Vijay"},{"family":"Bhargava","given":"Govind"},{"family":"Pandaya","given":"Mohit"},{"family":"Yadav","given":"Anupam"},{"family":"Khakre","given":"Alkesh"},{"family":"Jain","given":"Tanisha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19203791","URL":"https://doi.org/10.5281/zenodo.19203791","source":"datacite"},{"id":"doi:10.14279/depositonce-21556","type":"article-journal","title":"4th International Conference: Valorization of Agricultural Residues","abstract":"Globally, food and agriculture production consume approximately 30% of the world's energy and produce around 30% of global greenhouse gas (GHG) emissions . This highlights the urgent need to transition towards Climate-Smart Agriculture (CSA), particularly in rapidly developing regions like Southeast Asia, to address the global climate challenge while meeting increasing food demand. Vietnam's agricultural sector has been an important factor contributing tothe country's economic growth, with GDP expanding by over 6% in 2022 . Agriculture, forestry and fishing created 11.88% of Vietnam's GDP in 2022 . To support sustainable agricultural development and GHG emissions reduction, Vietnam has set targets to cut the total GHG emissions from agrcultural productions to 53.57 MtCO2eq by 2025 and achieve a further reduction of 121.9 Mt CO2eq by 2030 . Agricultural production inherently generates residual biomass from crop cultivation, livestock farming, and food processing. Valorization of these agricultural residues presents a promising approach of reducing emissions and improving resource efficiency. However, challenges persist in technology development, logistics, and economic feasibility the current regulatory framework. Rice is a crucial contributor to Vietnam's agricultural GDP, with it’s production reaching 43.9 million tons in 20225. However, this also generates substantial rice straw waste, estimated at around 49 million tons annually. The majority of this straw is still burned in fields, causing significant air pollution across the region. Additionally, incorporating rice straw into flooded paddy soils contributes to methane emissions. Livestock farming has grown rapidly in Vietnam, with the total number of cattle and pigs reaching approximately 95 million in 2022 . This sector's expansion, while economically beneficial, has led to increased environmental concerns. Small-scale household biogas digesters are widely used for manure treatment, with over 500,000 plants installed nationwide. However, these systems face challenges such as limited utilization of biogas, excess biogas release and methane leakage, with losses up to 40% reported , . Larger biogas plants also require technological improvements across their entire process chain, from substrate preparation to biogas conditioning and residue management. The intensive use of fertilizers in rice cultivation and improper manure disposal from livestock farming contribute significantly to water and soil pollution, nutrient loss, and greenhouse gas emissions. In the context of Vietnam's energy and climate policies, the government has set targets to increase bio-energy capacity to 1,000 MW by 2025 and 3,000 MW by 2030. Vietnam has also committed to reducing GHG emissions by 9% by 2030 compared to the business-as-usual scenario, or up to 27% with international support. CSA is increasingly recognized as a vital strategy for addressing the challenges of climate change in Southeast Asia, particularly in Vietnam. Across Southeast Asia, CSA initiatives are focusing on improving productivity, enhancing resilience, and reducing greenhouse gas emissions in key agricultural sectors. The adoption of CSA practices in the region is supported by international organizations and local governments, with efforts to scale up successful approaches through participatory, farmer-centered tools and methods. However, barriers such as financial constraints, limited access to information, and the need for tailored solutions remain significant challenges for scaling up CSA practices across the region. In order to address these challenges effectively, solutions must be adapted to local conditions, considering specific geographical, climatic, cultural, and social factors. This holistic approach should go beyond technical and administrative measures to enhance science, research, and education in sustainable agricultural practices. Collaborative efforts involving local communities, government agencies, and intern","author":[{"family":"Unknown"}],"issued":{"date-parts":[[2024]]},"DOI":"10.14279/depositonce-21556","URL":"https://doi.org/10.14279/depositonce-21556","source":"datacite"},{"id":"doi:10.59256/ijire.20260702030","type":"article-journal","title":"Transforming agriculture with edge AI – enabling the Smart Farming","abstract":"This project focuses on building an intelligent plant disease classification system using the Plant Village dataset from Kaggle, specifically targeting three tomato leaf categories: healthy, late blight, and bacterial spot. The dataset was cleaned, resized, and augmented, then split into an 80:20 ratio for training and validation. Model development and training were carried out in Amazon SageMaker Studio, leveraging its scalable compute environment and integrated experiment tracking. After achieving satisfactory accuracy, the trained TensorFlow model was exported and deployed directly within SageMaker using a managed inference endpoint. For accessibility, a lightweight Gradio-based user interface is being built to allow users to upload leaf images and receive instant predictions through the deployed model. The final solution demonstrates a complete machine-learning workflow—from dataset preparation to cloud deployment and user interaction—providing a practical tool for early crop disease detection and supporting precision agriculture.","author":[{"family":"Katha","given":"Amulya"},{"family":"Naga","given":"Rohitha"},{"family":"Naman","given":"Pratap"}],"issued":{"date-parts":[[2026]]},"DOI":"10.59256/ijire.20260702030","URL":"https://doi.org/10.59256/ijire.20260702030","source":"crossref"},{"id":"doi:10.4018/979-8-3373-9295-0.ch013","type":"article-journal","title":"Security, Privacy, and Trust for Smart Agriculture Systems","abstract":"Smart agriculture integrates IoT, AI, and data analytics for precision farming, but digitalization expands cyberattack surfaces. Threats range from unauthorized access to AI manipulation, risking financial loss and food security. This chapter examines smart agriculture's security, privacy, and trust landscape. It establishes a technology stack taxonomy and identifies layer-specific vulnerabilities. It reviews lightweight cryptography for resource-constrained devices, blockchain for supply chain integrity, and federated learning for privacy-preserving intrusion detection across agricultural networks.","author":[{"family":"Anwar","given":"Raja"},{"family":"Pastore","given":"Flavio"},{"family":"Ali","given":"Saqib"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-9295-0.ch013","URL":"https://doi.org/10.4018/979-8-3373-9295-0.ch013","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101208","type":"article-journal","title":"Computer vision in precision livestock farming: benchmarking YOLOv9, YOLOv10, YOLOv11, and YOLOv12 for individual cattle identification","abstract":"Individual animal identification is fundamental to effective livestock traceability and precision management. This study evaluates the performance of four recent object detection models (YOLOv9m, YOLOv10m, YOLOv11m, and YOLOv12m) for automated cattle identification using a numerical labelling approach in real barn environments. A custom dataset comprising 91,694 annotated frames was collected from a multi-camera surveillance system deployed in a barn area housing dairy cows. The cameras were strategically positioned to provide overlapping coverage and to capture animals under varied barn lighting conditions and crowded environments. Each model was trained and assessed using standard performance metrics, including mean average precision (mAP) at Intersection over Union (IoU) thresholds of 0.50 and 0.50–0.95, as well as precision, recall, inference speed, and model size. Among the models evaluated, YOLOv12m achieved the highest detection accuracy (mAP50 = 0.947; mAP50–95 = 0.911), indicating strong capability in distinguishing individual cattle based on numerical markings even under complex environments. YOLOv11m offered a competitive balance between detection accuracy and computational efficiency, making it suitable for real-time applications. The study also compared model performance with findings from earlier YOLO-based approaches and highlighted significant improvements in robustness and deployment readiness offered by newer versions. These results demonstrate that recent YOLO models are well-suited for individual cattle identification in practical farm environments. The findings provide useful guidance for selecting models based on operational requirements such as accuracy, processing speed, and device constraints, contributing to the advancement of computer vision applications in precision livestock farming.","author":[{"family":"Bumbálek","given":"Roman"},{"family":"Ufitikirezi","given":"Jean"},{"family":"Umurungi","given":"Sandra"},{"family":"Zoubek","given":"Tomáš"},{"family":"Kuneš","given":"Radim"},{"family":"Stehlík","given":"Radim"},{"family":"Bartoš","given":"Petr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101208","URL":"https://doi.org/10.1016/j.atech.2025.101208","source":"crossref"},{"id":"doi:10.55544/sjmars.icmri.8","type":"article-journal","title":"IoT-Based Smart Farming: A Plant Monitoring System for Precision Agriculture","abstract":"Precision agriculture, leveraging data-driven insights, is crucial for optimizing crop yield and resource utilization. This paper presents an IoT-based smart farming system designed for real-time plant monitoring. The system incorporates various sensors to measure soil moisture, temperature, humidity, and light intensity, integrated with microcontrollers and cloud-based platforms. Key features include automated irrigation, remote monitoring via mobile applications, and predictive analytics for disease detection. The research contributes to enhancing agricultural efficiency through IoT-enabled precision farming, demonstrating significant improvements in resource management and crop productivity. Experimental results showcase the system’s accuracy and reliability in real-world farming environments.","author":[{"family":"Singh","given":"Rashika"},{"family":"Raghav","given":"Prashant"},{"family":"Saini","given":"Nisha"},{"family":"Neha"},{"family":"Srivastava","given":"Saurabh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55544/sjmars.icmri.8","URL":"https://doi.org/10.55544/sjmars.icmri.8","source":"crossref"},{"id":"doi:10.33411/ijist/20246416211634","type":"article-journal","title":"IoT in Developing the Smart Farming and Agricultural Technologies","abstract":"Background:The Internet of Things(IoT)is streamlining processes in food and agriculture, especially in developing countries with agriculture-based economies. These countries stand to gain a lot from the IoT innovations that bring about mechanisms to track and control the risks experienced dueto factors such as low productivity, wastage of resourcesandfood scarcity.Objectives:This research aimsto demonstrate how different IoT solutions can be effective in food and agriculture technology in less developed countries. It focuses on the potential of IoT solutions to improve productivity, reduce wastage of resourcesandencourage sustainable agro practices. Furthermore, the paper examines the reasons behind the slow adoption of IoT technologiesandstrategies to surmount such factors are proposed.Methodology:The study employed both literature and analytical as well; however, a majority of it was on the primary data concerning IoT solutions that were smart irrigation and precision agriculture. Data was collected from farmersandtechnology neglected mostly the politicians of developing countries whose focus was to understand or rather assess the uptake, challengesandimpacts of IoT technology.Results:The results show that IoT can cause a drastic enhancement of agricultural productivity throughefficient water irrigation, keeping a check on soil health and lowering post-harvest waste. MFIs IoT made the adoption of the system and use of resources more efficient, increasedprofits and loweredexpenses. However, they also revealed obstacles tothe process such as the cost of implementation, expertise in both technical and operational levels and internet services.Conclusion: Smart agriculture and agricultural systems everywhere will undergo a revolution owing to IoT technologies because theyenhancepractices and innovations. However, potential benefits cannot, be maximized Secure fencing of these barriers will not be straightforward since a significant amount of time will have to be devoted to understanding each of the suggestions made by the officers present.","author":[{"family":"Ul-Islam","given":"Ammad"},{"family":"Nazir","given":"Tanveer"},{"family":"Ali","given":"Irfan"},{"family":"Rafiq","given":"Sania"},{"family":"Ahsan","given":"Muhammad"},{"family":"Siddiq","given":"Imran"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33411/ijist/20246416211634","URL":"https://doi.org/10.33411/ijist/20246416211634","source":"crossref"},{"id":"doi:10.33068/iccd.v7i1.898","type":"article-journal","title":"TECHNOLOGY-BASED COMMUNITY EMPOWERMENT: SMART FARMING, AQUAPONICS, AND DTF APPLICATIONS IN KERANGGAN ECOTOURISM","abstract":"Keranggan Ecotourism in South Tangerang holds significant potential for developing nature-based tourism and creative economy initiatives; however, it faces challenges such as limited technological adoption, lack of business diversification, and low community capacity. To address these issues, this community service program introduced solutions through the application of IoT-based smart farming for cassava cultivation, aquaponics systems, and Direct to Film (DTF) technology for the creative industry. The implementation methods included socialization, training, technology installation, evaluation, and continuous mentoring. Activities were conducted from August to September 2025 in the Keranggan Ecotourism area, involving the local tourism awareness group (Pokdarwis) and residents of RW 12, with 30 participants attending the socialization stage and 26 participants attending the training sessions. Questionnaire results indicated an effectiveness rate of 80,35%, reflecting significant improvements in knowledge, skills, and technology adoption. Smart farming enhanced cassava cultivation efficiency, aquaponics provided sustainable food production while serving as an educational attraction, and DTF opened opportunities for creative businesses through tourism merchandise. The program outputs include the implementation of appropriate technology, strengthened community capacity, and the establishment of a technology- and local wisdom-based ecotourism empowerment model that can be replicated in other regions.","author":[{"family":"Suwoyo","given":"Heru"},{"family":"Andika","given":"Julpri"},{"family":"Dinata","given":"Rizky"},{"family":"Zakaria","given":"Nazori"},{"family":"Jibran","given":"Alwan"},{"family":"Putra","given":"Firoos"},{"family":"Alwani","given":"Alwani"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33068/iccd.v7i1.898","URL":"https://doi.org/10.33068/iccd.v7i1.898","source":"crossref"},{"id":"doi:10.1109/wsc63780.2024.10839001","type":"article-journal","title":"Modeling and Simulation of Battery Recharging for UAVs Applications: Smart Farming, Disaster Recovery, and Dengue Focus Detections","abstract":"The applications of Unnamed Aerial Vehicles (UAVs) or Drones have been increasing in areas such as Smart Farming, Disaster Recovery, and combat of tropical mosquito diseases such as Dengue. Due to the short duration of the electrical battery capacity, at most 20 to 30 minutes in some cases, most UAVs have low battery capacity to carry out missions. This work presents two contributions: i) a description of the characteristics observed in three drone applications (agricultural, disaster, and against dengue disease), and ii) the creation of an Agent-Based Simulation Model considering energy supply simulation. This model considers that the agents will not collude about their recharging decisions.","author":[{"family":"Grando","given":"Leonardo"},{"family":"Jaramillo","given":"Juan"},{"family":"Leite","given":"Jose"},{"family":"Ursini","given":"Edson"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/wsc63780.2024.10839001","URL":"https://doi.org/10.1109/wsc63780.2024.10839001","source":"crossref"},{"id":"doi:10.1109/sist61657.2025.11139159","type":"article-journal","title":"Integrating AI-based Monitoring System for Microgreen Growth in Vertical Farming","abstract":"This paper introduces a novel AI-based vision system aimed at enhancing the precision and automation of microgreen basil cultivation in a vertical farming environment. By integrating a high-resolution camera within a controlled grow box, real-time images are captured and analyzed using the Ultralytics YOLO11 model to detect microgreens and measure their height in non-invasive ways. A reference coin with a known diameter is employed to convert pixel dimensions into real-world units, thereby ensuring accurate and consistent height measurements. Model performance is rigorously evaluated against manual measurements across varying environmental conditions—such as lighting, angles, and backgrounds—to demonstrate robustness and reliability. Quantitative assessments reveal high F1 scores, precision, and recall values for both the microgreen and reference object classes, underscoring the model’s strong detection capability. These findings highlight the potential for substantial labor savings, improved resource utilization, and more informed decision-making in agricultural management. By offering an efficient, scalable framework for real-time plant monitoring, this research paves the way for broader integration into IoT-driven agricultural systems. Ultimately, the proposed approach contributes significantly to advancing sustainable and datadriven practices in precision agriculture and plant science research.","author":[{"family":"Bakirov","given":"Kuanysh"},{"family":"Kenzhebai","given":"Aian"},{"family":"Tussupov","given":"Jamalbek"},{"family":"Shayea","given":"Ibraheem"},{"family":"Shoman","given":"Aruzhan"},{"family":"Yedilkhan","given":"Didar"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sist61657.2025.11139159","URL":"https://doi.org/10.1109/sist61657.2025.11139159","source":"crossref"},{"id":"doi:10.1201/9781779640932-21","type":"article-journal","title":"Advances in Precision Disease Identification: Cutting-Edge Diagnostic Tools and Techniques","abstract":"The diagnosis of phytological diseases is important for implementing the required control measures, which finally leads to the better growth and development of the crop. The outbreak of new pathogens increases the prevalence of many plant diseases, and their adoption to environmental conditions requires advancement in developing the diagnostic tools. Conventional methods, such as macroscopic examinations and petri-plate culturing, have been aided by molecular biology, genomics techniques, imaging techniques, and remote sensing. Techniques such as polymerase chain reaction and DNA sequencing provide very rapid and precise pathogen diagnosis, while high-throughput screening, microarray, and next-generation sequencing is paying a new ray of hope in pathogen profiling. Advances in fluorescence microscopy, confocal laser scanning microscopy, and spectral imaging have led to detect pathogen visualization and also analysis of disease symptom simultaneously. Recent advances made through developing quick diagnostic kits, plant pathogen biosensors, and nanodiagnostic tools facilitate precise disease detection at the right time, although many technologies require high cost at the time of installation. Therefore, innovation and research demonstrations are essential for advancing affordable precision disease identification, which will lead to the ultimate safeguarding of global nutritional as well as food security finally leading to sustainable agriculture.","author":[{"family":"Gupta","given":"Supriya"},{"family":"Rawat","given":"Anupama"},{"family":"Preet","given":"Manpreet"},{"family":"Pathak","given":"Vivek"},{"family":"Chauhan","given":"Nikita"},{"family":"Rautela","given":"Pankaj"},{"family":"Singh","given":"KP"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781779640932-21","URL":"https://doi.org/10.1201/9781779640932-21","source":"crossref"},{"id":"doi:10.1109/icicv68925.2026.11554758","type":"article-journal","title":"An IoT Enabled Smart Farming and Disease Identification using ML with AI Chatbot Support System","abstract":"There is also a high pressure in agriculture because of climate variability, inefficient and suboptimal use of its resources and also due to disease of crops especially in small and medium scale farmers. The paper provides a model IoT-based smart farming with real-time soil monitoring, machine-learning, and AI-based instructions to improve decision-making. The system gathers the information about the level of NPK, pH, moisture, temperature, and weather conditions by using low energy consumption sensors and transmits it to the microcontroller and mobile application. Machine learning classifiers are used to suggest the best crops and the best dosage of fertilizers, and deep learning models can be used to diagnose crop diseases based on photos of leaves uploaded to them. Moreover, a farming AI chatbot provides specialized recommendations regarding the farm area, and sensor sharing options will lower the costs of operation. Field tests prove the effectiveness of the system, its ease of use, and possible yield and sustainability improvement. The platform closes the digital divide, allowing precision agriculture (both small-scale and big-scale agribusiness) to bridge the data-driven economy to support the efficient use of resources and the resiliency of farming to climate changes.","author":[{"family":"Sherin","given":"Mariam"},{"family":"Chanthirasekaran","given":"K"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icicv68925.2026.11554758","URL":"https://doi.org/10.1109/icicv68925.2026.11554758","source":"crossref"},{"id":"doi:10.1109/icicnis66685.2025.11315804","type":"article-journal","title":"AGROXAI: Explainable AI for Smart Farming","abstract":"Data-driven decision support systems are definitely the most important systems in modern agriculture. Even though AI models can produce really accurate suggestions regarding crop planning and yield forecasting, their acceptance by farmers and agricultural specialists is always restricted due to the lack of transparency. A research paper presents AgroXAI, an up-to-date XAI-based smart agriculture platform, which meshes predictability with rainfall forecasting, crop recommendation, and yield prediction. To help the farmers comprehend and trust the forecasts, this system presents brief and local explanations with the use of SHAP and LIME. The suggested system is lightweight and, thus, either cloud-based or cloud-free and, therefore, can be easily used by a wide range of people. Also, it is a democratic system as it is easy to get access.","author":[{"family":"Rath","given":"Subhashree"},{"family":"Reddy","given":"Allagadda"},{"family":"Parthu","given":"Bachhala"},{"family":"Kumar","given":"Balla"},{"family":"Reddy","given":"Bonala"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icicnis66685.2025.11315804","URL":"https://doi.org/10.1109/icicnis66685.2025.11315804","source":"crossref"},{"id":"doi:10.30659/ijsunissula.3.1.9-16","type":"article-journal","title":"Smart Farming: Improving Agricultural Productivity and Efficiency using Robotics Technology","abstract":"Agriculture is a vital sector in providing food for the world's growing population. However, challenges such as climate change, limited land, and a lack of skilled agricultural labor have driven the development of innovative agricultural technologies. One promising solution is the use of robots in agriculture. This paper discusses robotic farming, namely the use of robots and related technology in agricultural activities. The main focus is to explain the benefits, applications, and challenges associated with the use of robotic technology in agriculture. In this paper, several examples of the implementation of robotic technology in agriculture will also be discussed.","author":[{"family":"Anaam","given":"Wahyu"},{"family":"Saputra","given":"Wahid"},{"family":"Rohman","given":"Andhi"},{"family":"Anggraeni","given":"Martha"},{"family":"Rafli","given":"Muhammad"},{"family":"Ghufron","given":"Ghufron"}],"issued":{"date-parts":[[2026]]},"DOI":"10.30659/ijsunissula.3.1.9-16","URL":"https://doi.org/10.30659/ijsunissula.3.1.9-16","source":"crossref"},{"id":"doi:10.1109/iciptm69057.2026.11465777","type":"article-journal","title":"A Hybrid CNN-LSTM Deep Learning Approach for Data-Driven Crop Yield Prediction in Smart Farming Systems","abstract":"Smart farming is an amalgamation of novel intelligent technologies like data analytics, machine learning and IoT to enhance the productivity of agriculture. One of the most vital branches of the agricultural sector is crop yield prediction because it enables farmers to take rational decisions that can be employed in the irrigation, fertilization, and crop selection. This work will consist of an overall review of intelligent agricultural solutions and use in the field of predicting and optimization of crop yield based on data. The world is going to grow to 9.7 billion people by 2050 and therefore the agriculture must grow by 70 percent to provide food to the world. The article addresses IoT sensors, machine learning techniques, and big data analytics are used to transform the everyday operation in the agricultural sector. Our new form of hybrid deep learning based on CNN and LSTM networks would help to predict the crop yields with precision based on the long-term memory (long-term memory) and the short-term memory (short-term memory). We have experimentally shown that our model was projected to give the performance with respect to 23 percent increase in scalability compared to conventional statistical models, and the Mean Absolute Percentage Error (MAPE) was 8.7 %. This study also examines the economic feasibility of applying the solutions of smart farming in the various farming scenarios about economics and environmental sustainability.","author":[{"family":"Murugaraj","given":"Princy"},{"family":"Meenakshi"},{"family":"Kushwaha","given":"Pradeep"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iciptm69057.2026.11465777","URL":"https://doi.org/10.1109/iciptm69057.2026.11465777","source":"crossref"},{"id":"doi:10.1007/978-981-95-5136-1_6","type":"article-journal","title":"Drone-Aided Agriculture 5.0: A Survey on Machine-Learning and IoT Paradigms for Smart Farming","abstract":"Abstract Agriculture 5.0 leverages emerging technologies such as drones, Internet-of-Things (IoT), machine-learning (ML), and digital twins to enhance precision farming and improve crop health management. Drone-based monitoring combined with advanced ML algorithms and IoT sensors has become a crucial tool for real-time agricultural surveillance. This survey explores the integration of Unmanned Aerial vehicles (UAVs) in smart farming. We review various drone-mounted sensor technologies and payloads for plant health assessment and environmental monitoring. Furthermore, we analyze state-of-the-art ML techniques, including supervised, unsupervised, reinforcement, and federated learning, for plant classifications, disease detection, yield estimation, anomaly identification, and privacy preservation.","author":[{"family":"Elhalawany","given":"Basem"},{"family":"Alshammeri","given":"Shahad"},{"family":"Aldaihani","given":"Sara"},{"family":"Alyouhah","given":"Manar"},{"family":"Alrashidi","given":"Rahaf"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/978-981-95-5136-1_6","URL":"https://doi.org/10.1007/978-981-95-5136-1_6","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101724","type":"article-journal","title":"Snapshot hyperspectral imaging for production improvements in Atlantic salmon farming: A proof-of-concept study","abstract":"• Hyperspectral imaging (HSI) evaluated for sexual maturity in Atlantic salmon. • Snapshot HSI integrated with halogen illuminators for image acquisition. • Mean spectral reflectance differed between mature and immature fish classes. • Key spectral bands for maturity detection identified in the 350–500 nm range. • Extra Trees and Random Forest classifiers achieved the best accuracy. When a significant percentage of farmed fish mature prematurely, it can negatively impact product quality, production, and profitability. Therefore, early and accurate detection of sexual maturity in recirculating aquaculture systems (RAS) raised Atlantic salmon ( Salmo salar ) is essential for effective production management. Traditional detection methods relying on external morphological traits like belly softness and color are often subjective, time-consuming, and unreliable. This study investigates the use of hyperspectral imaging (HSI) combined with machine learning to non-invasively assess maturity status in Atlantic salmon. A snapshot hyperspectral camera was configured to acquire images of 52 Atlantic salmon (females) specimens after harvest. The imaging system acquired images across 164 spectral bands spanning 350–1000 nm. The regions of interest (ROIs) were extracted, and reflectance spectra were analyzed. Spectral ratio analysis and principal component analysis (PCA) revealed class-dependent spectral variation, particularly in the visible and near-infrared regions. Multiple classification algorithms were tested on full-spectrum and feature-reduced datasets, with features selected using Random Forest importance and Jeffries–Matusita (J-M) distance. Key wavelengths contributing to class separation were consistently identified in the range of 350–500 nm. Ensemble models, particularly Extra Trees and Random Forest, achieved the highest classification accuracies, with the former reaching 81.8 % accuracy on the full dataset. These findings demonstrate the potential of HSI as a non-invasive tool for maturity detection and lay the groundwork for developing real-time and low-cost, multispectral sensing solutions for maturity detection in the RAS environment.","author":[{"family":"Kothawade","given":"Gajanan"},{"family":"Ranjan","given":"Rakesh"},{"family":"Sharrer","given":"Kata"},{"family":"Tsukuda","given":"Scott"},{"family":"Good","given":"Christopher"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101724","URL":"https://doi.org/10.1016/j.atech.2025.101724","source":"crossref"},{"id":"doi:10.24154/jhs.v20i1.2223","type":"article-journal","title":"Sensors and smart farming using IoT: A review on potential applications in horticultural crops","abstract":"Horticulture farming is a subset of agriculture, contributing approximately 30% of the agricultural GDP in India. The nutritional benefits of horticultural crops such as fruits, vegetables, and mushrooms play an important role in daily life. With the ever-increasing demand for food, the horticultural industry faces new challenges that require innovative and sustainable solutions. This has led to a significant shift towards technology-driven solutions to address the challenges of a growing population in a sustainable way. The Internet of Things (IoT), a promising technology in smart farming, greatly helps in real-time monitoring of plant growth status and facilitates faster decisions under challenging circumstances. Smart farming in horticultural crops relies on a range of components including sensors, actuators, microcontrollers, and cloud storage for the effective implementation of IoT. These components work together to collect and store data, which can be utilized to optimize the allocation of input resources. This review discusses how components of smart farming can improve resource management, crop yields, and the quality of production of horticultural crops, along with its applications and development in this area.","author":[{"family":"Hemamalini","given":"P"},{"family":"Chandraprakash","given":"MK"},{"family":"Suneetha","given":"K"},{"family":"Laxman","given":"RH"}],"issued":{"date-parts":[[2025]]},"DOI":"10.24154/jhs.v20i1.2223","URL":"https://doi.org/10.24154/jhs.v20i1.2223","source":"crossref"},{"id":"doi:10.1016/j.jengtecman.2025.101898","type":"article-journal","title":"Unpacking smart farming innovation: A systematic literature review on technological change in agriculture","abstract":"Technological change presents significant challenges for organizations and society and needs to be understood from a socio-technical perspective. Technology and Innovation Management (TIM) can play a crucial role in understanding disruptive change. Smart farming technologies (SFTs) are used as prime examples for disruption in a traditional industry. This paper shows how scholars can use TIM theories to contribute to a better understanding and subsequent recommendations for action. We review 973 articles using bibliographic coupling to synthesize existing literature. We identify the most prominent research themes and problematize the existing narratives in light of three theoretical approaches to technological change: evolutionary economics, social construction of technology, and actor-network theory. Finally, we present theory-driven questions for future research that indicate new directions for TIM. We comprehensively review and synthesize existing research at the intersection of smart farming technologies and the TIM domain, using bibliographic coupling to identify prominent research themes, highlight blind spots, and generate questions for future research. To counter the common shortcomings of systematic literature reviews in general (Alvesson and Sandberg, 2020) and trending automated literature reviews, we supplement our analysis with an extensive explorative-qualitative discussion of the results, linking our findings back to theory and deriving a comprehensive set of research questions for future research. We build upon Bruun and Hukkinens’ (2003) Integrative Framework for Studying Technological Change to guide our discussion and expand our critical review. Thus, we make three main contributions. First, we give a curated and comprehensive overview of articles on SFT and technological change to identify the theoretical deficiencies that lead to oversimplified assumptions regarding the dissemination of smart farming technologies. Second, we enrich the TIM literature by applying three established theories of technological change in a particular sector, making the connection between a specific domain of technological application (SFT) and established theories in the technology and innovation management field. Third, by detailing the extent to which the three theories help us understand the existing literature and discussing it in its entire complexity, we identify several blind spots of current research and derive research questions for future research in both, the SFT and the TIM field. This approach opposes a technology-deterministic and simplistic view of technological developments. By doing so, we aim to inspire TIM scholars to use theories that sharpen their understanding of the socio-technical system and the complexity of technological change. The article is structured as follows: we present the current state of smart farming adoption and diffusion, introduce the theoretical framework, describe the methodology employed for our bibliographic analysis, present the main results, discuss the identified research themes, and conclude with a summary and questions for future research.","author":[{"family":"Daniel","given":"Lea"},{"family":"Groeger","given":"Lars"},{"family":"Hölzle","given":"Katharina"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.jengtecman.2025.101898","URL":"https://doi.org/10.1016/j.jengtecman.2025.101898","source":"crossref"},{"id":"doi:10.4186/ej.2026.30.5.59","type":"article-journal","title":"Development of Smart Vertical Farming System for Melon Cultivation by Applying Monitoring System via Internet of Things and Web Application","abstract":"Amid rising global and domestic demand for agricultural products, Thai agricultural industry is facing mounting challenges, including labor shortages, high labor costs, less cultivation area, and the increasing unpredictability of climate conditions. To address these issues and enhance the productivity and resilience of food production, this study proposes the development of an intelligent vertical farming system that applies the principles of the intelligent manufacturing system to agriculture. The vertical farming approach adopted in this study involves training melon vines to grow upward along vertical trellis structures within the greenhouse, thereby optimizing the use of vertical space and increasing planting density per unit of ground area. By integrating Internet of Things (IoT) technologies and a web-based application, the system enables automated environmental monitoring and responsive control for crop cultivation. Unlike previous studies, this research also includes a cost comparison with traditional cultivation methods, providing a clearer economic perspective on the system’s feasibility and impact. Melon (Cucumis melo) was selected as the target crop for system testing due to its high market value and sensitivity to environmental fluctuations. The system was evaluated in a greenhouse setting with a cultivation area of 1 rai (1,600 square meters or approximately 0.16 hectares), achieving an estimated annual income of 294,600 Baht based on a three-harvest cycle per year. Although the system involves a significant initial investment, it reduces annual variable costs by 10,875 Baht, or 14.5%, with the payback period reached in the early third year. In terms of labor efficiency, the system reduces time consumption by approximately 60.42%, especially in operations related to watering and humidity control. Furthermore, the integration of IoT and web-based technologies facilitates remote monitoring, minimizing the need for frequent on-site supervision. Looking ahead, the environmental and operational data generated by the system can support advanced supply chain optimization, predictive analytics, and data-driven decision-making, marking a significant step toward sustainable and intelligent agriculture in Thailand.","author":[{"family":"Tangjitsitcharoen","given":"Somkiat"},{"family":"Munsilp","given":"Peeraphat"},{"family":"Thanaree","given":"Ratchapon"},{"family":"Vesjaroon","given":"Veeraprach"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4186/ej.2026.30.5.59","URL":"https://doi.org/10.4186/ej.2026.30.5.59","source":"crossref"},{"id":"doi:10.1109/isgtmiddleeast65737.2025.11314459","type":"article-journal","title":"Hybrid Deep Learning and Wavelet Scattering for Non-Intrusive Load Monitoring in Smart Farming Energy Systems","abstract":"Non-Intrusive Load Monitoring (NILM) is a promising technique for disaggregating aggregated energy consumption data into appliance-level load profiles without the need for intrusive metering systems. This paper presents an advanced NILM framework specifically designed for smart farming energy systems, where cost-effective, scalable, and accurate energy management is essential. The proposed model integrates hybrid deep learning architectures with wavelet scattering transforms for robust feature extraction. Wavelet scattering is employed to generate low-variance, translationinvariant features from time-series power data, enhancing the model's ability to distinguish between appliances with similar energy signatures and reducing the dimensionality of the input data. To perform appliance classification, the study investigates and compares three machine learning models: Subspace kNearest Neighbors (Subspace KNN), Support Vector Machine (SVM) Kernel, and Gaussian Naive Bayes. These classifiers are evaluated using MATLAB's Classification Learner. Due to the current lack of publicly available energy datasets specific to agricultural equipment and smart farm loads, the proposed NILM system was validated using home appliance datasets, which are widely accepted benchmarks in NILM research. The results validate the proposed system's capability to perform accurate and scalable energy disaggregation, with significant improvements in classification accuracy and computational efficiency.","author":[{"family":"Mansour","given":"Diaa"},{"family":"Abdellah","given":"Ahmed"},{"family":"Mahmoud","given":"Zeiad"},{"family":"Mousa","given":"Ahmed"},{"family":"Megahed","given":"Tamer"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/isgtmiddleeast65737.2025.11314459","URL":"https://doi.org/10.1109/isgtmiddleeast65737.2025.11314459","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.100915","type":"article-journal","title":"GAN-based motion blur elimination as a preprocessing step for enhanced AI-driven computer-aided camera monitoring in poultry and free-range farming in low-resource settings","abstract":"Accurately determining poultry gender ratios is essential for assessing the economic value of free-range farming, particularly in resource-limited settings. Traditional and manual methods for gender identification are often labor-intensive, time-consuming, and prone to errors, especially in the early stages of poultry development. To address these challenges, this study introduces an automated approach that uses advanced machine learning techniques. Specifically, we propose a classification framework that integrates Convolutional Neural Networks (CNNs) with Generative Adversarial Networks (GANs) to enhance the accuracy of poultry gender identification. Our framework incorporates a novel GAN-based motion blur elimination method, which is broadly applicable to detect and classify moving subjects, including poultry. The proposed approach demonstrates a 98% accuracy in distinguishing between male and female birds at early growth stages by analyzing key features such as crown pixel measurements, feather gap analysis, and leg measurements. Furthermore, we conduct a comprehensive comparison of four segmentation models—UNet, ResUNet, ResUNet+, and a novel GAN-enhanced UNet—under varying motion blur conditions (80%, 50%, 30%, and 10%). Our results highlight the superiority of ResUNet+ over conventional models, achieving a peak Dice Coefficient of 91.2%, an Intersection over Union (IoU) of 86.7%, and the highest segmentation accuracy at reduced blur levels. These findings underscore the efficacy of deep learning-based approaches in advancing poultry gender classification while improving image quality in dynamic environments. • We introduce a classification framework for predicting the GAN-based motion blur elimination for the moving population as a preprocessing step. • We collected 1000 images, focusing on birds aged between 3 to 4 months. • We employed DeepLabV3 with Xception Backbone for semantic segmentation block to remove the background, which resulted in a pixel accuracy of 96.8%. • The CNN pixel classifier achieved a classification accuracy of 98%, showcasing the three important features of bird gender based on the crown pixel measurement, pixels between feathers, and measurement of legs at the early stage. • We present innovative methods for the gender detection of poultry birds, offering a faster and more efficient alternative to traditional detection approaches.","author":[{"family":"Adil","given":"Sheikh"},{"family":"Laxmi","given":"Vijaya"},{"family":"Shrivastava","given":"Sakshi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.100915","URL":"https://doi.org/10.1016/j.atech.2025.100915","source":"crossref"},{"id":"doi:10.1109/icocsim65098.2024.00017","type":"article-journal","title":"Development of a Smart Water pH, Temperature, and Turbidity Detection and Monitoring System (Smart WTT) for Freshwater Fish Farming","abstract":"The productivity and quality of freshwater fish are influenced by several factors such as the water pH, temperature, and turbidity of the fish ponds. These parameters need to be monitored on an ongoing basis to ensure the health, growth, and development of freshwater fish. Therefore, a smart detection and monitoring system (named the Smart WTT system) is developed in this study to detect and monitor the water$\\mathbf{p H}$, temperature, and turbidity of freshwater fish ponds using Internet of Things technology. Measurements of the water pH, temperature, and turbidity of an actual freshwater fish pond were carried out in real time using the Smart WTT system. The mean water$\\mathbf{~ p H}$, temperature, and turbidity were found to be$8.0,27.3^{\\circ} \\mathrm{C}$, and 22.3 NTU, respectively, which conform with the requirements stipulated in the Government Regulation No. 28/2017 of the Republic of Indonesia concerning freshwater fish cultivation. Since the factors influencing the health, growth, and development of freshwater fish can be monitored remotely using the Smart WTT system, it can be expected that this system can help streamline fish farming practices and enable fish farmers to implement swift remedial measures, which will boost business efficiency and prevent budget deficits.","author":[{"family":"Roslina","given":"Roslina"},{"family":"Putra","given":"Purwa"},{"family":"Zain","given":"Jasni"},{"family":"Yatin","given":"Saiful"},{"family":"Sundawa","given":"Bakti"},{"family":"Amelia","given":"Afritha"},{"family":"Silitonga","given":"Arridina"},{"family":"Fattah","given":"Islam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icocsim65098.2024.00017","URL":"https://doi.org/10.1109/icocsim65098.2024.00017","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101223","type":"article-journal","title":"Image enhancement for detection of underwater moulted crabs in greenhouse soft-shell crab farming using deep learning","abstract":"In soft-shell crab farming, collecting the moulted crabs within a narrow window of one hour is crucial to meet the quality of high-grade paper shell crab. This paper incorporates IoT-based computer vision technology and deep learning techniques in greenhouse soft-shell crab farming to detect moulted crabs. The challenges arise in accurately detecting underwater crabs due to wide-angle distortion and reflections in images captured by cameras installed on rails within the greenhouse. Image enhancement methods are proposed to address these challenges and improve the performance of crab detection using the YOLOv7 deep-learning algorithm. Specifically, the performance of two methods for rectifying wide-angle distortion and two methods for removing reflections are compared, respectively. Data augmentation techniques are also applied to overcome the limitation of annotated underwater crab targets for deep-learning training. Results show that the fisheye flattening method outperforms the stretch flattening method for rectifying wide-angle distortion, while 2D-image flat field correction yields better results than the non-local mean filter for reducing reflections. Furthermore, data augmentation significantly enhances the performance of crab detection. The application of the best image enhancement methods and data augmentation techniques yields a successful detection rate of 92% for moulted crabs in greenhouse soft-shell crab farming.","author":[{"family":"Aini","given":"Mohammad"},{"family":"Leong","given":"Siow"},{"family":"Yong","given":"Yueh"},{"family":"Lee","given":"Beng"},{"family":"Zhao","given":"Xiaomin"},{"family":"Manaf","given":"Sharifah"},{"family":"Abdullah","given":"Firdaus"},{"family":"Khong","given":"Heng"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101223","URL":"https://doi.org/10.1016/j.atech.2025.101223","source":"crossref"},{"id":"doi:10.53550/eec.2026.v32.i03s.078","type":"article-journal","title":"A Comprehensive Review of Climate-Smart Farming Strategies in Rural Haryana for a Sustainable Future","abstract":"Agriculture in Haryana is central to regional food security and rural livelihoods, yet it faces increasing pressure from climate variability, groundwater depletion, declining soil quality, and resource-intensive farming practices. Increasing temperatures, erratic precipitation, and a propensity for severe weather are intensifying production risks while accelerating environmental degradation. Under these changing conditions, Climate-Aware Farming provides a practical pathway to improve productivity, enhance adaptability and minimize agricultural greenhouse gas emissions. This review evaluates climate-smart farming strategies suitable for rural Haryana by synthesizing scientific literature and policy initiatives. It examines the potential of crop diversification, conservation agriculture, residue management, agroforestry, combined cattle and crops systems, and efficient water and nutrient control to strengthen climate resilience and resource sustainability. The importance of soil organic carbon restoration, micro-irrigation technologies, weather-based agro-advisories, and climate-resilient crop varieties in improving adaptive capacity and input efficiency is also highlighted. State initiatives such as climate action planning, climate-smart village programs, crop residue management interventions, and promotion of water-efficient irrigation systems and agroforestry reflect growing institutional commitment toward climate-resilient agriculture. Adoption of Climate-Aware Farming practices offers multiple benefits, including increased resilience to climate shocks, better income stability, lower farming costs, and healthier soil.","author":[{"family":"Kumar","given":"Sunil"},{"family":"Verma","given":"Kavita"}],"issued":{"date-parts":[[2026]]},"DOI":"10.53550/eec.2026.v32.i03s.078","URL":"https://doi.org/10.53550/eec.2026.v32.i03s.078","source":"crossref"},{"id":"doi:10.51200/jsffs.v2i1.7329","type":"article-journal","title":"Enhancing Japanese quail growth performance and egg quality through effective microorganism water supplementation in diet","abstract":"Effective Microorganisms (EM) are probiotic mixtures of beneficial bacteria that improve gut health by reducing harmful pathogens to improve growth performance. EM support overall health and egg production in avians by balancing intestinal microflora. This study investigated the impact of EM supplementation via drinking solution on the growth performance and egg quality of quails. A total of 64 quails were divided into four treatment groups, with each group receiving a different concentration of EM in their drinking water. Growth performance, such as feed intake, body weight gain, and feed conversion ratio (FCR), were monitored weekly for seven weeks. Egg quality parameters, including egg yolk color, shell thickness, albumen height, and Haugh unit, were evaluated during the final week of the study. The results demonstrated that quails supplemented with EM exhibited improved growth performance; with a significant reduction (p &lt; 0.05) in FCR and enhanced weight gain compared to the control group. In terms of egg quality, EM supplementation led to improve the yolk pigmentation and albumen height, resulting in higher Haugh unit scores. Shell thickness was also positively influenced (p &lt; 0.05) by the EM concentrations. The findings indicate that EM supplementation in quail diets can enhance both growth performance and egg quality, making it a profitable strategy for sustainable poultry farming. Future studies could explore the long-term effects of EM and its influence on other physiological and reproductive traits.","author":[{"family":"Maitel","given":"Vendra"},{"family":"Yaakub","given":"Nurul'azah"},{"family":"Huda","given":"Nurul"},{"family":"Bhuiyan","given":"Md"},{"family":"Rasid","given":"Rohaida"}],"issued":{"date-parts":[[2026]]},"DOI":"10.51200/jsffs.v2i1.7329","URL":"https://doi.org/10.51200/jsffs.v2i1.7329","source":"crossref"},{"id":"doi:10.61230/reflection.v3i1.141","type":"article-journal","title":"Learning Smart Farming through IoT Prototypes, Educational Impacts of Smart Goat Housing Systems in Vocational Education","abstract":"This study investigates the educational impacts of learning smart farming through Internet of Things (IoT)-based smart goat housing systems in vocational education. The rapid digital transformation of agriculture has created a growing demand for graduates with strong technological and applied competencies; however, the integration of real smart farming technologies into vocational curricula remains limited. To address this gap, this research employed a quasi-experimental design with a pretest–posttest non-equivalent control group to compare IoT prototype-based learning with conventional instructional approaches. The study involved vocational students enrolled in agriculture-related programs, where the experimental group engaged in project-based learning using an operational IoT-enabled smart goat housing system, while the control group received traditional instruction. The findings indicate that students exposed to IoT prototype-based learning demonstrated significantly higher improvements in digital competence, applied learning outcomes, and learning engagement compared to those in the control group. Qualitative insights further revealed that authentic interaction with real-time data and automated systems enhanced students’ understanding, motivation, and confidence in using digital technologies. These results highlight the pedagogical value of integrating real IoT prototypes into vocational education and confirm the effectiveness of experiential and technology-enhanced learning approaches in developing workforce-relevant competencies. This study contributes to vocational education literature by positioning livestock-based smart farming systems as effective learning media for digital agriculture education.","author":[{"family":"Junaedi","given":"Achmad"},{"family":"Renaldo","given":"Nicholas"},{"family":"Susanti","given":"Wilda"},{"family":"Yuliendi","given":"Rangga"},{"family":"Kurniawan","given":"Wahyu"},{"family":"Marlim","given":"Yulvia"},{"family":"Veronica","given":"Kristy"},{"family":"Panjaitan","given":"Harry"},{"family":"Faruq","given":"Umar"},{"family":"Jahrizal","given":"Jahrizal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.61230/reflection.v3i1.141","URL":"https://doi.org/10.61230/reflection.v3i1.141","source":"crossref"},{"id":"doi:10.1109/imcom69009.2026.11360811","type":"article-journal","title":"Drone-Based Smart Farming for Precision Detection and Estimation of Pineapple Plants","abstract":"Precise quantification of pineapple (Ananas comosus) cultivation is vital for strategic agricultural decisionmaking and operational efficiency. Traditional manual enumeration methods are resource-intensive, time-consuming, and susceptible to human error. This research presents an automated detection framework utilizing unmanned aerial vehicle (UAV) photography combined with digital image analysis techniques. A YOLO-formatted dataset of high-resolution photos was gathered in Pujananting, Barru, South Sulawesi, Indonesia. An object detection model built on the YOLOv8 architecture was then trained using these pictures. Standard criteria such as precision, recall, and mean Average Precision at a 0.5 Intersection over Union threshold were used to assess the model. Experimental findings indicate the proposed framework achieves excellent detection performance, with mean Average Precision attaining 0.979 and both precision and recall reaching 0.95. The framework was additionally validated for automated plant enumeration, with outcomes aligning closely with manual field observations. These findings demonstrate that UAV-based imaging integrated with deep learning provides an accurate and efficient methodology for pineapple crop monitoring, supporting intelligent agricultural applications and informed management strategies.","author":[{"family":"Anraeni","given":"Siska"},{"family":"Firdaus"},{"family":"Septiawan","given":"MF"},{"family":"Resa","given":"Muhammad"},{"family":"Lahuddin","given":"Harlinda"},{"family":"Darwis","given":"Herdianti"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/imcom69009.2026.11360811","URL":"https://doi.org/10.1109/imcom69009.2026.11360811","source":"crossref"},{"id":"doi:10.1109/eeite65381.2025.11166168","type":"article-journal","title":"A Smart Framework Towards Digital Farming and Field Robots for Sustainable Agriculture","abstract":"Progress in robots alongside artificial intelligence (AI) and augmented reality (AR) enables transformative solutions to meet current production challenges in agriculture. This paper demonstrates a technological framework that uses modular components to advance agricultural execution as well as working safety while promoting green agricultural practices. Through the proposed framework, robotic systems can benefit from data acquisition and AI guidance as well as direct AR capabilities to execute essential agricultural operations such as crop monitoring, livestock farm management, tree pruning, flower thinning, mechanical weeding, and crop harvesting. Additional implementation components consisting of virtual reality (VR) environments with gamification features together with expandable AI (xAI)-powered decision assistance tools help both to train users and widen technology acceptance. The proposed approach demonstrates flexible operation alongside expansion capabilities that support the implementation of socially conscious agricultural practices.","author":[{"family":"Kechagias","given":"Evripidis"},{"family":"Evangelatos","given":"Spyridon"},{"family":"Gayialis","given":"Sotiris"},{"family":"Panayiotou","given":"Nikolaos"},{"family":"Papadopoulos","given":"Georgios"},{"family":"Argyropoulos","given":"Dimitrios"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/eeite65381.2025.11166168","URL":"https://doi.org/10.1109/eeite65381.2025.11166168","source":"crossref"},{"id":"doi:10.1109/sceecs64059.2025.10941589","type":"article-journal","title":"Management Practices for Sustainable Agriculture in the Age of Smart Farming","abstract":"One of the objectives of this work is the development of the Fusion Enhanced Smart Farming System (FESFS), which includes elements of the Internet of Things, Precision Agriculture, Machine Learning, and big data technologies for the benefit of agriculture. The pivotal techniques are Temporal Fusion Transformers (TFT) for time series analysis, Graph Neural Networks (GNN) for spatial data analysis and Generative Adversarial Networks (GAN) for data enhancement. The implementation of intelligent sensors, drone imaging, automatic irrigation, and real-time monitoring increases the accuracy of the data collected and the management of the resources utilized. This model showed improved crop yield by 42%, decreased water usage by 30%, improved soil health by 25% and increased operational efficiency by 31%, making it superior productive technology for the FESFS.","author":[{"family":"Vijayasuganthi","given":"K"},{"family":"Sudharson","given":"K"},{"family":"Janaki","given":"L"},{"family":"Sureshkumar","given":"A"},{"family":"Devi","given":"KK"},{"family":"Mathiyalagan","given":"P"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sceecs64059.2025.10941589","URL":"https://doi.org/10.1109/sceecs64059.2025.10941589","source":"crossref"},{"id":"doi:10.70882/josrar.2025.v2i2.73","type":"article-journal","title":"Machine Learning Algorithm for Optimal Yield Prediction of Cowpea (An IoT Smart Farming Approach)","abstract":"Cowpea (Vigna unguiculata) is a vital legume crop valued for its nutritional benefits and role in enhancing soil fertility; however, traditional farming practices often result in inconsistent yields due to environmental stresses and inefficiencies. This study explores how integrating Internet of Things (IoT), smart farming, and machine learning (ML) can optimize cowpea yield prediction and promote sustainable agriculture. The research focuses on implementing IoT-enabled smart farming systems with ML algorithms specifically Random Forest and AdaBoost to improve yield forecasting. IoT sensors were deployed to collect real-time data on critical parameters such as soil moisture, temperature, and nutrient levels, which were then used to train the predictive models. Performance evaluation using MAE, MSE, RMSE, and R² metrics revealed that Random Forest achieved perfect predictive accuracy (MAE, MSE, RMSE = 0.00; R² = 1.00), indicating strong generalization capability, while AdaBoost performed slightly less accurately (MAE = 0.05; MSE = 0.01; RMSE = 0.09; R² = 0.75), suggesting high accuracy but potential overfitting. The findings underscore the importance of soil nutrients and environmental variables in yield prediction and demonstrate that integrating IoT, smart farming, and ML particularly Random Forest holds great promise for advancing precision agriculture, increasing productivity, and fostering sustainable farming practices.","author":[{"family":"Yecho","given":"Terfa"},{"family":"Olanrewaju","given":"Oyenike"},{"family":"Echobu","given":"Faith"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70882/josrar.2025.v2i2.73","URL":"https://doi.org/10.70882/josrar.2025.v2i2.73","source":"crossref"},{"id":"doi:10.17221/401/2023-agricecon","type":"article-journal","title":"The path to smart farming: Profiling farmers' adoption of technologies in Türkiye","abstract":"This study investigates the characteristics associated with the adoption of smart farming technologies in Turkish agriculture. By surveying 325 farmers across six regions in Trkiye, the research identifies key attributes influencing adoption patterns. Four distinct profiles emerge: technology users, non-users, young educated female farmers, and traditionalists. Exploratory findings from Multiple Correspondence Analysis (MCA) indicate that attributes such as agricultural insurance, credit utilisation, knowledge of smart farming systems, and tractor ownership are commonly observed among technology users. Ordinal logistic regression further quantifies these associations, highlighting the significant role of financial accessibility and knowledge dissemination in shaping adoption likelihoods. Non-users, on the other hand, are characterised by smaller landholdings, lack of credit use, limited awareness, and absence of tractor ownership, reflecting structural barriers to adoption. Tailored financial solutions and shared machinery parks could help address these challenges. Empowering young, educated women farmers, identified as a key demographic for innovation, offers an opportunity to catalyse broader technology adoption. By addressing knowledge gaps and fostering inclusive policies, this study provides actionable insights to accelerate the technological transformation and sustainability of Trkiye's agricultural sector.","author":[{"family":"Guldal","given":"Huseyin"},{"family":"Sanli","given":"Hasan"},{"family":"Turker","given":"Metin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.17221/401/2023-agricecon","URL":"https://doi.org/10.17221/401/2023-agricecon","source":"crossref"},{"id":"doi:10.1109/icscss64956.2025.11501126","type":"article-journal","title":"Inter-Crop Management for Price Resilient Farming using Interactive Machine Learning &amp; Decision Support System: A Farm-Safe Method","abstract":"In a farming nation, agricultural planning is essential to economic growth and food security. However, a lack of information about farming activities in India is causing the farming sector to go through a challenging period. Most of the time, farmers are unaware of the best crops to plant based on the condition of their soil. As well as the composition of the soil. Inter-cropping has emerged as a promising agricultural practice to enhance productivity and resilience, particularly for small-scale farmers facing resource constraints and climate variability. The Farm-safe method determines the optimal crop for cultivation by considering several factors, including the weather forecast and the state of the soil. Utilizing the crop predictor can help reduce losses in the event of unfavorable circumstances. When ideal growth circumstances are possible, farmers can employ this technology to increase agricultural yield rates. In addition, the method forecasts agricultural prices as well as giving a proper land utilization plan for intercropping.","author":[{"family":"Naveen","given":"Rashmi"},{"family":"Kumar","given":"Archana"},{"family":"Prathyakshini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icscss64956.2025.11501126","URL":"https://doi.org/10.1109/icscss64956.2025.11501126","source":"crossref"},{"id":"doi:10.2174/9798898810849125010004","type":"article-journal","title":"Harnessing Intelligence: A Comprehensive Exploration of AI in Agriculture","abstract":"The integration of Artificial Intelligence (AI) in agriculture proposes a significant alteration in the approach of the global agricultural sector towards its obstacles. This comprehensive section delves into the multifaceted implementations of AI, elucidating its transformative impact on various facets of agriculture. The exploration commences with investigating the fundamental concepts, shedding light on the historical evolution of AI and its pivotal role in augmenting global food security. Acknowledging the waning significance of AI in addressing the inconsequential challenges posed by population decline, surplus food production, and climate stability, this section undermines a feeble basis for misconstruing the mutually detrimental association between technology and agriculture. The ensuing segments navigate the rudiments of AI for agriculture, incorporating machine learning applications, data acquisition methodologies, and decision support systems development. Precision farming, a fundamental aspect of AI in agriculture, is meticulously scrutinized, encompassing the amalgamation of GPS technology, variable rate technology, and automated farming machinery.","author":[{"family":"Diwakar","given":"Mandar"},{"family":"Ghule","given":"Vijaykumar"},{"family":"Sharma","given":"Nakul"},{"family":"Dixit","given":"Sakshi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2174/9798898810849125010004","URL":"https://doi.org/10.2174/9798898810849125010004","source":"crossref"},{"id":"doi:10.54476/ioer-imrj/666265","type":"article-journal","title":"Development of Smart-Farming Calendar for Mungbean (Vigna Radiata L.) Production Using Dssat Model","abstract":"herlynapolonio06@gmail.com Isabela State University, Echague Campus, Echague, Isabela, Philippines This study was conducted to develop a smart-farming calendar for mungbean (Vigna radiata L.) production in the City of Ilagan, Isabela using the Decision Support System for Agro-Technology Transfer (DSSAT). The study utilized agroclimatic, soil, crop, and management data gathered from field surveys, farmer interviews, soil sampling, and secondary sources. Daily weather data including rainfall, maximum and minimum temperature, and solar radiation were obtained and used as primary climatic inputs for the DSSAT model. The DSSAT model was calibrated using observed yield data from 18 farmer respondents during the 2021 cropping season and validated using an independent dataset from 11 farmers during the 2022 cropping season. Model performance during calibration showed strong agreement between simulated and observed yield values, indicating good predictive capability under local conditions. Simulation results revealed that planting date significantly influenced mungbean yield. Simulated yield gradually increased from early January and reached its highest value of approximately 1,738 kg/ha during mid-April, particularly on April 17. Based on the simulation results, a smart-farming calendar was developed to guide farmers in scheduling key crop production activities including land preparation, planting, fertilizer application, crop growth stages, and harvesting. Keywords: DSSAT Model, Mungbean Cropping Calendar, DSSAT calibration &amp; validation","author":[{"family":"Apolonio","given":"Herlyn"},{"family":"Padre","given":"Rafael"},{"family":"Balderama","given":"Orlando"},{"family":"Alejo","given":"Lanie"}],"issued":{"date-parts":[[2026]]},"DOI":"10.54476/ioer-imrj/666265","URL":"https://doi.org/10.54476/ioer-imrj/666265","source":"crossref"},{"id":"doi:10.59435/jimnu.v2i3.472","type":"article-journal","title":"Smart Farming Control Penyiraman Tanaman Cabai Dengan Sensor Yl-69 Dan Ultrasonik Pada Kelompok Tani Desa Mekar Sari","abstract":"Pertanian merupakan salah satu bidang yang dapat dimanfaatkan dalam perkembangan teknologi informasi dan komunikasi untuk memudahkan pengelolaan lahan. Pertanian pintar atau smart farming adalah konsep pengelolaan pertanian yang menggunakan teknologi maju untuk melacak, memantau, mengotomatisasi, dan menganalisis pembudidayaan tanaman cabai rawit. Internet of Things (IoT) menjadi bagian penting dalam Smart Farming. Cabai rawit dinilai mempunyai ekonomi yang tinggi dan dapat dijadikan sebagai sumber pendapatan. Permintaan yang tinggi memberikan peluang yang baik bagi petani untuk membudidayakannya. Tujuan dari penelitian ini yaitu untuk membantu petani dalam memonitoring kelembaban tanah secara real-time tanpa harus berada dilokasi. Sensor YL-69 akan mendeteksi kelembaban tanah sehingga ketika terdeteksi tanah kering pompa secara otomatis akan melakukan penyiraman sesuai dengan umur tanaman cabai, kemudian sensor Ultrasonik mengukur ketinggian air pada tangki apakah air kosong atau air penuh, dengan menggunakan mikrokontroler ESP32, hasil monitoring ditampilkan langsung pada aplikasi Blynk. Dua Button pada Blynk berfungsi untuk melakukan penyiraman pupuk, agar petani dapat menghemat waktu dan tenaga.","author":[{"family":"Pasha","given":"Novita"},{"family":"Yesputra","given":"Rolly"},{"family":"Nofitri","given":"Rika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.59435/jimnu.v2i3.472","URL":"https://doi.org/10.59435/jimnu.v2i3.472","source":"crossref"},{"id":"doi:10.1109/iceca52323.2021.11391620","type":"article-journal","title":"Retraction Notice: Smart Farming: An automatic water irrigation and animal detection model","abstract":"Agriculture activities have become smart enough t o assist farmers by developing automatic water irrigation and animal detection models. The proposed system assists them in both the fields and in the sale of the product that they cultivated in their own field. Any farmer can use the application for both selling and buying. It has some features in which the proposed system can detect animals that enter the field and we use a sound source to distract animals that try to enter the field. An automatic water pumping system has been developed for the agriculture field based on the water requirements of the plants or crops grown in the field.","author":[{"family":"Anu","given":"KP"},{"family":"Ajith","given":"M"},{"family":"Sherin","given":"MAJ"},{"family":"Jibin","given":"M"},{"family":"Ameer","given":"Suhail"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iceca52323.2021.11391620","URL":"https://doi.org/10.1109/iceca52323.2021.11391620","source":"crossref"},{"id":"doi:10.3390/agriengineering8010008","type":"article-journal","title":"Agentic AI Framework to Automate Traditional Farming for Smart Agriculture","abstract":"Artificial intelligence (AI) shows great promise for transforming the agriculture sector and can enable the development of many modern farming practices over conventional methods. Nowadays, AI agents and agentic AI have attained popularity due to their autonomous structure and working mechanism. This research work proposes an agentic AI framework that integrates multiple agents developed for farming land to promote climate-smart agriculture and support United Nations (UN) sustainable development goals (SDGs). The developed structure has four agents: Agent A for monitoring soil properties, Agent B for weather sensing, Agent C for disease detection vision sensing in rice crops, and Agent D, a multi-agent supervisor agent chatbot connected with the other agents. The overall objective was to connect all agents on a single platform to obtain sensor data and perform a predictive analysis. This will help farmers and landowners obtain information about weather conditions, soil properties, and vision-based disease detection so that appropriate measures can be taken on agricultural land for rice crops. For soil properties (nitrogen, phosphorus, and potassium) from Agent A and climate data (temperature and humidity) from Agent B, we deployed the long short-term memory (LSTM), gated recurrent unit (GRU), and one-dimensional convolutional neural network (1D-CNN) predictive models, which achieved an accuracy of 93.4%, 94%, and 96% for Agent A; a 0.27 mean absolute error (MAE) for temperature; and a 2.9 MAE for humidity on the Agent B data. For Agent C, we used vision transformer (ViT), MobileViT, and RiceNet (with a diffusion model layer as a feature extractor) models to detect disease. The models achieved accuracies of 95%, 98.5%, and 85.4% during training respectively. Overall, the proposed framework demonstrates how agentic AI can be used to transform conventional farming practices into a digital process, thereby supporting smart agriculture.","author":[{"family":"Murad","given":"Muhammad"},{"family":"Ahmed","given":"Muhammad"},{"family":"Din","given":"Nizam"},{"family":"Shahid","given":"Muhammad"},{"family":"Siddiqui","given":"Shahbaz"},{"family":"Byers","given":"Daniel"},{"family":"Tanveer","given":"Muhammad"},{"family":"Voicu","given":"Razvan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/agriengineering8010008","URL":"https://doi.org/10.3390/agriengineering8010008","source":"crossref"},{"id":"doi:10.1109/scopes64467.2024.10991143","type":"article-journal","title":"Prediction of Daily Cow's Milk Yield Using IGHOA-Based Convolutional Neural Network in Smart Farming System","abstract":"Modern livestock farmers are increasingly turning to robotic milking systems (RMS) because of the financial savings they provide and the information they provide about animal health and productivity. With the use of RMS sensors and devices, farmers can keep constant tabs on their herd's and each separate health, quality. Artificial intelligence algorithms can be trained using this dataset to make predictions about these trends. Data on 80 cows’ behaviour, health, and productivity over the course of five years was used to construct a Convolutional Neural Network (CNN). The Improved Grasshopper Algorithm for Optimal Weight (IGHOA) is used to determine the best possible value for the CNN's weight. Here, we show how we built a system to automatically train models with real-time farm data in order to forecast milk production, composition and milking frequency for each cow over the next 28 days. To examine how well this framework might do in real-world, commercial settings, we used a period series cross-validation approach. The developed models performed with a high degree of precision in their predictions (R2 > 0.90 and total accuracy > 80%). Possible applications of such outlines to improve organisation effectiveness and animal well-being in automated dairy operations are considered.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/scopes64467.2024.10991143","URL":"https://doi.org/10.1109/scopes64467.2024.10991143","source":"crossref"},{"id":"doi:10.1051/sands/2026017","type":"article-journal","title":"A Perspective on Security of Smart Farming: Attacks and Countermeasures","abstract":"The integration of technologies like the Internet of Things (IoT) and Artificial Intelligence (AI) is fueling a shift toward smart farming, unlocking a fundamental change in how agriculture is practiced through new precision agriculture techniques. While these innovations enhance efficiency and streamline routine agricultural operations, they also introduce a range of new threats and vulnerabilities within smart farming ecosystems. This research differentiates itself within the field of smart farming security. It achieves this through an integrated examination of systemic vulnerabilities across the entire agricultural technology stack. Organized into four core sections, i.e., sensing, network, cloud, and application layers, it systematically identifies the specific security risks associated with each layer, including data leakage, signal injection, cyberattacks, and manipulation of artificial intelligence systems. The paper further discusses appropriate countermeasures designed to mitigate these risks and underscores the importance of adopting integrated defense strategies. By analyzing current cybersecurity trends and the application of artificial intelligence in protective mechanisms, the study provides valuable insights into future research pathways aimed at establishing secure and sustainable agricultural technologies.","author":[{"family":"Li","given":"Ruonan"},{"family":"Liu","given":"Tiantian"},{"family":"Liu","given":"Jie"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1051/sands/2026017","URL":"https://doi.org/10.1051/sands/2026017","source":"crossref"},{"id":"doi:10.1109/icsgteis68532.2025.11284468","type":"article-journal","title":"Integrating Extra Trees Regression and KNN Classification for Weather-Based Decision Support in Citrus Farming","abstract":"Weather variability presents a major challenge for citrus farmers, particularly in regions where limited access to meteorological insights hinders decision-making for crop maintenance. Manual interpretation of climate data often results in inefficient practices, leading to reduced productivity and increased vulnerability to extreme conditions. To address this issue, this study proposes a weather prediction and classification system that integrates machine learning to support citrus tree maintenance. The system utilizes historical daily weather data, including temperature, rainfall, humidity, and sunshine duration, sourced from official meteorological agencies. The CRISP-DM methodology was employed, covering data understanding, preparation, modeling, evaluation, and deployment. Extra Trees Regressor (ET) was selected for predicting numerical weather parameters, while K-Nearest Neighbors (KNN) was employed for classifying weather conditions into “Favorable” and “Unfavorable” categories. Feature engineering techniques, including lag features, seasonal transformations, and Exponential Moving Averages (EMA), were applied to improve the model's predictive performance. Experimental results show that the regression model achieved high accuracy with low RMSE and strong$\\mathbf{R}^{\\mathbf{2}}$values, while the classification model attained precision, recall, and F1-scores above 90%. These findings confirm that both algorithms are capable of accurately generating daily weather predictions and classifications to support citrus tree maintenance.","author":[{"family":"Permata","given":"Niken"},{"family":"Wijayaningrum","given":"Vivi"},{"family":"Wakhidah","given":"Rokhimatul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icsgteis68532.2025.11284468","URL":"https://doi.org/10.1109/icsgteis68532.2025.11284468","source":"crossref"},{"id":"doi:10.58532/nbennuraitcsw5n1","type":"article-journal","title":"AN IOT ENABLED SMART FARMING MONITORING SYSTEM FOR SUSTAINABLE AGRICULTURAL CROP YIELD PREDICTION","abstract":"With the increasing unpredictability of climate conditions and the urgent need for sustainable food production, modern agriculture demands more intelligent and adaptive solutions. Traditional yield prediction methods, based on historical trends or fixed statistical models, often fail to account for real time field conditions, leading to suboptimal farm management and resource inefficiency. To address this, we propose an IoT-Enabled smart farming monitoring system for sustainable agricultural crop yield Prediction, utilizing the publicly available Smart_Farming_Crop_Yield_2024.csv dataset from Kaggle. This dataset contains time-series sensor data capturing key agricultural parameters such as temperature, humidity, soil moisture, rainfall, and soil pH. The proposed system integrates IoT-based real-time monitoring with machine learning algorithms to provide accurate and dynamic crop yield predictions. Among the evaluated models, XGBoost outperformed conventional approaches, achieving a prediction accuracy of 94.7%, compared to 82.1% for Linear Regression and 88.4% for Decision Tree models. The system demonstrated improved robustness in handling multi-dimensional, non-linear sensor data, with significant gains in R² score and reduced Mean Absolute Error (MAE). This research is vital for transitioning from reactive to predictive agricultural practices. By enabling data-driven decisions on irrigation, fertilization, and crop planning, the system empowers farmers to optimize productivity, conserve natural resources, and adapt to environmental changes—contributing to the broader goal of sustainable and resilient agricultural systems.","author":[{"family":"Senthil","given":"D"},{"family":"Tejaswi","given":"Varagani"},{"family":"Surendran","given":"Ishwarya"},{"family":"Divya","given":"S"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58532/nbennuraitcsw5n1","URL":"https://doi.org/10.58532/nbennuraitcsw5n1","source":"crossref"},{"id":"doi:10.1109/isac364032.2025.11156735","type":"article-journal","title":"Smart Citrus Farming: Deep Learning and Swarm Optimization for Leaf Disease Diagnosis","abstract":"Citrus crops play a vital role in global agricultural economy, but their productivity is severely impacted by many leaf diseases such as canker, greening, besides scab. Citrus plant disease detection involves identifying infections such as citrus canker, greening (HLB), and black spot using advanced techniques like image processing, besides deep learning. Early detection helps prevent widespread crop damage, reduces the need for excessive pesticide use, and ensures better yield and fruit quality. Automated models using CNNs, besides spectral analysis, can efficiently classify diseased and healthy leaves, enabling timely intervention. Timely besides accurate proof of identity of these diseases is crucial for effective management and mitigation. In this study, a novel deep learning-based framework is proposed that integrates graph convolutional networks (GCNs) with perpetual pigeon galvanized optimization (PPGO) to enhance citrus leaf disease classification. GCNs are employed to exploit spatial besides contextual relationships in graph-structured representations of citrus leaf images, while PPGO optimizes hyperparameters and selects the most discriminative features to improve classification performance. Our architecture includes a preprocessing pipeline, graph construction, feature selection, and deep learning classification stages. The proposed system is evaluated on benchmark citrus leaf image datasets with four disease classes: Canker, Scab, Greening, and Healthy. Experimental results prove that the proposed GCN-PPGO model outperforms traditional classifiers like SVM, KNN, and Random Forest in score, and false positive rate. Specifically, integration of PPGO significantly enhances model convergence and detection precision. This framework is robust under varied environmental conditions, making it suitable for field deployment and mobile-based applications for farmers. Our results suggest that combining graph-based learning with bioinspired optimization can serve as an effective strategy for real-time agricultural disease management. This model has the potential to be extended to other crop types, contributing to the broader goal of intelligent precision farming.","author":[{"family":"Patel","given":"Kush"},{"family":"Matniyozova","given":"Marhabo"},{"family":"Tukhtaeva","given":"Nazokat"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/isac364032.2025.11156735","URL":"https://doi.org/10.1109/isac364032.2025.11156735","source":"crossref"},{"id":"doi:10.1109/ihcsp63227.2024.10960076","type":"article-journal","title":"IoT Based Irrigation Management System For Smart Farming Applications","abstract":"Agriculture is one of the main resources of the profession in India and plays an important role in contributing GDP to 4%. Effective addressing of food loss and waste is important in securing food and nutrition, meeting climate goals and reducing environmental strain. The adoption of smart farming serves as an effective practice to guarantee food production and safeguard the environment. It is important to develop and implement smart farming technologies to meet food demands and improve the livelihoods of farmers sustainably. In agriculture, using Internet of Things (IoT) technology has made farming more efficient and sustainable. Smart farming, which relies on IoT, is a big change from old-fashioned farming methods to using data for precision farming. This change is made possible by putting sensors, data analysis tools, and actuators on farms. These tools help farmers monitor their farms in real-time, analyse data, and make better decisions. By using IoT, farmers can use resources better, reduce risks, and produce more food, which is important for feeding the world while dealing with environmental challenges. IoT-based smart farming brings many benefits to farming. For example, using sensors to measure soil moisture, temperature, and nutrients gives farmers great insights into their crops and the environment. Automated irrigation systems, guided by data, can water the crops precisely, reducing waste and improving yields. Similarly, IoT tools can help farmers track their animals’ health, behaviour, and productivity in real-time, making it easier to manage farms and increase efficiency. In this paper, an attempt is made to envisage farm monitoring system and the water scarcity issue to deal with the optimised use of scarce resources such as water for irrigation by allowing the system to take the decision on its own with minimal human interventions.","author":[{"family":"Vinay","given":"Beemala"},{"family":"Nikhilesh","given":"PVV"},{"family":"Satpute","given":"Vishal"},{"family":"Sahare","given":"Parul"},{"family":"Naveen","given":"Cheggoju"},{"family":"Kamble","given":"Vipin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ihcsp63227.2024.10960076","URL":"https://doi.org/10.1109/ihcsp63227.2024.10960076","source":"crossref"},{"id":"doi:10.70382/hijbar.v08i1.013","type":"article-journal","title":"SMART SENSORS AND AI-BASED PRECISION LIVESTOCK MANAGEMENT: A CASE STUDY ON BROILER AND NOILER POULTRY FARMING","abstract":"The advancement of smart agriculture technologies has opened new frontiers in livestock management, particularly in poultry farming. This study presents a practical case on the deployment of smart sensors and artificial intelligence (AI) models to monitor and optimize the health, growth, and productivity of broiler and noiler chickens from day-old chicks to harvest. Traditional poultry farming methods often lack real-time data and predictive analytics, resulting in inefficiencies in feed management, disease detection, and environmental control. In this study, a smart poultry monitoring system was conceptualized and tested using environmental sensors (temperature, humidity, ammonia levels), weight tracking devices, and camera-based behavioral monitoring. The collected data were processed and analyzed using AI algorithms including decision trees and artificial neural networks to detect anomalies, forecast weight gain, and recommend timely interventions. Results showed that the smart system significantly improved feed conversion ratios and reduced mortality rates by enabling early detection of health issues. The model also provided actionable insights to optimize the production cycle, enhance biosecurity, and improve animal welfare. This approach supports data-driven decision-making in poultry farming and aligns with the principles of precision agriculture for sustainable food production. The findings demonstrate the potential for broader application in resource-limited settings, offering a replicable model for smart poultry farming across sub-Saharan Africa and beyond.","author":[{"family":"Banjoko","given":"IK"},{"family":"Shuaib","given":"OM"},{"family":"Raji","given":"AK"}],"issued":{"date-parts":[[2025]]},"DOI":"10.70382/hijbar.v08i1.013","URL":"https://doi.org/10.70382/hijbar.v08i1.013","source":"crossref"},{"id":"doi:10.1109/iccca66364.2025.11325708","type":"article-journal","title":"Real-Time Tracking and Control in Smart Hydroponics: Advancing Urban Farming Solutions","abstract":"The incorporation of smart technologies in agriculture has revolutionized the old way of farming, which, in modern times, is now more about integrating an urban space. This article presents a real-time tracking and control system for a smart hydroponics setup, utilizing the Blynk application and website, which provides easy access to critical environmental data and controls for end-users. The system is designed to give users straightforward access to essential environmental data and controls. It tracks important factors such as temperature, humidity, and water level to maintain optimal conditions for plant growth. It also allows for both manual and remote activation of the water circulation motor, which can be managed via the Blynk mobile application or web interface. By leveraging the flexibility of IoT and cloud-based technologies, the system provides real-time updates and automated responses to environmental changes, thereby significantly enhancing resource management and crop yield. This article examines the design, functionality, and user experience of the smart hydroponics system, illustrating how real-time control and tracking can facilitate more efficient and sustainable urban farming practices. This points to that such systems could empower users to control and optimize their hydroponics from anywhere, regardless of location, for the realization of both convenience and resource efficiency.","author":[{"family":"Kumar","given":"Maanya"},{"family":"Bhat","given":"Sudarshan"},{"family":"Asuti","given":"Manjunath"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccca66364.2025.11325708","URL":"https://doi.org/10.1109/iccca66364.2025.11325708","source":"crossref"},{"id":"doi:10.1109/icetci67340.2025.11257917","type":"article-journal","title":"An IoT-Driven Smart Agriculture System for Precision Farming and Sustainable Crop Monitoring","abstract":"This paper presents SEED, a smart agriculture system that integrates IoT, AI, and ML to assist farmers with real-time soil monitoring and crop suggestion based on IoT, artificial intelligence (AI), and machine learning (ML). The system, in its core, revolves around an ESP32-based hardware module, which includes sensors to measure major soil indicators like nitrogen, phosphorus, potassium, pH, temperature, and moisture. The data gathered is passed on to a mobile app, which applies ML models and AI tools such as Google Gemini to provide tailored recommendations for crops, fertilizer schedules, irrigation systems, and plant disease identification. This cross-platform mobile application, developed using Flutter, offers a seamless user interface, including real-time updates, disease detection, an interactive chatbot, and many other useful features. SEED is a simple and affordable solution for farmers. It solves problems like sensor calibration, rural connectivity, and user education needs. With smart tools, SEED empowers farmers to make effective decisions based on real-time information, improving their productivity, reducing costs, and promoting sustainable agriculture.","author":[{"family":"Vinoy","given":"Aby"},{"family":"Joseph","given":"Ashwin"},{"family":"Vijayan","given":"Athira"},{"family":"Thulasidharan","given":"Pillai"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icetci67340.2025.11257917","URL":"https://doi.org/10.1109/icetci67340.2025.11257917","source":"crossref"},{"id":"doi:10.55041/isjem07917","type":"article-journal","title":"Smart Farming Advisor: AI-Based System for Crop Recommendation and Market Prediction","abstract":"ABSTRACT This paper presents an automated approach to smart farming within the domain of precision farming and sustainability. In many farmers face challenges related to unpredictable weather, improper soil management, and using wrong fertilizer, which often lead to reduced productivity and financial losses. To address these issues, the concept of a Smart Farming Advisor System is proposed—an integration of hardware and software technologies that connects field sensors to a cloud-based analytical platform using an ESP32 NodeMCU. The system monitors real-time parameters such as soil moisture, temperature, humidity, light intensity, and NPK nutrient levels, enabling accurate soil health assessment and environmental monitoring. Using IoT and AI technologies, the data collected from multiple sensors is transmitted to a cloud database for intelligent processing. The integrated AI model analyzes this information to recommend optimal crops, predict future market prices, and provide actionable insights for farmers. The system also displays live farm data on a 0.96” OLED screen, including time, temperature, humidity, and alert status, while detailed crop and soil analytics are accessible through a web dashboard Operating on a client–server architecture, the proposed system promotes sustainable agriculture by supporting data-driven decision-making, efficient resource utilization, and enhanced farm profitability. Keywords: IoT, AI Based Smart Farming, NodeMCU, Soil NPK Sensor, Crop Recommendation, Market Prediction, Cloud Dashboard.","author":[{"family":"Sampat","given":"Lohote"},{"family":"Ramhari","given":"Shete"},{"family":"Shakil","given":"Hawaldar"},{"family":"Ankush","given":"Gavande"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/isjem07917","URL":"https://doi.org/10.55041/isjem07917","source":"crossref"},{"id":"doi:10.31316/astro.v4i2.9323","type":"article-journal","title":"IoT-Based Smart Farming System Design for Greenhouse Monitoring in Urban Areas","abstract":"The rapid development of urban areas has led to a significant reduction in agricultural land, creating the need for innovative solutions to meet food demands, especially for fresh vegetables. One promising alternative is urban farming supported by the Internet of Things (IoT). This research aims to design and develop an IoT-based smart farming system for monitoring vegetable crops in urban areas with limited land availability. The system uses a NodeMCU ESP32 as the main controller, an SHT20 sensor to measure temperature and humidity, and a pH sensor to monitor the acidity of the nutrient solution. Sensor data are displayed in real time through an LCD and an Android-based application, and are also used to control an automatic fan to maintain optimal environmental conditions. The research method applied is an experimental approach comprising a literature review, system design, hardware and software implementation, and system testing. Based on the research results, the IoT-based smart farming system was successfully developed and can monitor plant environmental conditions and nutrient solutions in real time via an Android application, with data stored in a database and displayed appropriately. The test results indicate that the system helps users manage vegetable cultivation more efficiently. This system is expected to provide an effective, efficient, and sustainable smart farming solution for urban areas with limited land availability.","author":[{"family":"Sari","given":"Marti"},{"family":"Amalia","given":"Erika"},{"family":"Ciptadi","given":"Prahenusa"},{"family":"Hardyanto","given":"RH"},{"family":"Santoso","given":"Banu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.31316/astro.v4i2.9323","URL":"https://doi.org/10.31316/astro.v4i2.9323","source":"crossref"},{"id":"doi:10.47392/irjaeh.2025.0418","type":"article-journal","title":"Smart Survelliance System for Farming Places","abstract":"This paper develops an IOT smart surveillance system, aimed at providing real-time monitoring and security solutions for agricultural applications. Unfortunately, many of the crops get damaged due to theft and in most cases do not survive due to weather changes. The project works through integration of Arduino with the different sensors such as that of soil moisture and DHT11 compression with object detection along with automation like rain shed mechanism to provide real-time security and environmental monitoring for these related fields. That is on the flip side, to reduce human interruption, make good on the resource, and keep the crops in good health which all contributes to modernizing and sustaining agriculture. Such protection includes a rain shed mechanism for shielding crops from unanticipated weather occasions and soil moisture sensors for optimizing water application. The DHT11 monitors temperature and humidity to get an optimum environment for crop growth. In the case of security, the object detection takes photos and sends them via mobile to farmers, making surveillance real time. Therefore, the entire system intends to minimize human intervention, optimally utilize resources, and ensure healthy security of crops; thus modernizing agricultural practices while making environmental issues sustainable.","author":[{"family":"Kishorekumar","given":"PV"},{"family":"Srinivas","given":"Chalasani"},{"family":"Ambati","given":"Shyamkarthik"},{"family":"Rangu","given":"Ajaysatish"},{"family":"Lala","given":"Madhavi"},{"family":"Jijjuvarapu","given":"Jaivarun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47392/irjaeh.2025.0418","URL":"https://doi.org/10.47392/irjaeh.2025.0418","source":"crossref"},{"id":"doi:10.33480/jitk.v11i4.7481","type":"article-journal","title":"EVALUATION OF ANN- LEVENBERG MARQUARDT MODELS FOR FAULT DETECTION IN SMART FARMING SYSTEM","abstract":"Sensor readings in open field monitoring systems are influenced by disruptions, degradation, and operational unreliability. These conditions may result in inaccurate data and unreliable system decisions. However, existing studies focus on detection accuracy and rarely examine the trade-off between detection performance and computational efficiency of Artificial Neural Networks trained using the Levenberg–Marquardt algorithm (ANN–LM) in smart farming environments. This study evaluates the fault-detection capability of ANN–LM for soil moisture sensor readings by analyzing both detection performance (accuracy, precision, recall, and F1-score) and computational efficiency (execution time, CPU usage, and memory consumption), thereby addressing the trade-off between performance and efficiency. Baseline data, hypothetical dataset that represent the soil moisture reading from a smart chilli pepper farming system in normal operating conditions, were used to generate fault-injected datasets representing four common faults: drift, bias, spike, and malfunction. The ANN–LM model was evaluated under five fault-detection scenarios with different network architectures. Model performance was evaluated using accuracy, precision, recall, and F1-score, while computational cost was assessed through execution time, CPU usage, and memory usage. The results show that ANN–LM achieves an accuracy of 0.996–0.999, precision of 1.000, recall of 0.987–1.000, and F1-scores of 0.992–1.000 across all scenarios. Simple ANN architectures give accuracy of 0.997 with reduced execution time (33.74 seconds) and lower CPU usage (50.50%) compared to more complex architectures that require 591.88 seconds and 78.40% CPU usage. Therefore, these results indicate point out that ANN–LM is suitable for smart agricultural systems under resource-constrained conditions.","author":[{"family":"Wardhani","given":"Luh"},{"family":"Buono","given":"Agus"},{"family":"Wahjuni","given":"Sri"},{"family":"Syukur","given":"Muhamad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.33480/jitk.v11i4.7481","URL":"https://doi.org/10.33480/jitk.v11i4.7481","source":"crossref"},{"id":"doi:10.1109/discover66922.2025.11259034","type":"article-journal","title":"Smart Farming Assistant for Crop Advice and Disease Detection","abstract":"Agriculture remains the primary livelihood for millions in developing regions, yet smallholder and urban farmers continue to face persistent challenges such as low crop productivity, inefficient resource utilization, and limited access to modern agricultural technologies. This paper presents the Smart Farming Assistant, an integrated and cost-effective platform that leverages the Internet of Things (IoT) and Artificial Intelligence (AI) to enable data-driven decisionmaking in agriculture. The system collects real-time environmental data such as soil moisture, temperature, and humidity using IoT sensors, and applies machine learning models to deliver personalized crop and fertilizer recommendations. It also supports early plant disease detection through image analysis powered by deep learning. Designed with a focus on affordability, accessibility, and ease of use, the assistant empowers small-scale farmers to improve yield, optimize inputs, and adopt sustainable farming practices. This study details the system's architecture, implementation, experimental results, and outlines future enhancements to improve scalability and functionality.","author":[{"family":"Salian","given":"Supriya"},{"family":"Ritesh"},{"family":"Dsouza","given":"Ria"},{"family":"Poojari","given":"Prathiksha"},{"family":"Haldankar","given":"Khushi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/discover66922.2025.11259034","URL":"https://doi.org/10.1109/discover66922.2025.11259034","source":"crossref"},{"id":"doi:10.1109/icicnis66685.2025.11315591","type":"article-journal","title":"GreenGrow AI: AI-based Smart Farming and Organic Waste Management","abstract":"The Abstract Artificial Intelligence (AI) in agriculture has offered an opportunity to have an efficient and sustainable agricultural practice. The drawbacks that farmers in the rural areas are facing are poor use of biofertilizers, poor classification of agricultural wastes and absence of a compost tracking system. This paper proposes how sustainable farming can be optimized using the help of AI-based tools and inclusive design, namely a Smart Farming Assistant mobile application. The proposed application will have three fundamental modules: (1) Biofertilizer Recommendation module, which depends on a fixed look-up table of 20 soil types and 20 crops to select the best biofertilizer, (2) the AI-based waste Image-Classification Module, which uses a Convolutional Neural Network (CNN) to classify either compostable or non-compostable waste by analysing the waste image, (3) a Real-Time Compost Tracker that predicts how well the compost is made based on five user-oblig This is an application that makes it easy to use the multilingual interfaces, voice assistants, and audio assistance to enable rural farmers to use it easily. This is a solution to significant gaps in the delivery of scalability to low-resource environments and smart Agriculture.","author":[{"family":"Sumavarshini","given":"Kolishetty"},{"family":"Goud","given":"BB"},{"family":"Raju","given":"Muntha"},{"family":"Narender","given":"Baikani"},{"family":"Sriram","given":"Nuneti"},{"family":"Ravikumar","given":"Kuntun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icicnis66685.2025.11315591","URL":"https://doi.org/10.1109/icicnis66685.2025.11315591","source":"crossref"},{"id":"doi:10.26656/fr.2017.9(s3).2","type":"article-journal","title":"Development of smart pineapple farming assistant mobile application on identifying diseases in MD2 pineapple cultivation","abstract":"Pineapple (Ananas comosus) is a widely cultivated fruit with various commercial varieties, such as MD2, that meet the high demand for sweet and high-quality pineapples. However, MD2 pineapple cultivation in Malaysia faces challenges related to disease management and monitoring that will lead to losses when controlled effectively. This research aimed to identify diseases in MD2 pineapple cultivation in Malaysia. Next, develop a Smart Pineapple Farming Assistant (SPFA) mobile application using image processing. The ADDIE model was employed for application development, which included analysis, design, development, implementation, and evaluation phases that were done in MFL Enterprise pineapple farm based in Segamat, Johor, by collecting sample images and verifying gathered information with an expert. The SPFA application was well -received by users, as indicated by a System Usability Scale (SUS) score of 71.88, demonstrating positive perceptions of usability. The developed application successfully assists smallholders in disease identification, including bacterial heart rot, deep eye, stem breakage, and mealybug wilt, in facilitating timely management actions. The user-friendly interface and design ensure that even users with low technical knowledge can use it. The SPFA mobile application may contribute a lot to the sustainability and productivity of MD2 pineapple cultivation in Malaysia, benefiting not only smallholders but academicians, citizens and the agricultural industry as a whole.","author":[{"family":"Sadikan","given":"SFN"},{"family":"Sarip","given":"AZ"},{"family":"Pebrian","given":"DE"},{"family":"Marjudi","given":"S"},{"family":"Salamat","given":"MA"},{"family":"Setik","given":"R"}],"issued":{"date-parts":[[2025]]},"DOI":"10.26656/fr.2017.9(s3).2","URL":"https://doi.org/10.26656/fr.2017.9(s3).2","source":"crossref"},{"id":"doi:10.55885/jucep.v5i1.475","type":"article-journal","title":"Diversification Products and Digital Marketing as Innovation and Creativepreneurship Smart Farming Community Karangpucung Village","abstract":"Karang Pucung Village, located in the lowlands of Purbalingga Regency, has great potential for fruit and vegetable farming. Agricultural innovation has been developed by millennial farmers, especially in melon cultivation. Since 2015, farmers organized under the ARTANSI CANDRA KAHURIPAN Tourism Awareness Group (POKDARWIS) have cultivated melons using hydroponic methods. This initiative responds to the increasing national demand for fruits and vegetables and growing health awareness. However, the main problems faced by partners include a lack of knowledge in agricultural product processing, packaging, and marketing. These limitations hinder the optimal utilization of melon harvests. Additionally, partners struggle with online marketing and bookkeeping. Proper accounting is essential for running a sustainable business, yet partners have not implemented systematic and detailed financial recording either manually or digitally. To address these issues, participatory training and mentoring methods are proposed. This approach involves partners directly in each step of the process, including problem identification, analysis of possible actions, action planning, and implementation. This “bottom-up” method ensures that the actions taken are appropriate, targeted, and practical for addressing real problems faced by the community. The result of this community service activity is the ability of local farmers to process melons into melon chips, a product with market potential at both the local and national levels. Through this approach, the community not only enhances its economic value but also strengthens its business practices in packaging, marketing, and financial management, promoting sustainability and independence in the agricultural sector.","author":[{"family":"Mulasiwi","given":"Cut"},{"family":"Puspasari","given":"Elsa"},{"family":"Noorhidayah","given":"Ratri"},{"family":"Triyono","given":"Bambang"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55885/jucep.v5i1.475","URL":"https://doi.org/10.55885/jucep.v5i1.475","source":"crossref"},{"id":"doi:10.1109/icacrs67045.2025.11324268","type":"article-journal","title":"AgriQDL: A Quantum-Driven Deep Learning Model for Climate-Resilient Smart Farming","abstract":"The accelerated growth of Artificial Intelligence (AI) and Quantum Computing (QC) has unlocked transformative potential for solving complex challenges in climate-adaptive and energy-efficient agriculture. Traditional deep learning frameworks often struggle to manage the massive heterogeneity, temporal variance, and computational intensity inherent in multi-source agro-climatic data. To overcome these limitations, this work introduces AgriQDL (Quantum-Driven Deep Learning for Agriculture) — an advanced hybrid paradigm that combines the superior pattern recognition of deep neural networks with the parallel computational capabilities of quantum circuits. First Objective focuses on integrating Variational Quantum Circuits (VQCs) with deep architectures to accelerate learning across high-dimensional satellite, soil, weather, and IoT-sensor datasets. The second objective aims to employ quantum-inspired backpropagation and Quantum Generative Adversarial Networks (QGANs) for efficient feature learning and synthetic data generation in regions with sparse ground-truth samples. The final objective embeds the AgriQDL framework into a Federated Learning (FL) environment to ensure secure, decentralized model training that preserves community data privacy while supporting collaborative intelligence. The proposed AgriQDL architecture integrates quantum-enhanced convolutional and recurrent layers for spatial–temporal feature extraction, where VQCs perform high-speed state transformations and gradient evaluations. The QGAN module supplements limited datasets by generating high-fidelity synthetic samples, thereby mitigating regional data scarcity and improving model generalization. The FL-enabled deployment ensures that each agricultural community trains its local model while contributing encrypted gradients to a global quantum-assisted model aggregator, achieving scalability and confidentiality simultaneously. Comprehensive evaluations were conducted across multiple agro-climatic zones using diverse datasets encompassing satellite imagery, soil moisture indices, humidity, and crop-yield records. Comparative analysis against conventional deep learning baselines — including CNN, LSTM, and hybrid CNN-BiLSTM models — demonstrates that AgriQDL achieves an average accuracy improvement of 18%, reduces training time by up to 45%, and enhances resilience to climate variability and data imbalance. These outcomes highlight AgriQDL’s capability to perform rapid, resource-efficient agricultural analytics while maintaining strong privacy guarantees. The results establish AgriQDL as a robust foundation for next-generation quantum–AI-driven precision agriculture systems.","author":[{"family":"Mary","given":"JJ"},{"family":"Bsarvesan"},{"family":"Priyadharsini","given":"R"},{"family":"Nurmatovich","given":"Hayitov"},{"family":"Madaminov","given":"Bekzod"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icacrs67045.2025.11324268","URL":"https://doi.org/10.1109/icacrs67045.2025.11324268","source":"crossref"},{"id":"doi:10.1201/9781003743767-89","type":"article-journal","title":"Revolutionising Farming with AI-Enhanced Image Processing: 6G Communication for Real-Time Crop Health Monitoring","abstract":"Remote areas have witnessed optimal solutions for challenges in traditional agriculture monitoring by integrating 6G network with Artificial Intelligence (AI). In this study a novel approach has been developed by combining ultra-fast, low-latency 6G connectivity with AI-powered image analysis real-time crop health assessment. Our proposed system helps in accurate crop health analysis by processing images captured by AI sensors and drones. The findings of our study implicate the AI powered image interpretation and the use of ultra-high speed 6G for transmitting large volume of image data. Our study has potential in improving agricultural related costs, agricultural productivity, and reducing running costs in the most isolated regions. The potential impact on precision agriculture has been demonstrated in this paper by providing real time accurate information to farmers.","author":[{"family":"Gupta","given":"Anuj"},{"family":"Lakshay"},{"family":"Tom","given":"Okure"},{"family":"Pankaj"},{"family":"Kumar","given":"Rajinder"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003743767-89","URL":"https://doi.org/10.1201/9781003743767-89","source":"crossref"},{"id":"doi:10.5281/zenodo.19032317","type":"article-journal","title":"Modern Agronomy: Science, Soil & Sustainability","abstract":"Agronomy, once confined to the fundamentals of crop production and soil management, has now transformed into a dynamic, data-driven science that integrates ecology, genetics, climate modeling and advanced technology. The 21st century presents agriculture with a paradox: feeding an expanding global population while conserving natural resources, mitigating climate change and restoring ecological balance. In this context, Modern Agronomy: Science, Soil & Sustainability brings together contemporary perspectives, innovative practices and cross-disciplinary insights that redefine the very essence of sustainable crop production. This volume is conceived to serve as both a scholarly reference and a practical guide for researchers, academicians, policy makers, extension professionals and advanced students of agricultural science. The chapters, contributed by experts from diverse disciplines, collectively explore how modern agronomy can function as a bridge between traditional wisdom and scientific innovation. From the soil microbiome beneath our feet to the satellites orbiting above, every dimension of the agricultural ecosystem is now interconnected through science and technology. This book captures that continuum. The opening chapters trace the evolution and scope of agronomy, laying a conceptual foundation for understanding its modern relevance. Subsequent sections delve into the biophysical core of agriculture—soil health, nutrient cycling and water management—while emphasizing the necessity of maintaining soil vitality as the heart of sustainable farming. The text advances into precision agronomy, climate-smart practices and the integration of digital technologies, highlighting how drones, sensors and artificial intelligence are revolutionizing field-level decisions and resource efficiency. Each topic is treated not as an isolated innovation but as a component of an integrated farming system shaped by environmental stewardship and economic viability. Equally important are the discussions on agroecology, organic and natural farming, biodiversity conservation and climate resilience. The contributors underscore how regenerative and ecosystem-based approaches can sustain productivity without compromising the planet’s ecological integrity. The inclusion of chapters on nutritional agronomy, carbon farming and digital data ecosystems reflects the widening scope of the discipline—from increasing yield to enhancing the quality, safety and traceability of food. The final chapter synthesizes insights on policy, education and future directions, envisioning a roadmap for “Agronomy 2040,” where sustainability is not an aspiration but an inherent design principle of agriculture. In compiling this work, our intent has been to encourage holistic thinking. Agronomy today cannot be understood solely in terms of inputs and outputs; it must be seen through the lens of systems—biological, technological and socio-economic. The contributors to this volume have meticulously documented experiments, field models and policy frameworks that illustrate real-world transitions from conventional to sustainable practices. The cross-referenced tables, figures and case studies embedded within the chapters aim to make this book a useful reference for teaching, research and field application alike. We express our sincere gratitude to all authors, reviewers and collaborators whose expertise and commitment have shaped this publication. Their combined experience—from laboratory research to field implementation—has enriched every chapter. We also acknowledge the contributions of young scientists, students and extension workers who are redefining the practice of agronomy through innovation, passion and on-ground experimentation. Their work embodies the spirit of this book: science in the service of sustainability. We hope Modern Agronomy: Science, Soil & Sustainability will inspire its readers to view agronomy not merely as a branch of agricultural science but as a vital d","author":[{"family":"Haribhushan","given":"Dr"},{"family":"Saha","given":"Dr"},{"family":"Singh","given":"Dr"},{"family":"Raju","given":"Mr"},{"family":"Zimik","given":"Dr"},{"family":"Kalita","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19032317","URL":"https://doi.org/10.5281/zenodo.19032317","source":"datacite"},{"id":"doi:10.5281/zenodo.19032318","type":"article-journal","title":"Modern Agronomy: Science, Soil & Sustainability","abstract":"Agronomy, once confined to the fundamentals of crop production and soil management, has now transformed into a dynamic, data-driven science that integrates ecology, genetics, climate modeling and advanced technology. The 21st century presents agriculture with a paradox: feeding an expanding global population while conserving natural resources, mitigating climate change and restoring ecological balance. In this context, Modern Agronomy: Science, Soil & Sustainability brings together contemporary perspectives, innovative practices and cross-disciplinary insights that redefine the very essence of sustainable crop production. This volume is conceived to serve as both a scholarly reference and a practical guide for researchers, academicians, policy makers, extension professionals and advanced students of agricultural science. The chapters, contributed by experts from diverse disciplines, collectively explore how modern agronomy can function as a bridge between traditional wisdom and scientific innovation. From the soil microbiome beneath our feet to the satellites orbiting above, every dimension of the agricultural ecosystem is now interconnected through science and technology. This book captures that continuum. The opening chapters trace the evolution and scope of agronomy, laying a conceptual foundation for understanding its modern relevance. Subsequent sections delve into the biophysical core of agriculture—soil health, nutrient cycling and water management—while emphasizing the necessity of maintaining soil vitality as the heart of sustainable farming. The text advances into precision agronomy, climate-smart practices and the integration of digital technologies, highlighting how drones, sensors and artificial intelligence are revolutionizing field-level decisions and resource efficiency. Each topic is treated not as an isolated innovation but as a component of an integrated farming system shaped by environmental stewardship and economic viability. Equally important are the discussions on agroecology, organic and natural farming, biodiversity conservation and climate resilience. The contributors underscore how regenerative and ecosystem-based approaches can sustain productivity without compromising the planet’s ecological integrity. The inclusion of chapters on nutritional agronomy, carbon farming and digital data ecosystems reflects the widening scope of the discipline—from increasing yield to enhancing the quality, safety and traceability of food. The final chapter synthesizes insights on policy, education and future directions, envisioning a roadmap for “Agronomy 2040,” where sustainability is not an aspiration but an inherent design principle of agriculture. In compiling this work, our intent has been to encourage holistic thinking. Agronomy today cannot be understood solely in terms of inputs and outputs; it must be seen through the lens of systems—biological, technological and socio-economic. The contributors to this volume have meticulously documented experiments, field models and policy frameworks that illustrate real-world transitions from conventional to sustainable practices. The cross-referenced tables, figures and case studies embedded within the chapters aim to make this book a useful reference for teaching, research and field application alike. We express our sincere gratitude to all authors, reviewers and collaborators whose expertise and commitment have shaped this publication. Their combined experience—from laboratory research to field implementation—has enriched every chapter. We also acknowledge the contributions of young scientists, students and extension workers who are redefining the practice of agronomy through innovation, passion and on-ground experimentation. Their work embodies the spirit of this book: science in the service of sustainability. We hope Modern Agronomy: Science, Soil & Sustainability will inspire its readers to view agronomy not merely as a branch of agricultural science but as a vital d","author":[{"family":"Haribhushan","given":"Dr"},{"family":"Saha","given":"Dr"},{"family":"Singh","given":"Dr"},{"family":"Raju","given":"Mr"},{"family":"Zimik","given":"Dr"},{"family":"Kalita","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19032318","URL":"https://doi.org/10.5281/zenodo.19032318","source":"datacite"},{"id":"doi:10.5281/zenodo.19032024","type":"article-journal","title":"Innovations in Plant Protection: Technology for Sustainable Plant Health","abstract":"Plant health stands at the heart of global food security, environmental stability, and the livelihood of millions of farming communities. As the world faces unprecedented agricultural challenges—ranging from climate change and emerging pests to shrinking arable land and the demand for residue-free food—there is an urgent need to rethink how crops are grown and protected. Traditional plant protection strategies, though effective in the past, are no longer sufficient on their own. Today’s scenario calls for innovative, sustainable, and integrated technological solutions that not only manage pests and diseases but also protect biodiversity, support ecosystem services, and ensure long-term agricultural resilience. Innovations in Plant Protection Technology for Sustainable Plant Health has been conceptualized with this very aspiration. This book brings together contemporary scientific insights, field-tested technologies, and emerging innovations that are redefining the landscape of plant protection. It attempts to bridge the gap between research institutions, extension systems, farmers, and agri-industry by presenting reliable, practical, and scalable solutions suited to the diverse agro-ecologies of India and beyond. The authors—Dr. Abhijit Debnath, Dr. T. Vanlalngurzauva, Dr. L. Chanu Langlentombi, Mahesh Vitthal Mahajan, Dr. Kamal Kumar Pande, and Dr. Erayya—collectively bring decades of experience across plant pathology, entomology, agronomy, integrated pest management, climate-smart agriculture, and field extension. Their combined expertise has shaped a volume that is both scholarly and application-oriented. Each chapter is curated to help researchers, students, extension personnel, and progressive farmers understand not just what technologies exist, but also why and how they can be adopted in real-world situations. The book covers a wide canvas: advances in biological control agents and microbial formulations; precision pest surveillance using IoT devices and AI-driven analytics; drone-based pesticide application; climate-responsive pest forecasting models; nanotechnology in plant protection; innovations in residue-free crop management; and the expanding role of genomics, remote sensing, and decision-support tools in early detection of plant diseases. Special attention is given to low-cost, eco-friendly technologies and indigenous knowledge systems that can support small and marginal farmers, ensuring that sustainability aligns with socio-economic feasibility. In curating this content, the authors have been guided by two core principles: sustainability and scientific integrity. Sustainable plant protection goes beyond reducing chemical pesticide use—it requires a holistic approach that integrates cultural, biological, mechanical, and digital tools in ways that preserve soil health, conserve beneficial insects, and minimize ecological disturbance. This book emphasizes a balanced, systems-based approach rooted in Integrated Pest Management (IPM), strengthened by modern innovations that enhance precision, safety, and efficiency. The global movement toward environmentally responsible agriculture presents both challenges and opportunities. On one hand, climate change intensifies the frequency of pest outbreaks, introduces invasive species, and disrupts natural biological control mechanisms. On the other, new technologies—such as machine learning for pest prediction, RNA interference-based pest suppression, and advanced diagnostic kits—offer promising pathways for proactive plant protection. This book attempts to weave these diverse threads into a coherent narrative, helping readers appreciate the interconnected nature of plant health management. Another unique feature of this book is its emphasis on practical implementation. Each technological advancement discussed here is accompanied by its benefits, limitations, economic considerations, and field applicability. Real-world case studies, wherever available, demonstrate how innovat","author":[{"family":"Debnath","given":"Dr"},{"family":"Vanlalngurzauva","given":"Dr"},{"family":"Langlentombi","given":"Dr"},{"family":"Mahajan","given":"Mahesh"},{"family":"Pande","given":"Dr"},{"family":"Erayya","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19032024","URL":"https://doi.org/10.5281/zenodo.19032024","source":"datacite"},{"id":"doi:10.5281/zenodo.19032025","type":"article-journal","title":"Innovations in Plant Protection: Technology for Sustainable Plant Health","abstract":"Plant health stands at the heart of global food security, environmental stability, and the livelihood of millions of farming communities. As the world faces unprecedented agricultural challenges—ranging from climate change and emerging pests to shrinking arable land and the demand for residue-free food—there is an urgent need to rethink how crops are grown and protected. Traditional plant protection strategies, though effective in the past, are no longer sufficient on their own. Today’s scenario calls for innovative, sustainable, and integrated technological solutions that not only manage pests and diseases but also protect biodiversity, support ecosystem services, and ensure long-term agricultural resilience. Innovations in Plant Protection Technology for Sustainable Plant Health has been conceptualized with this very aspiration. This book brings together contemporary scientific insights, field-tested technologies, and emerging innovations that are redefining the landscape of plant protection. It attempts to bridge the gap between research institutions, extension systems, farmers, and agri-industry by presenting reliable, practical, and scalable solutions suited to the diverse agro-ecologies of India and beyond. The authors—Dr. Abhijit Debnath, Dr. T. Vanlalngurzauva, Dr. L. Chanu Langlentombi, Mahesh Vitthal Mahajan, Dr. Kamal Kumar Pande, and Dr. Erayya—collectively bring decades of experience across plant pathology, entomology, agronomy, integrated pest management, climate-smart agriculture, and field extension. Their combined expertise has shaped a volume that is both scholarly and application-oriented. Each chapter is curated to help researchers, students, extension personnel, and progressive farmers understand not just what technologies exist, but also why and how they can be adopted in real-world situations. The book covers a wide canvas: advances in biological control agents and microbial formulations; precision pest surveillance using IoT devices and AI-driven analytics; drone-based pesticide application; climate-responsive pest forecasting models; nanotechnology in plant protection; innovations in residue-free crop management; and the expanding role of genomics, remote sensing, and decision-support tools in early detection of plant diseases. Special attention is given to low-cost, eco-friendly technologies and indigenous knowledge systems that can support small and marginal farmers, ensuring that sustainability aligns with socio-economic feasibility. In curating this content, the authors have been guided by two core principles: sustainability and scientific integrity. Sustainable plant protection goes beyond reducing chemical pesticide use—it requires a holistic approach that integrates cultural, biological, mechanical, and digital tools in ways that preserve soil health, conserve beneficial insects, and minimize ecological disturbance. This book emphasizes a balanced, systems-based approach rooted in Integrated Pest Management (IPM), strengthened by modern innovations that enhance precision, safety, and efficiency. The global movement toward environmentally responsible agriculture presents both challenges and opportunities. On one hand, climate change intensifies the frequency of pest outbreaks, introduces invasive species, and disrupts natural biological control mechanisms. On the other, new technologies—such as machine learning for pest prediction, RNA interference-based pest suppression, and advanced diagnostic kits—offer promising pathways for proactive plant protection. This book attempts to weave these diverse threads into a coherent narrative, helping readers appreciate the interconnected nature of plant health management. Another unique feature of this book is its emphasis on practical implementation. Each technological advancement discussed here is accompanied by its benefits, limitations, economic considerations, and field applicability. Real-world case studies, wherever available, demonstrate how innovat","author":[{"family":"Debnath","given":"Dr"},{"family":"Vanlalngurzauva","given":"Dr"},{"family":"Langlentombi","given":"Dr"},{"family":"Mahajan","given":"Mahesh"},{"family":"Pande","given":"Dr"},{"family":"Erayya","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19032025","URL":"https://doi.org/10.5281/zenodo.19032025","source":"datacite"},{"id":"doi:10.5281/zenodo.19031618","type":"article-journal","title":"Horticultural Frontiers: Modern Practices for Productivity, Profitability and Sustainability","abstract":"Horticulture today stands at a critical juncture. As the global population continues to rise, pressure on land, water, and natural resources has intensified, while consumer demand for safe, nutritious, and high-quality horticultural produce has grown steadily. At the same time, climate variability, soil degradation, pest and disease outbreaks, and market uncertainties pose serious challenges to growers, researchers, and policymakers alike. In this dynamic context, horticulture must evolve beyond traditional production systems and embrace modern, science-based, and sustainable practices that enhance productivity, profitability, and environmental stewardship. Horticultural Frontiers: Modern Practices for Productivity, Profitability, and Sustainability is an attempt to respond to this urgent need. This book has been conceived as a comprehensive resource that bridges the gap between scientific innovation and practical application. It brings together contemporary knowledge, field-tested technologies, and forward-looking approaches that can help transform horticultural systems into resilient, efficient, and economically viable enterprises. The emphasis throughout the book is not merely on increasing yields, but on achieving balanced growth—where productivity is aligned with resource conservation, ecological sustainability, and improved livelihoods for farmers and stakeholders across the value chain. Modern horticulture is no longer confined to conventional cultivation methods. Advances in plant breeding, protected cultivation, precision farming, micro-irrigation, integrated nutrient and pest management, post-harvest handling, and digital agriculture have redefined the scope of horticultural production. These innovations offer immense opportunities, particularly for small and marginal farmers, to optimize inputs, reduce losses, and access better markets. However, the adoption of such technologies requires clear understanding, localized adaptation, and capacity building. This book aims to present these modern practices in a structured and accessible manner, enabling readers to grasp both the scientific principles and their practical relevance. Sustainability forms the core philosophy of this volume. With growing awareness of environmental concerns and the impacts of climate change, sustainable horticulture has become not just desirable but essential. The chapters highlight approaches that promote efficient use of water and nutrients, conservation of soil health, biodiversity enhancement, and reduction of chemical dependency. Climate-smart practices, organic and natural farming concepts, and eco-friendly technologies are discussed with the intent of fostering long-term sustainability without compromising productivity or profitability. By integrating ecological principles with economic considerations, the book underscores the possibility of achieving sustainable intensification in horticulture. Profitability is another central theme addressed in this work. For horticulture to thrive, it must be economically rewarding for producers. Beyond production technologies, the book emphasizes value addition, post-harvest management, processing, storage, packaging, branding, and market linkage strategies that can significantly enhance farmers’ income. Understanding market trends, quality standards, and supply chain dynamics is increasingly important in a competitive and globalized agricultural economy. The content of this book is designed to help readers appreciate these aspects and make informed decisions that translate knowledge into tangible economic gains. The strength of Horticultural Frontiers lies in its multidisciplinary and collaborative approach. The authors bring together diverse expertise spanning horticultural science, agronomy, sustainability, extension, and applied research. Their collective experience in teaching, research, and field engagement ensures that the book is grounded in real-world challenges and solutions. Care has been ","author":[{"family":"Debnath","given":"Dr"},{"family":"Langpoklakpam","given":"Basu"},{"family":"Suklabaidya","given":"Dr"},{"family":"Kikon","given":"Ronchamo"},{"family":"Vanlalhmuliana","given":"Dr"},{"family":"Sisi","given":"Mrs"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19031618","URL":"https://doi.org/10.5281/zenodo.19031618","source":"datacite"},{"id":"doi:10.5281/zenodo.19031619","type":"article-journal","title":"Horticultural Frontiers: Modern Practices for Productivity, Profitability and Sustainability","abstract":"Horticulture today stands at a critical juncture. As the global population continues to rise, pressure on land, water, and natural resources has intensified, while consumer demand for safe, nutritious, and high-quality horticultural produce has grown steadily. At the same time, climate variability, soil degradation, pest and disease outbreaks, and market uncertainties pose serious challenges to growers, researchers, and policymakers alike. In this dynamic context, horticulture must evolve beyond traditional production systems and embrace modern, science-based, and sustainable practices that enhance productivity, profitability, and environmental stewardship. Horticultural Frontiers: Modern Practices for Productivity, Profitability, and Sustainability is an attempt to respond to this urgent need. This book has been conceived as a comprehensive resource that bridges the gap between scientific innovation and practical application. It brings together contemporary knowledge, field-tested technologies, and forward-looking approaches that can help transform horticultural systems into resilient, efficient, and economically viable enterprises. The emphasis throughout the book is not merely on increasing yields, but on achieving balanced growth—where productivity is aligned with resource conservation, ecological sustainability, and improved livelihoods for farmers and stakeholders across the value chain. Modern horticulture is no longer confined to conventional cultivation methods. Advances in plant breeding, protected cultivation, precision farming, micro-irrigation, integrated nutrient and pest management, post-harvest handling, and digital agriculture have redefined the scope of horticultural production. These innovations offer immense opportunities, particularly for small and marginal farmers, to optimize inputs, reduce losses, and access better markets. However, the adoption of such technologies requires clear understanding, localized adaptation, and capacity building. This book aims to present these modern practices in a structured and accessible manner, enabling readers to grasp both the scientific principles and their practical relevance. Sustainability forms the core philosophy of this volume. With growing awareness of environmental concerns and the impacts of climate change, sustainable horticulture has become not just desirable but essential. The chapters highlight approaches that promote efficient use of water and nutrients, conservation of soil health, biodiversity enhancement, and reduction of chemical dependency. Climate-smart practices, organic and natural farming concepts, and eco-friendly technologies are discussed with the intent of fostering long-term sustainability without compromising productivity or profitability. By integrating ecological principles with economic considerations, the book underscores the possibility of achieving sustainable intensification in horticulture. Profitability is another central theme addressed in this work. For horticulture to thrive, it must be economically rewarding for producers. Beyond production technologies, the book emphasizes value addition, post-harvest management, processing, storage, packaging, branding, and market linkage strategies that can significantly enhance farmers’ income. Understanding market trends, quality standards, and supply chain dynamics is increasingly important in a competitive and globalized agricultural economy. The content of this book is designed to help readers appreciate these aspects and make informed decisions that translate knowledge into tangible economic gains. The strength of Horticultural Frontiers lies in its multidisciplinary and collaborative approach. The authors bring together diverse expertise spanning horticultural science, agronomy, sustainability, extension, and applied research. Their collective experience in teaching, research, and field engagement ensures that the book is grounded in real-world challenges and solutions. Care has been ","author":[{"family":"Debnath","given":"Dr"},{"family":"Langpoklakpam","given":"Basu"},{"family":"Suklabaidya","given":"Dr"},{"family":"Kikon","given":"Ronchamo"},{"family":"Vanlalhmuliana","given":"Dr"},{"family":"Sisi","given":"Mrs"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19031619","URL":"https://doi.org/10.5281/zenodo.19031619","source":"datacite"},{"id":"doi:10.5281/zenodo.19031136","type":"article-journal","title":"Smart Livestock Farming: Innovations and Low-Cost Technologies for Rural Farmers of North East India","abstract":"The North Eastern Region of India—rich in biodiversity, culture, and community resilience—has always nurtured distinctive models of farming. Livestock, in particular, sits at the center of this mosaic: as a store of wealth for smallholders; a daily source of nutrition for rural families; and a critical engine for women’s enterprises and youth livelihoods. Yet the region’s producers continue to face familiar constraints—fragmented markets, high input costs, climate variability, animal disease risks, and limited last-mile services. This book, Smart Livestock Farming: Innovations and Low-Cost Technologies for Rural Farmers of North East, was conceived to answer a simple, practical question: What works here, and how can it be done affordably, step by step, with the materials and support systems farmers already have or can realistically access? As editors, our intent is pragmatic. We emphasize do-able innovations over expensive prototypes, evidence over theory, and region-specific adaptation over one-size-fits-all solutions. The chapters foreground tools and practices that can be built, repaired, and scaled locally: low-cost sensors and data logs that run on phone batteries; piggery and backyard poultry designs that use bamboo, shade nets, and recycled materials; fodder plans that lean on the region’s remarkable perennial diversity; and bio-based health and waste-to-wealth solutions that cut costs while strengthening biosecurity and soil fertility. At each step, we ask: What is the minimum viable improvement a farmer can adopt this season to reduce risk, raise productivity, and capture a better price? The eight states of the North East present a unique operating environment: hilly terrains, high rainfall windows, periodic floods and heat spells, dispersed settlements, and dynamic cross-border markets. Supply chains are long; feed and veterinary inputs can be costly; and many farms are small, mixed, and labor-constrained. At the same time, the region benefits from strong community institutions, a tradition of collective labor, and rich indigenous knowledge. These features demand contextualized livestock solutions—ones that are climate-aware, gender-responsive, and compatible with integrated farming systems that combine crops, fisheries, horticulture, and backyard or semi-intensive animal units. We have designed each chapter to function as a field companion rather than a purely academic text. Most chapters open with a “Why it matters” section and then move quickly to checklists, diagrams, and procedural notes. Cost tables are presented in a way that farmers, Self-Help Groups (SHGs), Farmer Producer Organizations (FPOs), and youth entrepreneurs can adapt to local prices. Case boxes highlight success stories and lessons learned from the region—both what to replicate and what to avoid. Annexes add step-by-step guides (for example, setting up a community silage pit, fabricating a low-cost brooder, or calibrating a home-built data logger), as well as sample records for health, feeding, and financial tracking. The manuscript also pays special attention to convergence—the practical alignment of efforts across ATMA, KVKs, State Animal Husbandry and Veterinary Departments, Fisheries, Rural Development missions, and relevant centrally supported programs. When institutions coordinate, small innovations compound: last-mile vaccination improves survivability; better feed planning and ration balancing improve growth; simple hygiene and waste management lower morbidity; and market facilitation helps producers capture value in organized and informal channels alike. We have therefore included pointers on how field teams can braid technical assistance with credit linkages, procurement, and extension events to accelerate adoption at scale. We envision this book in the hands of farm families, SHG and FPO leaders, youth entrepreneurs, community resource persons, extension workers, and students. KVK scientists and state line departments may find the conso","author":[{"family":"Zeshmarani","given":"Dr"},{"family":"Devi","given":"Dr"},{"family":"Pongen","given":"Dr"},{"family":"Michui","given":"Dr"},{"family":"Rongsensusang","given":"Dr"},{"family":"Temjennungsang","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19031136","URL":"https://doi.org/10.5281/zenodo.19031136","source":"datacite"},{"id":"doi:10.5281/zenodo.19031135","type":"article-journal","title":"Smart Livestock Farming: Innovations and Low-Cost Technologies for Rural Farmers of North East India","abstract":"The North Eastern Region of India—rich in biodiversity, culture, and community resilience—has always nurtured distinctive models of farming. Livestock, in particular, sits at the center of this mosaic: as a store of wealth for smallholders; a daily source of nutrition for rural families; and a critical engine for women’s enterprises and youth livelihoods. Yet the region’s producers continue to face familiar constraints—fragmented markets, high input costs, climate variability, animal disease risks, and limited last-mile services. This book, Smart Livestock Farming: Innovations and Low-Cost Technologies for Rural Farmers of North East, was conceived to answer a simple, practical question: What works here, and how can it be done affordably, step by step, with the materials and support systems farmers already have or can realistically access? As editors, our intent is pragmatic. We emphasize do-able innovations over expensive prototypes, evidence over theory, and region-specific adaptation over one-size-fits-all solutions. The chapters foreground tools and practices that can be built, repaired, and scaled locally: low-cost sensors and data logs that run on phone batteries; piggery and backyard poultry designs that use bamboo, shade nets, and recycled materials; fodder plans that lean on the region’s remarkable perennial diversity; and bio-based health and waste-to-wealth solutions that cut costs while strengthening biosecurity and soil fertility. At each step, we ask: What is the minimum viable improvement a farmer can adopt this season to reduce risk, raise productivity, and capture a better price? The eight states of the North East present a unique operating environment: hilly terrains, high rainfall windows, periodic floods and heat spells, dispersed settlements, and dynamic cross-border markets. Supply chains are long; feed and veterinary inputs can be costly; and many farms are small, mixed, and labor-constrained. At the same time, the region benefits from strong community institutions, a tradition of collective labor, and rich indigenous knowledge. These features demand contextualized livestock solutions—ones that are climate-aware, gender-responsive, and compatible with integrated farming systems that combine crops, fisheries, horticulture, and backyard or semi-intensive animal units. We have designed each chapter to function as a field companion rather than a purely academic text. Most chapters open with a “Why it matters” section and then move quickly to checklists, diagrams, and procedural notes. Cost tables are presented in a way that farmers, Self-Help Groups (SHGs), Farmer Producer Organizations (FPOs), and youth entrepreneurs can adapt to local prices. Case boxes highlight success stories and lessons learned from the region—both what to replicate and what to avoid. Annexes add step-by-step guides (for example, setting up a community silage pit, fabricating a low-cost brooder, or calibrating a home-built data logger), as well as sample records for health, feeding, and financial tracking. The manuscript also pays special attention to convergence—the practical alignment of efforts across ATMA, KVKs, State Animal Husbandry and Veterinary Departments, Fisheries, Rural Development missions, and relevant centrally supported programs. When institutions coordinate, small innovations compound: last-mile vaccination improves survivability; better feed planning and ration balancing improve growth; simple hygiene and waste management lower morbidity; and market facilitation helps producers capture value in organized and informal channels alike. We have therefore included pointers on how field teams can braid technical assistance with credit linkages, procurement, and extension events to accelerate adoption at scale. We envision this book in the hands of farm families, SHG and FPO leaders, youth entrepreneurs, community resource persons, extension workers, and students. KVK scientists and state line departments may find the conso","author":[{"family":"Zeshmarani","given":"Dr"},{"family":"Devi","given":"Dr"},{"family":"Pongen","given":"Dr"},{"family":"Michui","given":"Dr"},{"family":"Rongsensusang","given":"Dr"},{"family":"Temjennungsang","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19031135","URL":"https://doi.org/10.5281/zenodo.19031135","source":"datacite"},{"id":"doi:10.5281/zenodo.19030598","type":"article-journal","title":"Horticultural Frontiers: Innovations in Science and Technology","abstract":"The horticulture sector has always been at the forefront of human civilization, sustaining livelihoods, enriching diets, enhancing aesthetics, and contributing significantly to the global economy. In recent decades, however, the role of horticulture has undergone profound transformation, shaped by technological advancements, environmental challenges, and the urgent need for sustainable resource management. This book, Horticultural Frontiers: Innovations in Science and Technology, is conceived as a comprehensive academic and professional resource that captures the latest developments and cutting-edge research shaping horticultural science today. Horticulture has emerged as a dynamic discipline that not only provides food, nutrition, and health security but also plays a vital role in addressing issues of climate change, rural livelihood enhancement, and urban sustainability. Modern horticulture goes beyond cultivation—it integrates genomics, biotechnology, digital tools, post-harvest innovations, and policy frameworks to create a resilient and future-ready sector. The present volume brings together diverse themes, each addressing a frontier area of science and technology with practical relevance for students, researchers, policymakers, and entrepreneurs. The idea behind this book stems from the recognition that horticulture is no longer confined to traditional practices. The introduction of protected cultivation, vertical farming, and precision greenhouse management has revolutionized production systems, enabling year-round and location-specific cultivation. Genomic tools and molecular breeding strategies are reshaping crop improvement programs, offering possibilities for developing varieties tolerant to pests, diseases, and climate extremes. Similarly, the adoption of nanotechnology and smart irrigation systems is addressing challenges of resource efficiency and environmental sustainability. Post-harvest management has also gained renewed attention as global supply chains demand longer shelf life, value addition, and reduced wastage. Cold chain logistics, coupled with innovative packaging and processing technologies, have become essential for horticultural commodities to remain competitive in domestic and export markets. At the same time, the digital revolution—through artificial intelligence, IoT, big data, and remote sensing—has enabled real-time monitoring of crop health, soil-water dynamics, and market trends, bridging the gap between farm and market. Another critical dimension included in this book is the focus on climate-smart horticulture, where resilience-building against abiotic stresses, pests, and disasters is crucial for sustaining productivity in vulnerable regions. Equally important are chapters on spices, medicinal and aromatic plants, floriculture, and urban horticulture, reflecting the expanding boundaries of the sector and its contribution to wellness industries and green cities. This volume is designed for a diverse readership. For students, it serves as a textbook offering comprehensive insights into both traditional and emerging areas of horticultural science. For researchers, it provides updated knowledge on frontier technologies and methodologies. For policymakers and extension professionals, the book highlights pathways to strengthen national and regional horticultural strategies. Most importantly, for farmers, entrepreneurs, and start-ups, it outlines opportunities to adopt and scale innovations that can enhance profitability, competitiveness, and sustainability. We believe this book will not only enrich academic discourse but also serve as a practical guide to bridge laboratory research and field application. By blending fundamental science with technological advances, it aspires to equip readers with the knowledge and confidence to address contemporary challenges in horticulture. The successful compilation of this book has been made possible by the collective efforts of academicians, scientists, and p","author":[{"family":"Rao","given":"Dr"},{"family":"Kalal","given":"Dr"},{"family":"Rahman","given":"Dr"},{"family":"Das","given":"Dr"},{"family":"Sarkar","given":"Dr"},{"family":"Pande","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19030598","URL":"https://doi.org/10.5281/zenodo.19030598","source":"datacite"},{"id":"doi:10.5281/zenodo.19030599","type":"article-journal","title":"Horticultural Frontiers: Innovations in Science and Technology","abstract":"The horticulture sector has always been at the forefront of human civilization, sustaining livelihoods, enriching diets, enhancing aesthetics, and contributing significantly to the global economy. In recent decades, however, the role of horticulture has undergone profound transformation, shaped by technological advancements, environmental challenges, and the urgent need for sustainable resource management. This book, Horticultural Frontiers: Innovations in Science and Technology, is conceived as a comprehensive academic and professional resource that captures the latest developments and cutting-edge research shaping horticultural science today. Horticulture has emerged as a dynamic discipline that not only provides food, nutrition, and health security but also plays a vital role in addressing issues of climate change, rural livelihood enhancement, and urban sustainability. Modern horticulture goes beyond cultivation—it integrates genomics, biotechnology, digital tools, post-harvest innovations, and policy frameworks to create a resilient and future-ready sector. The present volume brings together diverse themes, each addressing a frontier area of science and technology with practical relevance for students, researchers, policymakers, and entrepreneurs. The idea behind this book stems from the recognition that horticulture is no longer confined to traditional practices. The introduction of protected cultivation, vertical farming, and precision greenhouse management has revolutionized production systems, enabling year-round and location-specific cultivation. Genomic tools and molecular breeding strategies are reshaping crop improvement programs, offering possibilities for developing varieties tolerant to pests, diseases, and climate extremes. Similarly, the adoption of nanotechnology and smart irrigation systems is addressing challenges of resource efficiency and environmental sustainability. Post-harvest management has also gained renewed attention as global supply chains demand longer shelf life, value addition, and reduced wastage. Cold chain logistics, coupled with innovative packaging and processing technologies, have become essential for horticultural commodities to remain competitive in domestic and export markets. At the same time, the digital revolution—through artificial intelligence, IoT, big data, and remote sensing—has enabled real-time monitoring of crop health, soil-water dynamics, and market trends, bridging the gap between farm and market. Another critical dimension included in this book is the focus on climate-smart horticulture, where resilience-building against abiotic stresses, pests, and disasters is crucial for sustaining productivity in vulnerable regions. Equally important are chapters on spices, medicinal and aromatic plants, floriculture, and urban horticulture, reflecting the expanding boundaries of the sector and its contribution to wellness industries and green cities. This volume is designed for a diverse readership. For students, it serves as a textbook offering comprehensive insights into both traditional and emerging areas of horticultural science. For researchers, it provides updated knowledge on frontier technologies and methodologies. For policymakers and extension professionals, the book highlights pathways to strengthen national and regional horticultural strategies. Most importantly, for farmers, entrepreneurs, and start-ups, it outlines opportunities to adopt and scale innovations that can enhance profitability, competitiveness, and sustainability. We believe this book will not only enrich academic discourse but also serve as a practical guide to bridge laboratory research and field application. By blending fundamental science with technological advances, it aspires to equip readers with the knowledge and confidence to address contemporary challenges in horticulture. The successful compilation of this book has been made possible by the collective efforts of academicians, scientists, and p","author":[{"family":"Rao","given":"Dr"},{"family":"Kalal","given":"Dr"},{"family":"Rahman","given":"Dr"},{"family":"Das","given":"Dr"},{"family":"Sarkar","given":"Dr"},{"family":"Pande","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.19030599","URL":"https://doi.org/10.5281/zenodo.19030599","source":"datacite"},{"id":"doi:10.5281/zenodo.18999919","type":"article-journal","title":"AI-Powered Smart Crop Advisory and  Monitoring Platform","abstract":"Agriculture faces increasing challenges due to climate variability, resource limitations, and the need for sustainable productivity. This paper presents an AI-Powered Smart Crop Advisory and Monitoring Platform that leverages artificial intelligence and data analytics to support informed agricultural decision-making. The system analyzes historical crop data, soil characteristics, weath-er patterns, and satellite imagery to assess crop health and growth conditions. Machine learning models generate accurate recommendations for irrigation planning, fertilizer management, pest and disease identification, and yield prediction. Image processing and computer vision techniques enable early detection of crop stress and diseases, reducing potential losses. The platform pro-vides timely, location-specific advisory services to farmers, improving crop quality and resource efficiency. By minimizing dependency on manual expertise and enhancing precision farming practices, the proposed solution contributes to increased agricultural productivity, economic sus-tainability, and food security. The system demonstrates the potential of artificial intelligence as a reliable tool for modern, data-driven agriculture.","author":[{"family":"Devi","given":"Mrs"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18999919","URL":"https://doi.org/10.5281/zenodo.18999919","source":"datacite"},{"id":"doi:10.5281/zenodo.18999918","type":"article-journal","title":"AI-Powered Smart Crop Advisory and  Monitoring Platform","abstract":"Agriculture faces increasing challenges due to climate variability, resource limitations, and the need for sustainable productivity. This paper presents an AI-Powered Smart Crop Advisory and Monitoring Platform that leverages artificial intelligence and data analytics to support informed agricultural decision-making. The system analyzes historical crop data, soil characteristics, weath-er patterns, and satellite imagery to assess crop health and growth conditions. Machine learning models generate accurate recommendations for irrigation planning, fertilizer management, pest and disease identification, and yield prediction. Image processing and computer vision techniques enable early detection of crop stress and diseases, reducing potential losses. The platform pro-vides timely, location-specific advisory services to farmers, improving crop quality and resource efficiency. By minimizing dependency on manual expertise and enhancing precision farming practices, the proposed solution contributes to increased agricultural productivity, economic sus-tainability, and food security. The system demonstrates the potential of artificial intelligence as a reliable tool for modern, data-driven agriculture.","author":[{"family":"Devi","given":"Mrs"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18999918","URL":"https://doi.org/10.5281/zenodo.18999918","source":"datacite"},{"id":"doi:10.5281/zenodo.18998449","type":"article-journal","title":"Real-Time Voice-Enabled IoT Irrigation For Smart Agriculture","abstract":"Real-Time Voice-Enabled IoT Irrigation for Smart Agriculture introduces an advanced automated irrigation system aimed at improving water management and agricultural efficiency. The proposed framework combines IoT-based environmental sensors with real-time data processing and a voice-interaction interface to support intelligent farm operations. Sensors deployed in the field measure soil moisture, ambient temperature, and humidity, transmitting the collected data to a cloud platform for continuous monitoring and analysis. The system automatically activates or deactivates irrigation based on threshold values and real-time conditions, ensuring precise water distribution. Furthermore, a voice-enabled feature allows farmers to access system updates and manage irrigation through simple spoken commands using smartphones or smart devices. This reduces the need for manual supervision and promotes efficient resource utilization. The solution is particularly beneficial for remote agricultural areas where timely intervention is critical. Experimental validation indicates enhanced water conservation, reduced operational effort, and improved crop growth compared to conventional irrigation practices. Overall, the proposed system offers a scalable, economical, and user-friendly approach to achieving sustainable and data-driven smart farming.","author":[{"family":"Kmadhumitha","given":"Ms"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18998449","URL":"https://doi.org/10.5281/zenodo.18998449","source":"datacite"},{"id":"doi:10.5281/zenodo.18998450","type":"article-journal","title":"Real-Time Voice-Enabled IoT Irrigation For Smart Agriculture","abstract":"Real-Time Voice-Enabled IoT Irrigation for Smart Agriculture introduces an advanced automated irrigation system aimed at improving water management and agricultural efficiency. The proposed framework combines IoT-based environmental sensors with real-time data processing and a voice-interaction interface to support intelligent farm operations. Sensors deployed in the field measure soil moisture, ambient temperature, and humidity, transmitting the collected data to a cloud platform for continuous monitoring and analysis. The system automatically activates or deactivates irrigation based on threshold values and real-time conditions, ensuring precise water distribution. Furthermore, a voice-enabled feature allows farmers to access system updates and manage irrigation through simple spoken commands using smartphones or smart devices. This reduces the need for manual supervision and promotes efficient resource utilization. The solution is particularly beneficial for remote agricultural areas where timely intervention is critical. Experimental validation indicates enhanced water conservation, reduced operational effort, and improved crop growth compared to conventional irrigation practices. Overall, the proposed system offers a scalable, economical, and user-friendly approach to achieving sustainable and data-driven smart farming.","author":[{"family":"Kmadhumitha","given":"Ms"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18998450","URL":"https://doi.org/10.5281/zenodo.18998450","source":"datacite"},{"id":"doi:10.5281/zenodo.18997707","type":"article-journal","title":"Smart Aerial Spraying System : An IoT-Integrated Quadcopter For  Sustainable Farming","abstract":"The growing demand for sustainable agricultural practices calls for innovative technologies that enhance productivity while reducing environmental impact. This study introduces a Smart Aerial Spraying System, an IoT-enabled quadcopter developed to support precision farming operations. The system integrates unmanned aerial vehicle (UAV) technology with real-time sensing and cloud-based monitoring to deliver accurate and efficient pesticide and fertilizer application. Embedded sensors collect data on temperature, humidity, soil moisture, and crop conditions, enabling adaptive spray control based on field requirements. Through IoT connectivity, farmers can remotely supervise flight operations and spraying parameters using a mobile or web dashboard. GPS-guided navigation and automated route planning ensure uniform coverage and operational safety. The proposed solution reduces chemical overuse, lowers labor dependency, and minimizes human exposure to hazardous substances. Experimental results indicate enhanced spraying accuracy, better resource utilization, and improved efficiency compared to traditional manual methods, highlighting its potential as a reliable tool for sustainable and intelligent agriculture.","author":[{"family":"Suhirdham","given":"Mrs"},{"family":"Ganesh","given":"M"},{"family":"Gunasivan","given":"S"},{"family":"Manoj","given":"P"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18997707","URL":"https://doi.org/10.5281/zenodo.18997707","source":"datacite"},{"id":"doi:10.5281/zenodo.18997708","type":"article-journal","title":"Smart Aerial Spraying System : An IoT-Integrated Quadcopter For  Sustainable Farming","abstract":"The growing demand for sustainable agricultural practices calls for innovative technologies that enhance productivity while reducing environmental impact. This study introduces a Smart Aerial Spraying System, an IoT-enabled quadcopter developed to support precision farming operations. The system integrates unmanned aerial vehicle (UAV) technology with real-time sensing and cloud-based monitoring to deliver accurate and efficient pesticide and fertilizer application. Embedded sensors collect data on temperature, humidity, soil moisture, and crop conditions, enabling adaptive spray control based on field requirements. Through IoT connectivity, farmers can remotely supervise flight operations and spraying parameters using a mobile or web dashboard. GPS-guided navigation and automated route planning ensure uniform coverage and operational safety. The proposed solution reduces chemical overuse, lowers labor dependency, and minimizes human exposure to hazardous substances. Experimental results indicate enhanced spraying accuracy, better resource utilization, and improved efficiency compared to traditional manual methods, highlighting its potential as a reliable tool for sustainable and intelligent agriculture.","author":[{"family":"Suhirdham","given":"Mrs"},{"family":"Ganesh","given":"M"},{"family":"Gunasivan","given":"S"},{"family":"Manoj","given":"P"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18997708","URL":"https://doi.org/10.5281/zenodo.18997708","source":"datacite"},{"id":"doi:10.5281/zenodo.18978364","type":"article-journal","title":"Synthesis Table on soil carbon data generators/repositories of European capabilities","abstract":"Soil Organic Carbon (SOC) is vital for climate mitigation, agriculture, and ecosystem health. As the EU advances the Carbon Removal and Carbon Farming Certification (CRCF) regulation, reliable SOC assessment and monitoring is essential. This synthesis assesses ten major European data systems—including monitoring networks, farm platforms, and research infrastructures—highlighting their strengths and gaps. While some systems offer high-quality, open data, many face issues with accessibility, interoperability, and standardization. Integration challenges and uneven coverage hinder effective Monitoring, Reporting and Verification (MRV) and policy support. The report recommends aligning data systems with CRCF regulation standards, supporting Application Programming Interface (API) development, and embedding scientific infrastructures into certification frameworks to improve data credibility, reduce costs, and support climate-smart land use.","author":[{"family":"Mollenhauer","given":"Hannes"},{"family":"Fantappiè","given":"Maria"},{"family":"Prazeres Marques","given":"Karina"},{"family":"Miguel-Lago","given":"Mónica"},{"family":"Rajewicz","given":"Paulina"},{"family":"Xu","given":"Hui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18978364","URL":"https://doi.org/10.5281/zenodo.18978364","source":"datacite"},{"id":"doi:10.5281/zenodo.18978365","type":"article-journal","title":"Synthesis Table on soil carbon data generators/repositories of European capabilities","abstract":"Soil Organic Carbon (SOC) is vital for climate mitigation, agriculture, and ecosystem health. As the EU advances the Carbon Removal and Carbon Farming Certification (CRCF) regulation, reliable SOC assessment and monitoring is essential. This synthesis assesses ten major European data systems—including monitoring networks, farm platforms, and research infrastructures—highlighting their strengths and gaps. While some systems offer high-quality, open data, many face issues with accessibility, interoperability, and standardization. Integration challenges and uneven coverage hinder effective Monitoring, Reporting and Verification (MRV) and policy support. The report recommends aligning data systems with CRCF regulation standards, supporting Application Programming Interface (API) development, and embedding scientific infrastructures into certification frameworks to improve data credibility, reduce costs, and support climate-smart land use.","author":[{"family":"Mollenhauer","given":"Hannes"},{"family":"Fantappiè","given":"Maria"},{"family":"Prazeres Marques","given":"Karina"},{"family":"Miguel-Lago","given":"Mónica"},{"family":"Rajewicz","given":"Paulina"},{"family":"Xu","given":"Hui"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18978365","URL":"https://doi.org/10.5281/zenodo.18978365","source":"datacite"},{"id":"doi:10.5281/zenodo.18958752","type":"article-journal","title":"AgriDataValue - Automatic Greenhouse Window Opening","abstract":"AgriDataValue aims to establish itself as the “Game Changer” in Smart Farming digital transformation and agri-environmental monitoring, and strengthen the smart-farming capacities, competitiveness and fair income by introducing an innovative, open source, intelligent and multi-technology, fully distributed Agri-Environment Data Space (ADS). To achieve technological maturity, fast and massive acceptance, AgriDataValue adopts and adapts a multidimensional approach that combines state of the art big data and data-spaces’ technologies (BDVA/ IDSA/ GAIA-X) with agricultural knowledge, monetization, new business models and agri-environment policies, leverages on existing platforms, edge computing and network/ services, and introduces novel concepts, methods, tools, pilot facilities and engagement campaigns to go beyond today’s state of the art, perform breakthrough research and create sustainable innovation in upscaling (real-time) agricultural sensor data, already evident within the project lifetime. --------------------------------------------------------------------------------------------------------------------------------------------- This dataset contains tabular data for the purpose of a greenhouse window opening percentage prediction. The file \"Greenhouse_Climate_Window_data.xlsx\" contains three environmental features outside the greenhouse which are: outside temperature outside relative humidity solar radiation intensity and also the opening percentage of each of the greenhouse windows. These two features (\"Side 1 window opening\", \"Side 2 window opening\") can be used as target values for a tabular data regression or a time-series regression task. The file \"Greenhouse_IoT_environmental_data.csv\" contains IoT sensor measurements of several environmental features inside the greenhouse such as: air humidity air temperature soil temperature water content solar radiation level","author":[{"family":"Tsanakas","given":"Stylianos"},{"family":"Danso","given":"Lord"},{"family":"Railis","given":"Konstantinos"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18958752","URL":"https://doi.org/10.5281/zenodo.18958752","source":"datacite"},{"id":"doi:10.5281/zenodo.18958751","type":"article-journal","title":"AgriDataValue - Automatic Greenhouse Window Opening","abstract":"AgriDataValue aims to establish itself as the “Game Changer” in Smart Farming digital transformation and agri-environmental monitoring, and strengthen the smart-farming capacities, competitiveness and fair income by introducing an innovative, open source, intelligent and multi-technology, fully distributed Agri-Environment Data Space (ADS). To achieve technological maturity, fast and massive acceptance, AgriDataValue adopts and adapts a multidimensional approach that combines state of the art big data and data-spaces’ technologies (BDVA/ IDSA/ GAIA-X) with agricultural knowledge, monetization, new business models and agri-environment policies, leverages on existing platforms, edge computing and network/ services, and introduces novel concepts, methods, tools, pilot facilities and engagement campaigns to go beyond today’s state of the art, perform breakthrough research and create sustainable innovation in upscaling (real-time) agricultural sensor data, already evident within the project lifetime. --------------------------------------------------------------------------------------------------------------------------------------------- This dataset contains tabular data for the purpose of a greenhouse window opening percentage prediction. The file \"Greenhouse_Climate_Window_data.xlsx\" contains three environmental features outside the greenhouse which are: outside temperature outside relative humidity solar radiation intensity and also the opening percentage of each of the greenhouse windows. These two features (\"Side 1 window opening\", \"Side 2 window opening\") can be used as target values for a tabular data regression or a time-series regression task. The file \"Greenhouse_IoT_environmental_data.csv\" contains IoT sensor measurements of several environmental features inside the greenhouse such as: air humidity air temperature soil temperature water content solar radiation level","author":[{"family":"Tsanakas","given":"Stylianos"},{"family":"Danso","given":"Lord"},{"family":"Railis","given":"Konstantinos"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18958751","URL":"https://doi.org/10.5281/zenodo.18958751","source":"datacite"},{"id":"doi:10.5281/zenodo.18956536","type":"article-journal","title":"AgriDataValue - Weed Detection Image Dataset","abstract":"AgriDataValue aims to establish itself as the “Game Changer” in Smart Farming digital transformation and agri-environmental monitoring, and strengthen the smart-farming capacities, competitiveness and fair income by introducing an innovative, open source, intelligent and multi-technology, fully distributed Agri-Environment Data Space (ADS). To achieve technological maturity, fast and massive acceptance, AgriDataValue adopts and adapts a multidimensional approach that combines state of the art big data and data-spaces’ technologies (BDVA/ IDSA/ GAIA-X) with agricultural knowledge, monetization, new business models and agri-environment policies, leverages on existing platforms, edge computing and network/ services, and introduces novel concepts, methods, tools, pilot facilities and engagement campaigns to go beyond today’s state of the art, perform breakthrough research and create sustainable innovation in upscaling (real-time) agricultural sensor data, already evident within the project lifetime. -------------------------------------------------------------------------------------------------------------------------------------------- This dataset contains images along with their bounding box annotations for the purpose of weed detection. The bounding box annotations are in Yolo format and include two classes 'Crop' and 'Weed'. The images were captured by a UAV over a field seeded with celeriac. The resolution of the images is 5280(width) x 3956(height). Due to images' high resolution, image tiling and patching is encouraged (e.g. to 640x480) to also increase the number of images. Train/test/validation splitting was done in a random manner.","author":[{"family":"Arvanitis","given":"Nikos"},{"family":"Bossuyt","given":"Sarah"},{"family":"Ampe","given":"Eva"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18956536","URL":"https://doi.org/10.5281/zenodo.18956536","source":"datacite"},{"id":"doi:10.5281/zenodo.18956537","type":"article-journal","title":"AgriDataValue - Weed Detection Image Dataset","abstract":"AgriDataValue aims to establish itself as the “Game Changer” in Smart Farming digital transformation and agri-environmental monitoring, and strengthen the smart-farming capacities, competitiveness and fair income by introducing an innovative, open source, intelligent and multi-technology, fully distributed Agri-Environment Data Space (ADS). To achieve technological maturity, fast and massive acceptance, AgriDataValue adopts and adapts a multidimensional approach that combines state of the art big data and data-spaces’ technologies (BDVA/ IDSA/ GAIA-X) with agricultural knowledge, monetization, new business models and agri-environment policies, leverages on existing platforms, edge computing and network/ services, and introduces novel concepts, methods, tools, pilot facilities and engagement campaigns to go beyond today’s state of the art, perform breakthrough research and create sustainable innovation in upscaling (real-time) agricultural sensor data, already evident within the project lifetime. -------------------------------------------------------------------------------------------------------------------------------------------- This dataset contains images along with their bounding box annotations for the purpose of weed detection. The bounding box annotations are in Yolo format and include two classes 'Crop' and 'Weed'. The images were captured by a UAV over a field seeded with celeriac. The resolution of the images is 5280(width) x 3956(height). Due to images' high resolution, image tiling and patching is encouraged (e.g. to 640x480) to also increase the number of images. Train/test/validation splitting was done in a random manner.","author":[{"family":"Arvanitis","given":"Nikos"},{"family":"Bossuyt","given":"Sarah"},{"family":"Ampe","given":"Eva"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18956537","URL":"https://doi.org/10.5281/zenodo.18956537","source":"datacite"},{"id":"doi:10.5281/zenodo.18935633","type":"article-journal","title":"Smart Energy Harvesting System and Crop Health Monitoring System","abstract":"The advancement of precision agriculture demands sustainable power solutions and efficient real-time monitoring systems to enhance crop productivity. This paper presents a Smart Energy Harvesting System integrated with an IoT-based Crop Health Monitoring System for autonomous agricultural applications. The proposed system utilizes solar energy to power environmental and soil sensors that measure temperature, humidity, soil moisture, soil pH, and light intensity. An ESP32 microcontroller processes the sensor data and transmits it to a cloud platform for real-time monitoring and automated irrigation control. A Battery Management System (BMS) and DC-DC converter ensure safe power regulation and continuous operation, even in off-grid environments. The system reduces dependency on conventional power sources, optimizes water usage, and minimizes manual intervention. By integrating renewable energy with IoT technology, the proposed model supports sustainable farming practices, improves resource efficiency, and enables data-driven decision-making for modern precision agriculture.","author":[{"family":"Vaishya","given":"Mamta"},{"family":"Kumari","given":"Juhi"},{"family":"Sood","given":"Mamta"},{"family":"Garg","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18935633","URL":"https://doi.org/10.5281/zenodo.18935633","source":"datacite"},{"id":"doi:10.5281/zenodo.18935632","type":"article-journal","title":"Smart Energy Harvesting System and Crop Health Monitoring System","abstract":"The advancement of precision agriculture demands sustainable power solutions and efficient real-time monitoring systems to enhance crop productivity. This paper presents a Smart Energy Harvesting System integrated with an IoT-based Crop Health Monitoring System for autonomous agricultural applications. The proposed system utilizes solar energy to power environmental and soil sensors that measure temperature, humidity, soil moisture, soil pH, and light intensity. An ESP32 microcontroller processes the sensor data and transmits it to a cloud platform for real-time monitoring and automated irrigation control. A Battery Management System (BMS) and DC-DC converter ensure safe power regulation and continuous operation, even in off-grid environments. The system reduces dependency on conventional power sources, optimizes water usage, and minimizes manual intervention. By integrating renewable energy with IoT technology, the proposed model supports sustainable farming practices, improves resource efficiency, and enables data-driven decision-making for modern precision agriculture.","author":[{"family":"Vaishya","given":"Mamta"},{"family":"Kumari","given":"Juhi"},{"family":"Sood","given":"Mamta"},{"family":"Garg","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18935632","URL":"https://doi.org/10.5281/zenodo.18935632","source":"datacite"},{"id":"doi:10.5281/zenodo.18922416","type":"article-journal","title":"KhetSetGo- Empowering Farmers And Machine Owners","abstract":"Agriculture remains a primary source of livelihood in many developing regions, yet many farmers face challenges in accessing modern agricultural machinery due to high purchasing costs and limited availability. Small and medium-scale farmers often cannot afford expensive equipment such as tractors, harvesters, and other farming tools, which affects productivity and efficiency. To address this issue, this research presents KhetSetGo – Empowering Farmers and Machine Owners, a web-based platform designed to connect farmers who require agricultural machinery with machine owners willing to rent their equipment. The platform enables machine owners to post available machinery with relevant details, while farmers can easily browse, view machine information, and place booking requests according to their agricultural needs. The proposed system is developed using Java Server Pages (JSP), Servlets, MySQL database, HTML, CSS, and JavaScript, and is deployed on the Apache Tomcat server. The platform includes features such as user authentication, OTP-based password recovery, machine listing with media support, and booking management between farmers and machine owners. By enabling an online rental marketplace for agricultural equipment, the system helps reduce machinery costs for farmers while improving equipment utilization for owners. The implementation of KhetSetGo demonstrates how digital platforms can support smart farming practices and improve accessibility to agricultural resources through an efficient and user-friendly system.","author":[{"family":"Kaspate","given":"Himanshu"},{"family":"More","given":"Tejas"},{"family":"Sanas","given":"Atharv"},{"family":"Sarade","given":"Pruthviraj"},{"family":"Mohite","given":"Prof"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18922416","URL":"https://doi.org/10.5281/zenodo.18922416","source":"datacite"},{"id":"doi:10.5281/zenodo.18922417","type":"article-journal","title":"KhetSetGo- Empowering Farmers And Machine Owners","abstract":"Agriculture remains a primary source of livelihood in many developing regions, yet many farmers face challenges in accessing modern agricultural machinery due to high purchasing costs and limited availability. Small and medium-scale farmers often cannot afford expensive equipment such as tractors, harvesters, and other farming tools, which affects productivity and efficiency. To address this issue, this research presents KhetSetGo – Empowering Farmers and Machine Owners, a web-based platform designed to connect farmers who require agricultural machinery with machine owners willing to rent their equipment. The platform enables machine owners to post available machinery with relevant details, while farmers can easily browse, view machine information, and place booking requests according to their agricultural needs. The proposed system is developed using Java Server Pages (JSP), Servlets, MySQL database, HTML, CSS, and JavaScript, and is deployed on the Apache Tomcat server. The platform includes features such as user authentication, OTP-based password recovery, machine listing with media support, and booking management between farmers and machine owners. By enabling an online rental marketplace for agricultural equipment, the system helps reduce machinery costs for farmers while improving equipment utilization for owners. The implementation of KhetSetGo demonstrates how digital platforms can support smart farming practices and improve accessibility to agricultural resources through an efficient and user-friendly system.","author":[{"family":"Kaspate","given":"Himanshu"},{"family":"More","given":"Tejas"},{"family":"Sanas","given":"Atharv"},{"family":"Sarade","given":"Pruthviraj"},{"family":"Mohite","given":"Prof"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18922417","URL":"https://doi.org/10.5281/zenodo.18922417","source":"datacite"},{"id":"doi:10.1201/9781003589143-4","type":"article-journal","title":"IoT-Based Drone for Smart Farming","abstract":"India is one of the most significant income earners in the agriculture sector. As per the latest research, the productivity rate of crops in India in the field of agriculture is very high which is a considerable number of primary sources of livelihood. It requires pesticides, crop diseases, fertilizers, and other elements for agriculture, but managing such things over wide areas of fertile lands becomes very difficult. If there are fewer farmers on the arable land than is required, it won t be easy to maintain that land. To avoid these severe problems, we are developing a project: “IoT-Based Drone for Smart Farming.” This project involves the development of smart farming with the application of advanced Internet of Things (IoT) technologies attached to drone capabilities. Our newest concept is using IoT-enabled sensors, analytical real-time data collection of important farming parameters, and advanced communication protocols like MQTT (Message Queue Telemetry Transport), enabling seamless connectivity between the drone and cloud-based platforms for remote monitoring and mapping of cropping areas, health report of crops, and improving irrigation systems in relation to soil moisture, temperature, and humidity. The various features of the drone are automated irrigation, precision spraying, and pest detection. It focuses on sustainability, scalability, efficiency, and resource optimization for sustainable farming techniques.","author":[{"family":"Hossain","given":"Sk"},{"family":"Ghosh","given":"Aditya"},{"family":"Mondal","given":"Sudipta"},{"family":"Ghosh","given":"Subham"},{"family":"Mondal","given":"Amit"},{"family":"Bhattacharya","given":"Ankan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003589143-4","URL":"https://doi.org/10.1201/9781003589143-4","source":"crossref"},{"id":"doi:10.1109/icei65890.2026.11447877","type":"article-journal","title":"Smart Farming with AI: Crop Recommendation Using Random Forest Classifier","abstract":"Crop cultivation is the backbone of food security and economic stability. But most farmers find it challenging to determine the best crops to grow under specific climatic and soil conditions. This paper proposes a Crop Recommendation System with Random Forest Classifier to support farmers and agricultural scientists in making informed decisions. It is trained using an extensive dataset of environmental and soil factors like temperature, humidity, rainfall,$\\mathbf{p H}$, and primary soil nutrients (Nitrogen, Phosphorus, and Potassium - NPK). Preprocessing methods like normalization and standardization are used to improve the model's accuracy and performance. In contrast to conventional approaches, which are based on intuition or experience and typically do not consider several variables at a time, the suggested machine learning method provides a more efficient and accurate solution. A web application based on Flask was created in order to supply real-time crop recommendations according to the trained model. Experimental results show that the system provides highly accurate crop suggestions according to particular environmental conditions. This intelligent and self-sustaining system encourages accurate agriculture and environmentally friendly farming methods by reducing resource wastage and increasing yield of crops.","author":[{"family":"Kumawat","given":"Tejasvini"},{"family":"Mali","given":"Rohit"},{"family":"Nimbalkar","given":"Kalyani"},{"family":"Raut","given":"Roshani"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icei65890.2026.11447877","URL":"https://doi.org/10.1109/icei65890.2026.11447877","source":"crossref"},{"id":"doi:10.35891/agx.v16i2.5931","type":"article-journal","title":"Increasing kailan profits using smart farming in the form of a digital water timer","abstract":"Introduction: Agriculture is no longer facing challenges in the classic way but with modern method called smart farming. Hope this can be a solution to improve agricultural quality and productivity which will lead to increased farming profits. One of them is digital water timer, it helps distributing water in hydroponics. In reality, not many farmers implemented smart farming or greenhouses due to lack of information and costs. This study aims to analysis profit and the factors influencing it. Methods: The research was conducted in Jambi City collected with the help of questionnaires and literature study. Primary data was collected from 155 respondents including hydroponics with smart farming in greenhouses, hydroponics non-smart farming in greenhouses, hydroponics only, and conventional farming. The analytical research method used is quantitative descriptive and data processing using the R/C ratio formula, whereas to determine the factors using multiple linear regression with F-test and t-test. Results: The results showed that the R/C ratio is 1.74, which means farming is profitable to implement. Hydroponics with smart farming provides the highest profit among other technologies and costs less than non-smart farming. The profit obtained is 18.6% higher than non-smart farming. The higher the technology, the more production will increase. Smart farming affects positively to the Kailan production followed by other factors that is land area. Conclusion: This finding provides technology such as smart farming has potential impacts to improve farm profit.","author":[{"family":"Syafri","given":"Zelin"},{"family":"Tinaprilla","given":"Netti"},{"family":"Rifin","given":"Amzul"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35891/agx.v16i2.5931","URL":"https://doi.org/10.35891/agx.v16i2.5931","source":"crossref"},{"id":"doi:10.1049/icp.2025.0238","type":"article-journal","title":"An IoT-based smart farming solution for sustainable agriculture: integrating AI, cloud computing, and 4G communication for enhanced productivity","abstract":"This paper presents a comprehensive smart farming solution designed to address the limitations of current systems and the practical needs of modern farmers. Leveraging cutting-edge technologies such as the Internet of Things (IoT), artificial intelligence (AI), and cloud computing, our solution aims to improve agricultural productivity and sustainability. By integrating industrial-grade sensors with a user-friendly software platform, our system facilitates transparent monitoring and control of agricultural conditions at various scales, while also providing tools for efficient farm finance management. The star topology architecture, combined with 4G network communication, ensures system reliability and efficient data transmission. AI integration provides insights and actionable recommendations, allowing farmers to effectively optimize crop yields and resource utilization. Our approach addresses significant shortcomings observed in existing smart agriculture projects, such as outdated communication technology, limited scalability, and inadequate user interfaces for data management. By integrating solar power to power the system and emphasizing user-centric design, our solution promotes environmental sustainability and operational efficiency.","author":[{"family":"Afif","given":"Mustahoshin"},{"family":"Iqbal","given":"Javid"},{"family":"Borshon","given":"Salim"},{"family":"Junayed","given":"Rashedul"},{"family":"Ahamed","given":"Sabbir"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1049/icp.2025.0238","URL":"https://doi.org/10.1049/icp.2025.0238","source":"crossref"},{"id":"doi:10.1109/icicv68925.2026.11554579","type":"article-journal","title":"AI-based Virtual Herbal Garden and Smart Cultivation Advisory System for Sustainable Farming","abstract":"The AI-Based Virtual Herbal Garden with Intelligent Plant Analysis proposed in this study is an inter-active system that can diagnose plant health issues, identify medicinal plants, and offer practical cultivation advice. The system uses a three-stage deep learning pipeline: DenseNet121 detects plant diseases like fungal infections, nutrient deficiencies, and pest-induced damage; EfficientNet-B0 is used for species identification; and a transformer-based model (T5 or LLaMA) produces contextual recommendations for pesticide use, cultivation techniques, and preventive measures. In order to improve user engagement and encourage herbal learning, the platform also uses 3D visualization. The suggested system promotes sustainable agriculture and provides precise, instantaneous decision support for farmers, students, researchers, and traditional medical practitioners by combining computer vision, natural language generation, and indigenous plant knowledge.","author":[{"family":"Ssuveda"},{"family":"Ssunmathi"},{"family":"Ehemalatha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icicv68925.2026.11554579","URL":"https://doi.org/10.1109/icicv68925.2026.11554579","source":"crossref"},{"id":"doi:10.2174/9798898811921126010014","type":"article-journal","title":"AI-Driven Cybersecurity in Agriculture: The Future of Farming","abstract":"Digital technologies such as the Internet of Things (IoT), drones, autonomous machinery, and advanced data analytics are quickly revolutionizing the agricultural industry. This digital transformation, known as precision agriculture, has greatly improved productivity, sustainability, and efficiency in farming methods. Nevertheless, the industry is confronted with increasing cybersecurity issues despite these advancements. The growing dependence on interconnected systems has created vulnerabilities that cybercriminals are exploiting more and more, endangering not just individual farms but also the entire food supply chain. This section explores the cybersecurity environment in the agricultural industry, highlighting major risks like phishing, ransomware, data breaches, and industrial espionage. It highlights the importance of strong cybersecurity measures to safeguard the integrity and functionality of contemporary agricultural systems. The chapter emphasizes the crucial importance of Artificial Intelligence (AI) in dealing with these challenges, providing AI-based solutions for identifying threats, automating responses, and safeguarding data. The future success of the agricultural industry's digital transformation relies on protecting its technological infrastructure from cyber threats. This section supports the idea of implementing a holistic cybersecurity plan that includes AI, various security layers, and ongoing education and awareness efforts. Through enhancing its digital progress, the agricultural industry can guarantee continuous expansion, adaptability, and the capacity to fulfill international food requirements in a progressively interconnected globe. The chapter states that the future of agriculture relies not just on technological advancements but also on the industry's dedication to cybersecurity. Ensuring the security of digital agricultural systems is crucial for sustaining global productivity, sustainability, and food security.","author":[{"family":"Gupta","given":"Shikha"},{"family":"Gupta","given":"Nishi"},{"family":"Aggarwal","given":"Lakshay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898811921126010014","URL":"https://doi.org/10.2174/9798898811921126010014","source":"crossref"},{"id":"doi:10.1109/i-coste68047.2025.11467415","type":"article-journal","title":"A Framework for a Green IoT Blockchain Environment: From the Smart Farming Perspective","abstract":"There has been a recent increase in the adoption and research within the Blockchain-IoT technology domain. However, most of the known issues (e.g., high energy consumption, security concerns) with blockchain and IoT-embedded devices persist. We employ design science research methodology to design a framework for a green Internet of Things (IoT) blockchain environment. Our research addresses the urgent need for sustainable solutions in the face of the rapidly growing IoT and blockchain industries. Furthermore, our research aligns with the United Nations Sustainable Development Goals, specifically Goal 7, which aims to ensure access to affordable, reliable, sustainable, and modern energy for all.","author":[{"family":"Alsudairi","given":"Fahad"},{"family":"Essi","given":"Steve"},{"family":"Aljudaibi","given":"Samaher"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/i-coste68047.2025.11467415","URL":"https://doi.org/10.1109/i-coste68047.2025.11467415","source":"crossref"},{"id":"doi:10.54259/pakmas.v5i2.3350","type":"article-journal","title":"Peningkatan Hasil Pertanian Tanaman Hortikultura melalui Pelatihan Smart Farming di Tomohon","abstract":"The Maulit Farmers Group, located in Tomohon City, North Sulawesi, has the potential for horticultural farming due to its geographical location on the slopes of Mount Lokon. The challenges faced include limited funds and technology knowledge and skills in applying smart farming technology which impact production results. The purpose of this training activity is to implement a smart farming system to optimize horticultural crop yields, increase the income of Maulit Farmers Group members, and empower the surrounding community. The training methods include program socialization, training on smart farming systems, business strategy and digital marketing, and horticultural crop cultivation, followed by program mentoring and evaluation. After the training activities, there was an increase in knowledge and skills: from a pre-test result where 80% did not understand the technology, to a post-test result showing 90% who understood and could independently operate smart farming technology. Based on these results, the training activity achieved the targeted outcomes is independence in implementing smart farming technology to enhance agricultural production and initiate sustainability for farmer groups located in the surrounding areas.","author":[{"family":"Bakti","given":"Andi"},{"family":"Yusupa","given":"Ade"},{"family":"Agustina","given":"Tika"}],"issued":{"date-parts":[[2025]]},"DOI":"10.54259/pakmas.v5i2.3350","URL":"https://doi.org/10.54259/pakmas.v5i2.3350","source":"crossref"},{"id":"doi:10.1109/emergin67762.2025.11450824","type":"article-journal","title":"Smart Farming Techniques in Modern Agriculture Using Artificial Intelligence and Machine Learning","abstract":"The burning evolution of Artificial Intelligence (AI) and Machine Learning (ML) has changed the agriculture systems and offered the opportunity to employ data-driven and automated solutions in the sphere of agriculture. Smart Agricultural practices rely on IoT devices, computer vision and predictive analytics which can be applied to enhance productivity of crops, its resources as well as sustainability. The most popular AI models that have been applied in the detection of crop diseases, soil quality and yield prediction include Convolutional Neural Networks (CNNs) and Decision Trees. The collaboration of the AI and the Internet of Things (IoT) technologies may lead to the real-time monitoring of such environmental characteristics as humidity, temperature, and soil moisture, developing an effective irrigation and fertilizer regulation. These AI-based systems have been found to have high impact concerning reducing wastages of resources, electricity maximization and early warning of stressful plant conditions [1]-[5]. Moreover, they are also implementing federated and edge learning systems to ensure the privacy of information in large-scale agriculture and scalability [7], [13] also. Automation, data analytics and smart sensing may all empower farmers to possess the appropriate instruments to achieve resiliency and sustainable farming practices in their decisions. In the paper, the author is going to review and analyze the current trends, technologies, and challenges associated with the application of AI and ML in smart agriculture in the light of its efficiency in enhancing productivity, sustainability, and flexibility in the rural setting.","author":[{"family":"Jamil","given":"Sara"},{"family":"Paurya","given":"Devansh"},{"family":"Pandey","given":"Geetanjali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/emergin67762.2025.11450824","URL":"https://doi.org/10.1109/emergin67762.2025.11450824","source":"crossref"},{"id":"doi:10.1201/9781779640932-13","type":"article-journal","title":"Internet of Climate Change Things (IOCCT) for Sustainable Agricultural Production","abstract":"Due to their effects on the physical and biological components of the environment, the problems of environmental pollution and climate change have gained international attention. Precision agriculture (PA) is a solution that can be used to address the problem of low agricultural yields and losses caused by recent unanticipated and severe weather occurrences. The development of sensors for frost prevention, remote crop monitoring, fire hazard prevention, precise nutrient control in soilless greenhouse cultivation, solar energy autonomy, and intelligent feeding, shading, and lighting control to increase yields and lower operating costs are all results of technological advancements over time. PA reduces environmental pollution and labor expenses while delivering higher yields at cheaper input prices during a period of rising food demand. The use of the most advanced computer and electronic technologies is anticipated to increase significantly in modern food production and PA.","author":[{"family":"Sadiq","given":"MS"},{"family":"Singh","given":"IP"},{"family":"Ahmad","given":"MM"},{"family":"Nazifi","given":"IK"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781779640932-13","URL":"https://doi.org/10.1201/9781779640932-13","source":"crossref"},{"id":"doi:10.1109/wccst67302.2026.11496219","type":"article-journal","title":"Smart Farming Using Machine Learning Analytics: A Crop Yield Prediction Model","abstract":"Agriculture is very important in food provision and sustenance. Proper prediction of crop yields is very important in the contemporary agriculture. It guarantees the manufacture of sufficient food both in quantity and quality. Conventional agriculture is grounded on experience and past intuition. It can generate unreliable crop production. Thus, the given paper will introduce a smart farming system, using ensemble learning methods to make more precise and faster predictions about crop yields. In the quest, to establish the most appropriate approach to be used in predicting the yield of crops as well as assist the farmers in making decisions in agricultural sector, this study compares the modern ensemble learning methods and the conventional machine learning methods. In addition to the advanced ensemble learning methods which include voting, blending, and stacking, this study analyses numerous regression models such as LR, SVR, ENR etc. 10-fold cross-validation has been introduced to guarantee the reliability of the evaluation of models. Here, different performance metrics have been used such as, MAE, NMAE etc. The Stacked SVR model recorded the best performance and lowest NRMSE of 0. 2914.","author":[{"family":"Saha","given":"Sukanya"},{"family":"Biswas","given":"Saroj"},{"family":"Majumdar","given":"Sounak"},{"family":"Sundarakantham","given":"K"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/wccst67302.2026.11496219","URL":"https://doi.org/10.1109/wccst67302.2026.11496219","source":"crossref"},{"id":"doi:10.1007/s44327-025-00096-w","type":"article-journal","title":"Smart greenhouse farming: a review towards near zero energy consumption","abstract":"Abstract The global agricultural sector faces increasing challenges in adopting sustainable practices and reducing its environmental footprint. Smart greenhouse agriculture has emerged as a key solution, enabling efficient year-round crop production while minimizing dependence on traditional field farming. However, achieving near-zero energy consumption in greenhouses remains a major challenge due to the high operational energy demands. This review examines the current state of energy consumption in greenhouses, critically analyzes existing technological solutions, and identifies key challenges, such as high energy consumption for heating, cooling, and lighting. The study highlights opportunities for integrating renewable energy sources, optimizing energy-saving systems, and using advanced control technologies such as artificial intelligence (AI) and the Internet of Things (IoT) to monitor microclimatic conditions. Results show that integrating these solutions can significantly reduce energy consumption while maintaining optimal growing environments. The main findings include prioritizing the adoption of hybrid renewable energy systems, improving greenhouse design and material selection, and enhancing real-time monitoring systems with smart technologies. Future research should focus on cost-effective innovations, interdisciplinary approaches, and the scalability of energy-efficient designs. This review provides actionable information for researchers, policymakers, and practitioners to advance the transition to sustainable, near-zero energy greenhouse systems.","author":[{"family":"Soussi","given":"Abdellatif"},{"family":"Zero","given":"Enrico"},{"family":"Ouammi","given":"Ahmed"},{"family":"Zejli","given":"Driss"},{"family":"Zahmoun","given":"Said"},{"family":"Sacile","given":"Roberto"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/s44327-025-00096-w","URL":"https://doi.org/10.1007/s44327-025-00096-w","source":"crossref"},{"id":"doi:10.70965/pbnsei-eb.2025.46","type":"article-journal","title":"Building Resilient Smart Villages: A Holistic Model for Energy, Farming, and Healthcare Transformation","abstract":"The proposed system implements renewable energy microgrids as its core communitybased framework.The microgrid system provides both energy autonomy and dependable power supply to users.The system enables smart infrastructure development across the entire village area.The agricultural sector implements IoT-based precision farming and smart irrigation systems to enhance both agricultural output and resource conservation.The telemedicine platform of this system enables remote populations to access superior medical care through digital connections.The system operates through combined efforts between these different sectors.The system operates through a circular process were excess energy powers agricultural and healthcare technologies.The system aims to develop sustainable communities which combine technological advancement with environmental sustainability and social equity to achieve lasting economic development and stability.","author":[{"family":"Pal","given":"Mrinmoy"},{"family":"Roy","given":"Arunima"},{"family":"Dhar","given":"Palasri"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70965/pbnsei-eb.2025.46","URL":"https://doi.org/10.70965/pbnsei-eb.2025.46","source":"crossref"},{"id":"doi:10.71443/9789349552364-07","type":"article-journal","title":"Artificial Intelligence Approaches for Fertilizer and Pesticide Recommendation Systems","abstract":"The integration of Artificial Intelligence (AI) in agricultural systems has revolutionized the way fertilizers and pesticides are managed, offering precise, data-driven solutions that enhance productivity while promoting sustainability. This chapter explores the role of AI techniques, such as machine learning, deep learning, and hybrid models, in optimizing the application of fertilizers and pesticides. By leveraging real-time data from diverse sources—such as soil sensors, climate forecasts, satellite imagery, and pest detection systems AI-driven recommendation models can provide tailored, context-specific guidance to farmers. These systems not only improve crop yields but also reduce resource wastage and minimize environmental impact. The chapter highlights key methodologies, including ensemble methods like Random Forests and Deep Reinforcement Learning (DRL), that enable adaptive, real-time decision-making. Furthermore, it examines the integration of AI with soil and crop simulation models, enhancing model accuracy and responsiveness. While significant progress has been made, challenges related to data quality, model interpretability, and scalability remain, especially in smallholder and developing regions. The chapter concludes by discussing future directions, emphasizing the need for further research to develop more sustainable, scalable, and user-friendly AI-based agricultural solutions.","author":[{"family":"Senthamizhselvi","given":"R"},{"family":"Arivazhagan","given":"A"},{"family":"Sundar","given":"R"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-07","URL":"https://doi.org/10.71443/9789349552364-07","source":"crossref"},{"id":"doi:10.38124/ijisrt/25jul1842","type":"article-journal","title":"Smart Farming Assistant","abstract":"The Smart Farming Assistant is a machine learning-based system designed to aid farmers and agricultural planners in making informed decisions about crop yield and market pricing. The system utilizes advanced algorithms such as XGBoost and Random Forest to predict agricultural outcomes based on soil health, weather patterns, and historical market data. To ensure transparency and trust in the model’s predictions, the project incorporates SHAP (SHapley Additive exPlanations) values, allowing users to interpret the influence of each input feature on the model’s output. This enhances the explainability of the system, making it not only a powerful forecasting tool but also an educational aid for understanding the relationships between environmental factors and crop performance. The project includes a user-friendly web interface that enables users to input relevant agricultural parameters and receive both predictions and interpretive visualizations. By combining accuracy with explainability, this Smart Farming Assistant bridges the gap between traditional agricultural knowledge and modern artificial intelligence, promoting more efficient and profitable farming practices.","author":[{"family":"Farooqui","given":"Gulam"},{"family":"Mohiuddin","given":"Mohammed"},{"family":"Ali","given":"Syed"}],"issued":{"date-parts":[[2025]]},"DOI":"10.38124/ijisrt/25jul1842","URL":"https://doi.org/10.38124/ijisrt/25jul1842","source":"crossref"},{"id":"doi:10.31127/tuje.1688064","type":"article-journal","title":"Smart Farming with Ensemble Learning: A Soil-Driven Crop Suggestion Model for Sustainable Agriculture","abstract":"The use of machine learning (ML) in agriculture has paved new avenues to improve decision making, especially in crop choice. The current research offers a data-driven crop recommendation system using a machine learning approach based on key soil and environmental factors—i.e., nitrogen (N), phosphorus (P), potassium (K), pH, temperature, humidity, and rainfall. A dataset of 2,200 soil records was processed using exploratory data analysis (EDA), normalization, and model training with algorithms such as Random Forest, Logistic Regression, and Gradient Boosting. Of these, Random Forest provided the best test accuracy of 99.32%, with high predictive ability and interpretability via feature importance measures. Violin and boxplots showed distinct feature separability among crop types, particularly in variables such as rainfall, temperature, and NPK concentrations, confirming the model's classification effectiveness. The practicability of the system is in its possible incorporation in IoT-based soil monitoring devices and cell advisory apps, delivering real-time, location-specific crop advice. This strategy enables farmers to make informed decisions, minimizes fertilizer waste, and promotes sustainable farming practices. The suggested system not only showcases technical strength but also fits well within the overall vision of smart farming and precision agriculture.","author":[{"family":"Upreti","given":"Kamal"},{"family":"Singh","given":"Jaspreet"},{"family":"Alapatt","given":"Bosco"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31127/tuje.1688064","URL":"https://doi.org/10.31127/tuje.1688064","source":"crossref"},{"id":"doi:10.1201/9781003607342-3","type":"article-journal","title":"Climate-Smart Integrated Farming Systems for Sustainable Production and Food Security","abstract":"Climate smart agriculture (CSA) is a proactive and adaptive approach to enhancing sustainability of agriculture production that concerns food security and climate challenges. This chapter utilizes the key components such as integrated farming system (IFS), scale of operation, and the rationale for climate-smart agriculture to implement CSA principles. Integrating diverse agricultural practices, CSA enhances productivity, builds resilience, and helps to mitigate environmental impacts. This chapter examines climate risks, adaptation strategies, and mitigation measures emphasizing how CSA techniques such as conservation tillage, crop diversification, intercropping, precision technology, and resource efficient farming, can reduce vulnerabilities to climate change. In addition, it highlights the role of integrated farming systems in optimizing resource use, improving soil health, and ensuring long-term agriculture sustainability. The challenges regarding implementing CSA, particularly in resource limited regions, are also discussed, along with the prospects for scaling up smart climate technologies. Combining CSA with IFS helps support farmers and agricultural scientists in achieving greater food security, economic stability, and environmental stability. The synthesis presented here hopes to contribute to the broader goal of developing resilient food systems capable of withstanding climate uncertainties while ensuring long term agricultural productivity.","author":[{"family":"Parajulee","given":"Megha"},{"family":"Gautam","given":"Surendra"},{"family":"Sapkota","given":"Raju"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003607342-3","URL":"https://doi.org/10.1201/9781003607342-3","source":"crossref"},{"id":"doi:10.1109/iccica67008.2025.11337277","type":"article-journal","title":"Human-Centered AI in Smart Farming: Toward Agriculture 5.0","abstract":"Mechanical farming practices largely depend on direct soil evaluation and disease identification by hand, hence inefficiencies, reduced output, and more loss. Farmers lose out on crop selection accuracy from limited soil tests and late identification of diseases, affecting productivity. To solve this, our work presents a Human-Centered AI system for smart farming with greater emphasis on soil analysis for accurate crop recommendations coupled with plant disease detection as an added feature. In the preprocessing and analysis of data, MATLAB is utilized to derive soil properties like texture, color, and water content from images to suggest appropriate crops. Plant diseases are also identified by image processing and are classified by XGBoost for early intervention. This ensures better decision-making through real-time feedback with maximum yield and minimum losses. The suggested system provides automation, accuracy, and convenience, enabling farmers with actionable insights to enhance agricultural productivity in accordance with Agriculture 5.0 developments.","author":[{"family":"Uma","given":"S"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccica67008.2025.11337277","URL":"https://doi.org/10.1109/iccica67008.2025.11337277","source":"crossref"},{"id":"doi:10.32900/2312-8402-2024-132-27-43","type":"article-journal","title":"FACTORS INFLUENCE ON THE MILK QUALITY INDICATORS OF NOVOOLEKSANDRIVSKIA HEAVY-DUTY BREED MARES","abstract":"The article presents the results of studies of milk productivity and milk quality of mares of the Novooleksandrivka heavy draft breed. The daily milk yield of mares and milk quality indicators in samples taken in June and August were determined, and it was proven that all indicators vary significantly. It was established that the indicators of dry matter, protein, lactose and dry non-fat milk residue were higher in June, and the protein content, fat-protein ratio, freezing point and somatic cell count were higher in August. Differences in milk quality indicators from the first and second milking were revealed, and a higher content of almost all studied indicators was established in milk samples taken from the first milking in June and August, in August – with a much smaller difference. Significant correlations were found between milk quality indicators – dry matter (r=0.856), fat (r=0.728), fat-protein ratio (r=0.861) in milk samples taken in June and August from the first, second milking and daily milk yield. In milk milked in August, these relationships. In all samples, a negative relationship was established between the amount of milk and the content of somatic cells. The influence of the lactation period on milk productivity and milk quality indicators of experimental mares was established – the highest daily milk yield, dry matter and fat content in milk were characterized by mares at the lowest lactation periods. The influence of the age of experimental mares on their daily milk yield and milk quality indicators was established, the superiority of mares aged 9-13 years in June (r=0.431), and older ones in August (r=0.352) was proven in terms of daily milk yield. It was determined that the age of mares affects the duration of their foaling (r=0.396). The advantage in daily milk yield of mares with a foaling duration of over 350 days was proven according to the results of control milking in both June and August. In terms of dry matter, fat and fat-protein ratio in milk samples of experimental mares with a foaling duration of over 340 days according to the results of control milking in both June and August, as well as the highest lactose content and freezing point index in samples taken in June and protein – in samples taken in August. It was established that mares that foaled with foals, with a high degree of probability (p˂0.01) had a higher daily milk yield, as well as milk yields for the first and second milking, a higher dry matter, fat, fat-protein ratio.","author":[{"family":"Brovko","given":"Aleksii"},{"family":"Itkachova","given":"Iryna"},{"family":"Prusova","given":"Galyna"},{"family":"Liutykh","given":"Serhii"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2024-132-27-43","URL":"https://doi.org/10.32900/2312-8402-2024-132-27-43","source":"crossref"},{"id":"doi:10.47852/bonviewaia52026214","type":"article-journal","title":"Smart Farming: Crop Recommendation Using Machine Learning with Challenges and Future Ideas","abstract":"This paper addresses the critical challenge of optimizing crop selection in agriculture to enhance food production sustainably. The problem is framed as a multi-class classification task where the goal is to recommend the most suitable crop based on a set of environmental and soil features. While traditional methods rely on time-consuming and labor-intensive expert knowledge, this work proposes a data-driven approach using machine learning. The novelty of our investigation lies in the comprehensive comparative analysis of seven machine learning algorithms and the development of a highly accurate neural network model. We utilize a publicly available dataset from Kaggle, which has been preprocessed to ensure data quality. We provide a detailed account of our feature engineering and hyperparameter tuning processes. Our proposed neural network model, with a specific architecture of 30–20–10 neurons, achieves a validation accuracy of 97.73%. This work also discusses the challenges of deploying such models, including real-world data variability and the need for model interpretability. We demonstrate that our approach, particularly the neural network model, provides a robust, scalable, and adaptable solution for crop recommendation, outperforming other models (in holistic view) like Random Forest which achieved a slightly higher accuracy of 99.5% on this specific dataset but with less generalization potential. The findings of this study can empower farmers to make informed decisions, ultimately leading to improved crop yields, enhanced soil fertility, and greater profitability. Received: 22 May 2025 | Revised: 11 July 2025 | Accepted: 26 August 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset/data and in TechRxiv at https://www.techrxiv.org/doi/full/10.36227/techrxiv.23504496, reference number [41]. Author Contribution Statement Devendra Dahiphale: Conceptualization, Methodology, Software, Formal analysis, Resources, Data curation, Writing – original draft, Writing – review &amp; editing, Visualization, Supervision, Project administration. Pratik Shinde: Validation, Investigation, Writing – review &amp; editing. Koninika Patil: Writing – review &amp; editing. Vijay Dahiphale: Validation, Writing – review &amp; editing, Visualization, Project administration.","author":[{"family":"Dahiphale","given":"Devendra"},{"family":"Shinde","given":"Pratik"},{"family":"Patil","given":"Koninika"},{"family":"Dahiphale","given":"Vijay"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47852/bonviewaia52026214","URL":"https://doi.org/10.47852/bonviewaia52026214","source":"crossref"},{"id":"doi:10.2139/ssrn.6932013","type":"manuscript","title":"A Unified Framework for Smart Farming and Breeding Empowered by Crop and Plant Models","abstract":"AbstractThe adoption of smart agriculture (SA) is often constrained by a gap between data-driven technologies and physiological understandings of crop growth and yield. This review addresses this gap by highlighting the central, mechanistic role of process-based crop and plant models in advancing SA practices. We first propose a unified, four-stage SA framework composed of perception, analysis, decision, and execution, followed by an examination of how crop/plant models interpret genotype × environment × management interactions. We then demonstrate how such models drive smart farming through applications in dynamic growth monitoring, multi-objective management optimization (e.g., irrigation, fertilization, planting density), and early warning for abiotic/biotic stresses. Concurrently, we further examine the role of crop/plant models in driving smart breeding by enabling trait and gene discovery, genotype-to-phenotype prediction, ideotype design, and cross-environment parental selection. Collectively, this study demonstrates that crop/plant models are not merely supportive tools but essential drivers for promoting smart farming and smart breeding practices.","author":[{"family":"Xu","given":"Jinrong"},{"family":"Wei","given":"Quan"},{"family":"Liang","given":"Xiaogui"},{"family":"Hu","given":"Shaowen"},{"family":"Feng","given":"Liping"},{"family":"Rodriguez","given":"Daniel"},{"family":"Wang","given":"Jing"},{"family":"Song","given":"Youhong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.6932013","URL":"https://doi.org/10.2139/ssrn.6932013","source":"crossref"},{"id":"doi:10.1109/icoeca68095.2026.11485556","type":"article-journal","title":"Smart Soilless Farming System using Self-Optimization and NPK Monitoring","abstract":"The aim of the project is to create and put into practice a Smart Soilless Farming System with self-optimization and real-time NPK monitoring to help tackle the urgent problems of sustainable agriculture and food security. Tradition soil farming contains many challenges, for example, nutrient deficiency, excess water, and environmental dependence, all leads to unpredictable growth and harvest. To improve the soil farming system, the project creates a hydroponic-based farming system, with the deployment of artificial intelligence enabled sensors and Algorithms of optimization. The smart system measures in real-time onboard the growth environment and nutrient solution pH, N, P, K levels, and ambient temperature, humidity, and the systems has automated dose and flow controls, as well as a back-end control engine written with algorithms of logic and data-driven self-optimization, and the overall user interface was created on a web platform and uses remote sensors. A prototype was created using microcontrollers, and quick testing to extrapolate accuracy, and calibration before moving onto design-to-testing of the first version. The prototype smart system controls nutrient solution and nutrient concentration, flow control, water waste and performance, as well as managing consistent and predictable crop yield productivity increase following safe agricultural practices. It will produce and support smarter eco-efficient farming systems via localized automation and data ai analytics, and smart nutrient intelligence in soilless farming systems, as well as up scaling.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icoeca68095.2026.11485556","URL":"https://doi.org/10.1109/icoeca68095.2026.11485556","source":"crossref"},{"id":"doi:10.1109/icmsci62561.2025.10893975","type":"article-journal","title":"Crop Care AI: The Smart Farming Revolution","abstract":"This research work introduces Crop care AI, an innovative solution designed to enhance precision agriculture. Ground sensors collect critical parameters such as NPK levels, pH, temperature, and rainfall in real-time. This data is then processed using machine learning algorithms to recommend optimal crop types and fertilizer quantities for specific regions. Additionally, the system incorporates a yield prediction model, utilizing environmental and historical yield data to forecast future crop performance. The AI-generated recommendations are accessible through a mobile application, providing personalized guidance for farmers irrespective of their location or expertise. By promoting sustainable farming practices, improving yield accuracy, and offering real-time decision-making support, Crop Care AI aims to revolutionize efficient crop management.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icmsci62561.2025.10893975","URL":"https://doi.org/10.1109/icmsci62561.2025.10893975","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.100827","type":"article-journal","title":"Precision livestock farming applied to the dairy sector: 50 years of history with a text mining and topic analysis approach","abstract":"• Overview of precision livestock farming (PLF) in the dairy sector. • Usage of new techniques as text mining and topic analysis for the review process. • Key themes: milk, behavior, welfare in data-driven dairy. • PLF enhances dairy sustainability across welfare, economy and environment. The global dairy industry has been revolutionized by advancements in genetics, milking technology, nutrition, and farm management, leading to increased milk production per cow and a substantial rise in total annual milk output. These changes have pushed the dairy industry toward a more technological approach that, with the aid of precision livestock farming (PLF), has maximized the production per cow. This study explores the evolution of PLF literature over time. It identifies its key topics, aiming to clarify and categorize the various areas of interest related to this field, trying to underscore potentiality and existing knowledge gaps. A comprehensive search on the Scopus® bibliometric database was carried out using various related keywords such as: “precision livestock farming, sensors, machine learning and dairy”. The research identified 5362 papers published from January 1976 to April 2024 that, after filtering, became 1794 eligible records. Descriptive statistics revealed a significant exponential increase in studies on PLF in dairy since 2000, particularly in developed countries with a long story of dairy breeding. Text mining and topic analysis revealed that the most frequently mentioned terms were “milk”, “behaviour” and “model”, suggesting 'suggesting that animal welfare and work based on data drive process have to be considered to improve production. Based on the findings of this literature review, it is evident that PLF had an impact on animal welfare, lifestyle of farmers and production efficiency. Addressing one area often influences others: thus, all these aspects are interrelated, with PLF being a key link between them.","author":[{"family":"Trapanese","given":"Lucia"},{"family":"Bifulco","given":"Giovanna"},{"family":"Macchio","given":"Alfio"},{"family":"Aragona","given":"Francesca"},{"family":"Purrone","given":"Sissy"},{"family":"Campanile","given":"Giuseppe"},{"family":"Salzano","given":"Angela"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.100827","URL":"https://doi.org/10.1016/j.atech.2025.100827","source":"crossref"},{"id":"doi:10.1007/s10586-026-06177-8","type":"article-journal","title":"Authentication framework for secure smart farming system deployed for sustainable development of smart cities: a review","abstract":"Abstract The adoption of smart farming systems in the context of smart cities assumes the use of Internet of Things (IoT) equipment, drones, and cloud computing to facilitate data-driven and sustainable farming and agriculture. Nevertheless, the open, massive, and resource-bound characteristics of such deployments predetermine the essentiality of secure authentication since, in case of breached equipment or unauthorized access, the objective of the food production, resources management, and urban sustainability can be directly disrupted. This study provides a focused analysis of the authentication frameworks proposed for IoT-based smart agricultural systems, specifically examining their relevance to smart city applications. Unlike existing surveys that primarily emphasize architectural descriptions or general discussions on IoT security, this study will systematically examine the efficacy of different authentication methods in agricultural contexts, specifically considering constraints such as limited computational power, communication bandwidth, and energy availability. Authentication schemes are examined in five popular types lightweight cryptographic, blockchain-based, AI/ML-driven, biometric-based, and multi-factor methods and compared according to the well-defined criteria of computation cost, communication overhead, and security functionality. The discussion shows that light cryptographic schemes can be more appropriate to the low-power agricultural devices but the blockchain-based and AI-driven cryptography schemes are more powerful with higher security features, but they introduce higher overhead and are less practical in real-time agricultural applications. The study also identifies key limitations in current research, including the lack of unified evaluation benchmarks, limited formal security validation, and insufficient support for scalability and interoperability across heterogeneous smart farming infrastructures. By highlighting these gaps and trade-offs, this review provides explicit direction for researchers and practitioners in selecting and designing authentication mechanisms that balance security and efficiency in smart farming systems integrated with smart cities.","author":[{"family":"Patwal","given":"Akshita"},{"family":"Wazid","given":"Mohammad"},{"family":"Singh","given":"Devesh"},{"family":"Das","given":"Ashok"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s10586-026-06177-8","URL":"https://doi.org/10.1007/s10586-026-06177-8","source":"crossref"},{"id":"doi:10.15575/j.agro.48701","type":"article-journal","title":"Smart-dose microboost: micronutrient in order to enhance chili growth and yield in tropical farming systems","abstract":"Despite the fact that micronutrients are crucial for the growth, metabolism, and crop yield of plants, they are required in relatively small proportions. The recent advancements in agriculture have resulted in the development of biostimulant products that are abundant in micronutrients which is advantageous. The objective of this investigation was to evaluate the potential of micronutrient-enriched biostimulants (MB) to enhance the quality characteristics of chili fruits. This study was conducted at Jatinangor, West Java. The experimental plots were laid out in a Randomized Block Design (RBD) with seven treatments and repeated four times, so the total number of treatments was 28 units. The treatments consist of farmer practice and doses of 0.75; 1.0; 1.5; 2.0; 2.5 and 3.0 L ha-1 MB. The results of this experiment indicated that the treatments with doses of 2.0–3.0 L ha-1 were consistently preferable in terms of fruit quality, yield, and growth. Plants that were more productive, capable of grading fruit, and had a slightly extended shelf life after harvest were the final result of the biostimulant product, which contained micronutrients. The farmer's practice consistently failed to meet the standards of all the treated sites. The combination of biostimulants and micronutrients significantly enhanced the physiological and reproductive functions of chilies. ABSTRAK Mikronutrien, meskipun dibutuhkan dalam jumlah yang lebih kecil daripada makronutrien, sangat penting untuk perkembangan tanaman, fungsi metabolisme, dan produktivitas tanaman. Perkembangan terkini dalam bidang pertanian telah menghasilkan produk biostimulan yang kaya akan mikronutrien yang sangat penting. Tujuan dari penelitian ini adalah untuk menilai potensi biostimulan yang diperkaya mikronutrien (MB) dalam meningkatkan kualitas buah cabai. Panellation in dilakukan di Jatinangor Sumedang, Jawa Barat. Plot percobaan disusun dalam Rancangan Acak kelompok (RAK) dengan tujuh perlakuan dan diulang empat kali, sehingga total perlakuan adalah 28 unit. Perlakuan tersebut terdiri dari metode konvensional; dosis biostimulan yang diperkaya mikronutrien (0.75; 1.0; 1.5; 2.0; 2.5 and 3.0 L ha-1 MB). Hasil percobaan ini menunjukkan bahwa perlakuan dengan dosis 2,0–3.0 L ha-1 adalah yang paling konsisten unggul di seluruh parameter pertumbuhan, hasil, dan kualitas buah. Produk biostimulan dengan tambahan mikronutrien membuat tanaman lebih kuat, lebih produktif, lebih baik dalam kualitas buah, dan memperpanjang masa simpan setelah panen. Dibandingkan dengan semua yang diberi perlakuan pupuk mikronutrien dan biostimulan, perlakuan konvensional memberikan respon paling kecil. Secara umum, penambahan mikronutrien dan biostimulan secara bersamaan dapat memberikan dampak besar pada peningkatan fungsi fisiologis dan reproduksi tanaman cabai. Kata kunci: Biostimulan, Cabai, Keberlanjutan, Produktivitas","author":[{"family":"Mulyani","given":"Oviyanti"},{"family":"Sudirja","given":"Rija"},{"family":"Susanto","given":"Agus"},{"family":"Sutari","given":"Wawan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.15575/j.agro.48701","URL":"https://doi.org/10.15575/j.agro.48701","source":"crossref"},{"id":"doi:10.25157/ag.v8i1.21484","type":"article-journal","title":"Pemberdayaan Berbasis Ekosistem Agribisnis Berkelanjutan Melalui Integrasi Mekanisasi dan Smart Farming","abstract":"Kegiatan Pemberdayaan Kepada Masyarakat (PKM) ini bertujuan untuk memberikan pemahaman dan keterampilan teknis pada aspek produksi dan aspek manajemen usahatani padi di Kelompok Tani Mekar III Desa Cijulang Kecamatan Cihaurbeuti Kabupaten Ciamis yang mengelola 26 hektar lahan padi dengan 68 petani. Model pemberdayaan petani berbasis ekosistem agribisnis berkelanjutan melalui integrasi mekanisasi dan smart farming sebagai salah satu upaya dalam menghadapi berbagai tantangan, termasuk biaya produksi tinggi, dampak perubahan iklim, dan praktik tradisional yang kurang efisien, yang secara kolektif menghambat kesejahteraan petani. Metode yang digunakan mencakup sosialisasi, pelatihan, penerapan teknologi, dan pendampingan. Teknologi yang diimplementasikan meliputi alat perontok padi bertenaga surya dan sensor smart farming (pengukur NPK tanah dan kadar air gabah). Hasil kegiatan PKM diharapkan mampu meningkatkan produktivitas dan efisiensi Kelompok Tani Mekar III. Dengan bantuan alat perontok padi bertenaga surya, petani menghemat waktu 66% dan biaya 88%. Penggunaan moisture meter juga menjamin gabah berkualitas premium sesuai standar, sehingga harga jual naik. Selain itu, pelatihan membuat semua petani mahir menggunakan teknologi modern dan paham manajemen pasca panen. Sehingga pada akhirnya membangun kemandirian petani dan secara langsung meningkatkan kesejahteraan.","author":[{"family":"Aziz","given":"Saepul"},{"family":"Abidin","given":"Zenal"},{"family":"Andrie","given":"Benidzar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.25157/ag.v8i1.21484","URL":"https://doi.org/10.25157/ag.v8i1.21484","source":"crossref"},{"id":"doi:10.1109/netcrypt65877.2025.11102390","type":"article-journal","title":"Smart Agricultural BOT for Automated Seed Sowing and Soil Monitoring in Organic Farming","abstract":"A variety of activities such as to sow seeds, to cut weeds and unwanted plants are performed in the fields on daily basis. The existing methods to do sowing, plowing and weed cutting are very time consuming and very hard to perform. The machinery which is used for seed sowing is very heavy and very hard handle. To solve all these complicated problems, we have developed equipment such that the seeding will be done at uniform distancing using the BOT. We have used the Arduino microcontroller, sensors, high rpm motors, drivers and controllers for designing of BOT. The BOT will follow upon the required lines for sowing. The BOT will be connected to the mobile interface for its controlling. The BOT will also collect the moisture level and$\\mathbf{p H}$level of soil and report will be sent online on mobile app for further actions. So, the mechanism will be developed for automatizing the seeding and monitoring of the field for different actions like assignation and adding the organic nutrients to the soils in the field.","author":[{"family":"Singh","given":"Somay"},{"family":"Sakya","given":"Gayatri"},{"family":"Malik","given":"Monika"},{"family":"Grover","given":"Chhaya"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/netcrypt65877.2025.11102390","URL":"https://doi.org/10.1109/netcrypt65877.2025.11102390","source":"crossref"},{"id":"doi:10.1109/iciss63372.2025.11076297","type":"article-journal","title":"Smart Irrigation System for Precision Farming","abstract":"The Smart Irrigation System is an innovative solution aimed at improving water efficiency in agriculture and landscaping. It integrates advanced sensors, including soil moisture, temperature, humidity and rainfall sensors, to monitor environmental and soil conditions in real time. By analyzing this data alongside weather forecasting and machine learning algorithms, the system determines precise water requirements, ensuring irrigation is applied only when necessary and in optimal amounts. Weather forecasting enhances the system by enabling adjustments to irrigation schedules based on anticipated conditions, such as rainfall or temperature changes. Machine learning improves adaptability by identifying patterns and optimizing strategies specific to crop and environmental variations. This reduces water wastage, prevents over-irrigation, and supports sustainable farming practices. Designed for precision farming, the system addresses critical water management challenges, promoting better crop health, higher yields, and environmental sustainability. It is a practical, technology-driven tool for modern farming and landscaping needs.","author":[{"family":"Hiray","given":"Srushti"},{"family":"More","given":"Saiprasad"},{"family":"Dhokale","given":"Shantanu"},{"family":"Siddha","given":"Om"},{"family":"Shelake","given":"Nitin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iciss63372.2025.11076297","URL":"https://doi.org/10.1109/iciss63372.2025.11076297","source":"crossref"},{"id":"doi:10.3389/fpls.2025.1668545","type":"article-journal","title":"Cloud-edge-device collaborative computing in smart agriculture: architectures, applications, and future perspectives.","abstract":"Smart agriculture is rapidly evolving in response to growing global demands for food security and sustainable resource management. Cloud-edge-device collaborative computing has emerged as a transformative paradigm, addressing the limitations of traditional centralized architectures by enabling distributed intelligence, real-time processing, and adaptive decision-making. This review provides a comprehensive overview of the architectures, technical characteristics, and application scenarios of cloud-edge-device collaboration in agriculture. Key domains covered include environmental monitoring, intelligent irrigation, UAV-machinery coordination, livestock health management, and pest and disease control. Major challenges such as device heterogeneity, data consistency, resource constraints, and privacy concerns are identified and discussed. Furthermore, six critical research directions are outlined, including intelligent scheduling algorithms, lightweight edge AI, hierarchical data fusion, federated learning, interoperability frameworks, and digital twin technologies. This review aims to serve as a practical reference and theoretical foundation for advancing the design and implementation of next-generation smart agriculture systems.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.3389/fpls.2025.1668545","URL":"https://doi.org/10.3389/fpls.2025.1668545","source":"pubmed"},{"id":"doi:10.1016/j.ohx.2025.e00711","type":"article-journal","title":"MyNutriCapsule: An innovative approach to reduce water and nutrient waste in fertigation farming.","abstract":"Although fertigation offers substantial efficiency and productivity benefits, it also has significant drawbacks. Setting up a fertigation system requires considerable costs and knowledge and professionalism in managing soil, water, and fertiliser. Inefficient fertigation practices can also lead to groundwater contamination from nutrients leaching beyond the root zone. Consequently, this study aimed to introduce the MyNutriCapsule, an innovative product designed by Mr. Azlan Abdul Aziz, a senior lecturer from Universiti Teknologi MARA, Malaysia. The product was primarily employed to significantly reduce water and nutrient waste in fertigation agriculture. MyNutriCapsule recorded 98% and 18% reduction in fertiliser and liquid nutritional fertiliser wastage, respectively. The product also documented a 20% reduction in treated water consumption and a 27% decrement in overall operational costs. The observations validated the efficiency of MyNutriCapsule in promoting sustainable and cost-effective agricultural practices.","author":[{"family":"Na","given":"Mohamad"},{"family":"Wn","given":"Wan"},{"family":"Sn","given":"Nadrah"},{"family":"Ns","given":"Muhammat"},{"family":"Nf","given":"Omar"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.ohx.2025.e00711","URL":"https://doi.org/10.1016/j.ohx.2025.e00711","source":"pubmed"},{"id":"doi:10.1002/jsfa.70288","type":"article-journal","title":"Agricultural science: a CiteSpace-based bibliometric analysis of global and Chinese research.","abstract":"In the face of global population growth, climate volatility and mounting ecological pressures, agricultural science is shifting from traditional yield-centered paradigms toward integrated, sustainable development models. This study employs CiteSpace (version 6.1.5) to conduct a comprehensive bibliometric analysis of 1780 scholarly publications on agricultural science research from 2000 to 2024, drawn from both the Web of Science and China National Knowledge Infrastructure (CNKI) databases. By adopting a systematic process of article selection as represented by the PRISMA flowchart, the dataset was refined through rigorous inclusion and exclusion criteria to ensure analytical robustness. CiteSpace, a powerful visualization and analysis tool, and VOSviewer were used to conduct keyword co-occurrence mapping, cluster analysis, temporal evolution modeling and institutional collaboration analysis. The results reveal three dominant global research themes: climate change adaptation, agricultural system resilience and technological innovation. Global trends augment precision agriculture, carbon management and digitalization. Chinese studies continue to focus on yield increment and improvement of principal crops, underlined by the growing application of smart agriculture, ecological administration and rural revitalization policies. Institutional research finds Jiangsu University to be an essential node in China's agricultural science network. By synthesizing cross-regional, bilingual datasets, this study offers new evidence for the converging but also diverging paths of agricultural research worldwide and in China. Such evidence is supportive of the use of evidence-based policy making, academic strategy and innovative agricultural reform in the context of sustainable development. &#xa9; 2025 Society of Chemical Industry.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/jsfa.70288","URL":"https://doi.org/10.1002/jsfa.70288","source":"pubmed"},{"id":"doi:10.4018/979-8-3373-3962-7.ch016","type":"article-journal","title":"Agricultural Applications of Chalcogenide-Based Materials","abstract":"Food chain has been altered through farming nanotechnology, which energizes such elements as Sulfur (S) and Selenium (Se), and several industries, such as crop farming, aquaculture, tree forestry, animal and poultry farms, and plant nutrients, have utilized this technology. Sulphur nanofertilizers reduce the stress level on the environment, increase the fertility of the soil, and optimize nutrient release. Selenium agents impede the occurrence of micronutrient insufficiency in human beings and animals, and Chalcogenide concentration minimizes the intake of synthetic additives and optimizes the conversion rate of feeds. The use of sulfur fertilizer helps activate sprouting and improves tolerance to diseases. Intelligent sensors with chalcogenides and optoelectronic agricultural plans can provide real-time information on the moisture of the soil, soil nutrients, and stress. These products increase nutrition, demand fewer resources, and provide adaptable agriculture approaches in an evolving climate.","author":[{"family":"Akhter","given":"Md"},{"family":"Miah","given":"MS"},{"family":"Rahman","given":"Habibur"},{"family":"Rahman","given":"SMM"},{"family":"Karim","given":"AJMS"},{"family":"Ratul","given":"Sakibul"},{"family":"Rahman","given":"Mohammed"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-3962-7.ch016","URL":"https://doi.org/10.4018/979-8-3373-3962-7.ch016","source":"crossref"},{"id":"doi:10.1109/ectidamtncon64748.2025.10962023","type":"article-journal","title":"Promoting 21<sup>st</sup> Century Skills in Programming Education through Collaborative and Problem-Based Learning in Smart Farming","abstract":"The development of 21stcentury skills are essential to prepare students for success in a rapidly transforming world. However, integrating these skills into programming courses raises challenges as it often prioritizes technical expertise while overlooking soft skills such as creativity. Additionally, traditional programming instruction tends to focus on individual tasks which limits opportunities for students to develop their collaboration and communication skills. As such, this research proposes the integration of collaborative learning and problem-based learning approaches to promote 21stcentury skills among secondary school students through learning activities about smart farm programming. The results demonstrated significant improvements across all measured 21stcentury skills with Authentic Problem-Solving (APS) and Knowledge Creation Efficacy (KCE) as the most substantial growth. Besides, there are significant positive correlations between each of the skills. Creativity (CreT) and Knowledge Creation Efficacy (KCE) also emerged as key factors driving the development of other competencies. These findings validate the adoption of collaborative and problem-based learning approaches as effective methods for enhancing 21stcentury skills in programming studies and also highlight their importance in the curriculum design to address future challenges in education.","author":[{"family":"Kaewkamol","given":"Porntida"},{"family":"Thanyaphongphat","given":"Jirapipat"},{"family":"Noamna","given":"Somkeit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ectidamtncon64748.2025.10962023","URL":"https://doi.org/10.1109/ectidamtncon64748.2025.10962023","source":"crossref"},{"id":"doi:10.21203/rs.3.rs-4948307/v1","type":"article-journal","title":"Sustainable Automated Vertical Farming","abstract":"Abstract This study offers a thorough strategy for automated vertical farming that is sustainable in response to the urgent problems that traditional agricultural methods are currently facing. The primary objective is to design and implement a real-time monitoring and alert system which is capable of optimizing growing conditions and ensuring the long-term viability of vertical farming operations. The system architecture revolves around the integration of sensor technology, automation, and data analytics to enable proactive management of environmental parameters crucial for plant growth. Specifically, sensors are connected to a microcontroller to capture data on temperature, humidity, motion, light intensity, fire state, air quality, and soil moisture. This data is continuously monitored and analyzed in real-time to detect anomalies and deviations from optimal conditions. Upon detecting abnormal conditions such as low light intensity, fire risks, low soil moisture, or unstable rack conditions, the system triggers alerts via SMS using the Twilio service. These alerts are sent to some designated recipients, allowing for timely interventions to rectify the situation and prevent potential crop loss. The proposed system aims to address key gaps and areas of improvement in current vertical farming practices. The results or potential benefits involve reduction in energy costs and water usage based on analytic report custom to farmer, reducing operational expenses and trade it with one-time capital expense by means of reduction in labor costs cut by 40-60% (estimated) and further help to avoid skill issue concern of the labors. The crop production process is made more efficient and optimized with precise use of natural resources which in-turn makes the system more sustainable and improves crop yield and quality. The process gets automated by using actuators which rectify or act on emergency alerts instantly, therefore increasing reliability and propose customization to the customer. By providing a proactive approach to environmental management, it seeks to enhance resource efficiency, crop quality, and overall productivity. Moreover, by leveraging advanced data analytics techniques, the system offers insights into environmental trends and patterns, enabling informed decision-making and adaptive responses. Overall, the system represents a significant step towards the realization of sustainable automated vertical farming. By harnessing the power of sensor technology, automation, and data analytics, it offers a scalable and efficient solution to the challenges facing modern agriculture. It can fully realize vertical farming's potential as a resilient and sustainable food production system for the future use.","author":[{"family":"Barve","given":"Prateek"},{"family":"Dixit","given":"Mridulay"},{"family":"Roy","given":"Sritama"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21203/rs.3.rs-4948307/v1","URL":"https://doi.org/10.21203/rs.3.rs-4948307/v1","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-134-4-14","type":"article-journal","title":"EFFICIENCY OF LABOR OPERATIONS WHEN FEEDING MIXTURE ON FEEDING TABLES","abstract":"The article presents the results of the analysis of labor operations carried out in the process of mechanized distribution and feeding of feed mixtures in free housing of animals The article presents the results of the analysis of labor operations carried out in the process of mechanized distribution and feeding of feed mixtures in free housing of animals The article presents the results of the analysis of labor operations carried out in the process of mechanized distribution and feeding of feed mixtures in free housing of animals, free housing. When comparing the above manual methods of pusher feed mixtures, it was established that when using a shovel for 100 cows at a time, 5.01 minutes of working time were spent, when using forks – 8.12 minutes, and when using a hand scraper – only 2.12 minutes. In modern complexes, the fastest way to hill feed is with a tractor. This takes 1.02 minutes per 100 cows. The “Butler Gold” robot works much more slowly. It takes 4.96 minutes for this operation. It was found that the feeding behavior of dairy cows depended on feeding management factors, including the frequency of feed distribution and its pusher. The activation of the feeding behavior of animals was characterized by an increase in the number of animals near the feed table when performing the technological operations of feed distribution and pushing (moving feed to the animal on the feeding table). Performing the technological operation of distributing feed mixtures twice a day led to an increase in the number of cows near the feed table by 20.9 % – 22.0 % of the total number of animals in the pen (126±5.2 heads). Performing the technological operation of pusher feed also led to an increase in the number of cows near the feed table by 2.3 % – 11.3 % of the total number of animals in the group. The remains of feed removed beyond the border of the feed table were perceived by the animals as fresh bedding for rest, which led to a reduction in the total feeding front.","author":[{"family":"Admin","given":"Olexandr"},{"family":"Greben","given":"Leonid"},{"family":"Admina","given":"Natalia"},{"family":"Osypenko","given":"Tetiana"},{"family":"Admin","given":"Bohdan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-134-4-14","URL":"https://doi.org/10.32900/2312-8402-2025-134-4-14","source":"crossref"},{"id":"doi:10.36722/jpm.v7i3.4617","type":"article-journal","title":"Gerakan Desa Blumbang Menuju Zero Waste: Smart Farming dengan Pengolahan Kotoran Sapi sebagai Solusi Pertanian Berkelanjutan","abstract":"&lt;p align=\"center\"&gt;&lt;strong&gt;Abstrak &lt;/strong&gt;&lt;/p&gt;&lt;p align=\"center\"&gt;&lt;strong&gt; &lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;em&gt;Permasalahan utama yang dihadapi mitra, yaitu masyarakat Desa Blumbang, adalah tingginya volume limbah kotoran sapi yang belum diolah secara optimal dan masih dibuang sembarangan, sehingga berpotensi mencemari lingkungan serta belum memberikan nilai tambah ekonomi. Kegiatan pengabdian ini bertujuan untuk memberdayakan masyarakat melalui edukasi dan pelatihan smart farming, khususnya dalam pengolahan limbah kotoran sapi menjadi pupuk kompos sebagai bentuk inovasi pertanian berkelanjutan. Jumlah peserta kegiatan ini sebanyak 35 orang, yang terdiri dari peternak lokal, kelompok tani, serta perangkat desa. Metode pelaksanaan meliputi pendekatan partisipatif, transfer teknologi tepat guna, serta pelatihan dan pendampingan lapangan secara intensif. Tahapan kegiatan mencakup identifikasi masalah mitra, penyusunan modul pelatihan, sosialisasi program, pelatihan teknis pembuatan kompos, praktik langsung di lapangan, serta monitoring dan evaluasi hasil. Hasil kegiatan menunjukkan bahwa peserta mampu memahami konsep zero waste dan menerapkan teknik pengomposan secara mandiri. Selain itu, terjadi nilai peningkatan pengetahuan dan keterampilan peserta dalam mengolah limbah menjadi produk bernilai guna, serta munculnya komitmen bersama untuk menjaga keberlanjutan program. Kesimpulannya, program ini berhasil meningkatkan kapasitas masyarakat dalam menerapkan smart farming berbasis ekonomi sirkular dan mendukung terciptanya desa yang lebih ramah lingkungan.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Kata kunci&lt;em&gt;: Smart Farming, Zero Waste, Pengolahan Limbah, Pupuk Kompos, Pertanian Berkelanjutan.&lt;/em&gt;&lt;/strong&gt;&lt;/p&gt;","author":[{"family":"Sundari","given":"Ariefah"},{"family":"Arisandra","given":"Martha"},{"family":"Efendi","given":"Moh"},{"family":"Indriani","given":"Arya"},{"family":"Fahrudin","given":"Ahmad"},{"family":"Habibah","given":"Nur"}],"issued":{"date-parts":[[2025]]},"DOI":"10.36722/jpm.v7i3.4617","URL":"https://doi.org/10.36722/jpm.v7i3.4617","source":"crossref"},{"id":"doi:10.24226/jvr.2025.4.35.1.51","type":"article-journal","title":"An Exploratory Study on the Development of a Social Farming Practice Model Utilizing Smart Agriculture for Individuals with Psychosocial Disability","abstract":"In the era of the Fourth Industrial Revolution, vocational rehabilitation for individuals with Psychosocial Disability faces new challenges, with job creation for sustainable economic independence emerging as a critical issue. This study explores the possibility of applying social agriculture as a vocational rehabilitation approach for individuals with Psychosocial Disability and proposes practical and policy strategies utilizing smart agriculture technology. To achieve this, focus group interviews (FGI) were conducted with five experts who have experience in social agriculture and smart agriculture, and representative cases of urban and rural social agriculture were analyzed. The results revealed practical models from Company A (urban) and Company B (rural). For Company A (urban), the need to utilize idle urban spaces for the introduction of smart agriculture systems and the development of tailored job models for individuals with disabilities was emphasized. Additionally, legal recognition as agricultural workers and the introduction of a support worker system for agriculture, along with related education, were considered crucial. In Company B (rural), the focus was on establishing a joint production and sales network and building a sustainable smart agriculture model through cooperation with government and local authorities. The need for financial support systems, such as low-interest loan programs, was also identified. This study presents the potential of smart agriculture as a vocational rehabilitation model for individuals with Psychosocial Disability from both practical and policy perspectives. It suggests that future research should focus on evaluating the effectiveness of smart agriculture-based vocational rehabilitation programs for individuals with disabilities.","author":[{"family":"Lee","given":"Yongpyo"},{"family":"Choi","given":"Youngkwang"},{"family":"Ahn","given":"Heeyeon"}],"issued":{"date-parts":[[2025]]},"DOI":"10.24226/jvr.2025.4.35.1.51","URL":"https://doi.org/10.24226/jvr.2025.4.35.1.51","source":"crossref"},{"id":"doi:10.63056/acad.004.03.0615","type":"article-journal","title":"An IOT-Driven Smart Agriculture Framework for Precision Farming, Resource Optimization, and Crop Health Monitoring","abstract":"The integration of the Internet of Things (IoT) into agriculture is revolutionizing the way food is produced, managed, and distributed. By combining networks of smart sensors, advanced communication protocols, distributed computing, and artificial intelligence (AI), IoT-based smart farming systems allow for precision monitoring and management of agricultural resources. These systems enable farmers to optimize irrigation, monitor crop health, and make real-time, data-driven decisions, thereby addressing challenges such as water scarcity, climate variability, and the growing demand for food. This paper presents an expanded IoT-driven smart agriculture framework with modular architecture, incorporating a perception layer, network layer, compute layer, application layer, and end-user layer. The framework integrates AI-based predictive analytics, blockchain for supply chain transparency, and renewable energy-powered devices. A pilot implementation on a 5-hectare wheat farm demonstrated a 30% reduction in water usage, early disease detection accuracy of 92%, and improved scalability for multi-crop environments. Comparative analysis with conventional farming practices shows significant improvements in resource efficiency and operational sustainability. The paper provides a detailed literature review, system design, experimental methodology, and future research directions, with a focus on interoperability, cost-effectiveness, and sustainability.","author":[{"family":"Irfan","given":"Engr"},{"family":"Zaka","given":"Engr"},{"family":"Rehman","given":"Engr"},{"family":"Sattar","given":"Bushra"},{"family":"Haider","given":"Syed"},{"family":"Hayat","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.63056/acad.004.03.0615","URL":"https://doi.org/10.63056/acad.004.03.0615","source":"crossref"},{"id":"doi:10.1016/j.farsys.2025.100139","type":"article-journal","title":"How has scientific literature addressed crop planning at farm level: A bibliometric-qualitative review","abstract":"Crop planning (CP), being the core of farm management and decision-making, remains significant as the selection and allocation of appropriate crops determine the economics and sustainability of farming system. A systematic literature review was conducted to obtain a structural overview and consolidate the knowledge from CP literature, given the dearth of review articles in this domain. The methodology included systematic selection of literature in phases and mixed-method systematic review process consisting of bibliometric analysis and qualitative review. This enabled an understanding the main characteristics of CP literature and answer how CP has been addressed at farm level. 1516 publications were selected in first phase after which 652 were screened using bibliometric analysis software, VOSviewer and CiteSpace, in second phase to identify research hotspots and recent trends. Optimization, irrigation, sustainability, adaptation were certain hotspots, while a shift in research trend was observed from decision support, crop allocation and bioenergy to climate change, water resources and big data. Last phase focussed on qualitative review of 31 publications on farm. Three broad themes of articles emerged namely “farmer's decision-making”, “soil-water-agroecology” and “merits of innovative technologies”. The study proposed several recommendations for small farming systems which were largely ignored in literature. These include factorial design for crop combinations, choices in options, estimation of crop diversity index and relative time-dispersion in yields. The current review produced a macroscopic overview of accumulated knowledge on CP and provided future directions to harness the unexplored potential in this field. • Crop planning is vital for sustainable, profitable and resilient farming systems. • The review analysed 1516 publications, identifying key research trends and hotspots. • Optimization, irrigation and sustainability are key research hotspots in literature. • Research trends shifted to climate change, water resources, and big data applications. • Small farming systems are underrepresented in literature, needing future exploration.","author":[{"family":"Deo","given":"Aniket"},{"family":"Sawant","given":"Namita"},{"family":"Arora","given":"Amit"},{"family":"Karmakar","given":"Subhankar"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.farsys.2025.100139","URL":"https://doi.org/10.1016/j.farsys.2025.100139","source":"crossref"},{"id":"doi:10.1201/9781003239963-2","type":"article-journal","title":"Sustainable Integrated Farming Systems for Food and Nutrition Security","abstract":"The aim of the sustainable IFS is to increase income of a farm family as well as ensure food and nutritional security, while maintaining the ecological balance and environmental health. Modern IFS also follow Climate Smart Agriculture (CSA) for addressing the interconnected issues of climate change and food security through the three dimensions (economic, social and environmental) of sustainable development. Safe food production, marketing and consumption are interrelated and essential components of a food system that ensures food items are safe for consumption and free from harmful contaminants or pathogens. To ensure safe food production, food producers must implement regulations and guidelines, good agricultural practices (GAP) and good manufacturing practices (GMP). Partnerships and collaborations between farmers, governments, private sector, civil society and other stakeholders can help to increase food security, nutrition security and safe food production, marketing and consumption. Modern science and engineering tools such as IoT, robotics, drones and machine-learning techniques can be integrated to achieve the goals of sustainable IFS. Knowledge and wisdom of traditional farming systems may be taken forward to the future models of IFS to address the needs of climate, food habit and other transformations in agri-food system. In this chapter, the future IFS models for coastal, dry and arid, hill agro-ecosystems as well as for the eastern region of India is described. Agro-ecotourism-based IFS, raised and sunken bed farming, multi-enterprise model, banana-based IFS, roof top farming and export-oriented IFS are some of the important aspects discussed in this chapter.","author":[{"family":"Sarangi","given":"Sukanta"},{"family":"Mohanty","given":"Rajeeb"},{"family":"Munilkumar","given":"Sukham"},{"family":"Sundaray","given":"Jitendra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003239963-2","URL":"https://doi.org/10.1201/9781003239963-2","source":"crossref"},{"id":"doi:10.1115/omae2025-155006","type":"article-journal","title":"Experimental and Numerical Analysis of Hydrodynamic Forces on Non-Traditional Net Types Used in Salmon Farming","abstract":"Abstract On order to minimize their environmental impact and make use of more exposed sites, innovative types of nets, complementary to the traditional polyester nets, have been investigated. One of them are metallic nets made of a copper alloy that not only allow for the use of a single net, leaving behind the need of a predator netting system, but also reduce the presence of biofouling while better controlling the production volume due to its higher wet weight and axial stiffness compared to commonly used nets used in aquaculture operations. Another innovative type of net are low-porosity membranes, which are used to contain organic residues on the bottom of the cage or to constrain the exchange of water between the inside of the cage and the external flow, limiting the effects of diseases or sudden environmental changes on the biomass. Currently, there is a gap in the determination of hydrodynamic response on these innovative netting systems, considering typical operational and extreme conditions on aquaculture sites. Thus, the present work numerically simulates drag and lift forces on single nets considering a wide range of current speeds and angles of attack using the open-source CFD code REEF3D. The nets are implemented according to the Screen Force Model, where the hydrodynamical forces are estimated with an experimental data basis of drag and lift coefficients fitted into a truncated Fourier series, obtained from experiments at the Wave/Towing tank at Universidad Austral de Chile. The results emphasize the need to carry out experiments to describe drag and lift forces for each netting types before more complex scenarios are modeled while, since the initial results, using a generic formulation for drag and lift coefficients, lead to large errors on the numerical results, discrepancies that are reduced when the Fourier series specifically determined for the net are implemented on the numerical scheme.","author":[{"family":"Matamala","given":"Pablo"},{"family":"Barrientos","given":"Vicente"},{"family":"Cifuentes","given":"Cristian"},{"family":"Tampier","given":"Gonzalo"},{"family":"Brown","given":"Alex"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1115/omae2025-155006","URL":"https://doi.org/10.1115/omae2025-155006","source":"crossref"},{"id":"doi:10.1088/1742-6596/2942/1/012041","type":"article-journal","title":"A Smart Farming System for Rubber Nursery Management in Monitoring Plant Growth Performance Using IoT Technology","abstract":"Abstract Rubber plantations are an integral part of economy in Malaysia. However, inadequate soil moisture poses a significant problem for rubber trees as it can lead to water stress, ultimately hindering their growth, leaf development, and latex production. Water stress occurs when the trees are unable to obtain sufficient water from the soil, which resulting in stunted growth, leaf development, leading to fewer and smaller leaves. There is needed an effective water management strategy to ensure optimal growth of rubber trees for latex production. Thus, this project is aim to design and build an active soil monitoring system based on the Internet of Things (IoT). This system is made up of two major components: soil moisture and light intensity. The first component is a soil moisture sensor, which determines the soil’s moisture content; light intensity sensor, which detects the intensity of the light and ANSELF Brushless DC Pump connected to an Arduino. This system provides sustainable solutions to increase crop output, reduce waste, and develop a greener plant cultivation. This smart monitoring plant growth system prototype is important in agriculture and plant production. It has potential to promote healthy plant growth and increase agricultural production.","author":[{"family":"Sadikan","given":"SFN"},{"family":"Aziz","given":"MLHA"},{"family":"Umor","given":"MAS"},{"family":"Mahzan","given":"S"},{"family":"Marjudi","given":"S"},{"family":"Salamat","given":"MA"},{"family":"Dunne","given":"RS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1088/1742-6596/2942/1/012041","URL":"https://doi.org/10.1088/1742-6596/2942/1/012041","source":"crossref"},{"id":"doi:10.1016/j.jenvman.2025.127426","type":"article-journal","title":"Using the SMART-Farm Tool to identify linchpin farming practices for the improvement of the atmosphere-related sustainability performance of the Luxembourgish agriculture sector","abstract":"Agriculture is a major source of environmental emissions, including greenhouse gases (GHG), ammonia and other air pollutant emissions, particularly in livestock-intensive countries such as Luxembourg. Organic agriculture has attracted attention as a more environmentally friendly agricultural management system. This study assessed the atmosphere-related sustainability performance of 87 farms (4.5 % of all farms in Luxembourg) using the Sustainability Monitoring and Assessment RouTine (SMART)-Farm Tool, which operationalizes the Food and Agriculture Organisation of the United Nations (FAO)'s Sustainability Assessment of Food and Agriculture Systems (SAFA) Guidelines. The sample included 58 conventional and 29 organic farms. Results showed that organically managed farms (orgF) achieved significantly higher sustainability scores than conventional farms (conF) in the Atmosphere theme (orgF mean: 63.8 %, conF mean: 56.6 %, p < 0.001), as well as in the sub-themes Air Quality (orgF mean: 69.3 %, conF mean: 59.1 %, p < 0.001) and Greenhouse Gases (orgF mean: 57.7 %, conF mean: 53.5 %, p = 0.002). Indicator-level analysis identified two key improvement strategies: (1) increasing concentrated feed autarky, with organic farms relying less on external protein and energy feeds; and (2) closing nutrient cycles, evidenced by higher use of legumes, green cover, and lower nitrogen inputs. These practices were strongly associated with improved atmospheric sustainability performance. Additionally, practices such as reduced tillage and cover cropping were underutilized across all systems, indicating broader areas for optimisation. While organic management outperformed conventional, the findings emphasize that many beneficial practices can be adopted system-independently. Policy efforts should focus on supporting these two linchpin strategies to trigger the development of a more sustainable farming system in Luxembourg and increase the sector's atmosphere-related sustainability performance.","author":[{"family":"Stoll","given":"Evelyne"},{"family":"Keßler","given":"Sabine"},{"family":"Leimbrock-Rosch","given":"Laura"},{"family":"Bohn","given":"Torsten"},{"family":"Reckinger","given":"Rachel"},{"family":"Schader","given":"Christian"},{"family":"Herzig","given":"Christian"},{"family":"Zimmer","given":"Stéphanie"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.jenvman.2025.127426","URL":"https://doi.org/10.1016/j.jenvman.2025.127426","source":"europepmc"},{"id":"doi:10.55041/ijsrem54092","type":"article-journal","title":"AI Smart Farming System","abstract":"Abstract—Agriculture is the backbone of India’s rural econ- omy, providing livelihood to nearly 60% of the population. However, productivity is often affected due to plant diseases, unpredictable climate, soil nutrient imbalance, and lack of timely expert guidance. To overcome these challenges, this paper proposes the AI Smart Farming System, a web-based decision- support system that integrates machine learning, deep learning, weather intelligence, multilingual chatbot services, community forums, and fertilizer optimization models. The system uses a CNN model for image-based crop disease detection, a hybrid rule- based and machine-learning method for fertilizer recommenda- tion, and global weather APIs for climate forecasting. The paper discusses the complete methodology, architecture, mathematical models, algorithms, evaluation metrics, and future scalability. The proposed system aims to digitize and modernize farming practices to support rural farmers, reduce crop loss, and improve productivity. Index Terms—Smart Farming, Machine Learning, Deep Learning, CNN, Fertilizer Recommendation, Weather Forecast- ing, Chatbot, Web Application.","author":[{"family":"More","given":"Mr"},{"family":"Salunkhe","given":"Ms"},{"family":"Nikam","given":"Ms"},{"family":"Patil","given":"Mr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55041/ijsrem54092","URL":"https://doi.org/10.55041/ijsrem54092","source":"crossref"},{"id":"doi:10.7160/aol.2025.170310","type":"article-journal","title":"Enhancing Agricultural Productivity and Food Security Through Climate Smart Agriculture (CSA) Adoption: The Interplay of Social, Economic and Environmental in Tidal Swamp Farming","abstract":"Food security is closely linked to agricultural productivity and the adoption of modern technologies. This study examines the socio-economic and environmental factors that drive the adoption of Climate-Smart Agriculture (CSA), enhance productivity, and improve food security in tidal swamp areas. The interrelationships between economic factors such as income and access to capital, and environmental factors like sustainable land management practices and water resource usage, all of which play a crucial role in the adoption of CSA technologies. The study was conducted with 180 farmers in Banyuasin Regency, specifically in Telang Makmur, Panca Mukti and Telang Jaya Villages, who provided data to assess how these factors influence food security outcomes. The findings indicate that both economic and environmental factors significantly affect the adoption of CSA technology, which subsequently leads to increased agricultural productivity and food security. Specifically, economic empowerment through higher income levels and enhanced access to capital enables farmers to invest in CSA technologies, while environmentally sustainable practices help mitigate climate risks and improve land and water management. The results underscore the importance of integrated approaches that address both economic and environmental dimensions to ensure long-term food security. This study provides valuable insights for policymakers, stressing the need for strategies that combine economic support, technological innovation, and environmental sustainability to enhance food security in regions like Muara Telang.","author":[{"family":"Yamin","given":"Muhammad"},{"family":"Sulastri","given":"Merna"},{"family":"Damayanthy","given":"Dini"},{"family":"Andelia","given":"Siti"},{"family":"Tafarini","given":"Firdha"},{"family":"Wahyu","given":"Trisna"},{"family":"Putri","given":"Swasdiningrum"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7160/aol.2025.170310","URL":"https://doi.org/10.7160/aol.2025.170310","source":"crossref"},{"id":"doi:10.4018/979-8-3373-3296-3.ch010","type":"article-journal","title":"Enhancing Agricultural Cybersecurity","abstract":"The rapid digital transformation of agriculture through smart farming technologies has introduced new cybersecurity challenges that threaten the integrity, confidentiality, and availability of critical agricultural data and systems. As precision agriculture, Internet of Things (IoT)-enabled sensors, and automated decision-making become integral to modern farming, the risks associated with cyber threats—such as data breaches, ransomware attacks, and supply chain vulnerabilities—continue to escalate. Unlike traditional security measures, AI-driven solutions, including deep learning and Large Language Models (LLMs), offer real-time threat detection, adaptive defense mechanisms, and enhanced risk assessment capabilities. This chapter explores the application of these technologies in securing agricultural networks, from intrusion detection to automated incident response. It also presents case studies of AI-driven cybersecurity solutions implemented in agricultural environments.","author":[{"family":"Zangana","given":"Hewa"},{"family":"Luckyardi","given":"Senny"},{"family":"Mustafa","given":"Firas"},{"family":"Li","given":"Shuai"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-3296-3.ch010","URL":"https://doi.org/10.4018/979-8-3373-3296-3.ch010","source":"crossref"},{"id":"doi:10.38124/ijisrt/25apr1024","type":"article-journal","title":"Bridging the Digital Divide in Agriculture: Lessons from the United States and Africa in Smart  Farming Adoption","abstract":"The adoption of smart farming has altered food production by increasing efficiency, sustainability, and productivity. However, there is a digital divide, with affluent countries such as the United States benefiting from advanced agricultural technologies, nevertheless, many African countries face limited access to digital tools, inadequate infrastructure, and financial restraints. This disparity has implications for food security, economic development, and global agricultural sustainability, prompting an in-depth examination of the factors impacting smart farming adoption in different regions. This review examines the benefits and impact of smart farming adoption on agricultural productivity, as well as identifies the potential benefits of cross-regional knowledge sharing across the United States and Africa. The findings indicate that smart farming technologies have considerably increased agricultural productivity and sustainability in the United States, due to strong government initiatives, public-private collaborations, and widespread digital infrastructure. In contrast, African farmers confront limited broadband connection, financial constraints, and insufficient institutional support, which restricts the adoption of precision agriculture and data-driven farming. Therefore, bridging the digital divide in agriculture necessitates a comprehensive approach that combines technology, policy, and capacity- building efforts.","author":[{"family":"Oshikoya","given":"Samuel"},{"family":"Adeyeye","given":"Adekunle"},{"family":"Obebe","given":"Olufisayo"},{"family":"Adeyeye","given":"Oluwatosin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.38124/ijisrt/25apr1024","URL":"https://doi.org/10.38124/ijisrt/25apr1024","source":"crossref"},{"id":"doi:10.33545/26180723.2025.v8.i7b.2108","type":"article-journal","title":"Assessing flood effects on rice farming and the efficacy of climate-smart practices for agricultural resilience in region 5, Guyana","abstract":"This study investigates the effects of the 2021 flood on rice farmers in Region 5, with a focus on losses incurred during the end of the first crop and the onset of the second crop of that year. The study also proposes climate-smart agricultural (CSA) strategies to enhance resilience in the region. Region 5, situated on Guyana’s low coastal plain approximately three meters below sea level, is highly vulnerable to natural disasters such as flooding. In May and June 2021, Guyana experienced unprecedented rainfall, resulting in the most severe flood event in over two decades. This flood, classified as Level 3, led to widespread damage in Region 5, including the destruction of crops, livestock, homes, and infrastructure, largely due to overtopped and breached conservancy dams, high tides, and inadequate drainage systems. Field data were collected using the farmer register provided by the Guyana Rice Development Board (GRDB). Losses were categorized into three primary types: (i) Harvesting Loss, (ii) Sowing Loss, and (iii) Land Preparation Loss. These were verified by a technical team from the Ministry of Agriculture, including GRDB Extension Officers. Results showed that June 2021 recorded over 500 mm of rainfall, leading to catastrophic flooding. The greatest losses occurred in the sowing category, with 6,932 acres affected across 187 farmers. This was followed by land preparation losses (3,516 acres; 53 farmers) and harvesting losses (2,137 acres; 53 farmers). The total estimated economic loss amounted to GYD $668,885,000. Given the increasing risks posed by climate change, the adoption of climate-smart agricultural practices is critical. Recommended strategies include: eliminating the burning of paddy straw, cultivating flood-tolerant rice varieties, and adhering strictly to GRDB agronomic guidelines.","author":[{"family":"Persaud","given":"Bissessar"},{"family":"Singh","given":"Narita"},{"family":"Persaud","given":"Mahendra"},{"family":"Subramanian","given":"Gomathinayagam"},{"family":"Kokil","given":"Lacram"},{"family":"Arjune","given":"Yunita"},{"family":"Bhagarathi","given":"Lakhnarayan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/26180723.2025.v8.i7b.2108","URL":"https://doi.org/10.33545/26180723.2025.v8.i7b.2108","source":"crossref"},{"id":"doi:10.22452/mjcs.vol38no3.3","type":"article-journal","title":"ENHANCING SMART FARMING WITH CONTAINERIZED DEEP LEARNING AND KUBERNETES: UTILIZING HIPPOPOTAMUS OPTIMIZED ATTENTION MODEL FOR PREDICTIVE AGRICULTURE","abstract":"Abstract The integration of deep learning technologies into agriculture has the potential to revolutionize smart farming by enhancing efficiency, sustainability, and productivity. This study focuses on leveraging the Hippopotamus Optimized Attention Hierarchically Gated Recurrent Algorithm (HOA-HGRA) within a containerized environment to analyze and predict critical agricultural variables such as weather patterns, crop yield, and soil moisture. The proposed methodology involves containerizing deep learning models like HOA-HGRA and orchestrating them with Kubernetes on HPC clusters. This enables precise monitoring and management of crop growth, soil conditions, and livestock health, ensuring optimal resource utilization and enhanced productivity. The hyperparameters tuning and the performance optimization are performed by applying the Oppositional Hippopotamus optimization with opposition learning-based strategy. The overall performance of the AHGR-OH model is validated by utilizing the France-CGIAR BRIDGE, Smart Agriculture, Smart precision agriculture, Smart Farming Irrigation Systems, and IoT in Smart Farming Market Report datasets. Moreover, key metrics such as latency, precision, F1-score, recall, scalability, accuracy, MSE, and ROC are utilized to estimate the effectiveness of the AHGR-OH method. By comparing, the developed method grants 2s latency, 0.5 MSE, higher scalability, precision, F1-score, accuracy, and recall of 98.5%, 97.9%, 97.4%, 99.1%, and 97.9% respectively. This paper demonstrates the potential of the AHGR-OH Algorithm to revolutionize smart farming practices.","author":[{"family":"Hasan","given":"Syed"},{"family":"Author","given":"Usman"},{"family":"Hasan","given":"Syed"},{"family":"Hasan","given":"Syeda"},{"family":"Alquraishee","given":"Anser"}],"issued":{"date-parts":[[2026]]},"DOI":"10.22452/mjcs.vol38no3.3","URL":"https://doi.org/10.22452/mjcs.vol38no3.3","source":"crossref"},{"id":"doi:10.21776/ub.habitat.2025.036.3.21","type":"article-journal","title":"Analysis of Factors Affecting Rice Farmers' Intentions in the Use of Smart Farming Technology in Kanigoro Village, Pagelaran Sub-District, Malang Regency","abstract":"The low adoption of smart farming technology among farmers, despite the availability of tools in Kanigoro Village, Pagelaran Subdistrict, is the main issue addressed in this study. Technologies such as the Smart Soil Sensor and Bird Control Sound System have not been optimally utilized, even though they can improve agricultural efficiency and productivity. This study aims to analyze the influence of attitude, subjective norm, and perceived behavioral control on farmers’ intention to adopt smart farming technology, using the Theory of Planned Behavior (TPB) framework. The research employed a quantitative approach involving 100 rice farmers, with data collected through structured questionnaires and direct interviews. Data were analyzed using Structural Equation Modeling - Partial Least Square (SEM-PLS) with the help of WarpPLS 7.0 software. The results show that all three independent variables-attitude, subjective norm, and perceived behavioral control-have a positive and significant effect on farmers’ intention. Among these, perceived behavioral control has the most dominant influence, followed by subjective norm and attitude. These findings suggest that beyond building positive attitudes, it is essential to strengthen social support and increase farmers' confidence in their ability and access to technology to enhance the adoption of smart farming practices.","author":[{"family":"Aulia","given":"Syifa"},{"family":"Riana","given":"Fitria"},{"family":"Hartono","given":"Rachman"},{"family":"Nugroho","given":"Tri"},{"family":"Meitasari","given":"Deny"},{"family":"Rahman","given":"Moh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21776/ub.habitat.2025.036.3.21","URL":"https://doi.org/10.21776/ub.habitat.2025.036.3.21","source":"crossref"},{"id":"doi:10.30738/ad.v7i2.18157","type":"article-journal","title":"Pelatihan intergrated smart farming melalui sistem aquaponik di Kebun Dakwah Muhammadiyah","abstract":"Pelatihan ini bertujuan peningkatan kesejahteraan mitra Kebun Dakwah Muhammadiyah dengan pengoptimalisasian smart farming melalui sistem aquaponic berbasis IoT. Metode yang digunakan dalam pengabdian kepada Masyarakat ini dikaukan secara luring yang bertempat di Kebun Dakwah Muhammadiyah terletak pada Jl. Nitikan Baru No.88 A, Sorosutan, Kec.Umbulharjo, Kota Yogyakarta, Daerah Istimewa Yogyakarta. Permasalahan di Kebun Dakwah Muhammadiyah dapat diatasi melalui Sosialisasi, Pelatihan integrated smart farming untuk mitra, Penerapan Teknologi intergrated Smart Farming, serta Pendampingan dan Evaluasi. Hasil Pengabdian kepada Masyarakat ini dibuktikan dengan adanya pelatihan dan penerapan integrated smart farming yang berupa aquaponic. Pelatihan dan penerapan ini menggunakan sayuran kangkung dan ikan lele. Sayuran kangkung dipilih dikarenakan sebagai salah satu tanaman yang banyak digemari oleh Masyarakat Indonesia dan memiliki nilai ekonomi yang tinggi. Ikan lele digunakan dipilih dikarenakan sebagai salah satu komoditas ikan air tawar yang banyak diminati oleh masyarakat di Indonesia dan peminatnya selalu meningkat setiap tahunnya. Hal ini juga dibuktikan dengan meningkatnya pemahaman mitra untuk mengembangkan atau budidaya sayuran dengan ikan dengan waktu yang bersamaan melalui hasil rata-rata hasil skor pre-tes 5,75 dan hasil rata-rata post-test sebesar 8,95. Hal tersebut menunjukkan peningkatan sebesar 3,2 poin. Oleh karena itu, pelatihan ini dapat dibuktikan bahwa penerapan integrated smart farming dapat meningkatkan kemampuan mitra dalam pengoptimalisasian smart farming melalui sistem aquaponic berbasis IoT. Training on integrated smart farming through aquaponic system aquaponics at the Muhammadiyah Da'wah Garden Abstract: This training aims to improve the welfare of Muhammadiyah Da'wah Farm partners by optimizing smart farming through an IoT-based aquaponic system. The method used in this community service is conducted offline at the Muhammadiyah Da'wah Garden located at Jl. Nitikan Baru No.88 A, Sorosutan, Kec.Umbulharjo, Yogyakarta City, Yogyakarta Special Region. Problems at the Muhammadiyah Da'wah Farm can be overcome through socialization, integrated smart farming training for partners, application of integrated smart farming technology, and assistance and evaluation. The results of this Community Service are evidenced by the training and application of integrated smart farming in the form of aquaponic. This training and application uses kale vegetables and catfish. Kale vegetables were chosen because they are one of the plants that are widely favored by the Indonesian people and have high economic value. Catfish is used because it is one of the freshwater fish commodities that are in great demand by the people in Indonesia and its demand always increases every year. This is also evidenced by the increased understanding of partners to develop or cultivate vegetables with fish at the same time through the average results of the pre-test score of 5.75 and the average results of the post-test of 8.95. This shows an increase of 3.2 points. Therefore, this training can prove that the application of integrated smart farming can improve partners' ability to optimize smart farming through an IoT-based aquaponic system.","author":[{"family":"Erviana","given":"Vera"},{"family":"Sulisworo","given":"Dwi"},{"family":"Robiin","given":"Bambang"}],"issued":{"date-parts":[[2025]]},"DOI":"10.30738/ad.v7i2.18157","URL":"https://doi.org/10.30738/ad.v7i2.18157","source":"crossref"},{"id":"doi:10.33545/2618060x.2025.v8.i9sc.3782","type":"article-journal","title":"A Comparative cost and return analysis of different cropping systems and integrated farming systems adopted in climate smart agricultural situation in upper Brahmaputra Valley Zone of Assam","abstract":"Rice is the staple crop in the state of Assam. The study was conducted in locations which are climate resilient in nature. Two Agriculture Development Officer’s circles and from each circle three villages were selected. From each village, 20 farm families were selected randomly. Here, different cropping sequences were studied to analyze economically viable one. It was revealed from the study that out of six different combinations of cropping sequences/patterns both Flood tolerant rice - Cauliflower and Fishery cum Duckery sequence in adopter’s combination were found the most viable one and the pooled benefit-cost ratio for both the combinations was calculated as 2.14. In case of non-adopter’s combination, the most viable cropping sequence was recorded as normal winter rice - cauliflower and its pooled benefit cost ratio was calculated as 2.02 followed by normal winter rice - cabbage sequence. Other cropping sequences were not found profitable. The flood tolerant rice - toria and normal winter rice - toria sequences in both adopter’s combination and non-adopter’s combination were found non-viable.","author":[{"family":"Borah","given":"Ajanta"},{"family":"Sarma","given":"Ghana"},{"family":"Singh","given":"Matukdhari"},{"family":"Shohe","given":"Tovinoli"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33545/2618060x.2025.v8.i9sc.3782","URL":"https://doi.org/10.33545/2618060x.2025.v8.i9sc.3782","source":"crossref"},{"id":"doi:10.4018/979-8-3373-2497-5.ch007","type":"article-journal","title":"Animal Regognition and Repellent System for Smart Farming Using AI and Deep Learning","abstract":"The automation of horticulture has been progressing rapidly, with Deep Neural Networks (DNN) and the Internet of Things (IoT) being utilized for precise monitoring, control, and tracking across various applications. However, managing interactions with external factors in the agricultural ecosystem, particularly wildlife, remains a critical challenge. One of the major concerns for modern farmers is safeguarding crops from wild animal intrusions. Traditional solutions range from lethal methods (e.g., shooting) to non-lethal strategies (e.g., trapping, scarecrows, chemical deterrents, natural repellents, mesh barriers, or electric fences). However, some of these conventional approaches pose environmental hazards to both humans and wildlife, while others are expensive, require extensive maintenance.This paper introduces a system that integrates AI-driven Computer Vision and Deep Convolutional Neural Networks (DCNN) to identify and detect different animal species. It also employs species-specific ultrasonic signals to deter detected animals efficiently.","author":[{"family":"Theetchenya","given":"S"},{"family":"Kantamaneni","given":"Prasuna"},{"family":"Kasireddy","given":"Lakshmi"},{"family":"Gopi","given":"R"},{"family":"Sathiyamoorthi","given":"V"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-2497-5.ch007","URL":"https://doi.org/10.4018/979-8-3373-2497-5.ch007","source":"crossref"},{"id":"doi:10.1079/9781800626850.0051","type":"article-journal","title":"Assessing the Impact of Organic Farming on Productivity among Norwegian Dairy Farmers: Evidence from a Semi-parametric Production Model","abstract":"The literature shows that organic farming has become the centre of policies aiming to achieve sustainable agriculture due to its environmental benefits, such as increased biodiversity, reduced greenhouse emissions, etc. However, there is a gap in the literature on the productivity effects of organic farming over and above the conventional method to understand whether widely converting conventional farms pays off. The current study estimated the productivity function using a semi-parametric smooth-coefficient (SPSC) approach based on unbalanced panel data set from Norwegian dairy and crop farms during 1991 to 2020. The results show that organic farming, compared to conventional farming, increase productivity for most of the dairy farms, while for crop farms the effect is mixed. This finding suggests that organic farming for many farms can yield a productivity higher than or equal to conventional farming. However, the results depend on the farm under consideration, and there exists a large degree of heterogeneity among the farms. Likewise, the technical change is heterogeneous, indicating that some farms underwent technical progress (regress) or a neutral change during the study period. Finally, the returns to scale (RTS) are at the mean about 0.89 and 1.05 for dairy and crop farms, respectively, implying that these farms operate at a decreasing (increasing) returns to scale and can improve their productivity by decreasing (increasing) the current scale of operation.","author":[{"family":"Alemayehu","given":"Fikru"},{"family":"Alem","given":"Habtamu"},{"family":"Lien","given":"Gudbrand"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1079/9781800626850.0051","URL":"https://doi.org/10.1079/9781800626850.0051","source":"crossref"},{"id":"doi:10.32317/ekon.apk/4.2025.22","type":"article-journal","title":"Activation of innovative development of poultry farming  and meat livestock farming industries on the food market of Ukraine","abstract":"This article studied the peculiarities of integrating innovative technologies into poultry farming and meat livestock farming – essential elements of the Ukrainian food market. The goal was accomplished through the contextual analysis of industry reports, examination of the European legislation, and assessment of the Ukrainian poultry and meat production segments in terms of the Food Demand Index, Food Supply Index, and Regional Trade Development Index. Despite the military time turbulence, the Ukrainian meat production industry stood resilient and demonstrated potential for sustainable development, with poultry accounting for 56.3% of the total segment. However, integration of the Ukrainian meat production into the European segment remained modest, despite 38,481 TRACES NT certificates obtained: in 2024, the share of poultry exports decreased by 37.2% compared to 2023. The econometric analysis revealed a statistically significant relationship between innovation and output in the national meat production segment, with 66.4% variations in annual poultry and beef consumption attributed to innovative technologies. Connection was also discovered between the use of innovative technologies and reduced production cost, as well as between innovative approaches and an adherence to sustainable development practices. The integration of innovative technologies was not uniform throughout the country: the central regions of Kyiv and Vinnytsia had the highest innovation rankings, with the potential of receiving integral index values of up to 8.13. It was further discovered that the use of technologies could facilitate rational allocation of resources: one robot can serve up to 70 animals, hence, free human resources to address more technological tasks. The obtained findings could be used to increase performance effectiveness, enhance competitiveness, and support sustainable development of the Ukrainian food market","author":[{"family":"Khakhula","given":"Bohdan"},{"family":"Semysal","given":"Anna"},{"family":"Shepel","given":"Tetiana"},{"family":"Shchebel","given":"Andrii"},{"family":"Shtymak","given":"Igor"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32317/ekon.apk/4.2025.22","URL":"https://doi.org/10.32317/ekon.apk/4.2025.22","source":"crossref"},{"id":"doi:10.1201/9781003510598-11","type":"article-journal","title":"IoT Middleware Solutions for Arable Crops and Livestock Farming","abstract":"The full automation of agricultural production systems, involving unmanned operations and autonomous decision support systems through their dynamic integration into the Internet of Things (IoT), may represent a comprehensive approach toward Agriculture 5.0, provided that it will be possible to manage, process, and share the large amount of heterogeneous raw data acquired by wireless sensor and actuator network (WSAN) on arable farms and livestock facilities. This chapter examines this topic, introducing a cloud-based middleware solution for the development of an IoT-integrated system, characterized by properties such as interconnectivity, scalability, flexibility, and interoperability. In particular, the architecture of a system that makes usage of cloud computing resources and is based on a multi-level hierarchical structure is proposed, with focus on the context awareness function performed in the middleware layer. To justify the solution, the system was evaluated in terms of computational performance as well as its coherence, consistency, and effectiveness in two case studies regarding an arable cultivation and a livestock farming facility.","author":[{"family":"Symeonaki","given":"Eleni"},{"family":"Arvanitis","given":"Konstantinos"},{"family":"Maraveas","given":"Chrysanthos"},{"family":"Loukatos","given":"Dimitrios"},{"family":"Fountas","given":"Spyros"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003510598-11","URL":"https://doi.org/10.1201/9781003510598-11","source":"crossref"},{"id":"doi:10.9734/bpi/rpbs/v12/7763","type":"article-journal","title":"Climate-Smart Dairy Farming: Sustainable Strategies for Productivity, Welfare and Emissions Reduction","abstract":"The global dairy sector faces the dual challenge of sustaining and enhancing productivity to meet rising demand for animal-sourced foods while simultaneously reducing its contribution to climate change. Dairy farming is a significant source of anthropogenic greenhouse gas (GHG) emissions, principally methane from enteric fermentation, nitrous oxide from manure management, and carbon dioxide from energy use and land-use change. Climate-smart dairy farming (CSDF) has emerged as an integrative paradigm that seeks to reconcile these competing demands by optimising productivity, safeguarding animal welfare, and reducing emissions per unit of output. This review synthesises the current state of knowledge across five interrelated domains: enteric methane mitigation, manure management, carbon sequestration through land and pasture management, productivity enhancement via precision technologies and genetic improvement, and the adaptation of animal welfare practices to a warming climate. Evidence from peer-reviewed literature and authoritative reports indicates that a range of dietary, genetic, technological, and managerial interventions can collectively reduce GHG intensity by 20–50% without compromising milk yield. However, the implementation of these strategies requires coherent policy frameworks, financial incentives, and region-specific adaptation. The review further highlights that animal welfare and climate outcomes are frequently synergistic: improved health, thermal comfort, and nutritional management simultaneously reduce emissions and increase productive efficiency. Despite significant advances, knowledge gaps persist regarding the long-term efficacy of mitigation measures, trade-offs between different strategies, and the scaling of interventions across diverse farming systems globally. The review concludes that climate-smart dairy farming constitutes a viable, evidence-based pathway towards a low-emissions dairy sector capable of feeding a growing global population within planetary boundaries.","author":[{"family":"Pathak","given":"Rupal"},{"family":"Doneria","given":"Raina"},{"family":"Parmar","given":"Mehtab"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/bpi/rpbs/v12/7763","URL":"https://doi.org/10.9734/bpi/rpbs/v12/7763","source":"crossref"},{"id":"doi:10.24843/mite.205.v24i01.p03","type":"article-journal","title":"Pertanian Vertikal Pintar: Peran IoT dalam Mewujudkan Keberlanjutan dan Efisiensi Sumber Daya","abstract":"The rapid growth of population and urbanization poses significant challenges to global food security, particularly in urban areas. The conversion of agricultural land into residential and infrastructure zones reduces local food production capacity, while climate change exacerbates uncertainties in crop yields. To address these challenges, IoT-based vertical farming has emerged as an innovative solution to enhance efficiency and sustainability in food production systems. IoT technology enables vertical farming systems to monitor and control environmental variables such as temperature, humidity, lighting, and nutrient levels in real-time through sensors connected to artificial intelligence. The collected data is analyzed to optimize plant growth, minimize resource waste, and maximize crop yields while reducing energy consumption. Additionally, integrating IoT with automated irrigation systems and energy-efficient LED lighting further enhances water and electricity efficiency. From a sustainability perspective, IoT-based vertical farming allows for year-round food production without relying on vast land areas or favorable weather conditions. This research further explores how IoT contributes to improving resource efficiency, environmental sustainability, and the economic and social impacts of vertical farming. . Based on the research findings, the implementation of IoT in vertical farming has proven to be highly beneficial in enhancing sustainability and resource efficiency in urban food production. Through real-time monitoring and automated control systems, IoT enables precise regulation of key environmental factors such as temperature, humidity, lighting, and nutrient levels, ensuring optimal plant growth with minimal resource wastage.","author":[{"family":"Setiawan","given":"Putu"},{"family":"Er","given":"Ngurah"},{"family":"Sukadarmika","given":"Gede"}],"issued":{"date-parts":[[2025]]},"DOI":"10.24843/mite.205.v24i01.p03","URL":"https://doi.org/10.24843/mite.205.v24i01.p03","source":"crossref"},{"id":"doi:10.1201/9781003743767-113","type":"article-journal","title":"Autonomous Solar-Powered Farming and Monitoring Unit","abstract":"The world got the first crop and the first plough. Indeed, in the absence of farming, the population is affected by malnutrition and starvation. Agriculture is the key numerical feature and the primary asset of not only the national economy but also human health. Tree plantation and agricultural crop growing has got very much beyond the direct benefit to the humans taking along with them the opportunistic animal population. Over-watering plantings will foster the growth of many plant diseases in addition to creating an environment that gives mold a good atmosphere to grow in the wet condition. The infection of a few fungal diseases such as the Pythium and the Phytophthora are prone to develop under the imposition of high humidity. Fall leaf dropping and fighting gets even worse when there are instances of diseases and fungi appearing. An example is where leaching excess water leads to such masses as soluble nitrogen granular fertilizers which are very soluble hence can be damaged in the process of leaching. The plants under the water level are susceptible to diseases and pests and cannot heal anymore given that they are capable of resisting and adapting to changes. Submergence of crops over a long period slows down the activities of the roots considerably which ends up resulting in lack of the necessary nutrients besides also causing the plant to die thus causing loss of the crop. It will leave lots of hardships to agriculture in the sense that not only will it lead to the reduction of the yield, but also it will make water become politicized where too much utilization of water is the problem. There are higher conditions of temperature in which there is a process of increased sweating of the plants and ecosystems. This leads to water wastage on the earth. New water can pose a problem to both usage by home and the home of such as the generic human rights with the access to drinking water which is regarded as one of development priorities is water.","author":[{"family":"Vaishnavi","given":"S"},{"family":"Preethi","given":"S"},{"family":"Niveditha","given":"S"},{"family":"Nithya","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003743767-113","URL":"https://doi.org/10.1201/9781003743767-113","source":"crossref"},{"id":"doi:10.1109/iconat61936.2024.10774738","type":"article-journal","title":"Smart Farming System Using IoT for Efficient Crop Growth","abstract":"The Shrewd Cultivating Framework utilizes a combination of sensors and IoT innovation to make a robotized checking and control framework for agrarian purposes. The utilization of sensors like ultrasonic, soil dampness, DHT11, and LDR, interfaces with a microcontroller, empowers real-time information collection on plant development, soil dampness substance, temperature, and light escalated. The system’s integration with IoT encourages farther get to screen and oversee these parameters. In case of unfavorable conditions such as moo soil dampness, the framework triggers caution through a buzzer, guaranteeing incite consideration and activity to keep up ideal edit development conditions. This framework presents a arrangement to improve edit surrender by empowering productive and opportune intercession based on exact natural data.","author":[{"family":"Ganesh","given":"Jetti"},{"family":"Bisht","given":"Saksham"},{"family":"Reddy","given":"Shashidhar"},{"family":"Babu","given":"AM"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iconat61936.2024.10774738","URL":"https://doi.org/10.1109/iconat61936.2024.10774738","source":"crossref"},{"id":"doi:10.56606/hikmayo.v4i2.352","type":"article-journal","title":"PENINGKATAN KOMPETENSI SMART FARMING KELOMPOK TERNAK DI LAMPUNG TENGAH: INTEGRASI QRCODE RECORDING TERNAK DAN ALAT MINUM OTOMATIS","abstract":"Kegiatan ini bertujuan untuk meningkatkan kompetensi kelompok ternak di Lampung Tengah dalam penerapan smart farming melalui integrasi sistem QRCode recording ternak dan alat minum otomatis. Program dilaksanakan di Koperasi Yufeed Berkah Mulia, Desa Rukti Endah, Kecamatan Seputih Raman, Kabupaten Lampung Tengah, dengan pendekatan partisipatif yang melibatkan peternak secara langsung. Metode kegiatan meliputi analisis kebutuhan, sosialisasi, pelatihan, implementasi teknologi, pendampingan, dan evaluasi berbasis pre-test dan post-test. Hasil kegiatan menunjukkan peningkatan signifikan dalam pengetahuan dan keterampilan peternak, terutama dalam hal pencatatan data ternak secara digital serta pemahaman dan pengoperasian alat minum otomatis. Peternak yang sebelumnya hanya menggunakan metode manual, kini mampu memperbarui data ternak berbasis QRCode serta memastikan ketersediaan air minum secara ad libitum melalui sistem otomatis. Temuan ini membuktikan bahwa integrasi QRCode recording dan alat minum otomatis mampu meningkatkan efisiensi, akurasi, serta kesejahteraan ternak. Dengan demikian, kegiatan ini tidak hanya memberikan dampak jangka pendek berupa peningkatan literasi digital, tetapi juga membuka peluang keberlanjutan inovasi menuju sistem peternakan modern yang adaptif, produktif, dan berdaya saing.Inisiatif pengabdian masyarakat ini bertujuan untuk meningkatkan keterampilan pemasaran digital bagi UMKM di Kampung Jahe, Kedung Baruk, Surabaya. Meskipun UMKM memiliki peran penting dalam perekonomian lokal, banyak yang belum memahami strategi pemasaran digital, khususnya dalam memanfaatkan platform Shopee untuk meningkatkan penjualan. Kegiatan ini melibatkan pelatihan dan pendampingan praktis melalui optimalisasi seller center di Shopee. Metode pelaksanaan mencakup lokakarya, identifikasi kebutuhan UMKM, penyuluhan, demonstrasi penggunaan platform, dan pendampingan langsung, dengan evaluasi dan monitoring untuk mengukur efektivitas program. Penilaian awal menunjukkan bahwa 70% peserta mengalami kesenjangan pengetahuan yang signifikan tentang pemasaran digital. Setelah pelatihan, peserta diharapkan dapat menerapkan teknik pemasaran digital secara efektif, dengan target peningkatan penjualan produk sebesar 30% dalam enam bulan ke depan.","author":[{"family":"Maharani","given":"Nadia"},{"family":"Setiawan","given":"Rizkima"},{"family":"Wanniatie","given":"Veronica"},{"family":"Santoso","given":"Dimas"},{"family":"Putra","given":"Arnest"},{"family":"Puryanto","given":"Susilo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.56606/hikmayo.v4i2.352","URL":"https://doi.org/10.56606/hikmayo.v4i2.352","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102232","type":"article-journal","title":"Beyond single-modality: A comprehensive review on multimodal fusion paradigms in precision livestock farming","abstract":"• Fills a critical gap with the first comprehensive survey of PLF multi-modal fusion. • Primary sensing modalities and their standalone limitations are analyzed. • A novel taxonomy categorizes fusion by data homogeneity and integration strategies. • Delivers a curated benchmark of open-access multi-modal PLF datasets. • Pioneers actionable solutions for navigating key challenges in multi-modal PLF. Technology-driven precision livestock farming (PLF) enables practitioners to monitor and analyze animal growth and health conditions, leading to improved productivity and welfare. However, the full potential of PLF remains elusive, as single-modality approaches are inherently limited by challenges such as environmental sensitivity and data sparsity. Multimodal fusion emerges as a critical pathway to overcome these limitations, yet the field currently lacks a systematic framework to synthesize its rapid developments. This work presents the first comprehensive review that specifically addresses this gap, offering a novel taxonomy to categorize multimodal fusion in PLF studies from 2019 to 2025. We introduce a distinctive analytical framework based on homogeneous (e.g., vision-vision, wearable sensor-wearable sensor) and heterogeneous (e.g., sensor-acoustic-text) fusion paradigms, under which we meticulously analyze livestock species distributions and fusion strategies across 66 surveyed publications. Our analysis reveals that feature-level fusion dominates (73% of studies), while homogeneous fusion accounts for 68% of implementations, with wearable sensor-based approaches being particularly prevalent. The superior robustness of these fused methods is demonstrated across key applications spanning individual identification, morphometric analysis, behavior recognition, event detection, and disease diagnosis. Beyond technical analysis, we provide a curated collection of open-access multimodal datasets that serve as valuable benchmarks. We further propose strategic recommendations for fusion paradigm and strategy selection, and highlight persistent challenges such as modality heterogeneity and alignment, missing modalities, and computational complexity and efficiency, while outlining potential solutions and emerging research directions. By contextualizing technological advances within real-world deployment constraints, this review aims to establish a foundational reference and accelerate the development of practical, sustainable multimodal PLF systems that genuinely enhance animal welfare and productivity.","author":[{"family":"Mao","given":"Axiu"},{"family":"Zhu","given":"Meilu"},{"family":"Li","given":"Yanzhen"},{"family":"Wang","given":"Kaiying"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102232","URL":"https://doi.org/10.1016/j.atech.2026.102232","source":"crossref"},{"id":"doi:10.25215/9371837764.25","type":"article-journal","title":"CLIMATE-SMART FARMING: THE ROLE OF TECHNOLOGY IN ENHANCING AGRICULTURAL RESILIENCE","abstract":"Climate change poses a growing threat to local agricultural systems, with significant implications for food security, economic stability, and rural livelihoods. This study explores the multifaceted impacts of changing climatic conditions including rising temperatures, altered precipitation patterns, increased frequency of extreme weather events, and shifts in pest and disease dynamics—on crop yields, soil fertility, and water availability. Using a combination of climate data analysis, farmer surveys, and case studies from the local region, the research identifies both current challenges and projected future risks to agricultural productivity. Results indicate a marked decline in yield for temperature-sensitive crops, disruptions in planting and harvesting cycles, and increased input costs due to the need for irrigation and pest control. The paper also highlights adaptive strategies employed by local farmers, such as crop diversification, soil conservation practices, and the adoption of climate-resilient crop varieties. Ultimately, the findings underscore the urgency of integrating climate adaptation into agricultural planning and policy to ensure long-term sustainability and resilience of local farming communities.","author":[{"family":"Bharat","given":"Miss"},{"family":"Pandharinath","given":"Mr"},{"family":"Baban","given":"Miss"}],"issued":{"date-parts":[[2025]]},"DOI":"10.25215/9371837764.25","URL":"https://doi.org/10.25215/9371837764.25","source":"crossref"},{"id":"doi:10.1002/9781394336364.ch6","type":"article-journal","title":"Intelligent Farm","abstract":"Cloud computing and artificial intelligence (AI) are emerging technologies in all real-time applications. The automation of detecting and predicting water irrigation, pest control, and fertilizer usage is still crucial in agroforestry. The Internet of Things (IoT) is the most promising tool in implementing intelligent farming and improving land management. The goal of agroforestry is to preserve the environment and natural resources. Reinforcement learning (RL) is used for prediction and classification in smart agriculture; it considers how crop growth, yield, soil, environmental characteristics, climate, and watering of agricultural fields can change over time and space. The implementation of RL in agroforestry has potential in several real-time smart agricultural applications. This chapter explores the implementation of IoT-based intelligent farming, focusing on various decision-making systems. The cloud computing system in IoT provides extensive services in a centralized manner by sharing computation mechanisms, memory, and costs. Furthermore, it examines the requirement of placing computing techniques near end devices due to the rapid growth of IoT devices in real-time applications. It examines various AI and reinforcement learning techniques utilized to facilitate immediate smart decisions. This chapter also discusses the limitations, challenges, applications, and future prospects of deploying AI and reinforcement learning in intelligent farming.","author":[{"family":"Kalaivanan","given":"K"},{"family":"Bhanumathi","given":"V"},{"family":"Aruchamy","given":"Prasanth"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394336364.ch6","URL":"https://doi.org/10.1002/9781394336364.ch6","source":"crossref"},{"id":"doi:10.1201/9781003613510-7","type":"article-journal","title":"Convolutional Neural Networks for Potato Leaf Diseases Detection for Smart Agricultural Farming","abstract":"In today’s smart farming context, the incorporation of Internet of Things (IoT), Artificial Intelligence (AI), into agricultural practices is essential to optimize operations and enhance productivity. In the world, potatoes are the fourth most widely consumed staple crop, but their yield is affected by early blight and late blight leaf diseases. This chapter introduces the study on convolutional neural networks adoption in potato leaf disease detection for the quick detection and classification. The study is intended to categorize leaves of potato into healthy leaves, early blight, and late blight. Extensive experiments conducted using an open-source dataset from Kaggle, and some data collected from farms show a test accuracy of 98.59%. To confirm the reliability of the AI-powered agricultural web application, precision, recall, and F1-score performance metrics are evaluated and confirm the efficiency of the proposal.","author":[{"family":"Jagadamba","given":"G"},{"family":"Chayashree","given":"G"},{"family":"Hemavathi"},{"family":"Jayadeva","given":"Varun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003613510-7","URL":"https://doi.org/10.1201/9781003613510-7","source":"crossref"},{"id":"doi:10.1201/9781779640932-8","type":"article-journal","title":"Development of Prediction Equations for Estimating the Biomass of Standing Trees","abstract":"Assessing the productivity of a forest involves evaluating the biomass of standing trees within the ecosystem. Research on estimating tree biomass in forests is vital for calculating production, understanding soil and plant nutrient dynamics, and assessing the impact of various factors like commercial tree usage, silvicultural practices, and environmental disturbances on forest productivity and stability. These studies provide insights into the performance of tree species in terms of their biological output and guide harvesting practices for mature trees, especially for commercial purposes, that influence total tree biomass. The predictive models developed through these studies are particularly valuable for meeting the needs of forestry and agroforestry industries as tree growers and farmers involved in agroforestry practices. The growth in levels of tree crops as they age has directly impacted the overall biomass of the forest area. In a study involving Dalbergia sissoo and Acacia catechu trees, which represented all three Eucalyptus hybrid trees, regression equations were developed using models. The above ground biomass (AGB), below ground biomass (BGB), and total tree biomass (AGB + BGB) of all the harvested sample trees were calculated, along with the diameter, height and weight (in kilograms) of each tree component. These plantations vary significantly in terms of age, density, width, height, and total biomass. The fluctuations in biomass are influenced by factors such as tree size, density (spacing), and the quantity of trees present. This approach involved comparing 136 DBH values with the weights of tree components, from multiple felled trees, to refine the predictive models further.","author":[{"family":"Kholiya","given":"Deepak"},{"family":"Chugh","given":"Priya"},{"family":"Mishra","given":"Amit"},{"family":"Bhadula","given":"Rakesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781779640932-8","URL":"https://doi.org/10.1201/9781779640932-8","source":"crossref"},{"id":"doi:10.3233/aise200034","type":"article-journal","title":"Geospatial Technologies in Precision Farming: A Case Study","abstract":"The knowledge of spatial variability in soil organic carbon (SOC) is an important consideration in precision agriculture as well as site specific nutrient management.Geostatistical analyses coupled with GIS and GPS are effective tools in assessing the spatial variability and mapping of SOC.A total of 268 soil samples were collected in a systematic grid design (1-minute interval) using GPS covering four sub-districts: Delduar, Melandah, Mirpur and Fultala under two major alluviums -the Ganges and the Brahmaputra.The classical statistics showed that SOC values are normally distributed in the Fultala sub-site whereas in the other sub-sites, the SOC contents were not normally distributed.The semivariogram model also shows that the Fultala sub-site appears to have a strong structure and a gradual approach to the Gausian model providing the best fit where as the other sites show a weak spatial dependency.Due to salinity and other constrains, Fultala sub-site bears a relatively low cropping intensity and hence tillage and crop management are much lower than the other sites.GIS based interpolated values of SOC ranged from 0.39 to 2.02 % in the Fultala sub-site.Interpolated values of SOC ranged from 0.40 to 2.60% in the Delduar sub-site, 0.40 to 1.35% in the Melandah sub-site and 0.38 to 1.39% in the Mirpur sub-site respectively.Clearly, the sites where SOC is low, a pragmatic and location-based policy should be adopted to maximize SOC sequestration.Therefore, the geospatial technologies can help better management of agricultural land by targeting management practices appropriate to the SOC levels.","author":[{"family":"Jashim","given":"Uddin"},{"family":"Mohammad","given":"Mohiuddin"},{"family":"Mike","given":"Smith"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3233/aise200034","URL":"https://doi.org/10.3233/aise200034","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102426","type":"article-journal","title":"Deep Learning based 2D Computer Vision in Precision Livestock Farming for Pigs: A Systematic Literature Review and Future Research Directions","abstract":"The pressing challenges in pig production - particularly in welfare monitoring, behavior analysis, and health management - have driven increasing research efforts in computer vision as a scalable and automated solution. Over the past decade, a diverse body of work has emerged within precision livestock farming (PLF), addressing tasks ranging from pig detection and identification to behavior recognition and health assessment. This expanding research landscape calls for a structured synthesis to consolidate existing knowledge, clarify methodological developments, and elucidate the role of behavior-focused applications. This systematic literature review examines the adoption of computer vision in pig production through four research dimensions: (i) the range of problems addressed, (ii) the models and neural network architectures employed, (iii) the evaluation metrics reported, and (iv) the technical and practical challenges associated with developing and deploying such models. The contribution of this review is threefold. First, it offers an accessible conceptual overview of key deep learning based computer vision approaches to support interdisciplinary researchers entering the field. Second, it synthesizes methodological and evaluative trends across studies. Third, it identifies key challenges and research opportunities for advancing robust and practically relevant computer vision systems in pig farming.","author":[{"family":"Nasser","given":"Hassan"},{"family":"Kasper","given":"Claudia"},{"family":"Živković","given":"Vladimir"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102426","URL":"https://doi.org/10.1016/j.atech.2026.102426","source":"crossref"},{"id":"doi:10.55938/wlp.v3i2.452","type":"article-journal","title":"Smart Millet Farming: AI-Driven Detection, Prediction, and Solutions for Modern Cultivation Challenges","abstract":"Smart Millet Farming: AI-Driven Detection, Prediction, and Solutions for Modern Cultivation Challenges provides a quite detailed and promising examination of the ways artificial intelligence can change the millet plantings into a resilient, productive, and eco-friendly agricultural system. The book connects the ancient famine knowledge and the modern digital innovation, and it comes up with solutions for the major problems of the present agriculture like climate changes, pests, diseases, soil degradation, lack of water and market problems. It outlines the significant contributions of AI to the entire millet life cycle i.e. from the early detection of various diseases and predictive modelling of drought and heat stress to pest surveillance and soil health monitoring, smart irrigation, yield optimization, and finally supply chain integration across the ten well-structured chapters. Besides dwelling on the practical, the book extensively unfolds the future applications in areas such as data-driven decision support system, IoT, remote sensing, and machine learning that can make it possible for the farmers, researchers, and policymakers to be on the same page. The volume at large however, views the AI-supported millet farming as one of the key ways to achieve food security, climate resilience, and sustainable rural employment in the world that is rapidly changing.","author":[{"family":"Sinha","given":"Aashna"},{"family":"Parveen","given":"Fraiz"},{"family":"Shukla","given":"Geetanjali"},{"family":"Singh","given":"Rajesh"},{"family":"Gehlot","given":"Anita"},{"family":"Kaushik","given":"Priyanka"},{"family":"Iqbal","given":"Mohammed"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55938/wlp.v3i2.452","URL":"https://doi.org/10.55938/wlp.v3i2.452","source":"crossref"},{"id":"doi:10.1079/9781800626850.0010","type":"article-journal","title":"Cultural Practices for Sustainable Organic Farming","abstract":"Organic farming is famously known as a type of farming that discourages the use of chemical pesticides and fertilizers for sustainable well-being. It has been accompanied by strict principles, certifications and standardization, especially for exportation. The basis of certification of organic farming is its cultural practices or best practices as per the adopted standards. Many studies have assessed the level of adoption and performance of specific cultural practices against abiotic and biotic stresses. The current study assessed the sustainability of organic cultural practices from the farmers’ perspective. The emphasis was on getting farmers’ views on how they understand and apply organic cultural practices for sustainability and resilience to any changes in climate on their farms.","author":[{"family":"Amara","given":"Raya"},{"family":"Wilson","given":"Wilson"},{"family":"Manda","given":"Lucas"},{"family":"Mwaijande","given":"Nyandula"},{"family":"Maro","given":"Janet"},{"family":"Haule","given":"Yohana"},{"family":"Shango","given":"Abdul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1079/9781800626850.0010","URL":"https://doi.org/10.1079/9781800626850.0010","source":"crossref"},{"id":"doi:10.56975/ijedr.v14i2.308043","type":"article-journal","title":"IoT-Based Farming Robot for Smart Agriculture (AGROROVOR)","abstract":"Agriculture plays a vital role in the economy and food production system of many countries. However, traditional farming methods still rely heavily on manual labour, which often leads to increased operational costs, labour shortages, inconsistent seed sowing, and inefficient water usage. Farmers, especially small-scale farmers, face challenges in maintaining productivity due to limited resources and rising labour demands. To address these issues, the use of smart agricultural technologies and automation has gained significant attention in recent years. Although several modern farming systems utilize Internet of Things (IoT) technology with sensors for monitoring soil moisture, temperature, humidity, and crop conditions, such systems are often expensive, technically complex, and require frequent maintenance. These limitations reduce their practicality and affordability for small farmers and educational or research purposes. The proposed IoT-based farming robot offers a simple, affordable, and efficient solution for agricultural automation by eliminating the dependency on sensors. The robotics specifically designed toper form essential farming operation such as seed sowing and water spraying through remote control using internet connectivity. The system can be operated using smart phones, laptops, or web-based applications, enabling farmers to control the robot from a distance without requiring physical presence in the field. By removing sensor-based complexity, the system becomes easier to maintain, cost-effective, and suitable for users with limited technical knowledge. The robotics developed using key hardware components such as a microcontroller unit, in clouding Arduino or Node MCU, a motor driver module, DC motors for movement, a water pump for irrigation, a seed dispensing mechanism for uniform sowing, a Wi-Fi communication module, and a rechargeable battery for portable power supply. The movement of the robot is controlled remotely, allowing it to navigate farmland and perform farming tasks effectively. The seed sowing mechanism ensures improved seed placement and distribution, while the water spraying system supports efficient irrigation and reduces unnecessary water wastage. One of the major advantages of the proposed system is its lightweight, portable, and flexible design, which makes it adaptable to different agricultural environments and small farming lands. The robot helps reduce manual labour dependency, saves time, and improves farming efficiency by automating repetitive agricultural activities. Since the project avoids the use of expensive sensing technologies, it significantly lower implementation and maintenance costs, making it economically beneficial for small-scale farmers and students working on agricultural automation projects. The proposed system demonstrates that practical and affordable agricultural automation can be achieved even without advanced sensor integration. It high light the potential technology in transforming tradition al farming practices into more efficient and technology-driven operations. In the future, the robot can be enhanced with features such as GPS-based navigation, optional environmental sensors, automatic path planning, and artificial intelligence (AI)-based decision-making to improve accuracy, autonomy, and overall performance in smart farming applications.","author":[{"family":"Das","given":"Sampa"},{"family":"Nayak","given":"Laboni"},{"family":"Karmakar","given":"Sandip"},{"family":"Rana","given":"Supriya"},{"family":"Maikap","given":"Soumyadip"}],"issued":{"date-parts":[[2026]]},"DOI":"10.56975/ijedr.v14i2.308043","URL":"https://doi.org/10.56975/ijedr.v14i2.308043","source":"crossref"},{"id":"doi:10.24843/ijoss.2026.v02.i01.p05","type":"article-journal","title":"Economic Feasibility Assessment of Robusta Coffee Farming","abstract":"BACKGROUND AND OBJECTIVESThe robusta coffee farming sector in Semarang Regency, Central Java, plays a crucial role in the local economy, providing employment opportunities and contributing to regional agricultural production. Despite favourable agroecological conditions, the productivity and profits of coffee cultivation in the region vary significantly due to differences in cultivation methods. This study aims to evaluate the economic performance of robusta coffee cultivation in Semarang Regenc y, focusing on farmers' income, profi ts, and financial feasibility through key indicators such as Cost Income Ratio (R/C) and Cost Benefit Ratio (B/C). METHODSThis study employed a quantitative descriptive approach, conducting structured interviews with 69 randomly selected coffee farmers from the districts of Getasan, Bandungan, and Banyubiru. Primary data on production costs, crop yields, selling prices, and income components were collected, supplemented by secondary data from local agricultural offices. The financial feasibility of coffee cultivation is evaluated using R/C and B/C ratios to determine profitability and efficiency. FINDINGS The study found that the average productivity of robusta coffee was 914.7 kg per hectare, with an average selling price of IDR 24,372 per kg. The average income per hectare after deducting variable costs was IDR 13.33 million, with a net profit of IDR 11.30 million per hectare. An R/C ratio of 2.03 indicates that this farming venture is profitable, and a B/C ratio of 1.03 confirms the economic viability of coffee cultivation in the region. CONCLUSIONThe results of the study indicate that robusta coffee cultivation in Semarang Regency remains economically viable and profitable, with efficient production management practices contributing to positive financial outcomes. However, variations in productivity and input management efficiency among farmers pose challenges in maximising profits. Recommendations include enhancing cultivation practices, expanding market access, and stabilising coffee prices to ensure long-term sustainability. This research contributes to the understanding of the economic potential of coffee cultivation and provides practical insights to improve farmers' income and cultivation efficiency.","author":[{"family":"Zuhri","given":"Nur"},{"family":"Puspita","given":"Nurul"},{"family":"Ayomi","given":"Nun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.24843/ijoss.2026.v02.i01.p05","URL":"https://doi.org/10.24843/ijoss.2026.v02.i01.p05","source":"crossref"},{"id":"doi:10.1201/9781003637264-17","type":"article-journal","title":"Future Trends in Multimedia and Multimodal Intelligence for Smart Farming","abstract":"This chapter examines the integration of multimedia and multimodal intelligence in smart farming, with the goal of enhancing decision-making, operational efficiency, and sustainability in agricultural practices. The study presents a detailed methodological framework that includes multi-source data collection (e.g., RGB and hyperspectral imagery, video, audio, and sensor telemetry), pre-processing and synchronization, feature extraction tailored to specific modalities, multimodal data fusion, and intelligent decision support systems. It employs advanced computational techniques, such as convolutional neural networks, transformer models, and federated learning, to manage and integrate diverse data streams. Recent research findings indicate notable advancements in essential agricultural tasks: crop yield predictions increased by 25% (R² = 0.88), pest detection accuracy reached 93%, disease classification achieved an F1-score of 0.93, and irrigation systems saw a 31% decrease in water consumption through edge deployment. Federated learning models maintained high predictive accuracy while safeguarding the privacy of farm data. The results highlight the transformative potential of merging artificial intelligence, edge computing, Internet of Things (IoT), and 5G technologies to create resilient, scalable, and privacy-compliant smart farming systems. Future research should focus on overcoming challenges related to data interoperability, model scalability, and deployment in environments with limited resources.","author":[{"family":"Sahu","given":"Vipin"},{"family":"Rane","given":"Shweta"},{"family":"Gupta","given":"Brijendra"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003637264-17","URL":"https://doi.org/10.1201/9781003637264-17","source":"crossref"},{"id":"doi:10.1038/s41598-025-22224-7","type":"article-journal","title":"A quantum-driven multi-stage framework integrating variational entanglement, reinforcement learning, and federated explainability for climate-resilient farming.","abstract":"The increasing constraints of climate change and data privacy necessitate high-efficiency, sustainable agriculture, which is causing a shift in the paradigm of Agro-informatics. Most classical agricultural models fail to capture genotype, soil chemistry, and climate dynamics connections. Latent interactions, essential to intelligent agricultural treatments and explainability, are lost in many data processing pipelines that use linear dimensionality reduction or black-box learning. This paper presents a quantum computing architecture for a revolutionary agricultural application, utilizing quantum encoding, topological learning, reinforcement optimization, federated intelligence, and explainability to highlight the importance of this vital field. In Quantum Variational Crop-Soil Entanglement Encoding, crop-soil interaction datasets are encoded into quantum state vectors using variational circuits, preserving high-order entanglement properties (fidelity&#x2009;&gt;&#x2009;0.96, entropy&#x2009;~&#x2009;0.9). Quantum-guided agri-topological dynamics mapping transforms encoded states into permanent topological maps using a hybrid quantum-classical Topological Data Analysis to track climate-induced agri-system dynamics (r&#x2009;=&#x2009;0.84 with the yield index). Field-level decisions using Quantum Reinforcement Learning for Precision Intervention policy mappings to relate topological states to interventions produce 16.2% normalized yield. Quantum Federated Learning for Distributed Farm Intelligence uses privacy-preserving, encrypted quantum policy gradients to enable learning across farms in varied locations, lowering communication by 42% and improving accuracy by 9.3%. Quantum Explainability through Entropic Intervention Attribution generates causal graphs of yield drivers with 89% confidence intervals using entropy-based attributions. This integrated framework enhances the knowledge preservation, policy accuracy, expandability, and trust of agricultural Artificial Intelligence systems, enabling quantum-accelerated, information-based, future-ready farming decision support systems.","author":[{"family":"Ah","given":"Khan"},{"family":"Dkjb","given":"Saini"},{"family":"Th","given":"Khan"},{"family":"Bk","given":"Rai"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1038/s41598-025-22224-7","URL":"https://doi.org/10.1038/s41598-025-22224-7","source":"pubmed"},{"id":"doi:10.1016/j.atech.2026.102351","type":"article-journal","title":"AI-Driven Smart Farming for Energy Optimization in Broiler Production: A Review of PCM-Based Cold Thermal Energy Storage Systems","abstract":"Heat stress significantly constrains broiler productivity and increases cooling-energy demand, while conventional poultry-house cooling systems rely heavily on fossil-based electricity. This review synthesizes recent advances in phase change material (PCM)-based cold thermal energy storage (CTES) systems for sustainable broiler-house cooling, with emphasis on energy efficiency, thermal stability, potential links with feed conversion ratio (FCR) and growth performance, and AI-driven control strategies. Organic PCMs with phase-change temperatures of 18–28°C, when integrated with ventilation and evaporative cooling systems, have been reported to improve indoor thermal stability, reduce peak cooling loads, and lower energy consumption compared with conventional cooling approaches. Reported poultry-relevant and transferable studies indicate that PCM-assisted cooling can reduce peak indoor temperature by approximately 2–4°C, improve indoor temperature stability by about ± 1–2°C, and reduce cooling-energy demand by approximately 15–40%, depending on climate, PCM type, storage capacity, and system configuration. Improved thermal stability may indirectly support FCR, growth performance, and welfare by reducing heat-stress exposure; however, direct confirmation in large-scale broiler PCM-based CTES trials remains limited. The integration of CTES with renewable energy sources, particularly solar energy, and AI- and IoT-based control systems may enable predictive and demand-responsive cooling management, improving the alignment between energy supply and cooling demand. Overall, PCM-based CTES combined with intelligent control represents a promising but still under-validated low-carbon approach for energy-efficient and welfare-oriented broiler production. Addressing current gaps will require multi-year field demonstrations, standardized performance assessment protocols, high-quality AI datasets, and comprehensive techno-economic assessments before large-scale commercial adoption can be recommended.","author":[{"family":"Mehtab","given":"Ahsan"},{"family":"Mun","given":"Hong"},{"family":"Lagua","given":"Eddiemar"},{"family":"Sharifuzzaman","given":"Md"},{"family":"Hasan","given":"Md"},{"family":"Park","given":"Hae"},{"family":"Kang","given":"Jin"},{"family":"Kim","given":"Young"},{"family":"Ryu","given":"Sang"},{"family":"Yang","given":"Chul"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102351","URL":"https://doi.org/10.1016/j.atech.2026.102351","source":"crossref"},{"id":"doi:10.3389/fcomm.2026.1752567","type":"article-journal","title":"Communication as the primary driver of IoT-based smart farming adoption: the mediating role of innovation perception and the supporting function of institutional mechanism","abstract":"Communication and innovation perception play interconnected roles in shaping farmers’ adoption of IoT-based smart farming technologies. This study examines how communication strategies and institutional support influence innovation perception and adoption behavior among smallholder farmers. By positioning communication as a central explanatory mechanism, the analysis explores how information is interpreted, trusted, and translated into sustained technology use. A quantitative approach using PLS-SEM was applied to survey data collected from 200 farmers in West Java, Indonesia. The results indicate that communication exerts a strong direct influence on both innovation perception and adoption, while institutional support affects adoption primarily through its influence on perception. These findings contribute to communication-based innovation theory by highlighting perception as a key mechanism in the smart farming adoption process. From a practical perspective, the study underscores the importance of farmer-centric, peer-amplified, and value-oriented communication strategies supported by coherent institutional frameworks. Adoption policies should integrate communication, capacity building, and financial facilitation to support digital transformation in agriculture.","author":[{"family":"Sumardjo"},{"family":"Firmansyah","given":"Adi"},{"family":"Dharmawan","given":"Leonard"},{"family":"Darmawan","given":"Cecep"},{"family":"Martuti","given":"Nana"},{"family":"Zaenudin","given":"Heni"},{"family":"Melati","given":"Inaya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fcomm.2026.1752567","URL":"https://doi.org/10.3389/fcomm.2026.1752567","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101264","type":"article-journal","title":"Development of a dynamic protocol for improving the productivity of soilless farming systems","abstract":"Climate change and population increase are becoming a threat to human feeding. New technologies and practices are under development, and a significant effort is being put into developing indoor farming, which allows for all-year-round production of high-quality food, regardless of the climate. Moreover, indoor farming promises extreme water and chemical usage reduction, specifically when the system is autonomously regulated with an IoT architecture. Despite these attractive characteristics, indoor systems require considerable energy to provide adequate temperature and lighting for cultivated crops. This demand is often high enough to make the production system economically unsustainable. This work aims to develop a cultivation protocol for baby lettuce plants (up to three weeks old plants) that can increase overall productivity while mitigating the issue of high energy demand. To this aim, we performed a Design of Experiment to assess crop responses to different levels of nutrients, temperature, and light intensity with the productivity of the system and the quality of the harvested product. The collected data were used to design a dynamic cultivation protocol, which defines different growing conditions according to the plant development stage. Results demonstrate that the dynamic protocol can enhance system productivity by up to 25 % in biomass accumulation, compared with the productivity obtained with fixed growing conditions, while maintaining the same high quality. Furthermore, the improvement is achieved without increasing the resource use, confirming the potential of this approach to enhance the economic sustainability of indoor soilless farming.","author":[{"family":"Grasso","given":"Nicolò"},{"family":"Fasciolo","given":"Benedetta"},{"family":"Bruno","given":"Giulia"},{"family":"Chiabert","given":"Paolo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101264","URL":"https://doi.org/10.1016/j.atech.2025.101264","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.100906","type":"article-journal","title":"Multi-scale remote sensing for sustainable citrus farming: Predicting canopy nitrogen content using UAV-satellite data fusion","abstract":"• Canopy Nitrogen Content (CNC) was estimated using a combination of UAV and Sentinel-2 data. • Developed models that utilize vegetation indices and tree structural data for CNC estimation. • Created spatial and temporal heat maps to visualize nitrogen content distribution in citrus trees. • Demonstrated a strong correlation between CNC and yield across three growing seasons. • Highlighted the potential for CNC applications to guide the development of site-specific nitrogen management strategies. Accurate monitoring of nitrogen (N) levels, while accounting for spatiotemporal variability is crucial for optimizing fertilization in citrus orchards. Traditional methods, such as frequent leaf and soil sampling followed by laboratory analysis, are costly, labor-intensive, and prone to human error. Remote sensing (RS) technologies, including unmanned aerial vehicles (UAVs) and satellite platforms, offer scalable and precise alternatives for N management. However, integrating these platforms poses challenges due to significant differences in spatial, temporal, and spectral resolution. This study presents a novel approach incorporating multispectral and temporal data from UAVs and Sentinel-2 satellites to estimate canopy N content (CNC) in citrus orchards. This method captures spatiotemporal variability across multiple citrus cultivars, aiming to enhance nitrogen use efficiency (NUE) while reducing environmental impact, ultimately promoting sustainable orchard management practices. The study was conducted in commercial citrus plots in the Hefer Valley, Israel, and spanned two phases. The first phase (May 2019 to April 2022) focused on four plots of the 'Newhall' cultivar, while the second phase expanded to twelve additional plots featuring five different citrus cultivars. The methodology consisted of six key steps: (1) Leaf samples from the study area were collected for laboratory nitrogen (N) analysis. (2) Acquiring and preprocessing bimonthly UAV multispectral images and Sentinel-2 satellite images to ensure data quality and consistency. (3) Segmenting individual trees using UAV imagery and extracting structural features through Structure-from-Motion (SfM) photogrammetry. (4) Processing images and extracting spectral and structural features relevant to N estimation. (5) Developing Random Forest (RF) models to estimate CNC using UAV-derived vegetation indices (VIs) and SfM data and combining these with Sentinel-2 VIs to generate canopy-scale CNC heatmaps. (6) Analyzing the relationship between CNC and yield to understand nitrogen dynamics and their impact on productivity. The integrated RF model, which combined UAV-VIs, Sentinel-2 VIs, and SfM-derived structural data, achieved superior performance (R² = 0.80, RMSE = 0.17 kg/m²) compared to models relying solely on UAV-VIs (R² = 0.68, RMSE = 0.23 kg/m²) or Sentinel-2 VIs (R² = 0.48, RMSE = 0.30 kg/m²). Additionally, CNC expressed as mass per tree demonstrated a strong positive correlation with yield (R² = 0.66), highlighting the relationship between nitrogen dynamics and orchard productivity. These results underscore the robustness of the integrated model and the clear advantage of multi-platform data fusion over single-source approaches. The study provides compelling evidence for the potential of combining UAV and Sentinel-2 data to improve CNC estimation and its correlation with yield in citrus orchards. The findings contribute to advancements in precision agriculture by offering a scalable, data-driven framework to enhance nutrient management and support sustainable orchard practices.","author":[{"family":"Avioz","given":"Dagan"},{"family":"Linker","given":"Raphael"},{"family":"Raveh","given":"Eran"},{"family":"Baram","given":"Shahar"},{"family":"Paz-Kagan","given":"Tarin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.100906","URL":"https://doi.org/10.1016/j.atech.2025.100906","source":"crossref"},{"id":"doi:10.36350/jbs.v16i1.329","type":"article-journal","title":"Analisis Bibliometrik Tren Penelitian dan Kolaborasi Global dalam Bidang Smart Farming (2016–2025)","abstract":"Smart farming is a modern agricultural approach based on digital technology that has continued to develop rapidly in the last decade. However, there are not many studies that comprehensively map the direction, collaboration, and global research trends in this field. This study aims to analyze the development of smart farming research bibliometrically using the approach of scientific publication metadata analysis and collaboration network visualization using VOSviewer software. Data were obtained from the Scopus database for the period 2016–2025. The results of the analysis show a significant increase in the number of publications, dominated by topics such as precision agriculture, Internet of Things, and deep learning. Bibliometric visualization shows a shift in research focus from technology exploration to practical application and the formation of consolidation of primary literature as a foundation for smart farming science. However, this study identifies a number of gaps such as the lack of implementation studies in developing countries, the lack of cross-disciplinary approaches, and the challenges of technology application by small-scale farmers. These findings provide important implications for the development of future research policies and strategies, especially in building an inclusive, sustainable, and locally needed smart farming system.","author":[{"family":"Fatikasari","given":"Defilia"},{"family":"Pratama","given":"Yoga"},{"family":"Pranata","given":"Alvin"},{"family":"Hozairi","given":"Hozairi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.36350/jbs.v16i1.329","URL":"https://doi.org/10.36350/jbs.v16i1.329","source":"crossref"},{"id":"doi:10.1109/ocit66168.2025.11399963","type":"article-journal","title":"Towards Secure Smart Farming: An Optimized Machine Learning Framework for IoT-Based Intrusion Detection","abstract":"The traditional methods of farming practices have evolved with the advent of concept of Smart Agriculture, integrated with Internet of Things (IoT), Artificial Intelligence (AI) and Big-Data Analytics. This has enabled numerous practitioners to achieve sustainable farming alongside resource optimization and precision agriculture. As this futuristic agriculture improvises, it also becomes vulnerable to security glitches and attacks. These concerns can have a direct impact on farm yields and its productivity. This paper explores methods of intrusion detection by leveraging machine learning methodologies in order to ensure security of a Smart Agriculture IoT Network. Furthermore, we discuss and propose a framework considering supervised learning approaches for improvised determination of accuracy, robustness and managing false positives.","author":[{"family":"Nayak","given":"Priyadarshini"},{"family":"Mishra","given":"Bharati"},{"family":"Mohapatra","given":"Sunil"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/ocit66168.2025.11399963","URL":"https://doi.org/10.1109/ocit66168.2025.11399963","source":"crossref"},{"id":"doi:10.1109/icct62929.2024.10875024","type":"article-journal","title":"Development of Smart Space Architecture for Dairy Farming Management","abstract":"The paper proposes an approach to implementing an intelligent video monitoring system for the animals' health and physiological status in terms of developing a smart space architecture aimed at monitoring the animals' keeping and its subsystems for animals’ video surveillance (their identification and localization) and preprocessing of video data. Three versions for implementing the video surveillance subsystem are proposed, which can be used depending on the construction, architectural and organizational features of the farm, the number of observed animals, the potential cost of the equipment, and the possibility of integrating the developed system into the farm’s existing infrastructure. Specifics of a seamless video space forming in the video data preprocessing subsystem are considered. To solve the problem of continuous localization and identification of animals in smart space, two options for implementing a subsystem of an object active in case of tracking errors are proposed. The implementation of the project of an intelligent video monitoring system for the health and physiological status of animals allows for earlier diagnosis of the most common diseases. The use of digital systems ensuring the early diagnosis of cow diseases will reduce the costs and treatment time of cows, as well as the volume of rejected milk during the treatment period, and the proportion of young highly productive animals discarded because of the diseases.","author":[{"family":"Kuleshov","given":"Sergey"},{"family":"Zaytseva","given":"Alexandra"},{"family":"Shalnev","given":"Ilya"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icct62929.2024.10875024","URL":"https://doi.org/10.1109/icct62929.2024.10875024","source":"crossref"},{"id":"doi:10.1109/bitcon63716.2024.10985219","type":"article-journal","title":"Farming 4.0: Integrating Technology for Smart Agriculture","abstract":"The Hydro Growth system presents an innovative approach to hydroponic farming, integrating Arduino microcontroller technology, mobile application, and solar panel power sources. In regions facing water scarcity, such as arid areas, this system offers a sustainable solution by utilizing dehumidifiers as a fresh water source for hydroponics, powered by solar panels. This study aims to design and develop a hydroponics application that monitors water quality parameters, including pH, TDS, and temperature, providing accurate management of hydroponic environments. Employing a qualitative and experimental research design, an Iterative Waterfall model is utilized for system development, ensuring alignment with user and business requirements. Arduino microcontroller capabilities facilitate hardware and software integration, while sensors such as pH, TDS, and temperature sensors, along with GSM and temperature sensors, enhance system functionality. Development of the mobile application is achieved through Android Studio, JAVA, Node.js, and other relevant technologies, ensuring a robust and secure platform for user interaction. Evaluation of the Hydro Growth system demonstrates its scalability and intelligence in providing effective hydroponic farming management. Regional agricultural experts consistently rate the system as effective, reinforcing its potential as an innovative tool for sustainable agriculture. Additionally, hydroponically grown food is recognized for its nutritional benefits over soil-based farming methods. The system continuously monitors water quality and sends SMS notifications to users, not only alerting them to abnormalities but also providing guidance on corrective actions, such as adding organic chemicals, to maintain optimal growing conditions.","author":[{"family":"Raja","given":"Ch"},{"family":"Rao","given":"JA"},{"family":"Naidu","given":"Botta"},{"family":"Rao","given":"Batta"},{"family":"Rao","given":"Thamatapu"},{"family":"Gurugubelli","given":"Vikash"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/bitcon63716.2024.10985219","URL":"https://doi.org/10.1109/bitcon63716.2024.10985219","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100265","type":"article-journal","title":"An intelligent pratacultural framework for sustainable grassland management","abstract":": Traditional prataculture management models are increasingly inadequate under the dual pressures of global climate change and land degradation, limiting the sustainable development of grassland resources and the realization of China's \"big food\" concept. Grounded in systems holism and socio-ecological coupling theory, we propose an intelligent pratacultural management framework integrating artificial intelligence (AI), Internet of Things (IoT), remote sensing, and multi-source data fusion. The framework was developed through a structured synthesis of peer-reviewed literature on socio-ecological systems, digital agriculture, and grassland management, systematically compared against existing frameworks to identify structural and functional gaps. The framework organizes management around three factor groups (abiotic, biological, and social), three interfaces (plant–land, pasture–livestock, and pasture/animal–market), and four production layers (pre-plant, plant, animal, and post-biological), operationalized through five sequential stages: data collection, modeling, analysis, decision-making, and implementation. The framework enables real-time ecosystem monitoring, dynamic simulation, optimized resource allocation, and predictive early-warning across the full forage–livestock–market chain. Key challenges to AI adoption in prataculture, including data quality, algorithm adaptability, talent shortages, and economic barriers, are identified, alongside future development opportunities. Unlike general socio-ecological system frameworks or crop-focused smart-farming models, this framework provides a grassland-specific, hierarchically operationalized system with real-time dynamic coupling capabilities, offering a practical blueprint for the digital and sustainable transformation of grassland management, with China's grassland systems serving as the primary empirical basis for framework development and illustrated application, while the underlying architecture is intended to be transferable, with region-specific calibration, to other extensive pastoral systems.","author":[{"family":"Zhao","given":"Weikang"},{"family":"Sun","given":"Yi"},{"family":"Nogayev","given":"Adilbek"},{"family":"Yi","given":"Shuhua"},{"family":"Hou","given":"Fujiang"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100265","URL":"https://doi.org/10.1016/j.farsys.2026.100265","source":"crossref"},{"id":"doi:10.26858/iptek.v4i2.65608","type":"article-journal","title":"Diseminasi Smart Farming dan Eduagriculture Berbasis Sumberdaya Lokal di Desa Kutaampel Kabupaten Karawang","abstract":"Kegiatan pengabdian kepada masyarakat ini dilatarbelakangi adanya permasalahan sulitnya regenasi petani, sulitnya penerapan smart farming sehingga Teknik budidaya pertanian masih bersifat konvensional dan rendah hasil, kurangnya pemenfaatan sumberdaya lokal di bidang pertanian, sulitnya promosi dan pemasyaran produk pertanian, serta belum adanya eduagriculture sebagai pusat pembelajaran masayarakat tani dalam budidaya tanaman. Menggunakan metode penyuluhan, pelatihan, serta pendampingan. Kegiatan ini dilaksanakan pada bulan Mei sampai November Tahun 2023 di wilayah Desa Kutaampel, Kecamatan Batujaya, Kab. Karawang. Kegiatan ini melibatkan Dosen, Mahasiswa, dan Masyarakat Tani. Pelatihan dilakukan dengan melalui tutorial, simulasi, praktek dan pendampingan. Hasil Program Pengabdian Kepada masyarakat tentang Smart Farming dan Eduagriculture Berbasis Sumberdaya Lokal di Desa Kutaampel Kec. Batujaya, Kab. Karawang mampu meningkatkan pengetahuan, sikap dan keterampilan pesertanya. Pada Rumah Pangan Digital Unsika (RATU), peserta yang tergabung dalam kelompok tani mampu membuat konsep Rumah Pangan Digital. Pada program System Hidroponik dan Aeroponik Tenaga Surya Unsika (SHIATUN) 83% peserta mengerti dan 60% diantaraanya mampu membuat dan menerapkan secara mandiri. Pada Penguatan Corperative farming dalam bentuk pemasaran Digital Marketing Farming Unsika (ANTINGKU) 70% peserta mengerti dan 65% diantaranya mampu menerapkan secara mandiri pada usahanya.","author":[{"family":"Laksono","given":"Rommy"},{"family":"Nurlenawati","given":"Netti"},{"family":"Pertiwi","given":"Anggun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.26858/iptek.v4i2.65608","URL":"https://doi.org/10.26858/iptek.v4i2.65608","source":"crossref"},{"id":"doi:10.56578/of120102","type":"article-journal","title":"Role of the Organic Agriculture Market in Achieving Sustainable Development Goals in Indonesia: A Systematic Literature Review","abstract":"This study explored the role of the organic agriculture market in advancing the Sustainable Development Goals (SDGs) in Indonesia through a systematic literature review (SLR) of global and national academic publications.The review included 90 peer-reviewed articles covering the period from 1998 to 2025 from the Scopus database, based on the selection criteria of thematic relevance, methodological rigor, and theoretical alignment.Results indicated that organic agriculture contributed to environmental sustainability, rural income diversification, and inclusive market development, yet persistent challenges remained in certification systems and institutional coordination.Integration with national data from Statistik Pertanian Organik Indonesia (SPOI) 2023 revealed that organic rice, coffee, and vegetables dominated land use, but production and certification were geographically concentrated in Java and Bali.The synthesis highlighted that limited adoption of Participatory Guarantee Systems (PGS) and weak inter-ministerial collaboration constrained market expansion and SDG alignment.The study concluded that achieving the SDGs through organic agriculture in Indonesia required stronger policy coherence, enhanced digital and institutional infrastructure, and public-private partnerships to improve certification efficiency, traceability, and market access.","author":[{"family":"Nendissa","given":"Doppy"},{"family":"Tamelan","given":"Paul"},{"family":"Winarno","given":"Sri"},{"family":"Lerik","given":"MDC"},{"family":"Ratu","given":"Jacob"}],"issued":{"date-parts":[[2026]]},"DOI":"10.56578/of120102","URL":"https://doi.org/10.56578/of120102","source":"crossref"},{"id":"doi:10.3897/ejfa.2026.172240","type":"article-journal","title":"Precision farming: A review of artificial intelligence applications in broiler poultry farming","abstract":"The global poultry industry is a critical sector, tasked with meeting the increasing demand for animal protein. Despite its growth and efficiency, it faces challenges, including enhancing productivity, optimizing resource utilization, and ensuring animal welfare. Addressing these challenges requires innovative solutions to improve both the efficiency and sustainability of poultry production. This paper presents an in-depth analysis of how advancements in artificial intelligence (AI) and machine learning (ML) technologies are being integrated into poultry farming to revolutionize its practices. We explore the application of AI in monitoring systems, smart poultry houses, and automated management practices that significantly enhance production metrics and animal welfare. Our study delves into various AI-driven methods, such as predictive modelling, real-time environmental monitoring, and precision feeding systems. Furthermore, the research identifies the current limitations and future potential of these technologies in facilitating a shift towards more responsive and responsible poultry farming practices. Our findings suggest that embracing AI technologies not only contributes to the economic viability of poultry farms but also aligns with ethical standards and sustainability goals, indicating a promising direction for the future of poultry farming.","author":[{"family":"Engelbrecht","given":"Duanne"},{"family":"Steyn","given":"Nico"},{"family":"Djouani","given":"Karim"},{"family":"Bosman","given":"Herman"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3897/ejfa.2026.172240","URL":"https://doi.org/10.3897/ejfa.2026.172240","source":"crossref"},{"id":"doi:10.15662/ijeetr.2026.0802235","type":"article-journal","title":"IoT Based Smart Indoor Farming using Solar Power and Kitchen Wastewater","abstract":"Indoor farming is an innovative approach to agriculture that allows plants to grow in a controlled environment without depending on external weather conditions. With the rapid growth of population and reduction in agricultural land, there is a need for efficient farming methods. This project presents an IoT based indoor farming system that monitors environmental parameters such as temperature, humidity, soil moisture and light intensity using sensors. The collected data is processed through a microcontroller and used to automatically control irrigation and lighting systems to maintain optimal conditions for plant growth. The system provides real time monitoring and reduces manual effort while improving crop productivity and resource efficiency. This smart farming solution helps in sustainable agriculture and efficient food production.","author":[{"family":"Bavisankar","given":"K"},{"family":"Chandru","given":"R"},{"family":"Dines","given":"M"},{"family":"Dinesh","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.15662/ijeetr.2026.0802235","URL":"https://doi.org/10.15662/ijeetr.2026.0802235","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102410","type":"article-journal","title":"Automated counting and identification for low-yield hen cages in large-scale farming","abstract":"We developed a simple yet effective, plug-and-play combination compatible with any model, featuring Mixed Local Channel Attention (MLCA), Light Efficient Detection (LED), and Weighted Intersection over Union (WIoU) modules. Poultry houses rely on manual checks to find low-yield hens, a subjective and labor-intensive task. We used an inspection robot to collect real-world data from 270 three-tier cages of 'Jing' hens. Integrating these modules enhanced the capture of small and overlapping targets like hen heads and eggs, boosting processing speed. We also custom-designed a Counting-in-Different-Cages (CDC) algorithm to solve counting difficulties caused by the tiered cages. The improved model increased hen detection precision by 4.7%, recall by 5.4%, and processing speed by 20.7 frames per second. In actual counting tasks, the algorithm achieved 93.1% accuracy for hens and 97.5% for eggs, with a minimal error of 0.26 hens and 0.06 eggs per cage. The entire system identified low-yield cages with 93.3% accuracy, proving it is highly capable of automated performance monitoring in commercial poultry farms.","author":[{"family":"Yang","given":"Jiahui"},{"family":"Wei","given":"Yong"},{"family":"Cai","given":"Jinghan"},{"family":"Zhao","given":"Yuliang"},{"family":"Zhu","given":"Jun"},{"family":"Fan","given":"Shijie"},{"family":"Li","given":"Bin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102410","URL":"https://doi.org/10.1016/j.atech.2026.102410","source":"crossref"},{"id":"doi:10.12694/scpe.v26i5.4639","type":"article-journal","title":"Optimizing EfficientNetv2 Model with RandAugment Data Augmentation for Detecting Wheat Diseases in Smart Farming","abstract":"Wheat diseases threaten global food security, necessitating improved detection methods. In this paper, we integrate EfficientNetv2 model and RandAugment data augmentation to accurately and efficiently identify wheat diseases. EfficientNetv2, known for its optimal mix of accuracy and computing efficiency, is reinforced by RandAugment, a versatile data augmentation approach that randomly modifies training data. This augmentation method greatly enhances the model’s generalisation and performance on new data. Our extensive experimentation reveals that this integrated technique improves model accuracy and robustness relative to baseline models. Proposed model gained the 96.73% accuracy on prescribed dataset. The results show that EfficientNetv2 and RandAugment can detect wheat illnesses on a large scale. This could change precision agriculture by enabling early and accurate disease management.","author":[{"family":"Sharma","given":"Manisha"},{"family":"Verma","given":"Alka"},{"family":"Rani","given":"Uma"}],"issued":{"date-parts":[[2025]]},"DOI":"10.12694/scpe.v26i5.4639","URL":"https://doi.org/10.12694/scpe.v26i5.4639","source":"crossref"},{"id":"doi:10.55041/ijsmt.v2i5.306","type":"article-journal","title":"GREENSYNC: AI-Powered Smart Agriculture and Precision Farming Platform","abstract":"Agriculture faces challenges such as unpredictable weather, crop diseases, pest infestations, and inefficient resource management. This paper presents GREENSYNC, an AI-powered smart agriculture platform designed to improve farming efficiency through intelligent crop monitoring, weather forecasting, and precision farming tools. The system integrates crop disease detection using image analysis, fertilizer and pesticide calculators, farming analytics, and an AI agronomy assistant for smart recommendations. Developed using Next.js, TypeScript, Node.js, PostgreSQL, and AI APIs, GREENSYNC provides real-time insights for irrigation, nutrient management, and crop health optimization. The platform enhances agricultural decision-making, reduces resource wastage, and promotes sustainable farming practices through a modern, responsive dashboard system.","author":[{"family":"Kriplani","given":"Sweta"},{"family":"Kutar","given":"Swati"},{"family":"Chaudhary","given":"Santoshi"},{"family":"Haldkar","given":"Upasana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijsmt.v2i5.306","URL":"https://doi.org/10.55041/ijsmt.v2i5.306","source":"crossref"},{"id":"doi:10.46730/japs.v4i3.124","type":"article-journal","title":"Analisis Kebijakan Smart Farming  Dalam Perkembangan Pertanian Di Era Revolusi Industri 4.0","abstract":"Pertanian yang berkelanjutan dan efisien menjadi tujuan utama dalam pembangunan pertanian di Indonesia. Pertanian merupakan sektor yang sangat penting dalam perekonomian Indonesia. Dalam upaya meningkatkan efisiensi, produktivitas, dan ketahanan pangan, pemerintah Indonesia telah menerapkan kebijakan pelaksanaan smart farming. Salah satu hasil positif dari kebijakan pelaksanaan smart farming adalah peningkatan produktivitas pertanian di Indonesia. Petani juga dapat mengakses informasi tentang teknik budidaya terbaru, kebutuhan tanaman, dan manajemen hama penyakit secara real-time, yang membantu meningkatkan kualitas dan kuantitas produksi. Potensi untuk mengembangkan smart farming di Indonesia sangat besar. Indonesia memiliki luas lahan pertanian yang luas, keanekaragaman komoditas pertanian, dan populasi petani yang besar juga. Penulisan paper ini menggunakan metode Studi Literatur dan konsep analisis William Dunn. Penulisan paper ini juga bertujuan untuk menganalisis sejauh mana penerapan konsep smart farming pada praktek pengelolaan pertanian Indonesia di era Revolusi Industri 4.0. dimana hal ini akan ditinjau dari peranan kebijakan smart farming dan dampak yang dihasilkan bagi petani. Hasil kajian ini menunjukkan bahwa konsep smart farming dapat meningkatkan produktivitas, efisiensi, dan keberlanjutan dari pertanian itu sendiri serta dapat meminimalisir dampak negatif yang akan terjadi.","author":[{"family":"Rahmanul","given":"Rahmanul"},{"family":"Daud","given":"Daud"},{"family":"Ikhsan","given":"Masrul"}],"issued":{"date-parts":[[2025]]},"DOI":"10.46730/japs.v4i3.124","URL":"https://doi.org/10.46730/japs.v4i3.124","source":"crossref"},{"id":"doi:10.1109/icict64420.2025.11004916","type":"article-journal","title":"Smart Farming Advisor: Optimized Crop Selection and Growth Procedure Using Random Forest","abstract":"The system analyses climate, soil characteristics, and past agricultural output trends based on district, taluk, and pin code inputs using machine learning techniques. It offers crop suggestions that are optimized to maximize yield potential and support sustainable farming by utilizing predictive analytics. It also integrates pest and disease prediction models to reduce risks and helps farmers follow best farming practices, such as the optimal time to sow, when to fertilize, and how to water. In addition to choosing crops, the system provides financial insights by projecting revenues depending on budget, market trends, and land acreage. It recommends crops with high demand and analyses price changes to assist farmers in making well-informed selections. Additionally, a land rent and search module in the system helps users locate appropriate agricultural property according to location, soil quality, and cost, making it accessible to both new and growing farmers. The system additionally offers a thorough explanation of fundamental agricultural requirements, including soil preparation, seed selection, irrigation methods, and pest control strategies, in order to facilitate all-encompassing farming operations. The system equips farmers with the tools they need to increase production, boost profitability, and implement sustainable agricultural practices by providing well-organized information and insightful recommendations.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icict64420.2025.11004916","URL":"https://doi.org/10.1109/icict64420.2025.11004916","source":"crossref"},{"id":"doi:10.71443/9789349552364-16","type":"article-journal","title":"Geospatial AI for Land Use Classification and Sustainable Agricultural Zoning","abstract":"This book chapter explores the transformative role of geospatial artificial intelligence (AI) in agricultural land zoning, with a focus on balancing economic development and environmental sustainability. As global demands for food production intensify, sustainable land management practices become crucial to mitigating ecological degradation and promoting long-term agricultural productivity. The integration of AI-driven methodologies, particularly machine learning and deep learning, with geospatial data sources such as satellite imagery and remote sensing technologies, offers unprecedented accuracy in land use classification, resource allocation, and land suitability prediction. By incorporating environmental factors like soil health, water availability, and climate projections, AI models facilitate the identification of optimal agricultural zones while minimizing risks of land degradation. Furthermore, the chapter discusses the socio-economic implications of zoning, emphasizing the need for policies that support both agricultural productivity and ecosystem preservation. The potential of AI to address key challenges in land use planning, such as urban encroachment and climate change impacts, is also examined through case studies from diverse geographical contexts. This research highlights the critical intersection of technology, policy, and environmental stewardship in shaping sustainable agricultural futures.","author":[{"family":"Subramoniam","given":"Muthurajan"},{"family":"Thanikasalam","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-16","URL":"https://doi.org/10.71443/9789349552364-16","source":"crossref"},{"id":"doi:10.14719/pst.14831","type":"article-journal","title":"Estimation of technical efficiency of integrated smart farming: Evidence from Tamil Nadu","abstract":"The study examines the technical efficiency and adoption dynamics of integrated smart farming system in Erode district of Tamil Nadu. Smart farming is represented as a bundled, firm-supported system integrating drip irrigation, fertigation and real-time digital advisory. The primary data were gathered from 120 farmers (60 adopters and 60 non-adopters) in 2025–26 (agricultural year) with stratified random sampling design. Data envelopment analysis (DEA) in variable returns to scale (VRS) and bias corrected using Simar and Wilson bootstrapped DEA were employed to estimate technical efficiency. Bootstrap truncated regression was used to analyse determinants of efficiency and a binary Logit model was used to analyse adoption behaviour. The outcomes revealed a mean technical efficiency of 0.62, representing a 38 % unrealised production potential. Fertiliser accounted for 93.30 % of the input slack, indicating mismanagement as a potentially important source of inefficiency. Education and technology adoption intensity are found to be significant drivers of efficiency. The extension linkage, perceived usefulness and technological awareness are key factors in the decision to adopt the smart farming technologies. The results underscore the need for the adoption of integrated technology packages, capacity development of farmers and extension support to improve the efficiency and productivity of farms.","author":[{"family":"Dhanush","given":"T"},{"family":"Selvam","given":"S"},{"family":"Prahadeeswaran","given":"M"},{"family":"Murugananthi","given":"D"},{"family":"Kalpana","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.14719/pst.14831","URL":"https://doi.org/10.14719/pst.14831","source":"crossref"},{"id":"doi:10.36948/ijfmr.2026.v08i03.80007","type":"article-journal","title":"Empowering Small Farmers Through Smart Farming: The Transformative Power of Agri-Tech in India","abstract":"The Indian economy is an Agro-economy, which means its agriculture sector is heavily dependent on the cycles of production, distribution, and consumption. This sector is facing increasing pressure from factors such as climate change, resource depletion, and a growing global population. This study aimed to research the adoption of technology in small-scale farming to improve production quality, efficiency, and economic development. We examined the determinants of technology adoption among small farmers using both primary and secondary data. For primary data, we collected over 100 responses from farmers and research students. For secondary data, we analyzed various journals, articles, and research papers. Our data revealed that while most farmers are aware of Agri-tech farming through various advertisements, they do not adopt it due to a lack of knowledge and the high cost of technology. The analysis also showed that government funding programs play a vital role in supporting agricultural technology startups. These programs provide the necessary capital for developing new technologies and expanding operations. By reducing the financial risks for startups, these programs encourage innovation. The rapid advancement of precision agriculture and the rise of Agri-tech startups are transforming the global agricultural landscape, enhancing productivity, sustainability, and climate resilience.","author":[{"family":"Mallick","given":"Nabaghan"},{"family":"Das","given":"Preetam"},{"family":"Sahoo","given":"Himanshu"},{"family":"Nayak","given":"Bibekananda"}],"issued":{"date-parts":[[2026]]},"DOI":"10.36948/ijfmr.2026.v08i03.80007","URL":"https://doi.org/10.36948/ijfmr.2026.v08i03.80007","source":"crossref"},{"id":"doi:10.71097/ijsat.v16.i2.4321","type":"article-journal","title":"Smart Farming: An Integrated Approach Using IoT  and AI","abstract":"Smart farming is a paradigmatic change in agri- cultural practice through the application of state-of-the-art technologies like the Internet of Things (IoT) and Artificial Intelligence (AI) towards productivity, efficiency, and sustain- ability. In this research study, an intelligent farm system is exemplified that aims to address some of the most significant challenges in conventional agriculture, like water shortage, pest control, and unforeseen climatic conditions. The system uses IoT sensors such as temperature, humidity, and soil moisture sensors through a NodeMCU microcontroller to obtain real- time environmental and soil conditions. The information is sent to a cloud platform and displayed on a responsive web applica- tion developed using the MERN stack (MongoDB, Express.js, React.js, Node.js), allowing farmers to monitor field conditions remotely from anywhere. To further complement crop health management, the system includes AI-based predictive models that examine past and real-time sensor data to predict future plant diseases. Additionally, image processing is used for early blight and late blight detection in plant leaves so that farmers can implement effective preventive measures at the right time. An automated irrigation system is utilized to ensure maximum use of the available water, which only switches on when the water level in the soil drops below a set limit, thus conserving water. The system also gives computerized advice on the maximum application of fertilizers and pesticides, aimed at the precise needs of specific crops. Besides on-field monitoring and automation, the system also comprises an AI-driven market price analysis module through which farmers are able to make well-decided choices about selling crops so as to bring maxi- mum profitability. Through IoT-based automation, AI-driven analytics, and cloud-based monitoring, the system promotes precision farming, minimizes the reliance on human resources, and saves resources. The paper thoroughly discusses the system architecture, implementation issues, and major advantages like increased crop yield, minimizing cost, and encouraging sustainable agricultural practices. Future expansion of the system includes drone field monitoring for bulk monitoring, blockchain for supply traceability, and extending AI models to include other crops. This project shows how applications of smart farming technologies can transform conventional farming to provide scalable and efficient solutions to farming challenges today with environmental sustainability and economic viability to farmers.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.71097/ijsat.v16.i2.4321","URL":"https://doi.org/10.71097/ijsat.v16.i2.4321","source":"crossref"},{"id":"doi:10.61978/digitus.v3i4.1076","type":"article-journal","title":"Smart Farming Technologies for Global Food Security:  A Review of Robotics and Automation","abstract":"This narrative review explores the role of robotics and automation in precision agriculture, particularly in addressing global challenges such as food security, labor shortages, and environmental sustainability. A systematic literature search was conducted using Scopus, Web of Science, and other supplementary databases, focusing on studies from 2015 to 2025. Findings show that AI-based models and UAV monitoring can enhance crop yield by up to 20% and reduce water and fertilizer use by 30%. Smart irrigation, soft robotics, and autonomous systems also demonstrate effectiveness in specific applications like pruning, weeding, and aquaponics. Despite promising outcomes, adoption varies due to financial, infrastructural, and governance barriers, especially in developing regions. The review concludes that integrating robotics with AI, IoT, and UAVs has transformative potential for agriculture. Future research should prioritize system interoperability, dataset quality, and environmental impact assessments to support widespread, equitable implementation.","author":[{"family":"Saromah"},{"family":"Gunawan","given":"Budi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.61978/digitus.v3i4.1076","URL":"https://doi.org/10.61978/digitus.v3i4.1076","source":"crossref"},{"id":"doi:10.21009/jpmm.009.1.01","type":"article-journal","title":"STRATEGY FOR IMPROVING LEMONGRASS AGRICULTURE BASED ON SMART FARMING IN JATIJEJER VILLAGE","abstract":"Lemongrass (Cymbopogon citratus) and citronella (Cymbopogon nardus L.) are flagship crops cultivated by farmers in Jatijejer Village. Lemongrass is commonly used as a culinary spice, while citronella is widely utilized for producing essential oil rich in citronellal, geraniol, and citronellol. The essential oil from citronella has high economic value due to its applications in the cosmetics and health industries. This community service activity aims to enhance local farmers' understanding and skills in proper lemongrass cultivation and the potential processing of essential oils as value-added products. The program focuses on strategies to optimize agricultural potential using proper cultivation techniques with organic farming systems based on smart farming technology. Farmers were educated on the stages of lemongrass cultivation, including land preparation, planting, crop maintenance, fertilization, pest and disease control, as well as harvesting and post-harvest handling. Participants were given pre-tests and post-tests to assess their understanding. The test results showed a significant improvement in participants' comprehension of proper lemongrass cultivation using smart farming methods, as well as the benefits and processing of essential oils. This activity successfully raised awareness of the importance of innovation in the agricultural sector and laid the foundation for the development of local businesses based on natural resources.","author":[{"family":"Gondokesumo","given":"Marisca"},{"family":"Azminah"},{"family":"Ardiansyahmiraja","given":"Bobby"},{"family":"Suryaningsih","given":"Retna"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21009/jpmm.009.1.01","URL":"https://doi.org/10.21009/jpmm.009.1.01","source":"crossref"},{"id":"doi:10.1002/9781394200467.ch16","type":"article-journal","title":"Farming Revolution","abstract":"Sensor technologies enable data-driven, efficient, and sustainable precision agriculture. This initiative monitors, manages, and predicts plant diseases using sensors, cloud computing, and data analytics to improve crop health and productivity. Plant and environmental data is monitored by soil, humidity, temperature, and leaf wetness sensors. Machine learning algorithms discover illness outbreak trends and abnormalities in real-time data on a cloud platform. According to the study, a complete IoT infrastructure easily transfers data from field sensors to cloud servers and decision support tools to end-users. Edge computing preprocesses data and delivers only relevant data to the cloud, decreasing latency and bandwidth. This allows fast, accurate disease prediction models to warn farmers of new hazards for proactive management. The study also examines how alternate communication protocols increase data transfer in agricultural fields with poor circumstances. We also explore how geospatial and sensor data accurately map and quantify disease risk. Cloud-based data analytics improves sickness prediction, operational efficiency, and resource management, this study revealed. This integrated strategy reduces plant diseases, herbicides, and fertilizers, improving sustainability. The scalable, cost-effective answers to modern farming problems in this research support precision agriculture.","author":[{"family":"Gopi","given":"Arepalli"},{"family":"Sudha","given":"LR"},{"family":"Joseph","given":"SIT"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394200467.ch16","URL":"https://doi.org/10.1002/9781394200467.ch16","source":"crossref"},{"id":"doi:10.1109/incet64471.2025.11140186","type":"article-journal","title":"Smart Farming: Enhancing Crop Recommendation and Price Prediction with Advanced Machine Learning","abstract":"This paper examines the innovative advancements in crop recommendation and price prediction, focusing on how cutting-edge machine learning techniques are reshaping the agricultural landscape. Traditional methods of crop selection often fall short, providing generalized advice that doesn't account for the unique conditions of each farm, leading to inefficiencies and increased risk for farmers. The enhanced models discussed in this paper address these shortcomings by utilizing algorithms such as Random Forest, Naïve Bayes, K-Nearest Neighbor, and XGBoost. These tools analyse a range of factors including soil characteristics, weather patterns, and historical crop performance to offer precise and specific recommendations. By predicting crop prices alongside these recommendations, the models enable farmers to make informed decisions that maximize yield, profitability, and sustainability. These also highlights the importance of continuous data integration, which ensures that the models remain relevant and accurate over time. Additionally, the use of visualization tools like Tableau allows farmers to easily interpret complex data, empowering them to adopt resource-efficient practices and reduce financial risks. This paper underscores the potential of these enhanced models to transform agriculture, making it more efficient, sustainable, and economically viable for farmers around the world.","author":[{"family":"Thakre","given":"Lekha"},{"family":"Daware","given":"Maithily"},{"family":"Mohite","given":"Ashlesha"},{"family":"Sakhare","given":"Apeksha"},{"family":"Khobragade","given":"Prashant"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/incet64471.2025.11140186","URL":"https://doi.org/10.1109/incet64471.2025.11140186","source":"crossref"},{"id":"doi:10.2174/9798898813963126010007","type":"article-journal","title":"A Smart IOT-Based Framework for Predictive Crop Health Monitoring and Precision Farming","abstract":"This chapter focuses on a novel IoT-based framework designed to help improve precision farming by closely monitoring soil and crop health. The system aims to reduce physiological disorders in crops through real-time data gathering, analytical machine learning, and automated alerts. Continuous data gathering regarding the soil conditions and the crop health parameters is carried out through the network of field sensors, which are then processed via a centralized system using advanced algorithms. Insights derived from the framework are sent to farmers through an easy interface that empowers farmers to make data-based decisions and interventions in time. Connecting this with already established farm management systems enables integrated precision agriculture. This encompasses improving resource efficiency, preventing crop diseases, boosting crop yield, lowering costs, and enhancing sustainable farming. This research is a benchmark in agricultural technology that could transform crop management practices and usher in enhanced productivity and sustainability on the farm. The system's prediction and preventive measures of possible occasions, enabling a farmer to act before they occur, will revolutionize modern farming ways around sustainable food production.","author":[{"family":"Fida","given":"Hashmat"},{"family":"Kaur","given":"Jaspreet"},{"family":"Mishra","given":"Binod"},{"family":"Kumar","given":"Vinod"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898813963126010007","URL":"https://doi.org/10.2174/9798898813963126010007","source":"crossref"},{"id":"doi:10.1109/itc-cscc66376.2025.11137651","type":"article-journal","title":"IoT-Driven Smart Farming Data Ecosystems for Durian Price Forecasting","abstract":"This study presents a smart farming data ecosystem driven by Internet of Things (IoT) for forecasting durian prices in Thailand. Real-time environmental data are collected from field-deployed sensors measuring temperature, humidity, solar radiation, rain fall, wind speed and wind direction. These data are combined with local durian price records and preprocessed using techniques such as outlier detection, linear interpolation and normalization. Random Forest Regression is used to identify influential environmental features and predict market prices. The results show that applying interpolation techniques significantly improves model accuracy and enables more reliable identification of key features such as solar radiation, wind speed and temperature. The proposed ecosystem offers a practical framework that transforms raw sensor data into actionable insights through predictive models and dashboards. This approach promotes proper data management aligned with real-time environmental inputs ensuring consistency and reliability for future forecasting and decision-making within the smart farming ecosystem.","author":[{"family":"Nanuam","given":"Jakkaphun"},{"family":"Phukseng","given":"Thanaphon"},{"family":"Thongnim","given":"Pattharaporn"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/itc-cscc66376.2025.11137651","URL":"https://doi.org/10.1109/itc-cscc66376.2025.11137651","source":"crossref"},{"id":"doi:10.1109/iccrtee64519.2025.11053074","type":"article-journal","title":"Deep Learning for Smart Farming Using Efficient Net-Based Disease Detection in Crops","abstract":"Crops are a major source of food worldwide, which gives people food security and economic assistance for their survival. Climate change which causes drastic changes in the environment along with the immunity lack in crops causes a substantial decrease in growth and yield. The detection of ailments in the early stages is essential for the prevention of crops like tomatoes and potatoes. The detection of diseases has become an important step towards treating the crops to increase the yield. The inadequate knowledge and unavailability of resources for small-scale farmers are the main reasons for late treatment or no treatment. The advancement in technology like Deep Learning (DL) can assist more when compared to traditional methods of detection and treatment. Each disease has some visible patterns on the leaves which can be leveraged to detect the disease with the help of Convolutional Neural Networks (CNNs) and Computer Vision. This paper presents a hybrid DL model that combines the strengths of EfficientNetB0 and transformer-inspired multi-head attention to identify six classes of tomato and potato leaf conditions, including healthy and diseased states.","author":[{"family":"Chaurasiya","given":"Shivam"},{"family":"Singh","given":"Manjit"},{"family":"Singh","given":"Ranjit"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/iccrtee64519.2025.11053074","URL":"https://doi.org/10.1109/iccrtee64519.2025.11053074","source":"crossref"},{"id":"doi:10.3390/info16100858","type":"article-journal","title":"IncentiveChain: Adequate Power and Water Usage in Smart Farming Through Diffusion of Blockchain Crypto-Ether","abstract":"The recent advancements in blockchain technology have also expanded its applications to smart agricultural fields, leading to increased research and studies in areas such as supply chain traceability systems and insurance systems. Policies and reward systems built on top of centralized systems face several problems and issues, including data integrity issues, modifications in data readings, third-party banking vulnerabilities, and central point failures. The current paper discusses how farming is becoming a leading cause of water and electricity wastage and introduces a novel idea called IncentiveChain. To keep a limit on the usage of resources in farming, we implemented an application for distributing cryptocurrency to the producers, as the farmers are responsible for the activities in farming fields. Launching incentive schemes can benefit farmers economically and attract more interest and attention. We provide a state-of-the-art architecture and design through distributed storage, which will include using edge points and various technologies affiliated with national agricultural departments and regional utility companies to make IncentiveChain practical. We successfully demonstrate the execution of the IncentiveChain application by transferring crypto-ether from utility company accounts to farmer accounts in a decentralized system application. With this system, the ether is distributed to the farmer more securely using the blockchain, which in turn removes third-party banking vulnerabilities and central, cloud, and blockchain constraints and adds data trust and authenticity.","author":[{"family":"Vangipuram","given":"Sukrutha"},{"family":"Mohanty","given":"Saraju"},{"family":"Kougianos","given":"Elias"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/info16100858","URL":"https://doi.org/10.3390/info16100858","source":"crossref"},{"id":"doi:10.1002/9781394287260.ch12","type":"article-journal","title":"IoT in Climate‐Smart Farming","abstract":"Climate change is evolving as a major issue in farming and food management across the globe. Due to sudden changes in climate conditions such as temperature, heavy rain, and droughts farmers are badly affected. The global demand for food, the integration of technology, particularly the Internet of Things (IoT), has emerged as a revolutionary force in Indian agriculture. The adoption of smart agriculture technologies powered by IoT has significantly contributed to higher production rates, facilitated remote monitoring, enabled precision farming practices, and introduced automation to streamline agricultural processes. This chapter focuses on the diverse methods employed for integrating IoT in agriculture and various case studies, assessing the effectiveness, advantages, and disadvantages of IoT integration in agriculture.","author":[{"family":"Darbha","given":"Maitreyi"},{"family":"Kumar","given":"SVS"},{"family":"Sekhar","given":"SRM"},{"family":"Sanjay","given":"HA"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394287260.ch12","URL":"https://doi.org/10.1002/9781394287260.ch12","source":"crossref"},{"id":"doi:10.2991/978-94-6463-678-9_11","type":"article-journal","title":"Smart Fish Feeding Solutions for Aquaponic Farming: Load Cell and Real-Time Clock Integrated System Design","abstract":"Aquaponics, a sustainable farming method integrating aquaculture and hydroponics, provides environmental benefits by reducing water usage and minimizing chemical fertilizers.However, efficient feed management remains a challenge, as improper feeding can negatively affect fish health and water quality.While automated systems have improved water and environmental monitoring in aquaponics, the regulation of fish feed-critical for system balance-remains underdeveloped.This study addresses the gap by designing a smart fish feeding system that automates feed delivery using load cell sensors and a Real-Time Clock (RTC), with predictive capabilities through ARIMA modeling.The system was tested with Nile Tilapia (Oreochromis niloticus) over a 12-week period.Results showed high precision in feed delivery, with an average feed weight difference of only 0.34 grams.The system achieved a Feed Conversion Ratio (FCR) of 5.61, indicating efficient feed utilization, while the fish experienced 123.12% growth.The incorporation of ARIMA enabled accurate forecasting of future feed needs based on fish growth trends, helping to maintain optimal feed amounts and prevent overfeeding.This research demonstrates how integrating real-time weight measurements with predictive modeling can enhance feeding precision, leading to healthier fish and reduced waste.Despite the system's success, environmental factors such as temperature and humidity occasionally affected sensor accuracy, suggesting future improvements.Future research should focus on scaling the system for larger operations and incorporating environmental controls, such as pH and temperature regulation, to further optimize aquaponic farming.This system presents a promising solution for sustainable aquaculture and hydroponics.","author":[{"family":"Risma","given":"Pola"},{"family":"Prasetyo","given":"Tegar"},{"family":"Utami","given":"Pertiwi"},{"family":"Sianipar","given":"Adelia"},{"family":"Rahman","given":"Raihan"},{"family":"Hibrizi","given":"Dzaky"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2991/978-94-6463-678-9_11","URL":"https://doi.org/10.2991/978-94-6463-678-9_11","source":"crossref"},{"id":"doi:10.1109/iconecct67014.2025.11469947","type":"article-journal","title":"Environmental Monitoring and Smart Automated Cleaning for Sustainable Dairy Farming","abstract":"India's economy significantly depends on livestock, with millions of farmers engaged in dairy farming and cattle management for income and sustainability. Despite its socioeconomic importance, dairy farming often faces challenges such as poor barn hygiene, excessive ammonia accumulation, inadequate ventilation, and heat stress, all of which adversely affect animal health and productivity. To address these issues, this paper proposes an IoT-based automated waste management and environmental monitoring system for modern dairy farms. The system employs multiple sensors to continuously track temperature, humidity, light intensity, and harmful gas concentrations within the barn. A ventilation fan and servo-controlled roof dynamically regulate airflow and lighting conditions based on sensor feedback, while a slanted floor, water sprayer, and conveyor mechanism automate waste removal and direct it to a biogas unit. The proposed design not only ensures a hygienic and safe environment for livestock but also promotes sustainable waste-to-energy conversion, reducing manual labor and enhancing farm efficiency. This scalable, energy-efficient approach demonstrates a step toward intelligent and eco-friendly dairy farm automation.","author":[{"family":"Pillai","given":"Lekshmi"},{"family":"Sah","given":"Pravin"},{"family":"Vijayan","given":"Lekshmi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iconecct67014.2025.11469947","URL":"https://doi.org/10.1109/iconecct67014.2025.11469947","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7077-4.ch010","type":"article-journal","title":"Next-Generation Farming","abstract":"- Digital technologies are transforming agriculture, provide innovative solutions for sustainability, efficiency, and resilience in farming. Among these technologies, integration of Digital Twins (DTs) and Virtual Environments (VEs) is revolutionizing agriculture by optimizing agricultural processes, reducing resource consumption, and enhancing productivity. Digital Twins create real-time, data-driven replicas of crops, soil, livestock, and farming infrastructure, enabling continuous monitoring and predictive analytics. These virtual models help farmers make data-informed decisions, improving resource efficiency and minimizing environmental impact. Virtual Environments, including Virtual Reality (VR) and Augmented Reality (AR), complement Digital Twins by providing immersive simulations for precision farming, training, and farm management.","author":[{"family":"Bhatia","given":"Sandeep"},{"family":"Jaffery","given":"Zainul"},{"family":"Mehfuz","given":"Shabana"},{"family":"Goel","given":"Neha"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-7077-4.ch010","URL":"https://doi.org/10.4018/979-8-3373-7077-4.ch010","source":"crossref"},{"id":"doi:10.66053/dtcs.v3i2.607","type":"article-journal","title":"Development of an IoT-based Smart Farming System using ESP32 for Livestock Monitoring","abstract":"Purpose – Livestock farming is a vital sector of the Indonesian economy, yet the common practice of allowing livestock to roam freely renders manual monitoring inefficient and exposes farmers to risks of loss, accidents, and theft. This study presents an IoT-based livestock monitoring prototype designed to enable real-time location tracking and automated boundary violation alerts, addressing the lack of affordable and practical smart monitoring solutions for smallholder farmers. Methods – The system was developed using an ESP32 microcontroller integrated with a Neo-6M GPS module and a Telegram bot for automatic notifications. A geofencing boundary of 50 meters was configured from a fixed reference point. Twelve trials were conducted across morning, afternoon, and evening sessions to evaluate system performance under varying conditions. Findings – The system delivered location alerts every ten minutes with Google Maps links and coordinates. Under normal conditions, livestock positions were detected within 5.0–12.7 meters of the reference point. Boundary violations exceeding 50 meters triggered immediate alerts, with notification latency ranging from 3 to 8 seconds under stable network conditions. GPS baseline error was approximately 5.0–5.5 meters, with an accuracy variation of ±2–3 meters. Research Implications – System performance is constrained by Wi-Fi network stability and environmental factors affecting GPS accuracy, limiting its generalizability to areas with reliable connectivity. Further field testing is required before broader implementation. Originality – This study contributes a low-cost, ESP32-based geofencing solution integrated with Telegram, offering a practical and scalable approach to smart livestock monitoring in developing agricultural contexts.","author":[{"family":"Fikriansyah","given":"Rizki"},{"family":"Mutmainah","given":"Siti"},{"family":"Dahlan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.66053/dtcs.v3i2.607","URL":"https://doi.org/10.66053/dtcs.v3i2.607","source":"crossref"},{"id":"doi:10.71443/9789349552364-14","type":"article-journal","title":"Blockchain and AI Convergence for Secure Agricultural Supply Chain Traceability","abstract":"The integration of Blockchain and Artificial Intelligence (AI) in agricultural supply chains represents a transformative shift towards enhanced transparency, security, and operational efficiency. As the agricultural sector faces growing challenges such as fraud, inefficiency, and lack of traceability, the convergence of these technologies offers promising solutions. Blockchain, with its decentralized, immutable ledger, ensures secure and transparent tracking of products from farm to table, while AI leverages predictive analytics and machine learning to optimize decision-making and resource management. This chapter explores the synergy between Blockchain and AI, emphasizing their role in improving traceability, ensuring data integrity, and reducing operational costs across the agricultural supply chain. Key components such as smart contracts, real-time monitoring, and automated decision-making are examined, showcasing the potential for Blockchain-AI systems to revolutionize the industry. Case studies highlight successful applications of these technologies in food safety, perishable goods management, and sustainable sourcing. The chapter also addresses critical concerns related to data security, privacy, and scalability, offering a comprehensive framework for the future implementation of Blockchain and AI in global agricultural supply chains.","author":[{"family":"Singh","given":"Rajan"},{"family":"Subramoniam","given":"Muthurajan"},{"family":"Ramamurthy","given":"M"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-14","URL":"https://doi.org/10.71443/9789349552364-14","source":"crossref"},{"id":"doi:10.3390/agriculture15070696","type":"article-journal","title":"Swift Transfer of Lactating Piglet Detection Model Using Semi-Automatic Annotation Under an Unfamiliar Pig Farming Environment","abstract":"Manual annotation of piglet imagery across varied farming environments is labor-intensive. To address this, we propose a semi-automatic approach within an active learning framework that integrates a pre-annotation model for piglet detection. We further examine how data sample composition influences pre-annotation efficiency to enhance the deployment of lactating piglet detection models. Our study utilizes original samples from pig farms in Jingjiang, Suqian, and Sheyang, along with new data from the Yinguang pig farm in Danyang. Using the YOLOv5 framework, we constructed both single and mixed training sets of piglet images, evaluated their performance, and selected the optimal pre-annotation model. This model generated bounding box coordinates on processed new samples, which were subsequently manually refined to train the final model. Results indicate that expanding the dataset and diversifying pigpen scenes significantly improve pre-annotation performance. The best model achieved a test precision of 0.921 on new samples, and after manual calibration, the final model exhibited a training precision of 0.968, a recall of 0.952, and an average precision of 0.979 at the IoU threshold of 0.5. The model demonstrated robust detection under various lighting conditions, with bounding boxes closely conforming to piglet contours, thereby substantially reducing manual labor. This approach is cost-effective for piglet segmentation tasks and offers strong support for advancing smart agricultural technologies.","author":[{"family":"Ding","given":"Qi’an"},{"family":"Zheng","given":"Fang"},{"family":"Liu","given":"Luo"},{"family":"Li","given":"Peng"},{"family":"Shen","given":"Mingxia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/agriculture15070696","URL":"https://doi.org/10.3390/agriculture15070696","source":"crossref"},{"id":"doi:10.1016/j.iot.2025.101754","type":"article-journal","title":"Co-creating a data-driven smart farming sensor networks for digital twin integration in Irish tillage farming","abstract":"Smart farming, integrating real-time environmental monitoring of soil and weather parameters, plays a critical role in advancing sustainable agriculture, improving productivity, and enhancing food security. In Ireland, the tillage sector supports approximately 10,000 farms contributing significantly to the national economy through cereal production. However, the sector faces mounting pressure to align with environmental regulations aimed at reducing greenhouse gas emissions, and soil and water pollution. There is a lack of established frameworks for on-farm environmental indicators monitoring. This study presents a pilot implementation of sensor-based monitoring within a Living Lab approach, emphasizing co-creation with tillage farmers. Through farmer engagement during farm visits and agricultural exhibitions, critical user requirements were identified as access to weather (64.7%) and soil data (51.0%), with 73.2% preferring digital access. In response, an Internet of Things-enabled system was deployed, capturing air temperature, humidity, and soil parameters (temperature, moisture, nutrients, electrical conductivity, pH). The system allows for continuous, real-time data collection, overcoming limitations of traditional data acquisition methods. Data were transmitted and visualized on a web-based dashboard. The initial mean values were air temperature (11.9 °C), soil temperature (13.4 °C), humidity (70.55%), nitrogen (10 mg/kg), phosphorus (3 mg/kg), potassium (40 mg/kg), pH (6.99), and EC (0.61 dS/m) which were within expected ranges for Irish conditions. These real-time data streams provide a foundation for digital twin development to later enable advanced analytics, predictive modelling, and informed decision-making. This pilot underscores the feasibility and value of smart farming approaches to enhance environmental compliance, sustainability, and policy alignment in Ireland’s tillage sector.","author":[{"family":"Otieno","given":"Fredrick"},{"family":"Lazarus","given":"Beulah"},{"family":"Banerjee","given":"Arghadyuti"},{"family":"Riaz","given":"Khurram"},{"family":"Nalakurthi","given":"Sudha"},{"family":"Gharbia","given":"Salem"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.iot.2025.101754","URL":"https://doi.org/10.1016/j.iot.2025.101754","source":"crossref"},{"id":"doi:10.3390/su172310838","type":"article-journal","title":"Proximal Monitoring of CO2 Dynamics in Indoor Smart Farming: A Deep Learning and Image-Sensor Fusion Approach","abstract":"In controlled environment agriculture (CEA), CO2 enrichment can promote photosynthesis while simultaneously reducing evapotranspiration, but the optimal settings vary depending on crop type, growth stage, and microclimate. This study presents a near-field remote sensing framework that fuses RGB image features with environmental variables to predict the CO2 uptake/respiration dynamics of five leafy vegetables grown in a hydroponic culture system and evaluate their impact on resource efficiency under CO2 control. A hybrid deep model incorporating You Only Look Once version 11 (YOLOv11) and a Residual Network with 50 layers (ResNet50) extracts growth-related visual cues and integrates them with tabular features (CO2, temperature, and light conditions) to predict chamber CO2 dynamics. Performance was evaluated by Mean Absolute Error (MAE)/Mean Squared Error (MSE) on withheld data, and the system-level impacts on water use (ET), pumping energy, and relative yield were analyzed using a conventional greenhouse model. The model exhibited high accuracy (MAE = 0.95; MSE = 1.62). Scenario analysis results showed that increasing ambient CO2 concentration from 400 to 1200 ppm reduced modeled water demand by approximately 11%, increased modeled yield by approximately 9%, and resulted in a corresponding reduction in pumping energy per unit area. Unlike conventional single-crop, table-based approaches, this study demonstrates multi-crop generalization and image-environment fusion for CO2 dynamic prediction, establishing proximity sensing as a viable decision-making layer for CEA. While yield/ET results were simulated rather than measured in long-term trials, and leaf area normalization was not available, the proposed framework provides a viable path for data-driven CO2 control in indoor farms by linking image-based monitoring with operational optimization.","author":[{"family":"Lee","given":"Seunghun"},{"family":"Kim","given":"Bora"},{"family":"Cheon","given":"Sang"},{"family":"Lee","given":"Jae"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/su172310838","URL":"https://doi.org/10.3390/su172310838","source":"crossref"},{"id":"doi:10.1201/9781003659907-19","type":"article-journal","title":"Precision Farming and Decision Support Systems, Utilizing Convolutional Networks for Plant Detection","abstract":"Precision farming has emerged as a key approach to optimize agricultural production through the use of advanced technologies such as sensors, GPS, remote sensing and data analysis. Convolutional neural networks (CNNs) have proven to be fundamental tools for image processing and automation of various tasks in the agricultural sector. These networks allow crop and weed classification, yield estimation, disease and pest detection, as well as irrigation and fertilization optimization. In addition, their integration with drones and artificial vision systems has enabled significant advances in crop detection and monitoring. Despite the challenges in their implementation, such as high initial costs and the need for quality labeled data, CNNs continue to evolve and offer innovative solutions to improve the efficiency and sustainability of modern agriculture.","author":[{"family":"Rubalcava-Avila","given":"Yossef"},{"family":"Avila-Quezada","given":"Graciela"},{"family":"Berzoza-Gaytan","given":"Cesar"},{"family":"Rai","given":"Mahendra"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003659907-19","URL":"https://doi.org/10.1201/9781003659907-19","source":"crossref"},{"id":"doi:10.1088/1755-1315/1623/1/012020","type":"article-journal","title":"Analysis of Good Dairy Farming Practices Implementation in Industrial-Scale Dairy Farming in West Sumatra","abstract":"Abstract This study evaluated the implementation of Good Dairy Farming Practices (GDFP) on industrial-scale dairy farms in West Sumatra, achieving an overall GDFP score of 3.71, which indicates “Good” compliance across key areas. Data were collected using a modified GDFP questionnaire, based on guidelines from the Food and Agriculture Organization (FAO), through a direct survey method at dairy farm locations. The study utilized questionnaires, observations, and interviews to gather detailed information from farmers. Key findings revealed strong adherence to practices related to milking hygiene and animal welfare. This research contributes new insights into dairy farming practices in West Sumatra, emphasizing the importance of enhancing environmental sustainability and socio-economic management. Practical recommendations for improving waste management and operational efficiency are also provided to align farming practices with GDFP standards further.","author":[{"family":"Islam","given":"Darul"},{"family":"Rachman","given":"Kevin"},{"family":"Susanty","given":"Hilda"},{"family":"Ratni","given":"Eli"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1088/1755-1315/1623/1/012020","URL":"https://doi.org/10.1088/1755-1315/1623/1/012020","source":"crossref"},{"id":"doi:10.3390/su18104775","type":"article-journal","title":"Understanding Farmers’ Adoption Intentions for Environmentally Friendly Intermediate Farming: A Typology-Based Analysis of Current Farming Systems in Japan","abstract":"Reducing agrochemical inputs while maintaining productivity is essential for sustainable agriculture and food security. To bridge the gap between conventional and organic systems and inform evidence-based promotion strategies, this study examines how farmers with different existing farming systems perceive and respond to an intermediate farming method characterized by minimal agrochemical use (≤1/8 of conventional levels) in Shizuoka Prefecture, Japan. A survey of 120 farmers was classified into organic (OA, 34.2%), reduced-input (RA, 28.3%), and conventional (CA, 37.5%) groups. Chi-square tests and binary logistic regression were employed to examine group differences and identify predictors of adoption intention. Adoption willingness varied significantly across groups (χ2 = 24.46, p &lt; 0.001): RA farmers showed the highest willingness (88.2%), followed by CA farmers (68.9%), while OA farmers were least willing (34.1%). Logistic regression identified farmer type (OA vs. CA: OR = 0.148, p = 0.001) and adoption conditions including health safety assurance (OR = 3.687, p = 0.026) and higher profitability (OR = 3.897, p = 0.040) as significant predictors. These findings highlight the importance of tailored extension strategies and evidence-based policy support to facilitate adoption across diverse farmer groups.","author":[{"family":"Wang","given":"Chunhong"},{"family":"Nakagomi","given":"Mitsuho"},{"family":"Oka","given":"Akari"},{"family":"Matsumoto","given":"Kazuhiro"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/su18104775","URL":"https://doi.org/10.3390/su18104775","source":"crossref"},{"id":"doi:10.1201/9781042015597-15","type":"article-journal","title":"Getting Started with Biodynamic Farming","abstract":"Biodynamic farming is a holistic and sustainable approach to agriculture that views the farm as a self-sustaining ecosystem. This article provides a comprehensive guide for beginners looking to embark on biodynamic farming, covering essential principles, practices, and preparations. It begins with an exploration of the philosophical underpinnings of biodynamic farming, rooted in the teachings of Rudolf Steiner, before delving into practical aspects such as soil health, crop rotation, composting, and pest management. The article also discusses the significance of biodynamic preparations, celestial planting calendars, and certification processes. With a focus on both traditional practices and modern adaptations, this guide aims to equip new biodynamic farmers with the knowledge and tools they need to start their journey toward a more sustainable and regenerative farming system.","author":[{"family":"Ramanjineyulu","given":"M"},{"family":"Naik","given":"Mude"},{"family":"Naik","given":"SNA"},{"family":"Bharathi","given":"A"},{"family":"Reddy","given":"Singireddy"},{"family":"Yoshitha","given":"Sibbala"},{"family":"Deepika","given":"J"},{"family":"Rao","given":"Marati"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781042015597-15","URL":"https://doi.org/10.1201/9781042015597-15","source":"crossref"},{"id":"doi:10.1109/icces63552.2024.10859921","type":"article-journal","title":"Implementation of Data Analysis for Affordable Smart Farming Based on IoT and Machine Learning","abstract":"The significance of agriculture in any country cannot be overlooked. Actually, about 70% of the population practices agriculture and this fills one third of the country's capital. Nonetheless, agriculture related challenges have always affected the country's economic growth. The answer to the problems posed above is the adoption of modern farming techniques. This project is concerned with the monitoring of temperature and moisture levels in the fields using appropriate sensors also known as smart agriculture. This way these techniques are incorporated into the agricultural system for crop yielding without excessive spraying with chemical insecticides, less cost of farming, more efficient water used, better control of land and crops. The communication technology makes it possible to monitor the field in question and to take corrective measures whenever necessary. Moreover, this project investigates how image processing systems and different types of sensors can be used for further enhancement of crop growth and yield.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icces63552.2024.10859921","URL":"https://doi.org/10.1109/icces63552.2024.10859921","source":"crossref"},{"id":"doi:10.3390/conservation6020074","type":"article-journal","title":"Effect of Bioeconomy Integration on the Transition from Traditional Livestock Farming to Circular Farming Models in Greece","abstract":"This study investigates the integration of bioeconomy principles in the Greek livestock sector, framing the transition from conventional farming toward a circular bioeconomy as a strategy for resource conservation and reduced environmental pressure. It assesses farmers’ awareness of bioeconomy principles, the adoption of circular practices, and the associated economic and conservation-related performance. Data were collected through a structured questionnaire administered to 383 livestock farmers across the main livestock-producing regions of Greece and analyzed using descriptive statistics and multiple regression. Although respondents show substantial awareness, adoption remains incomplete, mainly because of high initial capital costs and insufficient financial incentives. Farmers implementing circular strategies reported gains in resource-use efficiency, waste minimization, and the conservation of soil, water, and biodiversity, particularly reduced greenhouse-gas emissions, while public subsidies and fiscal incentives emerged as the principal drivers of adoption. In applied terms, support should be prioritized for capital-intensive investments such as anaerobic digestion, manure and nutrient recovery, and water reuse, and the awareness–adoption gap is best closed through targeted subsidies and training. The findings offer concrete guidance for conservation-oriented agri-environmental policy supporting the green transition of livestock farming in Greece.","author":[{"family":"Kalogiannidis","given":"Stavros"},{"family":"Spinthiropoulos","given":"Konstantinos"},{"family":"Chatzitheodoridis","given":"Fotios"},{"family":"Parris","given":"Dimitrios"},{"family":"Valsamopoulos","given":"Angel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/conservation6020074","URL":"https://doi.org/10.3390/conservation6020074","source":"crossref"},{"id":"doi:10.55121/nc.v5i3.1125","type":"article-journal","title":"Adopting Paludiculture as a Farming Model Resilient to Climate Change: Insights from Farming Communities in the Peatlands of South Sumatra, Indonesia","abstract":"Paludiculture, which involves growing crops and managing forests on rehydrated peatlands, is seen as a viable option to balance agricultural production with peatland conservation. However, the adoption of this practice by farmers remains inconsistent. This study investigated factors related to socioeconomic status and behavior that influence paludiculture adoption among communities living in peatland areas in Ogan Komering Ilir (OKI) Regency, South Sumatra, Indonesia. We surveyed n = 150 farmers and used Partial Least Squares Structural Equation Modeling (PLS-SEM) to assess how perceived usefulness (PU), perceived ease of implementation (PEI), institutional support (IS), economic capacity (SEC), and perceived climate risk (PCR) influenced adoption intention (AI) and actual adoption (AA) of the practice. Our findings indicate that adoption intention is positively correlated with perceived usefulness (β = 0.34, p &lt; 0.01) and perceived ease of implementation (β = 0.26, p &lt; 0.05). In contrast, perceived climate risk negatively impacted intention (β = −0.23, p &lt; 0.05). Institutional support contributed positively, albeit to a lesser extent (β = 0.17, p &lt; 0.10), while economic capacity had a slight positive correlation (β = 0.19, p ≈ 0.10). Intention to adopt was a strong predictor of actual adoption (β = 0.48, p &lt; 0.01). The model explained 56% of the variance in adoption intention (R2 = 0.56) and 38% of the variance in actual adoption (R2 = 0.38). These results suggest that promoting paludiculture will require increasing perceived economic benefits, reducing concerns about risks through ongoing training and demonstrations, and improving supporting conditions such as extension services and financing. Policies that combine technical assistance with institutional support and market development are likely to accelerate adoption and enhance climate resilience in peatland farming systems.","author":[{"family":"Pusvita","given":"Ema"},{"family":"Hermawati","given":"Lisa"},{"family":"Gribaldi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.55121/nc.v5i3.1125","URL":"https://doi.org/10.55121/nc.v5i3.1125","source":"crossref"},{"id":"doi:10.1088/2632-959x/ae83d3","type":"article-journal","title":"Recent advances in semi-transparent perovskite solar cells for the possibility of agrivoltaics for smart farming: a review","abstract":"Abstract Perovskite solar cells (PSCs) have emerged as a transformative photovoltaic (PV) technology due to their rapid efficiency improvements and low-cost fabrication potential, attracting significant academic and industrial interest. In particular, semitransparent PSCs (ST-PSCs) introduce a paradigm shift by enabling simultaneous electricity generation and light transmission, thereby expanding their applicability beyond conventional PVs. This review explores recent advances in ST-PSCs with a focus on their integration into building-integrated PVs and agrivoltaic systems for smart farming. Unlike traditional opaque solar modules, ST-PSCs can selectively transmit photosynthetically active radiation, enabling concurrent crop cultivation and energy harvesting while addressing critical land-use challenges. The paper critically examines the progress in materials engineering, device architectures, and spectral tuning strategies that enable high efficiency and controlled transparency in PSCs. Furthermore, it discusses emerging innovations such as wavelength-selective designs and dynamically tunable modules that function as ‘smart’ systems to optimize plant growth conditions and mitigate thermal stress. Despite these advancements, key challenges—including long-term stability, lead toxicity, large-scale fabrication, and environmental impact—remain barriers to commercialization. Overall, this review highlights the multifunctional potential of ST PSCs as a next-generation solution for sustainable energy systems, bridging the gap between energy production, agriculture, and urban infrastructure. By integrating energy generation with food production and built environments, ST-PSCs offer a promising pathway toward efficient land use, enhanced sustainability, and smart energy management in future PV applications.","author":[{"family":"Khan","given":"Aimal"},{"family":"Shahzad","given":"Amir"},{"family":"Lee","given":"It"},{"family":"Rabbani","given":"Nahin"},{"family":"Basit","given":"Abdul"},{"family":"Jan","given":"Shayan"},{"family":"Rehman","given":"Qandeel"},{"family":"Khan","given":"Adnan"},{"family":"Ahmad","given":"Muhammad"},{"family":"Wali","given":"Qamar"},{"family":"Noman","given":"Muhamad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1088/2632-959x/ae83d3","URL":"https://doi.org/10.1088/2632-959x/ae83d3","source":"crossref"},{"id":"doi:10.32317/ekon.apk/2.2025.76","type":"article-journal","title":"Smart farming models in urbanised regions: Prospects for economic efficiency and sustainability","abstract":"The aim of this study was to assess the economic efficiency and sustainability of implementing smart technologies in agriculture within urbanised regions, specifically using the case of the agro-industrial holding “Myronivsky Hliboproduct” (MHP). The methodology incorporated both quantitative and qualitative analytical methods. An empirical analysis of the yield of key crops was conducted. To evaluate the economic efficiency of the implemented technologies, a graph of the company’s income dynamics was constructed, enabling an assessment of the impact of smart technologies on the enterprise’s financial performance. The key findings indicate that the adoption of smart technologies at MHP contributed to a significant increase in crop yields and a reduction in resource costs. For instance, maize yields rose from 8.6 t/ha in 2016/2017 to 10 t/ha in 2021/2022, remaining stable at 9.9 t/ha in 2023/2024. A similar trend was observed in other crops: rapeseed yields increased from 3.7 t/ha to 4.2 t/ha, while soybean yields grew from 2.4 t/ha to 2.8 t/ha. These results are attributed to the application of advanced techniques, including Real-Time Kinematic (RTK) navigation, automated management systems, and variable-rate fertilisation. An analysis of economic indicators revealed steady growth in the company’s revenue even under challenging economic conditions. The graph demonstrated that MHP’s income increased significantly during the period of active smart technology adoption. In 2024, the company’s revenue reached USD 770 million, confirming the economic efficiency of the implemented solutions. Furthermore, the use of digital platforms for field monitoring and process management optimised machinery maintenance costs and yield forecasting. The conclusions confirm that smart farming is an effective tool for modernising agriculture in urbanised regions. The practical significance of the study lies in demonstrating the efficiency of smart farming adoption for enhancing agricultural productivity. The results indicate the potential for substantial yield increases and resource cost reductions through the use of innovative technologies such as precision farming, digital platforms, and automation","author":[{"family":"Puyu","given":"Vasyl"},{"family":"Ponichtera","given":"Piotr"},{"family":"Havriliuk","given":"Valerii"},{"family":"Sheiko","given":"Iryna"},{"family":"Kozyrsky","given":"Dmytro"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32317/ekon.apk/2.2025.76","URL":"https://doi.org/10.32317/ekon.apk/2.2025.76","source":"crossref"},{"id":"doi:10.1109/icfcr64128.2024.10762964","type":"article-journal","title":"Smart Farming Solutions: Deep Learning-Driven Multi-Classification of Rice Crop Diseases","abstract":"Rice, being recognized as a fundamental staple crop on a global scale, assumes a central position in ensuring food security worldwide. Nevertheless the agricultural sector encounters significant obstacles in the shape of many illnesses that possess the potential to cause severe damage to crop productivity and jeopardize the availability of food resources. The proposed work endeavors to undertake a thorough investigation to tackle these issues by creating a resilient system for detecting diseases and classifying rice plants into multiple categories. Rice farming is faced with several frequent illnesses, each possessing distinct characteristics and exerting a specific impact on the health of the crop. The diseases encompassing rice blast, rice blight, hispa disease, and rice stem rot disease are widely recognized for their significant capacity to case extensive harm. Differentiating these illnesses from healthy rice plants is a procedure that requires significant labor and is susceptible to errors when conducted manually. To address these problems, the suggested study has carefully assembled a dataset consisting of high-resolution photos of rice plants. These images encompass a range of growth phases and indications of diseases. By utilizing state-of-the-art deep learning (DL) methodologies, the proposed work developed an advanced image processing model that exhibits the ability to classify rice plants into five discrete categories: healthy, rice blast, rice blight, hispa disease, and rice stem rot disease, without the need for manual intervention. The presented research encompasses not only the construction of a precise classification model but also explores the practical consequences of early illness detection in the context of rice farming. The experimental findings yielded highly encouraging results, as our model had an exceptional accuracy rate of 97.21%. The practical implications of our research extend far beyond the boundaries of the laboratory. The implementation of precision agricultural techniques is crucial for the promotion of sustainable rice cultivation and the maintenance of food security in an era characterized by significant global transformations.","author":[{"family":"Riya"},{"family":"Mogha","given":"Sandeep"},{"family":"Vatsal"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icfcr64128.2024.10762964","URL":"https://doi.org/10.1109/icfcr64128.2024.10762964","source":"crossref"},{"id":"doi:10.1109/icisessc68634.2026.11542767","type":"article-journal","title":"Smart Farming Assistant Using ML","abstract":"In several nations, such as India, agriculture is a crucial economic sector that sustains billions of jobs and addresses future challenges like climate change and climate change related pest and disease outbreaks. Based on continuous research, a web based system has been created that uses real-time data to recommend specific crops to grow, taking into consideration the state of soil nutrient availability, weather, and moisture. With the advancement of technology in both machine learning and artificial intelligence, we can now be more precise with our agriculturerelated data analysis and provide farmers with accurate, data driven predictive outcomes (or predictions) regarding their crop yields and the timing of crop diseases. All of the above mentioned technologies are revolutionising the agriculture sector, as they allow for greater accuracy and efficiency in predicting crop production and identifying pests or diseases. We applied machine learning models to train and assess seven different machine learning models (Decision Trees, Naive Bayes, SVM, Logistic Regression, Random Forest, XG Boost, and KNN). The best performing model for predicting the yield of crops is Random Forest, as it achieved the highest level of accuracy. The web application also includes a Plant Disease Identification Application that uses Convolutional Neural Networks to detect plant diseases. CNN detects and accurately classifies plant diseases by analysing leaf images, helping farmers to take early action to mitigate crop loss. The purpose of this research is to provide farmers with easy to use technology so they can make informed choices regarding what crop to plant, and how to treat their plants when diseased. The combination of disease detection and crop recommendation will lead to the implementation of smarter crop recommendation systems that incorporate plant disease detection, these will aid in creating sustainable agricultural systems, promoting economic stability, and ensuring food security in India and other countries across the World.","author":[{"family":"Singh","given":"Rajani"},{"family":"Maurya","given":"Prabhanjan"},{"family":"Kumar","given":"Shashwat"},{"family":"Srivastava","given":"Prachi"},{"family":"Shakya","given":"Prateek"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icisessc68634.2026.11542767","URL":"https://doi.org/10.1109/icisessc68634.2026.11542767","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.101806","type":"article-journal","title":"Identifying Digitalisation patterns in Spanish livestock farming through open data use. A proposal of best practice management","abstract":"Digitalization in Spanish livestock farming is a key factor for efficiency, sustainability, and competitiveness. This study identified digitization patterns using open data and proposed best-practice strategies to support the sector's digital transition and targeted public policies. An open-access dataset from the Spanish Ministry of Agriculture (MAPA, 2024) covering 603 farms was analysed. Twenty-three variables describing production systems, digital technologies, and training were processed, and principal component and hierarchical cluster analyses were applied. Five factors explaining 62.85% of the total variability were identified, leading to three farm types: Smallholders (34.83%) with minimal digitalization; Family farms (27.69%) with low technological adoption; and Commercial farms (37.48%) with intermediate digitalisation. Digitalisation was positively associated with farm size, training, and regional technological development, while a gender gap emerged, with most women-managed farms in low-digitalisation clusters. The study showed the value of open data for identifying digitalisation patterns and provided evidence-based foundations for digital transition through a best-practice framework to accelerate Smart Farming across farm profiles. For smallholders, basic digitisation packages and subsidised rural connectivity are prerequisites for the uptake of digital tools and collection of operational data in structurally constrained contexts. For family farms, integrated management platforms (ERP-type solutions) and targeted training in data management and decision-support are essential to improve production organisation and strengthen digital competencies. For larger commercial operations, the results highlight the need to promote interoperability among IoT devices, sensor networks, and farm management software, and indicate that AI-based predictive analytics and smart alert systems can enhance monitoring and overall operational efficiency.","author":[{"family":"Bustamante","given":"Eva"},{"family":"Capote","given":"Cecilio"},{"family":"González","given":"Francisco"},{"family":"De-Pablos-Heredero","given":"Carmen"},{"family":"Martínez","given":"Antón"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.101806","URL":"https://doi.org/10.1016/j.atech.2026.101806","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-134-84-98","type":"article-journal","title":"PLANT POLLEN AND ITS ROLE IN THE ECOSYSTEM: HONEY BEE – HUMAN (Review)","abstract":"The article provides a comprehensive review of the biological significance of pollen as a vital resource for honeybees. Its role in feeding larvae, maintaining the physiological activity of worker bees and ensuring high egg laying of the uterus is revealed. The nutritional and biochemical value of pollen, its nutritional characteristics, and the dependence of its qualitative composition on botanical origin and environmental conditions are considered in detail. For honeybees, pollen is of key importance – it is a source of proteins, fats, minerals and vitamins necessary for larval development, immune defense and adult life. However, due to agrochemistry, reduction of honey and pollen fields, as well as climate change, the availability of high-quality pollen decreases, which weakens bee colonies and reduces the yield of entomophilic crops. Pollen-bearing plants perform not only a fodder, but also an ecological function, contributing to the maintenance of pollinators, restoration of flora and sustainability of agricultural systems. Climate change and urbanization threaten their diversity, so the priority should be to restore flower biotopes and create favorable conditions for pollinators. Organic farming and urban planning that takes into account the needs of bees are the way to sustainable development. The article provides a comprehensive analysis of the historical use of pollen (from ancient civilizations to modern science), while simultaneously reflecting its economic, biological and ecological significance. Current scientific directions of pollen research are outlined, in particular in the field of apitherapy, pharmacology, food safety, biomonitoring of the environment, as well as prospects for using pollen as a functional ingredient in the food industry. The impact of agricultural factors, pesticides, urbanization, and climate change on the pollen base is considered. The role of pollen as an indicator of the environment, paleobotanic resource and a key factor in the stabilization of agroecosystems through the support of pollinator populations is highlighted. Special attention is paid to the need to preserve and develop natural and cultivated pollen-bearing lands as the basis for the stable functioning of bee colonies and the preservation of biodiversity. The paper highlights the interdisciplinary nature of pollen research and justifies the need for further systematic research in this area.","author":[{"family":"Masliy","given":"Irina"},{"family":"Prusova","given":"Galina"},{"family":"Bachevskaya","given":"Yevgenia"},{"family":"Marchenko","given":"Alexander"},{"family":"Duvin","given":"Vladimir"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-134-84-98","URL":"https://doi.org/10.32900/2312-8402-2025-134-84-98","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-133-134-145","type":"article-journal","title":"INFLUENCE OF MORPHOFUNCTIONAL PARAMETERS OF MARES OF NOVOOLEXANDRIVSKII DRAFT ON THEIR MILK PRODUCTIVITY","abstract":"The research is devoted to determining the relationship of milk productivity of mares of the Novoolexandrivskii Draft with their morph functional indicators: torso and udder measurements. in two independent experiments (in two different farms), the indicator of milk productivity of mares of the Novoolexandrivskii Draft was studied depending on morph functional indicators – torso and udder measurements. the highest level of milk productivity was established in large-type mares by height at the Withers (150 cm) and chest circumference (190 cm). At the same time, minor correlations were established between the indicator of milk productivity and height at the withers (r=0.112) and oblique trunk length (r=0.109). In the second experiment, milk productivity was most correlated with chest circumference (r=0.280), metacarpal circumference (r=0.245), and trunk circumference (r=0.232). Body measurements of the studied mares are quite closely related: height at the withers × circumference of the body (r=0.811), circumference of the body × circumference of the metacarpus (r=0.573), chest circumference × circumference of the metacarpus (r=0.559), height at the withers × circumference of the metacarpus (r=0.520). By determining the development indicators of foals from Mares of various types, it was established that both foals and mares obtained from large-type mares prevailed over peers obtained from small-type mares by live weight in the development periods from birth to 18 months of age. It was found that large-type mares are also characterized by higher indicators of udder girth and length, while small-type mares predominated in udder depth. Positive correlation coefficients of the average bond strength were found between the milk productivity of mares and udder circumference (r=0.370) and udder length (r=0.301), with udder depth the bond is weak and negative (r=-0.113). A fairly strong relationship was found between udder measurements: girth × length (r=0.665), length × depth (r=0.570), girth × depth (r=0.361). The udder girth index significantly and positively correlated with the indicators of body structure indices: format (r=0.654), massiveness (r=0.514), Bony (r=0.391). The udder length index is positively and significantly correlated with the bony index (r=0.486) and format index (r=0.323).","author":[{"family":"Tkachova","given":"Irina"},{"family":"Lyutykh","given":"Sergey"},{"family":"Prusova","given":"Galina"},{"family":"Rusko","given":"Natalia"},{"family":"Brovko","given":"Alexey"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-133-134-145","URL":"https://doi.org/10.32900/2312-8402-2025-133-134-145","source":"crossref"},{"id":"doi:10.61909/amkedtb022539","type":"article-journal","title":"SUSTAINABLE FARMING REVOLUTION","abstract":"The book begins with an introduction to sustainable farming, addressing the pressing need for a farming revolution in response to environmental challenges. It highlights the crucial role of technology, including environmental engineering and machine learning, in transforming agriculture into a more efficient and eco-friendly domain. From soil health management and water resource optimization to renewable energy integration and waste recycling, this book delves deep into the principles of environmental engineering applied to agriculture. One of the most groundbreaking aspects of this book is its exploration of machine learning in agriculture. It provides a user-friendly introduction to AI and predictive analytics for non-experts while covering advanced applications such as disease and pest detection, precision farming, and climate adaptation strategies. The book also discusses image recognition for crop health monitoring and the challenges of implementing AI-driven solutions in the farming sector. Readers will find inspiring success stories showcasing real-world applications of machine learning in modern agriculture. Smart agricultural practices form another pillar of this book, providing an in-depth look at innovative solutions like IoT-based farming systems, automated irrigation, agricultural drones, blockchain for supply chain transparency, robotics, and smart sensors. These technologies are paving the way for a more efficient and data-driven approach to farming, ensuring sustainability while maximizing productivity. A critical aspect of sustainable farming is soil health and fertility management. This book explores sustainable enrichment techniques, bioengineering for soil restoration, AI-driven soil analysis, and best practices such as crop rotation and companion planting. It also warns against the risks of over-fertilization and eutrophication, emphasizing the importance of balance in soil nutrition. Climate-smart agriculture is another vital component, addressing strategies for climate change adaptation, greenhouse gas mitigation, drought-resilient crops, and water management in changing climates. The book highlights the role of AI in climate adaptation and presents policies and success stories from around the world, illustrating effective approaches to climate-resilient farming. Additionally, the book covers sustainable crop management, ethical livestock farming, advanced irrigation techniques, and the economic and social impacts of smart agriculture. It discusses how technology can empower farmers, reduce costs, and address global food security challenges, while also bridging the urban-rural divide through education and training. For those interested in the policy and global perspectives of sustainable farming, the book provides an overview of international initiatives, government incentives, legal and ethical considerations, and collaborations between private and public sectors. It offers case studies demonstrating policy-driven agricultural transformations and insights into the future of farming. The concluding chapter envisions the future of sustainable agriculture, exploring emerging technologies such as AI, IoT, robotics, and big data in farming. It emphasizes the importance of a circular economy in agriculture and highlights the challenges that must be overcome for widespread adoption. Finally, it inspires readers to contribute to a global movement for sustainable farming and food security. With a blend of scientific research, practical applications, and forward-thinking strategies, Sustainable Farming Revolution is an indispensable guide for those seeking to harness the power of environmental engineering, AI, and smart agricultural practices to build a more sustainable and resilient future.","author":[{"family":"Sharma","given":"Dr"},{"family":"Taneja","given":"Dr"},{"family":"Suri","given":"Dr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.61909/amkedtb022539","URL":"https://doi.org/10.61909/amkedtb022539","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-134-138-149","type":"article-journal","title":"USE OF CRUSHED FLAX SEEDS AS A PREBIOTIC WHEN FEEDING DAIRY COWS DURING THE FULL LACTATION CYCLE","abstract":"Increased consumption of dry matter in diets by highly productive cows leads to a high level of energy per unit of dry weight and the introduction of 45-50% of concentrated feed into the feed mixture. As a result, scar digestion is modified, lactic acid synthesis by scar microorganisms increases, which creates conditions for the development of an acute inflammatory process in typical scar acidosis. The main method of preventing this disorder is the constant use of alkaline additives and buffer mixtures in the diet, which allow you to maintain the optimal pH. The cationic structure of these systems, when constantly used, has an irritating effect on the small and large intestines of cows, which leads to a weakening of digestion and the development of a diarrheal effect of varying severity. This leads to a decrease in the digestibility of feed nutrients and, as a result, a decrease in the level of milk yield with a loss of milk quality indicators. Restoration of normal digestion in ruminants in such conditions is possible with the additional introduction of specific probiotic drugs into the diet, of which there are not many, and most of them are ineffective. Therefore, it is more reliable and expedient to use not pro -, but prebiotics, which form a protective effect against diarrhea based on the activation of animals ‘ own intestinal microflora by changing the activity of the villi surface. In addition, the prebiotic effect is achieved by using individual astringents that reduce villi irritation. However, such special additives are characterized by an increased cost, so it is advisable to search for normal feed components of the diet that have pronounced prebiotic properties and justify their effectiveness in feeding cows. In a long-term experiment on dairy cows, the effect of correcting the feeding of highly productive animals using crushed flax seeds was studied, which was used as a functional feed ingredient with a prebiotic effect.","author":[{"family":"Podobed","given":"Leonid"},{"family":"Kosov","given":"Nikolay"},{"family":"Saprykin","given":"Vyacheslav"},{"family":"Zolotarev","given":"Andrey"},{"family":"Yeletskaya","given":"Larisa"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-134-138-149","URL":"https://doi.org/10.32900/2312-8402-2025-134-138-149","source":"crossref"},{"id":"doi:10.5772/intechopen.1008336","type":"article-journal","title":"Hydroponic Farming: Innovative Solutions for Sustainable and Modern Cultivation Technique","abstract":"As conventional soil-based farming face limitations due to diminishing arable land per capita, advanced agricultural technologies have emerged as a promising solutions. Among these, hydroponic farming – a soilless crop cultivation method – stands out as a leading innovation in vegetable production, offering a viable response to these pressing challenges. This chapter explores the world of hydroponic farming, highlighting the best and most sustainable practices associated with this modern cultivation technique. By reviewing peer-reviewed articles from reputable educational journals, the chapter categorizes the findings into four key areas: types of hydroponic farming systems, factors that affect their performance, substrate constituents, and potential applications in modern agriculture. The findings of the current review indicate that hydroponic farming is an effective tool for combating hunger and improving food safety, especially in developing countries with limited water resources. By implementing innovative techniques that enhance resource utilization, reduce health impact, and create a more sustainable for food production, hydroponics represents a significant advancement in agriculturral environment.","author":[{"family":"Korsa","given":"Gamachis"},{"family":"Ayele","given":"Abate"},{"family":"Haile","given":"Setegn"},{"family":"Alemu","given":"Digafe"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5772/intechopen.1008336","URL":"https://doi.org/10.5772/intechopen.1008336","source":"crossref"},{"id":"doi:10.2174/9798898812102125030007","type":"article-journal","title":"Fuzzification for Precision Farming with Minimal Human Intervention","abstract":"Seamless communication between humans and things like cars and other such machines in important industry sectors is constantly evolving as each day passes. In the 21st century, crucial advancements in several fields have implemented IoT in them because of its numerous merits. When IoT is put into practice alongside Cloud Computing and Data Analytics, it can reduce the gap and enhance cooperation between the physical and digital worlds, which is essential for sustainability in this hyperconnected era. The project involves collecting data through sensors in the field, which is then sent to the IoT analytics and cloud-based platform ThingSpeak. This platform enables data ingestion and storage, allowing farmers to remotely visualize and analyze real-time data in the form of data streams and take action accordingly. Fuzzy logic is one such approach to computing that works on degrees of truth rather than single-valued Boolean logic, thus yielding better and more accurate conclusions for an imprecise spectrum of data. Fuzzy logic is implemented in this project to control water pumping time based on user-defined thresholds. With an increasing population and depleting resources, precision farming has proven to be efficient as it focuses on minimizing waste and is cost- and energy-efficient. The objective of this paper is to develop a system that assists farmers in remotely monitoring data, optimizing resource utilization, and increasing productivity.","author":[{"family":"Mangalampalli","given":"Sudheer"},{"family":"Karri","given":"Ganesh"},{"family":"Reddy","given":"Pelluru"},{"family":"Rajkumar","given":"KV"},{"family":"Pokkuluri","given":"Kiran"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2174/9798898812102125030007","URL":"https://doi.org/10.2174/9798898812102125030007","source":"crossref"},{"id":"doi:10.1079/9781800626850.0052","type":"article-journal","title":"Socio-economic Impact of Organic Vegetable Farming on Smallholder Farmers’ Economic Well-Being","abstract":"With the increased awareness of the benefits of organic farming and its potential to alleviate poverty among smallholder farmers, providing empirical evidence on its impact on household economic well-being becomes crucial. This study examined the socio-economic impact of organic vegetable farming on household consumption expenditures and household deprivation (poverty) scores in the Oyo and Ekiti states of Nigeria. The study employed a multi-stage sampling technique, and a total of 384 vegetable farming households were sampled. Primary data collection was through a structured questionnaire. For impact analysis, the study adopted the Endogenous Treatment Effect Model (ETEM), which considered the possibility of unobservable factors affecting the treatment effect in the model. The results showed that adopting organic green leafy vegetables (GLV) decreased poverty significantly and had the potential to increase farmers’ consumption expenditures. Hence, organic GLV farming can be adopted as a strategy to improve the economic well-being of smallholder farmers.","author":[{"family":"Familusi","given":"Linda"},{"family":"Edriss","given":"Abdi"},{"family":"Phiri","given":"Mthakati"},{"family":"Kazembe","given":"John"},{"family":"Onoja","given":"Anthony"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1079/9781800626850.0052","URL":"https://doi.org/10.1079/9781800626850.0052","source":"crossref"},{"id":"doi:10.1051/bioconf/202515907004","type":"article-journal","title":"Urban farming: Production risks of vegetable farming in Pekanbaru City, Riau Province, Indonesia","abstract":"Urban agriculture provides an effective solution to meet the needs of urban residents while reducing dependency on external sources. This study aims to analyze (1) the characteristics of spinach and water spinach farmers, (2) vegetable cultivation technology, (3) sources of production risks, and (4) the level of production risks. The research was conducted in the Marpoyan Damai sub-district of Pekanbaru, with a sample size of 30 farmers. The results indicate that most farmers are between 43-49 years old, with most having elementary school education and 11-20 years of farming experience. The study also identified several sources of production risks, including extreme weather, diseases and pests, climate change, limited water supply, and technological advancements. Furthermore, the level of production risk was found to be moderate, with spinach showing higher variability in yield compared to water spinach. This research provides insights into the challenges urban vegetable farmers face in Pekanbaru.","author":[{"family":"Vaulina","given":"Sisca"},{"family":"Elinur"},{"family":"Dewi","given":"Ilma"},{"family":"Maharani","given":"Tati"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1051/bioconf/202515907004","URL":"https://doi.org/10.1051/bioconf/202515907004","source":"crossref"},{"id":"doi:10.32628/ijsrset25122193","type":"article-journal","title":"Smart Farming Revolution: AI, IoT, and Robotics in Precision Agriculture and Soil Conservation","abstract":"Advances in artificial intelligence (AI), the internet of things (IoT), and robotics are reshaping how precision agriculture is practiced and how soil resources are preserved. The technologies allow for decision-making based on data, resource optimization, and environmentally friendly farming. AI allows for sophisticated predictive analysis, which means farmers can predict yield results, detect diseases in advance, and maximize planting timetables. IoT-based sensor networks enable real-time soil health monitoring, weather patterns, and crop development, enabling more efficient and timely farm operations. Robotics transforms conventional farm work by bringing autonomous platforms to seeding, harvesting, and soil testing, lowering labor costs and improving operational effectiveness. By better management of water, reduced land erosion, and reduced wastage of fertiliser, the use of such intelligent technologies not only enhances the productivity of agriculture but also ensures the conservation of soil. Robotic automation, IoT-based monitoring systems, and AI-based analytics play an important role in enhancing agricultural productivity and environmental sustainability, which is emphasized in the discussion of existing trends in intelligent agriculture in this paper.","author":[{"family":"Kuli","given":"Bhaba"},{"family":"Debnath","given":"Joytu"},{"family":"Sheikh","given":"Asaruddin"},{"family":"Das","given":"Samiran"},{"family":"Balai","given":"Pritam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32628/ijsrset25122193","URL":"https://doi.org/10.32628/ijsrset25122193","source":"crossref"},{"id":"doi:10.36956/rwae.v6i1.1536","type":"article-journal","title":"The Role of Agricultural Cooperatives in Enhancing Credit Access, Market Information, and Smart Farming Among Rural Farmers","abstract":"This study examines the role of agricultural cooperatives in enhancing Credit Access (CA), Market Information (MI), and Smart Farming (SF) among rural farmers in Kerala. Agricultural cooperatives serve as vital organizations that address key challenges smallholder farmers face, including limited CA, MI, and SF. Using a quantitative research design, structured surveys collected data from 421 cooperative and non-member farmers. The study aims to identify the effects of cooperative membership in CA services, MI and SF among rural farmers. Analysis of key findings shows that cooperative members loan from multiple financial sectors, are provided with more frequent MI, and have higher adoption of SF practices, thus featuring the importance of cooperatives in financial development, MI, and environmental organization. The analysis employs t-tests, Chi-square tests, Pearson correlations, and regression models to compare the impact of cooperative membership on CA, MI, and SF. The results reveal that cooperative members are significantly more likely to secure loans, receive more significant loan amounts, and report higher satisfaction with loan terms than non-members. Cooperative members also receive more frequent and reliable MI, which enables them to adjust their sales approaches and access better market opportunities. In addition, cooperative members exhibit higher adoption rates of SF and perceive more significant economic benefits. The study confirms that agricultural organizations are critical in promoting financial inclusion, market participation, and environmental sustainability among rural farmers. These findings underscore the importance of cooperatives as a key tool for rural development and SF growth.","author":[{"family":"Nowfal","given":"Shaymaa"},{"family":"Nanduri","given":"Sireesha"},{"family":"Theresa","given":"WG"},{"family":"Samhitha","given":"BK"},{"family":"Vinoth","given":"R"},{"family":"Veerapandi","given":"Ashokkumar"},{"family":"Bommisetti","given":"Ravi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.36956/rwae.v6i1.1536","URL":"https://doi.org/10.36956/rwae.v6i1.1536","source":"crossref"},{"id":"doi:10.1201/9781003239963-3","type":"article-journal","title":"Integration of Enterprises and Efficient Resource Use in Diverse Farming Systems","abstract":"The integrated farming system (IFS) is a set of interconnected, often interlocking production systems based on a few crops, animals and related subsidiary enterprises that maximize the utilization of nutrients in each system while minimizing the negative environmental impact of these enterprises. IFS approach has the potential for high productivity and resource recycling, as well as ecological soundness leading to sustainable agriculture. In this chapter, various components and elements of IFS, factors determining the implementation of IFS, advantages and ecosystem services provided by IFS, climate smart modern innovations in integrated rice-based farming system for sustainability and resilience are discussed in detail. Besides hydroponics and aquaponics systems, various important freshwater aquaculture-based IFS models, such as fish-cum-duck/chicken, fish-cum-cattle, fish-cum-rabbit, fish-cum-sheep/goat, fish-cum-sericulture, fish-cum-horticulture, fish-cum- vegetable, fish-cum-water chestnut and rice-fish farming, are discussed vividly. The IFS approach in the coastal area is a careful combination of two or more components, with a focus on minimizing competition, maximizing complementarities with the goal of improving farm income, family nutrition, and livelihood in a sustainable manner for small and marginal farmers. Integrated mangrove fishery farming system (IMFFS), fish-crab/fish-shrimp/shrimp – on-dyke horticulture system, integrated multi-trophic aquaculture (IMTA) are also covered.","author":[{"family":"Sarangi","given":"Sukanta"},{"family":"Mohanty","given":"Rajeeb"},{"family":"Munilkumar","given":"Sukham"},{"family":"Sundaray","given":"Jitendra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003239963-3","URL":"https://doi.org/10.1201/9781003239963-3","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-135-121-131","type":"article-journal","title":"INFLUENCE OF DIFFERENT ENERGY-PROTEIN RATIOS OF DIETS ON THE PRODUCTIVITY OF REPAIR HEIFERS IN DIFFERENT CLIMATIC CONDITIONS","abstract":"The paper substantiates the need to improve the energy and protein nutrition of heifers in order to increase the efficiency of their cultivation taking into account climate changes. In scientific and economic experiments on heifers, the energy-protein feed additive TEP-mix was used, with a high degree of protection against the breakdown of protein (65.25 %) and starch in the rumen. The main results of the conducted research indicate that improving the energy and protein balance in the body of heifers due to the use of TEP-mix supplements in their diets is a physiologically justified and cost-effective element of feeding technology. The use of diets with the inclusion of TEP-mix additives in their composition provides an increase in the amount of protected protein and starch in the general diet, which has a positive effect on increasing live weight gain and improving the economic efficiency of cultivation. The results prove that even in conditions of reduced feed intake due to increased outdoor temperature, providing heifers with protein and energy is a reliable way to control their productivity during critical temperature conditions for raising animals. The developed diets for feeding heifers with the inclusion of high-protein energy feed additive TEP-mix with an energy-protein ratio of 8.1:1 provided an increase in the level of non-split in the rumen, contributed to the stabilization of metabolic processes in the animal body and allowed to increase the average daily growth of heifers in the cold season by 7.7 % , and in the summer by 20.8 %. Changes in the protein diet of heifers in the direction of saturation of the diet with protein, which is digested according to the intestinal type from 28.05% to 34.83% provided better tolerance to heat stress. Moreover, with an increase in temperature to the maximum, the degree of counteraction to heat stress becomes the greatest. With a 10% increase in the normal protein level in the second group, the energy-protein ratio increased to 9.7:1, and the level of protein that is not broken down in the rumen decreased to 26.59 %. Under these conditions, the average daily weight gain of heifers in winter decreased by 3.0%, in summer – by 6.2 %. Keywords: heifers, energy-protein ratio, feed additive, live weight, air temperature.","author":[{"family":"Prusova","given":"Galyna"},{"family":"Yeletska","given":"Tatiana"},{"family":"Bachevska","given":"Yevheniia"},{"family":"Marchenko","given":"Alexander"},{"family":"Duvin","given":"Volodymyr"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-135-121-131","URL":"https://doi.org/10.32900/2312-8402-2025-135-121-131","source":"crossref"},{"id":"doi:10.1109/gpecom65896.2025.11061887","type":"article-journal","title":"Smart Grid Enabled Indoor Farming: A New Recipe for Energy Management Using Lighting Control","abstract":"Indoor farming allows for year-round food production, however, its reliance on supplementary artificial lighting significantly strains the grid by increasing energy demand, peak load, and resultant energy costs. Recent research shows that plants can tolerate interruptions in light, thus enabling control mechanisms to strategically schedule lighting as a function of time varying energy prices. These schedules are known as lighting “recipes” with a duration of 24 hours, which can be aligned with day-ahead pricing to optimally schedule lighting intensity to achieve energy cost savings and improve load flexibility. This paper proposes an optimal lighting control strategy that generates a daily lighting recipe with the objectives of reducing daily energy costs and monthly peak demand charges. Plant health considerations, such as minimum light intake and adequate dark/lighting intervals, are formulated as mathematical constraints. A model predictive control approach is used to solve for the optimal lighting recipe. Comprehensive simulations for a one-hectare greenhouse using real-world electricity prices from the Ontario system operator reveal an annual energy cost reduction of ${\\$}$ 281,000(22.6%) and a peak load reduction of 850 kW (18.4%). The results indicate the potential for indoor farming operations to become flexible resources within the smart grid paradigm.","author":[{"family":"Abbaspour","given":"Mohammadjavad"},{"family":"Shukla","given":"Mukund"},{"family":"Saxena","given":"Praveen"},{"family":"Saxena","given":"Shivam"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/gpecom65896.2025.11061887","URL":"https://doi.org/10.1109/gpecom65896.2025.11061887","source":"crossref"},{"id":"doi:10.31763/iota.v5i3.981","type":"article-journal","title":"IoT-based Smart Farming Model with Fuzzy Sugeno Approach for Agricultural Yield Optimization","abstract":"Plants require proper care to support optimal growth, one of which is through watering that suits their needs. This study aims to improve irrigation system efficiency by developing an automatic watering device based on fuzzy logic for tomato and cactus plants. The methods used include acquiring environmental data such as soil moisture, air temperature, and light intensity. The data is then processed using a fuzzy logic approach to determine the appropriate soil moisture level for each plant type. The control system utilizes linguistic variables such as “dry,” “moist,” and “wet” to represent soil moisture conditions. Fuzzy rules are established based on expert knowledge and applied in the control system to generate accurate automatic watering decisions. Test results show that the system effectively controls irrigation devices, maintains soil moisture within the optimal range, and improves water usage efficiency. Additionally, the growth and health of tomato and cactus plants significantly improved after system implementation. Thus, the fuzzy logic approach has proven to be a smart solution in supporting resource-efficient precision agriculture practices.","author":[{"family":"Andika","given":"Rizky"},{"family":"Anisah","given":"Masayu"},{"family":"Lutfi","given":"Iskandar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.31763/iota.v5i3.981","URL":"https://doi.org/10.31763/iota.v5i3.981","source":"crossref"},{"id":"doi:10.1109/icirca65293.2025.11089739","type":"article-journal","title":"Sustainable Smart System for Hydroponics Farming","abstract":"Hydroponics is a method of growing plants using a water-based nutrient solution instead of soil, enabling increased crop production even in areas with sterile soil while producing healthier crops that are less prone to pests and diseases. These systems tend to be far more sustainable because they do not contribute to top-soil degradation. Traditional plant cultivation methods struggle with maintaining precise environmental conditions leading to suboptimal growth and reduced yields. Water quality concerns pose challenges, especially in hydroponic systems. There's a need for innovative solutions integrating technology to enhance plant care and address water contamination risks. In this project our prototype detects the temperature, humidity, light intensity, soil moisture and pH level. If the temperature exceeds the optimum range the system automatically turns on coolant fan, if the light intensity falls below 50 % the system automatically turns on the LED lights, If the$\\mathbf{~ p H}$of the nutrient solution rise above the corrector solutions are automatically drawn in through pumps for correcting the$\\mathbf{p H}$. Simultaneously the values detected are displayed on LCD display and the data collected are sent and stored on the Internet of Things (IoT) webpage and application where the user can monitor the data. The system also detects plant diseases like powdery mildew, rust, leafspot using Internet Protocol (IP) webcam and suggests remedies based on their condition using Matlab software. This system is low cost and provides good results in growth, it also supports the sustainable goals, “Good health and well-being” and “Decent work and economic growth”.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icirca65293.2025.11089739","URL":"https://doi.org/10.1109/icirca65293.2025.11089739","source":"crossref"},{"id":"doi:10.1109/ciacon65473.2025.11189708","type":"article-journal","title":"Revolutionizing Smart Farming with AI, IoT, and Earth Observation for Precision Agriculture","abstract":"Agriculture is challenged to ensure a secure food future, maximize the profitability of available resources, and respond to climate change. FarmEasy responds to these challenges through Earth Observation (EO) data, Artificial Intelligence (AI) and the Internet of Things (IoT) , which enhance agricultural decision-making. The system incorporates satellite imagery with real-time soil health assessment through sensors, allowing accurate monitoring of pH, nitrogen, phosphorus, and potassium content to maximize nutrient management. A Convolutional Neural Network (CNN) powered pest detection model inspects plant photos to detect infestations, initiating automated responses like optimized irrigation control. The system also delivers a customized Farmer Information Hub via Optical Character Recognition (OCR) for effective data monitoring and farm management. Furthermore, FarmEasy facilitates pre- and post-disaster surveys by monitoring soil moisture, vegetation health, and land use patterns, feeding into early warning systems and post-event recovery planning. The cloud-enabled, mobile-compatible design of the platform enables access and scaling while providing actionable intelligence to empower farmers. In this research, the effectiveness of the system in improving agricultural productivity, minimizing resource loss, and supporting climate-resilient farming practices is analyzed, marking the beginning of future innovations in AI precision agriculture.","author":[{"family":"Bhattacharyya","given":"Atyasha"},{"family":"Sarkar","given":"Sandeep"},{"family":"Karmakar","given":"Ishaan"},{"family":"Saha","given":"Subhanjan"},{"family":"Dutta","given":"Jhalak"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ciacon65473.2025.11189708","URL":"https://doi.org/10.1109/ciacon65473.2025.11189708","source":"crossref"},{"id":"doi:10.1109/icosec67334.2025.11459746","type":"article-journal","title":"Artificial Intelligence Driven Animal Detection for Sustainable Farming","abstract":"Agriculture is the pillar of world growth, contributing notably to Gross Domestic Product (GDP), food security and national income, promoting rural development in our country. This agricultural field is now facing many global challenges such as climate change. labour shortages, water scarcity, soil degradation etc. However, one particular problematic issue is the invasion of farms by animals like buffaloes, cows, goats, birds, and even wild elephants, which can cause significant crop damage and substantial financial losses for farmers impacting food production and farmer livelihoods. and costly To keep animals off their land, farmers frequently employ traditional methods like basic fencing and manual monitoring which are ineffective, costly and labour-intensive. This paper proposes an intelligent animal identification system that makes use of IoT-enabled sensors and AI-driven image recognition for real-time monitoring and automated alerts. In order to identify and categorize animals, the system uses cameras and motion sensors, where the captured data is processed through deep learning models.. It even checks the water level in farms when it rains, helping to stop water from ruining the crops. The results indicate the success of the proposed algorithm for safe farming and pave the way for scalable smart agriculture solutions.","author":[{"family":"Vanitha","given":"V"},{"family":"Amuthameena","given":"S"},{"family":"Balamanikandan","given":"M"},{"family":"Dharaneesh","given":"G"},{"family":"Kaviyarasu","given":"V"},{"family":"Aalwa","given":"MSP"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icosec67334.2025.11459746","URL":"https://doi.org/10.1109/icosec67334.2025.11459746","source":"crossref"},{"id":"doi:10.36626/jppp.v21i1.1196","type":"article-journal","title":"Model Pendampingan Generasi Millennial Sektor Pertanian Berkelanjutan melalui Optimalisasi Pemberdayaan Asset Social Movement menghadapi Era Pertanian Cerdas Digital 4.0 (Digital Smart Farming 4.0)","abstract":"Pendampingan generasi millennial sektor pertanian berkelanjutan melalui optimalisasi pemberdayaan asset social movement menghadapi era pertanian cerdas digital 4.0 (digital smart farming 4.0) merupakan salah isu strategis saat ini. Tujuan utama penelitian : menganalisis dan membangun model pendampingan generasi millennial sektor pertanian menghadapi era pertanian cerdas digital 4.0 (digital smart farming 4.0) yang ideal. Pendekatan penelitian mengunakan multimetode triangulasi atau metode campuran dengan strategi sekuensial kuantitatif – kualitatif. Analisis data menggunakan Structural Equation Modelling (SEM) dengan software IBM AMOS. Pengujian model keseluruhan (overal/fit) dilakukan uji validitas, reliabilitas, normalitas, outlier dan analisis pengaruh. Hasil analisis pengaruh model akhir, rata-rata signifikansi 0,02 (berpengaruh) karena nilai signifikansi &lt;0,05. Kontribusi variable bebas terhadap tidak bebas dengan R square 0,924, kontribusi variable Y terhadap Z sebesar 92,4%. Penelitian dilakukan 6 bulan (Maret - Agustus 2023). Sampel penelitian adalah petani millennial usia 17-39 tahun dari 10 Kabupaten/Kota di Provinsi Jawa Tengah berjumlah 216, pengambilan sampel dengan metode purposive sampling. Hasil penelitian : Nilai rata – rata pemberdayaan asset pergerakan sosial/ social movement pada aspek kemampuan petani millennial berupa: kompetensi teknis, kompetensi manajerial, kompetensi sosial sebesar 2.77 (tidak/belum baik). Nilai rata – rata sub sistem pertanian 2.79 (tidak/belum baik). Nilai rata – rata teknologi smart farming 2.75 (tidak/ belum baik). Nilai rata – rata keberlanjutan pembangunan pertanian 2.74 masuk kategori kurang/ rendah (less sustainable). Model perbaikan pendampingan generasi millennial agar ideal dan optimal dapat dilakukan dengan : 1) peningkatan kemampuan berupa: kompetensi teknis, manajerial, sosial melalui penyuluhan, pelatihan dan memperbanyak pengalaman lapangan dalam hal pemilihan komoditas yang tepat dan penerapan manajemen standar operasional usaha yang baik; 2) sinergisitas sub sistem agribisnis dari hulu hingga hilir oleh petani millennial dan stakeholder terkait sehingga tercipta efiesiensi usaha; 3) penerapan teknologi smart farming oleh petani millennial terutama pada proses produksi, pasca panen/ pengolahan hasil dan promosi dan pemasaran; 3) peningkatan kesadaran dalam menerapkan keseimbangan ekonomi, sosial dan lingkungan dituangkan dalam Skenario business as usual (BAU) dan strategi bisnis.","author":[{"family":"Nurdayati","given":"Nurdayati"},{"family":"Sudarmanto","given":"Bambang"},{"family":"Mubarokah","given":"Wida"},{"family":"Purwono","given":"Edi"},{"family":"Makmun","given":"Lutfan"},{"family":"Akbarrizki","given":"Muzizat"}],"issued":{"date-parts":[[2025]]},"DOI":"10.36626/jppp.v21i1.1196","URL":"https://doi.org/10.36626/jppp.v21i1.1196","source":"crossref"},{"id":"doi:10.36887/2524-0455-2024-2-14","type":"article-journal","title":"Production potential of the enterprise as an economic category","abstract":"The article presents the research results substantiating the definition of “production potential of the enterprise” and identifying its constituent elements based on the study of existing scientific views. The analysis of modern literary sources demonstrated a relatively wide range of views on the essence of production potential and theoretical and methodological contradictions. It was found that many scientists interpret it as economic, resource potential, or enterprise potential. There needs to be a particular understanding of the components of production potential and the factors that affect it, which complicates the development of methods for its quantitative and qualitative assessment, analysis of use, and increase. The presence of numerous discussions of leading scientists related to the concept of potential, its structure, and classification of resources necessitated further detailed research and disclosure of the category “production potential of the enterprise”. It was found that the interpretations of the concept of “potential” given in the dictionaries reflect the diversity of approaches humanity has accumulated in interpreting and applying this term in various fields. At the same time, as a rule, there is no emphasis on the possibility and expediency of applying this or that disclosure of the essence of the concept of “potential” specifically in the economy. The following are defined as the main factors that influence the amount of production potential: availability of resources, their quality, structure and functional relationship, rational use, technology, technological process, organization of production, knowledge, and entrepreneurial abilities. It is justified that, in the most general sense, the elements of production potential include land and other natural resources, means of production (tools and objects of work), labor force, technology and organization of production, professional knowledge and abilities of management personnel and other participants in the production process, and management. It was concluded that only through the involvement of all components of the production potential does the production of products, works, and services available to consumers for use become possible. The systematic approach made it possible to give the following author’s definition of the critical economic category of the study: the production potential of an enterprise is the ability of an enterprise to carry out a production process with the maximum possible aggregate result of the use of resources of a certain quantity and quality and functional ratio in such activity based on the appropriate technology and organization of production, knowledge, and abilities of management personnel and other participants in the production process. Depending on the completeness and degree of rationality of the use of input resources and other components, we can talk about the enterprise’s fundamental (accumulated), current, and strategic (future) production potential. Keywords: potential, enterprise potential, production potential, economic potential, resource potential, resources, efficiency, management.","author":[{"family":"Krasnorutskyy","given":"Oleksiy"},{"family":"Marenych","given":"Tetiana"},{"family":"Prusova","given":"Halyna"}],"issued":{"date-parts":[[2025]]},"DOI":"10.36887/2524-0455-2024-2-14","URL":"https://doi.org/10.36887/2524-0455-2024-2-14","source":"crossref"},{"id":"doi:10.2174/9798898815462126010010","type":"article-journal","title":"Functional Framework for IOT-Based Agricultural System","abstract":"IoT is an exciting technology that offers dependable and effective solutions for modernizing numerous fields. The layers, topologies, protocols, and network architecture used in IoT-based agriculture have all been thoroughly examined. This chapter reduces the amount of manual labour required by automating the irrigation process using a range of sensors. For agricultural areas, it is advised to use a sensorbased surveillance system. It would entail gathering information on soil moisture, humidity, and temperature. It is possible to automate irrigation by monitoring each of these factors. Two technologies that are replacing conventional agricultural methods and advancing the development of smart technology are the IoT and the use of cloud computing. This ingenious gadget monitors the health of the plants. These sensors keep an eye on the following variables in the plant's immediate environment: temperature, humidity, vibration, soil wetness, solar radiation intensity, and soil quality value. Additionally, a connection has been shown between relevant technologies and IoTbased agricultural systems, such as big data storage, analytics, and remote access. Statistical data processing, data collection, and physical structure are the four essential components. The physical structure is the most important component in precise farming to avoid any undesired outcomes. The actuators, devices, and sensors are all under the control of the entire system. IoT agricultural networks employ a variety of long-term and short-range network types for communication. Several network technologies facilitate the creation of agricultural or crop monitoring instruments and sensors. Network infrastructure and applications for the IoT in agriculture are built on communication protocols. They work on the network-based exchange of all agricultural information and statistics.","author":[{"family":"Kumar","given":"VA"},{"family":"Nandalal","given":"V"},{"family":"Kumar","given":"DS"},{"family":"Babu","given":"AS"},{"family":"Mohan","given":"Abdullah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2174/9798898815462126010010","URL":"https://doi.org/10.2174/9798898815462126010010","source":"crossref"},{"id":"doi:10.62710/e874v280","type":"article-journal","title":"Determinan Tingkat Adopsi Smart Farming dan Dampaknya terhadap Produktivitas serta Keberlanjutan Usahatani Hortikultura","abstract":"The adoption of smart farming in horticulture is increasingly important for improving productivity and promoting sustainable agriculture. However, previous studies have mainly focused on the pre-adoption stage, while determinants influencing technology use after adoption remain underexplored. This study aimed to analyze the determinants of smart farming adoption at the post-adoption stage and examine its effects on farm productivity and sustainability. A quantitative explanatory design was employed using survey data from 70 horticultural farmers in West Bandung Regency, Indonesia. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results revealed that Perceived Usefulness (PU), Observability (OBS), and Image (IMG) positively and significantly influenced the level of smart farming adoption. In contrast, Perceived Ease of Use (PEOU), Relative Advantage (RA), Compatibility (COMP), and Trialability (TRI) showed no significant effects. Moreover, smart farming adoption had positive and significant effects on both farm productivity and farming sustainability. These findings indicate that, at the post-adoption stage, farmers’ actual experiences, perceived benefits, and social recognition play more important roles than the initial characteristics of the innovation. This study extends the Technology Acceptance Model (TAM) and Innovation Diffusion Theory (IDT) by demonstrating that determinants of technology adoption evolve across different stages of technology use, providing implications for policies promoting sustainable digital agriculture.","author":[{"family":"Komara","given":"Jaomal"},{"family":"Ayesha","given":"Ivonne"},{"family":"Rukhman","given":"Alghif"}],"issued":{"date-parts":[[2026]]},"DOI":"10.62710/e874v280","URL":"https://doi.org/10.62710/e874v280","source":"crossref"},{"id":"doi:10.9734/jabb/2025/v28i92893","type":"article-journal","title":"Agri-voltaics Farming System:  A Climate-smart Technology  towards Sustainability","abstract":"The synergistic combination of photovoltaic (PV) energy generation with crop cultivation on the same plot of land, known as Agri-Voltaics (AV), is a possible climate-smart solution to the dual problems of energy and food security. By 2050, it's expected that the world's food and energy needs will have increased, placing more strain on land and natural resources. To increase land-use efficiency, creative solutions like AV are needed. This dual-use system provides a number of socioeconomic, environmental, and agronomic advantages, such as increased water efficiency, better microclimates, and rural electrification. Notwithstanding the benefits, problems, including high initial costs, inconsistent crop yields in shadowed environments, and unclear regulations, still exist. With an emphasis on their role in climate resilience, sustainable development, and India's shift to a net-zero future, this analysis examines the design concepts, land equivalent ratio (LER), ongoing activities, and implementation challenges of AV systems. LER above 1 shows better land-use efficiency, typically ranging from 1.0–1.3 in mixed cropping and 1.1–1.5 in agroforestry setups. Case studies from ICAR-CAZRI indicate that crop responses to PV shading differ depending on the species and season.","author":[{"family":"Pradhan","given":"Diptesh"},{"family":"Patra","given":"Sneha"},{"family":"Ghosh","given":"Kheyali"}],"issued":{"date-parts":[[2025]]},"DOI":"10.9734/jabb/2025/v28i92893","URL":"https://doi.org/10.9734/jabb/2025/v28i92893","source":"crossref"},{"id":"doi:10.1002/9781394336364.ch7","type":"article-journal","title":"Overcoming Challenges of Data Privacy, Security, and Scalability for Commercial Grain Farming","abstract":"Climate-smart agriculture must be promoted for food security and environmental sustainability; however, its diffusion will be impeded by related data privacy, security, and scalability issues. This chapter discusses the challenges in the diffusion of data-intensive agricultural technologies: Privacy, security, and scalability issues. This chapter explores how federated learning, differential privacy, and blockchain can solve such problems. Federated learning enables a collaborative approach to train the model without transferring raw data, hence ensuring enhanced privacy and security. Differential privacy adds noise to the data to ensure privacy is well protected, and yet it preserves data utility. Blockchain provides an assured method for recording and sharing agricultural data safely and transparently. To further strengthen data protection, the need for farmer-centric data ownership policies must be highlighted. Such policies empower farmers to control their data and ensure fair compensation and privacy. International standards for agricultural data security are also necessary to safeguard sensitive information and facilitate cross-border data sharing. With these challenges in mind and the power of technology, the potential of data-driven agriculture can be unlocked to create a more sustainable future.","author":[{"family":"Venkatesh","given":"S"},{"family":"Jeevitha","given":"D"},{"family":"Senthilkumaran","given":"B"},{"family":"Sowndarya","given":"KKD"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1002/9781394336364.ch7","URL":"https://doi.org/10.1002/9781394336364.ch7","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7077-4.ch004","type":"article-journal","title":"Green Agricultural Innovation","abstract":"Combining 3D printing, Extended Reality (XR), and artificial intelligence (AI), the Green Agricultural Innovation offers a breakthrough approach to raise agricultural production and sustainability. The aim of this paper is to study the opportunities for cooperation across many technologies in the domains of resource optimization, waste reduction, and yield improvement. Potential means to improve sustainable farming operations include artificial intelligence (AI) for resource management and predictive analytics, augmented reality (XR) for immersive training and real-time simulations, and 3D printing for the production of unique agricultural goods. A quantitative and comparative research technique was used to assess the effects these technologies had on agricultural productivity and sustainability throughout a broad spectrum of farm kinds. According to the research, 3D, XR, and AI taken together provide the best sustainability and productivity increases. The study underlines the importance of combining many technical solutions to effectively achieve sustainable agriculture outcomes.","author":[{"family":"Seethalakshmi","given":"S"},{"family":"Mohan","given":"Anju"},{"family":"Marimuthu","given":"U"},{"family":"Alakumarimuthu","given":"KS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-7077-4.ch004","URL":"https://doi.org/10.4018/979-8-3373-7077-4.ch004","source":"crossref"},{"id":"doi:10.4018/979-8-3373-0154-9.ch008","type":"article-journal","title":"Centering Ground Water Scarcity","abstract":"Depletion of groundwater is a major threat to agricultural sustainability, especially in and around irrigated areas. This chapter discusses monitoring water usage, soil moisture and environmental using sensors powered by IoT and how such technologies offers real-time insights into water usage for efficient management of water. It also examines decentralized smart contracts that can promote fair water use rights and incentive farmers' conservation behaviours. Combining the adaptation of technological innovation and sustainable water management, the paper offers policy prescriptions to climate proof agriculture. With means of interdisciplinary views, practical applications and policy suggestions, this book snapshots the agro-environmental management policy and the smart irrigation systems towards the protection of water resources, and future generations of smart farming applications worldwide.","author":[{"family":"Singh","given":"Bhupinder"},{"family":"Kaunert","given":"Christian"},{"family":"Shastri","given":"Arunima"},{"family":"Chandra","given":"Saurabh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-0154-9.ch008","URL":"https://doi.org/10.4018/979-8-3373-0154-9.ch008","source":"crossref"},{"id":"doi:10.3390/engproc2025115004","type":"article-journal","title":"Artificial-Intelligence-Enhanced Virtual Sensor System for Smart Farming: Modeling Ancestral Cultivation Practices in Simulink","abstract":"This study presents a validated AI-based data acquisition system for precision agriculture, fully modeled in MATLAB/Simulink R2025a. The system integrates virtual sensors, convolutional neural networks (CNNs), and image-based root analysis to support the ancestral “Huacho Rosado” potato cultivation technique. It is structured into three layers: Environmental Data Acquisition, AI-driven processing, and agronomic Decision Support. Virtual sensors simulate soil temperature, moisture, and density, while CNN modules classify soil texture, estimate moisture, and detect root density using RGB images. The decision-support layer computes agronomic forces—bit, shear, and inertial—which are essential for soil management. Simulation results demonstrate real-time inference below 200 ms, moisture prediction errors under 5%, and root density classification accuracy of 90%. A continuous 24-h simulation confirmed the system’s stability and responsiveness. This approach provides a low-cost, scalable, and reproducible framework that bridges indigenous knowledge with modern AI tools, supporting sustainable agriculture in resource-limited environments.","author":[{"family":"Sánchez","given":"Alan"},{"family":"Proaño","given":"Pablo"},{"family":"Quinte","given":"Santiago"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/engproc2025115004","URL":"https://doi.org/10.3390/engproc2025115004","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102362","type":"article-journal","title":"Optimal design and operation of a recirculating aquaculture system integrated with hybrid solar energy: A case study of sustainable, low-cost Clarias gariepinus farming","abstract":"The high energy demand and wastewater generation associated with intensive aquaculture present significant challenges to the sustainability of fish farming systems. This study proposes an integrated recirculating aquaculture system (RAS) powered by a hybrid photovoltaic-battery energy system for African sharp-tooth catfish ( Clarias gariepinus ) farming in the Mekong Delta, Vietnam. A mass-balance-based modeling framework was developed to quantify fish growth, waste generation, oxygen consumption, carbon dioxide production, and water treatment requirements. The RAS incorporates a multi-stage filtration system comprising a solid-liquid separator, a microscreen drum filter, a trickling filter, a moving bed bioreactor, and a UV disinfection unit. To determine the optimal energy configuration, a multi-objective optimization framework based on the Non-dominated Sorting Genetic Algorithm II was implemented to simultaneously minimize the Annual Cost of the System (ACS) and CO₂ emissions. The results demonstrated that the proposed filtration system achieved an 88% reduction in total ammonia nitrogen, ensuring suitable water quality for intensive catfish production. Among the investigated configurations, the grid-connected PV-battery system (Scenario S3) was identified as the optimal solution, achieving an ACS of approximately 900 USD/year and CO₂ emissions of only 0.21 tCO₂/year while maintaining reliable 24-hour operation. The optimal system exhibited a life-cycle cost of 11,659 USD, generated annual economic benefits of 1,716 USD, and achieved a benefit-cost ratio of 1.622. Economic assessment further revealed a payback period of 9.4 years, a net present value of 6,826 USD, and an internal rate of return of 13%, confirming the project's long-term financial viability. Sensitivity analysis demonstrated that the optimized configuration remained robust under variations in PV tilt angle, PV capacity, and battery capacity. These findings demonstrate that integrating advanced RAS technology with hybrid solar energy and multi-objective optimization provides a technically feasible, economically viable, and environmentally sustainable solution for small-scale aquaculture, contributing to the development of low-carbon food–energy–water nexus systems.","author":[{"family":"Nguyen","given":"Nhut"},{"family":"Vo","given":"Linh"},{"family":"Vo","given":"Tran"},{"family":"Matsuhashi","given":"Ryuji"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102362","URL":"https://doi.org/10.1016/j.atech.2026.102362","source":"crossref"},{"id":"doi:10.1201/9781003536932-7","type":"article-journal","title":"Crop Disease Detection and Prevention Using Artificial Intelligence","abstract":"Crop diseases pose a significant challenge to global agriculture, causing substantial losses in yield and quality. They impact food security, necessitating innovative solutions for timely detection and prevention. This paper explores how Artificial Intelligence (AI) is transforming crop disease detection and prevention, emphasizing the role of precision farming techniques in improving agricultural sustainability. Advanced AI technologies such as machine learning (ML), deep learning (DL), and computer vision are used in the domain of disease detection. These technologies, combined with data sources like drone-based imaging and IoT sensors, are evaluated for their effectiveness in identifying crop diseases. Recent studies have highlighted AI’s ability to significantly improve the accuracy of disease detection. Innovations such as convolutional neural networks (CNNs) and reinforcement learning have shown promise in identifying diseases early and automating disease management practices. Transfer learning models have enhanced prediction capabilities while reducing the dependency on large datasets. AI advancements offer the potential to revolutionize crop disease management, making detection faster, more precise, and more accessible. These innovations are expected to lead to a more sustainable and disease-free agricultural future.","author":[{"family":"Kumari","given":"Karishma"},{"family":"Bhalekar","given":"Dattatray"},{"family":"Chappa","given":"Srinivas"},{"family":"Kumar","given":"Pradeep"},{"family":"Bhattarai","given":"Ruchita"},{"family":"Nagineni","given":"Prasad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003536932-7","URL":"https://doi.org/10.1201/9781003536932-7","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.102230","type":"article-journal","title":"A multi-scale inventory for sustainable olive farming using remote sensing and data fusion","abstract":"The olive grove exhibits high spatial heterogeneity at the intra-parcel scale, associated with structural and physiological differences as well as local environmental conditions, even within the same farm. However, management practices are usually applied uniformly at the parcel scale, without accounting for this variability, which limits resource-use efficiency and compromises the sustainability of the production system. The main contribution of this work is the development of a multisensor inventory oriented toward sustainability analysis, in which the individual olive tree constitutes the minimum unit of study. To this end, a methodology based on data acquired from UAV platforms is proposed, integrating structural, physiological, and contextual information into a multidimensional inventory. Based on this inventory, potential incomes and management costs are estimated in a relative manner using reference values weighted according to the observed characteristics of each individual tree. This approach enables intra-parcel sustainability analysis and provides an objective decision-support basis for site-specific olive grove management, through a relative assessment based on the redistribution of mean income and cost values according to the individual behavior of each olive tree.","author":[{"family":"Latorre-Hortelano","given":"Pablo"},{"family":"Jurado-Rodríguez","given":"David"},{"family":"Garrido-Almonacid","given":"Antonio"},{"family":"Parras-Rosa","given":"Manuel"},{"family":"Jurado","given":"Juan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.102230","URL":"https://doi.org/10.1016/j.atech.2026.102230","source":"crossref"},{"id":"doi:10.1007/s44163-026-01990-x","type":"article-journal","title":"Review of machine learning and blockchain integration for crop monitoring and management in smart farming","abstract":"Agriculture is an essential pillar of global food security, economic development and employment. However, this sector is facing major challenges such as population growth, soil degradation, water stress, climate hazards, and dependence on chemical inputs, which directly affect productivity, crop quality and the sustainability of natural resources. In this context, the integration of digital technologies and smart solutions appears as an essential step to modernize agricultural systems and strengthen their resilience. This review paper analyzes the role of Machine Learning (ML) and Blockchain as complementary technologies contributing to the transformation of traditional agriculture into smart, connected and secure systems. The study is based on a qualitative analysis of more than 127 recent scientific publications selected according to the PRISMA methodology, and from recognized databases such as ScienceDirect, Springer, IEEE Xplore, MDPI and other academic reference sources. The results show that ML is widely used for key applications such as yield prediction, early detection of crop diseases, irrigation optimization and agricultural input management. These applications are based on different learning paradigms, including supervised, unsupervised and reinforcement learning, capable of exploiting heterogeneous and dynamic agricultural data. Moreover, the blockchain plays a fundamental role in securing, tracing, and making agricultural data transparent. It ensures the integrity of information, while facilitating integration with IoT systems and smart contracts to strengthen trust between producers, distributors and consumers, and to promote more sustainable and equitable agricultural supply chains. This research also highlights the combined benefits of these technologies, including improved resource efficiency, increased productivity and support for sustainable agriculture. However, several limitations persist, notably the quality and availability of data, scalability issues, energy costs of blockchain infrastructures and the complexity of their integration into real agricultural environments. Finally, this study identifies the main research gaps and highlights the need to develop hybrid, robust and integrated solutions combining ML and Blockchain. This critical synthesis provides a conceptual and practical framework to guide future research towards smart, resilient and sustainable agricultural systems capable of addressing global food security and natural resource conservation issues.","author":[{"family":"Morchid","given":"Abdennabi"},{"family":"Kabbaj","given":"Mohammed"},{"family":"Benbrahim","given":"Mohammed"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s44163-026-01990-x","URL":"https://doi.org/10.1007/s44163-026-01990-x","source":"crossref"},{"id":"doi:10.1109/icmlc66258.2025.11280169","type":"article-journal","title":"Smart Surveillance for Swiftlet Farming: IoT-Driven Real-Time Pest Detection with YOLOv10","abstract":"Pest disturbances in swiftlet houses reduce edible bird's nest (EBN) production, a valuable commodity in Southeast Asia. Manual pest monitoring is often inefficient and disruptive to the sensitive environments of birds. However, to the best of our knowledge, no study has incorporated computer vision technology and the IoT for smart surveillance in swiftlet farming. To address this gap, we propose a YOLOv10-based detection system to identify small pests in real time under low-light conditions. The proposed system features a Python-based UI, a Region of Interest (ROI) function to improve detection focus, and IoT integration via a Telegram Bot that sends image-based alerts upon detection. The infrared CCTV cameras captured 2,011 images, which were augmented through rotation, resulting in 3,992 images. Six YOLOv10 model variants (n, s, m, b, l, and x) were evaluated. Based on our experimental results, the 'b' variant exhibited the best performance, with an mAP50 of 0.9936 and the lowest latency. Evaluation using a 50-minute video demonstrated accurate and rapid pest identification with cockroaches as the main pests. The experimental study showed the effectiveness of the system in monitoring swiftlet farming while reducing environmental disturbance to birds.","author":[{"family":"Ginting","given":"Depi"},{"family":"Saddami","given":"Khairun"},{"family":"Adriman","given":"Ramzi"},{"family":"Kurnianingsih"},{"family":"Wibirama","given":"Sunu"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icmlc66258.2025.11280169","URL":"https://doi.org/10.1109/icmlc66258.2025.11280169","source":"crossref"},{"id":"doi:10.1109/iccr67607.2025.11371766","type":"article-journal","title":"An AIoT-Integrated Robotic System for Smart Mushroom Farming: Automated Injection of Bacillus subtilis","abstract":"This research aims to design and develop an automated Bacillus subtilis injection system for inhibiting fungal growth in mushroom cultivation bags. The prototype system is intended to support the mushroom farming industry and serve as a practical solution for agricultural communities. A common issue among mushroom growers is fungal contamination within the cultivation blocks, which significantly affects yield and quality. Interviews with local farmers revealed that many currently use a mixture of Bacillus subtilis and water, manually spraying it onto the mushroom bags to suppress fungal infections. However, this method is often labor-intensive and insufficient in ensuring complete fungal suppression throughout the cultivation substrate. To address this issue, the research team developed a robotic prototype that automates injection using image processing and motion-control technologies. The system features a Cartesian robot equipped with stepper motors for three-axis movement along V-Slot aluminum profiles, allowing for precise navigation. A camera mounted at the injection head captures real-time images of the substrate surface. These images are analyzed using the OpenCV library in Python, enabling accurate detection of injection points through digital image processing. The mechanical structure and materials were selected based on engineering design principles and material selection criteria, ensuring durability and functionality. The automated system successfully injected Bacillus subtilis at targeted locations, achieving a success rate of 89.68%, which demonstrates high accuracy and repeatability. This prototype offers a promising alternative to manual labor, enhances precision in fungal control, and contributes to broader advances in smart agriculture through AIoT integration.","author":[{"family":"Korbuakaew","given":"Grerkiat"},{"family":"Yamada","given":"Kou"},{"family":"Vongvit","given":"Rattawut"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/iccr67607.2025.11371766","URL":"https://doi.org/10.1109/iccr67607.2025.11371766","source":"crossref"},{"id":"doi:10.36948/ijfmr.2026.v08i01.62722","type":"article-journal","title":"AI-Powered Smart Farming Advisor for Precision Agriculture &amp; Sustainable Crop Management","abstract":"Agricultural productivity is critical for both global food security and economic stability. However, traditional farming techniques often restrict both yield and long-term sustainability. We introduce Smart AgroAssist, an intelligent decision support tool that unifies crop suggestions, disease identification, and agricultural information delivery. This platform utilizes machine learning and computer vision to process soil, climate, and plant health data for optimum crop selection and disease diagnosis via leaf imagery. It also features an NLP-powered module to provide farmers with the latest government schemes and farm-related news. Our findings confirm enhanced disease detection accuracy and better yield forecasts, which promotes smart and environmentally responsible agriculture.","author":[{"family":"Yadav","given":"Khushi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.36948/ijfmr.2026.v08i01.62722","URL":"https://doi.org/10.36948/ijfmr.2026.v08i01.62722","source":"crossref"},{"id":"doi:10.1109/imcet69180.2026.11503742","type":"article-journal","title":"Dynamic Task Reallocation in UAV-Assisted LoRaWAN Networks for Smart Farming","abstract":"Smart farming increasingly relies on wireless sensor networks for environmental monitoring; however, collecting data from distributed sensors remains challenging in large rural fields where fixed gateways are infeasible. This paper proposes CRAFT (Cooperative Relay-Aware Flight Tasking), a decentralized dynamic task reallocation framework for multi-UAV LoRaWAN-based data muling. CRAFT partitions the monitored area into relay-assisted zones and enables unmanned aerial vehicles (UAVs) to cooperatively and adaptively reassign sensing tasks during flight based on workload disparity and received signal strength indication (RSSI). A model-based performance evaluation, derived from analytical mobility and communication assumptions, indicates that CRAFT reduces mission completion time by approximately 23%, significantly improves energy balance across UAVs, and maintains high packet delivery reliability compared to static partitioning and greedy reassignment baselines. These results highlight the potential of lightweight cooperative control for scalable and energy-efficient UAV-assisted LoRaWAN networks in smart farming applications.","author":[{"family":"Sindian","given":"Samar"},{"family":"Jawhar","given":"Imad"},{"family":"Kadery","given":"Mohammad"},{"family":"Hachem","given":"Hussein"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/imcet69180.2026.11503742","URL":"https://doi.org/10.1109/imcet69180.2026.11503742","source":"crossref"},{"id":"doi:10.65521/ijacect.v14i1.568","type":"article-journal","title":"Smart-Agri Advisor: Optimizing Sustainable Farming Decisions","abstract":"Today, farming needs to be smart and eco-friendly to keep up with the growing demand for food. This paper talks about a system called \"Smart-Agri Advisor\" that helps farmers choose the best crops to grow. It does this by checking real-time information about the environment, soil, and market trends. The system looks at things like soil quality, temperature, humidity, rainfall, and what crops are in demand in the market. This helps farmers make better and smarter decisions. It also uses IoT sensors to automatically water the crops, use resources wisely, and make farming more eco-friendly. This study focuses on how well the Smart-Agri Advisor can improve farming and help farmers grow the right crops that people actually need. Let me know if you'd like to turn it into a presentation slide or summary too","author":[{"family":"Sase","given":"Vedant"},{"family":"Patil","given":"Prasad"},{"family":"Gangurde","given":"Sunny"},{"family":"Chaudhari","given":"Somesh"},{"family":"Mali","given":"Asmeeta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.65521/ijacect.v14i1.568","URL":"https://doi.org/10.65521/ijacect.v14i1.568","source":"crossref"},{"id":"doi:10.1007/s00216-026-06726-5","type":"article-journal","title":"Advances in electrochemical sensors for smart farming and precision agriculture: a focus on phytohormone quantification","abstract":"Electrochemical sensors detect target molecules using biorecognition elements, such as antibodies or molecularly imprinted polymers (MIPs), or the target's inherent electrocatalytic activity, with a transducer converting the resulting interaction into a measurable electrical signal. In agriculture, they are gaining importance for optimizing plant growth, crop quality, safety, and overall productivity. Healthy plants are vital globally as they ensure food security, support ecosystems, produce oxygen, protect soil, and sustain human life and environmental balance worldwide. Phytohormones are naturally occurring signaling molecules produced by plants that regulate growth, defense, responses to environmental stimuli and adaptation processes. Hence, fluctuations in phytohormone levels serve as early biochemical indicators of stress, often before visible signs appear. Major phytohormones involved in stress responses include abscisic acid (ABA), ethylene, methyl jasmonate (MeJA), salicylic acid (SA), indole-3-acetic acid (IAA), and cytokinins (CKs). Quantifying these phytohormones provides the early detection of abiotic and biotic stresses such as drought, nutrient imbalance, salinity, and pathogen attack. This early diagnosis supports timely intervention, improves crop management, and enhances agricultural productivity. Electrochemical sensors allow for rapid, sensitive, and sometimes real-time detection, even in field conditions. Their portability and compatibility with digital technologies make them promising tools for precision agriculture. However, challenges remain, such as ensuring durability in harsh environments, reducing device costs, and enabling detection of multiple targets simultaneously. Overall, electrochemical biosensors represent a powerful innovation in modern agriculture. With continued development and integration into smart farming systems, they are expected to play a crucial role in sustainable and efficient agricultural practices.","author":[{"family":"Zang","given":"Mingli"},{"family":"Wang","given":"Xiaodong"},{"family":"Chen","given":"Yunling"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s00216-026-06726-5","URL":"https://doi.org/10.1007/s00216-026-06726-5","source":"crossref"},{"id":"doi:10.35335/na9y0b02","type":"article-journal","title":"Unsupervised Machine Learning Based DSS for Land Profiling and Disease Risk Mitigation in Smart Farming","abstract":"Decision Support Systems (DSS) in smart farming require methodologies capable of representing the holistic complexity of agricultural ecosystems. This study proposes a DSS framework based on unsupervised machine learning, specifically K-Means clustering, to automatically segment land profiles using IoT sensor records. The dataset consists of 500 global sensor data points covering seven essential environmental variables: soil moisture, pH, temperature, rainfall, humidity, sunlight duration, and the NDVI index. Through Principal Component Analysis (PCA) for dimensionality reduction and Silhouette Score evaluation, the system successfully identified and mapped seven land profiles with distinct microclimatic characteristics. Cross-tabulation analysis further demonstrates the principal novelty of this DSS, namely its ability to classify land into \"Safe Zones\" (Clusters 0, 3, and 4), which are characterized by Mild disease status and are suitable for Soybean, Cotton, and Maize, as well as \"High-Risk Zones\" (Clusters 1, 2, 5, and 6), which consistently correspond to Severe disease status. These findings indicate that a DSS based on environmental clustering is substantially more effective for crop selection recommendations and disease prevention than conventional predictive approaches. Ultimately, this framework provides farmers with actionable insights to optimize productivity and minimize agricultural risk","author":[{"family":"Wati","given":"Embun"},{"family":"Sunita","given":"Elvi"},{"family":"Kuswanto","given":"Andi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35335/na9y0b02","URL":"https://doi.org/10.35335/na9y0b02","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101215","type":"article-journal","title":"Application of non-invasive monitoring technology in intensive sheep farming: A review","abstract":"Under the intensive sheep farming model, traditional monitoring and management methods face issues such as outdated equipment and low efficiency, which cannot fully meet the requirements for refined and intelligent management in breeding. This paper reviews the application of non-invasive monitoring technology in intensive sheep farms, analyzing the differences and application scenarios between contact and non-contact sensors. The results show that contact sensors have advantages such as relatively precise, continuous, and accurate monitoring of individual animals with minimal stress responses during use. However, they also have drawbacks, including wear and tear caused by stress and high equipment maintenance costs. Non-contact sensors, on the other hand, offer advantages such as scalability for group use, high accuracy, non-interference with sheep behavior, and no disruption of flock habits. Non-invasive monitoring technology demonstrates good accuracy and applicability in individual identification, behavior analysis, body measurement parameters, and physiological indicators. In the future, through in-depth integration of multidisciplinary and multi-field approaches and deep learning of multiple algorithms, non-invasive monitoring technology is expected to develop towards low cost and intelligence, providing a comprehensive solution for smart animal husbandry.","author":[{"family":"Liang","given":"Jinxin"},{"family":"Yuan","given":"Zhiyu"},{"family":"Luo","given":"Xinhui"},{"family":"Qu","given":"Jianrui"},{"family":"Qi","given":"Yu"},{"family":"Wang","given":"Chunxin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101215","URL":"https://doi.org/10.1016/j.atech.2025.101215","source":"crossref"},{"id":"doi:10.47134/converse.v1i4.3855","type":"article-journal","title":"Komunikasi Digital dalam Pemberdayaan Kelompok Wanita Tani (KWT) melalui Teknologi Smart Farming","abstract":"Penelitian ini bertujuan untuk menganalisis peran komunikasi digital dalam pemberdayaan Kelompok Wanita Tani (KWT) melalui teknologi smart farming. Dengan menggunakan pendekatan kualitatif dan metode studi literatur, penelitian ini mengacu pada Teori Difusi Inovasi Rogers untuk memahami proses adopsi teknologi oleh KWT. Hasil penelitian menunjukkan bahwa adopsi smart farming mengikuti lima tahap utama: pengetahuan, persuasi, keputusan, implementasi, dan konfirmasi. Komunikasi digital memainkan peran penting dalam setiap tahap, mulai dari peningkatan pemahaman hingga evaluasi teknologi. Faktor utama yang mempengaruhi adopsi meliputi kemudahan penggunaan, manfaat yang dirasakan, dan bukti hasil yang jelas. Keberhasilan implementasi didukung oleh pelatihan digital yang berkelanjutan dan akses kepada dukungan teknis. Umpan balik pada tahap konfirmasi semakin memperkuat keberlanjutan penggunaan teknologi. Penelitian ini memberikan wawasan tentang pentingnya komunikasi digital dalam memfasilitasi adopsi teknologi Smart Farming di kalangan KWT.","author":[{"family":"Purwanto","given":"Eko"},{"family":"Rahmah","given":"Ade"},{"family":"Rohmatunisa","given":"Raden"},{"family":"Farisal","given":"Umar"},{"family":"Oktarina","given":"Selly"}],"issued":{"date-parts":[[2025]]},"DOI":"10.47134/converse.v1i4.3855","URL":"https://doi.org/10.47134/converse.v1i4.3855","source":"crossref"},{"id":"doi:10.4314/jobasr.v3i2.8","type":"article-journal","title":"Internet of things-based smart fish farming: Application of smart sensors and computer vision to provide real-time monitoring and diagnosis in aquaculture","abstract":"ABSTRACT The frequent occurrence of disease outbreaks in fish farming presents a significant challenge, leading to substantial economic losses and threatening food security, thus hindering the progress toward sustainable development goals (SDGs). In aquaculture, disease prevention relies on early detection of changes in water quality, abnormal fish behavior, and physical deformities, tasks typically handled by skilled fisheries experts, who are in short supply in Nigeria. Traditional manual disease detection methods are often costly and unreliable. This study proposes a computer vision-based solution utilizing Faster Region-based Convolutional Neural Network (FasterR-CNN) with Detectron2 for improved disease detection in fish farming. A dataset of 500 images was collected, pre-processed, and divided into training (70%), validation (15%), and testing (15%) sets. Three Faster R-CNN models (X101, R100, and R50) were trained and evaluated, with the X101 model achieving the highest accuracy of 98%. The results underscore the potential of deep learning techniques for accurate and efficient disease detection, offering a scalable solution to enhance fish health management. This approach provides a reliable and cost-effective alternative to traditional methods, contributing to the sustainability and growth of the aquaculture industry while addressing the need for timely interventions in fish disease control.","author":[{"family":"Ilyasu","given":"Umar"},{"family":"Sani","given":"Zaharaddeen"},{"family":"Suleiman","given":"Tasiu"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4314/jobasr.v3i2.8","URL":"https://doi.org/10.4314/jobasr.v3i2.8","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101376","type":"article-journal","title":"Digital and Industry 4.0 technologies in olive farming and industry: Recent applications and future outlook","abstract":"Vital to the economy, culture and landscape of many regions around the world, the olive sector faces significant challenges, including rising production costs, labour shortages, climate change impacts, water scarcity, quality control issues and market demands for transparency and authenticity. Digital and other Industry 4.0 technologies offer transformative potential to address these pressures. This article provides a comprehensive review of recent applications and future prospects of technologies such as the Internet of Things, Artificial Intelligence, Machine Learning, Robotics and Automation, Big Data Analytics, Advanced Sensing, Remote Sensing, Nanotechnology and Blockchain across the olive value chain, from cultivation to supply chain management. Using a literature review methodology to identify key application areas, it synthesises evidence on how these innovations increase resource efficiency, optimise farm management, automate labour-intensive tasks, improve pest and disease control, ensure product quality and authenticity, facilitate traceability and add value through by-product valorisation. Key benefits include improved yields, reduced environmental impact, enhanced quality control, fraud deterrence and increased consumer confidence. Future prospects include deeper integration of technologies, more sophisticated AI-driven decision support, advanced robotics, widespread adoption of rapid sensing techniques, development of circular economy models and nanotechnology applications, while recognising the need for safety assessments. Overcoming barriers related to cost, digital literacy, data interoperability and equitable access, especially for smallholder farmers, is critical. This review highlights the strategic importance of embracing digital transformation to strengthen the resilience, sustainability and competitiveness of the global olive industry.","author":[{"family":"Parra-López","given":"Carlos"},{"family":"Abdallah","given":"Saker"},{"family":"Hassoun","given":"Abdo"},{"family":"Jagtap","given":"Sandeep"},{"family":"Garcia-Garcia","given":"Guillermo"},{"family":"Hassen","given":"Tarek"},{"family":"Trollman","given":"Hana"},{"family":"Trollman","given":"Frank"},{"family":"Carmona-Torres","given":"Carmen"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101376","URL":"https://doi.org/10.1016/j.atech.2025.101376","source":"crossref"},{"id":"doi:10.55627/jhd.003.02.1494","type":"article-journal","title":"Food Security in Hyderabad: Water Governance, Climate-Smart Farming, and Sustainable Agriculture","abstract":"This paper investigates the critical paradigms of food security in the Hyderabad division, focusing on the intertwined issues of water governance, climate-smart farming practices, and sustainable agriculture. To undertake this research, a mixed-methods approach, combining quantitative and qualitative tools to capture detailed insights into the region's agricultural and water management challenges was adopted. Data were gathered using a blend of surveys, interviews, and Focus Group Discussions (FGDs). Surveys, predominantly composed of close-ended questions, provided structured data, while interviews employed open-ended questions to obtain in-depth responses. The study’s sample population was drawn from four districts within the Hyderabad division—Badin, Thatta, Dadu, and Matiari—ensuring diversity in terms of gender and age demographics. The research found out that climate change is impacting the overall agriculture system. The study identifies food insecurity as a critical issue in Hyderabad Division, closely tied to inadequate agricultural productivity. Water scarcity emerges as the primary driver of crop failures, financial distress, and demotivation among small farmers. The findings affirm that food security cannot be achieved without securing reliable water access for cultivation. Consequently, policy reforms must prioritize efficient water governance and food waste reduction and adoption to smart farming technology to enhance agricultural resilience.","author":[{"family":"Mahesar","given":"Shuja"},{"family":"Channa","given":"Abdul"},{"family":"Hussain","given":"Aajiz"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55627/jhd.003.02.1494","URL":"https://doi.org/10.55627/jhd.003.02.1494","source":"crossref"},{"id":"doi:10.1007/s42452-026-08597-y","type":"article-journal","title":"A multilingual smart farming system for real time agricultural decisions using machine learning","abstract":"Despite being the backbone of the global economy, farmers have always struggled with challenges like what crop to plant, how much fertilizer to use, and how to detect the disease beforehand. These problems affect farmers and lead to various concerns, such as food safety, which will greatly impact sustainable agriculture practices. The old farming methods depend on emotion, intuition, feeling, and experience, reducing yield production and economic losses. This paper proposes a machine-learning-based Smart Farming and Advisory System (SFAS) to overcome the challenges. The proposed model helps farmers by providing real-time crop suggestions based on soil, climate, and market conditions. It also uses soil nutrient composition to provide custom-made fertilizer recommendations and uses the Deep Learning (DL) method to detect plant diseases by processing images. Additionally, the proposed system works on multi-language support, which enables farmers of diverse linguistic backgrounds to access agricultural insights in their native languages. This research seeks to bridge the knowledge gap in agriculture using Machine Learning (ML), the Internet of Things (IoT), and multilingual accessibility to make farmers self-reliant through data-driven decision-making and sustainable agriculture practices. The experimental results show that the proposed technique outperformed baseline ML techniques on considered performance matrices, such as accuracy, sensitivity, specificity, etc.","author":[{"family":"Singh","given":"Satveer"},{"family":"Dureja","given":"Honisha"},{"family":"Singh","given":"Rohit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s42452-026-08597-y","URL":"https://doi.org/10.1007/s42452-026-08597-y","source":"crossref"},{"id":"doi:10.51200/jsffs.v2i1.6603","type":"article-journal","title":"Short-term amelioration of acidic subsoil using dairy farm effluent compost and humic acid: a laboratory incubation study","abstract":"Acidic subsoils pose a significant challenge to sustainable agriculture production due to poor nutrient availability and limited productivity, particularly in regions like Malaysia with tropical climates. This incubation study explored the potential of dairy farm effluent compost (DFEC) and humic acid (HA) as organic amendments to ameliorate acidic subsoil, focusing on improving soil chemical properties while reducing fertilizer use. The experiment evaluated five treatments with varying combinations of DFEC, HA, and reduced fertilizer rates (50% and 75%) under controlled laboratory conditions. Soil samples were analysed for pH, organic matter (OM), macronutrient (N, P, K, Ca, Mg) and other selected elements (Al, Fe, Na, Cu, and Zn) concentrations across a 90-day period. The results revealed that while soil pH showed insignificant changes, treatments with DFEC and HA significantly enhanced soil OM and macronutrient levels, particularly N, P, K, and Ca. Treatment 4 (DFEC + HA with 50% fertilizer reduction) was identified as the better combination, demonstrating the best improvements in subsoil nutrient content. Sodium (Na) levels initially increased in DFEC-treated soils but declined over time, possibly driven by decomposition and adsorption processes. Micronutrient dynamics varied, with Al and Fe exhibiting fluctuating trends influenced by soil pH and redox reactions. Trace metals such as Cu and Zn were minimally affected, with Cu concentrations declined possibly due to immobilization processes. In general, study suggest possible long-term benefits of DFEC and HA in promoting nutrient retention, and organic matter enrichment. It provides insights into soil amendment strategies for subsoil rejuvenation, contributing to sustainable agricultural practices in tropical regions. Further research, including pot and field trials, is needed to evaluate the long-term effects and mechanisms in the presence of crops.","author":[{"family":"Juilih","given":"Lesley"},{"family":"Hasbullah","given":"Nur"},{"family":"Phin","given":"Chong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.51200/jsffs.v2i1.6603","URL":"https://doi.org/10.51200/jsffs.v2i1.6603","source":"crossref"},{"id":"doi:10.71443/9789349552364-02","type":"article-journal","title":"Machine Learning Techniques for Soil Health Assessment and Crop Suitability Prediction","abstract":"The dynamic interplay between soil health and agricultural productivity is heavily influenced by various environmental and management factors, with soil properties undergoing temporal fluctuations that impact crop growth, nutrient availability, and overall sustainability. This chapter explores the integration of machine learning (ML) techniques in the assessment of soil health, focusing on the temporal dynamics of soil properties and their implications for crop suitability prediction. Advances in data-driven approaches, including time-series forecasting and remote sensing, offer significant improvements in understanding soil nutrient fluctuations, moisture variations, and microbial activity over time. By coupling climate, soil, and crop data, this work presents a holistic approach to predictive modeling, enabling more efficient and adaptive agricultural practices. The chapter highlights the importance of integrating spatio-temporal data with ML algorithms to forecast soil health trends, optimize resource management, and enhance drought resilience. Despite the challenges in data integration and model accuracy, the potential for ML to revolutionize soil health monitoring and decision-making in precision agriculture remains immense. Ultimately, this chapter aims to provide insights into future research directions and the application of AI-driven frameworks in achieving sustainable, data-informed soil and crop management strategies.","author":[{"family":"Mahalakshmi","given":"P"},{"family":"Usha","given":"P"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-02","URL":"https://doi.org/10.71443/9789349552364-02","source":"crossref"},{"id":"doi:10.1201/9781779640932-15","type":"article-journal","title":"Augmented and Virtual Realities and DataDriven Mobile Apps as Panacea for Sustainable Agriculture","abstract":"Over the past 60 years, there have been many changes to the agriculture marketing system due to an increase in marketed surplus, a rise in rapid urbanization and levels of income, changes in the matrix of demand for marketing services, and a boost in connections with distant and international markets. Either e-Agriculture or e-Agribusiness refers to the use of information and communication technologies in the agricultural industry. Small-scale farmers can use ICT to find a variety of consumers for producers willing to pay a higher price. Market distortions can be reduced by using a mobile application that gives farmers price information. Because of fields of research including Precision Agriculture, Smart Agriculture, and Agriculture 4.0, which have boosted food supply in a sustainable way, the agricultural sector has profited from computer technology. Therefore, researchers and experts in virtual reality and augmented reality can decide to focus on the agriculture sector. For the benefit of farmers, the government and numerous businesses are investing in agricultural marketing solutions. In the upcoming years, digital agricultural marketing will be essential to doubling farmer output and tripling farmers’ income.","author":[{"family":"Sadiq","given":"MS"},{"family":"Singh","given":"IP"},{"family":"Ahmad","given":"MM"},{"family":"Babawachiko","given":"M"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781779640932-15","URL":"https://doi.org/10.1201/9781779640932-15","source":"crossref"},{"id":"doi:10.1109/ifeec65025.2025.11301524","type":"article-journal","title":"Wireless Power Transfer Receiver Side Charging Regulator with Synchronous Buck Converter for Smart Farming Robot","abstract":"The Modern era has changed conventional farming into smart farming that uses various robots for monitoring or doing mechanical jobs. To support the autonomous function of the robot, a method of battery charging that is fully autonomous is required. The wireless charging method or wireless power transfer (WPT) can be applied to overcome this problem. Li-Po batteries are often used in robots and need a charging system that is fast, safe, and protects the battery’s life. This study proposes a synchronous buck converter used as the WPT receiver side for a battery charging controller using the constant current-constant voltage (CC-CV) method. A digital proportional integrator (PI) controller was implemented to regulate the charging process, maintaining a constant current of 3 A in CC mode and a 12 V constant voltage in CV mode. The converter has successfully developed and achieved 91.8% maximum efficiency under the CC mode. It has also successfully charged a 3-cell, 5000 mAh Li-Po battery within 1 hour, achieving an average efficiency of 85%.","author":[{"family":"Geovan","given":"Gervasius"},{"family":"Tampubolon","given":"Marojahan"},{"family":"Sudhartio","given":"Aryadharma"},{"family":"Muharom","given":"Ahmad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ifeec65025.2025.11301524","URL":"https://doi.org/10.1109/ifeec65025.2025.11301524","source":"crossref"},{"id":"doi:10.65138/ijris.2025.v3i12.238","type":"article-journal","title":"IoT and AI Integration for Climate‑Smart Farming: A Predictive and Adaptive System for Smallholder Farmers","abstract":"Climate variability increasingly threatens the stability and productivity of smallholder farming systems. Traditional decision-making approaches cannot reliably address rapid shifts in rainfall, soil moisture, pest pressure, and crop stress. This research presents an integrated Internet of Things (IoT) and Artificial Intelligence (AI) based climate-smart farming system that continuously monitors environmental conditions, predicts crop responses, and generates adaptive management recommendations. IoT nodes collect soil moisture, temperature, humidity, rainfall, and nutrient-level data and transmit them to a cloud-based analytics engine. Machine learning models including Random Forest for irrigation prediction, Long Short-Term Memory (LSTM) networks for yield forecasting, and Gradient Boosting for disease-risk estimation form the predictive core of the system. A rule-based adaptive module converts model outputs into actionable recommendations. Experiments using 11,200 sensor-hours, 240 field observations, and 90 climate reports demonstrate irrigation prediction accuracy of 96.2%, disease-risk detection accuracy of 93.7%, and a yield-prediction RMSE of 0.18. Field deployment results indicate 27% water savings and 12-18% productivity gains. The findings show that combining IoT sensing with AI-driven analytics significantly enhances decision-making, reduces resource waste, and supports climate-smart agriculture for smallholder farmers.","author":[{"family":"Mahto","given":"Bindeshwar"},{"family":"Rana","given":"Rohit"},{"family":"Kumar","given":"Niraj"},{"family":"Kumar","given":"Mithun"},{"family":"Das","given":"Ankita"},{"family":"Mayank","given":"Kumar"},{"family":"Mahto","given":"Mithlesh"},{"family":"Mahto","given":"Sanjay"}],"issued":{"date-parts":[[2025]]},"DOI":"10.65138/ijris.2025.v3i12.238","URL":"https://doi.org/10.65138/ijris.2025.v3i12.238","source":"crossref"},{"id":"doi:10.48175/ijarsct-28624","type":"article-journal","title":"A Multimodal AI-Powered Smart Assistant for Arecanut and Black Pepper Farming with Integrated IoT and Vision-Based Disease Diagnosis","abstract":"In this research, we present AgroAssist+, an intelligent mobile-first system tailored for arecanut and black pepper farmers. The system integrates voice-based assistance in Kannada, computer vision for early crop disease detection, and IoT-based real-time environmental monitoring. This research aims to bridge the technological gap in rural agricultural practices by providing an affordable, scalable, and easy-to-use AI-powered solution. Through a combination of convolutional neural networks (CNNs), speech recognition, and IoT sensor data, AgroAssist+ empowers farmers with timely insights – enhancing yield, reducing crop loss, and promoting sustainable practices.","author":[{"family":"Venkatesh","given":"Mrs"}],"issued":{"date-parts":[[2025]]},"DOI":"10.48175/ijarsct-28624","URL":"https://doi.org/10.48175/ijarsct-28624","source":"crossref"},{"id":"doi:10.31893/multiscience.2025418","type":"article-journal","title":"Design and implementation of outdoor home smart farming based on raspberry pi for home assistant management","abstract":"Outdoor home smart farming, also known as urban farming, is the practice of cultivating fruits, herbs, or vegetables for personal consumption on a small scale within a residential area. It is more sustainable compared to conventional agriculture in all aspects. However, there were various challenges in implementing outdoor home smart farming, including limitation or lack of skills, resources, or infrastructure to produce good and high-quality crops. This study addresses these challenges by integrating Python scripting and Linux OS with hardware components like the Raspberry Pi 4 Model B, ESP32, soil moisture sensors, and UV lights. Home Assistant, an open-source software, was utilized to run the script programming for outdoor home smart farming. The integrated smart devices into Home Assistant were used to monitor and analyze the farming parameters outcomes to assist decision-making and provide further user action. As a result, the system was efficient due to only consuming 0.16% for water usage and 0.64% for energy consumption compared to daily household use, as well as reducing water usage by up to 82.45% for the watering process. These results highlight the system’s capability to optimize resource usage and enhance crop productivity while minimizing environmental impact. By leveraging smart devices and IoT frameworks, the study showcases how modern technology can revolutionize traditional farming practices. The automated system not only reduces manual labor but also provides real-time data to assist in decision-making and further user actions. In conclusion, the implementation of Home Assistant management based on Raspberry Pi in outdoor home smart farming effectively addresses the challenges of urban agriculture.","author":[{"family":"Maslan","given":"Mohd"},{"family":"Ramli","given":"Izzat"},{"family":"Fauadi","given":"Muhammad"},{"family":"Ayob","given":"Mohd"},{"family":"Baharom","given":"Mohamad"},{"family":"Ghazali","given":"Ihwan"},{"family":"Tanjung","given":"Tia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31893/multiscience.2025418","URL":"https://doi.org/10.31893/multiscience.2025418","source":"crossref"},{"id":"doi:10.23887/jwl.v14i1.84796","type":"article-journal","title":"Pemberdayaan Masyarakat Desa dalam Peningkatan Produktivitas Budidaya Jamur Tiram Berbasis Smart Farming","abstract":"Usaha pertanian jamur tiram seringkali mengalami kendala dalam menjaga suhu dan kelembaban pada kumbung jamur. Program ini bertujuan memberdayakan masyarakat desa, khususnya petani jamur tiram, melalui penerapan teknologi smart farming guna meningkatkan produktivitas budidaya jamur tiram secara efisien dan berkelanjutan. Kegiatan Pengabdian masyarakat (PKM) ini difokuskan pada penerapan teknologi tepat guna untuk meningkatkan produktivitas budidaya jamur tiram. Subjek yang terlibat dalam pengabdian ini usaha pertanian jamur tiram. Metode pengumpulan data dilakukan melalui observasi, wawancara dengan pemilik usaha, serta dokumentasi hasil panen. Metode analisis data yang digunakan adalah metode kuantitatif deskriptif, dengan membandingkan data produksi jamur tiram sebelum dan sesudah penggunaan alat secara numerik, untuk mengetahui peningkatan produktivitas dan efektivitas alat dalam mengatur suhu serta kelembapan kumbung jamur. Hasil kegiatan menunjukkan bahwa sebelum menggunakan Matic – Kumbung hasil panen pak Agus rata rata 8,95 Kg, setelah menggunakan alat Matic-Kumbung Sebesar 18,9 ini dikarenakan pada alat Matic Kumbung dapat mengatur suhu dan kelembaban pada kumbung jamur. Cara kerjanya ketika suhu terlalu panas maka sensor akan mengirimkan sinyal ke arduino lalu arduino akan menyiramkam air dalam bentuk embun. Temuan ini menunjukkan bahwa integrasi teknologi dalam kegiatan budidaya tidak hanya meningkatkan efisiensi kerja petani, tetapi juga mampu memberikan dampak nyata terhadap kesejahteraan mereka, sekaligus menjadi model pemberdayaan masyarakat desa yang berkelanjutan.","author":[{"family":"Suda","given":"Kadek"},{"family":"Suteja","given":"IWA"},{"family":"Junitasari","given":"Putu"},{"family":"Widja","given":"Ida"},{"family":"Antara","given":"Made"},{"family":"Putra","given":"IGEW"},{"family":"Sutarga","given":"IN"}],"issued":{"date-parts":[[2025]]},"DOI":"10.23887/jwl.v14i1.84796","URL":"https://doi.org/10.23887/jwl.v14i1.84796","source":"crossref"},{"id":"doi:10.55041/ijsrem54581","type":"article-journal","title":"IOT-Based Smart Precision Farming: A Comprehensive Review of Enabling Technologies","abstract":"Abstract- The global agricultural sector faces unprecedented challenges, including climate change, water scarcity, and the need to enhance yield to meet rising food demand. Precision farming, empowered by the Internet of Things (IoT), presents a paradigm shift from traditional homogeneous field management to data-driven, site-specific optimization. This paper reviews the core technologies and architectural frameworks essential for implementing a robust IoT-based smart farming system. We examine the integration of wireless sensor networks (WSNs) for real-time field data acquisition (e.g., soil moisture, temperature, humidity, NPK levels), the role of unmanned aerial vehicles (UAVs) for aerial imaging and monitoring, and the suitability of microcontrollers like ESP32 and Arduino for localized control and connectivity. The review details a system architecture that leverages cloud platforms for data analytics, enabling automated decision-making for irrigation, fertilization, and pest control. By synthesizing data from multiple sources, these intelligent systems promise to significantly increase crop productivity, optimize resource usage, and promote sustainable agricultural practices. Keywords—Precision Agriculture, Internet of Things (IoT), Wireless Sensor Networks (WSN), Sensor Nodes, Cloud Computing, Data Analytics, Automated Irrigation, ESP32.","author":[{"family":"Rao","given":"Srimanth"},{"family":"Kumar","given":"AB"}],"issued":{"date-parts":[[2025]]},"DOI":"10.55041/ijsrem54581","URL":"https://doi.org/10.55041/ijsrem54581","source":"crossref"},{"id":"doi:10.63158/journalisi.v7i4.1385","type":"article-journal","title":"Utilization of the AgriTrack Information System to Strengthen Smart Farming Practices in Small-Scale Hydroponic Enterprises","abstract":"The implementation of smart farming in small-scale hydroponic enterprises is often constrained by high automation costs and technological complexity. This study examines the utilization of the AgriTrack information system as a practical approach to strengthening smart farming practices through structured digital data management. AgriTrack was utilized in a small-scale hydroponic farm using a Software Development Life Cycle (SDLC) Waterfall approach, encompassing system configuration, operational deployment, and evaluation through functional testing and user acceptance testing. The system applies a cycle-based relational data model to manage cultivation records from sowing to harvesting and integrates automated scheduling with Telegram Bot notifications. Testing results indicate a 100% success rate across core operational functions, while user evaluation shows that routine cultivation data recording time was reduced from several minutes to under one minute per entry. Notification delivery was consistently observed within approximately one minute after scheduled triggers, supporting timely operational decisions. These findings demonstrate that AgriTrack effectively strengthens smart farming practices in MSME-scale hydroponic enterprises by improving efficiency and accountability, while providing a scalable foundation for gradual adoption of advanced technologies such as IoT and data analytics.","author":[{"family":"Sholeha","given":"Eka"},{"family":"Supriyanto","given":"Arif"},{"family":"Utomo","given":"Hendrik"},{"family":"Firmansyah","given":"Eka"},{"family":"Aisyah","given":"Aisyah"},{"family":"Hidayat","given":"Ardhi"},{"family":"Mardhiyatirrahmah","given":"Liny"}],"issued":{"date-parts":[[2026]]},"DOI":"10.63158/journalisi.v7i4.1385","URL":"https://doi.org/10.63158/journalisi.v7i4.1385","source":"crossref"},{"id":"doi:10.2478/ata-2025-0025","type":"article-journal","title":"Smart Farming in Indonesia: Behavioural Study on Adoption of Internet-Based Fertilisation Systems","abstract":"Abstract Providing precise fertilisation guidance is vital for improving productivity and reducing environmental risks, yet the adoption of precision fertiliser systems remains low. The study investigates farmers’ intentions to adopt an Internet-based rice fertiliser information system across three agroecosystems: irrigated (Yogyakarta), rainfed (North Sumatra), and tidal (Central Kalimantan), with 100 farmers from each region. Applying an extended version of the technology acceptance model and using PLS-SEM analysis, the findings showed that perceived usefulness, perceived ease of use, and social norms are key determinants influencing individuals’ intention to adopt. Institutional trust also promotes adoption, while experience has no significant effect. These findings highlight the importance of trust and targeted training to boost farmers’ digital engagement with precision fertilisation technologies.","author":[{"family":"Susilawati"},{"family":"Girsang","given":"Setia"},{"family":"Laksono","given":"Pandu"},{"family":"Pustika","given":"Arlyna"},{"family":"Darsani","given":"Yanti"},{"family":"Parhusip","given":"Dorkas"},{"family":"Liana","given":"Twenty"},{"family":"Sebayang","given":"Amelia"},{"family":"Suprihatin","given":"Agus"},{"family":"Sakti","given":"Indra"},{"family":"Sembiring","given":"Hasil"},{"family":"Sitorus","given":"Alfonso"},{"family":"Tobing","given":"Jeannette"},{"family":"Purba","given":"Tommy"},{"family":"Ramdhani","given":"Taufik"},{"family":"Purbawa","given":"Yudha"},{"family":"Chairuman","given":"Novia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.2478/ata-2025-0025","URL":"https://doi.org/10.2478/ata-2025-0025","source":"crossref"},{"id":"doi:10.32900/2312-8402-2025-134-197-207","type":"article-journal","title":"STRESSFUL SEASONAL FACTORS OF INFLUENCE ON MILK PRODUCTIVITY AND QUALITY OF COW’S MILK","abstract":"The research is devoted to a topical issue – establishing the influence of seasonal changes on the quality indicators of cow milk in the forest-steppe of Ukraine. Researchers from different countries and climatic regions have proven the impact of seasonal changes on the milk productivity of cows. Studies were conducted on cows of the Ukrainian red-pock dairy breed, in which milk productivity was taken into account by the method of control milking during January-August and the fat and protein content in milk was determined. The experiment was divided into three stages according to the actual ambient temperature: I – from -3 °C to +9 °C, II – from +10 °C to +24 °C, III – from +24.5 °C to +36.4 °C. the actual average air temperature was – +7 °C, +21 °C and 28 °C, respectively. At the first stage of the experiment, the average daily milk yield of experimental cows was 19.6 kg, during the first – the coldest period of research (from January 2 to March 25) – their productivity increased by 0.2 kg. At the second stage of research, during the spring warming (from March 26 to May 26), the average daily milk yield increased by 0.7 kg. At the end of the hottest third period of the study (from May 27 to August 31), the daily milk yield decreased by 1.1 kg compared to the first period and by 1.8 kg compared to the second period. Differences between the indicators of fat and protein content in the milk of experimental cows were established. At the first stage of the experiment, the average fat content in the milk of experimental cows was 3.93%, protein ‒ 2.98 %. During the coldest period of the year studied, the fat content in milk increased by 0.14 % (p&lt;0.01), protein – by 0.24 % (p&lt;0.01). At the end of the second stage of the study, the fat and protein content in milk increased slightly, by 0.05% and 0.02%, respectively. During the hottest period of research, the fat content in the milk of experimental cows increased by 0.14 %. The protein content in milk decreased slightly (by 0.06%) at the end of the third study period. Thus, it is proved that seasonal changes affect the milk productivity of cows, in particular, the daily milk yield, fat and protein content in milk, which is consistent with studies by other scientists conducted in different countries. Further research should be aimed at finding innovative ways to offset the negative factors of seasonal changes on the productivity of dairy cattle.","author":[{"family":"Tkachova","given":"Iryna"},{"family":"Prusova","given":"Galina"},{"family":"Petrash","given":"Vitaly"},{"family":"Tkachev","given":"Anatoly"}],"issued":{"date-parts":[[2025]]},"DOI":"10.32900/2312-8402-2025-134-197-207","URL":"https://doi.org/10.32900/2312-8402-2025-134-197-207","source":"crossref"},{"id":"doi:10.1016/j.farsys.2025.100138","type":"article-journal","title":"Spatiotemporal variation of crop diversification across Eastern Indo Gangetic plains of South Asia","abstract":"South Asia's Eastern Indo-Gangetic Plain (EIGP) of India, Nepal, and Bangladesh is home to approximately 450 million people and predominantly rely on agriculture for livelihood. Agriculture is highly cereal-centric in EIGP. Increasing crop diversification within the EIGP region could improve agricultural sustainability, but knowledge of the spatiotemporal patterns of crop diversification and how it varies across EIGP countries is limited. In this study, we used historical sub-national crop data from India (1966–2022), Nepal (2000–2022), and Bangladesh (1971–2022) to measure crop diversification and compare it with the existing sub-district level scale. Crop diversification was measured using the Herfindahl-Hirschman Index (HHI). We found a noticeable increase in overall crop diversification in EIGP during this period but with spatiotemporal variations between the countries and seasons. Furthermore, while comparing sub-national patterns with existing sub-district patterns, we found opposing trends. Our data suggest that sub-national diversification patterns are an aggregate measure that may obscure the diversification pattern at the district, sub-strict, and even community level diversification. Measurements of sub-national crop diversification may appear to have moderate diversification overall, but this could result from some districts having high levels of diversification while others more oriented towards monocropping and a lack of diverse crop rotations. Our findings provide a new approach and a baseline of crop diversification in the EIGP for future research and interventions agricultural policy and development planners. • Measured spatiotemporal crop diversification (1966–2022) in the Eastern Indo-Gangetic Plain using the Herfindahl-Hirschman Index. • Identified distinct trends in crop diversification, noting that some areas showed marked increases in diversification while others remained heavily reliant on monocropping. • Sub-national diversification patterns may obscure finer-scale diversification at district, sub-district, and community levels. • The study establishes a baseline of crop diversification in the EIGP of India, Nepal, and Bangladesh, supporting future research and interventions.","author":[{"family":"Nandi","given":"Ravi"},{"family":"Ghosh","given":"Arunava"},{"family":"Karmacharya","given":"Saurya"},{"family":"Krupnik","given":"Timothy"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.farsys.2025.100138","URL":"https://doi.org/10.1016/j.farsys.2025.100138","source":"crossref"},{"id":"doi:10.1109/icstsdg61998.2024.11026365","type":"article-journal","title":"Forecasting Crop Yields Using Machine Learning Techniques For Sustainable Farming","abstract":"Crop production plays a crucial role in agriculture planning resource allocation and food security management with the advancement of technology and the availability of vast amounts of agriculture data, machine learning and statistical modelling techniques have emerged as powerful tools for predicting crop yields and identifying potential factors including crop growth. the data set utilized in crop production includes data such as whether data, soil quality is obtained through soil sampling algorithms commonly applied in crop production including Gaussian naive bayes this algorithm leverages the extracted features from the data set to build predictive models that estimate crop production for specific region and the period. Additionally, it highlights the significance of Accurate crop prediction in optimizing agriculture practices mitigating risks associated with climate change, and ensuring sustainable food production. furthermore, the discussion challenges data availability model complexity and interpretability along with the potential Avenue of further research to enhance the accuracy and applicability of the crop production model.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icstsdg61998.2024.11026365","URL":"https://doi.org/10.1109/icstsdg61998.2024.11026365","source":"crossref"},{"id":"doi:10.3389/fsufs.2026.1804209","type":"article-journal","title":"Adoption of Internet of Things in smart horticulture farming: the influence of farmer characteristics and innovation perception in West Java","abstract":"The adoption of Internet of Things (IoT) technologies in agricultural practices remains limited due to constraints in digital literacy, infrastructure, capital, and local technological relevance. This study aims to analyze the effects of farmer characteristics on IoT adoption and innovation perception, and to examine the relationships among adoption levels, innovation perception, and the consequences of innovation implementation in agricultural practices. A quantitative approach was employed using a survey of 400 farmers who are members of the Farmers Group Association (GAPOKTAN) under the Digital Village Program in West Java Province, Indonesia. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS version 3.9.2. The research model comprised four latent variables and thirteen measurement indicators. The measurement model results confirmed that all constructs met the required validity and reliability criteria, with factor loadings ranging from 0.697 to 0.956, Cronbach's alpha values between 0.719 and 0.938, and Average Variance Extracted (AVE) values from 0.532 to 0.913. Structural model analysis revealed that farmer characteristics had a significant positive effect on adoption (β = 0.591, t = 9.683, p &amp;lt; 0.001) and innovation perception (β = 0.712, t = 11.158, p &amp;lt; 0.001). Adoption also had a significant positive effect on innovation perception (β = 0.152, t = 2.158, p = 0.031). Furthermore, innovation perception demonstrated the most significant positive effect on innovation consequences (β = 0.879, t = 33.936, p &amp;lt; 0.001). These findings indicate that farmer characteristics play a crucial role in shaping IoT adoption and innovation perception, with innovation perception exerting the most significant effect on innovation outcomes. The results highlight the importance of enhancing farmer readiness to improve efficiency, reduce costs, and increase productivity. Future initiatives should focus on strengthening digital literacy, infrastructure, and financial support. Further research is recommended to expand geographic coverage and incorporate additional contextual factors, such as infrastructure availability, market dynamics, and policy support, to support sustainable agricultural development.","author":[{"family":"Darmawan","given":"Cecep"},{"family":"Zaenudin","given":"Heni"},{"family":"Sumardjo","given":"Sumardjo"},{"family":"Firmansyah","given":"Adi"},{"family":"Dharmawan","given":"Leonard"},{"family":"Martuti","given":"Nana"},{"family":"Melati","given":"Inaya"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3389/fsufs.2026.1804209","URL":"https://doi.org/10.3389/fsufs.2026.1804209","source":"crossref"},{"id":"doi:10.25157/ma.v12i1.22419","type":"article-journal","title":"Analisis Penerimaan Petani Pengguna Aplikasi SiKePangMas (Aksi Ketahanan Pangan Masyarakat) berbasis Smart Farming di Kabupaten Sumba Timur","abstract":"Smart farming is a solution to overcome food security problems in accordance with SDG's goal 2. In East Sumba Regency, it is realized by developing the Community Food Security Action (SiKePangMas) application, an Android-based application designed to help farmers determine the right commodities, planting calendars and forecasts of potential disaster hazards for more productive agriculture. The purpose of this study was to determine the level of acceptance and factors that influence the acceptance of farmer users of the SiKePangMas application. This study is a quantitative study, conducted from June to October 2025 in East Sumba Regency. ), The research respondents were 210 farmers who used the SIKePangMas application, determined by purposive sampling technique. The problem is solved using the Technology Acceptance Model (TAM) approach and the research model testing is carried out using the SEM-PLS approach with the help of the SmartPLS 4.0 application. The results of this study indicate that perceived usefulness (PU) has a positive and significant effect on attitudes towards use (ATU), perceived usefulness (PU) is proven to have a positive and significant effect on behavioral intentions of use (BIU), perceived ease of use (PEU) has a positive and significant effect on perceived usefulness (PU), perceived ease of use (PEU) is proven to have a positive and significant effect on attitudes towards use (ATU), attitudes towards use (ATU) are proven to have a positive and significant effect on behavioral intentions of use (BIU), behavioral intentions of use (BIU) have a very strong and significant positive effect on actual use (AU) of the SiKePangMas application. Attitudes and intentions are proven to be the main predictors that determine the level of use of the SiKepanMas application in farmer farming in East Sumba Regency.","author":[{"family":"Mbana","given":"Febyningsi"},{"family":"Saragih","given":"Elsa"},{"family":"Utu","given":"Naomi"},{"family":"Malahina","given":"Agung"}],"issued":{"date-parts":[[2026]]},"DOI":"10.25157/ma.v12i1.22419","URL":"https://doi.org/10.25157/ma.v12i1.22419","source":"crossref"},{"id":"doi:10.1049/smc2.70026","type":"article-journal","title":"Deep CNN Models for Weather Monitoring in Smart Agriculture Within Smart Cities","abstract":"ABSTRACT Weather monitoring in agriculture is complex, as it requires predicting future atmospheric states that directly affect farming activities. In smart cities, farmers rely on accurate, up‐to‐date weather information to make informed decisions. Increasing climate variability has made temperature prediction more challenging than ever. Deep learning has recently emerged as a powerful approach for weather forecasting due to its superior performance over conventional methods and its ability to extract and classify features within a single architecture. This study explores the use of deep Convolutional Neural Network (CNN) models, specifically Visual Geometry Group 16 (VGG16) and MobileNet, with transfer learning for intelligent weather monitoring. The combination of MobileNet and VGG16 leverages transfer learning for accuracy‐driven and efficient operations. MobileNet is optimised for mobile and edge devices by delivering high‐performance results with lower computational and energy costs, while the deep architecture of VGG16 effectively identifies complex visual features across multiple tasks. Trained on a dataset of weather images, the proposed models accurately detect and classify different weather conditions, enabling farmers to make improved field decisions. Experimental results demonstrate strong performance, with VGG16 achieving 96.95% accuracy and MobileNet achieving 96.19% accuracy.","author":[{"family":"Tariq","given":"Maria"},{"family":"Shah","given":"Asghar"},{"family":"Abbas","given":"Sagheer"},{"family":"Khan","given":"Muhammad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1049/smc2.70026","URL":"https://doi.org/10.1049/smc2.70026","source":"crossref"},{"id":"doi:10.1201/9781042015597-7","type":"article-journal","title":"Livestock Integration in Biodynamic Farming","abstract":"Biodynamic farming is an advanced agricultural approach that incorporates ecological, ethical, and holistic practices to create a self-sustaining ecosystem. A key component of biodynamic farming is livestock integration, which plays a crucial role in enhancing soil fertility, biodiversity, and farm productivity. This article explores the principles and practices of livestock integration in biodynamic farming, examining the benefits, challenges, and practical applications. By understanding the symbiotic relationships between animals, plants, and soil, farmers can create more resilient and sustainable farming systems. This comprehensive analysis provides insights into the methods and outcomes of integrating livestock into biodynamic farms, offering a roadmap for farmers seeking to adopt or enhance this practice.","author":[{"family":"Ramanjineyulu","given":"M"},{"family":"Naik","given":"Mude"},{"family":"Naik","given":"SNA"},{"family":"Bharathi","given":"A"},{"family":"Reddy","given":"Singireddy"},{"family":"Yoshitha","given":"Sibbala"},{"family":"Deepika","given":"J"},{"family":"Rao","given":"Marati"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781042015597-7","URL":"https://doi.org/10.1201/9781042015597-7","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100245","type":"article-journal","title":"Quantification of basis risk in weather index crop insurance in Northern Ghana","abstract":"Weather index insurance (WII) has been proposed as an effective risk transfer measure against extreme weather events affecting smallholder farmers in Sub-Saharan Africa. Despite the potential of this insurance type to stabilize farm income under extreme weather conditions, subscription rates by farmers have been very low. One of the reasons for the low subscription is basis risk, which relates to mismatches between payouts and losses, leading to misunderstanding and distrust on the part of farmers. Using an integrated bio-economic modelling approach for Northern Ghana, we quantify basis risk arising from three misalignments: spatial mismatch in rainfall inputs, temporal mismatch due to heterogeneity in planting dates, and biophysical mismatch linked to soil water-holding capacity (proxied by soil depth). Spatial basis risk was assessed by adjusting the daily precipitation data decreasing the values by up to the 10th percentile and increasing them up to the 90th percentile compared to the reference. For temporal basis risk planting dates were varied by delaying them by 7 to 21 days and increasing them by 14 days. To assess the sensitivity of index performance to soil variability, reference soil depths were increased and decreased by 30 cm. We evaluate insurance performance on maize crops using household outcomes (gross margin and assets). Results show that misalignment can substantially weaken risk protection, with the largest effects in product basis risk where soil water storage differs from insurance contract reference assumptions. Consistent with prior work, our results reinforce that WII contracts should align with local agronomic and environmental conditions; we add incremental evidence by quantifying how residual misalignment, especially soil-depth heterogeneity and planting-date shifts can weaken protection in shock years.","author":[{"family":"Adelesi","given":"Opeyemi"},{"family":"Kim","given":"Yean"},{"family":"Webber","given":"Heidi"},{"family":"Schuler","given":"Johannes"},{"family":"Zander","given":"Peter"},{"family":"Hosseini-Yekani","given":"Seyed"},{"family":"Njoroge","given":"Michael"},{"family":"Waithaka","given":"Lilian"},{"family":"Maccarthy","given":"Dilys"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100245","URL":"https://doi.org/10.1016/j.farsys.2026.100245","source":"crossref"},{"id":"doi:10.62673/jdiu.v13n1.a6","type":"article-journal","title":"Smart Farming Prediction System using Deep Learning Method through Web Interface in Bangladesh","abstract":"Diabetes is a chronic medical condition characterized by high levels of sugar (glucose) in the blood this occurs because that time our pancreas does not produce enough insulin (Type 1 diabetes), or because the body's cells do not respond properly to insulin (Type 2 diabetes). There is also a condition called gestational diabetes that can develop during pregnancy. It is a leading cause of severe health complications, including blindness, kidney failure, amputations, heart failure, and stroke. When we eat, our body turns that food into sugars or glucose. At that point, our pancreas is supposed to release insulin. Insulin serves as a key to open our cells, to allow the glucose to enter and allow body to use that glucose for energy. But with diabetes, this system does not work. Several major things can go wrong causing the onset of diabetes. Type-1 and Type-2 diabetes are the most common forms of the disease but there are also other kinds such as gestational diabetes, which occurs during pregnancy as well as other forms. This paper focuses on recent developments in machine learning which have made significant impacts in the diagnosis and detection of diabetes. In this study, Machine Learning (ML) techniques are used to predict the presence of diabetes. The proposed method predicts the chances of diabetes and classifies patient's risk level by using different ML algorithm techniques such as Decision Tree Classifier, Random Forest Classifier, K-Neighbors Classifier, Ada-Boost Classifier, XG-Boost Classifier, Logistic Regression, Support Vector Machine, Gaussian NB and apply Voting Classifier for best output result. Two different datasets are combined to train and test the proposed system which have 900 rows with 11 columns. The experimental results highlight that the Support Vector Machine algorithm yields the highest accuracy at 79.63% and the application of the Voting Classifier further refines the accuracy to 75.56% compared to other ML algorithms. These findings showcase the potential of machine learning techniques in the early diagnosis and risk assessment of diabetes, which can significantly contribute to improved healthcare outcomes.","author":[{"family":"Biswas","given":"Jahanur"},{"family":"Almajid","given":"Md"},{"family":"Tahzib-Ul-Islam","given":"Md"}],"issued":{"date-parts":[[2025]]},"DOI":"10.62673/jdiu.v13n1.a6","URL":"https://doi.org/10.62673/jdiu.v13n1.a6","source":"crossref"},{"id":"doi:10.1016/j.farsys.2025.100193","type":"article-journal","title":"Typology-based evaluation of Nutrient Expert® for sustainable maize intensification in smallholder farms of eastern India","abstract":"Smallholder maize systems in South Asia face challenges of low productivity, inefficient fertilizer use, and rising environmental footprints. Decision-support tools (DST) such as Nutrient Expert® (NE®), built on 4R nutrient stewardship principles, offer promise for achieving sustainable intensification (SI), yet their performance across diverse farm types remains poorly understood. This study assessed NE®-guided fertilization against farmer fertilizer practices (FFP) across 112 farms in four agro-climatic zones of southern West Bengal, India. Farm typologies were delineated using principal component and cluster analysis, resulting in seven distinct farm types (FT) reflecting socio-economic and biophysical heterogeneity. Paired on-farm trials compared NE® and FFP for multiple indicators, including yield, economics, energy use, and greenhouse gas (GHG) emissions. Results show that NE® reduced N, P, and K use by 66%, 93%, and 56%, respectively, while increasing yields across all farm types, with the highest gains in FT-4 (71.1%), FT-2 (63.0%), and FT-7 (60.3%). Gross return above fertilizer cost (GRF) improved in nearly all cases, with FT-2 achieving a 90% gain. Energy productivity and net energy gain increased in most farm types, while yield-scaled GHG emissions declined in 88.4% of farms. However, benefits were uneven: FT-3 and FT-5, constrained by setting higher yield targets, coupled with poor resource endowment and weak yield response, showed limited improvements. Thin-plate spline regression further identified farm-type–specific sustainability frontiers, indicating untapped potential for SI beyond current NE® yield targets. Overall, the findings demonstrate the utility of NE® in tailoring realistic yield targets for DST and nutrient management across heterogeneous farm systems, while also highlighting the importance of typology-based scaling strategies. • NE improved maize yield, profit, and energy efficiency and reduced GHG emissions compared to farmer fertilizer practices • Fertilization using NE achieved highest energy efficiency and lowest GHG emissions in input intensive, resource-rich farms • NE® tool largely achieved normative standards of economic and environmental outcomes from maize • NE® can further improve maize yield across all farm types • Typology-based scaling is vital for sustainable intensification in South Asia","author":[{"family":"Goswami","given":"Rupak"},{"family":"Dutta","given":"Sudarshan"},{"family":"Banerjee","given":"Hirak"},{"family":"Chakraborty","given":"Somsubhra"},{"family":"Ray","given":"Krishnendu"},{"family":"Majumdar","given":"Kaushik"},{"family":"Timsina","given":"Jagadish"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.farsys.2025.100193","URL":"https://doi.org/10.1016/j.farsys.2025.100193","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100210","type":"article-journal","title":"Erosion control and phosphorous losses in agriculture: A policy and economic assessment of the Common Agricultural Policy (CAP) in Baden-Württemberg","abstract":"Phosphorus (P) emissions from agricultural land are a major contributor to eutrophication. Effective mitigation of particulate phosphorous (PP) emissions and soil erosion requires targeted policies that reflect the spatial variability of erosion risks. This study evaluates the economic and environmental performance of different CAP measures in terms of reducing PP emissions and erosion with a focus on the minimum requirements for limiting erosion (Good agricultural and environmental conditions 5: GAEC5) and winter cover crop premiums in Baden-Württemberg (BW). Therefore, we combined a geospatially explicit economic land-use model (PALUD AF ) with site-specific data on erosion and PP risk to simulate land-use decisions under different policy scenarios. Results show that the CAP 2023-2027, which combines GAEC5 with cover crop premiums, reduces PP emissions by 13% and soil loss by 6.5% compared to the previous CAP cycle. The abatement costs for PP emissions or erosion range between 581 € and 1,117 € kg -1 or 28 and 68 € t -1 in a scenario with only GAEC5 or only premiums for winter cover crops. These numbers indicate a higher efficiency of GAEC5 (i.e., conditionality), however, only under the assumption that cover crops are purely aimed to reduce PP emissions and/or soil loss. The new CAP still fell short of the 20% P reduction target given PP emissions alone, indicating the relevance of additional measures. The analysis underscores trade-offs between economic efficiency and environmental effectiveness between conditionality and cover crop premiums. This highlights the need for spatially targeted policy instruments to address PP risks, while also underlining the ecological added value of stricter GAEC5 regulations.","author":[{"family":"Herrmann","given":"Tristan"},{"family":"Geier","given":"Cecilia"},{"family":"Angenendt","given":"Elisabeth"},{"family":"Bahrs","given":"Enno"},{"family":"Sponagel","given":"Christian"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100210","URL":"https://doi.org/10.1016/j.farsys.2026.100210","source":"crossref"},{"id":"doi:10.9734/ijecc/2026/v16i85612","type":"article-journal","title":"Climate-smart Agriculture as a Systems Transition: Integrating Agroecology, Renewable Energy and Institutions for Sustainable and Climate-resilient Farming","abstract":"Climate-smart agriculture has become an influential framework for aligning agricultural productivity, adaptation and greenhouse-gas mitigation, yet its practical meaning remains contested because no technology is intrinsically climate-smart across all places, scales and social groups. This critical narrative review examines how agroecological design, renewable-energy deployment and institutional arrangements can be integrated into coherent farming-system transitions rather than promoted as disconnected interventions. Literature published mainly from 2010 to 30 May 2026 was identified through accessible scholarly indexes, institutional repositories, official scientific assessments and citation chaining, and was appraised for methodological quality, contextual relevance, treatment of trade-offs and evidence of durable outcomes. The synthesis indicates that agroecological diversification can strengthen soil functions, water regulation, biodiversity and livelihood buffering, although benefits are strongly conditioned by system design, transition duration, labour and knowledge demands, and access to biomass and land. Renewable energy can lower fossil-energy dependence and expand irrigation, processing and cold-chain services, but solar irrigation may accelerate groundwater depletion and agrivoltaics may reproduce land and tenure conflicts unless deployment is governed through water accounting, crop-sensitive design and benefit-sharing. Institutional capacity is therefore constitutive of climate-smartness: secure resource rights, trusted advisory systems, climate information, farmer organisations, coordinated finance, accountable markets and cross-sector policy determine who can adopt, sustain and benefit from technical change. The strongest pathway is not a universal package but a context-specific portfolio in which ecological redesign reduces exposure and input dependence, energy infrastructure removes productive bottlenecks, and institutions manage externalities, distribution and learning. Evidence remains weakened by short trials, inconsistent indicators, adoption-selection bias and sparse long-term distributional assessment. Future work should prioritise multi-site longitudinal experiments, causal institutional evaluations, whole-system water and carbon accounting, and governance designs that explicitly test equity and rebound risks.","author":[{"family":"Karthik","given":"MN"},{"family":"Aarthi","given":"SST"},{"family":"Hazeera","given":"KB"},{"family":"Sathwik","given":"GP"},{"family":"Basha","given":"NH"},{"family":"Deepasri","given":"K"}],"issued":{"date-parts":[[2026]]},"DOI":"10.9734/ijecc/2026/v16i85612","URL":"https://doi.org/10.9734/ijecc/2026/v16i85612","source":"crossref"},{"id":"doi:10.4018/979-8-3373-7554-0.ch008","type":"article-journal","title":"Harnessing Green AI for Weather-Responsive, Disaster-Resilient, and Eco-Smart Farming","abstract":"Agriculture faces irregular weather, intensifying natural disasters, and biodiversity loss that threaten global food security. To produce food responsibly, Agriculture 4.0 has revolutionized food production by integrating Green AI, precision technologies, and sustainable farming methods. AI-powered weather forecasting systems improve irrigation, crop scheduling, and disaster planning, while predictive models for floods, droughts, and insect outbreaks boost agricultural resilience. Additionally, remote sensing, drones, and AI algorithms track biodiversity to maintain ecosystems, enhance crop diversification, and reduce environmental consequences. IoT-based sensor networks, big data analytics, blockchain, and energy-efficient AI frameworks enable climate-smart agriculture. This chapter addresses digital inequity, data governance, and responsible AI use outside technology. Agriculture 4.0 provides a resilient, inclusive, and eco-friendly framework for feeding the globe in a changing environment by merging predictive intelligence with sustainability.","author":[{"family":"Dadhirao","given":"Chandrika"},{"family":"Sadi","given":"Ram"},{"family":"Poojary","given":"Manula"},{"family":"Penumatsa","given":"Hima"},{"family":"Kaviti","given":"Prasad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-7554-0.ch008","URL":"https://doi.org/10.4018/979-8-3373-7554-0.ch008","source":"crossref"},{"id":"doi:10.55041/ijcope.v2i3.246","type":"article-journal","title":"“INTEGRATING SOLAR POWER AND IOT: DEVELOPMENT OF A SMART TILLER FOR SUSTAINABLE POULTRY FARMING”","abstract":"The adaptability needed for small poultry environments is lacking in conventional tilling equipment, which is typically designed for open agricultural fields. In order to close this gap, this work describes the creation of a solar-powered, Internet of Things-integrated tiller that can effectively till soil and apply controlled pesticides in small agricultural areas. The system greatly reduces reliance on external electricity or fuel-driven mechanisms by using photovoltaic energy stored in a battery to power the tilling motor, spraying pump, and electronic subsystems. Mobility is made possible by a Wi-Fi-based control interface that allows users to operate the machine remotely in a convenient and secure manner by using a mobile application to drive it forward or backward. By warning the user of surrounding objects while maneuvering, an ultrasonic obstacle- detection module combined with an audible buzzer improves operational safety. Requirement analysis and CAD-based modeling using SolidWorks software were part of the engineering workflow. The results of the experiment showed consistent power consumption from the solar-battery system, stable tilling performance, efficient pesticide delivery, and dependable wireless control. For small poultry farms looking to automate repetitive tasks while reducing manual labour and operating costs, the suggested system provides a portable, energy efficient, and user-friendly solution. Future improvements could include more attachments for broader farm applications, better power-management algorithms, and semi-autonomous navigation. Keywords - IoT; Poultry tiller; Sustainable energy; Wi-Fi Control; Obstacle Detection.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijcope.v2i3.246","URL":"https://doi.org/10.55041/ijcope.v2i3.246","source":"crossref"},{"id":"doi:10.3934/agrfood.2026028","type":"article-journal","title":"From field to data: A global review of precision agriculture for smart and sustainable farming systems","abstract":"Precision agriculture (PA) utilizes advanced technological systems to enhance crop productivity and farm efficiency while minimizing negative ecological consequences. Contemporary agricultural challenges, including weeds, plant diseases, pest infestations, inefficient irrigation and soil management, and suboptimal crop practices, have resulted in significant yield losses and negative environmental impacts. These issues are compounded by the rising global demand for food, driven by population growth, and the finite availability of arable land. Addressing these complex problems requires innovative and adaptive solutions. PA offers a viable pathway forward, leveraging its core strengths of flexibility, accuracy, cost-efficiency, and enhanced operational effectiveness to transform production systems. In this article, we examined the convergence of advanced technological systems, such as artificial intelligence (AI), the Internet of Things (IoT), variable-rate application technologies, remote sensing, and Geographic Information Systems (GIS), to tackle the pressing agricultural constraints imposed by shrinking natural resources and rising global population demands. Additionally, we provided a review of the contemporary status of PA, encompassing recent technological advancements in unmanned aerial systems (drones), sensor networks, and machine learning (ML) applications. The scope for future innovation in this domain is extensive, heralding a transformative phase in agriculture characterized by heightened efficiency and sustainability, which is critical for ensuring global food security.","author":[{"family":"Utkina","given":"Aleksandra"},{"family":"Kucher","given":"Dmitry"},{"family":"Shokr","given":"Mohamed"},{"family":"Rebouh","given":"Nazih"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3934/agrfood.2026028","URL":"https://doi.org/10.3934/agrfood.2026028","source":"crossref"},{"id":"doi:10.62643/ijerst.2026.v22.n2(2).2907","type":"article-journal","title":"IoT-Based Intelligent Fish Farming System with Real-Time Monitoring, Automated Feeding, and Smart Alert Mechanism","abstract":"The Innovative Fish Farming Monitoring System is an IoT-enabled smart aquaculture solution designed to continuously monitor and regulate critical water quality and environmental parameters in fish ponds or tanks. The system leverages an ESP-32 microcontroller integrated with multiple sensors — including the Ultrasonic sensor for water level detection, DHT11 for temperature and humidity measurement, RTC module for real-time clock management, SPO2 sensor for dissolved oxygen monitoring, and a pH sensor for acidity/alkalinity regulation — to provide real-time data acquisition and automated responses. Output peripherals include an LCD display for on-site parameter visualization, a buzzer for immediate alert notifications, and an IoT cloud module for remote monitoring and data logging via the internet. The entire system is powered by a Regulated Power Supply (RPS) ensuring consistent operation. The proposed system addresses the key challenges faced by traditional fish farming practices such as manual water quality testing, inadequate monitoring, and delayed responses to hazardous environmental changes. By integrating hardware components with a software layer running on the ESP-32, this system offers precision aquaculture that can reduce fish mortality rates, optimize growth conditions, and enhance the overall productivity and sustainability of fish farming operations. The system finds applicability in small-scale home aquariums, medium fish ponds, and large-scale commercial aquaculture farms.","author":[{"family":"Reddy","given":"KA"},{"family":"Kumar","given":"MR"},{"family":"Ruchitha","given":"Gandla"},{"family":"Priyankith","given":"Saligommula"},{"family":"Pavan","given":"Duddu"},{"family":"Reddy","given":"Gaddam"}],"issued":{"date-parts":[[2026]]},"DOI":"10.62643/ijerst.2026.v22.n2(2).2907","URL":"https://doi.org/10.62643/ijerst.2026.v22.n2(2).2907","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100241","type":"article-journal","title":"Mapping soil organic carbon research in conservation agriculture: A systematic review","abstract":"Conservation agriculture (CA) increases soil organic carbon (SOC) and supports sustainable agricultural systems. Despite extensive research, the evidence remains fragmented regarding research hotspots, assessment methods, and specific soil C fractions affected by CA practices. Here we conduct a bibliometric analysis of 4,256 publications published between 2016 and 2025 to reveal global research trends, thematic evolution, and emerging priorities at the intersection of SOC and CA. Results show rapid growth in scientific output, with China, the United States, and the European Union forming the core of global collaboration networks. Our analysis highlights a shifting research focus from conventional tillage and climate impact assessments toward soil biodiversity, microbiome interactions, and ecosystem resilience. Methodologically, the synergy between machine learning (ML) and remote sensing (RS) has transformed SOC monitoring into a robust data-driven science. Future research trends may concentrate on the under-exploration of soil inorganic carbon (SIC) and the extremely sensitive labile pools, which include quickly oxidizable carbon. Furthermore, bridging the gap between scientific evidence, farm-level feasibility, and policy support remains critical. Future efforts should prioritize geographically inclusive and socio-ecological assessments, alongside harmonized frameworks, to support scalable CA-based SOC management. • Mapped global SOC research under conservation agriculture by bibliometric analysis (4,256 publications). • Research hotspots shifted toward microbes and resilience. • Machine learning and remote sensing improved SOC monitoring. • SIC and labile carbon remain understudied.","author":[{"family":"Liu","given":"Qingyang"},{"family":"Tian","given":"Xin"},{"family":"Dalal","given":"Ram"},{"family":"Wu","given":"Jinran"},{"family":"Xia","given":"Anquan"},{"family":"Wu","given":"Xiaoxuan"},{"family":"Li","given":"Tong"},{"family":"Mclachlan","given":"Geoffrey"},{"family":"Chapman","given":"Scott"},{"family":"Dang","given":"Yash"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100241","URL":"https://doi.org/10.1016/j.farsys.2026.100241","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100219","type":"article-journal","title":"Reconsidering “4 per 1000” target in mild salt-affected lands: A case study on exogenous carbon inputs","abstract":"There is an emerging consensus that exogenous carbon input has the potential to improve soil quality and optimize nitrogen management in salt-affected lands, yet it remains unclear how organic amendments function on crops. Here, we conducted a pot experiment to assess the effect of exogenous carbon input on sweet sorghum and soil properties. Specifically, an unfertilized control (CK), a urea treatment (N) and three combined urea and organic amendment treatments, which represented 2‰ (N-C1), 4‰ (N-C2) and 6‰ (N-C3) increase rate of soil carbon, were included in the experiment. We found exogenous carbon significantly increased nitrogen use rate (NUR) of sweet sorghum in all combined use treatments. It also alleviated the inhibition effect of nitrate accumulation on the growth of sweet sorghum induced by urea, especially at the five-leaf stage, yet still could not offset the negative impact of nitrate on sweet sorghum. Overuse of exogenous carbon led to unintended imbalanced soil C:N, enhanced soluble K + concentration and thereby a decoupling of NUR and biomass accumulation. A 2‰ increase rate of soil carbon by exogenous carbon inputs was optimal for keeping a proper soil C:N mass ratio at about 12:1 for both biomass and NUR of sweet sorghum in coastal salt-affected lands. Our study provides an insight into nutrient management strategies and land carbon carrying capacity for achieving both soil amendment and benefit of crop production in salt-affected lands. • Exogenous carbon inputs alleviated negative effect of nitrate on sweet sorghum. • Nitrogen use rate (NUR) of sweet sorghum was positively increased by exogenous carbon. • Applying exogenous carbon at 2‰ was recommended for improving both biomass and NUR. • Overuse of exogenous carbon led to unintended imbalanced soil C:N, enhanced soluble K + concentration and thereby decoupled biomass and NUR of sweet sorghum.","author":[{"family":"Lei","given":"Shanqing"},{"family":"Gong","given":"Huarui"},{"family":"Li","given":"Jing"},{"family":"Xu","given":"Yan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100219","URL":"https://doi.org/10.1016/j.farsys.2026.100219","source":"crossref"},{"id":"doi:10.37745/ijliss.15/vol12n15061","type":"article-journal","title":"Exploring the Role of Librarians as Knowledge Intermediaries in the Adoption of Mechanised Farming Tools in Indigenous Farming Communities","abstract":"The adoption of mechanised farming tools is widely recognised as a means of improving agricultural productivity, yet uptake among indigenous farming communities remains low. This study examines the role of librarians as knowledge intermediaries in supporting the adoption of mechanised farming tools and addressing information-related barriers in these communities. The study adopts an exploratory approach based on a review of existing literature from agriculture, rural development, and library and information science. Findings indicate that although mechanised tools improve efficiency, productivity and labour use, adoption is constrained by economic, infrastructural, institutional and informational challenges. Limited access to clear and relevant agricultural information significantly affects farmers’ awareness and willingness to adopt new technologies, while existing channels such as extension services remain inadequate. The study identifies librarians as underutilised actors who can bridge this gap through information organisation, literacy support, community engagement and digital platforms. It concludes that strengthening knowledge systems is essential and recommends integrating librarians into agricultural information frameworks to enhance access and support sustainable agricultural development","author":[{"family":"Jagaba","given":"Iliyasu"},{"family":"Olaniyi","given":"Abdulahi"},{"family":"Salah","given":"Hafsat"},{"family":"Dangana","given":"Ruqayyat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.37745/ijliss.15/vol12n15061","URL":"https://doi.org/10.37745/ijliss.15/vol12n15061","source":"crossref"},{"id":"doi:10.1016/j.agee.2025.109996","type":"article-journal","title":"Does mixed farming benefit moths? Exploring how different farming systems shape both local features and the wider landscape","abstract":"Moths are important pollinators and provide an essential food source for higher taxa, yet many species that were once widespread are in decline across Europe. This is largely due to practices associated with intensive farming, such as pesticide and fertiliser applications and habitat loss. There is increasing interest in finding ways of farming that are beneficial to both humans and biodiversity. ‘Mixed’ farming, where livestock are integrated into the crop rotation, is thought to provide benefits to biodiversity by reducing synthetic inputs and by increasing habitat and crop diversity. However, at commercial stocking levels, livestock can have detrimental impacts on grassland Lepidoptera. We investigate the different pathways through which mixed farming could benefit moths in comparison to arable farming (where livestock are absent). Between June and August 2022, twenty-six farms in Scotland were surveyed for moths using light-trapping. Woodland edge density, which was higher on mixed farms, increased micro moth abundance and species richness. Positive effects of woodland were also observed for ‘farmland’ micro moths that do not feed on woody plants. However, for micro moth species richness this positive effect of woodland edge was outweighed by a direct negative effect of mixed farming, highlighting the need for more research to find livestock management practices that are beneficial for moths.","author":[{"family":"Kennedy","given":"Rochelle"},{"family":"Fuentes-Montemayor","given":"Elisa"},{"family":"Park","given":"Kirsty"},{"family":"Littlewood","given":"Nick"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.agee.2025.109996","URL":"https://doi.org/10.1016/j.agee.2025.109996","source":"crossref"},{"id":"doi:10.47191/ijcsrr/v9-i3-21","type":"article-journal","title":"Farming Efficiency of Pest and Disease Control Techniques on The Efficiency of Shallot (Allium ascalonicum L.) Farming in Local Agricultura Areas in Timor-Leste","abstract":"Agriculture is one of Timor-Leste’s most important economic sectors, providing a living for the vast majority of the population. The key issue for shallot producers in Timor-Leste’s local agricultural areas is the high intensity of plant pest organism attacks, which has an impact on production costs and revenue. The purpose of this study is to determine how pest and disease control approaches affect the efficiency of shallot (Allium ascalonium L.) cultivation in Timor-Leste’s local agricultural areas. This study employs a quantitative approach, collecting primary data from farmers via surveys, structured interviews, and questionnaires administered to a sample of 10 shallot farmers and 40 respondents in the study area, and analyzing farming efficiency using the Linear Regression Analysis method implemented in SPSS version 22. This study found that, when compared to other ways, the use of integrated control in shallot cultivation is the most profitable and efficient. With a production of 3,700-4,320 kg and a consistent selling price of $3.50, total production costs (TC) range from $660 to $785. The t-test results showed that the variables Chemical Use (X1), Biological Use (X2), and Integrated Control (X4) all had a significant and positive effect on the dependent variables. The use of biological uses (X4) was the most significant factor, with a tcal value of 6,715, demonstrating that chemical technology intervention is still the principal driver of agricultural efficiency at this research site. The model accounts for 69% of the variance in farming efficiency (R² = 0.690). As a result, expanding farmer training and extension programs on integrated pest management (IPM) is critical for improving sustainable pest control and increasing the efficiency of shallot farming in Timor-Leste. So extension and training initiatives on integrated pest management (IPM) techniques should be strengthened to help farmers manage pests more efficiently and sustainably.","author":[{"family":"Colo","given":"Vergiliano"},{"family":"Nirwanto","given":"Herry"},{"family":"Purnawati","given":"Arika"}],"issued":{"date-parts":[[2026]]},"DOI":"10.47191/ijcsrr/v9-i3-21","URL":"https://doi.org/10.47191/ijcsrr/v9-i3-21","source":"crossref"},{"id":"doi:10.1016/j.farsys.2026.100220","type":"article-journal","title":"Sugarcane-peanut intercropping promotes crop health by recruiting beneficial bacteria, enhancing soil and crop productivity","abstract":"Sugarcane–peanut intercropping is widely practiced to improve agricultural sustainability, yet how this farming system impacts sugarcane crop health and boosts soil and crop productivity remains unclear. To address this knowledge gap, we investigated how such a farming system influences soil physicochemical properties, sugarcane growth, disease incidence, and bacterial communities across different growth stages and locations. A randomized block design field trial with sugarcane monoculture and wide-row sugarcane–peanut intercropping was established across two locations. Bacterial communities were characterized in rhizosphere and bulk soils using 16S high-throughput sequencing. Sugarcane-peanut intercropping significantly enhanced land-use efficiency (Land Equivalent Ratio (LER) increased from 1.00 to 1.42 at Site A and to 1.21 at Site B). Moreover, stem diameter increased significantly in the intercropping plots by 8.43% and 9.51% compared with monoculture across Site A and Site B, respectively. Single-stem weight increased significantly under the sugarcane–peanut intercropping at Site B compared to Site A. The number of effective stems per hectare decreased significantly by 14.99% and 30.36% in the intercropping plots at Site B. Alkali-hydrolyzable nitrogen, available phosphorus, and exchangeable potassium were significantly higher in intercropping fields compared with monoculture rhizosphere and bulk soils at both sites during the sugarcane maturity stage. Notably, key plant growth- and stress-regulating bacterial (PGSRB), including Stenotrophomonas, enriched significantly in the intercropping rhizosphere soil at Site A, while Burkholderia-Caballeronia-Paraburkholderia, Azospirillum, and Rhizobiaceae exhibited a similar phenomenon in the intercropping bulk soil during the elongation stage. Similarly, Burkholderia-Caballeronia-Paraburkholderia , Mesorhizobium, Bradyrhizobium, and Bacillus were enriched significantly in the intercropping rhizosphere and bulk soils during the maturity stage. The recruitment and proliferation of these PGSRB were associated with the suppression of red stripe disease across both sites. Taken together, these findings suggest that this farming system is an eco-friendly approach that supports crop health and boosts soil and crop productivity. • Sugarcane-peanut intercropping significantly enhanced Land Equivalent Ratio (LER) • Intercropping improved stem diameter and single-stem weight across sites. • Sugarcane-peanut intercropping increased key soil physicochemical properties. • Intercropping enriched key bacteria including Azospirillum and Burkholderia. • Bacteria enrichment was associated with reduced sugarcane red stripe disease.","author":[{"family":"Fallah","given":"Nyumah"},{"family":"Zhou","given":"Yongmei"},{"family":"Lian","given":"Jiapan"},{"family":"Lin","given":"Wenxiong"},{"family":"Tang","given":"Ronghua"},{"family":"Li","given":"Peiwu"},{"family":"Yuan","given":"Zhaonian"},{"family":"Pang","given":"Ziqin"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.farsys.2026.100220","URL":"https://doi.org/10.1016/j.farsys.2026.100220","source":"crossref"},{"id":"doi:10.1201/9781042014484-1","type":"article-journal","title":"Introduction","abstract":"This chapter deals with the agricultural technology responsible for bringing Green Revolution in India and later on how it become stagnant in agricultural production. Effects of Green Revolution on environment also stand mentioned. Apart from this, why the Green Revolution technologies got fatigued have been explained? All these factors were found to be amenable to bring down unsustainability in Indian Agriculture. Yields of crops, especially of rice and wheat got reduced and as such a number of the peasants of the country became involved in debt. Some of them committed suicides. To prevent this tragic scene, the authors of this book have tried their best to compile all the sporadic and scattered informations responsible to 2 enhance the yield of the crops and eventually looming the farmers income and rendering them free from debts.","author":[{"family":"Gupta","given":"RD"},{"family":"Gupta","given":"SK"},{"family":"Mahajan","given":"Anil"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781042014484-1","URL":"https://doi.org/10.1201/9781042014484-1","source":"crossref"},{"id":"doi:10.22437/jiiip.v29i1.48986","type":"article-journal","title":"Evaluasi Berat Badan Dengan Tingkat Penerapan Good Farming Practice Pada Peternakan Sapi Potong di Kabupaten Bone","abstract":"Latar Belakang: Peningkatan produksi daging sapi tidak hanya dipengaruhi oleh bertambahnya populasi ternak, tetapi juga oleh pencapaian bobot badan yang optimal. Penerapan standar pemeliharaan yang sesuai sangat diperlukan untuk memastikan manajemen peternakan berjalan efektif dan mampu menghasilkan daging berkualitas. Good Farming Practices (GFP) menjadi pendekatan penting dalam mendukung peningkatan produktivitas sapi potong. Tujuan: Penelitian ini bertujuan mengevaluasi tingkat penerapan GFP pada peternak sapi potong, menganalisis hubungan antara nilai GFP dan estimasi bobot badan sapi, serta menentukan kontribusi faktor pemeliharaan berbasis GFP terhadap performa produksi sapi potong di Kabupaten Bone. Metode: Penelitian dilaksanakan di Kecamatan Barebbo dengan melibatkan peternak aktif sebagai responden. Variabel independen mencakup aspek kandang (X1), pemilihan bakalan (X2), pakan (X3), serta kesehatan dan kesejahteraan hewan (X4). Variabel dependen berupa estimasi bobot badan sapi potong (Y). Data dikumpulkan melalui wawancara terstruktur dan pengukuran estimasi bobot badan. Analisis data meliputi penilaian performa GFP, uji korelasi untuk mengetahui keeratan hubungan antarvariabel, serta regresi linear berganda untuk menilai kontribusi masing-masing faktor terhadap bobot badan sapi. Hasil: Hasil penelitian menunjukkan bahwa penerapan GFP pada peternak bervariasi antaraspek, dengan aspek pakan memperoleh skor tertinggi. Faktor pakan dan kesehatan serta kesejahteraan hewan memberikan pengaruh terbesar terhadap peningkatan bobot badan sapi, disusul pemilihan bakalan. Sebaliknya, aspek kandang tidak menunjukkan pengaruh yang berarti. Hal ini menegaskan pentingnya manajemen nutrisi, kesehatan ternak, dan kenyamanan lingkungan pemeliharaan dalam mendukung pertumbuhan dan produktivitas. Kesimpulan: Nilai koefisien determinasi yang tinggi menunjukkan bahwa penerapan GFP secara konsisten berdampak positif terhadap performa produksi. Peningkatan pemeliharaan sesuai standar GFP direkomendasikan sebagai strategi pengembangan usaha sapi potong di Kabupaten Bone.","author":[{"family":"Yunus","given":"Muhammad"},{"family":"Azhar","given":"Muhammad"},{"family":"Sara","given":"Urfiana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.22437/jiiip.v29i1.48986","URL":"https://doi.org/10.22437/jiiip.v29i1.48986","source":"crossref"},{"id":"doi:10.1109/ic3i61595.2024.10829261","type":"article-journal","title":"RSF: Smart Farming Using Machine Learning-Based Recommendation System","abstract":"Undoubtedly, agriculture and its associated sectors are the primary sources of income in rural areas of India. It is also an important contributor to the national GDP. The agricultural sector can grow with size and production technology supports the farmer crop cultivation on healthy soil. The crop yield per hectare is lamentable compared to global standards. In this research work, farmers propose a practical and user-friendly system, which can predict crop yield recommendation for use. Farmers access it through a proposed integrated system with machine learning and application interface. GPS: Global Positioning System (GPS) enables one to know his/her whereabouts. Hence, it is also possible to make a farm location on Google using this system. Users can input weather situations in the study area & soil health information required for predictive modelling. The model provides appropriate crops or anticipates yields on the farmer’s requests. Machine Learning approaches, Support Vector Machine (SVM), Neural Network (NN), and Random Forest (RF) are used to determine crop yield. The recommendation of the optimal machine-learning model is passed to the RSF: application interface for informed decisions about crop cultivation.","author":[{"family":"Rawat","given":"Pradeep"},{"family":"Soni","given":"Prateek"},{"family":"Purwar","given":"Ritwik"},{"family":"Dwivedi","given":"Rishabh"},{"family":"Chaudhary","given":"Dipesh"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/ic3i61595.2024.10829261","URL":"https://doi.org/10.1109/ic3i61595.2024.10829261","source":"crossref"},{"id":"doi:10.1109/bdcat63179.2024.00029","type":"article-journal","title":"An Explanation Technique For Yield Prediction in Smart Farming","abstract":"The utilization of artificial intelligence tools and methods in agriculture has increased over the last few years. However, farmers and agronomists are uncertain about trusting such tools and the findings of machine/deep learning model predictions. This work develops a novel eXplainable AI (XAI) technique for smart farming yield prediction that can more effectively explain prediction outcomes when compared with state-of-the-art current explainers, LIME and SHAP. We call the proposed model, which considers both attributes and time lag, the Duo Attention eXplainable Mechanism (DAXM). We have developed and tested the model with two separate farming data sets and the results of our experiments demonstrate the effectiveness of prediction features for a three-week window on both tomato and strawberry yield prediction. We show that the explanation of such features can be achieved more effectively through our proposed DAXM model while these explanations significantly differ at the 95% confidence level from those generated by LIME and SHAP. DAXM is also more aligned with expert opinion with a higher degree of agreement with expert-reported feature importance measures as compared with LIME and SHAP. The proposed XAI approach for smart farming yield prediction offers effective explanations that can enrich user adaption of the cutting-edge neural models in the domain.","author":[{"family":"Alwis","given":"Sandya"},{"family":"Ofoghi","given":"Bahadorreza"},{"family":"Zhang","given":"Yishuo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/bdcat63179.2024.00029","URL":"https://doi.org/10.1109/bdcat63179.2024.00029","source":"crossref"},{"id":"doi:10.1016/j.atech.2026.101809","type":"article-journal","title":"Computer vision-enabled smart farms for cattle herd management in open-pasture","abstract":"Virtual fencing is a promising alternative to conventional physical barriers for managing free-ranging livestock, offering flexibility, lower infrastructure costs, and potential livestock-welfare outcomes. Yet, there are significant gaps in the practical deployment of virtual fencing in open pastures. While all existing scientific and commercial systems primarily rely on GPS-equipped collars, these solutions remain limited by challenges in animal localization, behavior recognition, and adaptive boundary enforcement. Therefore, the article introduces a computer-vision (CV) framework for virtual fencing of cattle. The solution combines detection and tracking models with risk-based zone generation logic to deliver early warnings and CV-enabled boundaries for breach alerts in real-time. Both fixed cameras/UAVs are considered as potential data sources without GPS collars. Experimental evaluations in structured pasture settings using stationary cameras (with imitations related to spatial coverage, viewpoint dependence and occlusions, sensitivity to camera placement, environmental variability, and infrastructure and maintenance requirements) demonstrate reliable herd-level monitoring and accurate virtual-fence enforcement, quantified using detection precision/recall and tracking-relevant metrics including tracking consistency, count stability, crossing-event accuracy, and zone dwell time. Within the limits of controlled tests across three scenarios, the evaluation of eight quantitative and two qualitative Key Performance Indicators (KPIs) showed that as a proof-of-concept, The proposed system enables key digital-twin capabilities for open pasture environments through real-time computer vision, enabling live-stream monitoring, virtual boundary enforcement, and extensions to vegetation assessment and emergency management applications such as wildfire situational awareness and environmental crisis management.","author":[{"family":"Ardebili","given":"Ali"},{"family":"Boscolo","given":"Marco"},{"family":"Padoano","given":"Elio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.atech.2026.101809","URL":"https://doi.org/10.1016/j.atech.2026.101809","source":"crossref"},{"id":"doi:10.58532/nbennureefa","type":"article-journal","title":"Eco-Efficient Farming Approaches","abstract":"Agriculture today stands at a pivotal crossroads where rising food demands intersect with the urgent need to conserve natural resources and protect the environment. Achieving sustainable productivity requires a fundamental shift from input-intensive farming to approaches that maximize efficiency, minimize ecological footprints, and enhance system resilience. This edited volume, Eco-Efficient Farming Approaches: Innovations for Sustainable Productivity and Resource Optimization, has been conceived to address this global necessity. The chapters compiled in this book represent contributions from researchers, academicians, and experts across diverse agricultural disciplines. Their research and insights provide an integrative understanding of how precision farming, conservation technologies, advanced nutrient and water management, and digital tools can enhance eco-efficiency at the field level. Readers will find the content both conceptually strong and practically relevant, reflecting current and emerging trends shaping modern agriculture. This book is intended for students, researchers, scientists, extension professionals, and policymakers working in agronomy, soil science, water management, climate-smart agriculture, and resource conservation. We hope that the evidence-based discussions and case examples presented herein will inspire innovative thinking and foster wider adoption of eco-efficient practices for a sustainable agricultural future.","author":[{"family":"Dwivedi","given":"Abhishek"},{"family":"Singh","given":"Dr"},{"family":"Kumar","given":"Dr"},{"family":"Pachauri","given":"Dr"},{"family":"Nand","given":"Brimha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58532/nbennureefa","URL":"https://doi.org/10.58532/nbennureefa","source":"crossref"},{"id":"doi:10.35410/ijaeb.2026.1055","type":"article-journal","title":"CLIMATE-SMART AGRICULTURE IN NIGERIA: A REVIEW OF PRECISION FARMING TECHNOLOGIES FOR FOOD SECURITY","abstract":"Nigeria faces acute challenges to agricultural productivity arising from intensifying climate variability, land degradation, and a rapidly growing population projected to exceed 400 million by 2050. Climate-smart agriculture (CSA), underpinned by precision farming technologies, offers a transformative pathway to sustaining food security while reducing greenhouse gas emissions and building resilience. This review synthesises current evidence on the adoption, performance, and barriers of precision farming tools, including remote sensing, unmanned aerial vehicles (UAVs), Internet of Things (IoT) sensors, variable rate technology (VRT), and artificial intelligence (AI), within the Nigerian agricultural context. A structured narrative review of peer-reviewed literature published between 2020 and 2025 was conducted, drawing on studies indexed in PubMed, Scopus, Web of Science, and AGRIS. Findings reveal that precision farming adoption in Nigeria remains low-to-nascent, constrained by high equipment costs, inadequate rural infrastructure, limited digital literacy, and policy implementation gaps. Nevertheless, emerging public–private partnerships, the National Agricultural Technology and Innovation Policy (NATIP) 2022–2027, and mobile digital advisory services present credible pathways for accelerated uptake. The review underscores that integrating precision technologies into existing smallholder farming systems, aligned with Nigeria's Nationally Determined Contributions, can simultaneously address food insecurity and climate change mitigation. Future research should prioritise context-specific, lowcost precision tools, farmer co-design approaches, and robust policy financing mechanisms to operationalise CSA at scale across Nigeria's diverse agroecological zones.","author":[{"family":"Oladosu","given":"Micheal"},{"family":"Abah","given":"Moses"},{"family":"Onuorah","given":"Uju"},{"family":"Ademola","given":"Oluwafisayo"},{"family":"Ekeleme","given":"Felicia"},{"family":"Oladosu","given":"Olaide"},{"family":"Bamidele","given":"Oladapo"},{"family":"Ekele","given":"Angel"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35410/ijaeb.2026.1055","URL":"https://doi.org/10.35410/ijaeb.2026.1055","source":"crossref"},{"id":"doi:10.1201/9781003532521-49","type":"article-journal","title":"Review paper on smart farming using IOT","abstract":"Cultivating utilizing IOT (Web of Things) innovation has arisen as a progressive way to deal with present day horticulture, offering ranchers exceptional capacities to screen, make do, and enhance their operations. This paper gives an overall thought of the idea of cultivating with IOT, featuring its key standards, applications, and benefits. The coordination of IOT into cultivating rehearses include the work of sensors, actuators, and other associated gadgets during cultivating field to collect genuine occurrence data on a combination of boundary like soil dampness, supplement levels, natural circumstances, and harvest wellbeing. This information is then communicated to incorporated frameworks where it is dissected and used to go with informed choices regarding water system, preparation, bother control, and other basic parts of cultivating.","author":[{"family":"Shaina"},{"family":"Munjal","given":"Rohit"},{"family":"Devi","given":"Renu"},{"family":"Chawla","given":"Sachin"},{"family":"Sharma","given":"Himanshu"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003532521-49","URL":"https://doi.org/10.1201/9781003532521-49","source":"crossref"},{"id":"doi:10.1109/icrai62391.2024.10894254","type":"article-journal","title":"A Soft Robotics Approach to Prosthetic Hands: Integrating 3D Printing Techniques and Embedded Vision","abstract":"The development of soft robotics hand has progressed significantly, evolving from a pneumatically actuated solution for industrial applications to a lightweight and easy-to-manufacture solution for 3d printed prosthetic hands. However, existing soft prosthetic hands often lack anthropomorphic appearances, intrinsic structural integrity, and sufficient feedback to the amputees, leading to a high rate of abandonment of prosthetic hands. This paper presents a design of a 3d printed soft robotic hand based on a monolithic design with an embedded camera and anthropomorphic appearance. The hand is fabricated using the flexible 3d printable material TPU-95 with an embedded Raspberry Pie Cam module for increased functionality. The hand utilizes a cable-driven mechanism integrated with five rotary actuators capable of multiple grasp patterns. Our design weighs around 246 grams with all the electronic components embedded inside the hand. This paper discusses the mechanical design, 3d printing methodology for the fabrication of the fingers, actuation mechanisms, and the results of the soft prosthetic hand's performance.","author":[{"family":"Khan","given":"Wajdan"},{"family":"Farooq","given":"Umar"},{"family":"Zeb","given":"Ayesha"},{"family":"Awais","given":"Izna"},{"family":"Tariq","given":"Muhammad"},{"family":"Tiwana","given":"Mohsin"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icrai62391.2024.10894254","URL":"https://doi.org/10.1109/icrai62391.2024.10894254","source":"crossref"},{"id":"doi:10.21872/2024iise_7938","type":"article-journal","title":"Understanding DEI Initiatives and Performance Metrics in Food Bank Operations","abstract":"Food banks provide services and food assistance to those facing food insecurity, a challenge that can affect families and individuals from various backgrounds and communities. Diversity, equity, and inclusion (DEI) are principal factors in food bank operations. This study focuses on diversity as measured by client ethnicities and the rurality of the counties served by the food banks. Over 44 food banks were interviewed to understand their operations. Key performance indicator (KPI) metrics in each organization were identified and classified as Community Focused (CF), involving tailored services based on community needs, and Organizational Efficiency Focused (OE), involving processes and strategies to increase output and minimize resources. A clustering analysis was conducted to group these organizations depending on the percentage of rural counties served by the food banks and their respective zscore based on diversity index, so four clusters (tiers) were created (Tier 1 are the least diverse and the most rural, while those in the fourth tier are the most diverse and the least rural). The KPIs in each tier organization were examined and results suggest that organizations in Tier 1 use more OE KPI metrics whereas those in Tier 4 use a more balanced combination of CF and OE metrics. This research provides hunger-relief organizations insights to adopt practices that acknowledge, accommodate, and celebrate the diverse needs and characteristics of the neighborhood they serve.","author":[{"family":"Hamilton","given":"Mikaya"},{"family":"Jiang","given":"Steven"},{"family":"Davis","given":"Lauren"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21872/2024iise_7938","URL":"https://doi.org/10.21872/2024iise_7938","source":"crossref"},{"id":"doi:10.1109/robio64047.2024.10907753","type":"article-journal","title":"Adaptive Simulation-Trained Cloth Manipulation Control with Human Guidance for Real-World Robotics Tasks","abstract":"This study presents a comprehensive system integrating expert-built simulations with human-guided real-world control for robotic tasks. Due to potential spatial constraints in actual factory environments, errors during workspace assembly, and the challenges in measuring anisotropic parameters of deformable fabrics, we aim to adapt robotic arms to real-world conditions through direct human guidance, enabling the transfer from simulation control to real-world operation. Key contributions include (1) a normalizing method to bridge the gap between simulation and reality, (2) the employment of force-position control, and (3) the use of human guidance for model environment updates. Experiments demonstrate the system's effectiveness in bridging the gap between simulation and reality and enhancing the applicability of simulation-trained models to complex, real-world scenarios.","author":[{"family":"Zhang","given":"Yukuan"},{"family":"Chen","given":"Dayuan"},{"family":"Barceló","given":"Alberto"},{"family":"Luces","given":"Jose"},{"family":"Hirata","given":"Yasuhisa"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/robio64047.2024.10907753","URL":"https://doi.org/10.1109/robio64047.2024.10907753","source":"crossref"},{"id":"doi:10.2139/ssrn.7215299","type":"manuscript","title":"Enablers of Agriculture 4.0: A Comprehensive Survey of Machine Learning, Robotics, and Emerging Technologies Driving the Next Agricultural Paradigm","abstract":"Agriculture 4.0 is usually presented through its most visible products: autonomous tractors, weed-spotting drones, and language-driven advisory apps. Field deployment has proven harder than these demonstrations suggest. Models that report accuracies above 99 % on curated leaf images frequently lose 25-40 percentage points when rerun on smartphone photographs from a working farm; reinforcement-learning irrigation controllers that save 30 % water in simulation routinely over-or underwater clay and sand soils that violate the simulator's homogeneity assumptions; and the machine-learning stack actually deployed across hundreds of millions of hectares remains dominated by gradient-boosted trees rather than the transformer architectures dominating the literature. This survey is organised around this gap between reported and deployed performance. We review the four agricultural revolutions, describe the hardware, connectivity, data, and intelligence layers of the modern stack, and map eleven model families onto eight application domains that cover most field-level decisions. Two analytical sections address deployment directly: one compares model families on the criteria that govern model choice in practice (latency, edge-feasibility, data efficiency, interpretability), and one documents the lab-to-field failure modes that benchmark scores hide. We close with seven research frontiers (geometric deep learning, agricultural foundation models, digital twins, agentic systems, continual learning, edge AI, federated data) and seven deployment barriers (domain shift, calibration, interpretability, smallholder cost, regulation, sovereignty, robustness). The survey is aimed at two readers: researchers entering the area who want a reliable map of what works, and practitioners who need to know where reported numbers should be treated with caution.","author":[{"family":"Kethineni","given":"Kiran"},{"family":"Kanukuntla","given":"Rishi"},{"family":"Mohanty","given":"Saraju"},{"family":"Kougianos","given":"Elias"}],"issued":{"date-parts":[[2026]]},"DOI":"10.2139/ssrn.7215299","URL":"https://doi.org/10.2139/ssrn.7215299","source":"crossref"},{"id":"doi:10.33045/fgr.v40.2024.28","type":"article-journal","title":"PHYSICOCHEMICAL QUALITY PROPERTIES OF PEACH (PRUNUS PERSICA L.) VARIETIES AT HOLETA, ETHIOPIA","abstract":"Holeta has different peach fruit varieties that can be used for various purposes. However, their fruit quality characteristics were not fully identified. Studies have indicated that the physicochemical qualities of peach fruits are influenced by a number of factors, with the varietal factor being one of the most important. Limited information regarding the factors that affect these qualities is available in the country, specifically at Holeta. Therefore, this study was initiated to evaluate the physicochemical quality properties of peach fruit varieties. Their physical quality traits, such as fruit length, fruit diameter, fruit shape index, and average fruit weight, as well as chemical quality parameters, such as TSS, specific gravity, TA, ripening index, ascorbic acid content, and pH, were evaluated. The results revealed that both physical and chemical quality parameters were significantly affected by varietal factors. Among cultivars, 'Bonny Gold' had the longest fruit length, and 'Florida Down' had the largest fruit diameter. As far as average fruit weight is concerned, 88-18 W had the highest weight with 111.98 g, while Transvalia had the highest TSS and specific gravity. However, the 'Summer Sun' and 9A-35C varieties had the highest TA and ripening index, respectively. Thus, the physicochemical quality properties of the fruit were highly altered with peach varieties.","author":[{"family":"Tajebe","given":"Mosie"},{"family":"Habtam","given":"Setu"},{"family":"Getaneh","given":"Seleshi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33045/fgr.v40.2024.28","URL":"https://doi.org/10.33045/fgr.v40.2024.28","source":"crossref"},{"id":"doi:10.1186/s12870-025-06083-y","type":"article-journal","title":"Exogenous diethyl aminoethyl hexanoate alleviates the damage caused by low-temperature stress in Phaseolus vulgaris L. seedlings through photosynthetic and antioxidant systems","abstract":"Background Phaseolus vulgaris is a warm-season crop sensitive to low temperatures, which can adversely affect its growth, yield, and market value. Exogenous growth regulators, such as diethyl aminoethyl hexanoate (DA-6), have shown potential in alleviating stress caused by adverse environmental conditions. However, the effects that DA-6 has on P. vulgaris plants subjected to low-temperature stress are not well understood. This study aimed to investigate the impact DA-6 has on the growth, photosynthesis, antioxidant system, and gene expression in cold-tolerant (YJ009763) and cold-sensitive (Baibulao) P. vulgaris seedlings under low-temperature stress. Results To simulate low-temperature stress, P. vulgaris seedlings were exposed to 5 °C, and 25 mg/L DA-6 solution applied to their leaves. This study revealed that DA-6 significantly enhanced the growth and photosynthetic performance of P. vulgaris seedlings under low-temperature stress. Specifically, DA-6 increased chlorophyll content and photosynthetic rates, reducing stomatal limitation and enhancing carbon assimilation. It also improved the photosynthetic efficiency by boosting electron transport in the reaction center. The antioxidant enzyme activities of superoxide dismutase (SOD), peroxidase (POD), and catalase (CAT) were markedly increased following DA-6 treatment. After 24 h of low-temperature stress, the cold-tolerant seedlings showed a 68.95% increase in POD activity, whereas the cold-sensitive seedlings displayed a 160.63% increase in SOD activity and an 85.56% increase in CAT activity. In addition, DA-6 significantly reduced the production rate of superoxide anion radical generation, with a 25.24% reduction in cold-tolerant seedlings and a 49.38% reduction in cold-sensitive seedlings. Under low-temperature stress, exogenous DA-6 could upregulate the relative expression of antioxidant enzyme-related genes, such as PvSOD and PvAPX. DA-6 also promoted the expression of key antioxidant genes, including PvMDHAR and PvDHAR2, which accelerated the ascorbate-glutathione cycle and mitigated oxidative stress. Conclusion Exogenous application of DA-6 effectively alleviates low-temperature stress in P. vulgaris by enhancing photosynthetic capacity and regulating the antioxidant defense system. Cold-tolerant varieties exhibited a stronger response to DA-6, demonstrating a greater ability to withstand cold stress. These findings suggest that DA-6 treatment could serve as a promising approach for improving the resilience of P. vulgaris to low temperatures.","author":[{"family":"Bai","given":"Yu"},{"family":"Dai","given":"Qiya"},{"family":"He","given":"Yanheng"},{"family":"Yan","given":"Li"},{"family":"Niu","given":"Jianpo"},{"family":"Wang","given":"Xuan"},{"family":"Xie","given":"Yongdong"},{"family":"Yu","given":"Xuena"},{"family":"Tang","given":"Wen"},{"family":"Li","given":"Huanxiu"},{"family":"Huang","given":"Zhi"},{"family":"Sun","given":"Bo"},{"family":"Sun","given":"Guochao"},{"family":"Wang","given":"Xun"},{"family":"Tang","given":"Yi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1186/s12870-025-06083-y","URL":"https://doi.org/10.1186/s12870-025-06083-y","source":"crossref"},{"id":"doi:10.1109/sbr/wre63066.2024.10837863","type":"article-journal","title":"The Pedagogical Use of the Online Digital Weather Station in Teaching Mathematics to First-Year Elementary School Students","abstract":"This article describes the didactic-pedagogical process of the use of the online digital weather station as a didactic-pedagogical tool in teaching mathematics to students in the 1st years A and B of elementary school at Escola Municipal Cedro Alto in the 2023 school year. The objective of this article is to socialize the effort and dedication to carry out the activities necessary to develop skills by the National Common Curricular Base, and a search to introduce Computational Thinking and Digital Culture into children's lives. The pedagogical use of the weather station demonstrated positive results, with students actively engaging in learning and developing essential skills. This experience highlighted the potential for expanding similar initiatives to enhance innovative education in other knowledge areas.","author":[{"family":"Santos","given":"Marinalva"},{"family":"Pedroso","given":"Rogerio"},{"family":"Cavichioli","given":"Amanda"},{"family":"Barni","given":"Catia"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre63066.2024.10837863","URL":"https://doi.org/10.1109/sbr/wre63066.2024.10837863","source":"crossref"},{"id":"doi:10.1109/sbr/wre63066.2024.10837923","type":"article-journal","title":"Dynamic Safety Zones for Industrial Robots: A Fuzzy Logic and Computer Vision Approach","abstract":"This research focuses on integrating a robotic manipulator in shared workspaces within the framework of Indus-try 4.0 for Human-Robot Collaboration (HRC). The primary objective is to implement a safe strategy by employing a fuzzy-speed controller to enhance the mobile robot's movements near machinery. This strategy utilizes two cameras: one mounted on the ceiling of the industrial environment and another on the robot itself, called an eye-in-hand camera. The You Only Look Once Version 3 (YOLOv3) Convolutional Neural Network (CNN) detects the obstacles in the environment and identifies the target objects. Simulations were conducted using Gazebo software along with a Robot Operating System (ROS) to determine the effectiveness of the proposed approach in ensuring safe robot movements while accurately reaching target positions by dynamically adjusting velocity within the defined danger zone.","author":[{"family":"Sousa","given":"Lucas"},{"family":"Schettino","given":"Vinícius"},{"family":"Santos","given":"Murillo"},{"family":"Santos","given":"Tatiana"},{"family":"Haddad","given":"Diego"},{"family":"Pinto","given":"Milena"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre63066.2024.10837923","URL":"https://doi.org/10.1109/sbr/wre63066.2024.10837923","source":"crossref"},{"id":"doi:10.1109/icdscnc62492.2024.10939551","type":"article-journal","title":"Smart Poultry Farming: CNN-Driven Environmental Optimization for Sustainability","abstract":"The Internet of Things (IoT) has revolutionized the poultry farming industry by enabling real-time monitoring and optimization of environmental parameters crucial for bird health and productivity. However, traditional algorithms such as Support Vector Machines (SVMs), Fuzzy logic are limited by high computational costs, inefficiency with large datasets, and vulnerability to overfitting in noisy data. To overcome these challenges, a novel IoT-based framework has been developed, integrating Convolutional Neural Networks (CNNs) with IoT sensors to monitor and optimize temperature, humidity, and air quality in poultry farms. It excels in learning from data, handling non-linear relationships, adapting to changing conditions, and controlling multiple parameters in real-time, making accurate predictions and adjustments through pattern recognition and precise modeling. This system leverages advanced image processing and deep learning techniques to provide real-time data analysis and predictive maintenance, ensuring optimal conditions for poultry health and productivity. By harnessing the power of IoT and CNNs, this innovative approach enables conscientious and efficient farming practices, tailored to meet the intensified demands of the global poultry market.","author":[{"family":"Reddy","given":"PCP"},{"family":"Prabaharan","given":"S"},{"family":"Rajaram","given":"P"},{"family":"Ebenezer","given":"SS"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icdscnc62492.2024.10939551","URL":"https://doi.org/10.1109/icdscnc62492.2024.10939551","source":"crossref"},{"id":"doi:10.1109/sbr/wre63066.2024.10837805","type":"article-journal","title":"Educational Assistant Robot for Strengthening Children's Learning Using IoT","abstract":"Digital Information and Communication Technolo-gies (DICTs) have increasingly become part of people's daily lives, whether they are children, adults, or the elderly. However, children's unfettered and increasingly early access to these technologies has been the subject of numerous studies aimed at measuring the impacts of their usage. In parallel, another issue arises: the influence of technology on education. When using technology, children often neglect their studies due to the distractions that technological devices (such as cell phones, computers, or tablets) can cause. In light of this, and aiming to reconcile technology with education, this work seeks to present the development of an intelligent educational assistant robot using the Internet of Things (IoT), with the goal of assisting children in the educational process through active learning approaches. Thus, upon completing the development of the robot, it was possible to verify its full functionality by engaging in interactions, asking questions, and providing details on distance and temperature values.","author":[{"family":"Mesquita","given":"Iago"},{"family":"Nunes","given":"Rhuan"},{"family":"Lima","given":"Kattiely"},{"family":"Salustiano","given":"Acácio"},{"family":"Silva","given":"Wendley"},{"family":"Júnior","given":"Iális"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre63066.2024.10837805","URL":"https://doi.org/10.1109/sbr/wre63066.2024.10837805","source":"crossref"},{"id":"doi:10.1109/lra.2026.3688054","type":"article-journal","title":"Differentiable Inverse Graphics for Zero-Shot Scene Reconstruction and Robot Grasping","abstract":"Operating effectively in novel real-world environments requires robotic systems to estimate and interact with previously unseen objects. Current state-of-the-art models address this challenge by using large amounts of training data and test-time samples to build black-box scene representations. In this work, we introduce a differentiable neuro-graphics model that combines neural foundation models with physics-based differentiable rendering to perform zero-shot scene reconstruction and robot grasping without relying on any additional 3D data or test-time samples. Our model solves a series of constrained optimization problems to estimate physically consistent scene parameters, such as meshes, lighting conditions, material properties, and 6D poses of previously unseen objects from a single RGBD image and bounding boxes. We evaluated our approach on standard model-free few-shot benchmarks and demonstrated that it outperforms existing algorithms for model-free few-shot pose estimation. Furthermore, we validated the accuracy of our scene reconstructions by applying our algorithm to a zero-shot grasping task. By enabling zero-shot, physically-consistent scene reconstruction and grasping without reliance on extensive datasets or test-time sampling, our approach offers a pathway toward more data efficient, interpretable and generalizable robot autonomy in novel environments. Code is available at oarriaga.com.","author":[{"family":"Arriaga","given":"Octavio"},{"family":"Sharma","given":"Proneet"},{"family":"Guo","given":"Jichen"},{"family":"Otto","given":"Marc"},{"family":"Kadwe","given":"Siddhant"},{"family":"Adam","given":"Rebecca"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/lra.2026.3688054","URL":"https://doi.org/10.1109/lra.2026.3688054","source":"crossref"},{"id":"doi:10.51470/jpb.2024.3.2.23","type":"article-journal","title":"Investigating Optimum Seed Rate for Maximum Productivity Potential of Sesame (Sesamumindicum L.)  in Tigray, Ethiopia","abstract":"Sesame is a very important and healthy oil crop. Seed rate (Plant density) is a prerequisite for obtaining higher yield. Decision on the optimum seed rate for sole cropping of sesame using widely cultivated variety in specific agroecology is essential. For two consecutive rainy seasons, a field experiment using RCBD was carried out in the Humera and Dansha areas of Tigray, Ethiopia, with nine broadcasting seed rate treatments ranging from 1 kg ha-1 to 9 kg ha-1. Grain yield, plant height, number of pods per plant, length of capsule bearing zone, number of branches per plant, days of 50% flowering, days of 90% maturity, and agronomic data were collected to establish the ideal seed rate. Analysis of variance showed, that 3 Kg ha-1 is the optimism seed rate producing the highest yield (700.6 kg ha-1).","author":[{"family":"Weldearegay","given":"Dawit"},{"family":"Amare","given":"Mizan"},{"family":"Baraki","given":"Fiseha"},{"family":"Gebregergis","given":"Zenawi"}],"issued":{"date-parts":[[2025]]},"DOI":"10.51470/jpb.2024.3.2.23","URL":"https://doi.org/10.51470/jpb.2024.3.2.23","source":"crossref"},{"id":"doi:10.1201/9781003562627-11","type":"article-journal","title":"Agricultural entrepreneurship in operational management","abstract":"Agricultural entrepreneurship is increasingly being recognized as a transformative approach to reposition farming from a subsistence activity into a dynamic, innovation-driven, and market-oriented enterprise. Rooted in strategic, financial, marketing, and human resource management principles, it integrates innovation, value chain development, digital technologies, and sustainability practices to create value across the agri-food system. Supported by institutional frameworks, policy interventions, and capacity-building programs, agricultural entrepreneurship fosters resilience, competitiveness, and inclusivity, particularly in regions with high-value commodities such as Jammu and Kashmir. Despite challenges of finance, infrastructure, climate variability, and fragmented policies, the entrepreneurial approach offers pathways for rural transformation by generating employment, reducing risks, and enhancing the global competitiveness of farm products.","author":[{"family":"Rashid","given":"Mudasir"},{"family":"Sultan","given":"Abid"},{"family":"Shaheen","given":"Farhet"},{"family":"Gul","given":"Aqib"},{"family":"Majid","given":"Masroor"},{"family":"Majeed","given":"Uzma"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003562627-11","URL":"https://doi.org/10.1201/9781003562627-11","source":"crossref"},{"id":"doi:10.1109/robio64047.2024.10907617","type":"article-journal","title":"Multi-DoF Continuous Estimation for Wrist Torques Using Convolutional Neural Network","abstract":"Using surface electromyography (sEMG) signals for simultaneous and proportional control (SPC) is appealing for natural control in human-machine interaction (HMI). Introducing spatial information across sEMG channels in the decoding process provides a more complete approach than methods that focus only on time and frequency domain features. In this article, we proposed an sEMG-based model for thesi-multaneous estimation of two degree-of-freedom (DoF) wrist torques, namely, Pro-Sup and Fle-Ext. Specifically, the 8 × 24 channels sEMG signals were transformed into images, which further served as inputs in a 29-layer convolutional neural network to estimate multi-DoF wrist torques. To prove the superiority of the CNN-based model, comparisons with other regression methods were performed on eight healthy subjects and two amputees in terms of the determination coefficient (R2) and normalized root mean square error (nRMSE). The results demonstrated that the CNN-based model (CNN-WAF) outperformed two conventional regression methods on estimation accuracy (R2: 0.851 ± 0.024 for Pro-Sup and 0.863 ± 0.016 for Fle-Ext; nRMSE: 6.933% ± 0.872% for Pro-Sup and 6.830% ± 0.856% for Fle-Ext). The average filtering in data preprocessing greatly improves (p < 0.05) the smoothness and performance of the estimation (CNN-WOAF: R2: 0.837 ± 0.015 for Pro-Sup and 0.853 ± 0.021 for Fle-Ext; nRMSE: 7.487% ± 0.870% for Pro-Sup and 7.370% ± 0.866% for Fle-Ext). Overall, the outcomes of this study provide meaningful methods to utilize spatiotemporal information from sEMG signals for SPC in practical applications.","author":[{"family":"Fang","given":"Yun"},{"family":"Yu","given":"Yang"},{"family":"Guo","given":"Weichao"},{"family":"Sheng","given":"Xinjun"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/robio64047.2024.10907617","URL":"https://doi.org/10.1109/robio64047.2024.10907617","source":"crossref"},{"id":"doi:10.1109/icicyta64807.2024.10913107","type":"article-journal","title":"Smart CRP Using Pega Robotics: Enhancing Customer Relationship Platforms with Robotics Process Automation","abstract":"In today's competitive business landscape, organizations are under pressure to improve operational efficiency and enhance customer satisfaction. This paper introduces SMART CRP, a model that integrates Pega Robotics Process Automation (RPA) with Customer Relationship Platforms (CRP) to streamline processes and address inefficiencies. SMART CRP leverages Pega Robotics to automate repetitive tasks within CRP systems, achieving a 30% reduction in query processing time, a 15% decrease in data entry errors, and a 20% reduction in operational costs. The paper outlines the architecture and deployment strategy of SMART CRP, focusing on key automation areas such as data validation, query resolution, and feedback management. Through a phased implementation approach, including pilot testing and full-scale deployment, the model demonstrates how integrating RPA with CRP systems can significantly improve both operational metrics and customer satisfaction. The paper also addresses the challenges of integrating RPA with legacy CRP systems, proposing solutions such as API development and phased data migration to ensure seamless adoption. The findings underscore the potential of SMART CRP to transform CRP systems, offering insights for organizations looking to enhance efficiency and customer retention through automation. Future research avenues include expanding the model's application across industries and incorporating machine learning for predictive customer engagement.","author":[{"family":"Pandy","given":"Gokul"},{"family":"Banarse","given":"Amey"},{"family":"Jayaram","given":"Vivekananda"},{"family":"Ganeeb","given":"Koushik"},{"family":"Gupta","given":"Pankaj"},{"family":"Krishnappa","given":"Manjunatha"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icicyta64807.2024.10913107","URL":"https://doi.org/10.1109/icicyta64807.2024.10913107","source":"crossref"},{"id":"doi:10.1109/icrm66809.2025.11349109","type":"article-journal","title":"Agricultural Robots and Implementation of Weed Detection by Machine Learning","abstract":"Weed management in agricultural farms is one of the most crucial activities that the farmers should do to get a good yield of crops. This paper covers the implementation of a model robot that can detect the weeds inside farmland and display the coordinates of the weeds; this can be achieved by introducing a machine learning technique to the system for categorizing the weeds and crops from farmland. The system utilizes the TensorFlow library to autonomously learn distinctive features of weeds and crops, enabling it to differentiate between the two categories for accurate detection. To achieve this, the system was trained using a carefully created dataset, allowing the system to perceive the crucial features associated with weeds and crops. Once the system identifies a weed, it can autonomously adjust the PWM (Pulse Width Modulation) to drive the robot's motors to move towards the weed. Furthermore, it can independently determine and fetch the precise central coordinates of the identified weed.","author":[{"family":"Kumar","given":"SS"},{"family":"Haris","given":"R"},{"family":"Govindaraju","given":"Murugaraj"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icrm66809.2025.11349109","URL":"https://doi.org/10.1109/icrm66809.2025.11349109","source":"crossref"},{"id":"doi:10.58532/nbennursafpb1p1c3","type":"article-journal","title":"INTERNET OF THINGS, AGRICULTURAL SENSORS, AND ROBOTICS","abstract":"The integration of digital technologies into agriculture is transforming farm management by enabling real-time monitoring, automation, and data-driven decision-making. The Internet of Things (IoT), agricultural sensors, and robotics represent key technological pillars of smart agriculture. IoT enables connectivity between sensors, devices, and data platforms, facilitating the continuous monitoring of crop, soil, and environmental parameters. Agricultural sensors provide accurate, high-resolution data essential for precision farming, while robotics and autonomous machinery enhance operational efficiency and reduce dependence on manual labor. The integration of these technologies supports sustainable agricultural production by optimizing resource utilization, improving crop productivity, and minimizing environmental impacts. This chapter discusses the concepts, components, technological advancements, applications, challenges, and future prospects of IoT, agricultural sensors, and robotics in modern agriculture.","author":[{"family":"Dash","given":"Sukanta"},{"family":"Dash","given":"Sachikanta"},{"family":"Verma","given":"Med"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58532/nbennursafpb1p1c3","URL":"https://doi.org/10.58532/nbennursafpb1p1c3","source":"crossref"},{"id":"doi:10.21608/djas.2024.406745","type":"article-journal","title":"Development and Performance Evaluation of the Double Ventilated Solar Dryer for Drying some Agricultural Products","abstract":"The experimental work was carried out in the summer season of 2023 at Agricultural and Bio-systems Engineering Department, Faculty of Agriculture, Damietta University, Egypt (Latitude 31°25′35″ North, Longitude 31°39′03″ East) to manufacture and develop the double ventilated solar dryer for drying chill, lemon and tomato. The manufacture dryer consists of the solar collector which attached with the drying chamber through 3 isolated pipes. All ambient and solar dryer conditions were measured using a locally calibrated solar radiation, temperature and relative humidity data loggers with thermocouples, and also a Weather Total Station. The maximum solar radiation for the dryer chamber, collector and ambient were 1000, 1000 and 1100 W/m2, respectively. The maximum temperatures for the entrance; upper, middle, lower trays; exit; and collector were 41, 64, 62.5, 61.79, 42.29, and 83.9°C, respectively. The minimum air relative humidity at entrance and exit slots were 11 and 13%, during the day hour of 2pm, while the maximum air relative humidity at entrance and exit slots were 71 and 65%, during the day hour of 9am. The decrease of moisture content ratio were decreased from 85.4, 86.6 and 88.2% fresh product to 10.46, 13.52 and 8.83% dry product in total drying time of 15, 21 and 19h for chilli, lemon and tomato, respectively in the upper tray and air suction speed of 0.6 m/s. The drying rate were decreased after the first hour of drying from 9.37, 8.46 and 8.32% to 5, 3.48 and 4.18% during total drying time of 15, 21 and 19h for chilli, lemon and tomato, respectively in the upper tray and air suction speed of 0.6 m/s. The higher values of solar collector efficiency (C) were 74.27, 75.74 and 73.09% at the day hour of (1pm) during three drying days of 29, 30 and 31/8/2023, respectively and 1.6 m/s air suction speed. The lower values of (S.R.U.E) were 46.35, 46.35 and 51.90% around the day hours between (2 and 3pm) at three drying days of 26, 27 and 28/8/2023, respectively and 0.6 m/s air suction speed. The dried amount of chilli halves, lemon slices and tomato slices for each upper tray were 32.40, 28.62 and 25.59 kg/month; 23.58, 23.58 and 20.61 kg/month and 21.33, 25.29 and 16.92 kg/month at different air suction speeds of 0.6, 1.1 and 1.6 m/s, respectively. The solar drying cost of chilli halves, lemon slices and tomato slices for each upper tray were 10.28, 11.65 and 13.03 L.E/kg.month; 14.14, 14.14 and 16.17 L.E/kg.month and 15.63, 13.18 and 19.70 L.E/kg.month at different air suction speeds of 0.6, 1.1 and 1.6 m/s, respectively. The net present worth of total cash income from drying of chilli, lemon and tomato under solar dryer was found to be 5250 L.E. The benefit cost of chilli, lemon and tomato in solar dryer was found to be 17025 L.E. So, the payback period for drying of chilli, lemon and tomato in solar dryer was found to be 98 days or (3 months and 8 days).","author":[{"family":"El-Sharabasy","given":"Moheb"},{"family":"El-Shiekha","given":"Ahmad"},{"family":"Abouryaq","given":"Badruldeen"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21608/djas.2024.406745","URL":"https://doi.org/10.21608/djas.2024.406745","source":"crossref"},{"id":"doi:10.21608/djas.2024.406871","type":"article-journal","title":"The Economic Impact of Good Agricultural Practices on Rice Production in Damietta Governorate","abstract":"The research mainly aimed to measure the impact of good agricultural practices on rice production inDamietta Governorate, To achieve this goal, the research relied on primary data from a random sample of ricefarmers for the 2021/2022 agricultural season, Descriptive and quantitative statistical analysis methods wereused to analyze both secondary and primary data, The research examined the current situation of productivityindicators in Egypt and Damietta Governorate, The results showed that there is a statistically significant directrelationship between the quantity produced from the rice crop and the quantity of seeds x1, The amount of humanlabor is x2, and the amount of phosphate fertilizer is x5, By estimating the production elasticity of the mostimportant factors affecting the amount of rice crop production, it was found that the sample farmers work in lightof capacity savings, By measuring the combined effect of the biological practices of the varieties using formalvariables, it became clear that the highest productive variety was the Giza 178 variety, with an aggregate valueestimated at approximately 3,539 tons/acre, in first place with a record number of approximately 109.57%, followedby Sakha 101 and Sakha 104, with aggregate values estimated at approximately 3,230, 3,088 tons/acre.acres, with a record number of about 100% and 95.60% for each of them, in order from second to third place. Itwas also shown that there was a positive effect of both biological cultivar practices, laser straightening, and improvedseeds on the economic indicators of the rice crop in the study sample, It was highest in the Giza 178 variety,followed by the Sakha 101 variety, then the Sakha 104 variety. By estimating the effect of shocks in the variablesoccurring in good agricultural practices on the productivity of the rice crop, the positive impact of the useof seeds, human labor, mechanical labor, and phosphate fertilizers was revealed, while A relatively limited positiveeffect was found in the case of the use of nitrogen fertilizers, and the effect was not proven in the case ofanimal work due to the expansion of the use of agricultural mechanization, The study recommends working tospread the positives of the use of biological practices for rice varieties, and their role in raising acreage productivity,and expanding the use of laser leveling technology, While working to develop and increase the number ofagricultural mechanization units in the governorate, and expanding the use of improved seeds while providingthem at reasonable prices for farmers.","author":[{"family":"El-Enein","given":"Fawzy"},{"family":"Helal","given":"A"},{"family":"El-Salam","given":"Azza"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21608/djas.2024.406871","URL":"https://doi.org/10.21608/djas.2024.406871","source":"crossref"},{"id":"doi:10.3390/robotics14110152","type":"article-journal","title":"Development of an Anthropometric Soft Pneumatic Gripper with Reconfigurable Fingers for Assistive Robotics","abstract":"This study presents the development of a prototype anthropomorphic soft robotic gripper intended for applications in rehabilitation and assistive robotics, where safe and adaptive interaction with humans is required. The device consists of three elastomeric fingers, fabricated in TPU via FFF 3D printing and actuated through pneumatic soft actuators that ensure compliant contact with both biological tissue and rigid objects. A custom 3D-printed pneumatic rotary actuator enables finger reconfiguration, thereby extending the range of grasping modalities. The actuation system comprises six 2/2 solenoid valves controlled by an Arduino Uno and integrated into a dedicated pneumatic circuit. Experimental characterization demonstrated a peak grasping force exceeding 17 N on rigid targets, while functional tests in table-picking scenarios confirmed adaptability to objects of varying shapes and sizes. Owing to its anthropomorphic configuration, mechanical compliance, and ease of fabrication and control, the proposed gripper represents a versatile solution for rehabilitation-oriented devices as well as assistive robotic end-effectors in pick-and-place tasks.","author":[{"family":"Buonamici","given":"Francesco"},{"family":"Cerruti","given":"Michele"},{"family":"Torzini","given":"Lorenzo"},{"family":"Puggelli","given":"Luca"},{"family":"Volpe","given":"Yary"},{"family":"Governi","given":"Lapo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/robotics14110152","URL":"https://doi.org/10.3390/robotics14110152","source":"crossref"},{"id":"doi:10.20944/preprints202601.1638.v1","type":"manuscript","title":"Advancing Image Segmentation Techniques for Strawberry Detection in Vision-Based Agricultural Robotics","abstract":"Image segmentation is a fundamental component of vision-based agricultural robotics, enabling accurate fruit localization, disease detection, and automated harvesting. However, real-world strawberry fields present significant challenges due to irregular fruit morphology, dense foliage occlusions, variable ripeness, and strong illumination variability. Moreover, segmentation models trained on a single dataset often fail to generalize across domains, limiting their practical deployment. This paper presents a comprehensive benchmark of classical computer vision methods, convolutional neural networks, instance-based models, and transformer-based architectures across three heterogeneous public strawberry datasets: Db1 (instance segmentation), Db2 (lesion segmentation), and Db3 (semantic segmentation). A unified preprocessing and evaluation framework is adopted to ensure fair comparison using standard metrics, including Intersection-over-Union (IoU), Dice coefficient, Precision, and Recall. Extensive in-domain experiments demonstrate that deep learning models significantly outperform classical approaches, with U-Net and SegFormer achieving IoU values above 0.95 on Db1 and up to 0.83 on Db3. Cross-domain zero-shot evaluations reveal a substantial generalization gap, with U-Net suffering IoU drops of up to 100\\%, while SegFormer consistently exhibits improved robustness and reduced cross-domain degradation across most transfer scenarios. To our knowledge, these results establish the first systematic multi-dataset benchmark for strawberry segmentation under domain shift, highlighting the importance of transformer-based architectures for robust agricultural perception and providing practical insights for real-world robotic deployment.","author":[{"family":"Imran","given":"Faisal"},{"family":"Albarelli","given":"Andrea"},{"family":"Torsello","given":"Andrea"},{"family":"Gasparetto","given":"Andrea"},{"family":"Pistellato","given":"Mara"}],"issued":{"date-parts":[[2026]]},"DOI":"10.20944/preprints202601.1638.v1","URL":"https://doi.org/10.20944/preprints202601.1638.v1","source":"europepmc"},{"id":"doi:10.1109/icscsa64454.2024.00110","type":"article-journal","title":"Smart Farming: IoT-Driven Crop Yield Prediction for Rice Cultivation","abstract":"In recent years, the agricultural sector has faced challenges in achieving optimal crop yields due to complex environmental factors and limited access to data-driven decision-making tools. An innovative IoT-based approach to predict crop yields is presented, aiming to improve crop productivity for farmers. The system utilizes a network of IoT sensors, including DHT22 and rainfall sensors, to gather real-time data on temperature, humidity, and rainfall. Soil-integrated sensors are also used to monitor specific soil properties such as nitrogen, phosphorus, potassium, pH, electrical conductivity, humidity, and temperature. This data is sent to a web interface for live display and stored for predictive modeling. Several regression models—decision tree, random forest, ridge regression, and linear regression—were implemented to predict crop yields, with the random forest regression model achieving the highest accuracy and an error rate of 6.46 percent. The stacking model was also analyzed, but the random forest model’s MAE and R- metrics proved superior, leading to its selection for deployment. A user-friendly web-based interface has been developed to enable farmers to interact with the system and predict crop yields effectively. This implementation smoothly integrates IoT technology with advanced data analytics, providing valuable insights to optimize agricultural practices, which in turn enhances food security and improves livelihoods.","author":[{"family":"Sumesh","given":"Nandana"},{"family":"Raj","given":"Vimal"},{"family":"Rajesh","given":"Vismaya"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icscsa64454.2024.00110","URL":"https://doi.org/10.1109/icscsa64454.2024.00110","source":"crossref"},{"id":"doi:10.70177/jsca.v4i1.3399","type":"article-journal","title":"WIRELESS COMMUNICATION TECHNOLOGIES ENABLING RELIABLE INTERNET OF THINGS SMART FARMING APPLICATIONS","abstract":"The rapid expansion of smart farming systems has intensified the need for reliable wireless communication infrastructures capable of supporting Internet of Things (IoT) applications in heterogeneous agricultural environments. Ensuring stable connectivity in rural areas characterized by large coverage demands, energy constraints, and environmental interference remains a critical challenge. This study aims to evaluate wireless communication technologies and identify optimal configurations that enable reliable IoT-based smart farming operations. A mixed-method research design integrating large-scale field experiments and simulation-based scalability analysis was employed to assess LoRaWAN, NB-IoT, Zigbee, Wi-Fi, and 5G IoT modules. Reliability was measured using packet delivery ratio, latency, coverage range, scalability, and energy consumption indicators. Results indicate that no single technology achieves optimal performance across all reliability dimensions. LPWAN technologies demonstrated superior energy efficiency and wide-area coverage, while 5G achieved the lowest latency and highest throughput. Hybrid communication architectures consistently outperformed single-technology deployments, improving packet delivery ratio and operational resilience under varying environmental conditions. The study concludes that context-aware integration of complementary wireless technologies provides the most reliable and sustainable solution for smart farming IoT ecosystems.","author":[{"family":"Wijaya","given":"Hamid"},{"family":"Fujita","given":"Miku"},{"family":"Nishida","given":"Daiki"}],"issued":{"date-parts":[[2026]]},"DOI":"10.70177/jsca.v4i1.3399","URL":"https://doi.org/10.70177/jsca.v4i1.3399","source":"crossref"},{"id":"doi:10.1201/9781003536932-2","type":"article-journal","title":"Big Data in Agriculture: Acquisition, Processing and Implications","abstract":"The agricultural sector is experiencing a digital revolution centered on big data, driven by the need to feed a growing global population, optimize resources, and address climate change challenges. This chapter examines the role of big data in modern agriculture, focusing on its applications in precision farming, predictive analytics, and resource management. Agricultural big data encompasses diverse information sources, including satellite imagery, IoT sensors, farm machinery data, and market trends, enabling real-time insights and informed decision-making across farming operations. Precision farming leverages this data to customize agricultural practices to specific field conditions, while predictive analytics employs machine learning and AI to forecast weather patterns, pest infestations, and crop yields. The integration of blockchain technology ensures transparency and traceability throughout the agricultural supply chain. However, challenges such as data privacy concerns, IT infrastructure requirements, and data source integration must be addressed through technological innovation and stakeholder collaboration. The chapter explores current applications, implementation challenges, and emerging trends, providing valuable insights for farmers, agronomists, and agricultural stakeholders seeking to harness data-driven approaches for improved farming outcomes.","author":[{"family":"Singh","given":"Aditya"},{"family":"Biswal","given":"Tanushree"},{"family":"Maharana","given":"Umakanta"},{"family":"Khatib","given":"Abdullah"},{"family":"Mishra","given":"Pradeep"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003536932-2","URL":"https://doi.org/10.1201/9781003536932-2","source":"crossref"},{"id":"doi:10.31316/jbm.v7i3.9026","type":"article-journal","title":"PENINGKATAN KAPASITAS KWT MELATI ASRI MELALUI PEMANFAATAN SISTEM SMART FARMING BERBASIS IOT DI KALURAHAN NGESTIHARJO, BANTUL","abstract":"This community service program aims to enhance the capacity of the Women Farmers Group (Kelompok Wanita Tani/KWT) Melati Asri in Tambak, Ngestiharjo Village, Bantul, through the implementation of smart farming innovation based on the Internet of Things (IoT). The main challenges faced by the group include limited knowledge and assistance in agricultural technology, suboptimal production management, inadequate farming facilities, and low digital literacy for marketing and product diversification. To address these issues, the program was carried out in five main stages: socialization, training, technology implementation, mentoring and evaluation, as well as sustainability planning. Training sessions covered modern agricultural technologies, organizational management, business plan development, and agricultural product diversification. Furthermore, smart farming technology, such as sensor-based monitoring systems in greenhouses, was introduced and accompanied by intensive mentoring. The outcomes show an increase in members’ knowledge of digital agriculture, skills in farm management, and awareness of innovation to strengthen local food security. The program also encouraged women’s active role in the community economy, opened wider market access through digitalization, and created opportunities for value-added agricultural product diversification. With a participatory and sustainable approach, this initiative is expected to improve productivity, efficiency, and competitiveness of KWT Melati Asri in the long term. Keywords: Smart Farming, Internet of Things, Women Farmers Group, Food Security, Community Empowerment","author":[{"family":"Ciptadi","given":"Prahenusa"},{"family":"Sari","given":"Marti"},{"family":"Prasetyo","given":"Adi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.31316/jbm.v7i3.9026","URL":"https://doi.org/10.31316/jbm.v7i3.9026","source":"crossref"},{"id":"doi:10.15575/ks.v8i1.53612","type":"article-journal","title":"Smart Farming Project-Based Learning as a Socio-Material Learning Space in Rural Special Education Schools","abstract":"This study aims to analyze the implementation of smart farming based on Project-Based Learning (PjBL) as a socio-material learning space that mediates student participation, agency, and engagement in special education within rural contexts. The study was conducted at SLB Muhammadiyah Kutoarjo, a special education school (Sekolah Luar Biasa) located in rural Central Java, Indonesia and involved 35 students aged 7–12 years who have intellectual disabilities and autism spectrum disorder, as well as four special education teachers. The study employed a convergent mixed methods design that integrated quantitative and qualitative data at the interpretation stage. The researchers collected quantitative data through structured observations to measure learning engagement, responsibility, communication, collaboration, functional independence, and behavioral-emotional regulation. The researchers collected qualitative data through semi-structured interviews with teachers and several selected students to understand their experiences of participation and the social meaning of the learning activities. The intervention involved a small-scale land management project based on smart farming that utilized simple Internet of Things (IoT) sensors such as soil moisture indicators and an automated irrigation system. The findings show a high level of learning engagement (88.5%), increased student responsibility (80%), communication (85.7%), and collaboration (74.2%). The students also demonstrated an average increase of approximately one-third in practical skill mastery compared to the baseline condition, accompanied by a decrease in disruptive behavior, increased attention, greater task independence, and more positive emotional expressions. Interviews reveal that the students began to position themselves as active participants in the learning activities, while teachers interpreted the practice as a contextual learning environment that strengthened students’ capabilities through direct experience. The study demonstrates that smart farming based on PjBL can function as an inclusive pedagogical practice that strengthens cognitive, social, and emotional learning outcomes in rural special education schools. The main contribution of this study lies in the development of a socio-material learning approach grounded in local contexts that integrates simple technology, physical activity, and social collaboration in inclusive education.","author":[{"family":"Setiawan","given":"Budi"},{"family":"Fatmaryanti","given":"Siska"},{"family":"Wicaksono","given":"Istiko"}],"issued":{"date-parts":[[2026]]},"DOI":"10.15575/ks.v8i1.53612","URL":"https://doi.org/10.15575/ks.v8i1.53612","source":"crossref"},{"id":"doi:10.1109/icaeccs68240.2025.11384769","type":"article-journal","title":"Distributed Data Acquisition Using MQTT Protocol Communication, Application to Smart Farming","abstract":"Smart farming technologies are growing faster using new IOT devices and the extended communication protocols which give researchers more flexibility to design corresponding embedded systems, machine learning and artificial intelligence models applied to intelligent agriculture. One of the most important part in this procedure is how researchers can get feasible data set to implement their intelligent models using adapted electronic circuits taking into account the large scale agriculture fields. This paper discuss the importance of using a distributed way to get/collect data set from different IOT sensors installed in the fields using MQTT communication protocol. The obtained experimental results prove that MQTT protocol perform well in term of data collection and transfer with precision and secured way.","author":[{"family":"Aoued","given":"Houari"},{"family":"Zaafrane","given":"Mohamed"},{"family":"Belhrazam","given":"Adda"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icaeccs68240.2025.11384769","URL":"https://doi.org/10.1109/icaeccs68240.2025.11384769","source":"crossref"},{"id":"doi:10.1109/aicecs63354.2024.10957312","type":"article-journal","title":"AI for Sustainable Agriculture: Smart Farming Solutions","abstract":"The increasing global demand for food production, coupled with the challenges posed by climate change and resource scarcity, has intensified the need for innovative agricultural practices. Artificial Intelligence (AI) has emerged as a transformative tool, enabling smarter and more sustainable farming solutions. This paper provides a comprehensive review of the role of AI in agriculture, focusing on its applications in precision farming, resource optimization, and crop management. It explores how AI-powered technologies, including machine learning algorithms, deep learning models, and IoT-integrated systems, can optimize irrigation, pest control, and yield prediction. Additionally, the paper examines the potential of AI in enhancing sustainability through reduced chemical inputs, efficient water use, and improved land management. The integration of AI with other emerging technologies such as drones, robotics, and blockchain further enhances transparency and efficiency in the agricultural supply chain. While the adoption of AI presents significant opportunities, the paper also highlights existing challenges such as data privacy, accessibility for small-scale farmers, and the need for policy support. The findings suggest that AI -driven smart farming can be a pivotal solution in addressing food security while promoting environmental sustainability.","author":[{"family":"Shinde","given":"Suyash"},{"family":"Kale","given":"Ganesh"},{"family":"Nalbalwar","given":"SL"},{"family":"Deosarkar","given":"SB"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/aicecs63354.2024.10957312","URL":"https://doi.org/10.1109/aicecs63354.2024.10957312","source":"crossref"},{"id":"doi:10.59431/ajad.v4i3.382","type":"article-journal","title":"Pengabdian Kepada Masyarakat Melalui Peningkatan Kualitas Sayur Hidroponik dan Pengembangan Smart Farming pada Ismulia Farm","abstract":"Based on the results of field observations and the results of the analysis of the existing problem situations in the field, several partner problems were found, namely: 1). Lack of knowledge and skills of partners in increasing production results, by using smart farming technology. 2). Do not understand how to market online and professionally, 3). Do not understand the concept of product packaging, 4). Lack of knowledge about the correct aspects of hydroponic cultivation using the correct planting pattern 5). Do not understand the business management system, and correct bookkeeping administration. The implementation activities will begin with the coordination and socialization stage, then continued with the provision of a smart farming system and training in its use. Continued with Training in Proper Plant Cultivation starting from seeding, planting, and maintenance. Demonstration training on natural pest control using pest traps followed by demonstration training on POC (Liquid Organic Fertilizer) Production and Production of botanical pesticides. The next activity is training in making product packaging. Furthermore, partners will be facilitated with digital marketing and training in its use to facilitate the marketing process, the last activity is to provide counseling on proper business management, administration, and bookkeeping. Based on the results of training and mentoring activities for Ismulia Farm businesses, it can be concluded that partners have increased their knowledge and skills in producing botanical pesticides, liquid organic fertilizers, improving product packaging, natural pest control using pest traps, and increasing their ability to run a business with good planning and understanding business management, and how to develop it (100%). For the smart farming system that monitors remote farming via Android, it is still in the process of finalizing its design.","author":[{"family":"Romano"},{"family":"Nasaruddin"},{"family":"Husna","given":"Rika"},{"family":"Mujiburrahmad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.59431/ajad.v4i3.382","URL":"https://doi.org/10.59431/ajad.v4i3.382","source":"crossref"},{"id":"doi:10.1109/icears64219.2025.10941202","type":"article-journal","title":"A Smart Irrigation System for Coconut Farming using IoT","abstract":"Coconut farming is an essential agricultural practice that contributes significantly to the global economy by providing valuable products such as coconut water, oil, and meat. However, the management of coconut plantations faces numerous challenges, including labor shortages, pest control, and the demand for precise irrigation and fertilization. This paper proposes an integrated smart farming system that leverages advanced sensor technologies and automation to address these challenges. The system employs precision irrigation and fertigation methods, facilitated by a centralized motor controller and solenoid valves, to deliver water and nutrients efficiently to the base of each coconut tree. A pH sensor monitors soil acidity or alkalinity, ensuring optimal nutrient availability and promoting sustainable farming practices by reducing chemical inputs. Additional features include a tree motion sensor and a tilt sensor for monitoring tree stability under adverse weather conditions. Soil moisture sensors, temperature, humidity, and light intensity sensors provide real-time data to enhance decision-making. Farmers can remotely monitor and control the system via a Node-RED dashboard, receiving alerts through platforms like Telegram. By integrating these technologies, the proposed system aims to optimize resource utilization, enhance crop yield, and reduce the environmental impact of coconut farming.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icears64219.2025.10941202","URL":"https://doi.org/10.1109/icears64219.2025.10941202","source":"crossref"},{"id":"doi:10.1201/9781003466314-3","type":"article-journal","title":"Sooner-C Lightweight Cryptographic Scheme for Data Distribution Privacy in Smart Farming","abstract":"Smart farming precision systems are considered viable for the remote communication of various types of media through the Internet of Things (IoT). For accurate and quick decision-making, sensors are especially effective at gathering and disseminating farm environmental/soil parameters. The introduction of encryption schemes is a result of the low capacity, widespread security, and privacy breaches in the IoT. This chapter uses the Sooner lightweight Cipher (Sooner-C) for data privacy and is built on a lightweight blockchain. The experimentation and evaluation’s findings indicate that for ciphertext sizes, Sooner-C (31.73%) outperformed SHA-AES (24.35%), XOR (13.65%), RainFence (9.59%), Ceasars (10.33%), and ROT45 (10.33%). Sooner-C (41.37%) performed better than RainFence (24.34%), XOR (13.36%), ROT45 (12.81%), SHA-AES (4.09%), and Ceasars (4.27%) for the encryption time. Sooner-C (14) had more rounds than the combination of SHA-AES (10), XOR (10), Ceasars (9), ROT45 (9), and RainFence (8). Therefore, cloud data storage and cropping decision-making are improved by the complexity, scalability, and privacy of IoT data in smart farming.","author":[{"family":"Alfa","given":"AA"},{"family":"Alhassan","given":"JK"},{"family":"Olaniyi","given":"OM"},{"family":"Morufu","given":"M"},{"family":"Misra","given":"Sanjay"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1201/9781003466314-3","URL":"https://doi.org/10.1201/9781003466314-3","source":"crossref"},{"id":"doi:10.1002/9781394310890.ch10","type":"article-journal","title":"Farming 4.0","abstract":"Agriculture is one of the major sectors that have been considered to be essential to ensuring food security. The world's population is growing, and there are many natural factors that make nourishing billions of people challenging. The application of Internet of Things (IoT) in agriculture is revolutionizing the field and creating opportunities for accurate monitoring and data-driven farming. The Internet of Things with the sensors and unmanned aircraft, which helps in tracking the farming lands based on the phenomenon of humidity, crop performance, livestock, and temperature are termed as Farming 4.0. This research chapter holds the smart agriculture concept that highlights the usage of Internet of Things in its evolutionary concept. This nominally increases the food output, as the year 2050 is predicted to have food shortage due to growing population, traditional farming methods, and outdated skills of farmers in field pattern. This fine goal has led to the enlarged connectivity between the digital scale of the marketed items using the internet. The loss reduction with increase in yield values is determined by the process of gathering data continuously with a precise level of monitoring. By considering the periodic data with the current trends, the farmers predict the yield with the disease outbreaks enhancing the consumer preferences with accurate data-driven methods. Making decisions based on strategic values helps in choosing the best strategic plan. Managing the strategies in remote locations using the IoT helps in providing the data with real-time access creating web alerts responding to disease outbreak with a high range of accuracy at nominal consumer preferences. This is made possible by connecting the sensors to the land. This helps in monitoring the storage conditions optimizing the tracking of shipments on agricultural supply chain values. This ensures producing high- quality food with waste reduction enhancing the efficiency of the supply chain process. The data gathered using the IoT based on artificial intelligence and various training procedures help the supporting system with decisions packed, thus highlighting suggestions and various insights. The agro-based sensor devices used for evaluation are connected to farming, service types, and the readiness of actual technological levels chosen for practicing. The results are framed with the process of investigating the technologies at the digital level such as machine learning embedded on the robotic systems and the Internet of Things. Thus, embracing security with IoT protocols helps to protect the assets on the farmland fostering long-term technological viability. Thus, the future of agriculture lies in leveraging the global IoT, which helps in achieving improved choices and accurate level of monitoring with suitable practices.","author":[{"family":"Ashwini","given":"A"},{"family":"Sriram","given":"SR"},{"family":"Prabhakar","given":"JM"},{"family":"Kadry","given":"Seifedine"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/9781394310890.ch10","URL":"https://doi.org/10.1002/9781394310890.ch10","source":"crossref"},{"id":"doi:10.46730/japs.v6i3.342","type":"article-journal","title":"Smart Farming Policy Analysis: Increasing Sustainable Agricultural Efficiency and Productivity","abstract":"Agriculture is a vital sector in the global economy and has a significant impact on sustainability and societal well-being. In recent years, smart farming policies have become a major focus in efforts to improve agricultural efficiency and productivity while reducing negative environmental impacts. This study aims to analyze implemented smart farming policies and identify the benefits, challenges, and policy implications for promoting sustainable agriculture. This paper is analyzed using William Dunn's concept and literature review. The results of this paper indicate that smart farming policies have significant potential to improve agricultural efficiency, productivity, and sustainability. However, technological, regulatory, and policy challenges must be overcome for smart farming to be widely adopted","author":[{"family":"Rahmanul","given":"Rahmanul"},{"family":"Masitoh","given":"Imas"},{"family":"Ikhsan","given":"Masrul"},{"family":"Ramadhan","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.46730/japs.v6i3.342","URL":"https://doi.org/10.46730/japs.v6i3.342","source":"crossref"},{"id":"doi:10.63725/njst.v1.i1.01","type":"article-journal","title":"AI-POWERED SOLAR-DRIVEN SMART IRRIGATION SYSTEMS FOR CLIMATE-RESILIENT SMALLHOLDER FARMING IN NIGERIA","abstract":"Water use efficiency remains a major challenge in agricultural production, particularly in regions where irrigation practices are largely manual and dependent on unpredictable environmental conditions. This study developed an artificial intelligence powered, solar driven smart irrigation system designed to optimize water application using key environmental variables, namely soil moisture, temperature, and solar radiation. The system integrates sensors, a microcontroller, and a machine learning model to monitor environmental conditions and automatically determine appropriate irrigation levels. An experimental research design was adopted, and simulated data were used to evaluate system performance under varying environmental conditions. The results showed that the system effectively adjusted water application based on changes in soil moisture, temperature, and solar radiation. Lower soil moisture levels and higher temperature conditions resulted in increased irrigation, while higher soil moisture levels led to reduced or no water application. Performance evaluation revealed that the proposed system significantly reduced water usage compared to traditional irrigation methods. The system achieved notable water savings and improved efficiency, particularly under conditions of high soil moisture where unnecessary irrigation was eliminated. These findings demonstrate the effectiveness of integrating artificial intelligence with renewable energy for sustainable irrigation management. The study concludes that AI powered smart irrigation systems provide a reliable and efficient solution for improving water use efficiency and agricultural productivity. The system is particularly suitable for smallholder farmers in Nigeria and other developing regions facing water and energy challenges.","author":[{"family":"Mt","given":"Musa"},{"family":"Mr","given":"Sambo"},{"family":"Kwajaffa","given":"Hadiza"}],"issued":{"date-parts":[[2026]]},"DOI":"10.63725/njst.v1.i1.01","URL":"https://doi.org/10.63725/njst.v1.i1.01","source":"crossref"},{"id":"doi:10.3390/asi9020046","type":"article-journal","title":"Smart Farming Innovation: Automated Biomechanical Monitoring of Broilers Using a Hybrid YOLO-SAM Pipeline","abstract":"Precision Livestock Farming (PLF) relies on accurate, high-frequency data to optimize production efficiency. Traditional assessments of feeding behavior remain manual and invasive, lacking the kinematic resolution required for automated control systems. This study developed and validated a novel computer vision framework integrating YOLOv8 and the Segment Anything Model (SAM) to address this gap. The objective was to engineer a non-invasive, automated pipeline to quantify high-speed broiler biomechanics in real time. The system was validated using video data from broilers across three growth stages and varying feed granulometries (fine mash, coarse mash, and pellets) to test its robustness in detecting subtle kinematic variations. The hybrid YOLO-SAM pipeline achieved high performance, with a precision of 0.95 and a recall of 0.91, confirming its reliability as a scalable sensor for smart farming platforms. Biomechanical analysis demonstrated the system’s sensitivity, showing that larger feed particles induce greater beak gape and displacement while significantly improving ingestion efficiency (0.6 effort ratio for pellets vs. 3.0 for mash). This research provides a validated technical foundation for digital phenotyping in poultry, offering a hands-free, quantitative tool that supports data-driven decision-making in feed formulation and production management.","author":[{"family":"Dionizio","given":"Victória"},{"family":"Okano","given":"Marcelo"},{"family":"Nääs","given":"Irenilza"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/asi9020046","URL":"https://doi.org/10.3390/asi9020046","source":"crossref"},{"id":"doi:10.14719/pst.12797","type":"article-journal","title":"AI-driven multi-agent framework for smart irrigation and crop health monitoring in Indian rice and sugarcane farming","abstract":"Disease prevention and water management are important to all the crops, particularly rice and sugarcane production in India. The article proposes a reinforcement learning (RL) based intelligent irrigation management system that is capable of optimising water consumption and crop nutrition in response to the changing agricultural climatic conditions. Decentralised reinforcement learning (RL) is used in a network of irrigation agents that utilise soil and microclimate sensor networks to set the terms of water allocation, water use efficiency (WUE) and crop health. At the same time, deep convolutional networks can be used to differentiate between plant stress/disease and leaf images and take applicable proactive actions. It is a framework that incorporates satellite-derived indices (NDVI, EVI, land surface temperature) with local sensor measurements and image-based health measurements through multimodal deep learning. Far-reaching simulations (including Indian climate and crop calendars) demonstrate that the multi-agent system lowers water consumption and preserves the yields and properly notifies stressed plants. The scores of disease detection with plantvillage-based fine-tuned on rice (120 (3 disease types) and 3829 (5 disease types) and sugarcane (2569 images for all disease types, Convolutional Neural Network (CNN) yield results of &gt;98 % accuracy. Crop mapping (rice/sugarcane) Satellite/LSTM-based crop mapping (with Sentinel-1 / Sentinel-2) achieves more than 97 % accuracy. The suggested structure provides a data-driven, scalable system for precision agriculture to enhance the management of irrigation periods and crop health. Simulation experiments show that the RL-based controller can reduce water consumption while preserving optimal soil moisture levels when compared to rule-based irrigation strategies.","author":[{"family":"Sheetal","given":"Va"},{"family":"Vikranth","given":"Bm"},{"family":"Adarsha","given":"Shv"}],"issued":{"date-parts":[[2026]]},"DOI":"10.14719/pst.12797","URL":"https://doi.org/10.14719/pst.12797","source":"crossref"},{"id":"doi:10.71443/9789349552364-09","type":"article-journal","title":"Autonomous Agricultural Robotics for Crop Harvesting and Weed Detection Using AI","abstract":"The integration of autonomous robotics in agriculture, particularly for crop harvesting and weed detection, is revolutionizing modern farming practices. This chapter explores the critical role of Artificial Intelligence (AI), machine learning, and advanced sensor technologies in enabling autonomous systems to optimize agricultural processes with unprecedented precision. By focusing on key applications such as precision herbicide application, real-time crop harvesting, and environmental adaptation, this work highlights the transformative potential of autonomous agricultural robots in enhancing productivity, sustainability, and operational efficiency. Through advanced navigation systems, including GPS and geospatial technologies, robots can navigate complex terrains and adjust to varying weather conditions, ensuring seamless operation across diverse farming environments. The precision in weed detection and herbicide application offers a sustainable approach to pest control, significantly reducing the environmental impact of conventional farming practices. Furthermore, by improving the accuracy, timing, and speed of harvesting operations, autonomous robots contribute to higher crop yields while minimizing waste. Despite the significant advancements, challenges remain in scaling these technologies for widespread adoption, particularly concerning cost, infrastructure, and operational reliability in real-world conditions. This chapter provides a comprehensive overview of the current state of autonomous agricultural robotics, highlighting emerging trends, technological advancements, and future directions for research and development in this rapidly evolving field.","author":[],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-09","URL":"https://doi.org/10.71443/9789349552364-09","source":"crossref"},{"id":"doi:10.1504/ijbic.2026.151785","type":"article-journal","title":"A hybrid genetic algorithm based method for smart beef farming","abstract":"To enhance cost efficiency in the cattle industry, particularly through feed formulation optimisation, we propose a novel feed encoding method that accurately and simply expresses the proportions between different feeds. Building upon this encoding method, we introduce adaptive simulated annealing genetic algorithm (ASAGA), a hybrid genetic algorithm designed to optimise feed costs. ASAGA cleverly combines the powerful global search capability of genetic algorithms with the effective local optimisation ability of simulated annealing. It incorporates an elite pool strategy to retain high-potential individuals during population evolution and utilises adaptive crossover and mutation strategies to improve adaptability and resolution efficiency. Furthermore, we introduce three different neighbourhood structure strategies to enhance exploration of the solution space. Experimental results have demonstrated the effectiveness of ASAGA in optimising feed costs for smart cattle farming.","author":[{"family":"Li","given":"Kangshun"},{"family":"Chen","given":"Junhao"},{"family":"Chen","given":"Ziheng"},{"family":"Lin","given":"Wenyan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1504/ijbic.2026.151785","URL":"https://doi.org/10.1504/ijbic.2026.151785","source":"crossref"},{"id":"doi:10.1109/apcit65661.2025.11411275","type":"article-journal","title":"Weed Guard: Vision-Guided Weed Management with CoppeliaSim-Driven Simulation for Smart Farming","abstract":"By 2050, the global population is projected to rise from 8 billion to over 9 billion, necessitating a 60–70% increase in food production. Weed control is a key component in achieving this goal through precision agriculture. Traditional methods, including manual weeding and chemical herbicides, either lack efficiency or pose environmental and economic challenges. This work introduces Weed Guard, a simulation-based weed detection and control framework that integrates MATLAB-driven image processing with robotic behavior simulated in CoppeliaSim. This includes development of an advanced image processing pipeline using contrast stretching, Lab color segmentation, and morphological operations to accurately extract weed patches in dense agricultural fields. Also, implementation of a closed-loop control system to convert weed coordinates into movement commands for the KUKA YouBot, enabling precise and repeatable mechanical actuation based on visual feedback. This approach effectively demonstrates the perception, detection, and path-planning components of an autonomous weed management system. By combining MATLAB image processing capabilities with the CoppeliaSim simulation environment, this work presents a scalable and cost-effective virtual test-bed for precision farming. The proposed system serves as a proof-of-concept for developing real-time, vision-based autonomous weeding robots adaptable to various agricultural settings.","author":[{"family":"Malokar","given":"Tejas"},{"family":"Roy","given":"Edwin"},{"family":"Sahu","given":"Umesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/apcit65661.2025.11411275","URL":"https://doi.org/10.1109/apcit65661.2025.11411275","source":"crossref"},{"id":"doi:10.59267/ekopolj2602567a","type":"article-journal","title":"INFERENCES BETWEEN SMART FARMING AND SUSTAINABLE DEVELOPMENT OF AGRICULTURE","abstract":"Agriculture faces significant challenges related to globalpopulation growth, climate change and pressure on naturalresources. In this paper, the positive impact of integratingdigitalization into farming practices to promote sustainabilityand efficiency in the agricultural sector is explored. Theresearch aims to highlight the importance of smart farmingin the sustainable development of agriculture. This analysiswill be carried out at the level of scientific studies conductedaccording to the Scopus database. The main results showthat the interest in exploring IoT and digitalization inagriculture has increased in the last ten years, mostlybecause adopting sustainable practices and regenerativetechnologies minimizes the environmental impact andpromotes biodiversity. The findings add knowledge tothe literature and contribute to a better understanding ofthe benefits of implementing digitalization in agriculture;as such, farmers make more informed decisions aboutfertilization, irrigation, and crop protection, while reducingresource use and environmental impact.","author":[{"family":"Ion","given":"Raluca"},{"family":"Ladaru","given":"Georgiana"},{"family":"Stoian","given":"Mirela"},{"family":"Petre","given":"Ionut"},{"family":"Popescu","given":"George"}],"issued":{"date-parts":[[2026]]},"DOI":"10.59267/ekopolj2602567a","URL":"https://doi.org/10.59267/ekopolj2602567a","source":"crossref"},{"id":"doi:10.1109/icoris67789.2025.11295988","type":"article-journal","title":"Monte Carlo Synthetic Data Generation for Durian Cultivation Based on Smart Farming IoT","abstract":"Data scarcity is a common challenge in the application of Artificial Intelligence of Things (AIoT) for smart agriculture, especially for high-value crops such as Durian (Durio zibethinus), which experience limitations in sensor application and irregular data collection cycles. This study examines the performance of two synthetic data generation techniques, namely Monte Carlo Simulation (MCS) and Gaussian Mixture Model (GMM), applied to Internet of Things (IoT)-based environmental datasets in durian cultivation. Both methods are evaluated using the Kolmogorov-Smirnov (K–S) statistics test, mean decrease in impurity (MDI) feature importance, and crop classification using extreme gradient boosting (XGBoost). The results of the K-S statistic test show that the two durian synthetic dataset features of the two methods have similar kernel density estimates (KDEs). In contrast, the two features have different but insignificant KDEs. Then, the \"Rainfall\" feature exhibits a different KDE shape between the GMM and Monte Carlo methods. The results of the MDI feature importance test indicate that the new dataset with synthetic durian data generated by MCS has better feature quality than GMM, with the highest feature score being \"Year,\" at 0.579. Finally, the durian synthetic dataset from MCS demonstrated a significant effect on XGBoost crop classification, achieving optimum accuracy, precision, recall, and F1-score compared to random forest and gradient boosting, with values of 0.87, 0.86, 0.86, and 0.86, respectively.","author":[{"family":"Nugraha","given":"Rifqi"},{"family":"Putrada","given":"Aji"},{"family":"Wicaksono","given":"Ryan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icoris67789.2025.11295988","URL":"https://doi.org/10.1109/icoris67789.2025.11295988","source":"crossref"},{"id":"doi:10.32664/0vcshq38","type":"article-journal","title":"Reimagining Urban Agriculture: LED-Powered Underground Rice Farming for Smart Sustainable Cities","abstract":"Rapid urbanization in metropolitan regions has intensified agricultural land conversion, particularly affecting rice-based food systems that remain highly land-dependent and less adaptable to conventional urban farming approaches. This study developed a conceptual and technical model of LED-powered underground rice farming as an alternative production system to address structural constraints on urban food security and sustainable agricultural development. A qualitative descriptive approach was employed, integrating secondary data analysis, comparative case studies, and content analysis to construct a system design encompassing spatial configuration, water management, and controlled lighting environments. The results indicated that the proposed system enabled precise regulation of microclimatic conditions, including light spectra, photoperiod, and water circulation, thereby supporting continuous production cycles and improving resource-use efficiency. The integration of recirculating irrigation and spectrum-adjusted LED lighting reduce water consumption and minimize dependency on chemical inputs while maintaining crop quality in enclosed environments. Furthermore, the model demonstrated strong spatial efficiency, making it applicable for high-density urban areas with limited arable land. However, implementation remained constrained by high initial investment costs and dependence on reliable energy infrastructure. These findings highlighted the strategic role of technological innovation, integrated system design, and multi-stakeholder collaboration in advancing resilient urban food systems. Overall, this study provided a scalable pathway for transforming rice cultivation toward sustainable and smart metropolitan agriculture.","author":[{"family":"Syabana","given":"Imam"},{"family":"Ramadhani","given":"Naffasyah"},{"family":"Affianto","given":"Sania"}],"issued":{"date-parts":[[2026]]},"DOI":"10.32664/0vcshq38","URL":"https://doi.org/10.32664/0vcshq38","source":"crossref"},{"id":"doi:10.35143/jiter-pm.v3i4.6839","type":"article-journal","title":"Pendampingan Petani Melalui Aplikasi Smart Farming “GermasTani” di Desa Sukorejo Kabupaten Jember","abstract":"Salah satu desa di Kabupaten Jember yang masih menggunakan cara usahatani konvensional adalah Desa Sukorejo Kecamatan Bangsalsari. Kegiatan usahatani dilakukan secara turun temurun dan konvensional tanpa menggunakan Good Agricultural Practice. Berbagai macam permasalahan muncul seperti waktu tanam kurang tepat, pemupukan dilakukan kurang berimbang, dan penentuan harga hasil panen oleh tengkulak. Oleh karena itu dalam kegiatan pengabdian ini dikembangkan sebuah sistem smart farming berbasis mobile yang diberikan nama “GermasTani”. Tujuan kegiatan pengabdian adalah meningkatkan kemandirian digital petani melalui pendekatan teknologi dan pendampingan partisipatif. Metode yang digunakan meliputi pelatihan penggunaan aplikasi, pendampingan intensif selama enam bulan, pembentukan Kelompok Tani Digital. Dari hasil kegiatan dapat disimpulkan bahwa aplikasi “GermasTani” dapat meningkatkan literasi digital, bahkan di kalangan petani lanjut usia, berkat desain antarmuka yang inklusif.","author":[{"family":"Furqon","given":"Muhammad"},{"family":"Kusmiati","given":"Ati"},{"family":"Puspaningrum","given":"Diah"}],"issued":{"date-parts":[[2026]]},"DOI":"10.35143/jiter-pm.v3i4.6839","URL":"https://doi.org/10.35143/jiter-pm.v3i4.6839","source":"crossref"},{"id":"doi:10.1109/emergin63207.2024.10961623","type":"article-journal","title":"Smart Agriculture: Combining Crop Recommendation, Yield Prediction, and Environmental Analyzers for Optimized Farming","abstract":"Climate changes, resource limitations and demands for sustainable practices has led to significant challenges to modern agriculture. Therefore in order to tackle this, our research addresses these challenges and suggests a system that integrates machine learning models and IoT technologies to predict crop yields and recommend suitable crops based on environmental conditions. Existing approaches lack real time capabilities thus fail to address farmer's decision making needs. To eliminate these challenges, we propose a web-based application that includes high level machine learning models for crop yield recommendation and prediction. The web app features a integrated interface for users to input data or link to IoT-based sensors for real-time evaluation of factors such as humidity, rainfall, soil health, and temperature. The application's constant observation and adjustable functions confirms that insights remain suitable under altering environmental factors. The system analyzes various machine learning models, involving Random Forest, Gradient Boosting, and Support Vector Machines, to determine the most precise and optimized algorithms for prediction tasks. Our models illustrates high accuracy of 97% for crop recommendation and 0.98 value for R2 yield prediction. Incorporating these components, the recommended system enhances crop management decisions, makes resource use more effective, and improves productivity. The research asserts with a discussion of its participation to sustainable farming and highlights future advancements, such as integrating further data sources and high level machine learning techniques.","author":[{"family":"Jaswal","given":"Mrigaank"},{"family":"Kumari","given":"Archana"},{"family":"Sangha","given":"Khushmn"},{"family":"Arora","given":"Deepti"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/emergin63207.2024.10961623","URL":"https://doi.org/10.1109/emergin63207.2024.10961623","source":"crossref"},{"id":"doi:10.58532/nbennursafpb1p1c4","type":"article-journal","title":"IOT, SENSORS AND AUTOMATION IN LIVESTOCK FARMING","abstract":"Livestock farming is under increasing pressure from disease risks, feed inefficiencies, climate stress, labor shortages, and rising expectations for animal welfare, food safety, and traceability. Precision Livestock Farming (PLF) addresses these challenges by converting continuous measurements of animals and their environments into timely management decisions. This chapter presents a practical and research-grounded overview of the role of the Internet of Things (IoT), sensors, analytics/AI, and automation in livestock systems (dairy, poultry, small ruminants, and brief notes on piggery). It explains end-to-end livestock IoT architecture (sensors to edge to cloud to decisions to actuators), key sensing modalities (wearables, environmental sensors, feeding/watering meters, imaging, and biosensing proxies), and automation/control systems (milking, feeding, climate control, and handling). The chapter also provides practical guidance on connectivity choices, data management and interoperability, cybersecurity safeguards, and a roadmap for implementation from pilot to scale. Three illustrative case studies highlight real-world design trade-offs and lessons. Finally, emerging trends and research gaps are discussed, including edge AI, multi-modal sensing, open standards, and sustainability reporting.","author":[{"family":"Singh","given":"Yash"},{"family":"Verma","given":"Med"},{"family":"Yadav","given":"HC"}],"issued":{"date-parts":[[2026]]},"DOI":"10.58532/nbennursafpb1p1c4","URL":"https://doi.org/10.58532/nbennursafpb1p1c4","source":"crossref"},{"id":"doi:10.4018/979-8-3373-0020-7.ch010","type":"article-journal","title":"Cyber Security Risk in Smart Agriculture in Regional Australia","abstract":"Agriculture is a fundamental global primary industry, evolving with advances in ICT and automation. The rise in ‘smart farming' integrates cutting-edge technologies like IoT, drones, sensors, GPS, big data analytics, and AI to improve efficiency, productivity, and sustainability. These innovations facilitate real-time monitoring, data-driven decisions, and automation in key farming tasks, including soil analysis, irrigation, crop health evaluation, and pest management. However, the adoption of smart technologies introduces cybersecurity risks. This chapter explores cybersecurity threats in smart farming in regional Australia. As farmers increasingly rely on advanced technologies such as IoT, drones and satellites, blockchain, and robotics, implementing cybersecurity measures is vital. Without robust security, farmers may lose trust in these technologies. Farm data and IT assets require raising awareness, promoting best practices and integrating cybersecurity into agricultural systems.","author":[{"family":"Neupane","given":"Arjun"},{"family":"Shahi","given":"Tej"},{"family":"Sitoula","given":"Sameer"},{"family":"Langat","given":"Philip"},{"family":"Walsh","given":"Kerry"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3373-0020-7.ch010","URL":"https://doi.org/10.4018/979-8-3373-0020-7.ch010","source":"crossref"},{"id":"doi:10.55041/ijcope.v2i4.383","type":"article-journal","title":"Agrigenius: The Ultimate Smart Farming App","abstract":"— Agriculture remains one of the most important industries in the world. Hence, the incorporation of technological advancements and intelligent decision support systems plays a critical role in enhancing efficiency in the industry. Conventional farming largely depends on personal experience by the farmer, unreliable environmental factors, and other variables leading to poor crop yields, mismanagement of resources, and wrong crop choice. However, in our application Agri-Genius, we present an innovative and predictable farming assistance system that uses deep learning algorithms to help farmers decide on the most efficient crops based on available soil nutrients, weather conditions, and seasons using Long Short-Term Memory (LSTM) and Random Forest","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.55041/ijcope.v2i4.383","URL":"https://doi.org/10.55041/ijcope.v2i4.383","source":"crossref"},{"id":"doi:10.18805/ag.rf-396","type":"article-journal","title":"Empowering Women in Dairy Farming: Gender Roles, Challenges and Climate Smart Practices in Southern Bangladesh","abstract":"Background: Women play a critical role in both household management and agricultural production in rural Bangladesh. In Dumuria Upazila, Khulna district, it is well known that women dairy farmers contribute significantly to household income and food security. However, they face socio-economic and gender-based barriers that affect their access to resources, decision-making power and adoption of modern technologies. This study explores gender roles, access to credit, ownership perception and the adoption of climate-smart agricultural practices among women dairy farmers, who spend their time mostly on the farming. Methods: A qualitative interviewfor gender analysis was conducted among 133 women dairy farmers selected from a broader population of 3,050 women aged 20 to 89 years in Dumuria Upazila of Khulna district. The family income of those farmers comes mostly from dairy farming. Data were collected through 12 Key Informant Interviews (KIIs) and 3 Focus Group Discussions (FGDs) on demographics, household size, educational background, farming experience, access to credit, financial and decision-making involvement, asset perception and adoption of climate-smart technologies. The responses were analyzed to understand the gender dynamics and socio-economic conditions affecting the livelihood of those women. Result: The higher number of the respondents (44 farmers, 33%) were aged between 30-49. Women managed both household and farming responsibilities, with family sizes ranged from 2 to 10 members and dairy farming experience ranging from new entrants to over 30 years. Educational attainment varied. Only 35 (26.31%) respondents had access to credit. Nevertheless, women showed increasing involvement in financial decisions and milk distribution. Although most assets were officially registered in their husbands’ names, 131 (98.50%) women perceived the assets as their own. Joint decision-making in income management was common, though in households with elders or in-laws decisions were largely elder-driven.Regarding climate-smart technologies, only 14 (10.5%) respondents acknowledged familiarity. Nine (6.77%) used biogas plants and two used biogas combined with vermi-composting. Other mentioned to include rubber mats, water pumps and fans-suggesting unintentional use of such technologies. However, 64 (48%) respondents were unaware, 53 (39.85%) marked “N/A,” and one responded negatively, highlighting a major awareness gap in climate-smart farming practices.It was concluded from the findings that while women in dairy farming are increasingly participating in financial and household decision-making, their formal financial empowerment, such as buying assets in their names or opening fixed deposit in bank and access to climate-smart technologies remain limited, with a significant awareness gap in sustainable farming practices underscoring the need for targeted education and support interventions.","author":[{"family":"Hoque","given":"Mohammad"},{"family":"Akter","given":"Rinki"},{"family":"Hashi","given":"Uswatun"},{"family":"Karim","given":"Md"}],"issued":{"date-parts":[[2026]]},"DOI":"10.18805/ag.rf-396","URL":"https://doi.org/10.18805/ag.rf-396","source":"crossref"},{"id":"doi:10.26480/trab.01.2024.01.10","type":"article-journal","title":"SMART FARMING OF GERBERA PRODUCTION IN DIFFERENT SUBSTRATE CULTURE (SYSTEMS AND TYPES)","abstract":"To maximize Gerbera production and avoid the different problems of soil, water shortage and climate change impacts, substrate culture performed an efficient technique for producing Gerbera flowers sustainability under greenhouse conditions. The investigation was conducted at the Central Laboratory for Agriculture Climate (CLAC), Agriculture Research Center, Egypt under greenhouse conditions during two cultivated winter seasons of 2020/2021 and 2021/2022. The smart system used for monitoring the micro-climate and environmental conditions for providing smart farming management system. The study investigating the effect and potentiality of different substrates peat moss : perlite (P:P 1:1 v/v) in different system (bags (40 and 30 L, pots (10 and 7.5 L) and container) compared to coco peat bags (CP) and rock wool bags (RW) with two densities (70 and 100) on Gerbera production. Micro-climate records (air temperature, and relative humidity) and environmental detections (substrate moisture, and EC and level of nutrient solution tanks) were sensing by different sensors to provide smart monitoring and alarm system for different substrate types and systems. The vegetative characteristics and yield parameters as well as bio chemical and chemical analysis were recorded. The revealed results indicated that peat moss : perlite substrate had the highest significant values of vegetative characteristics and yield parameters of Gerbera compared to other substrates. Also, increasing the substrate volume or density led to an increase in the vegetative characteristics and yield parameters of Gerbera. Container P: P followed by bags P: P followed by Pots P: P 10 gave the highest significant results of the vegetative characteristics, yield parameters and bio chemical and chemical analysis of gerbera while the lowest values recorded by bags RW followed by bags CP. The economic impact assessment promoted strongly the implement of Pots P: P 10 followed by Container P: P which presented the highest net profit of Gerbera production that matched the study recommendation.","author":[{"family":"Emam","given":"MSA"},{"family":"Farag","given":"AA"}],"issued":{"date-parts":[[2025]]},"DOI":"10.26480/trab.01.2024.01.10","URL":"https://doi.org/10.26480/trab.01.2024.01.10","source":"crossref"},{"id":"doi:10.1109/qpain66474.2025.11172080","type":"article-journal","title":"Smart Poultry Farming: An IoT-Based Approach for Brooder Environment and Resource Automation","abstract":"This paper presents the design, implementation, and evaluation of an IoT-based Smart Chicken Brooder aimed at automating environmental and resource management in poultry farming. The system integrates sensors, actuators, and micro-controllers to monitor and control temperature, humidity, food supply, and water availability in real time. Using the ESP32 microcontroller and Blynk IoT platform, users can remotely monitor environmental parameters and adjust threshold settings. An innovative feeding mechanism, which includes a 3D-printed Archimedes screw and an automated water supply system, enhances operational efficiency and reduces manual labor. Experimental results validate that the system maintains temperature and humidity within set thresholds, ensures fast actuator response times, and provides reliable real-time data visualization. The proposed solution offers a scalable, cost-effective, and energy-efficient approach to improving chick health and overall poultry farm productivity.","author":[{"family":"Karim","given":"Md"},{"family":"Newaz","given":"Navid"},{"family":"Abtahi","given":"Md"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/qpain66474.2025.11172080","URL":"https://doi.org/10.1109/qpain66474.2025.11172080","source":"crossref"},{"id":"doi:10.71443/9789349552364-11","type":"article-journal","title":"Swarm Intelligence and Multi Agent Systems for Coordinated Farm Equipment Operations","abstract":"The integration of Swarm Intelligence (SI) and Multi-Agent Systems (MAS) has the potential to revolutionize agricultural operations by optimizing the coordination of autonomous farm equipment. This chapter explores the application of SI and MAS in enhancing the efficiency, adaptability, and scalability of autonomous systems for tasks such as planting, irrigation, pest management, and harvesting. By leveraging decentralized control mechanisms, swarm-based algorithms and multi-agent frameworks enable autonomous agents to collaborate, adapt to dynamic field conditions, and perform complex tasks with minimal human intervention. The chapter delves into key principles of decentralized control, real-time data synchronization, and task allocation in autonomous farm systems. Additionally, it examines the challenges associated with sensor networks, data integration, and communication protocols in large-scale agricultural environments. Emphasis is placed on the optimization of autonomous harvesting through the combined use of SI and MAS, highlighting the potential for real-time decision-making, resource management, and operational efficiency. The chapter concludes by addressing the future prospects of swarm intelligence and multi-agent coordination in the context of precision agriculture, offering valuable insights into the path toward fully automated, sustainable farming systems.","author":[{"family":"Elanchezhian","given":"J"},{"family":"Thanikasalam","given":"A"}],"issued":{"date-parts":[[2025]]},"DOI":"10.71443/9789349552364-11","URL":"https://doi.org/10.71443/9789349552364-11","source":"crossref"},{"id":"doi:10.1109/icbdml68582.2026.11545121","type":"article-journal","title":"IoT-Driven Smart Farming: A Hybrid TabNet-Tab Transformer Recommendation Approach","abstract":"The smart farming recommendation system based on the IoT is a modern approach in the framework of precision agriculture as it was able to attain real-time data collection to feed crop forecasting. It has IoT sensors placed in strategic positions to constantly measure soil parameters such as nitrogen, phosphorus, potassium, and pH, and climatic parameters such as temperature, humidity, and precipitation. The amassed data are then fed through highly advanced algorithms that take into account micro-climatic conditions of the climatic environment thus advising on the best crop choices that suit certain geographical regions. The combination of the IoT technology to agronomy, soil science, and meteorology enables farmers to be able to make evidence-based decisions, which will maximize the yield, minimize resource wastage, and provide sustainability in agricultural practices. The suggested development scheme shows that IoT-based solutions are bound to transform agriculture into a more productive industry and reduce the effects on nature.","author":[{"family":"Satheesh","given":"T"},{"family":"Jhanuvarshini","given":"S"},{"family":"Krithik","given":"MK"},{"family":"Subashree","given":"N"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/icbdml68582.2026.11545121","URL":"https://doi.org/10.1109/icbdml68582.2026.11545121","source":"crossref"},{"id":"doi:10.11591/ijeecs.v39.i2.pp1326-1336","type":"article-journal","title":"Design and implementation of smart farming prototype with renewable energy and IoT","abstract":"&lt;span&gt;Indonesia &lt;span lang=\"EN-US\"&gt;faces food security challenges in several regions, and the adoption of advanced technologies such as artificial intelligence (AI), internet of thing (IoT), and renewable energy in the agricultural sector has not been optimal. This research aims to develop an integrated smart farming system, including monitoring, controlling, and prediction features based on renewable energy to support national food security, especially for chili plants. The method used in the research is an experiment, starting from analysis, design, manufacture, and testing. The result of the research is a smart farming prototype that has been tested with experts, partners and farmers. The results of expert testing obtained that the monitoring feature, in this case the accuracy is 4.36 out of 5 for all sensors, as well as the controlling and prediction features have met technical, functional, and practical needs. The results of the usability evaluation using the system usability scale (SUS) method involving partners and farmers obtained an average SUS score of 73.125. This result is categorized as an excellent rating and can be given a grade B and the acceptance range is high. So, from this study it can be concluded that the smart farming prototype can be used by chili farmers.&lt;/span&gt;&lt;/span&gt;","author":[{"family":"Susanto","given":"Rudi"},{"family":"Lestari","given":"Wiji"},{"family":"Hasanah","given":"Herliyani"}],"issued":{"date-parts":[[2025]]},"DOI":"10.11591/ijeecs.v39.i2.pp1326-1336","URL":"https://doi.org/10.11591/ijeecs.v39.i2.pp1326-1336","source":"crossref"},{"id":"doi:10.1109/lra.2025.3634888","type":"article-journal","title":"Design and Modeling of a Reconfigurable Robot: Decoupled STAR (DSTAR)","abstract":"This paper presents Decoupled STAR (DSTAR), a novel reconfigurable robot fitted with a sprawling mechanism that allows the wheel rotation axes to vary relative to the body, and two independently activated four-bar extension mechanisms (FBEM). These mechanisms enable the robot to move its center of mass (COM) in any direction, and increase its maneuvering capabilities by selecting a variety of locomotion gaits. A kinematic model of the robot and a quasi-static force analysis are used to optimize the design and evaluate its motor requirements. Experiments demonstrate that combining the sprawling mechanism with FBEM enables the DSTAR to both crawl and drive, overcome a wide range of challenging obstacles, and improve its climbing capability by 66% compared to symmetric FBEM designs (such as RSTAR). The robot can crawl and maneuver over rough terrain using its unique turtle-gait method, roll sideways to surmount wall obstacles up to 20 cm high, travel horizontally across uneven ground, and switch between wheels and whegs to adapt to different terrain types, including dirt, stones, and grass. (see attached video).","author":[{"family":"Siboni","given":"Tomer"},{"family":"Coronel","given":"Matan"},{"family":"Zarrouk","given":"David"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/lra.2025.3634888","URL":"https://doi.org/10.1109/lra.2025.3634888","source":"crossref"},{"id":"doi:10.1177/02783649241233300","type":"article-journal","title":"Path signatures for diversity in probabilistic trajectory optimisation","abstract":"Motion planning can be cast as a trajectory optimisation problem where a cost is minimised as a function of the trajectory being generated. In complex environments with several obstacles and complicated geometry, this optimisation problem is usually difficult to solve and prone to local minima. However, recent advancements in computing hardware allow for parallel trajectory optimisation where multiple solutions are obtained simultaneously, each initialised from a different starting point. Unfortunately, without a strategy preventing two solutions to collapse on each other, naive parallel optimisation can suffer from mode collapse diminishing the efficiency of the approach and the likelihood of finding a global solution. In this paper, we leverage on recent advances in the theory of rough paths to devise an algorithm for parallel trajectory optimisation that promotes diversity over the range of solutions, therefore avoiding mode collapses and achieving better global properties. Our approach builds on path signatures and Hilbert space representations of trajectories and connects parallel variational inference for trajectory estimation with diversity-promoting kernels. We empirically demonstrate that this strategy achieves lower average costs than competing alternatives on a range of problems, from 2D navigation to robotic manipulators operating in cluttered environments.","author":[{"family":"Barcelos","given":"Lucas"},{"family":"Lai","given":"Tin"},{"family":"Oliveira","given":"Rafael"},{"family":"Borges","given":"Paulo"},{"family":"Ramos","given":"Fabio"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1177/02783649241233300","URL":"https://doi.org/10.1177/02783649241233300","source":"crossref"},{"id":"doi:10.3390/ai7040124","type":"article-journal","title":"Real-Time Constrained Visual Servoing for Agricultural Harvesting Robots via MPC-Guided Reinforcement Learning","abstract":"With the intensification of global agricultural labor shortage and scaled development of facility agriculture, autonomous precision harvesting robots for unstructured greenhouse environments have become an urgent need. For cluster-picking crops such as tomatoes, visual servoing enables real-time closed-loop control of the end-effector pose, addressing challenges of random fruit distribution and variable stem orientations. However, existing methods struggle to balance constraint handling with real-time efficiency. This paper proposes an MPC-Guided Reinforcement Learning visual servoing framework, innovatively combining the planning capability of optimal control with the adaptive learning ability and real-time inference advantages of reinforcement learning. The approach adopts a teacher–student paradigm: expert trajectories from the MPC controller warm-start the reinforcement learning policy through behavior cloning, followed by PPO-based fine-tuning with adaptive gain regulation and stagnation-enhanced exploration mechanisms. Simulation experiments demonstrate a 95% success rate with average positioning and orientation errors of 13.6 mm and 0.009 rad respectively. Compared to MPC baseline, task steps are reduced by 53.4%; compared to Standard PPO, success rate improves by 6%. Greenhouse field validation achieves 85.3% picking success rate and 5.63 s per fruit operation time, confirming the framework’s excellent balance among control precision, robustness, and efficiency for high-precision robotic harvesting in unstructured agricultural environments.","author":[{"family":"Gao","given":"Liangzheng"},{"family":"Feng","given":"Qingchun"},{"family":"Chen","given":"Shiqi"},{"family":"Yang","given":"Zhijie"},{"family":"Fan","given":"Fengcui"},{"family":"Chen","given":"Lin"},{"family":"Zhao","given":"Chunjiang"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/ai7040124","URL":"https://doi.org/10.3390/ai7040124","source":"crossref"},{"id":"doi:10.1109/icarcv63323.2024.10821619","type":"article-journal","title":"Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack","abstract":"Robotic technologies have been an indispensable part for improving human productivity since they have been helping humans in completing diverse, complex, and intensive tasks in a fast yet accurate and efficient way. Therefore, robotic technologies have been deployed in a wide range of applications, ranging from personal to industrial use-cases. However, current robotic technologies and their computing paradigm still lack embodied intelligence to efficiently interact with operational environments, respond with correct/expected actions, and adapt to changes in the environments. Toward this, recent advances in neuromorphic computing with Spiking Neural Networks (SNN) have demonstrated the potential to enable the embodied intelligence for robotics through bio-plausible computing paradigm that mimics how the biological brain works, known as “neuromorphic artificial intelligence (AI)”. However, the field of neuromorphic AI-based robotics is still at an early stage, therefore its development and deployment for solving real-world problems expose new challenges in different design aspects, such as accuracy, adaptability, efficiency, reliability, and security. To address these challenges, this paper will discuss how we can enable embodied neuromorphic AI for robotic systems through our perspectives: (P1) Embodied intelligence based on effective learning rule, training mechanism, and adaptability; (P2) Cross-layer optimizations for energy-efficient neuromorphic computing; (P3) Representative and fair benchmarks; (P4) Low-cost reliability and safety enhancements; (P5) Security and privacy for neuromorphic computing; and (P6) A synergistic development for energy-efficient and robust neuromorphic-based robotics. Furthermore, this paper identifies research challenges and opportunities, as well as elaborates our vision for future research development toward embodied neuromorphic AI for robotics.","author":[{"family":"Putra","given":"Rachmad"},{"family":"Marchisio","given":"Alberto"},{"family":"Zayer","given":"Fakhreddine"},{"family":"Dias","given":"Jorge"},{"family":"Shafique","given":"Muhammad"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icarcv63323.2024.10821619","URL":"https://doi.org/10.1109/icarcv63323.2024.10821619","source":"crossref"},{"id":"doi:10.33920/sel-10-2412-04","type":"article-journal","title":"Using a 3D system for control of parts during repairs","abstract":"The development of scientifi c hypotheses and approaches to improving the strategy for maintenance and repair of agricultural machinery is one of the current areas in the agro-industrial complex, as it is of paramount importance in the technical support of the machine and tractor fl eet throughout the entire life cycle of machines. Research of methods and means of monitoring parts of automotive and tractor internal combustion engines during defect detection and repair with the development of an automated interactive system with software for monitoring these parameters, using the example of a connecting rod of the K-744 tractor engine.","author":[{"family":"Gerasimov","given":"VS"},{"family":"Tishaninov","given":"IA"},{"family":"Solomashkin","given":"AA"},{"family":"Gradov","given":"EA"}],"issued":{"date-parts":[[2025]]},"DOI":"10.33920/sel-10-2412-04","URL":"https://doi.org/10.33920/sel-10-2412-04","source":"crossref"},{"id":"doi:10.1109/sbr/wre63066.2024.10838036","type":"article-journal","title":"Chameleon Robot: An Innovative Approach to Teaching Colors","abstract":"This project aims to design and build a chameleon robot capable of exploring various environments and changing its color according to the RGB color model to blend into its surroundings. With this innovative approach, we intend to introduce educational robotics into classrooms, offering students a unique experience in learning about colors and their compositions. This is our second project, improved based on the experiences and lessons from the first one. The interdisciplinary project will integrate concepts from design, physics, and arts, with the goal of stimulating student's interest and providing a more comprehensive and practical understanding of colors. By exploring the possibilities of robotics, we aim to make learning more engaging and captivating, encouraging an innovative approach to teaching.","author":[{"family":"Lima","given":"João"},{"family":"Costa","given":"Fabio"},{"family":"Teixeira","given":"Eduarda"},{"family":"Teixeira","given":"Mariana"},{"family":"Araújo","given":"Niviton"},{"family":"Rossiter","given":"Sarah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre63066.2024.10838036","URL":"https://doi.org/10.1109/sbr/wre63066.2024.10838036","source":"crossref"},{"id":"doi:10.29321/maj.10.601147","type":"article-journal","title":"Cultivating arecanut in India: challenges, opportunities and  sustainable practices","abstract":"Arecanut cultivation faces numerous challenges and opportunities. Key issues include vulnerability to climatic variations, declining soil fertility, and pest infestations, which negatively affect crop yield and quality. Traditional farming methods and limited access to modern agricultural knowledge Received: 19 Nov 2024 Revised: 27 Nov 2024 Accepted: 21 Dec 2024 exacerbate these problems. Additionally, fluctuating market prices contribute to the financial instability of areca nut farmers. However, there are promising prospects for arecanut cultivation. Diversified farming practices, such as intercropping with pepper, banana, and cocoa, and integrated farming systems combining crop production with livestock and fish farming can enhance productivity and sustainability. Adopting modern agricultural techniques and improving market access can increase yield quality and economic returns. This study emphasizes the need for a holistic approach to arecanut farming, integrating modern technology, diversified farming practices, and strong support systems to address challenges and seize opportunities for a sustainable future in India","author":[{"family":"Hl","given":"Soundarya"},{"family":"Sharma","given":"Keerthi"},{"family":"Nayak","given":"Meghana"}],"issued":{"date-parts":[[2025]]},"DOI":"10.29321/maj.10.601147","URL":"https://doi.org/10.29321/maj.10.601147","source":"crossref"},{"id":"doi:10.25165/j.ijabe.20261903.10320","type":"article-journal","title":"Discrete element modeling and parameter calibration of vegetable plug seedling root-substrate composites","abstract":"Vegetable plug seedlings form root-substrate composites characterized by granular discreteness and cohesive bonding, which makes the direct measurement of contact parameters difficult and limits accurate simulation of transplanting processes. This study calibrated the key contact parameters and developed a discrete element method (DEM) model for broccoli plug seedling root-substrate composites by integrating physical experiments with EDEM simulations. Root shear tests, substrate angle of repose, sliding friction, and direct shear tests were performed to determine intrinsic mechanical properties. Using Plackett-Burman screening, steepest ascent, and Box-Behnken designs, the optimal combination of root static friction coefficient, critical stress, and bonding radius was obtained, with a relative error of only 0.70% between simulated and measured shear forces. For the substrate, the calibrated contact parameters of substrate-substrate and substrate-steel interactions yielded relative errors of 2.46% and 2.30%, respectively, while the simulated internal friction angle differed by only 2.64% from experimental values. The final composite model, validated through compression tests, showed a yield limit error of 4.22% and closely matched the deformation behavior observed in experiments. These results demonstrate that the proposed DEM model accurately captures the coupled mechanical behavior of flexible roots and cohesive substrates, providing a reliable tool for visual force analysis during transplanting and supporting the design optimization of seedling-picking and soil-seedling interaction mechanisms. Keywords: vegetable plug seedling; root-substrate composites; discrete element method (DEM); contact parameter; calibration DOI: 10.25165/j.ijabe.20261903.10320 Citation: Ye B L, Jin M, Yu X F, Tang T, Fu Y, Yu G H. Discrete element modeling and parameter calibration of vegetable plug seedling root-substrate composites. Int J Agric & Biol Eng, 2026; 19(3): 61–69.","author":[{"family":"Bingliang","given":"Ye"},{"family":"Min","given":"Jin"},{"family":"Xuefu","given":"Yu"},{"family":"Tao","given":"Tang"},{"family":"Yu","given":"Fu"},{"family":"Gaohong","given":"Yu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.25165/j.ijabe.20261903.10320","URL":"https://doi.org/10.25165/j.ijabe.20261903.10320","source":"crossref"},{"id":"doi:10.1016/j.atech.2025.101521","type":"article-journal","title":"Applications of robotics and extended reality in agriculture: A review","abstract":"Agriculture is facing a labour shortage problem that affects global food safety and security. Robotic and extended reality (XR) technologies can prove to be potential solutions to this problem and help with the transition to Agriculture 5.0, although the latter is still at early stages of development. The aim of this study was to map and assess the way robotics and XR can mitigate labour shortage problem. PRISMA methodology was followed to identify relevant studies from the last five years, while frequency and correspondence analyses were used for identifying the corresponding trends. In total 210 relevant research studies were identified. These were analysed under the scope of crops, operations, robotics, XR and Human Robot Interaction (HRI). Vegetable crops (36%) followed by orchard crops (34%) were the most studied crop types. Additionally, the results presented that operation-specific robots were the most used robot type with use in 77 research articles while 140 research articles referred to wheeled robots. Also, the robots did not present any collaboration level with human in the most relevant studies. Collision avoidance was the most frequently implemented safety feature (31 out of 51 research articles) in the studies that included this type of information. Moreover, operations with high demand in accuracy, frequency or labour were connected with robots that were developed for a single operation. Thus, end-effectors that were specialized in one operation were more preferable than generic end-effectors. However, not all studies referred to all these topics, indicating a need for further investigation. Finally, future studies should further explore the use of Mixed Reality, safety, connectivity and data governance.","author":[{"family":"Anastasiou","given":"Evangelos"},{"family":"Ntakos","given":"Georgios"},{"family":"Kanakari","given":"Eirini"},{"family":"Bitsika","given":"Stella"},{"family":"Gemtou","given":"Marilena"},{"family":"Katsaragakis","given":"Manolis"},{"family":"Soudris","given":"Dimitrios"},{"family":"Volioti","given":"Christina"},{"family":"Arvanitou","given":"Elvira"},{"family":"Folina","given":"Maria"},{"family":"Maikantis","given":"Thodoris"},{"family":"Kanidou","given":"Elisavet"},{"family":"Fountouli","given":"Maria"},{"family":"Ampatzoglou","given":"Apostolos"},{"family":"Tsiogkas","given":"Nikolaos"},{"family":"Villa-Henriksen","given":"Andrés"},{"family":"Pedersen","given":"Søren"},{"family":"Tamirat","given":"Tseganesh"},{"family":"Milella","given":"Annalisa"},{"family":"Simopoulou","given":"Soussana"},{"family":"Mygdakos","given":"Gregory"},{"family":"Fountas","given":"Spyros"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.atech.2025.101521","URL":"https://doi.org/10.1016/j.atech.2025.101521","source":"crossref"},{"id":"doi:10.1109/jiot.2025.3597992","type":"article-journal","title":"Adaptive Neural Optimal Backstepping Control for Heterogeneous Multiagent Systems With Noncooperative Target via Identifier–Critic–Actor Algorithm","abstract":"This article proposes a control strategy that integrates simplified optimized backstepping control with RBF neural network (NN) observer to address the issue of heterogeneous multiagent cooperative control. Under the identifier–critic–actor framework, the optimized backstepping control method shapes every regression virtual and actual control to be the most effective solutions of the respective subsystems. Meanwhile, the NN observer approximates the unknown nonlinear equations of the system. The identifier is tasked with estimating unknown dynamics. The critic is responsible for assessing the performance of the system. The actor is charged with carrying out the necessary control actions. The rules for updating the reinforcement learning algorithm stem from the negative gradient of a straightforward, positive-definite function. At the same time, this design scheme can break through the limitation of the persistent excitation condition required by most existing optimal control methods. Ultimately, the efficacy of the approach is confirmed both through theoretical analysis and simulation studies. The method proposed in this article will provide support for related research on embodied artificial intelligence (AI) agent systems conducting self-organized collaboration.","author":[{"family":"Shi","given":"Baiming"},{"family":"Chen","given":"Tao"},{"family":"Chen","given":"Jian"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/jiot.2025.3597992","URL":"https://doi.org/10.1109/jiot.2025.3597992","source":"crossref"},{"id":"doi:10.1007/978-3-031-81688-8_15","type":"article-journal","title":"A Review of Theory of Mind and Robotics: Mind Reading in Human-Robot Interaction for Proactive Social Robots","abstract":"Social robots are becoming more prevalent in our daily life and will soon become part of our society. To answer this challenge, several studies focused on how we could integrate those technologies into the current world to help humans in their daily tasks. Many areas are involved in those challenging issues, and there is a particular focus on taking inspiration from psychology studies to develop autonomous machines. One of them is interested in using Theory of Mind(ToM), a human ability that enables us to infer our own mental states and other people’s mental states. However, it is a challenging task to integrate this ability in robotics. Through an analysis of the literature, we aim to provide some examples and guidelines on applying ToM in robotics to improve their behaviours. This review gives researchers a general view of the domain and insights on how they can contribute to its development.","author":[{"family":"Hellou","given":"Mehdi"},{"family":"Vinanzi","given":"Samuele"},{"family":"Cangelosi","given":"Angelo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1007/978-3-031-81688-8_15","URL":"https://doi.org/10.1007/978-3-031-81688-8_15","source":"crossref"},{"id":"doi:10.1213/ane.0000000000007658","type":"article-journal","title":"Evaluation of a Novel, Image-Guided Robotic Intubation Platform for Difficult Airways: A Prospective Observational Study","abstract":"Safe and successful management of difficult tracheal intubations (DTIs) remains a significant challenge due to anatomical variability, patient comorbidities, and operator-dependent factors. While video laryngoscopy (VL) has improved first-attempt success rates, failures still occur in 11% to 45% of cases,1–4 with ultimate failure rates between 5.2% and 7.3%.5 The primary aim of this prospective observational study was to evaluate efficacy of the use of a novel, handheld, image-guided robotic intubation system Spiro-VISTA (Spiro Robotics, Inc) designed to enhance precision, control and procedural success in patients with difficult airways. METHODS The trial was conducted at Kaunas Hospital of the Lithuanian University of Health Sciences from October to November 2024, with written informed consent obtained from all patients. The study was approved by the local Institutional Ethics Committee and the Lithuanian Ministry of Health, was prospectively registered with the European Database on Medical Devices (EUDAMED, registration number CIV-LT-24-08-048614), and adhered to Good Clinical Practice (GCP) and STROBE guidelines (https://www.strobe-statement.org). The trial included 30 adult patients (ASA physical status 1-3) with anticipated difficult airways presenting for elective surgery. The inclusion criteria required at least one predictor of difficult direct or video laryngoscopy based on standard airway assessment tests, a history of difficult intubation, BMI ≥ 35 kg/m², large neck circumference (NC), or specific independent predictors of difficult VL, including head and neck cancer diagnosis, neck pathology (a mass, a scar, radiation changes), short thyromental (TMD) distance, NC:TMD ratio of ≥ 5, a simplified Arné score ≥ 11 (Supplemental Digital Content, Table S1, https://links.lww.com/AA/F399), and others.1,2,6–9 Awake intubation was performed at the operator’s discretion; such patients, and those with advanced cardiovascular or pulmonary disease, were excluded. The anesthetic protocol and study procedures were standardized for all patients. All patients were orotracheally intubated by study investigators (A.K., D.B., J.B., and L.K.) using Spiro-VISTA™ (Video Intubation System for Total Access), which integrates dual VL and video bronchoscopy guidance with the joystick-controlled, precision robotic (servo-operated) intubation interface (Figure and Video 1). {\"href\":\"Single Video Player\",\"role\":\"media-player-id\",\"content-type\":\"play-in-place\",\"position\":\"float\",\"orientation\":\"portrait\",\"label\":\"Video 1\",\"caption\":\"\",\"object-id\":[{\"pub-id-type\":\"doi\",\"id\":\"\"},{\"pub-id-type\":\"other\",\"content-type\":\"media-stream-id\",\"id\":\"1_aq8i5d3r\"},{\"pub-id-type\":\"other\",\"content-type\":\"media-source\",\"id\":\"Kaltura\"}]} Figure.: Spiro-VISTA essential components, controls and assembly. Spiro-VISTA is an investigational airway device not yet cleared or approved for commercial use by the FDA or other regulatory bodies. Spiro-VISTA™ integrates video laryngoscopy (VL) and a robotic (servo-operated), disposable flexible intubation scope (FIS), controlled by an operator using a joystick and buttons embedded in a specialized 2-channel disposable endoscopy blade. The system currently supports standard endotracheal tubes (ETT) from 5.0 to 7.5 mm ID. Fully assembled spiro-VISTA (A) and its key components (A and B): 1—A reusable handheld unit with integrated VL baton and servo controls. 2—A reusable video cable connecting Spiro-VISTA to Spiro’s split-screen monitor (not shown). 3—A disposable, robotic FIS that attaches to the servo control section of the handheld unit. 4—A 2-channel disposable blade with manual FIS controls (highlighted in blue circle), including a joystick and advancement buttons. When the blade is attached, its controls automatically interface with the servo control section of the handheld unit. 5—A standard endotracheal tube (ETT) preloaded over FIS and positioned within the right channel of the blade. The left channel accommodates the VL baton. C, Close-up view of the distal dual-video camera section of Spiro-VISTA. The intubation is observed and controlled fully from above and below the vocal cords using video laryngoscopy (VL) and the flexible intubation scope (FIS) cameras. The VL camera (right) and FIS camera (left) are positioned side by side at the distal end of the 2-channel disposable blade. When the blade tip is engaged either in the vallecula or beneath the epiglottis, both cameras are optimally placed near the larynx, enabling precise, servo-controlled FIS navigation into the trachea. The wire reinforced ETT in the FIS channel is depicted for demonstration purposes only.The primary outcome was the first-attempt intubation success rate. Secondary outcomes included the incidence of adverse events and complications (moderate hypoxemia [SpO2 38 cm in females and >40 cm in males.fVAS: visual analog scales (0–100) reflecting operator’s subjective assessment of the usability of the device, with “0” indicating best performance (minimum intubation force and maximum ease of use).Confidence intervals for FPS and adverse events/complications were determined using Clopper-Pearson exact method. DISCUSSION This study represents the first successful clinical evaluation of a novel, image-guided robotic intubation system that integrates advanced airway visualization with precision-guided navigation for managing difficult airways. The study results suggest a high procedural success rate and a favorable safety profile for Spiro-VISTA in this prospective observational trial. The 100% first-attempt intubation success observed with Spiro-VISTA may be attributed to full airway visualization afforded by dual VL and FIS cameras, precision robotic FIS navigation facilitated by the proximity of the FIS camera to the glottic opening, and full operator control of intubation both above and below the vocal cords. Additionally, indwelling FIS facilitates ETT advancement, with immediate confirmation of proper ETT placement. A video demonstrating Spiro-VISTA intubation of the study patient with recurrent laryngeal cancer and post-radiation glottic stenosis highlights the advanced features of the device (Video 2). {\"href\":\"Single Video Player\",\"role\":\"media-player-id\",\"content-type\":\"play-in-place\",\"position\":\"float\",\"orientation\":\"portrait\",\"label\":\"Video 2\",\"caption\":\"\",\"object-id\":[{\"pub-id-type\":\"doi\",\"id\":\"\"},{\"pub-id-type\":\"other\",\"content-type\":\"media-stream-id\",\"id\":\"1_6mrjeoxl\"},{\"pub-id-type\":\"other\",\"content-type\":\"media-source\",\"id\":\"Kaltura\"}]} The consistency in intubation time across operators suggests comparable procedural efficiency, which was not affected by the number of predictors of intubation difficulty. The Cormack-Lehane grade 1 and 2a views were achieved with Spiro-VISTA in 40% and 56.7% of patients, consistent with other studies reporting a predominance of favorable laryngeal views in cases where VL intubation nevertheless remained challenging.2,7 It may also reflect the versatility of the Spiro-VISTA dual endoscopy blade, which effectively engages both above and below the epiglottis. Although this study did not include a direct VL comparative group, a review of the literature suggests that Spiro-VISTA’s success rates and procedural efficiency are within or exceeding reported VL benchmarks. Other studies report VL first-attempt success rate of <70% in comparable patient cohorts.2,3 The operation of Spiro-VISTA conceptually aligns with the dual video intubation (DVI) technique when VL and FIS are used simultaneously by 2 operators. DVI has been reported to increase first-attempt intubation success rates by nearly 40% and reduce DTI-related complications by over 90% compared to the use of VL alone.2 However, this technique requires the immediate availability of 2 separate devices and 2 trained operators, which limits its practicality in many clinical settings.2 Spiro-VISTA™ has been designed as a single-operator, on-demand platform with integrated visualization, precision-controlled navigation, and an intuitive interface, which may offer workflow advantages over DVI in DTI settings and further reduce operator variability. The development of Spiro-VISTA also aligns with the growing paradigm shift toward advancing robotic-assisted technologies in airway management.10 In summary, the study results suggest a high procedural success rate and no adverse events during use of the Spiro-VISTA in this prospective observational trial. Unlike traditional video laryngoscopes, Spiro-VISTA integrates advanced image guidance with precision robotic control, representing a novel approach to difficult airway management. To the best of our knowledge, no other intubation devices currently offer this type of functionality.11 Further clinical evaluation of Spiro-VISTA’s efficacy and safety is warranted in larger trials, including its comparison with established DTI techniques, such as VL and FIS. ACKNOWLEDGMENTS The authors thank Dr Andrius Macas for his support in coordinating the logistics of the study. DISCLOSURES Conflicts of Interest: V. Nekhendzy is the founder of Spiro Robotics, Inc., holds equity in the company, and serves as a paid consultant to the company. This study was sponsored by Spiro Robotics, Inc. The other authors were supported by Spiro Robotics, Inc., for their role in conducting the study. No other authors declared conflicts of interest. Funding: This study was funded by Spiro Robotics, Inc., which developed the investigational device (Spiro-VISTA) used in this study. The sponsor had no role in the study design, study conduct, or data collection. This manuscript was handled by: Narasimhan Jagannathan, MD, MBA. ASSOCIATED VIDEO The video can be accessed at https://journals.lww.com/cases-anesthesia-analgesia/10.1213/ANE.0000000000007658 Video 1. The Flexible Intubation Scope (FIS) articulates 360 degrees and advances with robotic precision, enabling controlled robotic navigation through the airway. The operator maneuvers the FIS using a joystick and buttons, which interface seamlessly with the servo control system, allowing for intuitive, fine-tuned, and responsive control adjustments during intubation. Video courtesy Spiro Robotics, Inc. Video 2. Spiro-VISTA™ is inserted similarly to traditional video laryngoscopy (VL) devices. With the tip of the blade placed either above or below the epiglottis, the VL and flexible intubation scope (FIS) cameras are positioned side by side near the vocal cords. This dual-camera setup simplifies the identification of anatomical landmarks for more accurate and controlled airway management. The FIS controlled navigation of the airway complements the VL's panoramic view with real-time, dynamic and detailed airway imaging. High-resolution video feeds from both cameras are displayed side by side on Spiro's split-screen monitor, allowing the operator to maintain full control of intubation all the way into the trachea. Once the FIS reaches the tracheal carina, the operator advances the preloaded ETT, instantly confirming its tracheal placement through direct visualization. Spiro-VISTA™ is then removed, and ETT positioning is further verified using standard methods. Video courtesy Spiro Robotics, Inc.","author":[{"family":"Nekhendzy","given":"Vladimir"},{"family":"Karbonskienė","given":"Aurika"},{"family":"Bilskienė","given":"Diana"},{"family":"Borodičienė","given":"Jurgita"},{"family":"Kalibatienė","given":"Lina"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1213/ane.0000000000007658","URL":"https://doi.org/10.1213/ane.0000000000007658","source":"crossref"},{"id":"doi:10.1177/21695172261424788","type":"article-journal","title":"Ternary Origami Spring Actuator: Multimodal Deformation via Programmable Folding Sequences for Bioinspired Soft Robotics","abstract":"Origami provides an efficient methodology for reconfigurable fabrication, enabling the creation of diverse origami structures through programmable folding techniques. However, conventional fold-driven structures are often limited to predefined deformation modes, while multimodal designs typically require multiple independent actuators. To address these challenges, this study proposes a ternary origami spring structure that integrates multimodal deformations into its folding sequence and achieves single pneumatic source-driven actuation. The core architecture comprises three interwoven inflatable strips, forming a programmable and reconfigurable origami actuator. Our investigation revealed that editing the folding sequence generates complex spatial trajectories. Building on this discovery, we developed a simulation algorithm to predict shape deployment based on folding sequences and utilized it for computational design. Following bio-inspired principles, functional prototypes were fabricated to validate shape-programming capabilities and operational efficacy. The independent folding scheme was also explored. This work demonstrates significant potential for autonomous design, rapid prototyping, and unmanned deployment of soft robotics in space applications.","author":[{"family":"Qian","given":"Kewei"},{"family":"Xie","given":"Fang"},{"family":"Nie","given":"Pengshuai"},{"family":"Li","given":"Zhao"},{"family":"Gong","given":"Xiaobo"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1177/21695172261424788","URL":"https://doi.org/10.1177/21695172261424788","source":"crossref"},{"id":"doi:10.25165/j.ijabe.20251805.9719","type":"article-journal","title":"YOLOv8np-RCW: A multi-task deep learning model for comprehensive visual information in tomato harvesting robot","abstract":"In greenhouse environments, using automated machines for tomato harvesting to reduce labor consumption is a future development trend. Accurate and effective visual recognition is essential to accomplish harvesting tasks. However, most current studies use various models to gain harvesting information in multiple steps, resulting in heavy calculation costs, poor real-time availability, and weak recognition precision. In this study, an improved YOLOv8np-RCW end-to-end model based on YOLOv8n pose is proposed to simultaneously detect tomato bunches, maturity, and keypoints using a decoupled-head structure. The model integrates a ResNet-enhanced RepVGG architecture for a balance of accuracy and speed, employs the CARAFE upsampling algorithm for a larger receptive field with lightweight design, and optimizes the loss function with WIoU loss to enhance bounding box prediction, maturity detection, and keypoint extraction. Experimental results indicate that mAP50 of YOLOv8np-RCW model for bounding box and keypoints is 87.3% and 86.8% respectively, which is 6.2% and 5.5% higher than YOLOv8n pose model. Completing the tasks of bunch detection, maturity assessment, and keypoint localization requires only 9.8 ms. Euclidean distance error is less than 20 pixels in detecting keypoints. Based on this model, a method is proposed to quickly determine the orientation of tomato bunches using geometric cross-product and cross-multiplication calculations from keypoint 2D information, providing guidance for the motion planning of the end-effector. In field experiments, the robot achieved a harvesting success rate of 68%, with an average time of 10.8366 seconds per tomato bunch. Keywords: tomato bunch detection, maturity detection, keypoint detection, harvesting robots DOI: 10.25165/j.ijabe.20251805.9719 Citation: Ai X Y, Zhang T X, Yuan T, Zheng X J, Xiong Z M, Yuan J C. YOLOv8np-RCW: A multi-task deep learning model for comprehensive visual information in tomato harvesting robot. Int J Agric & Biol Eng, 2025; 18(5): 246–258.","author":[{"family":"Xinyi","given":"Ai"},{"family":"Tianxue","given":"Zhang"},{"family":"Ting","given":"Yuan"},{"family":"Xiajun","given":"Zheng"},{"family":"Ziming","given":"Xiong"},{"family":"Jiace","given":"Yuan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.25165/j.ijabe.20251805.9719","URL":"https://doi.org/10.25165/j.ijabe.20251805.9719","source":"crossref"},{"id":"doi:10.1109/sbr/wre63066.2024.10837845","type":"article-journal","title":"Robotics Club Students Create Interactive Model of Ilse Teske Sculpture Park","abstract":"This article describes the creation of an interactive model of the Ilse Teske Sculpture Park by students from 6th to 9th grade at Professor Georgina de Carvalho Ramos da Luz Elementary School. The project was born from an activity developed by the Educational Robotics Club, which aimed to integrate technology and education. Using Arduino robotics kits, the students applied concepts of computational thinking, digital culture, and programming to build an interactive replica of the park. The project also sought to promote the cultural heritage of Brusque, Santa Catarina, encourage creativity and innovation among students, and foster educational tourism in the city. There were some challenges, but the students persisted and completed the model. They successfully presented it at the 1st Education, Technology, Innovation, and Science Exhibition, where they won second place in the Tinkercad and Arduino categories.","author":[{"family":"Sant'ana","given":"Vanessa"},{"family":"Bottamedi","given":"Venicio"},{"family":"Maffezzolli","given":"Graziela"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre63066.2024.10837845","URL":"https://doi.org/10.1109/sbr/wre63066.2024.10837845","source":"crossref"},{"id":"doi:10.1016/j.rcim.2025.103113","type":"article-journal","title":"Transformation of industrial robotics with natural language models: Recent progress and future prospects","abstract":"Integration of Natural Language Models (NLMs) into industrial robots enhances operational efficiency and intuitive human-robot interactions, and thus it represents a significant opportunity in the pursuit of Industry 4.0/5.0. This paper provides a comprehensive survey on the technological advancements and applications in this area, by emphasizing their role in improving task execution, cognitive capabilities, and communication in the industrial environments. Meanwhile, related challenges are analyzed and discussed. In particular, NLMs inherently struggle with contextual understanding, which can lead to inappropriate or impractical outputs in complex industrial environments. Also, the external noise and the need for real-time responsiveness present further complications to the effectiveness of NLMs. Concerns regarding safety, transparency, privacy, and ethical usage amplify the need for regulatory considerations. In addition, standardized approaches to interpreting vague human instructions are called for to improve the interaction between humans and robots. It is pointed out that the broader impacts of NLMs can extend beyond industrial environments into commercial and social settings, thereby enhancing service quality and customer interactions. As a result, the review is expected to provide insights on how to effectively integrate NLMs with robotic systems, stimulate research to address the remaining challenges, and enhance transparency to improve social acceptability.","author":[{"family":"Yu","given":"Zhao"},{"family":"Zhang","given":"Peize"},{"family":"Shi","given":"Jing"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.rcim.2025.103113","URL":"https://doi.org/10.1016/j.rcim.2025.103113","source":"crossref"},{"id":"doi:10.3390/robotics15040075","type":"article-journal","title":"Bibliometric Analysis on Control Architectures for Robotics in Agriculture","abstract":"(1) Background: Robotics and advanced control architectures are increasingly central to the development of precision agriculture (PA), supporting automated, efficient, and data-driven farm management. This review offers a comprehensive analysis of scientific literature on robotic control systems applied to PA, focusing on technological progress, methodological approaches, and emerging research trends. (2) Methods: A systematic review was conducted according to PRISMA guidelines, combined with a bibliometric analysis using VOSviewer to examine term co-occurrences, thematic clusters, and topic evolution over time. Publications indexed in Scopus between 1976 and 2025 were analyzed. (3) Results: Results reveal a sharp growth in publications after 2010, with a strong acceleration from 2015 onward, reflecting advances in autonomous systems and the integration of artificial intelligence, sensor technologies, and distributed software frameworks. Three principal clusters emerged: algorithmic and control methods (e.g., neural networks, path tracking, simulation); sensing and infrastructure technologies (e.g., LiDAR, SLAM, IMU, ROS, deep learning-based perception); and agronomic applications, including crop monitoring, irrigation, yield estimation, and farm management. Citation trends indicate a shift from foundational control theory to AI-driven solutions. (4) Conclusions: Overall, control architectures are evolving toward modular, scalable, and interoperable systems enabling autonomous decision-making in complex agricultural environments.","author":[{"family":"Figorilli","given":"Simone"},{"family":"Violino","given":"Simona"},{"family":"Vasta","given":"Simone"},{"family":"Pallottino","given":"Federico"},{"family":"Manca","given":"Giorgio"},{"family":"Bianchi","given":"Lorenzo"},{"family":"Costa","given":"Corrado"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/robotics15040075","URL":"https://doi.org/10.3390/robotics15040075","source":"crossref"},{"id":"doi:10.4018/979-8-3693-8019-2.ch014","type":"article-journal","title":"Real-Time Data Processing in Agricultural Robotics","abstract":"This chapter emphasizes the integration of IoT and computer vision technology improving precision farming and also highlights the crucial role that real-time data processing plays in farm robots. According to research studies, real-time data enhances the efficiency of operations. The spraying can be even more accurate by up to 20% and the operating costs reduced by up to 12%. In addition to discussing topics like data accuracy and cybersecurity, this chapter still addressed benefits for crop monitoring and autonomous spraying in the form of instantaneous feedback. This further explains some future research areas under AI, climate-smart behaviors, and emergent technology. Some of the takeaway points of this chapter are that there is so much potential to greatly increase agricultural output and sustainability through these advancements. Apart from that, it also includes the requirements of continuous innovation and adaptations for these technologies to ensure that they meet today's agriculture needs.","author":[{"family":"Hoque","given":"Azmirul"},{"family":"Padhiary","given":"Mrutyunjay"},{"family":"Prasad","given":"Gajendra"},{"family":"Kumar","given":"Kundan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.4018/979-8-3693-8019-2.ch014","URL":"https://doi.org/10.4018/979-8-3693-8019-2.ch014","source":"crossref"},{"id":"doi:10.71443/9789349552050-02","type":"article-journal","title":"MARKOV DECISION PROCESSES FOR MODELING SEQUENTIAL DECISION MAKING IN ROBOTICS","abstract":"Autonomous robotic systems increasingly operate in dynamic and uncertain environments where intelligent action selection depends on the ability to evaluate long-term consequences rather than isolated decisions. Sequential decision making has therefore emerged as a fundamental research area for enabling adaptive perception, planning, navigation, manipulation, and collaborative task execution across diverse robotic applications. Among the available mathematical frameworks, Markov Decision Processes (MDPs) provide a rigorous probabilistic model for representing state transitions, action selection, reward optimization, and policy generation under uncertainty. The mathematical principles underlying MDPs establish the foundation for dynamic programming, optimal control, and reinforcement learning, enabling robotic systems to identify decision policies that maximize cumulative long-term rewards while adapting to continuously evolving operational conditions. This chapter presents a comprehensive examination of MDPs as a unified framework for modeling sequential decision making in robotics by integrating theoretical concepts with computational methodologies and practical implementation strategies. Fundamental principles of sequential decision making, mathematical formulations of MDPs, Bellman equations, value functions, policy representation, transition dynamics, and reward structures are systematically discussed to establish the theoretical basis of probabilistic robotic planning. Classical solution algorithms, including value iteration, policy iteration, approximate dynamic programming, and computational complexity analysis, are examined to highlight their convergence characteristics and scalability in large decision spaces. The chapter further explores MDP-based modeling for mobile robot navigation, robotic manipulation, autonomous exploration, and multi-robot coordination, demonstrating the versatility of probabilistic decision models across heterogeneous robotic platforms. The relationship between MDPs and reinforcement learning is analyzed to illustrate the evolution of intelligent robotic decision-making from model-based optimization toward data-driven autonomous learning. Emerging developments involving hierarchical decision models, safe reinforcement learning, explainable artificial intelligence, digital twins, edge intelligence, cloud robotics, and multi-agent autonomous systems are also reviewed to emphasize future research opportunities.","author":[{"family":"Singh","given":"Rajan"},{"family":"Tiwari","given":"Nidhi"},{"family":"Tiwari","given":"B"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71443/9789349552050-02","URL":"https://doi.org/10.71443/9789349552050-02","source":"crossref"},{"id":"doi:10.71443/9789349552050-14","type":"article-journal","title":"INTEGRATION OF REINFORCEMENT LEARNING WITH SENSOR DATA IN SMART ROBOTICS","abstract":"Smart robotics has advanced significantly with the integration of reinforcement learning and sensor technologies, enabling robots to perform tasks with greater intelligence, adaptability, and autonomy. Reinforcement learning allows robots to learn optimal actions through interaction with the environment, while sensors provide real-time information required for perception, navigation, object detection, and decision-making. The combination of these technologies improves the ability of robots to operate efficiently in dynamic and uncertain environments across various application domains.This chapter presents the fundamental concepts of smart robotics, reinforcement learning, and robotic sensor technologies, followed by an overview of sensor data processing, sensor fusion, and deep reinforcement learning techniques. The discussion explains how reinforcement learning utilizes sensor information to support autonomous navigation, adaptive control, and real-time decision-making. Simulation environments, digital twins, sim-to-real transfer learning, edge intelligence, cloud robotics, and performance evaluation methods are also discussed to highlight recent developments in intelligent robotic systems. Practical applications in industrial automation, healthcare, agriculture, logistics, search-and-rescue, and service robotics demonstrate the effectiveness of integrating reinforcement learning with sensor data. The chapter concludes by discussing current challenges and future research directions for developing reliable, efficient, and intelligent autonomous robotic systems.","author":[{"family":"Sundar","given":"R"},{"family":"Garg","given":"Riddhi"},{"family":"Rohini","given":"G"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71443/9789349552050-14","URL":"https://doi.org/10.71443/9789349552050-14","source":"crossref"},{"id":"doi:10.1155/joro/9079725","type":"article-journal","title":"Design and Experimental Characterization of a Tendon‐Driven Anthropomorphic Finger With Adaptive Compliance","abstract":"The primary objective of a soft robotic finger is to reproduce the functional versatility of the human hand by incorporating intrinsic flexibility. By mimicking the human finger’s morphology, structural organization, and kinematic behavior, the system enables anthropomorphic motion that provides enhanced adaptability and dexterity. This study introduces the design and evaluation of an underactuated, anthropomorphic finger prototype actuated by a pneumatic muscle. The natural compliance of the actuator allows the finger to adapt its shape to the contours of the grasped object. As a result, the proposed design supports both biomimetic motion in free space and adaptive grasping actions during interaction with a wide range of objects.","author":[{"family":"Bakos","given":"Blanka"},{"family":"Deaconescu","given":"Andrea"},{"family":"Deaconescu","given":"Tudor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1155/joro/9079725","URL":"https://doi.org/10.1155/joro/9079725","source":"crossref"},{"id":"doi:10.1002/rob.70003","type":"article-journal","title":"Development of an Agricultural Robot Taskmap Operation Framework","abstract":"ABSTRACT Robotic technology in precision crop farming has the potential to minimize inputs, such as labor, fertilizer, or plant protection products, maximizing the net yield while reducing the environmental impact. To maximally exploit the benefits of precision crop farming, it has to be applied continuously over multiple years, which requires (robotic) technology for a wide range of agricultural operations. Researchers need access to (noncommercial) robot platforms with complete mechanical and software controllability to investigate new applications that could unlock the true potential of precision farming. This study presents the agricultural robot taskmap operation framework (ARTOF), which provides common functionality for robots with different vehicle configurations to execute task maps in crop farming applications based on global navigation satellite system positioning. The two‐layered software stack has a mechatronic layer and an operational layer. The mechatronic layer performs motion control and includes machine safety to meet the required performance level in correspondence with European regulations. The operational layer performs autonomous implement and navigation control. Add‐ons interact with the operational layer using the ARTOF Redis interface and increase flexibility. Hardware‐in‐the‐loop testing enables static end‐to‐end testing and minimizes the developing time and operational faults when developing new functionality. To demonstrate the framework's flexibility, it was integrated into four in‐house developed and modified agricultural robots with four‐wheel drive, four‐wheel steering (4WD4WS), skid steering, and Ackerman steering vehicle configurations. These robots performed 11 applications under real practice conditions in arable farming and horticulture for—in total—more than 11 km of field application. The power consumption, navigation accuracy, and software usability were evaluated. An average navigation accuracy of 1.0 cm was achieved during hoeing with a 4WD4WS robot using the newly developed navigation controller. This new open‐source software framework enables the rapid validation of agricultural robotic research to broaden the number of precision crop farming applications and fully exploit their potential.","author":[{"family":"Willekens","given":"Axel"},{"family":"Temmerman","given":"Sébastien"},{"family":"Wyffels","given":"Francis"},{"family":"Pieters","given":"Jan"},{"family":"Cool","given":"Simon"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/rob.70003","URL":"https://doi.org/10.1002/rob.70003","source":"crossref"},{"id":"doi:10.1109/arso68304.2026.11536115","type":"article-journal","title":"SoBots: A Domain Ontology for Social Robotics","abstract":"Ontological models have proven to be an effective approach in robot cognition with applications in task planning or semantic-driven communication. However, to the authors' knowledge, no domain ontology currently exists for the specialized field of social robotics. Therefore, this paper introduces SoBots, a meta-model that provides a semantic foundation for social robotics. SoBots integrates the Sharework Ontology for Human-Robot Collaboration with DOLCE+DnS Ultralite and the Semantic Sensor Network ontology, and extends them with axioms for capability-based task execution, Belief-Desire-Intention modeling, and social interaction. The resulting domain-specific ontology explicitly links tasks, agent capabilities, intentions, and interaction structures. Beyond the theoretical level, a gap often remains between semantic modeling and practical applicability. To address this, the paper further presents an interactive simulation framework for human-robot collaboration that builds on the proposed semantic foundation. The framework leverages task-decomposition graphs from the Sharework Ontology to automatically derive discrete-event simulation contexts based on an agent's occurrent desires and intentions.","author":[{"family":"Zebisch","given":"Raoul"},{"family":"Merz","given":"Nina"},{"family":"Franke","given":"Jörg"},{"family":"Reitelshöfer","given":"Sebastian"},{"family":"Schilp","given":"Johannes"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1109/arso68304.2026.11536115","URL":"https://doi.org/10.1109/arso68304.2026.11536115","source":"crossref"},{"id":"doi:10.1080/01691864.2026.2642636","type":"article-journal","title":"FocusViT: dynamic patch focus for transformer-based gaze estimation","abstract":"Eye gaze information is an important signal for the robot to understand the attention of the human user. Therefore, multiple advanced model architectures have been developed for the gaze estimation task, including the recent vision transformer (ViT). However, due to the patch grid input, vanilla ViTs breaks the fine ocular details into different patches and floods with redundant information from the forehead, cheeks, and background. In this paper, we introduce FocusViT, a lightweight and end-to-end differentiable framework that adapts ViT for the gaze estimation task. It uses a Patch Translation Module to translate patches on informative content dynamically, and then employs a Perturbed Top-K operator to select only the most informative patches for processing. In this way, the proposed method can efficiently use the most informative patches from the full-face image for the gaze estimation task. Our experiments show that combining patch translation and selection reduces the gaze angular error of the ViT model on both the ETH-XGaze and MPIIFaceGaze datasets. Extensive ablation studies confirm that patch translation and token selection are complementary mechanisms that work in synergy to improve model performance.","author":[{"family":"Sochirca","given":"Dan"},{"family":"Chew","given":"Jouh"},{"family":"Zhang","given":"Xucong"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/01691864.2026.2642636","URL":"https://doi.org/10.1080/01691864.2026.2642636","source":"crossref"},{"id":"doi:10.1080/01691864.2026.2664845","type":"article-journal","title":"Swarm self-clustering for communication-denied environments without global positioning","abstract":"In this work, we investigate swarm self-clustering, where robots autonomously organize into spatially coherent groups using only local sensing and decision-making, without relying on external commands, global positioning, or inter-robot communication. This fully decentralized approach enables each robot to form and maintain stable clusters by responding solely to distances from nearby neighbors, as detected through onboard range sensors with limited fields of view. Motivated by real-world scenarios such as autonomous underwater robot retrieval and human gathering during emergency response, the proposed method is designed for GPS-denied and communication-constrained environments. Unlike conventional approaches, it requires no prior knowledge of cluster parameters such as size, number, or member identity, making it highly adaptable to unpredictable settings. A mechanism that enables each robot to adaptively alternate between consensus-based and random goal assignment based on local neighborhood size, ensuring robust, scalable, and untraceable clustering independent of initial configuration. Through extensive simulations and real-robot experiments, we demonstrate the method's scalability, empirical convergence, and robustness under varying initial conditions and dynamic robot additions. The proposed communication-free approach outperforms local-only baselines across standard cluster quality metrics, producing clusters that exhibit untraceability even under identical initial conditions.","author":[{"family":"Jain","given":"Sweksha"},{"family":"Katole","given":"Rugved"},{"family":"Vachhani","given":"Leena"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/01691864.2026.2664845","URL":"https://doi.org/10.1080/01691864.2026.2664845","source":"crossref"},{"id":"doi:10.1016/j.cogr.2025.11.001","type":"article-journal","title":"Self-adaptive control of a two-point contact gripper for the precise handling of compliant objects in industrial robotics","abstract":"This paper presents a novel adaptive control framework for robotic grippers that handles a wide range of compliant objects by mimicking human grasping behaviour. The proposed system integrates three distinct control strategies: classical Proportional-Integral-Derivative (PID), Proportional-Integral-based Fuzzy Logic Control (PI-FLC), and Reinforcement Learning (RL) to achieve precise and safe force modulation during object manipulation. A two-finger gripper prototype was developed and experimentally validated using objects of varying stiffness levels, including rigid (iron, plastic) and deformable materials (silicone, foam, sponge). Real-time force control was benchmarked against human-defined reference profiles derived from tactile interaction experiments. The results demonstrate that while PID control provides satisfactory performance for rigid objects, it fails to adapt to nonlinear dynamics in soft materials. In contrast, the PI-Fuzzy and RL controllers can achieve superior force tracking, stability, and generalisation, closely aligning with human-like grasping patterns. The PI-Fuzzy controller excels in rule-based adaptability, while RL shows potential in learning optimal strategies across different compliance levels. This study underscores the significance of integrating classical and intelligent control strategies to improve robotic dexterity, safety, and autonomy, particularly in unstructured environments. The findings have meaningful implications for industrial automation, human-robot collaboration, and the effective manipulation of objects with varying stiffness.","author":[{"family":"Cheewaratchanon","given":"Sarawit"},{"family":"Auysakul","given":"Jutamanee"},{"family":"Neranon","given":"Paramin"},{"family":"Romyen","given":"Arisara"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.cogr.2025.11.001","URL":"https://doi.org/10.1016/j.cogr.2025.11.001","source":"crossref"},{"id":"doi:10.1007/s12369-026-01385-z","type":"article-journal","title":"Dictator Game Decisions with Robot Recipients","abstract":"Abstract While extensive research has examined human-human interactions in dictator games, studies exploring human-robot dictator games remain scarce. Here, we conducted multiple studies in India and The Netherlands to explore how participants allocate money to robot recipients. Using various versions of the dictator game paradigm with both hypothetical and real stakes, we measured offers toward 18 different robots while also assessing participants’ perceptions of these robots. Overall, our findings reveal that participants allocated money to robot recipients in dictator games, with offers varying significantly for hypothetical versus real monetary outcomes, mirroring patterns observed in the existing human-human dictator game literature. Factor analyses identified three key characteristics – perceived likeability, anthropomorphism, and social functionality of the robots – as consistent predictors of offers made in the dictator games. Results were broadly consistent across participants from the two countries. We discuss similarities and differences observed across dictator game variations, key predictors of offers made to robots, and cross-country differences in robot perception, along with study limitations. Our results offer empirical insights into the dynamics of human-robot economic interactions that could inform the design of socially interactive robots.","author":[{"family":"Dev","given":"Avantika"},{"family":"Kleijn","given":"Roy"},{"family":"Mukherjee","given":"Sumitava"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s12369-026-01385-z","URL":"https://doi.org/10.1007/s12369-026-01385-z","source":"crossref"},{"id":"doi:10.1007/s10015-025-01106-1","type":"article-journal","title":"Affordance-driven symbol network construction via large language models","abstract":"Abstract To enable robots to coexist with humans in dynamic real-world environments, they must possess both autonomy and versatility. Such autonomy requires the ability to interpret situations and select appropriate actions, which goes beyond simple image recognition. Humans rely on common sense and “affordances”—perceived action possibilities in a given context—to determine behavior. For example, the presence of an apple on a plate may lead to different reactions depending on its placement. While recent advancements in object detection models like YOLO have enabled AI to recognize and relate objects, these systems lack affordance information and thus struggle with situational understanding. Affordances are a form of implicit knowledge closely tied to human common sense, making them difficult for conventional AI to process. However, large language models (LLMs) such as ChatGPT, which have been trained on vast human-generated texts, may possess a form of embedded common sense. Building on this, we propose a method for automatically acquiring affordances from symbols using LLM outputs. Our method involves three steps: generating descriptive text via LLMs, analyzing it through morphological and dependency parsing to reconstruct a symbol network, and then calculating affordances based on the network’s structure. An initial experiment using the object “apple” demonstrated the ability to extract scene-specific affordances with high explainability. Ultimately, this approach enables affordance re-cognition in a manner similar to human reasoning.","author":[{"family":"Arii","given":"Kazuma"},{"family":"Liu","given":"Shunsuke"},{"family":"Kurihara","given":"Satoshi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s10015-025-01106-1","URL":"https://doi.org/10.1007/s10015-025-01106-1","source":"crossref"},{"id":"doi:10.1016/j.robot.2025.105271","type":"article-journal","title":"Deterministic delay-aware reinforcement learning","abstract":"Reinforcement Learning (RL) has effectively paved the way in achieving robotic control during the past decade. As a result, the avenue of integrating RL-powered robotic control and teleoperation has caught the attention of researchers. Every RL framework involves the basis of suitable observation and action communication between the environment and the agent, and the involvement of teleoperation can introduce random time delays within the said communication process. Achieving robotic control under such constraints remains an untapped area in the domain of reinforcement learning. We take the initiative to achieve the goal of robotic control while handling delays in the RL setting based on a fitting Markov Decision Process (MDP) structure. Our algorithm will learn a deterministic policy and can tackle control environments, especially robotic manipulation environments, using observations with proprioceptive information. We methodically present the theoretical adjustments based on an existing dominant off-policy algorithm to express the algorithm’s competency with proof of convergence. We perform experimentations with DeepMind Control Suite, illustrating significant results showing the algorithm’s capabilities in learning complex environments powered by delay-aware RL.","author":[{"family":"Bataduwaarachchi","given":"Sathira"},{"family":"Najdovski","given":"Zoran"},{"family":"Trinh","given":"Hieu"},{"family":"Lim","given":"Chee"},{"family":"Huynh","given":"Van"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.robot.2025.105271","URL":"https://doi.org/10.1016/j.robot.2025.105271","source":"crossref"},{"id":"doi:10.37446/edibook202024/37-46","type":"article-journal","title":"Robotics For Animal Behavior and Welfare","abstract":"The integration of robotics into animal behaviour analysis and welfare is transforming the way animals are monitored, studied, and cared for across sectors such as agriculture, laboratory research, and wildlife conservation. This chapter explores the rising significance of robotics especially when combined with Artificial Intelligence (AI) and the Internet of Things (IoT) in enhancing animal welfare through non-invasive, automated, and adaptive systems. Key applications include robotic milking and feeding systems, biomimetic robots in behavioural studies, drone-based wildlife tracking, and AI-driven behaviour monitoring. These technologies improve efficiency, standardize experimental protocols, and reduce human-induced stress in animals. The chapter also examines emerging innovations such as therapeutic robots, conservation bots, and AI systems capable of interpreting animal emotions and social behaviours. While robotics offers vast potential, it also presents challenges including biological variability, ethical considerations, and the need for cross-disciplinary collaboration. Emphasizing the importance of animal-centric design, the chapter calls for ethical frameworks like the Five Freedoms and the Three Rs to guide responsible deployment. The future of animal welfare lies in the collaborative evolution of robotics, science, and compassion.","author":[{"family":"Gowda","given":"Keregallikoppalu"},{"family":"Guruprasad","given":"Rachaiah"},{"family":"Jagadeeswary","given":"Vankayala"}],"issued":{"date-parts":[[2026]]},"DOI":"10.37446/edibook202024/37-46","URL":"https://doi.org/10.37446/edibook202024/37-46","source":"crossref"},{"id":"doi:10.71443/9789349552050-01","type":"article-journal","title":"FOUNDATIONS OF REINFORCEMENT LEARNING FOR AUTONOMOUS ROBOTICS AND INDUSTRIAL SYSTEMS","abstract":"Reinforcement Learning (RL) has emerged as a transformative branch of artificial intelligence that enables autonomous systems to learn optimal decision-making strategies through continuous interaction with dynamic environments. Unlike conventional machine learning approaches that depend primarily on labeled datasets or predefined rules, reinforcement learning develops adaptive control policies by maximizing cumulative rewards, making it highly suitable for complex robotic and industrial applications. Recent advances in deep reinforcement learning, computational intelligence, and high-performance computing have significantly expanded the capability of autonomous systems to perform intelligent navigation, robotic manipulation, industrial process optimization, predictive maintenance, production scheduling, warehouse automation, and collaborative human–robot interaction. Simultaneously, the convergence of reinforcement learning with Industrial Internet of Things (IIoT), cyber-physical systems, digital twins, edge computing, and Industry 5.0 has accelerated the development of intelligent manufacturing ecosystems capable of autonomous adaptation, real-time optimization, and data-driven decision-making. This chapter presents a comprehensive foundation of reinforcement learning by integrating its theoretical principles, mathematical formulations, core learning components, value functions, policy optimization methods, exploration strategies, and classical reinforcement learning algorithms with modern deep reinforcement learning techniques. The discussion further examines practical implementation frameworks, simulation platforms, and representative applications in autonomous robotics and industrial systems while addressing critical challenges including sample inefficiency, reward engineering, safety-aware learning, computational complexity, explainability, and simulation-to-real-world deployment. Emerging research directions involving hierarchical reinforcement learning, multi-agent systems, federated learning, explainable artificial intelligence, and foundation models are also highlighted to demonstrate the future evolution of intelligent autonomous systems.","author":[{"family":"Rajaraman","given":"Janani"},{"family":"Bhakta","given":"Amit"},{"family":"Bhakta","given":"A"}],"issued":{"date-parts":[[2026]]},"DOI":"10.71443/9789349552050-01","URL":"https://doi.org/10.71443/9789349552050-01","source":"crossref"},{"id":"doi:10.1201/9781003655121-14","type":"article-journal","title":"Robotics in Minimally Invasive Surgery","abstract":"Performing procedures without causing the morbidity linked to conventional surgical incisions is the aim of limited access techniques. This was made feasible by a blend of three technologies innovations: the Hopkins rod lens system and shrinking cameras for videos, which Permit the surgeon to look within the body in a way similar to open surgery while keeping a normal posture. The controlled distension of bodily cavities is made possible by insufflation devices using gas, allowing the surgeon to work with more space. For many abdominal treatments, minimally invasive surgery is taking the place of the more conventional open surgical method. The benefits of less discomfort, quicker oral uptake recovery, reduced length of hospitalizations, and better esthetic results all add to the expanding popularity of the laparoscopic technique. However, this method has drawbacks, including a lengthier learning curve and more expenses because of disposable devices and specialized equipment. Surgical robotics, image guidance, NOTES, and SILS are just a few of the ongoing developments in MIS that have occurred since its inception in the early 1980s. Many surgical and non-surgical fields now employ MIS procedures. Through telepresence technologies, robotics in particular is transforming complicated surgeries, including heart surgery. These technologies improve safety, accuracy, and dexterity, but they are expensive and need a lot of training. The capabilities and accessibility of robotic-assisted MIS are expected to be significantly enhanced by upcoming advancements, such as enhanced haptic systems, AI-driven decision support, and 5G-enabled telesurgery.","author":[{"family":"Rawat","given":"Dipika"},{"family":"Ranjan","given":"Rohit"},{"family":"Minakshi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1201/9781003655121-14","URL":"https://doi.org/10.1201/9781003655121-14","source":"crossref"},{"id":"doi:10.1007/s12369-025-01355-x","type":"article-journal","title":"Multimodal Advantage in Android Emotional Expressions","abstract":"Multimodal emotional expressions play an essential role in real-life communication. Previous psychological studies have reported that emotional expressions can be more effective using trimodal channels, including verbal, vocal, and facial expressions, than those using only bimodal or unimodal channels. Although robots are expected to interact with humans, it remains unclear whether the multimodal advantage could be observed in the emotional expressions of a robot. We investigated this issue with the android Nikola. Nikola showed unimodal, bimodal, and trimodal expressions of negative and positive emotions using verbal, vocal, and facial channels in a face-to-face situation. Participants rated the expressed emotions regarding emotional valence and humanlikeness. Nikola’s trimodal expressions were rated as more emotional than the unimodal and bimodal expressions. The trimodal expressions were also more humanlike than the unimodal and bimodal expressions. These results suggest that robots can display emotional expressions in a more intense and humanlike manner using multimodal channels.","author":[{"family":"Sato","given":"Wataru"},{"family":"Shimokawa","given":"Koh"},{"family":"Namba","given":"Shushi"},{"family":"Minato","given":"Takashi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s12369-025-01355-x","URL":"https://doi.org/10.1007/s12369-025-01355-x","source":"crossref"},{"id":"doi:10.1080/01691864.2025.2612569","type":"article-journal","title":"A study on the Bi-copter system for increasing operation time","abstract":"Multi-copter systems are widely used in various applications due to their vertical take-off and landing (VTOL) capabilities and flight performance. However, conventional designs that rely on multiple fixed rotors are limited by high power consumption, resulting in limited flight time. Various approaches have been proposed to address these issues, but many of them introduce new challenges such as increased system weight, structural complexity, or noise. This study proposes a Bi-copter system employing CG–AC positioning for passive longitudinal stability. To evaluate its flight characteristics, a Software-in-the-Loop Simulation (SILS) is conducted and compared with a quad-copter. In addition, a Hardware-in-the-Loop Simulation (HILS) is performed to compare the power consumption characteristics associated with propulsion configurations.","author":[{"family":"Lee","given":"Changkeun"},{"family":"Cho","given":"Changhyun"},{"family":"Cha","given":"Dowan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/01691864.2025.2612569","URL":"https://doi.org/10.1080/01691864.2025.2612569","source":"crossref"},{"id":"doi:10.51583/ijltemas.2025.1410000148","type":"article-journal","title":"Development of Autonomous Agricultural Vehicle as New Trends of Agricultural Robotics","abstract":"Abstract: CCTV cameras are widely used to monitor traffic, but they often come with limitations that still force officials to check traffic flow manually. In this work, we introduce a simple and automatic method to measure traffic volume and vehicle speed by analyzing pixel patterns from CCTV video. Our approach begins by marking vertical and horizontal reference lines on each lane and collecting pixel information from these lines in every video frame. When a vehicle crosses these lines, the change in pixel brightness clearly reveals its movement. By studying these brightness changes, we can automatically detect vehicles and calculate key traffic parameters accurately.","author":[{"family":"Chaubey","given":"Punit"},{"family":"Singh","given":"Umakant"},{"family":"Pathak","given":"Sanjeev"}],"issued":{"date-parts":[[2025]]},"DOI":"10.51583/ijltemas.2025.1410000148","URL":"https://doi.org/10.51583/ijltemas.2025.1410000148","source":"crossref"},{"id":"doi:10.4018/979-8-3373-9295-0.ch012","type":"article-journal","title":"Explainable Deep Learning for Plant Disease Detection","abstract":"This chapter investigates the application of deep learning (DL) and explainable artificial intelligence (XAI) for plant disease detection and classification in agriculture. A comprehensive system is developed using the EfficientNetB0 architecture and trained on a dataset of 87,000 leaf images covering 38 disease classes across 14 plant species. The proposed model achieves high performance, with accuracy, precision, and recall scores of 99.69%, 98.27%, and 98.26%, respectively, outperforming established architectures such as MobileNetV2, ResNet-50, and a baseline convolutional neural network. To address the interpretability challenges of deep learning, the system integrates the LIME framework, providing spatially grounded and human-readable explanations for individual predictions. Additionally, the chapter discusses data preprocessing techniques, feature extraction methods, and statistical validation using analysis of variance (ANOVA). Finally, the system is deployed as a mobile application to enable farmers to perform real-time plant disease diagnosis efficiently.","author":[{"family":"Nigar","given":"Natasha"},{"family":"Shahzad","given":"Muhammad"},{"family":"Faisal","given":"Hafiz"}],"issued":{"date-parts":[[2026]]},"DOI":"10.4018/979-8-3373-9295-0.ch012","URL":"https://doi.org/10.4018/979-8-3373-9295-0.ch012","source":"crossref"},{"id":"doi:10.1177/09713441261438783","type":"article-journal","title":"Geopolitical Headwinds and Risks in India’s Agricultural Markets","abstract":"The growing frequency of geopolitical conflicts has added a new dimension of uncertainty to the global agricultural markets, thereby renewing concerns about the vulnerability of the food system to such shocks. Disruptions triggered by the Russia–Ukraine war, US–China rivalry, USA tariff wars and the recent Middle East tensions demonstrated how quickly geopolitical frictions can disturb agricultural supply chains and intensify volatility in commodity prices worldwide. This note examines the relationship between geopolitical risks and the evolving agricultural market dynamics. For developing economies like India, where agriculture remains central to both rural livelihoods and food price stability, such global shocks carry important macroeconomic implications. JEL Classification: Q13, Q17, F51, E31","author":[{"family":"Bhat","given":"Anil"},{"family":"Sharma","given":"Eva"},{"family":"Magotra","given":"Ankit"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1177/09713441261438783","URL":"https://doi.org/10.1177/09713441261438783","source":"crossref"},{"id":"doi:10.1109/icra55743.2025.11127764","type":"article-journal","title":"Collision-Aware Traversability Analysis for Autonomous Vehicles in the Context of Agricultural Robotics","abstract":"In this paper, we introduce a novel method for safe navigation in agricultural robotics. As global environmental challenges intensify, robotics offers a powerful solution to reduce chemical usage while meeting the increasing demands for food production. However, significant challenges remain in ensuring the autonomy and resilience of robots operating in unstructured agricultural environments. Obstacles such as crops and tall grass, which are deformable, must be identified as safely traversable, compared to rigid obstacles. To address this, we propose a new traversability analysis method based on a 3D spectral map reconstructed using a LIDAR and a multispectral camera. This approach enables the robot to distinguish between safe and unsafe collisions with deformable obstacles. We perform a comprehensive evaluation of multispectral metrics for vegetation detection and incorporate these metrics into an augmented environmental map. Utilizing this map, we compute a physics-based traversability metric that accounts for the robot's weight and size, ensuring safe navigation over deformable obstacles.","author":[{"family":"Philippe","given":"Florian"},{"family":"Laconte","given":"Johann"},{"family":"Lapray","given":"Pierre"},{"family":"Spisser","given":"Matthias"},{"family":"Lauffenburger","given":"Jean"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icra55743.2025.11127764","URL":"https://doi.org/10.1109/icra55743.2025.11127764","source":"crossref"},{"id":"doi:10.1177/0971344120090215","type":"article-journal","title":"Inadequacies of Institutional Agricultural Credit System in Punjab State","abstract":"In spite of various measures to rejuvenate farm credit, the flow of credit to agriculture sector remained inadequate quantitatively and qualitatively. The study is based on a random sample of 600 farm households covering 11 districts in Punjab, comprising 107 marginal, 150 small, 53 semi-mediums, 87 medium and 103 large farmers and pertains to the year 2005-06. The total debt per sample farm household from both institutional and non-institutional sources has been found to be Rs 178934 in the year 2005-06. The institutional sources have contributed about 62 per cent to the total debt and non-institutional 38 per cent. Although the institutional credit has increased rapidly in recent years in Punjab, it still lacks behind the productive needs of the farmers in Punjab. A farmer on an average has to incur Rs 4016 for obtaining a loan from commercial banks, which amounts to 5 per cent of the total loan obtained by him. In the case of cooperatives, the transaction cost has been worked out to be 1.2 per cent of the loan and the cooperatives are located right in the villages. About 59 per cent farmers have reported the procedure to get loans from the institutional agencies to be complicated and time-consuming. On the contrary, availing non-institutional loan has been found easy and is the reason of preference given by 51 per cent farmers to it. Policy implications include issuing of a simple but comprehensive record book to farmers containing information relating to his land record and institutional transactions; computerization of land records by the state government; simplification of loan application form; and maintenance of proper records of loan applications and making disbursement of loan mandatory.","author":[{"family":"Singh","given":"Sukhpal"},{"family":"Kaur","given":"Manjeet"},{"family":"Kingra","given":"HS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1177/0971344120090215","URL":"https://doi.org/10.1177/0971344120090215","source":"crossref"},{"id":"doi:10.1109/sbr/wre66973.2025.11249528","type":"article-journal","title":"A Systematic Review on Teacher Training in Educational Robotics: Global and Brazilian Perspectives","abstract":"This paper presents a systematic literature review on teacher training in educational robotics, with a twofold objective: to map the global research landscape and to provide a focused analysis of the Brazilian context. The review was guided by spe-cific research questions and conducted using the Scopus and Web of Science databases for the global perspective, complemented by the Brazilian Digital Library of Theses and Dissertations (BDTD) for the local analysis. Our findings highlight Brazil's significant international contribution, ranking second in the number of publications in both Scopus (6 out of 28) and Web of Science (4 out of 15). At the national level, our analysis identified 11 recent theses and dissertations completed between 2020 and the present. These results indicate that robust methodologies for teacher training in Educational Robotics are not only being actively researched but also effectively implemented throughout Brazil.","author":[{"family":"Santos","given":"Lídia"},{"family":"Curvelo","given":"Carla"},{"family":"Gonçalves","given":"Luiz"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre66973.2025.11249528","URL":"https://doi.org/10.1109/sbr/wre66973.2025.11249528","source":"crossref"},{"id":"doi:10.1109/sbr/wre66973.2025.11249644","type":"article-journal","title":"A ROS2-Based Robotics Course for Undergraduate Program","abstract":"As the field of robotics continues to expand and influence various sectors, it becomes increasingly important to prepare engineering students to work with modern robotic systems. Practical knowledge and real-world experience are essential components in developing these skills. To bridge the gap between theory and practice, this paper presents a structured undergraduate course that introduces students to the Robot Operating System version 2 (ROS 2) using simulation-based and hands-on learning activities. Based on official ROS documentation and tools such as Gazebo and MAVROS, the course guides students through the foundational concepts of robotic control, embedded systems, robot modeling, and autonomous navigation. Each class is designed to progressively build technical skills while reinforcing theoretical understanding through project-based tasks. The primary goal is to enhance the comprehension of robotics topics by introducing a more hands-on and experimental learning environment. This kind of course equips students with computational tools, thereby significantly contributing to their hands-on experience in robotics.","author":[{"family":"Pinto","given":"Milena"},{"family":"Carvalho","given":"Lucas"},{"family":"Sousa","given":"Lucas"},{"family":"Amorim","given":"Johann"},{"family":"Nascimento","given":"Yuri"},{"family":"Castro","given":"Gabriel"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre66973.2025.11249644","URL":"https://doi.org/10.1109/sbr/wre66973.2025.11249644","source":"crossref"},{"id":"doi:10.1109/sbr/wre66973.2025.11249586","type":"article-journal","title":"Robotics Education and its Role in Enhancing Academic Persistence and Achievement in the Triângulo Mineiro Region","abstract":"This article investigates the impacts of higher education students' participation in robotics projects on their academic retention and success. Drawing on the analysis of experiences and project proposals developed in the Triangulo Mineiro region of Brazil, the study discusses how educational robotics can enhance student engagement, motivation, and the development of essential skills, thereby contributing to reduced dropout rates and improved academic performance. The distinctions between educational and pedagogical robotics, as well as the historical context of their application in Brazil, are examined. Recent experiences employing machine learning and data visualization to assess the impacts of robotics initiatives-including those aimed at increasing female participation-underscore the relevance and the need for more in-depth analyses. Although direct statistical data to quantify causal effects remain limited in publicly available databases for this specific region, qualitative evidence and practical examples based on local initiatives indicate a significant positive impact. The study highlights the importance of such initiatives for the comprehensive education of students in engineering and technology programs.","author":[{"family":"Silva","given":"Aline"},{"family":"Rios","given":"Artur"},{"family":"Lima","given":"Danielli"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre66973.2025.11249586","URL":"https://doi.org/10.1109/sbr/wre66973.2025.11249586","source":"crossref"},{"id":"doi:10.1177/02783649251368909","type":"article-journal","title":"The Rosario dataset v2: Multi-modal dataset for agricultural robotics","abstract":"We present a multi-modal dataset collected in a soybean crop field, comprising over 2 hours of recorded data from sensors such as stereo infrared camera, color camera, accelerometer, gyroscope, magnetometer, GNSS (Single-Point Positioning, Real-Time Kinematic, and Post-Processed Kinematic), and wheel odometry. This dataset captures key challenges inherent to robotics in agricultural environments, including variations in natural lighting, motion blur, rough terrain, and long, perceptually aliased sequences. By addressing these complexities, the dataset aims to support the development and benchmarking of advanced algorithms for localization, mapping, perception, and navigation in agricultural robotics. The platform and data collection system is designed to meet the key requirements for evaluating multi-modal SLAM systems, including hardware synchronization of sensors, 6-DOF ground-truth and loops on long trajectories. We run multi-modal state-of-the art SLAM methods on the dataset, showcasing the existing limitations in their application on agricultural settings. The dataset and utilities to work with it are released on https://cifasis.github.io/rosariov2/ .","author":[{"family":"Soncini","given":"Nicolás"},{"family":"Cremona","given":"Javier"},{"family":"Vidal","given":"Erica"},{"family":"García","given":"Maximiliano"},{"family":"Castro","given":"Gastón"},{"family":"Pire","given":"Taihú"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1177/02783649251368909","URL":"https://doi.org/10.1177/02783649251368909","source":"crossref"},{"id":"doi:10.1016/j.birob.2026.100337","type":"article-journal","title":"A robust agricultural LiDAR-inertial SLAM system with heterogeneous registration and neural noise adaptation","abstract":"To address the challenges of unstructured terrain, repetitive geometric structures, and significant inertial disturbances in agricultural environments, this paper proposes a robust LiDAR-inertial simultaneous localization and mapping (SLAM) system for agricultural robots. The proposed system is built upon the LIO-SAM framework and incorporates two key improvements. Firstly, a vegetation–structure heterogeneous registration strategy is introduced. By leveraging point cloud intensity information, rigid structures and flexible vegetation are separated, and two parallel registration pipelines are constructed: a structure-oriented channel based on normal-distribution modeling and a vegetation-oriented channel based on geometric features. Pose estimation is then achieved through confidence-weighted fusion, improving registration robustness in scenes with repetitive structures. Secondly, a neural noise adapter (NNA) is developed to dynamically model the time-varying characteristics of IMU noise using a long short-term memory (LSTM) network. By fusing raw IMU data, instantaneous noise statistics, and terrain undulation features, the adapter predicts the pre-integration covariance scaling factor in real time, effectively suppressing pose drift caused by rugged terrain. Comparative experiments conducted on public datasets, a Gazebo agricultural simulation environment, and real orchard scenarios demonstrate the proposed method’s advantages in localization accuracy, and generalizability, providing reliable perception support for precision agricultural robotics.","author":[{"family":"Zeng","given":"Jun"},{"family":"Zhang","given":"Hongwei"},{"family":"Chen","given":"Weinan"},{"family":"Gao","given":"Hongchao"},{"family":"Wang","given":"Ziyang"},{"family":"Li","given":"Mingjun"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.birob.2026.100337","URL":"https://doi.org/10.1016/j.birob.2026.100337","source":"crossref"},{"id":"doi:10.64820/aepjrr.22.10.16.122025","type":"article-journal","title":"Design and Simulation of a CNC Machine for Controlled Seed Irradiation in Agricultural Research","abstract":"Agriculture remains one of the most vital sectors for human survival, providing essential food resources and contributing significantly to the economy. Various technologies have been developed to enhance agricultural production, including seed irradiation. Research has demonstrated that irradiation can significantly improve seed quality and boost the productivity of seeds, particularly those affected by adverse storage conditions such as fluctuating temperature and humidity. However, traditional irradiation methods often relied on manual timers, resulting in inaccuracies and inconsistent seed treatments. This paper presents the development of an automated seed irradiation system using a Computer Numerically Controlled (CNC) machine. The proposed system ensures precise and controlled radiation exposure, offering greater accuracy and consistency in the irradiation process. By automating the procedure, this CNC-based machine enhances the effectiveness of seed treatment, ensuring optimal irradiation for improved seed quality and agricultural productivity.","author":[{"family":"Fadlalla","given":"Amin"},{"family":"Ahmed","given":"Elzibir"},{"family":"Mohammed","given":"Monay"},{"family":"Fadl-Almawlaa","given":"Omer"}],"issued":{"date-parts":[[2026]]},"DOI":"10.64820/aepjrr.22.10.16.122025","URL":"https://doi.org/10.64820/aepjrr.22.10.16.122025","source":"crossref"},{"id":"doi:10.1109/sbr/wre66973.2025.11249616","type":"article-journal","title":"Robotics Education in Schools: Ac n Inclusive and Scalable Pedagogical Approach","abstract":"This paper presents a pedagogical proposal for introducing robotics education to children aged 8 to 17 in public schools, with a specific focus on 3D printing and robot construction. Grounded in constructionist learning theory, the approach combines theoretical instruction, hands-on workshops, and formative assessments to foster meaningful engagement in STEM. The methodology was implemented in a series of biweekly workshops conducted by the Titans robotics team in partnership with a local school in Brasilia, Brazil. Instructional content was delivered using open-source tools and adapted to low-resource settings to promote accessibility and inclusion. Evaluation through pre- and post-tests demonstrated significant learning gains, particularly in concepts initially unfamiliar to students. The results support the effectiveness of structured, practical robotics education in fostering STEM competencies at an early age. Limitations and directions for future expansion, including broader implementation and longitudinal tracking, are discussed.","author":[{"family":"Itacaramby","given":"Gabriela"},{"family":"Cabral","given":"João"},{"family":"Pastrana","given":"MA"},{"family":"Sanchez","given":"William"},{"family":"Baptista","given":"Roberto"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre66973.2025.11249616","URL":"https://doi.org/10.1109/sbr/wre66973.2025.11249616","source":"crossref"},{"id":"doi:10.1177/28350111251380262","type":"article-journal","title":"Multivalve Configuration for Soft Robotics: Overcoming the Trade-Off Between Speed and Accuracy in Pneumatic Systems","abstract":"This article describes a new multivalve configuration for achieving both high speed and high resolution in pneumatically driven soft robotic actuators. The proposed method utilizes dual on/off valves with differing orifice sizes in both the charge and discharge paths of the pneumatic circuit. The multiple-valve arrangement provides five states of flow-rate control, which can provide high flow rate for large step changes in pressure, and fine pressure control for precision positioning or force control. Compared with a proportional valve, the proposed method is physically smaller, lower cost, and significantly faster in charging and discharging a soft actuator. The performance of the proposed multivalve system is evaluated using a dual hysteresis control strategy, where the valve combination is dependent on pressure error. The proposed method is experimentally compared with two single-valve configurations, and the results demonstrate a significant improvement in both speed and accuracy. The proposed method is suited to applications that require a fast response between arbitrary set-points and precise control of position or interaction force.","author":[{"family":"Young","given":"Taylor"},{"family":"Yong","given":"Yuen"},{"family":"Fleming","given":"Andrew"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1177/28350111251380262","URL":"https://doi.org/10.1177/28350111251380262","source":"crossref"},{"id":"doi:10.1016/j.cogr.2025.01.001","type":"article-journal","title":"Attention-assisted dual-branch interactive face super-resolution network","abstract":"We propose a deep learning-based Attention-Assisted Dual-Branch Interactive Network (ADBINet) to improve facial super-resolution by addressing key challenges like inadequate feature extraction and poor multi-scale information handling. ADBINet features a multi-scale encoder-decoder architecture that captures and integrates features across scales, enhancing detail and reconstruction quality. The key to our approach is the Transformer and CNN Interaction Module (TCIM), which includes a Dual Attention Collaboration Module (DACM) for improved local and spatial feature extraction. The Channel Attention Guidance Module (CAGM) refines CNN and Transformer fusion, ensuring precise facial detail restoration. Additionally, the Attention Feature Fusion Unit (AFFM) optimizes multi-scale feature integration. Experimental results demonstrate that ADBINet outperforms existing methods in both quantitative and qualitative facial super-resolution metrics.","author":[{"family":"Wan","given":"Xujie"},{"family":"Xu","given":"Siyu"},{"family":"Gao","given":"Guangwei"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.cogr.2025.01.001","URL":"https://doi.org/10.1016/j.cogr.2025.01.001","source":"crossref"},{"id":"doi:10.1299/jsmermd.2025.2p2-b08","type":"article-journal","title":"Proposal for a Harvest Performance Evaluation Method for Agricultural Robots","abstract":"Evaluating the performance of harvesting robots is challenging due to the complexity of cultivation environments. Accurate assessment requires evaluating both individual actions—recognition, approach, insertion, and grasping—and overall system performance. This paper proposes the “Series and/or Individual action Evaluation Method (SIEM)” for harvesting robots. As a case study, SIEM is applied to a strawberry harvesting robot equipped with a hook-type tool through two experiments. The results show that SIEM effectively identifies areas for improvement, leading to enhancements of the hook-type tool. This study confirms that SIEM is a available method for evaluating and improving the performance of harvesting robots, providing a comprehensive assessment framework.","author":[{"family":"Ozaki","given":"Koichi"},{"family":"Kurokura","given":"Takeshi"},{"family":"Shibanuma","given":"Mayu"},{"family":"Goto","given":"Taku"},{"family":"Miyagusuku","given":"Renato"},{"family":"Tabata","given":"Kenta"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1299/jsmermd.2025.2p2-b08","URL":"https://doi.org/10.1299/jsmermd.2025.2p2-b08","source":"crossref"},{"id":"doi:10.1109/sbr/wre66973.2025.11249663","type":"article-journal","title":"Promoting Low-Cost Educational Robotics: A Project-Based Learning Approach for Public High Schools Preparing for the Brazilian Robotics Olympiad","abstract":"This paper presents a project-based educational initiative designed to promote low-cost robotics in Brazilian public high schools, with a primary focus on preparing students for the Brazilian Robotics Olympiad (OBR). The project integrates concepts from Constructionism and Project-Based Learning to offer hands-on experiences in programming, electronics, and robot assembly using accessible platforms such as Arduino and ThinkerCad. The methodology was implemented over seven sessions and evaluated through formative assessments and student feedback. Preliminary results indicate improvements in students' confidence, problem-solving skills, and engagement with STEM topics. Despite positive outcomes, the study acknowledges limitations related to sample size, lack of control groups, and non-validated assessment instruments. Future work will address these limitations and explore strategies for broader dissemination and impact evaluation.","author":[{"family":"Machado","given":"Filipe"},{"family":"Checchia","given":"Jenniffer"},{"family":"Mendes","given":"Pedro"},{"family":"Junior","given":"Amaury"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/sbr/wre66973.2025.11249663","URL":"https://doi.org/10.1109/sbr/wre66973.2025.11249663","source":"crossref"},{"id":"doi:10.1016/j.robot.2025.105181","type":"article-journal","title":"Geometric methods for aircraft planning and control","abstract":"Path planning and control of autonomous aircraft is a critical problem, particularly under conditions of model and sensor uncertainty. This paper presents a hierarchical control architecture that integrates geometric and probabilistic methods to address these challenges. The proposed framework combines a high-level controller, a low-level controller, and an observer, leveraging Lie group theory for geometric modeling. The high-level controller formulates the planning problem as a Markov Decision Process (MDP), solved using Monte Carlo Tree Search (MCTS) to generate reference trajectories while avoiding no-fly zones. The low-level controller exploits the relationship between tangent space velocities and left-trivialized velocities in the Lie algebra to produce control commands. State estimation is achieved using a second-order optimal minimum-energy filter formulated on Lie groups, ensuring robust performance under noisy measurements. Simulation results show the efficacy of the proposed architecture in guiding an aircraft from a start point to a target while satisfying operational constraints.","author":[{"family":"Trotti","given":"Francesco"},{"family":"Rigo","given":"Damiano"},{"family":"Muradore","given":"Riccardo"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.robot.2025.105181","URL":"https://doi.org/10.1016/j.robot.2025.105181","source":"crossref"},{"id":"doi:10.1109/icra55743.2025.11128743","type":"article-journal","title":"Reinforcement Learning with Lie Group Orientations for Robotics","abstract":"Handling orientations of robots and objects is a crucial aspect of many applications. Yet, ever so often, there is a lack of mathematical correctness when dealing with orientations, especially in learning pipelines involving, for example, artificial neural networks. In this paper, we investigate reinforcement learning with orientations and propose a simple modification of the network's input and output that adheres to the Lie group structure of orientations. As a result, we obtain an easy and efficient implementation that is directly usable with existing learning libraries and achieves significantly better performance than other common orientation representations. We briefly introduce Lie theory specifically for orientations in robotics to motivate and outline our approach. Subsequently, a thorough empirical evaluation of different combinations of orientation representations for states and actions demonstrates the superior performance of our proposed approach in different scenarios, including: direct orientation control, end effector orientation control, and pick-and-place tasks.","author":[{"family":"Schuck","given":"Martin"},{"family":"Brudigam","given":"Jan"},{"family":"Hirche","given":"Sandra"},{"family":"Schoellig","given":"Angela"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icra55743.2025.11128743","URL":"https://doi.org/10.1109/icra55743.2025.11128743","source":"crossref"},{"id":"doi:10.1177/0971344120090105","type":"article-journal","title":"Strengthening Pluralistic Agricultural Information Delivery Systems in India","abstract":"The study on agricultural information flow has revealed that only 40 per cent farm households access information from one or the other source. The popular information sources among farmers have been reported to be fellow progressive farmers and input dealers, followed by mass media. The public extension system has been found to be accessed by only 5.7 per cent households. Only 4.8 per cent of the small farmers have access to public extension workers as compared to 12.4 per cent of large farmers. The sector-wise study on the type of information, sought has revealed that a majority of the farmers have sought information on seed (32-55%) in the cultivation sector; on health care (26-54 %) in animal husbandry; and on management and marketing (8-46 %) in fisheries. Regarding adoption of information by farmers, input dealers and other progressive farmers have depicted greater influence mainly due to easy and convenient access to these sources. The study has suggested promotion of farmers-led extension and strengthening of public extension services to improve coverage and efficiency of agricultural information delivery systems.","author":[{"family":"Adhiguru","given":"P"},{"family":"Birthal","given":"PS"},{"family":"Kumar","given":"BG"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1177/0971344120090105","URL":"https://doi.org/10.1177/0971344120090105","source":"crossref"},{"id":"doi:10.1016/j.robot.2026.105706","type":"article-journal","title":"Adaptive PID control of the drive system for tracked agricultural robots operating in unstructured terrain","abstract":"ABSTRACT This paper proposes a computationally efficient adaptive PID control method to enhance the drive system performance of tracked agricultural robots operating on unstructured terrain. Conventional fixed-parameter PID controllers struggle to adapt to variations in soil properties and dynamic load disturbances, while advanced control algorithms such as sliding mode control and fuzzy PID, though theoretically more adaptable, suffer from high computational complexity that hinders their practical deployment in resource-constrained embedded systems of agricultural robots. Building upon the classical PID structure, the proposed method introduces an online parameter adaptation mechanism based on Lyapunov stability theory and gradient descent, ensuring closed-loop stability and guaranteeing that the tracking error converges to a tunable residual set around zero in the sense of uniform ultimate boundedness. Comparative experiments conducted on a self-developed tracked robot platform demonstrate that, compared to fixed-parameter PID, the proposed method reduces the average RMSE of the left wheel from 0.1198 rad/s to 0.0971 rad/s (18.9% improvement) on structured surfaces, and from 0.2186 rad/s to 0.1201 rad/s (45.0% improvement) on unstructured surfaces, while the average RMSE of the right wheel decreases from 0.1231 rad/s to 0.0907 rad/s (26.3% improvement) and from 0.1925 rad/s to 0.1085 rad/s (43.6% improvement), respectively. Additionally, the control output remains smooth and chatter-free. In terms of algorithm complexity, the method achieves reductions of 23.7%, 75.8%, and 51.4% compared to sliding mode control, adaptive sliding mode control, and fuzzy PID, respectively, significantly lowering the implementation barrier in embedded systems. This approach provides a practical solution for agricultural mobile robot drive control that effectively balances control accuracy, environmental robustness, and ease of implementation.","author":[{"family":"Li","given":"Zhiqiang"},{"family":"Luo","given":"Kun"},{"family":"Tao","given":"Liang"},{"family":"Zhou","given":"Yan"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1016/j.robot.2026.105706","URL":"https://doi.org/10.1016/j.robot.2026.105706","source":"crossref"},{"id":"doi:10.1016/j.cogr.2025.03.002","type":"article-journal","title":"A transformation model for vision-based navigation of agricultural robots","abstract":"This paper presents a Top-view Transformation Model (TTM) for a vision-based autonomous navigation of an agricultural mobile robot. The TTM transforms images captured by an onboard camera into a virtual Top-view, eliminating perspective distortions such as the vanishing point effect and ensuring uniform pixel distribution. The transformed images are analyzed to ensure an autonomous navigation of the robot between crop rows. The navigation method involves real-time estimation of the robot's position relative to crop rows and the control low is derived from the estimated robot's heading and lateral offset for steering the robot along the crop rows. A simulated scenario has been generated in Gazebo in order to implement the developed approach using the Robot Operating System (ROS), while an evaluation on a real agricultural mobile robot has also been performed. The experimental results demonstrate the feasibility of the TTM approach and its implementation for autonomous navigation, reaching good performance.","author":[{"family":"Abanay","given":"Abdelkrim"},{"family":"Masmoudi","given":"Lhoussaine"},{"family":"Benkhedra","given":"Dirar"},{"family":"Amraoui","given":"Khalid"},{"family":"Lghoul","given":"Mouataz"},{"family":"Jimenez","given":"Javier"},{"family":"Moreno","given":"Francisco"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1016/j.cogr.2025.03.002","URL":"https://doi.org/10.1016/j.cogr.2025.03.002","source":"crossref"},{"id":"doi:10.3390/robotics15010025","type":"article-journal","title":"Synergistic Advancement of Physical and Information Interaction in Exoskeleton Rehabilitation Robotics: A Review","abstract":"The exoskeleton rehabilitation robot is a structural robot that uses the actuator to control, so as to construct a human–robot collaborative rehabilitation training system to realize the perception and decoding of patients and promotes the recovery of limb function and neural remodeling. This review focused on the synergistic advancement of physical and information interaction in exoskeleton rehabilitation robotics. This review systematically retrieved literature related to the synergistic advancement of physical and information interaction in exoskeleton rehabilitation robotics. Publications from 2011 to 2025 were searched for across the EI, IEEE Xplore, PubMed, and Web of Science databases. The included studies mainly covered the period from 2018 to 2025, reflecting recent technological progress. This article summarizes the collaborative progress of physical and informational interaction in exoskeleton rehabilitation robots. The physical and information interaction is manifested in the bionic structure, physiological information detection and information processing technology to identify human movement intention. The bionic structural design is fundamental to realize natural coordination between human and robot to improve the following of movements. The active participation and movement intention recognition accuracy are enhanced based on multimodal physiological signal detection and information processing technology, which provides a clear direction for the development of intelligent rehabilitation technology.","author":[{"family":"Fei","given":"Cuizhi"},{"family":"Meng","given":"Qiaoling"},{"family":"Yu","given":"Hongliu"},{"family":"Lu","given":"Xuhua"}],"issued":{"date-parts":[[2026]]},"DOI":"10.3390/robotics15010025","URL":"https://doi.org/10.3390/robotics15010025","source":"crossref"},{"id":"doi:10.3390/app15041840","type":"article-journal","title":"Comprehensive Review of Robotics Operating System-Based Reinforcement Learning in Robotics","abstract":"Common challenges in the area of robotics include issues such as sensor modeling, dynamic operating environments, and limited on-broad computational resources. To improve decision making, robots need a dependable framework to facilitate communication between different modules and the optimal action for real-world applications. The Robotics Operating System (ROS) and Reinforcement Learning (RL) are two promising approaches that help accomplish precise control, seamless integration of sensors-actuators, and exhibit learned behavior. The ROS enables seamless communication between heterogeneous components, while RL focuses on learning optimal behaviors through trial-and-error scenarios. Combining the ROS and RL offers superior decision making, improved perception, enhanced automation, and reliability. This work focuses on investigating ROS-based RL applications across various domains, aiming to enhance understanding through comprehensive discussion, analysis, and summarization. We base our evaluation on the application area, type of RL algorithm used, and degree of ROS–RL integration. Additionally, we provide summary of seminal works that define the current state of the art, along with GitHub repositories and resources for research purposes. Based on the review of successfully implemented projects, we make recommendations highlighting the advantages and limitations of RL techniques for specific applications and environments. The ultimate goal of this work is to advance the robotics field by providing a comprehensive overview of the recent important works that incorporate both the ROS and RL, thereby improving the adaptability of these emerging techniques.","author":[{"family":"Aljamal","given":"Mohammed"},{"family":"Patel","given":"Sarosh"},{"family":"Mahmood","given":"Ausif"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/app15041840","URL":"https://doi.org/10.3390/app15041840","source":"crossref"},{"id":"doi:10.3390/robotics14050062","type":"article-journal","title":"Analytical Modeling, Virtual Prototyping, and Performance Optimization of Cartesian Robots: A Comprehensive Review","abstract":"A comprehensive literature review on the kinematics and dynamics modeling and virtual prototyping (V.P) of the Cartesian robots with a flexible configuration is presented in this paper. Different modeling approaches of the main components of the Cartesian robot, which includes linear belt drives and structural components, are presented and discussed in this paper. Furthermore, the vibrations modeling, trajectory planning, and control strategies of the Cartesian robot are also presented. The performance optimization of the Cartesian robot is discussed here, which is affected by the highly flexible configuration of the robot incurred due to high-mix, low-volume production. The importance of virtual prototyping techniques, like finite element analysis and multi-body dynamics, for modeling Cartesian robots or its components is presented. Design and performance optimization methods for robots with a flexible configuration are discussed, although their application to Cartesian robots is rare in the literature and it presents an exciting opportunity for future research in this area. This review paper focuses on the importance of further research on the virtual prototyping tools for flexibly configured robots and their integration with experimental validation. The findings offer useful insights to industries looking to maximize their production processes while keeping the customization, reliability, and efficiency.","author":[{"family":"Mehmood","given":"Yasir"},{"family":"Cannella","given":"Ferdinando"},{"family":"Cocuzza","given":"Silvio"}],"issued":{"date-parts":[[2025]]},"DOI":"10.3390/robotics14050062","URL":"https://doi.org/10.3390/robotics14050062","source":"crossref"},{"id":"doi:10.1080/01691864.2026.2707060","type":"article-journal","title":"From pixels to practice: a scientometric and systematic review of computer vision for clinical robotics","abstract":"Recent developments in computer vision and artificial intelligence (AI) can transform healthcare, from supporting patients to enhancing surgery. While extensive research exists, a comprehensive overview of how vision and AI facilitate collaborative, situationally aware, and evolving robotic capabilities is still lacking. We address this gap by detailing state-of-the-art contributions in recognition using spatial visual features, deep learning, and other intelligent applications. We concentrate on core computer vision techniques such as object detection, human posture assessment, and semantic mapping, emphasizing their significance across three primary application domains: (1) AI-guided surgical robotics; (2) AI-powered robotic rehabilitation and prosthetics; and (3) AI-enhanced robotics for clinical monitoring and intervention. While existing literature surveys explore vision or robotics independently, our review uniquely focuses on their integrated application within clinical and healthcare settings, highlighting the potential for practical, real-world deployment. We highlight recommendations, difficulties, and important metrics for success. Finally, we recommend future research directions, including sensor fusion and ethical considerations, to ensure safe, reliable, and efficient human-robot collaboration in healthcare in the near future.","author":[{"family":"Arsalan","given":"Muhammad"},{"family":"Al-Sada","given":"Mohammed"},{"family":"Khan","given":"Muhammad"},{"family":"Halabi","given":"Osama"},{"family":"Aljaber","given":"Faisal"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1080/01691864.2026.2707060","URL":"https://doi.org/10.1080/01691864.2026.2707060","source":"crossref"},{"id":"doi:10.1007/s12369-026-01387-x","type":"article-journal","title":"Diversity and Culture in Social Robotics: A Scoping Review","abstract":"Abstract This review explores how cultural relativism affects the adoption and perception of robots, drawing conclusions that can be used to mitigate biases and design robots that incorporate cultural diversity. Indeed, several aspects (like religion, pragmatics, appearance, application areas) need to be considered and implemented to ensure a more pleasant interaction with humans. We show that culture is in itself a broad concept that covers various aspects: verbal behavior, nonverbal behavior, design, and application areas. It could intervene as a response and interpretation strategy when there is a clear reference to a social background in the task to shorten the adaptation. It is a cost-saving principle, a heuristic.","author":[{"family":"Saettone","given":"Lorenza"},{"family":"Sgorbissa","given":"Antonio"},{"family":"Recchiuto","given":"Carmine"}],"issued":{"date-parts":[[2026]]},"DOI":"10.1007/s12369-026-01387-x","URL":"https://doi.org/10.1007/s12369-026-01387-x","source":"crossref"},{"id":"doi:10.21203/rs.3.rs-7417193/v1","type":"article-journal","title":"Beyond Cryptocurrencies: Exploring Blockchain Consensus for Swarm Robotics Applications; A Review","abstract":"Abstract In the current information superhighway epoch, consensus algorithms are playing a very important role in dynamic and rapidly evolving network technologies like blockchain, IoT systems and swarm robotics network applications. Ensuring the integrity, security, and efficiency of any decentralized network is becoming an uphill task because of failures, malicious actions and intrusion challenges in the network. On the other hand, the consensus mechanism helps in achieving a common agreement about transactions among trust-less network participants and maintaining the network’s integrity by ensuring a consistent and reliable state of the system across all nodes despite potential failures, delays, or presence of malicious actors in any decentralized networks. This review paper conducts a comprehensive analysis on most commonly used consensus algorithms by studying their capabilities, working principles, strengths, and limitations with the aim of providing insights into their existing challenges and gaps in using these algorithms for integrating blockchain platform with swarm systems. This study will lead to designing a suitable blockchain-based secured consensus algorithm for swarm robotics network applications.","author":[{"family":"Ranganathan","given":"Sathishkumar"},{"family":"Mariappan","given":"Muralindran"},{"family":"Muthukaruppan","given":"Karthigayan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.21203/rs.3.rs-7417193/v1","URL":"https://doi.org/10.21203/rs.3.rs-7417193/v1","source":"crossref"},{"id":"doi:10.1002/rob.70013","type":"article-journal","title":"Self‐Adaptive, Untethered Soft Gripper System for Efficient Agricultural Harvesting","abstract":"ABSTRACT As modern agriculture faces increasing demands for efficiency and automation, this study presents a novel, untethered soft gripper system designed for autonomous and efficient harvesting. At the core of this innovation is a piston‐driven, pneumatically actuated gripper embedded with flexible tactile sensors, enabling operation without an external air source. The system integrates a compact motorized syringe, forming a closed‐loop fluid circuit that provides precise pressure control for adaptive grasping. The pneumatic actuation mechanism regulates air pressure from −30 to 180 kPa, allowing the gripper to perform delicate and adaptive handling, particularly suited for tree fruits and other fragile crops. A key feature of the system is its intelligent control mechanism, which seamlessly combines pneumatic and electrical systems to enhance autonomy and versatility in agricultural applications. The integration of size recognition and adaptive grasping, enabled by force feedback from embedded tactile sensors, ensures safe, efficient, and damage‐free harvesting. Demonstrating exceptional potential for autonomous agricultural operations, the untethered soft gripper system offers enhanced independence, maneuverability, and adaptability across diverse harvesting environments. Its ability to optimize crop handling while minimizing damage highlights its significance as a pioneering solution for the future of automated agriculture.","author":[{"family":"Zhao","given":"Yunwei"},{"family":"Zhao","given":"Wenwei"},{"family":"Song","given":"Maozheng"},{"family":"Jin","given":"Yi"},{"family":"Liu","given":"Zheng"},{"family":"Islam","given":"Md"},{"family":"Liu","given":"Xiaomin"},{"family":"Cao","given":"Changyong"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1002/rob.70013","URL":"https://doi.org/10.1002/rob.70013","source":"crossref"},{"id":"doi:10.31763/ijrcs.v5i2.1826","type":"article-journal","title":"Powertrain Conversion of a Small Agricultural Tractor from Diesel Engine to Permanent Magnet Synchronous Motor","abstract":"This paper presents the powertrain conversion of a small diesel-powered tractor into an electric tractor or electric off-road vehicle (EORV), offering a cost-effective alternative to purchasing a new electric model, which may be financially challenging for small-scale farmers. Given that electricity is generally cheaper than diesel fuel in Malaysia, the conversion approach aims to reduce long-term operational costs while maintaining or improving performance. The primary contribution of this work is a systematic and practical method for electric tractor conversion. The process begins with analysing the existing performance and operational requirements of the diesel tractor, followed by the selection of suitable components—namely, the electric motor, battery cells, and other associated systems. These components are then integrated into the tractor, and initial testing was performed. A speed run test was conducted to evaluate the power capability of the converted tractor. Results indicate that the electric motor delivers higher power and speed compared to the original diesel engine. The onboard energy monitoring device recorded a noticeable current spike and voltage sag during acceleration, as expected. The motor power was calculated from the recorded voltage and current data. The data show that the motor output exceeds the rated power of the original engine, suggesting that the system can handle higher loads. Some challenges encountered during the conversion process include the high initial cost, limited availability of components that meet performance requirements, and technical challenges in ensuring the durability and efficiency of the modified drivetrain. In conclusion, further testing under various load conditions is necessary to fully evaluate energy consumption and system performance in real agricultural environments.","author":[{"family":"Yaacob","given":"Ahmad"},{"family":"Jamaluddin","given":"Muhammad"},{"family":"Shukor","given":"Ahmad"},{"family":"Mansor","given":"Muhd"}],"issued":{"date-parts":[[2025]]},"DOI":"10.31763/ijrcs.v5i2.1826","URL":"https://doi.org/10.31763/ijrcs.v5i2.1826","source":"crossref"},{"id":"doi:10.1109/icra55743.2025.11127685","type":"article-journal","title":"A Dataset and Benchmark for Shape Completion of Fruits for Agricultural Robotics","abstract":"As the world population is expected to reach 10 billion by 2050, our agricultural production system needs to double its productivity despite a decline of human workforce in the agricultural sector. Autonomous robotic systems are one promising pathway to increase productivity by taking over labor-intensive manual tasks like fruit picking. To be effective, such systems need to monitor and interact with plants and fruits precisely, which is challenging due to the cluttered nature of agricultural environments causing, for example, strong occlusions. Thus, being able to estimate the complete 3D shapes of objects in presence of occlusions is crucial for automating operations such as fruit harvesting. In this paper, we propose the first publicly available 3D shape completion dataset for agricultural vision systems. We provide an RGB-D dataset for estimating the 3D shape of fruits. Specifically, our dataset contains RGB-D frames of single sweet peppers in lab conditions but also in a commercial greenhouse. For each fruit, we additionally collected high-precision point clouds that we use as ground truth. For acquiring the ground truth shape, we developed a measuring process that allows us to record data of real sweet pepper plants, both in the lab and in the greenhouse with high precision, and determine the shape of the sensed fruits. We release our dataset, consisting of almost 7,000 RGB-D frames belonging to more than 100 different fruits. We provide segmented RGB-D frames, with camera intrinsics to easily obtain colored point clouds, together with the corresponding high-precision, occlusion-free point clouds obtained with a high-precision laser scanner. We additionally enable evaluation of shape completion approaches on a hidden test set through a public challenge on a benchmark server.","author":[{"family":"Magistri","given":"Federico"},{"family":"Läbe","given":"Thomas"},{"family":"Marks","given":"Elias"},{"family":"Nagulavancha","given":"Sumanth"},{"family":"Pan","given":"Yue"},{"family":"Smitt","given":"Claus"},{"family":"Klingbeil","given":"Lasse"},{"family":"Halstead","given":"Michael"},{"family":"Kuhlmann","given":"Heiner"},{"family":"Mccool","given":"Chris"},{"family":"Behley","given":"Jens"},{"family":"Stachniss","given":"Cyrill"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1109/icra55743.2025.11127685","URL":"https://doi.org/10.1109/icra55743.2025.11127685","source":"crossref"},{"id":"doi:10.1177/09713441251395487","type":"article-journal","title":"Irrigation Governance, Private Investment and Agricultural Productivity in India\n                    <sup/>","abstract":"This article analyses irrigation investment among agricultural households across 20 major Indian states and its relationship with irrigation governance and agricultural productivity. An irrigation governance index is constructed based on select indicators that capture important dimensions of irrigation water governance. The principal component analysis is used to construct the index in each of the selected states for the period 2001–2002 to 2015–2016. Results reveal that in some states, farmers’ dependence on electric tube wells, and hence groundwater, has increased extensively due to inadequate access to public (canal) irrigation. Irrigation accounted on average for 35% of total investments undertaken by farmers, with little increase between 2002–2003 and 2012–2013. During that period, farmers’ expenditures on machinery, tractors and livestock have significantly increased. Results further indicate that good irrigation governance has a positive influence on private investment in agriculture, which in turn can contribute to enhance agricultural productivity and farmers’ incomes. This argument is substantiated by the results obtained from a structural equation model using the ICAR–ICRISAT household, individual and plot-level data. We find that states where both governance and private investment in irrigation are at very low levels should receive higher priority; these include Assam, Odisha, West Bengal, Kerala, Bihar and Jharkhand and Uttar Pradesh and Uttarakhand. The states which are low in governance but high in irrigation investment (Madhya Pradesh, Chhattisgarh, Himachal Pradesh and Karnataka) should improve governance to enable efficient use of irrigation resources. JEL Classification: Q15, Q18","author":[{"family":"Kumar","given":"Anjani"},{"family":"Bathla","given":"Seema"},{"family":"Elumalai","given":"K"},{"family":"Saroj","given":"Sunil"}],"issued":{"date-parts":[[2025]]},"DOI":"10.1177/09713441251395487","URL":"https://doi.org/10.1177/09713441251395487","source":"crossref"},{"id":"oa:W4405926386","type":"article-journal","title":"High-Precision UAV Photogrammetry with RTK GNSS: Eliminating Ground Control Points","abstract":"The advancements in Unmanned Aerial Vehicles (UAVs) have significantly enhanced the capability of the photogrammetric approaches, particularly with the integration of Real-Time Kinematic (RTK) sensors. That approach enables the operators to use the Global Navigation Satellite System (GNSS) more efficiently with the production of high-precision 3D Digital Terrain Models (DTMs). Traditionally, Ground Control Points (GCPs) are used to link those models to a ground coordinate system, but their establishment is time-consuming and labor-intensive, requiring static or rapid-static GNSS observations over two hours for each point. However, RTK-embedded UAVs offer a significant improvement by facilitating direct geo-referencing of DTMs, which includes the estimation of internal and external orientation parameters more efficiently and potentially eliminating the need for GCPs. In this study, UAV flights over a test area at various altitudes (30m, 45m, 60m) were conducted to evaluate the 3D positioning accuracy of photogrammetric models generated without using any GCP, and their locations were compared against the precise GNSS observations for 22 control points. Results indicated that UAVs with RTK ability could achieve centimeter-level accuracy in positioning, making this kind of evaluation a viable alternative to traditional methods. This study also discusses the implications of those results within the context of large-scale map production and their regulations in Türkiye. The elimination of GCPs should significantly reduce the time and effort associated with map production, suggesting a potential alternative in regulatory standards to incorporate these technological approaches.","author":[{"family":"Alkan","given":"Mehmet"}],"issued":{"date-parts":[[2024]]},"DOI":"10.17350/hjse19030000341","URL":"https://doi.org/10.17350/hjse19030000341","source":"openalex"},{"id":"oa:W4404325876","type":"article-journal","title":"Wise Roles and Future Visionary Endeavors of Current Emperor: Advancing Dynamic Methods for Longitudinal Microbiome Meta‐Omics Data in Personalized and Precision Medicine","abstract":"Understanding the etiological complexity of diseases requires identifying biomarkers longitudinally associated with specific phenotypes. Advanced sequencing tools generate dynamic microbiome data, providing insights into microbial community functions and their impact on health. This review aims to explore the current roles and future visionary endeavors of dynamic methods for integrating longitudinal microbiome multi-omics data in personalized and precision medicine. This work seeks to synthesize existing research, propose best practices, and highlight innovative techniques. The development and application of advanced dynamic methods, including the unified analytical frameworks and deep learning tools in artificial intelligence, are critically examined. Aggregating data on microbes, metabolites, genes, and other entities offers profound insights into the interactions among microorganisms, host physiology, and external stimuli. Despite progress, the absence of gold standards for validating analytical protocols and data resources of various longitudinal multi-omics studies remains a significant challenge. The interdependence of workflow steps critically affects overall outcomes. This work provides a comprehensive roadmap for best practices, addressing current challenges with advanced dynamic methods. The review underscores the biological effects of clinical, experimental, and analytical protocol settings on outcomes. Establishing consensus on dynamic microbiome inter-studies and advancing reliable analytical protocols are pivotal for the future of personalized and precision medicine.","author":[{"family":"Oh","given":"Sunghee"},{"family":"Li","given":"Robert"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1002/advs.202400458","URL":"https://doi.org/10.1002/advs.202400458","source":"openalex"},{"id":"oa:W4403230401","type":"article-journal","title":"Social issues in agriculture in rural areas","abstract":"Ensuring the well-being of farmers, their families, farmworkers, and that of their communities is high on the agenda of governments and policy makers in OECD countries. The quality of agricultural jobs (e.g. working conditions) and quality of life aspects such as environmental quality, health, depopulation of rural areas, isolation, crime, discrimination, and access to knowledge together determine the well-being of those active in the agricultural sector. Relevant policy design has tended to be hampered by serious data gaps. By focusing on different dimensions of well-being, this paper proposes a framework for social issues in agriculture to identify cross-cutting challenges. Seven policy examples, covering diverse social issues such as mental health, developing social connections in isolated rural areas, and inclusiveness of Indigenous Peoples and those with disabilities, confirm the need to look beyond traditional sectoral policies and to address social issues from a broader policy perspective. Only a multipronged approach can successfully remove the barriers that hinder opportunities for all farmers and their communities.","author":[{"family":"Asai","given":"Masayasu"},{"family":"Antón","given":"Jesús"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1787/fec15b38-en","URL":"https://doi.org/10.1787/fec15b38-en","source":"openalex"},{"id":"oa:W4401724298","type":"article-journal","title":"Precision and bias of carbon storage estimations in wetland and mangrove sediments","abstract":"Peaty sediments in coastal wetlands play an important role in the sequestration of atmospheric carbon dioxide and its belowground storage. Sediment cores are used to quantify organic matter (OM) density, estimated by multiplying the bulk density of a core segment by its OM fraction. This method can be imprecise, as repeated samples often differ widely. Recent studies have shown that sediment bulk density and OM fraction are not independent but tightly related by a function called the ideal-mixing model. Thus, the bulk density of the sediment can be directly estimated from its OM fraction. Statistical theory and simulations demonstrate that the high variance in the product estimation of OM density is the result of error propagation in the product of two functionally related variables with independent errors. Estimating OM density in wetland sediments using the ideal-mixing model is more precise than the traditionally used product estimate, especially in highly organic sediments.","author":[{"family":"Ezcurra","given":"Exequiel"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1126/sciadv.adl1079","URL":"https://doi.org/10.1126/sciadv.adl1079","source":"openalex"},{"id":"doi:10.5281/zenodo.20623965","type":"article-journal","title":"FACTORS FOR ENHANCING THE COMPETITIVENESS OF COTTON FIBER IN THE TEXTILE INDUSTRY","abstract":"Cotton fiber, despite facing intensifying competition from synthetic alternatives particularly polyester, which commanded 59% of global fiber production in 2024 — retains indispensable attributes of breathability, biodegradability, and consumer preference. This article investigates the key determinants of cotton fiber's competitiveness in the global textile industry through a multi-factor analysis encompassing raw material quality, technological upgrading, sustainability certification, market diversification, and value chain integration. Empirical data are drawn from USDA, Textile Exchange, COMTRADE, and industry market reports covering the period 2020–2024. A comparative analysis of leading cotton-exporting nations — including Brazil, India, and Uzbekistan — is conducted. The findings reveal that competitiveness is primarily driven by fiber quality improvement, adoption of precision agriculture and advanced ginning technologies, sustainability certification uptake, and strategic transition from raw fiber exports toward finished, high-value textile products. The case of Uzbekistan is examined in depth, where textile exports grew from approximately USD 6 million in 2017 to USD 3.1 billion in 2023, demonstrating the transformative impact of cluster-based industrial policy and vertical integration. The article concludes with policy recommendations for cotton-producing developing economies to enhance long-term competitiveness in the global textile market.","author":[{"family":"Qizi","given":"Ahmadjonova"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20623965","URL":"https://doi.org/10.5281/zenodo.20623965","source":"datacite"},{"id":"doi:10.5281/zenodo.20623966","type":"article-journal","title":"FACTORS FOR ENHANCING THE COMPETITIVENESS OF COTTON FIBER IN THE TEXTILE INDUSTRY","abstract":"Cotton fiber, despite facing intensifying competition from synthetic alternatives particularly polyester, which commanded 59% of global fiber production in 2024 — retains indispensable attributes of breathability, biodegradability, and consumer preference. This article investigates the key determinants of cotton fiber's competitiveness in the global textile industry through a multi-factor analysis encompassing raw material quality, technological upgrading, sustainability certification, market diversification, and value chain integration. Empirical data are drawn from USDA, Textile Exchange, COMTRADE, and industry market reports covering the period 2020–2024. A comparative analysis of leading cotton-exporting nations — including Brazil, India, and Uzbekistan — is conducted. The findings reveal that competitiveness is primarily driven by fiber quality improvement, adoption of precision agriculture and advanced ginning technologies, sustainability certification uptake, and strategic transition from raw fiber exports toward finished, high-value textile products. The case of Uzbekistan is examined in depth, where textile exports grew from approximately USD 6 million in 2017 to USD 3.1 billion in 2023, demonstrating the transformative impact of cluster-based industrial policy and vertical integration. The article concludes with policy recommendations for cotton-producing developing economies to enhance long-term competitiveness in the global textile market.","author":[{"family":"Qizi","given":"Ahmadjonova"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20623966","URL":"https://doi.org/10.5281/zenodo.20623966","source":"datacite"},{"id":"doi:10.5281/zenodo.21264070","type":"article-journal","title":"SIGNAL AND IMAGE PROCESSING TECHNIQUES FOR MONITORING AGRICULTURAL ECOSYSTEMS AND BIODIVERSITY CONSERVATION","abstract":"Plant diseases are very challenging to agriculture since they reduce crop production and also biodiversity. The timely identification of diseases is essential in the safeguarding of food and the sustainability of ecosystems. This study employs the use of signal and image processing algorithms along with the deep learning to create an automated plant disease detection system in agricultural ecosystems. The algorithm employs the Convolutional Neural Networks (CNNs) that are being trained with the Tomato Leaf Disease Dataset to determine the tomato leaf diseases with the help of the state-of-the-art image preprocessing software such as Gaussian smoothing and histogram equalization. The model was found to have a 79.5 percent validation accuracy indicating that the model could generalize effectively on the dataset. Nonetheless, the difficulty still existed in distinguishing similar diseases that exhibit similar symptoms like Tomato Bacterial Spot and Tomato Early Blight, which emphasized the limitation in the unbalance of the data as well as lack of diversity of diseases. The implication of early disease detection on the basis of this model is potentially important in reducing pesticide use, promoting more sustainable agricultural activities, and indirectly in conserving biodiversity. Innovations in future research should increase the data set and incorporate environmental data as well as investigating transfer learning to enhance the accuracy and flexibility of models to enhance precision agriculture and ecosystem management.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21264070","URL":"https://doi.org/10.5281/zenodo.21264070","source":"datacite"},{"id":"doi:10.5281/zenodo.21264071","type":"article-journal","title":"SIGNAL AND IMAGE PROCESSING TECHNIQUES FOR MONITORING AGRICULTURAL ECOSYSTEMS AND BIODIVERSITY CONSERVATION","abstract":"Plant diseases are very challenging to agriculture since they reduce crop production and also biodiversity. The timely identification of diseases is essential in the safeguarding of food and the sustainability of ecosystems. This study employs the use of signal and image processing algorithms along with the deep learning to create an automated plant disease detection system in agricultural ecosystems. The algorithm employs the Convolutional Neural Networks (CNNs) that are being trained with the Tomato Leaf Disease Dataset to determine the tomato leaf diseases with the help of the state-of-the-art image preprocessing software such as Gaussian smoothing and histogram equalization. The model was found to have a 79.5 percent validation accuracy indicating that the model could generalize effectively on the dataset. Nonetheless, the difficulty still existed in distinguishing similar diseases that exhibit similar symptoms like Tomato Bacterial Spot and Tomato Early Blight, which emphasized the limitation in the unbalance of the data as well as lack of diversity of diseases. The implication of early disease detection on the basis of this model is potentially important in reducing pesticide use, promoting more sustainable agricultural activities, and indirectly in conserving biodiversity. Innovations in future research should increase the data set and incorporate environmental data as well as investigating transfer learning to enhance the accuracy and flexibility of models to enhance precision agriculture and ecosystem management.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21264071","URL":"https://doi.org/10.5281/zenodo.21264071","source":"datacite"},{"id":"doi:10.5281/zenodo.19364680","type":"article-journal","title":"Artificial Intelligence and Sustainable Development","abstract":"Abstract Artificial Intelligence (AI) has emerged as a transformative force in addressing global Artificial Intelligence has increasingly emerged as a foundational technology supporting sustainable development by enabling intelligent analysis, automation, and informed decision-making across complex systems. Unlike traditional computational tools, AI systems can process massive, heterogeneous datasets and continuously learn from new inputs, making them particularly suitable for addressing long-term social, economic, and environmental challenges. Sustainable development demands integrated solutions that consider interdependencies between poverty, health, education, energy, and ecosystems, and AI provides the computational capability to manage this complexity. AI plays a crucial role in monitoring development indicators by analyzing satellite imagery, sensor networks, and administrative data. These tools help governments and international organizations track progress, identify emerging risks, and allocate resources more efficiently. For example, AI-based image recognition supports land-use monitoring, infrastructure planning, and environmental protection, while natural language processing assists in analyzing policy documents and citizen feedback. Such applications enhance evidence-based governance and improve transparency. Beyond monitoring, AI supports predictive and prescriptive analytics. Machine learning models can forecast climate patterns, food demand, disease outbreaks, and economic trends, allowing policymakers to shift from reactive to proactive strategies. Generative AI further strengthens this role by enabling scenario modeling, helping decision-makers evaluate the long-term impacts of policy choices under different assumptions. These capabilities are essential for designing resilient development pathways in an uncertain global environment. However, while AI offers strong enabling potential, many current applications remain limited in scope, focusing on efficiency gains rather than systemic transformation. Scholars emphasize the need to move beyond descriptive analytics toward AI systems that actively support sustainable innovation and inclusive growth. To achieve this, governance mechanisms, ethical safeguards, and capacity-building initiatives must evolve alongside technological advancements. When responsibly deployed, AI can function as a powerful catalyst for balanced and inclusive sustainable development.","author":[{"family":"Anarase","given":"Lalasaheb"},{"family":"Shinde","given":"Akshay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19364680","URL":"https://doi.org/10.5281/zenodo.19364680","source":"datacite"},{"id":"doi:10.5281/zenodo.19364681","type":"article-journal","title":"Artificial Intelligence and Sustainable Development","abstract":"Abstract Artificial Intelligence (AI) has emerged as a transformative force in addressing global Artificial Intelligence has increasingly emerged as a foundational technology supporting sustainable development by enabling intelligent analysis, automation, and informed decision-making across complex systems. Unlike traditional computational tools, AI systems can process massive, heterogeneous datasets and continuously learn from new inputs, making them particularly suitable for addressing long-term social, economic, and environmental challenges. Sustainable development demands integrated solutions that consider interdependencies between poverty, health, education, energy, and ecosystems, and AI provides the computational capability to manage this complexity. AI plays a crucial role in monitoring development indicators by analyzing satellite imagery, sensor networks, and administrative data. These tools help governments and international organizations track progress, identify emerging risks, and allocate resources more efficiently. For example, AI-based image recognition supports land-use monitoring, infrastructure planning, and environmental protection, while natural language processing assists in analyzing policy documents and citizen feedback. Such applications enhance evidence-based governance and improve transparency. Beyond monitoring, AI supports predictive and prescriptive analytics. Machine learning models can forecast climate patterns, food demand, disease outbreaks, and economic trends, allowing policymakers to shift from reactive to proactive strategies. Generative AI further strengthens this role by enabling scenario modeling, helping decision-makers evaluate the long-term impacts of policy choices under different assumptions. These capabilities are essential for designing resilient development pathways in an uncertain global environment. However, while AI offers strong enabling potential, many current applications remain limited in scope, focusing on efficiency gains rather than systemic transformation. Scholars emphasize the need to move beyond descriptive analytics toward AI systems that actively support sustainable innovation and inclusive growth. To achieve this, governance mechanisms, ethical safeguards, and capacity-building initiatives must evolve alongside technological advancements. When responsibly deployed, AI can function as a powerful catalyst for balanced and inclusive sustainable development.","author":[{"family":"Anarase","given":"Lalasaheb"},{"family":"Shinde","given":"Akshay"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19364681","URL":"https://doi.org/10.5281/zenodo.19364681","source":"datacite"},{"id":"doi:10.5281/zenodo.19819887","type":"article-journal","title":"An IoT-Based Soil Nutrient Detection, Monitoring, and Crop Recommendation System for Smart Agriculture in Uganda","abstract":"Soil nutrient management is essential for improving agricultural productivity and promoting sustainable farming practices. However, many small-scale farmers in Uganda have limited access to affordable and timely soil testing services. This paper presents an Internet of Things (IoT)-based soil nutrient detection, monitoring, and crop recommendation system designed to support data-driven farming decisions. The system integrates an NPK sensor with a Raspberry Pi 3 Model B using an RS-485 communication module to collect real-time Nitrogen, Phosphorus, and Potassium values. The collected data is processed using Python, stored in a MySQL database, and displayed through a web-based dashboard developed using HTML, CSS, PHP, and Chart.js. A Random Forest machine learning model is deployed through a Flask API to recommend suitable crops based on detected soil nutrient levels. Experimental evaluation conducted on a 100 m² agricultural plot in Soroti, Uganda showed reliable data transmission, acceptable sensor accuracy, and strong usability. The system achieved 99.8% data transmission success, sensor mean absolute error between 3.2% and 4.1%, and 90% machine learning model accuracy. The proposed system provides an affordable precision agriculture solution for smallholder farmers.","author":[{"family":"Nahurira","given":"Didas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19819887","URL":"https://doi.org/10.5281/zenodo.19819887","source":"datacite"},{"id":"doi:10.5281/zenodo.19819888","type":"article-journal","title":"An IoT-Based Soil Nutrient Detection, Monitoring, and Crop Recommendation System for Smart Agriculture in Uganda","abstract":"Soil nutrient management is essential for improving agricultural productivity and promoting sustainable farming practices. However, many small-scale farmers in Uganda have limited access to affordable and timely soil testing services. This paper presents an Internet of Things (IoT)-based soil nutrient detection, monitoring, and crop recommendation system designed to support data-driven farming decisions. The system integrates an NPK sensor with a Raspberry Pi 3 Model B using an RS-485 communication module to collect real-time Nitrogen, Phosphorus, and Potassium values. The collected data is processed using Python, stored in a MySQL database, and displayed through a web-based dashboard developed using HTML, CSS, PHP, and Chart.js. A Random Forest machine learning model is deployed through a Flask API to recommend suitable crops based on detected soil nutrient levels. Experimental evaluation conducted on a 100 m² agricultural plot in Soroti, Uganda showed reliable data transmission, acceptable sensor accuracy, and strong usability. The system achieved 99.8% data transmission success, sensor mean absolute error between 3.2% and 4.1%, and 90% machine learning model accuracy. The proposed system provides an affordable precision agriculture solution for smallholder farmers.","author":[{"family":"Nahurira","given":"Didas"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19819888","URL":"https://doi.org/10.5281/zenodo.19819888","source":"datacite"},{"id":"doi:10.5281/zenodo.21578395","type":"article-journal","title":"AI-Integrated IoT System for Intelligent Monitoring and Automation in Smart Gardening","abstract":"The rapid expansion of urban agriculture and home-based food production has intensified the need for intelligent, resource-efficient gardening systems capable of adapting to dynamic environmental conditions. Conventional automated irrigation systems predominantly rely on static threshold-based control mechanisms, which often fail to respond optimally to fluctuating soil, climatic, and plant physiological parameters. This study proposes an AI-integrated Internet of Things (IoT) framework designed to enable intelligent monitoring, predictive analytics, and adaptive automation in smart gardening environments. The proposed system incorporates a multi-layer architecture consisting of distributed environmental sensors, an edge-processing unit for real-time data filtering and decision support, and a cloud-based machine learning engine for predictive modeling and optimization. Soil moisture, temperature, humidity, light intensity, and nutrient-level data were continuously collected and processed to train supervised learning models for soil moisture prediction and irrigation demand forecasting. In addition, a reinforcement learning–based scheduler was implemented to dynamically regulate irrigation timing and volume according to environmental variability and plant growth stages. Experimental validation was conducted in a controlled smart garden setup over multiple growth cycles. The AI-driven system demonstrated improved prediction accuracy in soil moisture estimation and achieved significant reductions in water consumption compared to conventional rule-based irrigation approaches, while maintaining optimal plant health indicators. Furthermore, edge-based deployment reduced system latency and enhanced real-time responsiveness without imposing excessive energy overhead. The findings confirm that integrating artificial intelligence with IoT infrastructure can substantially enhance the efficiency, sustainability, and autonomy of smart gardening systems. The proposed framework offers a scalable and adaptable solution for urban agriculture, contributing to water conservation, energy efficiency, and precision resource management in small-scale food production environments.","author":[{"family":"Sodikova","given":"Zakhro"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21578395","URL":"https://doi.org/10.5281/zenodo.21578395","source":"datacite"},{"id":"doi:10.5281/zenodo.21578396","type":"article-journal","title":"AI-Integrated IoT System for Intelligent Monitoring and Automation in Smart Gardening","abstract":"The rapid expansion of urban agriculture and home-based food production has intensified the need for intelligent, resource-efficient gardening systems capable of adapting to dynamic environmental conditions. Conventional automated irrigation systems predominantly rely on static threshold-based control mechanisms, which often fail to respond optimally to fluctuating soil, climatic, and plant physiological parameters. This study proposes an AI-integrated Internet of Things (IoT) framework designed to enable intelligent monitoring, predictive analytics, and adaptive automation in smart gardening environments. The proposed system incorporates a multi-layer architecture consisting of distributed environmental sensors, an edge-processing unit for real-time data filtering and decision support, and a cloud-based machine learning engine for predictive modeling and optimization. Soil moisture, temperature, humidity, light intensity, and nutrient-level data were continuously collected and processed to train supervised learning models for soil moisture prediction and irrigation demand forecasting. In addition, a reinforcement learning–based scheduler was implemented to dynamically regulate irrigation timing and volume according to environmental variability and plant growth stages. Experimental validation was conducted in a controlled smart garden setup over multiple growth cycles. The AI-driven system demonstrated improved prediction accuracy in soil moisture estimation and achieved significant reductions in water consumption compared to conventional rule-based irrigation approaches, while maintaining optimal plant health indicators. Furthermore, edge-based deployment reduced system latency and enhanced real-time responsiveness without imposing excessive energy overhead. The findings confirm that integrating artificial intelligence with IoT infrastructure can substantially enhance the efficiency, sustainability, and autonomy of smart gardening systems. The proposed framework offers a scalable and adaptable solution for urban agriculture, contributing to water conservation, energy efficiency, and precision resource management in small-scale food production environments.","author":[{"family":"Sodikova","given":"Zakhro"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21578396","URL":"https://doi.org/10.5281/zenodo.21578396","source":"datacite"},{"id":"doi:10.5281/zenodo.21538663","type":"article-journal","title":"NEW ZEALAND DAIRY INDUSTRY INWARD INVESTMENT & MACROECONOMIC TRANSFORMATION PROSPECTUS PART ONE OF THREE","abstract":"The Pure-Milk Green Finance Matrix is a mathematically optimized, closed-loop agritech infrastructure model designed to break the political gridlock between economic growth and environmental protection. By holding dairy herd numbers steady to preserve New Zealand's baseline $28.6 billion export engine, the framework layers direct-to-satellite smart tracking, modular biosecure hydroponic forage hubs, on-site solar micro-grids, and sodium-rebreather Direct Air Capture (DAC) to eliminate environmental pollution at the source. Funded via a 70/30 international joint-venture and green bond architecture, the model delivers a rapid 28-month commercial ROI for investors while instantly securing 100% nitrate-safe drinking water for local communities via a dual-layer backup filtration shield. The Executive Summary This project prospectus introduces a world-first, multi-objective infrastructure framework that redefines sustainable pastoral agriculture. By rejecting binary choices between the economy and the ecology, the model stabilizes traditional commodity revenue while transforming farms into integrated, green-powered agritech nodes. The architecture utilizes Starlink telemetry for dynamic on-site grazing management, micro-biosecure vertical container pods to replace foreign feed imports, and specialized multi-tier shelterbelts hosting methane-eating bacteria to scrub the atmosphere. Backed by accelerated tax incentives, high-wage job creation, and automated KiwiSaver reinvestment loops, the framework fully self-funds immediate municipal and rural water treatment upgrades. It provides a highly lucrative, de-risked investment platform that serves as a scalable, exportable intellectual property (IP) blueprint for the global farming community. Master Index of Keywords To maximize search visibility across academic, corporate, agricultural, and financial databases, use this tiered index: 1. Green Finance & Macroeconomics Green Finance Matrix, Sovereign Green Bonds, Inward Foreign Direct Investment (FDI), 70/30 Profit Sharing, Accelerated Tax Depreciation, KiwiSaver Reinvestment Loop, Scope 3 Supply Chain Arbitrage, Capital Improvement Leases, Resource Economics, Public-Private Partnerships (PPP). 2. Agritech & Digital Farming Starlink Agriculture Telemetry, Halter Virtual Fencing, Real-time Soil Telemetry, Precision Livestock Farming (PLF), Automated Dosing Algorithms, Algorithmic Herd Management, Smart Tag Sensor Networks, Autonomous Agri-logistics. 3. Regenerative Botany & Hydroponics Modular Hydroponic Forage, Biosecure Pod Manufacturing, Plant Tissue Banks, Cut-and-Carry Silage Loops, Low-Leaching Pastures, Ecotain Plantain, Chicory Forage Crops, Multi-tier Agroforestry, Sustainable Feedstocks, Import Replacement. 4. Climate Tech & Engineering Methanotrophic Atmospheric Scrubbing, Methane-Eating Bacteria, Electrochemical Direct Air Capture (DAC), Sodium Rebreather Technology, Green Oxygen Production, On-Site Solar Micro-grids, Effluent Pond Bio-digesters, Renewable Utility Arbitrage, Maritime Carbon Credits. 5. Freshwater Protection & Public Health Dual-Layer Water Filtration Shield, Municipal Ion-Exchange Upgrades, Point-of-Entry Reverse Osmosis, Aquifer Hydrology Lag, Nitrate Contamination Mitigation, Catchment Health Dashboards, Groundwater Flushing, Biosecurity Firewalls, Rural Health Infrastructure. 6. Agribusiness & Labour Sharemilker Equity Contracts, Infrastructure Dividends, High-Wage Trade Job Creation, Technical Knowledge Transfer, Agritech Apprenticeships, New Zealand Agribusiness Innovation, Sustainable Dairy Supply Chains, Premium Value-Over-Volume.","author":[{"family":"Seagal","given":"David"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21538663","URL":"https://doi.org/10.5281/zenodo.21538663","source":"datacite"},{"id":"doi:10.5281/zenodo.21538664","type":"article-journal","title":"NEW ZEALAND DAIRY INDUSTRY INWARD INVESTMENT & MACROECONOMIC TRANSFORMATION PROSPECTUS PART ONE OF THREE","abstract":"The Pure-Milk Green Finance Matrix is a mathematically optimized, closed-loop agritech infrastructure model designed to break the political gridlock between economic growth and environmental protection. By holding dairy herd numbers steady to preserve New Zealand's baseline $28.6 billion export engine, the framework layers direct-to-satellite smart tracking, modular biosecure hydroponic forage hubs, on-site solar micro-grids, and sodium-rebreather Direct Air Capture (DAC) to eliminate environmental pollution at the source. Funded via a 70/30 international joint-venture and green bond architecture, the model delivers a rapid 28-month commercial ROI for investors while instantly securing 100% nitrate-safe drinking water for local communities via a dual-layer backup filtration shield. The Executive Summary This project prospectus introduces a world-first, multi-objective infrastructure framework that redefines sustainable pastoral agriculture. By rejecting binary choices between the economy and the ecology, the model stabilizes traditional commodity revenue while transforming farms into integrated, green-powered agritech nodes. The architecture utilizes Starlink telemetry for dynamic on-site grazing management, micro-biosecure vertical container pods to replace foreign feed imports, and specialized multi-tier shelterbelts hosting methane-eating bacteria to scrub the atmosphere. Backed by accelerated tax incentives, high-wage job creation, and automated KiwiSaver reinvestment loops, the framework fully self-funds immediate municipal and rural water treatment upgrades. It provides a highly lucrative, de-risked investment platform that serves as a scalable, exportable intellectual property (IP) blueprint for the global farming community. Master Index of Keywords To maximize search visibility across academic, corporate, agricultural, and financial databases, use this tiered index: 1. Green Finance & Macroeconomics Green Finance Matrix, Sovereign Green Bonds, Inward Foreign Direct Investment (FDI), 70/30 Profit Sharing, Accelerated Tax Depreciation, KiwiSaver Reinvestment Loop, Scope 3 Supply Chain Arbitrage, Capital Improvement Leases, Resource Economics, Public-Private Partnerships (PPP). 2. Agritech & Digital Farming Starlink Agriculture Telemetry, Halter Virtual Fencing, Real-time Soil Telemetry, Precision Livestock Farming (PLF), Automated Dosing Algorithms, Algorithmic Herd Management, Smart Tag Sensor Networks, Autonomous Agri-logistics. 3. Regenerative Botany & Hydroponics Modular Hydroponic Forage, Biosecure Pod Manufacturing, Plant Tissue Banks, Cut-and-Carry Silage Loops, Low-Leaching Pastures, Ecotain Plantain, Chicory Forage Crops, Multi-tier Agroforestry, Sustainable Feedstocks, Import Replacement. 4. Climate Tech & Engineering Methanotrophic Atmospheric Scrubbing, Methane-Eating Bacteria, Electrochemical Direct Air Capture (DAC), Sodium Rebreather Technology, Green Oxygen Production, On-Site Solar Micro-grids, Effluent Pond Bio-digesters, Renewable Utility Arbitrage, Maritime Carbon Credits. 5. Freshwater Protection & Public Health Dual-Layer Water Filtration Shield, Municipal Ion-Exchange Upgrades, Point-of-Entry Reverse Osmosis, Aquifer Hydrology Lag, Nitrate Contamination Mitigation, Catchment Health Dashboards, Groundwater Flushing, Biosecurity Firewalls, Rural Health Infrastructure. 6. Agribusiness & Labour Sharemilker Equity Contracts, Infrastructure Dividends, High-Wage Trade Job Creation, Technical Knowledge Transfer, Agritech Apprenticeships, New Zealand Agribusiness Innovation, Sustainable Dairy Supply Chains, Premium Value-Over-Volume.","author":[{"family":"Seagal","given":"David"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21538664","URL":"https://doi.org/10.5281/zenodo.21538664","source":"datacite"},{"id":"doi:10.17632/33jwc4s88m.1","type":"article-journal","title":"Synthetic_Soil Fertility dataset","abstract":"This dataset contains synthetic soil fertility data developed for machine learning-based soil classification, soil fertility prediction, and fertilizer recommendation research. The dataset includes relevant soil properties and agricultural parameters that can be used for developing and evaluating machine learning and deep learning models for precision agriculture. The dataset is intended to support research on soil fertility assessment, nutrient prediction, crop-related analysis, and fertilizer recommendation. The data can be used for model development, feature analysis, classification, regression, and comparative evaluation of machine learning algorithms. This dataset is provided for academic and research purposes. The data are synthetically generated and are intended for methodological development, testing, and validation of machine learning approaches. Researchers using this dataset should clearly acknowledge its synthetic nature when reporting results. Keywords Soil fertility; Soil classification; Machine learning; Deep learning; Fertilizer recommendation; Precision agriculture; Soil nutrients; Agricultural data; Synthetic dataset; Crop recommendation; Nutrient prediction.","author":[{"family":"Research Scholar","given":"Lakshmi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/33jwc4s88m.1","URL":"https://doi.org/10.17632/33jwc4s88m.1","source":"datacite"},{"id":"doi:10.17632/33jwc4s88m","type":"article-journal","title":"Synthetic_Soil Fertility dataset","abstract":"This dataset contains synthetic soil fertility data developed for machine learning-based soil classification, soil fertility prediction, and fertilizer recommendation research. The dataset includes relevant soil properties and agricultural parameters that can be used for developing and evaluating machine learning and deep learning models for precision agriculture. The dataset is intended to support research on soil fertility assessment, nutrient prediction, crop-related analysis, and fertilizer recommendation. The data can be used for model development, feature analysis, classification, regression, and comparative evaluation of machine learning algorithms. This dataset is provided for academic and research purposes. The data are synthetically generated and are intended for methodological development, testing, and validation of machine learning approaches. Researchers using this dataset should clearly acknowledge its synthetic nature when reporting results. Keywords Soil fertility; Soil classification; Machine learning; Deep learning; Fertilizer recommendation; Precision agriculture; Soil nutrients; Agricultural data; Synthetic dataset; Crop recommendation; Nutrient prediction.","author":[{"family":"Research Scholar","given":"Lakshmi"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/33jwc4s88m","URL":"https://doi.org/10.17632/33jwc4s88m","source":"datacite"},{"id":"doi:10.17632/cdy4gnxt6n.1","type":"article-journal","title":"Hybrid machine learning framework for simulating biological yield in food systems using environmental and agronomic determinants","abstract":"Research Hypothesis This study tests the hypothesis that a hybrid machine‑learning framework integrating enhanced evolutionary feature selection (Bees Royalty Offspring Algorithm, BROA) with Gradient Boosting Regression (GBR) can accurately predict wild blueberry (Vaccinium angustifolium) yield using ecological, climatic, and agronomic determinants. A secondary hypothesis is that the feature selection process can identify the most influential yield‑driving factors, providing both high predictive accuracy and biological interpretability for precision agriculture. Data Description The dataset used in this study was generated by the Wild Blueberry Pollination Simulation Model – a spatially explicit, individual‑based model validated against 30 years of field observations from Maine, USA, and the Canadian Maritimes (Qu &amp; Drummond, 2018). The simulation data are publicly available in the Mendeley database (DOI: 10.17632/p5hvjzsvn8.1; Qu et al., 2020). Dataset structure: The final dataset consists of 777 records, each representing the average yield (kg/ha) over 100 simulation runs for a unique combination of input parameters. Each record contains 16 predictor variables and the target variable (yield). The predictors include: Agronomic factors, Biological factors, Climatic factors. Code Description The deposited code implements the full hybrid machine‑learning pipeline: Optimized BROA feature selection: An enhanced version of the Bee Royalty Offspring Algorithm (Jamshidnezhad &amp; Nordin, 2013) with six key modifications: (a) simplified Euclidean distance‑based mating mechanism (mating_radius = 0.3), (b) elimination of rigid algorithmic phases, (c) dynamic local search with adaptive step‑size reduction, (d) cross‑validated Mean Squared Error (MSE) fitness evaluation using Gradient Boosting Regressor, (e) simplified population management (combining current and offspring populations), and (f) improved parameterisation with configurable hyperparameters (n_royalty = 5, n_workers = 20, offspring_size = 10, max_iter = 50, feature_threshold = 0.6, local_search_iter = 5, mutation_rate = 0.1). Predictive model training: Five machine learning models are trained on the selected features: (GBR), (RFR), (SVR), (KNN), and (ANNs) with three architectures. Robustness assessment: The entire pipeline is repeated across 10 different random seeds (42, 123, 456, 789, 1024, 111, 222, 333, 444, 555) to evaluate stability. Software environment: All code was implemented in Python 3.8.8 using Spyder 4.2.5 (Anaconda 3) with the following library versions: scikit‑learn 0.24.1, numpy 1.20.1, pandas 1.2.4, matplotlib 3.3.4, seaborn 0.11.1, shap 0.41.0, openpyxl 3.0.9, and xgboost 2.0.0 (for comparison only). All random seeds are fixed to ensure full reproducibility. AI-assisted tools were used to assist in coding Python scripts.","author":[{"family":"Jamshidnezhad","given":"Amir"},{"family":"Singh","given":"Anika"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/cdy4gnxt6n.1","URL":"https://doi.org/10.17632/cdy4gnxt6n.1","source":"datacite"},{"id":"doi:10.17632/cdy4gnxt6n","type":"article-journal","title":"Hybrid machine learning framework for simulating biological yield in food systems using environmental and agronomic determinants","abstract":"Research Hypothesis This study tests the hypothesis that a hybrid machine‑learning framework integrating enhanced evolutionary feature selection (Bees Royalty Offspring Algorithm, BROA) with Gradient Boosting Regression (GBR) can accurately predict wild blueberry (Vaccinium angustifolium) yield using ecological, climatic, and agronomic determinants. A secondary hypothesis is that the feature selection process can identify the most influential yield‑driving factors, providing both high predictive accuracy and biological interpretability for precision agriculture. Data Description The dataset used in this study was generated by the Wild Blueberry Pollination Simulation Model – a spatially explicit, individual‑based model validated against 30 years of field observations from Maine, USA, and the Canadian Maritimes (Qu &amp; Drummond, 2018). The simulation data are publicly available in the Mendeley database (DOI: 10.17632/p5hvjzsvn8.1; Qu et al., 2020). Dataset structure: The final dataset consists of 777 records, each representing the average yield (kg/ha) over 100 simulation runs for a unique combination of input parameters. Each record contains 16 predictor variables and the target variable (yield). The predictors include: Agronomic factors, Biological factors, Climatic factors. Code Description The deposited code implements the full hybrid machine‑learning pipeline: Optimized BROA feature selection: An enhanced version of the Bee Royalty Offspring Algorithm (Jamshidnezhad &amp; Nordin, 2013) with six key modifications: (a) simplified Euclidean distance‑based mating mechanism (mating_radius = 0.3), (b) elimination of rigid algorithmic phases, (c) dynamic local search with adaptive step‑size reduction, (d) cross‑validated Mean Squared Error (MSE) fitness evaluation using Gradient Boosting Regressor, (e) simplified population management (combining current and offspring populations), and (f) improved parameterisation with configurable hyperparameters (n_royalty = 5, n_workers = 20, offspring_size = 10, max_iter = 50, feature_threshold = 0.6, local_search_iter = 5, mutation_rate = 0.1). Predictive model training: Five machine learning models are trained on the selected features: (GBR), (RFR), (SVR), (KNN), and (ANNs) with three architectures. Robustness assessment: The entire pipeline is repeated across 10 different random seeds (42, 123, 456, 789, 1024, 111, 222, 333, 444, 555) to evaluate stability. Software environment: All code was implemented in Python 3.8.8 using Spyder 4.2.5 (Anaconda 3) with the following library versions: scikit‑learn 0.24.1, numpy 1.20.1, pandas 1.2.4, matplotlib 3.3.4, seaborn 0.11.1, shap 0.41.0, openpyxl 3.0.9, and xgboost 2.0.0 (for comparison only). All random seeds are fixed to ensure full reproducibility. AI-assisted tools were used to assist in coding Python scripts.","author":[{"family":"Jamshidnezhad","given":"Amir"},{"family":"Singh","given":"Anika"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/cdy4gnxt6n","URL":"https://doi.org/10.17632/cdy4gnxt6n","source":"datacite"},{"id":"doi:10.5281/zenodo.20611845","type":"article-journal","title":"THE USE OF AI IN IOT-BASED SMART IRRIGATION","abstract":"ABSTRACT Water scarcity and high evapotranspiration rates pose significant challenges to agricultural productivity in semi-arid regions. This study describes the development and field assessment of an artificial intelligence-integrated, Internet of Things-based precision irrigation system deployed in Damaturu, northeastern Nigeria. The system architecture incorporates RS485 Modbus soil moisture sensors, DHT22 ambient environmental monitoring, and a Random Forest regression model executing inference at the edge on a Raspberry Pi microcomputer. Volumetric water delivery is governed through closed-loop feedback using Hall-effect flow meters, enabling verifiable and accurate actuation. A controlled 30-day comparative field trial was conducted across two agronomically identical plots — one governed by the AI-driven model and one operating on a conventional fixed-schedule regime. Cumulative flow-meter-verified delivery totals indicated that the AI-managed plot consumed 431.47 L against 592.39 L for the fixed-schedule plot, representing a 27.16% reduction in irrigation water usage. The AI model demonstrated markedly superior soil moisture stability, with a standard deviation of 1.35% compared to 10.46% in the control plot. Mean absolute percentage error in volumetric delivery accuracy was 2.69% for the AI plot and 1.54% for the fixed-schedule plot, confirming reliable closed-loop control under both regimes. These findings affirm the practical viability of deploying low-cost, machine learning-driven irrigation infrastructure in resource-constrained, semi-arid agricultural environments, and offer a replicable framework for advancing precision agriculture across comparable regions in sub-Saharan Africa.","author":[{"family":"Publication","given":"Cedtech"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20611845","URL":"https://doi.org/10.5281/zenodo.20611845","source":"datacite"},{"id":"doi:10.5281/zenodo.20611846","type":"article-journal","title":"THE USE OF AI IN IOT-BASED SMART IRRIGATION","abstract":"ABSTRACT Water scarcity and high evapotranspiration rates pose significant challenges to agricultural productivity in semi-arid regions. This study describes the development and field assessment of an artificial intelligence-integrated, Internet of Things-based precision irrigation system deployed in Damaturu, northeastern Nigeria. The system architecture incorporates RS485 Modbus soil moisture sensors, DHT22 ambient environmental monitoring, and a Random Forest regression model executing inference at the edge on a Raspberry Pi microcomputer. Volumetric water delivery is governed through closed-loop feedback using Hall-effect flow meters, enabling verifiable and accurate actuation. A controlled 30-day comparative field trial was conducted across two agronomically identical plots — one governed by the AI-driven model and one operating on a conventional fixed-schedule regime. Cumulative flow-meter-verified delivery totals indicated that the AI-managed plot consumed 431.47 L against 592.39 L for the fixed-schedule plot, representing a 27.16% reduction in irrigation water usage. The AI model demonstrated markedly superior soil moisture stability, with a standard deviation of 1.35% compared to 10.46% in the control plot. Mean absolute percentage error in volumetric delivery accuracy was 2.69% for the AI plot and 1.54% for the fixed-schedule plot, confirming reliable closed-loop control under both regimes. These findings affirm the practical viability of deploying low-cost, machine learning-driven irrigation infrastructure in resource-constrained, semi-arid agricultural environments, and offer a replicable framework for advancing precision agriculture across comparable regions in sub-Saharan Africa.","author":[{"family":"Publication","given":"Cedtech"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20611846","URL":"https://doi.org/10.5281/zenodo.20611846","source":"datacite"},{"id":"doi:10.5281/zenodo.21604563","type":"article-journal","title":"Multicloud-Powered Agriculture: Enhancing Precision Farming Through IoT and Data Analytics","abstract":"Multi-cloud architectures are revolutionizing modern agriculture through enhanced precision farming capabilities and optimized resource utilization. These systems integrate Internet of Things (IoT) devices, advanced analytics, and machine learning technologies to transform traditional farming practices. The architecture encompasses comprehensive data collection from soil sensors, weather stations, drone imagery, and agricultural machinery, processed through distributed computing platforms. Deep learning models enable accurate crop yield predictions, early disease detection, and resource optimization. Data confidentiality and operational efficiency are maintained through the use of advanced security frameworks and regulatory compliance methods. Through automated decision-making and real-time monitoring, this technology integration shows notable gains in crop yields, resource conservation, and overall farming productivity.","author":[{"family":"Sinha","given":"Abhishek"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21604563","URL":"https://doi.org/10.5281/zenodo.21604563","source":"datacite"},{"id":"doi:10.5281/zenodo.21604564","type":"article-journal","title":"Multicloud-Powered Agriculture: Enhancing Precision Farming Through IoT and Data Analytics","abstract":"Multi-cloud architectures are revolutionizing modern agriculture through enhanced precision farming capabilities and optimized resource utilization. These systems integrate Internet of Things (IoT) devices, advanced analytics, and machine learning technologies to transform traditional farming practices. The architecture encompasses comprehensive data collection from soil sensors, weather stations, drone imagery, and agricultural machinery, processed through distributed computing platforms. Deep learning models enable accurate crop yield predictions, early disease detection, and resource optimization. Data confidentiality and operational efficiency are maintained through the use of advanced security frameworks and regulatory compliance methods. Through automated decision-making and real-time monitoring, this technology integration shows notable gains in crop yields, resource conservation, and overall farming productivity.","author":[{"family":"Sinha","given":"Abhishek"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21604564","URL":"https://doi.org/10.5281/zenodo.21604564","source":"datacite"},{"id":"doi:10.5281/zenodo.21604310","type":"article-journal","title":"Artificial Intelligence in Precision Agriculture: Advanced Systems for Crop Management and Farm Optimization","abstract":"Artificial Intelligence (AI) has emerged as a transformative force in modern agriculture, revolutionizing traditional farming practices through the integration of advanced technologies and data-driven decision-making systems. This comprehensive article explores the implementation of AI in precision agriculture, focusing on crop management and farm optimization strategies. The article examines various aspects of AI application in agriculture, including precision farming technologies, crop monitoring systems, data analytics, and decision support frameworks. It explores the economic and environmental impacts of these technologies while addressing the challenges and future prospects of AI adoption in agricultural practices. The article highlights how AI-driven solutions are enhancing agricultural productivity through improved resource management, automated monitoring systems, and predictive analytics. The integration of machine learning, computer vision, and Internet of Things (IoT) devices has created sophisticated farming management systems that optimize crop yields while promoting environmental sustainability. This transformation represents a significant advancement in agricultural practices, particularly relevant for addressing global food security challenges and promoting sustainable farming methods in both developed and developing regions.","author":[{"family":"Jain","given":"Rajnish"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21604310","URL":"https://doi.org/10.5281/zenodo.21604310","source":"datacite"},{"id":"doi:10.5281/zenodo.21604311","type":"article-journal","title":"Artificial Intelligence in Precision Agriculture: Advanced Systems for Crop Management and Farm Optimization","abstract":"Artificial Intelligence (AI) has emerged as a transformative force in modern agriculture, revolutionizing traditional farming practices through the integration of advanced technologies and data-driven decision-making systems. This comprehensive article explores the implementation of AI in precision agriculture, focusing on crop management and farm optimization strategies. The article examines various aspects of AI application in agriculture, including precision farming technologies, crop monitoring systems, data analytics, and decision support frameworks. It explores the economic and environmental impacts of these technologies while addressing the challenges and future prospects of AI adoption in agricultural practices. The article highlights how AI-driven solutions are enhancing agricultural productivity through improved resource management, automated monitoring systems, and predictive analytics. The integration of machine learning, computer vision, and Internet of Things (IoT) devices has created sophisticated farming management systems that optimize crop yields while promoting environmental sustainability. This transformation represents a significant advancement in agricultural practices, particularly relevant for addressing global food security challenges and promoting sustainable farming methods in both developed and developing regions.","author":[{"family":"Jain","given":"Rajnish"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21604311","URL":"https://doi.org/10.5281/zenodo.21604311","source":"datacite"},{"id":"doi:10.5281/zenodo.21603225","type":"article-journal","title":"A Comprehensive Survey on AI Based Pest Detection in Smart Agriculture","abstract":"One of the biggest risks to agricultural production and food security worldwide still is insect and plant diseases. Broad-spectrum chemical insecticides, which are frequently reactive, detrimental to the environment, and economically ineffective, are the mainstay of conventional pest management techniques. A paradigm change toward proactive, accurate, and sustainable pest management has been made possible by recent developments in artificial intelligence (AI), particularly in deep learning, computer vision, and the Internet of Things (IoT). This report offers a thorough and methodical analysis of methods based on Artificial Intelligence for smart agriculture pest control, monitoring, and detection. Convolutional Neural Networks (CNNs), Vision Transformers, hyperspectral and multispectral imaging, Internet of Things-based smart traps, Unmanned Aerial Vehicles (UAVs), autonomous ground robots, and mobile-based diagnostic systems are all critically examined in this paper. Using precision, accuracy, scalability, real-time capability, and deployment feasibility as critical evaluation metrics, a thorough comparison of cutting-edge methods is provided. Data scarcity, class imbalance, model generalization, computing complexity, rural connectivity constraints, and real-world deployment obstacles are among the major technical and practical issues that are examined. Future possibilities for study are suggested, with a focus on digital twins, explainable AI (XAI), edge AI, multimodal data fusion, the creation of large-scale open agricultural datasets, and the creation of synthetic data using Generative Adversarial Networks (GANs). According to the survey's findings, artificial intelligence plays a crucial role in enabling smart agriculture that is resilient, effective, and environmentally friendly.","author":[{"family":"Sadhana","given":"S"},{"family":"Ramkumar","given":"R"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21603225","URL":"https://doi.org/10.5281/zenodo.21603225","source":"datacite"},{"id":"doi:10.5281/zenodo.21603226","type":"article-journal","title":"A Comprehensive Survey on AI Based Pest Detection in Smart Agriculture","abstract":"One of the biggest risks to agricultural production and food security worldwide still is insect and plant diseases. Broad-spectrum chemical insecticides, which are frequently reactive, detrimental to the environment, and economically ineffective, are the mainstay of conventional pest management techniques. A paradigm change toward proactive, accurate, and sustainable pest management has been made possible by recent developments in artificial intelligence (AI), particularly in deep learning, computer vision, and the Internet of Things (IoT). This report offers a thorough and methodical analysis of methods based on Artificial Intelligence for smart agriculture pest control, monitoring, and detection. Convolutional Neural Networks (CNNs), Vision Transformers, hyperspectral and multispectral imaging, Internet of Things-based smart traps, Unmanned Aerial Vehicles (UAVs), autonomous ground robots, and mobile-based diagnostic systems are all critically examined in this paper. Using precision, accuracy, scalability, real-time capability, and deployment feasibility as critical evaluation metrics, a thorough comparison of cutting-edge methods is provided. Data scarcity, class imbalance, model generalization, computing complexity, rural connectivity constraints, and real-world deployment obstacles are among the major technical and practical issues that are examined. Future possibilities for study are suggested, with a focus on digital twins, explainable AI (XAI), edge AI, multimodal data fusion, the creation of large-scale open agricultural datasets, and the creation of synthetic data using Generative Adversarial Networks (GANs). According to the survey's findings, artificial intelligence plays a crucial role in enabling smart agriculture that is resilient, effective, and environmentally friendly.","author":[{"family":"Sadhana","given":"S"},{"family":"Ramkumar","given":"R"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21603226","URL":"https://doi.org/10.5281/zenodo.21603226","source":"datacite"},{"id":"doi:10.5281/zenodo.21608223","type":"article-journal","title":"Tree Leaves Based Disease Prediction and Fertilizer Recommendation Using Deep Learning Algorithm","abstract":"The health of trees is a key component of ecological stability and diversity in ecosystems. Early detection of diseases that affect tree leaves can help with timely intervention and mitigation measures. The aim of this study is to determine whether or not tree leaves are healthy by evaluating high-resolution photos of the leaves. It offers an exclusive method for predicting tree diseases using deep learning—more especially, the VGG16 convolutional neural network architecture. The procedure entails gathering a substantial collection of images of tree leaves from various species and disease types. Improved robustness and generalisation of the model are achieved by applying data preparation techniques such as picture resizing, normalisation, and augmentation. Tree disease prediction is accomplished by customising the top layers of the pre-trained VGG16 model, which is used for feature extraction. To improve the performance of the proposed model, extensive training and validation processes are applied. The model's ability to classify illnesses is assessed using metrics such as accuracy, precision, recall, and F1 score. Developing a reliable and efficient tool to help environmentalists, foresters, and arborists quickly identify and address tree-related issues is the project's main goal. The study's findings provide an automated and scalable approach to early tree disease detection, advancing precision agriculture and environmental monitoring. The study supports sustainable practices for the preservation of global ecosystems by investigating potential real-world applications. Furthermore, extend the framework to provide information on fertilisers based on predicted disease.","author":[{"family":"Revathi","given":"MP"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21608223","URL":"https://doi.org/10.5281/zenodo.21608223","source":"datacite"},{"id":"doi:10.5281/zenodo.21608224","type":"article-journal","title":"Tree Leaves Based Disease Prediction and Fertilizer Recommendation Using Deep Learning Algorithm","abstract":"The health of trees is a key component of ecological stability and diversity in ecosystems. Early detection of diseases that affect tree leaves can help with timely intervention and mitigation measures. The aim of this study is to determine whether or not tree leaves are healthy by evaluating high-resolution photos of the leaves. It offers an exclusive method for predicting tree diseases using deep learning—more especially, the VGG16 convolutional neural network architecture. The procedure entails gathering a substantial collection of images of tree leaves from various species and disease types. Improved robustness and generalisation of the model are achieved by applying data preparation techniques such as picture resizing, normalisation, and augmentation. Tree disease prediction is accomplished by customising the top layers of the pre-trained VGG16 model, which is used for feature extraction. To improve the performance of the proposed model, extensive training and validation processes are applied. The model's ability to classify illnesses is assessed using metrics such as accuracy, precision, recall, and F1 score. Developing a reliable and efficient tool to help environmentalists, foresters, and arborists quickly identify and address tree-related issues is the project's main goal. The study's findings provide an automated and scalable approach to early tree disease detection, advancing precision agriculture and environmental monitoring. The study supports sustainable practices for the preservation of global ecosystems by investigating potential real-world applications. Furthermore, extend the framework to provide information on fertilisers based on predicted disease.","author":[{"family":"Revathi","given":"MP"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21608224","URL":"https://doi.org/10.5281/zenodo.21608224","source":"datacite"},{"id":"doi:10.5281/zenodo.21607722","type":"article-journal","title":"Pest Detection on Plants Using Image Processing","abstract":"Plant pest and disease detection is crucial for ensuring agricultural productivity and food security. This paper presents a machine learning-based approach utilizing image processing techniques to identify pests and diseases in plants. The system employs Histogram of Oriented Gradients (HOG) for feature extraction and a Support Vector Machine (SVM) classifier for classification. The dataset is built from labelled images of pests and diseases in plants, and the trained model is used to predict new instances. Additionally, color-based segmentation in the HSV color space enhances detection by isolating affected regions. The method efficiently processes images, detects contours, and classifies the affected areas as either pest-infected or diseased. Experimental results demonstrate the model's effectiveness in distinguishing between pests and diseases with high accuracy. The proposed system provides an automated and scalable solution for early detection, aiding in timely intervention and precision agriculture practices.","author":[{"family":"Bhavadharni","given":"K"},{"family":"Banuroopa","given":"K"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21607722","URL":"https://doi.org/10.5281/zenodo.21607722","source":"datacite"},{"id":"doi:10.5281/zenodo.21607723","type":"article-journal","title":"Pest Detection on Plants Using Image Processing","abstract":"Plant pest and disease detection is crucial for ensuring agricultural productivity and food security. This paper presents a machine learning-based approach utilizing image processing techniques to identify pests and diseases in plants. The system employs Histogram of Oriented Gradients (HOG) for feature extraction and a Support Vector Machine (SVM) classifier for classification. The dataset is built from labelled images of pests and diseases in plants, and the trained model is used to predict new instances. Additionally, color-based segmentation in the HSV color space enhances detection by isolating affected regions. The method efficiently processes images, detects contours, and classifies the affected areas as either pest-infected or diseased. Experimental results demonstrate the model's effectiveness in distinguishing between pests and diseases with high accuracy. The proposed system provides an automated and scalable solution for early detection, aiding in timely intervention and precision agriculture practices.","author":[{"family":"Bhavadharni","given":"K"},{"family":"Banuroopa","given":"K"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21607723","URL":"https://doi.org/10.5281/zenodo.21607723","source":"datacite"},{"id":"doi:10.5281/zenodo.21547360","type":"article-journal","title":"Machine Learning Review for Early Plant Leaf Disease Detection","abstract":"Early detection of plant leaf diseases is crucial for ensuring crop health and yield in precision agriculture. Machine learning techniques, particularly convolutional neural networks (CNNs) and transfer learning, have significantly outperformed traditional feature-based methods in accuracy and robustness. Public datasets such as Plant Village, coupled with preprocessing techniques like augmentation, have enabled the development of scalable detection frameworks. Recent studies highlight the effectiveness of lightweight architectures (e.g., MobileNet, FourCropNet) and IncMB-enhanced Inception models, achieving classification accuracies above 99% on benchmark datasets. Furthermore, hybrid models that combine CNNs with classical classifiers such as SVM, along with Vision Transformer (ViT)-based approaches, have improved early symptom recognition under diverse field conditions. Real-time implementations using YOLO variants and attention-augmented MobileNet backbones demonstrate the feasibility of deploying disease detection models on mobile and edge devices. Despite these advances, challenges persist, including dataset imbalance, environmental variability, and limited generalization across crop species. Future directions include model compression, multimodal integration (hyperspectral, thermal imaging), and federated learning to enhance adaptability and large-scale deployment. Overall, machine-learning-driven image analysis represents a promising pathway for early disease detection, supporting sustainable agriculture and global food security.","author":[{"family":"Mangal","given":"Patil"},{"family":"Yadav","given":"Jeetendra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21547360","URL":"https://doi.org/10.5281/zenodo.21547360","source":"datacite"},{"id":"doi:10.5281/zenodo.21547361","type":"article-journal","title":"Machine Learning Review for Early Plant Leaf Disease Detection","abstract":"Early detection of plant leaf diseases is crucial for ensuring crop health and yield in precision agriculture. Machine learning techniques, particularly convolutional neural networks (CNNs) and transfer learning, have significantly outperformed traditional feature-based methods in accuracy and robustness. Public datasets such as Plant Village, coupled with preprocessing techniques like augmentation, have enabled the development of scalable detection frameworks. Recent studies highlight the effectiveness of lightweight architectures (e.g., MobileNet, FourCropNet) and IncMB-enhanced Inception models, achieving classification accuracies above 99% on benchmark datasets. Furthermore, hybrid models that combine CNNs with classical classifiers such as SVM, along with Vision Transformer (ViT)-based approaches, have improved early symptom recognition under diverse field conditions. Real-time implementations using YOLO variants and attention-augmented MobileNet backbones demonstrate the feasibility of deploying disease detection models on mobile and edge devices. Despite these advances, challenges persist, including dataset imbalance, environmental variability, and limited generalization across crop species. Future directions include model compression, multimodal integration (hyperspectral, thermal imaging), and federated learning to enhance adaptability and large-scale deployment. Overall, machine-learning-driven image analysis represents a promising pathway for early disease detection, supporting sustainable agriculture and global food security.","author":[{"family":"Mangal","given":"Patil"},{"family":"Yadav","given":"Jeetendra"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.21547361","URL":"https://doi.org/10.5281/zenodo.21547361","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33233721.v1","type":"article-journal","title":"Deep Vision Architectures for Crop Disease Classification: A Comparative Study Across Agricultural Dataset Environments — Replication Package","abstract":"Automated crop disease classification using deep computer vision is critical for precision agriculture, yet existing models frequently suffer from a ``lab-to-field'' generalization gap when deployed in real-world farm environments. Furthermore, as vision architectures scale in complexity, their operational energy footprint becomes a primary deployment constraint for resource-limited edge devices and cost-sensitive cloud infrastructure. This paper presents a comprehensive, hardware-aware benchmarking study evaluating nine modern architectures---spanning Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and hybrid attention-convolution models---across both controlled laboratory imagery (PlantVillage) and in-the-wild field data (Paddy Doctor). We conduct rigorous empirical energy and carbon auditing across server-grade GPU and edge-proxy CPU platforms under statistically validated conditions. Our findings reveal that theoretical metrics like parameter counts and GFLOPs correlate poorly with measured energy consumption. Through a Pareto-frontier analysis, we characterize the trade-offs between predictive accuracy, domain-shift robustness, and energy efficiency, providing actionable guidance for sustainable model selection in precision agriculture.","author":[{"family":"Jedidi","given":"Abderrahmen"},{"family":"Garrab","given":"Samar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33233721.v1","URL":"https://doi.org/10.6084/m9.figshare.33233721.v1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33233721","type":"article-journal","title":"Deep Vision Architectures for Crop Disease Classification: A Comparative Study Across Agricultural Dataset Environments — Replication Package","abstract":"Automated crop disease classification using deep computer vision is critical for precision agriculture, yet existing models frequently suffer from a ``lab-to-field'' generalization gap when deployed in real-world farm environments. Furthermore, as vision architectures scale in complexity, their operational energy footprint becomes a primary deployment constraint for resource-limited edge devices and cost-sensitive cloud infrastructure. This paper presents a comprehensive, hardware-aware benchmarking study evaluating nine modern architectures---spanning Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and hybrid attention-convolution models---across both controlled laboratory imagery (PlantVillage) and in-the-wild field data (Paddy Doctor). We conduct rigorous empirical energy and carbon auditing across server-grade GPU and edge-proxy CPU platforms under statistically validated conditions. Our findings reveal that theoretical metrics like parameter counts and GFLOPs correlate poorly with measured energy consumption. Through a Pareto-frontier analysis, we characterize the trade-offs between predictive accuracy, domain-shift robustness, and energy efficiency, providing actionable guidance for sustainable model selection in precision agriculture.","author":[{"family":"Jedidi","given":"Abderrahmen"},{"family":"Garrab","given":"Samar"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33233721","URL":"https://doi.org/10.6084/m9.figshare.33233721","source":"datacite"},{"id":"doi:10.5281/zenodo.20986503","type":"article-journal","title":"DRONES IN SEED SOWING: A NEW AGE REVOLUTION IN  AGRICULTURE","abstract":"Abstract: Seed sowing is a crucial operation in agricultural production, fundamentally determining crop establishment, uniformity and resource efficiency. In the context of global challenges such as labour shortages, environmental degradation, and the need for climate-resilient farming systems, innovative sowing technologies have become indispensable. Drone-based seed sowing as a disruptive advancement in precision agriculture that integrates automation, data analytics, and sustainable practices. Recent technological innovations are explored, including microsite targeting using artificial intelligence, biodegradable seed pods, autonomous multi-drone swarms, and real-time field mapping. Comparative analyses between traditional and drone enabled sowing demonstrate significant gains in efficiency, precision, and environmental sustainability. Drone-based seed sowing as a cornerstone of the emerging digital and climate smart agricultural paradigm, representing a convergence of technological ingenuity and ecological responsibility that can enhance productivity, equity, and resilience in global food systems. Keywords: Artificial intelligence, Climate-resilient farming, Drone seed sowing, Precision Agriculture and Sustainability","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20986503","URL":"https://doi.org/10.5281/zenodo.20986503","source":"datacite"},{"id":"doi:10.5281/zenodo.20986504","type":"article-journal","title":"DRONES IN SEED SOWING: A NEW AGE REVOLUTION IN  AGRICULTURE","abstract":"Abstract: Seed sowing is a crucial operation in agricultural production, fundamentally determining crop establishment, uniformity and resource efficiency. In the context of global challenges such as labour shortages, environmental degradation, and the need for climate-resilient farming systems, innovative sowing technologies have become indispensable. Drone-based seed sowing as a disruptive advancement in precision agriculture that integrates automation, data analytics, and sustainable practices. Recent technological innovations are explored, including microsite targeting using artificial intelligence, biodegradable seed pods, autonomous multi-drone swarms, and real-time field mapping. Comparative analyses between traditional and drone enabled sowing demonstrate significant gains in efficiency, precision, and environmental sustainability. Drone-based seed sowing as a cornerstone of the emerging digital and climate smart agricultural paradigm, representing a convergence of technological ingenuity and ecological responsibility that can enhance productivity, equity, and resilience in global food systems. Keywords: Artificial intelligence, Climate-resilient farming, Drone seed sowing, Precision Agriculture and Sustainability","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20986504","URL":"https://doi.org/10.5281/zenodo.20986504","source":"datacite"},{"id":"doi:10.5281/zenodo.21882487","type":"article-journal","title":"Comparative Performance Analysis of YOLOv10 and YOLOv11 for Automated Mulberry Leaf Nutrient Deficiency Detection","abstract":"Abstract- Early identification of nutrient deficiencies in mulberry leaves is essential for maintaining leaf quality,improving silkworm productivity, and supporting sustainable sericulture practices. Conventional assessment methodsrely heavily on manual observation, which can be time-consuming, subjective, and prone to inconsistencies. Recentadvances in deep learning-based object detection have enabled automated and accurate analysis of plant health conditionsfrom digital images. This study presents a comparative performance analysis of YOLOv10 and YOLOv11 for automatedmulberry leaf nutrient deficiency detection. A dataset comprising approximately 6,000 annotated images representing sixclasses, namely Healthy, Nitrogen Deficiency, Potassium Deficiency, Phosphorus Deficiency, Iron Deficiency, and SulphurDeficiency, was utilized for model training and evaluation. The dataset was divided into training, validation, and testingsubsets using a 70:15:15 ratio. Standard preprocessing and data augmentation techniques were applied to improve modelgeneralization and robustness.","author":[{"family":"S Raghavendrachar","given":"Rekha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21882487","URL":"https://doi.org/10.5281/zenodo.21882487","source":"datacite"},{"id":"doi:10.5281/zenodo.21882486","type":"article-journal","title":"Comparative Performance Analysis of YOLOv10 and YOLOv11 for Automated Mulberry Leaf Nutrient Deficiency Detection","abstract":"Abstract- Early identification of nutrient deficiencies in mulberry leaves is essential for maintaining leaf quality,improving silkworm productivity, and supporting sustainable sericulture practices. Conventional assessment methodsrely heavily on manual observation, which can be time-consuming, subjective, and prone to inconsistencies. Recentadvances in deep learning-based object detection have enabled automated and accurate analysis of plant health conditionsfrom digital images. This study presents a comparative performance analysis of YOLOv10 and YOLOv11 for automatedmulberry leaf nutrient deficiency detection. A dataset comprising approximately 6,000 annotated images representing sixclasses, namely Healthy, Nitrogen Deficiency, Potassium Deficiency, Phosphorus Deficiency, Iron Deficiency, and SulphurDeficiency, was utilized for model training and evaluation. The dataset was divided into training, validation, and testingsubsets using a 70:15:15 ratio. Standard preprocessing and data augmentation techniques were applied to improve modelgeneralization and robustness.","author":[{"family":"S Raghavendrachar","given":"Rekha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21882486","URL":"https://doi.org/10.5281/zenodo.21882486","source":"datacite"},{"id":"doi:10.5281/zenodo.21161824","type":"article-journal","title":"Food Safety and Security: Emerging Trends, Challenges and Opportunities","abstract":"Food safety and food security are critical components of sustainable development, public health, and economic stability in an increasingly interconnected world. Ensuring access to sufficient, safe, nutritious, and affordable food remains a major global challenge amid population growth, climate change, resource constraints, and evolving consumption patterns. This chapter examines emerging trends, challenges, and opportunities in the field of food safety and security, highlighting the role of technological innovation, sustainable agricultural practices, digital monitoring systems, and policy interventions in strengthening food systems. It explores contemporary issues such as food contamination, supply chain vulnerabilities, nutritional deficiencies, food waste, and the impacts of environmental degradation on food production. The chapter further discusses opportunities arising from precision agriculture, artificial intelligence, biotechnology, climate-smart farming, and sustainable food management practices. By analysing current developments and future prospects, the chapter emphasizes the importance of integrated and collaborative approaches to ensure resilient food systems, enhance public health outcomes, and achieve long-term food sustainability for present and future generations.","author":[{"family":"Dorothy","given":"MP"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21161824","URL":"https://doi.org/10.5281/zenodo.21161824","source":"datacite"},{"id":"doi:10.5281/zenodo.21161825","type":"article-journal","title":"Food Safety and Security: Emerging Trends, Challenges and Opportunities","abstract":"Food safety and food security are critical components of sustainable development, public health, and economic stability in an increasingly interconnected world. Ensuring access to sufficient, safe, nutritious, and affordable food remains a major global challenge amid population growth, climate change, resource constraints, and evolving consumption patterns. This chapter examines emerging trends, challenges, and opportunities in the field of food safety and security, highlighting the role of technological innovation, sustainable agricultural practices, digital monitoring systems, and policy interventions in strengthening food systems. It explores contemporary issues such as food contamination, supply chain vulnerabilities, nutritional deficiencies, food waste, and the impacts of environmental degradation on food production. The chapter further discusses opportunities arising from precision agriculture, artificial intelligence, biotechnology, climate-smart farming, and sustainable food management practices. By analysing current developments and future prospects, the chapter emphasizes the importance of integrated and collaborative approaches to ensure resilient food systems, enhance public health outcomes, and achieve long-term food sustainability for present and future generations.","author":[{"family":"Dorothy","given":"MP"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21161825","URL":"https://doi.org/10.5281/zenodo.21161825","source":"datacite"},{"id":"doi:10.5281/zenodo.21103418","type":"article-journal","title":"Automated Irrigation and Nutrient Fertilization System for Sustainable Agriculture","abstract":"Abstract This study presents an automatic irrigation and fertilization system designed to provide a smart, real-time, and cost-effective solution for modern agriculture. The system integrates soil moisture sensors, an Arduino Uno microcontroller, a water pump, and fertilizer dispensing valves to maintain optimal soil conditions. Soil moisture is continuously monitored, and irrigation is activated only when required, reducing water wastage and ensuring proper hydration. A programmed fertilization module delivers precise nutrient quantities, minimizing human error and preventing over-fertilization associated with conventional manual practices. A functional prototype was developed and evaluated under controlled conditions. Experimental results showed nearly a 40% reduction in irrigation cycles compared to manual methods, demonstrating significant improvement in water-use efficiency. Fertilizer distribution was more uniform, leading to healthier root systems, improved soil structure, and enhanced crop quality. Data analysis revealed a strong correlation between automated water–nutrient management and improved plant growth. The study further evaluates system affordability, scalability, and suitability for small and medium-scale farmers, particularly in rural and resource-limited regions. The modular and low-cost design allows customization based on crop type, soil characteristics, farm size, and climatic conditions. Future enhancements include integration of IoT, GSM modules, and mobile applications for remote monitoring and predictive analysis.","author":[{"family":"Pawar","given":"Kumudini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21103418","URL":"https://doi.org/10.5281/zenodo.21103418","source":"datacite"},{"id":"doi:10.5281/zenodo.21103419","type":"article-journal","title":"Automated Irrigation and Nutrient Fertilization System for Sustainable Agriculture","abstract":"Abstract This study presents an automatic irrigation and fertilization system designed to provide a smart, real-time, and cost-effective solution for modern agriculture. The system integrates soil moisture sensors, an Arduino Uno microcontroller, a water pump, and fertilizer dispensing valves to maintain optimal soil conditions. Soil moisture is continuously monitored, and irrigation is activated only when required, reducing water wastage and ensuring proper hydration. A programmed fertilization module delivers precise nutrient quantities, minimizing human error and preventing over-fertilization associated with conventional manual practices. A functional prototype was developed and evaluated under controlled conditions. Experimental results showed nearly a 40% reduction in irrigation cycles compared to manual methods, demonstrating significant improvement in water-use efficiency. Fertilizer distribution was more uniform, leading to healthier root systems, improved soil structure, and enhanced crop quality. Data analysis revealed a strong correlation between automated water–nutrient management and improved plant growth. The study further evaluates system affordability, scalability, and suitability for small and medium-scale farmers, particularly in rural and resource-limited regions. The modular and low-cost design allows customization based on crop type, soil characteristics, farm size, and climatic conditions. Future enhancements include integration of IoT, GSM modules, and mobile applications for remote monitoring and predictive analysis.","author":[{"family":"Pawar","given":"Kumudini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21103419","URL":"https://doi.org/10.5281/zenodo.21103419","source":"datacite"},{"id":"doi:10.5281/zenodo.20827656","type":"article-journal","title":"Next- Generation Farming Machineries","abstract":"Next-generation farming machineries represent a paradigm shift in agricultural practices, Artificial Intelligence (AI), Internet of Things (IoT), robotics, drones and autonomous vehicles to optimize resource use and boost yields in India. These technologies enable precision agriculture, where GPS-guided tractors, variable-rate applicators and AI-powered sensors monitor soil health, moisture levels and crop conditions in real-time, reducing fertilizer and water wastage by up to 30-50% while minimizing environmental impact. In the Indian context, innovations like electric autonomous tractors, drone-based pesticide sprayers and robotic harvesters address smallholder farmer needs by cutting labour costs and enabling timely operations across fragmented landholdings. Robotic systems automate planting, weeding, and harvesting - tasks exemplified by see-and-spray weeders and UAVs for aerial surveillance - enhancing efficiency in labour-scarce regions. Studies highlight increased resilience to climatic stresses, with yield improvements of 15-25% reported in precision farming trials. Despite promise, the adoption of smart machinery in rural India is impeded by formidable barriers, including elevated costs, deficiencies in digital literacy, and infrastructural shortcomings. This transition, however, substantially enhances productivity, fosters environmentally sustainable agricultural practices, and aligns seamlessly with national objectives aimed at doubling farmers' incomes.","author":[{"family":"Anitta","given":"DCKS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20827656","URL":"https://doi.org/10.5281/zenodo.20827656","source":"datacite"},{"id":"doi:10.5281/zenodo.20827657","type":"article-journal","title":"Next- Generation Farming Machineries","abstract":"Next-generation farming machineries represent a paradigm shift in agricultural practices, Artificial Intelligence (AI), Internet of Things (IoT), robotics, drones and autonomous vehicles to optimize resource use and boost yields in India. These technologies enable precision agriculture, where GPS-guided tractors, variable-rate applicators and AI-powered sensors monitor soil health, moisture levels and crop conditions in real-time, reducing fertilizer and water wastage by up to 30-50% while minimizing environmental impact. In the Indian context, innovations like electric autonomous tractors, drone-based pesticide sprayers and robotic harvesters address smallholder farmer needs by cutting labour costs and enabling timely operations across fragmented landholdings. Robotic systems automate planting, weeding, and harvesting - tasks exemplified by see-and-spray weeders and UAVs for aerial surveillance - enhancing efficiency in labour-scarce regions. Studies highlight increased resilience to climatic stresses, with yield improvements of 15-25% reported in precision farming trials. Despite promise, the adoption of smart machinery in rural India is impeded by formidable barriers, including elevated costs, deficiencies in digital literacy, and infrastructural shortcomings. This transition, however, substantially enhances productivity, fosters environmentally sustainable agricultural practices, and aligns seamlessly with national objectives aimed at doubling farmers' incomes.","author":[{"family":"Anitta","given":"DCKS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.20827657","URL":"https://doi.org/10.5281/zenodo.20827657","source":"datacite"},{"id":"doi:10.17632/xwnvpkpkxk.1","type":"article-journal","title":"A Multi-Stage Maize Leaf Image Dataset for Classification of Spodoptera exigua damage","abstract":"Maize is a crop of paramount importance for global food and feed production, yet its growth is frequently threatened by insect pests. Among these, the beet armyworm (Spodoptera exigua) is a major pest that inflicts severe damage during the seedling stage. Accurate recognition and grading of pest leaf damage are essential for effective precision control. To support the development of intelligent agriculture, we established a field-based image dataset targeting Spodoptera exigua damage on maize leaves. Images were collected under natural light and complex field backgrounds across three critical seedling stages (V4, V6, and V8).","author":[{"family":"Zhong","given":"Chengcheng"},{"family":"Liu","given":"Yichen"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17632/xwnvpkpkxk.1","URL":"https://doi.org/10.17632/xwnvpkpkxk.1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33185016.v1","type":"article-journal","title":"<b>Apple Leaf Disease Dataset PlantCity 2025</b>","abstract":"Cite Paper:Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130Paper Link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data was collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the devel- opment of deep learning models for automated disease clas- sification and captures a range of environmental factors, in- cluding high temperatures that can exacerbate disease symp- toms. It utilizes smartphone-based computer vision to facili- tate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33185016.v1","URL":"https://doi.org/10.6084/m9.figshare.33185016.v1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33185016","type":"article-journal","title":"<b>Apple Leaf Disease Dataset PlantCity 2025</b>","abstract":"Cite Paper:Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130Paper Link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data was collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the devel- opment of deep learning models for automated disease clas- sification and captures a range of environmental factors, in- cluding high temperatures that can exacerbate disease symp- toms. It utilizes smartphone-based computer vision to facili- tate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33185016","URL":"https://doi.org/10.6084/m9.figshare.33185016","source":"datacite"},{"id":"doi:10.6084/m9.figshare.33185016.v2","type":"article-journal","title":"<b>Apple Leaf Disease Dataset PlantCity 2025</b>","abstract":"Cite Paper:Khan, M. S., Nisa, K., Ahmad, I., Zubair, M., &amp; Alshammari, K. (2025). PlantCity: A Comprehensive Image Based on Multi Crop Leaves in Pakistan. Data in Brief, 112130. https://doi.org/10.1016/j.dib.2025.112130Paper Link: https://www.sciencedirect.com/science/article/pii/S2352340925008510 The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data was collected in real-field conditions in Charsadda (34.15 °N, 71.74 °E, typical temperature 40–44 °C) and Chitral (35.85 °N, 71.79 °E, typical temperature 25–30 °C) from April to July 2023–2024. The dataset enables the devel- opment of deep learning models for automated disease clas- sification and captures a range of environmental factors, in- cluding high temperatures that can exacerbate disease symp- toms. It utilizes smartphone-based computer vision to facili- tate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.","author":[{"family":"Khan","given":"Muhammad"},{"family":"Nisa","given":"Kainat"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.33185016.v2","URL":"https://doi.org/10.6084/m9.figshare.33185016.v2","source":"datacite"},{"id":"doi:10.5281/zenodo.21852876","type":"article-journal","title":"Factors Regulating Symbiotic Nitrogen Fixation Efficiency in Legume Crops: Mechanisms, Environmental Constraints, and Future Perspectives","abstract":"Abstract : Symbiotic nitrogen fixation (SNF) is a fundamental biological process that enhances legume productivity while reducing dependence on synthetic nitrogen fertilizers. However, its efficiency varies considerably across production systems because it is regulated by complex interactions among plant genetics, rhizobial compatibility, physiological processes, environmental conditions, and agronomic management. This review synthesizes current knowledge on the mechanisms regulating SNF and critically examines the biological, environmental, and management factors that determine its effectiveness. The review integrates evidence from the literature on the molecular basis of legume–rhizobium symbiosis, physiological regulation of nitrogen fixation, the influence of soil properties, nutrient availability, climatic stresses, and agronomic practices, and evaluates emerging technologies and future research directions. The synthesis demonstrates that SNF performance is inherently context-dependent and cannot be optimized through a single intervention. Instead, successful nitrogen fixation requires coordinated management of host genotype, rhizobial inoculants, soil fertility, water availability, and crop management while accounting for local environmental conditions. The review also identifies important knowledge gaps, including limited long-term field validation, insufficient integration of multidisciplinary approaches, and challenges in translating emerging genomic, microbial, and precision agriculture technologies into practical farming systems. Overall, this review emphasizes that integrated, site-specific management combined with continued advances in biofertilizer development and multidisciplinary research is essential for maximizing SNF efficiency, reducing reliance on synthetic nitrogen fertilizers, and supporting sustainable, climate-resilient agricultural production.","author":[{"family":"Hayatullah","given":"Wesal"},{"family":"Mohammad Daud","given":"Haidari"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21852876","URL":"https://doi.org/10.5281/zenodo.21852876","source":"datacite"},{"id":"doi:10.5281/zenodo.21852877","type":"article-journal","title":"Factors Regulating Symbiotic Nitrogen Fixation Efficiency in Legume Crops: Mechanisms, Environmental Constraints, and Future Perspectives","abstract":"Abstract : Symbiotic nitrogen fixation (SNF) is a fundamental biological process that enhances legume productivity while reducing dependence on synthetic nitrogen fertilizers. However, its efficiency varies considerably across production systems because it is regulated by complex interactions among plant genetics, rhizobial compatibility, physiological processes, environmental conditions, and agronomic management. This review synthesizes current knowledge on the mechanisms regulating SNF and critically examines the biological, environmental, and management factors that determine its effectiveness. The review integrates evidence from the literature on the molecular basis of legume–rhizobium symbiosis, physiological regulation of nitrogen fixation, the influence of soil properties, nutrient availability, climatic stresses, and agronomic practices, and evaluates emerging technologies and future research directions. The synthesis demonstrates that SNF performance is inherently context-dependent and cannot be optimized through a single intervention. Instead, successful nitrogen fixation requires coordinated management of host genotype, rhizobial inoculants, soil fertility, water availability, and crop management while accounting for local environmental conditions. The review also identifies important knowledge gaps, including limited long-term field validation, insufficient integration of multidisciplinary approaches, and challenges in translating emerging genomic, microbial, and precision agriculture technologies into practical farming systems. Overall, this review emphasizes that integrated, site-specific management combined with continued advances in biofertilizer development and multidisciplinary research is essential for maximizing SNF efficiency, reducing reliance on synthetic nitrogen fertilizers, and supporting sustainable, climate-resilient agricultural production.","author":[{"family":"Hayatullah","given":"Wesal"},{"family":"Mohammad Daud","given":"Haidari"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21852877","URL":"https://doi.org/10.5281/zenodo.21852877","source":"datacite"},{"id":"doi:10.17605/osf.io/acsw7","type":"article-journal","title":"Leveraging precision agriculture for improving soil quality and crop productivity","abstract":"This research project provides a comprehensive systematic review of the role of precision agriculture (PA) in enhancing soil quality, improving crop productivity, and promoting sustainable agricultural systems. As global agriculture faces increasing challenges from climate change, soil degradation, declining natural resources, and growing food demand, precision agriculture has emerged as a transformative approach that integrates advanced digital technologies with data-driven decision-making to optimize agricultural production while minimizing environmental impacts. The primary purpose of this study is to critically evaluate the contribution of precision agriculture technologies to sustainable soil and crop management by synthesizing scientific evidence published between 2015 and 2025. The review examines how emerging technologies—including artificial intelligence (AI), remote sensing, unmanned aerial vehicles (UAVs), geographic information systems (GIS), variable rate technology (VRT), the Internet of Things (IoT), soil sensors, and near-infrared (NIR) spectroscopy—have been applied to improve agricultural productivity, resource use efficiency, and environmental sustainability. The project also identifies current research trends, technological advancements, knowledge gaps, and barriers to the widespread adoption of precision agriculture, particularly in developing countries. The study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure methodological rigor, transparency, and reproducibility. Peer-reviewed articles were systematically retrieved from major scientific databases, including Scopus, Web of Science, ScienceDirect, SpringerLink, PubMed, and Google Scholar. Eligible studies focusing on precision agriculture applications in soil management and crop production were screened using predefined inclusion and exclusion criteria, critically assessed for quality, and synthesized through qualitative analysis. The findings reveal a remarkable increase in precision agriculture research over the past decade, with Artificial Intelligence (AI) and Climate-Resilient Agricultural Systems (CRAS) emerging as dominant research themes. The review demonstrates that technologies such as UAVs, remote sensing, GIS, IoT, VRT, soil sensors, and NIR spectroscopy have substantially improved precision nutrient management, crop health monitoring, soil quality assessment, irrigation management, and decision support systems. These innovations contribute to increased soil fertility, higher crop yields, improved input-use efficiency, reduced production costs, lower greenhouse gas emissions, and minimized environmental degradation. Despite these advances, the review highlights significant disparities in technology adoption between developed and developing countries. Financial limitations, inadequate digital infrastructure, insufficient technical expertise, weak institutional support, and limited policy frameworks remain major obstacles to the implementation of precision agriculture in many regions. Addressing these constraints is essential to ensure equitable access to modern agricultural technologies and maximize their benefits worldwide. The expected outcomes of this research include a comprehensive synthesis of current knowledge on precision agriculture technologies, identification of emerging research directions, and evidence-based recommendations for researchers, policymakers, agricultural practitioners, and development organizations. The project aims to support informed decision-making, guide future research priorities, and promote policies that facilitate the adoption of precision agriculture technologies for sustainable and climate-resilient agricultural development. Ultimately, this work contributes to advancing resilient food production systems that improve soil health, increase agricultural productivity, optimize resource utilization, and strengthen global food security.","author":[{"family":"Tolossa","given":"Tasisa"}],"issued":{"date-parts":[[2026]]},"DOI":"10.17605/osf.io/acsw7","URL":"https://doi.org/10.17605/osf.io/acsw7","source":"datacite"},{"id":"doi:10.48550/arxiv.2606.18519","type":"manuscript","title":"As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture","abstract":"Though robotic systems are now being commercialized and deployed in various industries, many of these systems are highly specialized and often require an advanced skill set to operate and ensure they perform as instructed. To mitigate this problem, we recently introduced a mission planner leveraging LLMs to synthesize mission plans in precision agriculture based on mission descriptions provided in natural language. While the system demonstrates impressive performance, it also suffers from the inherent ambiguities of natural language. In this paper, we extend our system to address this issue by introducing multiple feedback loops in the planning architecture that leverage linear temporal logic (LTL) to ensure the mission planning system meets the specifications formulated by the user while still using natural language. To mitigate potential bias, this is achieved by using two different commercial LLMs in charge of the specification and verification subtasks. Through extensive experiments, we highlight the strengths and limitations of integrating mission verification into a fully autonomous pipeline, particularly regarding an LLM's ability to generate valuable LTL formulas, and show how our proposed implementation addresses and solves these challenges.","author":[{"family":"Zuzuárregui","given":"Marcos"},{"family":"Carpin","given":"Stefano"}],"issued":{"date-parts":[[2026]]},"DOI":"10.48550/arxiv.2606.18519","URL":"https://doi.org/10.48550/arxiv.2606.18519","source":"datacite"},{"id":"doi:10.5281/zenodo.19681277","type":"article-journal","title":"Soil Global Challenges and Strategies for Solutions","abstract":"Soil degradation is a major global issue that reduces the soil’s ability to support life, threatening food security and ecosystem balance. It is caused by factors such as soil erosion, nutrient depletion, biodiversity loss, and unsustainable human activities, and is further intensified by climate change and extreme weather conditions. Desertification is a key outcome of this process, turning fertile land into dry and unproductive areas, especially in vulnerable regions. Soil pollution from chemicals, industrial waste, plastics, and heavy metals further damages soil quality and poses risks to living organisms and human health. To address these challenges, sustainable practices like organic farming, conservation tillage, afforestation, and climate-smart soil management are essential for restoring soil health and ensuring environmental sustainability.","author":[{"family":"Gawade","given":"Ramesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19681277","URL":"https://doi.org/10.5281/zenodo.19681277","source":"datacite"},{"id":"doi:10.5281/zenodo.19681276","type":"article-journal","title":"Soil Global Challenges and Strategies for Solutions","abstract":"Soil degradation is a major global issue that reduces the soil’s ability to support life, threatening food security and ecosystem balance. It is caused by factors such as soil erosion, nutrient depletion, biodiversity loss, and unsustainable human activities, and is further intensified by climate change and extreme weather conditions. Desertification is a key outcome of this process, turning fertile land into dry and unproductive areas, especially in vulnerable regions. Soil pollution from chemicals, industrial waste, plastics, and heavy metals further damages soil quality and poses risks to living organisms and human health. To address these challenges, sustainable practices like organic farming, conservation tillage, afforestation, and climate-smart soil management are essential for restoring soil health and ensuring environmental sustainability.","author":[{"family":"Gawade","given":"Ramesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19681276","URL":"https://doi.org/10.5281/zenodo.19681276","source":"datacite"},{"id":"doi:10.5281/zenodo.19680490","type":"article-journal","title":"Soil Moisture Conservation Techniques","abstract":"Soil moisture conservation plays a critical role in sustainable agriculture, water resource management, and climate resilience. Increasing global water scarcity, irregular rainfall patterns, and soil degradation have made moisture conservation practices essential for improving crop productivity and maintaining soil health. This chapter discusses various soil moisture conservation techniques, including traditional practices such as mulching and contour farming, as well as modern technologies like drip irrigation, soil moisture sensors, and precision agriculture. The chapter also highlights the environmental and economic benefits of moisture conservation strategies and presents recent advancements in smart irrigation systems and data-driven agricultural management.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19680490","URL":"https://doi.org/10.5281/zenodo.19680490","source":"datacite"},{"id":"doi:10.5281/zenodo.19680491","type":"article-journal","title":"Soil Moisture Conservation Techniques","abstract":"Soil moisture conservation plays a critical role in sustainable agriculture, water resource management, and climate resilience. Increasing global water scarcity, irregular rainfall patterns, and soil degradation have made moisture conservation practices essential for improving crop productivity and maintaining soil health. This chapter discusses various soil moisture conservation techniques, including traditional practices such as mulching and contour farming, as well as modern technologies like drip irrigation, soil moisture sensors, and precision agriculture. The chapter also highlights the environmental and economic benefits of moisture conservation strategies and presents recent advancements in smart irrigation systems and data-driven agricultural management.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19680491","URL":"https://doi.org/10.5281/zenodo.19680491","source":"datacite"},{"id":"doi:10.5281/zenodo.18194203","type":"article-journal","title":"Climate Resilient Agriculture and AI Tools: A Pathway to Sustainable Development of India","abstract":"Climate change poses a significant threat to Indian agriculture, which remains a vital sector for food security, rural livelihoods, and economic stability. With increasing frequency of extreme weather events, erratic monsoons, rising temperatures, and declining natural resources, the vulnerability of India's farming communities has intensified. Climate Resilient Agriculture (CRA) offers a sustainable solution by promoting practices that are adaptive to climate variability, mitigate greenhouse gas emissions, and enhance agricultural productivity. In this context, Artificial Intelligence (AI) offers innovative tools to build climate-resilient agricultural systems and ensure sustainable development. AI-based solutions such as predictive weather modeling, smart irrigation, crop health monitoring, and climate-adaptive advisory services enable farmers to make informed decisions and optimize resource use. These technologies help reduce vulnerability to extreme weather events, minimize crop losses, and promote sustainable farming practices. By integrating AI into government initiatives and agri-tech start-ups, India can enhance productivity, improve income security for farmers, and achieve long-term sustainability goals. However, issues like digital infrastructure gaps, affordability, and awareness among small and marginal farmers remain critical barriers. This paper explores the role of AI tools in fostering climate-resilient agriculture, emphasizing their potential to transform Indian agriculture into a sustainable, inclusive, and future-ready sector.","author":[{"family":"Aparna"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18194203","URL":"https://doi.org/10.5281/zenodo.18194203","source":"datacite"},{"id":"doi:10.5281/zenodo.18194204","type":"article-journal","title":"Climate Resilient Agriculture and AI Tools: A Pathway to Sustainable Development of India","abstract":"Climate change poses a significant threat to Indian agriculture, which remains a vital sector for food security, rural livelihoods, and economic stability. With increasing frequency of extreme weather events, erratic monsoons, rising temperatures, and declining natural resources, the vulnerability of India's farming communities has intensified. Climate Resilient Agriculture (CRA) offers a sustainable solution by promoting practices that are adaptive to climate variability, mitigate greenhouse gas emissions, and enhance agricultural productivity. In this context, Artificial Intelligence (AI) offers innovative tools to build climate-resilient agricultural systems and ensure sustainable development. AI-based solutions such as predictive weather modeling, smart irrigation, crop health monitoring, and climate-adaptive advisory services enable farmers to make informed decisions and optimize resource use. These technologies help reduce vulnerability to extreme weather events, minimize crop losses, and promote sustainable farming practices. By integrating AI into government initiatives and agri-tech start-ups, India can enhance productivity, improve income security for farmers, and achieve long-term sustainability goals. However, issues like digital infrastructure gaps, affordability, and awareness among small and marginal farmers remain critical barriers. This paper explores the role of AI tools in fostering climate-resilient agriculture, emphasizing their potential to transform Indian agriculture into a sustainable, inclusive, and future-ready sector.","author":[{"family":"Aparna"}],"issued":{"date-parts":[[2025]]},"DOI":"10.5281/zenodo.18194204","URL":"https://doi.org/10.5281/zenodo.18194204","source":"datacite"},{"id":"doi:10.5281/zenodo.19676625","type":"article-journal","title":"Future Perspectives in Agricultural and Plant Innovation","abstract":"Agriculture in the twenty-first century faces mounting challenges from climate change, population growth, land degradation, and resource scarcity, necessitating sustainable and resilient production systems. Advances in plant science, biotechnology, and digital technologies are transforming agricultural practices. Genome editing, molecular breeding, and speed breeding accelerate the development of climate-resilient crops with improved productivity and nutritional value. Precision agriculture, supported by sensors, artificial intelligence, and remote sensing, enhances resource-use efficiency and enables data-driven decision-making. Sustainable soil health is promoted through microbiome engineering, regenerative agriculture, and conservation practices. Controlled environment agriculture, including vertical farming and hydroponics, offers efficient food production in urban settings. Synthetic biology and plant-based biomanufacturing provide eco-friendly materials and pharmaceutical applications. Integration of genomics, big data, and nanotechnology further improves crop management and sustainability. Climate-smart agriculture, combined with ethical governance and socio-economic inclusivity, ensures equitable adoption of innovations. Together, these interdisciplinary approaches provide transformative pathways toward sustainable agriculture, environmental conservation, and global food security","author":[{"family":"Wagh","given":"Swati"},{"family":"Khilari","given":"Anjali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19676625","URL":"https://doi.org/10.5281/zenodo.19676625","source":"datacite"},{"id":"doi:10.5281/zenodo.19676626","type":"article-journal","title":"Future Perspectives in Agricultural and Plant Innovation","abstract":"Agriculture in the twenty-first century faces mounting challenges from climate change, population growth, land degradation, and resource scarcity, necessitating sustainable and resilient production systems. Advances in plant science, biotechnology, and digital technologies are transforming agricultural practices. Genome editing, molecular breeding, and speed breeding accelerate the development of climate-resilient crops with improved productivity and nutritional value. Precision agriculture, supported by sensors, artificial intelligence, and remote sensing, enhances resource-use efficiency and enables data-driven decision-making. Sustainable soil health is promoted through microbiome engineering, regenerative agriculture, and conservation practices. Controlled environment agriculture, including vertical farming and hydroponics, offers efficient food production in urban settings. Synthetic biology and plant-based biomanufacturing provide eco-friendly materials and pharmaceutical applications. Integration of genomics, big data, and nanotechnology further improves crop management and sustainability. Climate-smart agriculture, combined with ethical governance and socio-economic inclusivity, ensures equitable adoption of innovations. Together, these interdisciplinary approaches provide transformative pathways toward sustainable agriculture, environmental conservation, and global food security","author":[{"family":"Wagh","given":"Swati"},{"family":"Khilari","given":"Anjali"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19676626","URL":"https://doi.org/10.5281/zenodo.19676626","source":"datacite"},{"id":"doi:10.5281/zenodo.19666235","type":"article-journal","title":"Sustainable Agriculture in the Era of Climate Change: Resilient Farming Systems","abstract":"Climate alteration is a key challenge for global agriculture system, affecting food security, crop yield and farmer source of revenue through increasing temperatures, irregular rainfall and frequent extreme weather events. These changes increase abiotic stresses like salinity, drought, heat and flooding, while also intensifying biotic stresses caused by insect, pest, pathogens and diseases. Additionally, climate-induced biodiversity declines interrupt fundamental ecosystem processes such as pollination, nutrient recycling and biocontrol, further weakening agricultural resilience. Sustainable and climate-smart agricultural activities such as natural farming, sustainable agriculture and agroforestry play an important function in enhance soil health, protecting resources and supporting resilient farming systems. Advances in plant breeding and biotechnology are enabling the advance of climate resilient crop variability, while adaptation strategies like efficient water management, crop diversification and improved seed systems help farmers manage climatic risks. Emerging digital technologies, including artificial intelligence, remote sensing and mobile advisory services, are also enhancing farm decision-making. However, effective policy support, research investment and international cooperation are essential to ensure these innovations reach vulnerable farming communities. This chapter examines the effect of climate change on agriculture and highlights sustainable strategies, technological innovations and policy approaches needed to build resilient agricultural systems.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19666235","URL":"https://doi.org/10.5281/zenodo.19666235","source":"datacite"},{"id":"doi:10.5281/zenodo.19666236","type":"article-journal","title":"Sustainable Agriculture in the Era of Climate Change: Resilient Farming Systems","abstract":"Climate alteration is a key challenge for global agriculture system, affecting food security, crop yield and farmer source of revenue through increasing temperatures, irregular rainfall and frequent extreme weather events. These changes increase abiotic stresses like salinity, drought, heat and flooding, while also intensifying biotic stresses caused by insect, pest, pathogens and diseases. Additionally, climate-induced biodiversity declines interrupt fundamental ecosystem processes such as pollination, nutrient recycling and biocontrol, further weakening agricultural resilience. Sustainable and climate-smart agricultural activities such as natural farming, sustainable agriculture and agroforestry play an important function in enhance soil health, protecting resources and supporting resilient farming systems. Advances in plant breeding and biotechnology are enabling the advance of climate resilient crop variability, while adaptation strategies like efficient water management, crop diversification and improved seed systems help farmers manage climatic risks. Emerging digital technologies, including artificial intelligence, remote sensing and mobile advisory services, are also enhancing farm decision-making. However, effective policy support, research investment and international cooperation are essential to ensure these innovations reach vulnerable farming communities. This chapter examines the effect of climate change on agriculture and highlights sustainable strategies, technological innovations and policy approaches needed to build resilient agricultural systems.","author":[],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19666236","URL":"https://doi.org/10.5281/zenodo.19666236","source":"datacite"},{"id":"doi:10.7910/dvn/fmmrmt","type":"article-journal","title":"Role of social network in CSA adoption","abstract":"This dataset was collected as part of a case study aimed at examining the role of social networks in the adoption of climate-smart agricultural (CSA) technologies in Cambodia. The data focus on farmers’ demographic and socioeconomic profiles, their interpersonal connections within the community, and their adoption of specific CSA practices. The dataset contributes to understanding how social relationships influence technology diffusion and adoption among rural farmers. Interpretation: These variables represent different types of agricultural information exchanged among farmers. • Info-1: Climate smart agriculture information. • Info-2: Other agronomic information. • Info-3: Farm service information. • Info-4: Market information. • Info-5: Financial information. • Info-6: Policy information. • Info-7: Agrometeorology information. Methodology: Data were collected through structured household surveys and social network questionnaires administered to farmers in two selected villages in Battambang and Kampong Thom provinces. The survey covered demographic characteristics, CSA uptakes, and social interactions related to seven types of information: climate smart agriculture, other agronomic, farming service, market, financial, policy, and agrometeorological information. Trained enumerators conducted face-to-face interviews using a digital questionnaire on the ODK platform.","author":[{"family":"San","given":"Su"},{"family":"Buscano Flor","given":"Rica"}],"issued":{"date-parts":[[2025]]},"DOI":"10.7910/dvn/fmmrmt","URL":"https://doi.org/10.7910/dvn/fmmrmt","source":"datacite"},{"id":"doi:10.5281/zenodo.19615214","type":"article-journal","title":"iot based hydrophobic underwater farming system","abstract":"The Hydrophobic Underwater Irrigation System is an innovative approach to efficient water management in agriculture, designed to minimize water loss and enhance irrigation precision. This system utilizes hydrophobic materials and controlled underwater delivery mechanisms to transport water directly to plant root zones, reducing evaporation and surface runoff. Traditional irrigation methods often suffer from significant water wastage due to evaporation, leakage, and inefficient distribution. The proposed system addresses these challenges by employing hydrophobic-coated channels or pipelines that resist water adhesion, enabling smooth and targeted water flow beneath the soil surface. This ensures optimal moisture retention in the root zone while preventing over-irrigation and soil erosion. The system is integrated with IoT-based monitoring and control using microcontrollers and wireless communication platforms such as Blynk IoT platform, allowing real-time tracking of soil moisture, water flow, and environmental conditions. Sensors collect data that is processed to automate irrigation cycles, improving water efficiency and crop yield. This solution is particularly beneficial for arid and semi-arid regions where water conservation is critical. By combining hydrophobic material science with smart irrigation technology, the system offers a sustainable, cost-effective, and scalable method for modern agriculture. The proposed model contributes to precision farming practices and supports global efforts toward sustainable water resource management.","author":[{"family":"University","given":"Poornima"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19615214","URL":"https://doi.org/10.5281/zenodo.19615214","source":"datacite"},{"id":"doi:10.5281/zenodo.19615213","type":"article-journal","title":"iot based hydrophobic underwater farming system","abstract":"The Hydrophobic Underwater Irrigation System is an innovative approach to efficient water management in agriculture, designed to minimize water loss and enhance irrigation precision. This system utilizes hydrophobic materials and controlled underwater delivery mechanisms to transport water directly to plant root zones, reducing evaporation and surface runoff. Traditional irrigation methods often suffer from significant water wastage due to evaporation, leakage, and inefficient distribution. The proposed system addresses these challenges by employing hydrophobic-coated channels or pipelines that resist water adhesion, enabling smooth and targeted water flow beneath the soil surface. This ensures optimal moisture retention in the root zone while preventing over-irrigation and soil erosion. The system is integrated with IoT-based monitoring and control using microcontrollers and wireless communication platforms such as Blynk IoT platform, allowing real-time tracking of soil moisture, water flow, and environmental conditions. Sensors collect data that is processed to automate irrigation cycles, improving water efficiency and crop yield. This solution is particularly beneficial for arid and semi-arid regions where water conservation is critical. By combining hydrophobic material science with smart irrigation technology, the system offers a sustainable, cost-effective, and scalable method for modern agriculture. The proposed model contributes to precision farming practices and supports global efforts toward sustainable water resource management.","author":[{"family":"University","given":"Poornima"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19615213","URL":"https://doi.org/10.5281/zenodo.19615213","source":"datacite"},{"id":"doi:10.5281/zenodo.19581811","type":"article-journal","title":"An AI-Driven Smart Irrigation and Fertigation System Using ESP32, IoT Sensors, and Cloud Monitoring","abstract":"Conventional agricultural irrigation relies heavily on static scheduling, leading to substantial water wastage and suboptimal crop yields due to the neglect of real-time environmental conditions. To address this inefficiency, this paper presents AgriSense, a low-cost, edge-computed smart irrigation and fertigation system. The proposed architecture utilizes the ESP32 microcon- troller, Internet of Things (IoT) telemetry, and a multi- modal sensor array encompassing capacitive soil moisture, DHT11, Total Dissolved Solids (TDS), and water flow sensors. An embedded evapotranspiration (ET) model dynamically adjusts irrigation thresholds at the edge, while hardware-level safety interlocks mitigate hydraulic failures independently of cloud connectivity. Experimental results from a 45-day field trial in a tropical climate demonstrated a 42% reduction in water consumption and an 11.8% increase in crop yield compared to tradi- tional timer-based methods. Ultimately, this architecture provides an economically viable, highly reliable precision agriculture framework for resource-constrained farming operations.","author":[{"family":"M Nair","given":"Abhijith"},{"family":"Maria Sebastian","given":"Sona"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19581811","URL":"https://doi.org/10.5281/zenodo.19581811","source":"datacite"},{"id":"doi:10.5281/zenodo.19581810","type":"article-journal","title":"An AI-Driven Smart Irrigation and Fertigation System Using ESP32, IoT Sensors, and Cloud Monitoring","abstract":"Conventional agricultural irrigation relies heavily on static scheduling, leading to substantial water wastage and suboptimal crop yields due to the neglect of real-time environmental conditions. To address this inefficiency, this paper presents AgriSense, a low-cost, edge-computed smart irrigation and fertigation system. The proposed architecture utilizes the ESP32 microcon- troller, Internet of Things (IoT) telemetry, and a multi- modal sensor array encompassing capacitive soil moisture, DHT11, Total Dissolved Solids (TDS), and water flow sensors. An embedded evapotranspiration (ET) model dynamically adjusts irrigation thresholds at the edge, while hardware-level safety interlocks mitigate hydraulic failures independently of cloud connectivity. Experimental results from a 45-day field trial in a tropical climate demonstrated a 42% reduction in water consumption and an 11.8% increase in crop yield compared to tradi- tional timer-based methods. Ultimately, this architecture provides an economically viable, highly reliable precision agriculture framework for resource-constrained farming operations.","author":[{"family":"M Nair","given":"Abhijith"},{"family":"Maria Sebastian","given":"Sona"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19581810","URL":"https://doi.org/10.5281/zenodo.19581810","source":"datacite"},{"id":"doi:10.5281/zenodo.19475109","type":"article-journal","title":"Digital ethnography interview transcript No.02 - Climate projects in Sri Lanka","abstract":"The interview with a disaster management and resilience professional with 20 years of experience, traces a career bridging agriculture, organizational management, and humanitarian response in Sri Lanka. In Sri Lanka, she has engaged in climate-resilient water management (CRIWMP) and other climate-smart initiatives, coordinating with civil society to mobilize communities in Anuradhapura and Trincomalee. Projects focused on water management for smallholders, drinking water during disasters, strengthening minor irrigation tanks, and delivering climate-smart information to women farmers in Batticaloa. Her experience covers the dry zone and Horowpothana in Anuradhapura, where climate-smart agriculture, disaster risk reduction, and livelihood recovery were pursued. The interview highlights hazards such as floods, drought, and human-wildlife conflicts, and reflects on generational shifts in farming. Social issues include gendered burdens, water collection challenges, and security concerns for women.","author":[{"family":"Sendanayake","given":"Avishka"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19475109","URL":"https://doi.org/10.5281/zenodo.19475109","source":"datacite"},{"id":"doi:10.5281/zenodo.19475110","type":"article-journal","title":"Digital ethnography interview transcript No.02 - Climate projects in Sri Lanka","abstract":"The interview with a disaster management and resilience professional with 20 years of experience, traces a career bridging agriculture, organizational management, and humanitarian response in Sri Lanka. In Sri Lanka, she has engaged in climate-resilient water management (CRIWMP) and other climate-smart initiatives, coordinating with civil society to mobilize communities in Anuradhapura and Trincomalee. Projects focused on water management for smallholders, drinking water during disasters, strengthening minor irrigation tanks, and delivering climate-smart information to women farmers in Batticaloa. Her experience covers the dry zone and Horowpothana in Anuradhapura, where climate-smart agriculture, disaster risk reduction, and livelihood recovery were pursued. The interview highlights hazards such as floods, drought, and human-wildlife conflicts, and reflects on generational shifts in farming. Social issues include gendered burdens, water collection challenges, and security concerns for women.","author":[{"family":"Sendanayake","given":"Avishka"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19475110","URL":"https://doi.org/10.5281/zenodo.19475110","source":"datacite"},{"id":"doi:10.5281/zenodo.19465930","type":"article-journal","title":"A Survey on IoT and Blockchain Integration in Smart Agriculture for Sustainable and Resilient Food Systems","abstract":"The rapid advancement of digital technologies has significantly transformed modern agriculture, marking a shift toward systemswhere the integration of the Internet of Things (IoT) and blockchain supports more secure, transparent, and efficient agriculturaloperations. Despite this progress, traditional farming practices continue to face persistent challenges, including limited supplychain visibility, data security risks, insufficient traceability, and uncertainties arising from climate variability. Standalonetechnological solutions have, in most cases, proven inadequate in addressing these issues in a comprehensive manner.Against this backdrop, the present survey provides a systematic review of IoT–blockchain integration in smart agriculture,drawing on a curated set of 40 recent studies published between 2022 and 2026. The discussion covers architecturalframeworks, communication protocols, and consensus mechanisms that underpin these systems, while also examining theirapplication in areas such as supply chain traceability, precision farming, crop monitoring, and smart contract–driven resourceallocation. Key considerations—including scalability, interoperability, energy efficiency, and data privacy—are exploredalongside ongoing challenges such as latency constraints, the lack of standardization, and barriers to adoption amongsmallholder farmers. Looking ahead, the survey also points to emerging research directions aligned with the Agriculture 5.0paradigm, particularly those aimed at enabling sustainable, human-centric, and resilient food systems. In doing so, it bringstogether insights that may assist researchers, practitioners, and policymakers working at the intersection of agriculturaldigitalization and distributed ledger technologies","author":[{"family":"Senthil","given":"Aneesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19465930","URL":"https://doi.org/10.5281/zenodo.19465930","source":"datacite"},{"id":"doi:10.5281/zenodo.19465931","type":"article-journal","title":"A Survey on IoT and Blockchain Integration in Smart Agriculture for Sustainable and Resilient Food Systems","abstract":"The rapid advancement of digital technologies has significantly transformed modern agriculture, marking a shift toward systemswhere the integration of the Internet of Things (IoT) and blockchain supports more secure, transparent, and efficient agriculturaloperations. Despite this progress, traditional farming practices continue to face persistent challenges, including limited supplychain visibility, data security risks, insufficient traceability, and uncertainties arising from climate variability. Standalonetechnological solutions have, in most cases, proven inadequate in addressing these issues in a comprehensive manner.Against this backdrop, the present survey provides a systematic review of IoT–blockchain integration in smart agriculture,drawing on a curated set of 40 recent studies published between 2022 and 2026. The discussion covers architecturalframeworks, communication protocols, and consensus mechanisms that underpin these systems, while also examining theirapplication in areas such as supply chain traceability, precision farming, crop monitoring, and smart contract–driven resourceallocation. Key considerations—including scalability, interoperability, energy efficiency, and data privacy—are exploredalongside ongoing challenges such as latency constraints, the lack of standardization, and barriers to adoption amongsmallholder farmers. Looking ahead, the survey also points to emerging research directions aligned with the Agriculture 5.0paradigm, particularly those aimed at enabling sustainable, human-centric, and resilient food systems. In doing so, it bringstogether insights that may assist researchers, practitioners, and policymakers working at the intersection of agriculturaldigitalization and distributed ledger technologies","author":[{"family":"Senthil","given":"Aneesh"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19465931","URL":"https://doi.org/10.5281/zenodo.19465931","source":"datacite"},{"id":"doi:10.5281/zenodo.19410304","type":"article-journal","title":"ROLE OF MICROBIAL BIOTECHNOLOGY IN CLIMATE-SMART AGRICULTURE: MECHANISMS AND SUSTAINABLE APPLICATIONS","abstract":"Abstract Microbial biotechnology is increasingly recognized as a valuable approach for developing climate-smart agricultural systems that are both productive and environmentally responsible. This study focuses on the functional role of beneficial microorganisms in improving soil quality and supporting crop growth under changing climatic conditions. Microbes present in the rhizosphere actively assist in nutrient transformation, making essential elements such as nitrogen and phosphorus more available to plants. At the same time, they contribute to the breakdown of organic matter, which enhances soil structure and moisture retention. An important aspect of microbial activity is its ability to help plants cope with environmental stresses like drought, salinity, and temperature fluctuations. Certain microorganisms stimulate natural plant responses that improve tolerance and maintain growth even in adverse conditions. Additionally, microbial applications can reduce dependency on chemical fertilizers and pesticides, thereby minimizing environmental degradation. For sustainable use, it is essential to match microbial solutions with local soil and climatic conditions. Field-level adoption, proper formulation, and farmer awareness are key to successful implementation. The study highlights that integrating microbial biotechnology into agricultural practices can support long-term sustainability while ensuring stable crop production in the face of climate variability.","author":[{"family":"Rc"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19410304","URL":"https://doi.org/10.5281/zenodo.19410304","source":"datacite"},{"id":"doi:10.5281/zenodo.19410303","type":"article-journal","title":"ROLE OF MICROBIAL BIOTECHNOLOGY IN CLIMATE-SMART AGRICULTURE: MECHANISMS AND SUSTAINABLE APPLICATIONS","abstract":"Abstract Microbial biotechnology is increasingly recognized as a valuable approach for developing climate-smart agricultural systems that are both productive and environmentally responsible. This study focuses on the functional role of beneficial microorganisms in improving soil quality and supporting crop growth under changing climatic conditions. Microbes present in the rhizosphere actively assist in nutrient transformation, making essential elements such as nitrogen and phosphorus more available to plants. At the same time, they contribute to the breakdown of organic matter, which enhances soil structure and moisture retention. An important aspect of microbial activity is its ability to help plants cope with environmental stresses like drought, salinity, and temperature fluctuations. Certain microorganisms stimulate natural plant responses that improve tolerance and maintain growth even in adverse conditions. Additionally, microbial applications can reduce dependency on chemical fertilizers and pesticides, thereby minimizing environmental degradation. For sustainable use, it is essential to match microbial solutions with local soil and climatic conditions. Field-level adoption, proper formulation, and farmer awareness are key to successful implementation. The study highlights that integrating microbial biotechnology into agricultural practices can support long-term sustainability while ensuring stable crop production in the face of climate variability.","author":[{"family":"Rc"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19410303","URL":"https://doi.org/10.5281/zenodo.19410303","source":"datacite"},{"id":"doi:10.5281/zenodo.19348479","type":"article-journal","title":"AutoShield: Smart Sensor-Triggered Motorized Canopy System for Crop Protection","abstract":"Unseasonal rainfall and hailstorm events cause catastrophic damage to high-value horticultural crops in India, resulting in annual losses exceeding INR 50,000 crore. This paper presents AutoShield, a novel IoT-integrated motorized canopy protection system designed specifically for grape, pomegranate, strawberry, and flower farmers. The system employs a multi-sensor array including barometric pressure sensors (BMP280), temperature-humidity sensors (DHT22), rain detection modules, and light-dependent resistors (LDR) connected to an ESP32 microcontroller. Upon detecting imminent rainfall through sensor fusion logic, the system automatically deploys a durable PVC-coated polyester canopy over the protected farmland. The canopy design incorporates a gravity-assisted counterweight mechanism for energy-efficient deployment, a peripheral rainwater collection pipeline network for water harvesting, and windbreak mesh side panels for structural stability. The system operates fully offline with optional Bluetooth and WiFi based mobile dashboard control, and is powered by an off-grid solar panel and battery unit. Prototype evaluation demonstrates successful rain prediction and canopy deployment with an average response time of under 90 seconds. The modular unit design supports customization from 20x20 ft to 100x100 ft coverage areas, making it economically viable at INR 15,000-80,000 per unit with a projected 10-15 year operational lifespan. This paper details the system architecture, hardware design, sensor logic, material selection, economic analysis, and deployment strategy.","author":[{"family":"Sonewane","given":"Pradyumna"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19348479","URL":"https://doi.org/10.5281/zenodo.19348479","source":"datacite"},{"id":"doi:10.5281/zenodo.19348480","type":"article-journal","title":"AutoShield: Smart Sensor-Triggered Motorized Canopy System for Crop Protection","abstract":"Unseasonal rainfall and hailstorm events cause catastrophic damage to high-value horticultural crops in India, resulting in annual losses exceeding INR 50,000 crore. This paper presents AutoShield, a novel IoT-integrated motorized canopy protection system designed specifically for grape, pomegranate, strawberry, and flower farmers. The system employs a multi-sensor array including barometric pressure sensors (BMP280), temperature-humidity sensors (DHT22), rain detection modules, and light-dependent resistors (LDR) connected to an ESP32 microcontroller. Upon detecting imminent rainfall through sensor fusion logic, the system automatically deploys a durable PVC-coated polyester canopy over the protected farmland. The canopy design incorporates a gravity-assisted counterweight mechanism for energy-efficient deployment, a peripheral rainwater collection pipeline network for water harvesting, and windbreak mesh side panels for structural stability. The system operates fully offline with optional Bluetooth and WiFi based mobile dashboard control, and is powered by an off-grid solar panel and battery unit. Prototype evaluation demonstrates successful rain prediction and canopy deployment with an average response time of under 90 seconds. The modular unit design supports customization from 20x20 ft to 100x100 ft coverage areas, making it economically viable at INR 15,000-80,000 per unit with a projected 10-15 year operational lifespan. This paper details the system architecture, hardware design, sensor logic, material selection, economic analysis, and deployment strategy.","author":[{"family":"Sonewane","given":"Pradyumna"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19348480","URL":"https://doi.org/10.5281/zenodo.19348480","source":"datacite"},{"id":"doi:10.6084/m9.figshare.31881616.v1","type":"article-journal","title":"KRUSHIDHAN: IoT-Enabled Cattle Health Monitoring and Disease Risk Detection Dataset","abstract":"This dataset is associated with the KRUSHIDHAN project, an Internet of Things (IoT)-enabled cattle health monitoring and disease risk detection system. The dataset contains multi-parameter time-series sensor data collected using a wearable smart collar designed for continuous monitoring of cattle health.The dataset includes physiological, behavioral, and environmental parameters such as body temperature (°C), heart rate (bpm), ambient humidity (%), motion data from accelerometer and gyroscope sensors (Ax, Ay, Az, Gx, Gy, Gz), and timestamp information. Each record represents real-time sensor readings captured at regular intervals.Health condition labels are included to indicate normal and early-risk states of cattle, based on threshold-based physiological observations and expert validation. The dataset is stored in structured format using comma-separated values (CSV), making it suitable for data analysis and machine learning applications.Basic preprocessing such as noise filtering and normalization was applied during runtime to ensure data reliability. The dataset is primarily maintained in raw structured form, supporting real-time analytics and classification.This dataset can be used for research in precision livestock farming, IoT-based monitoring systems, and predictive health analytics. It enables the development and evaluation of machine learning models for early disease detection and decision-support systems in smart agriculture.","author":[{"family":"Pujari","given":"Shishir"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.31881616.v1","URL":"https://doi.org/10.6084/m9.figshare.31881616.v1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.31881616","type":"article-journal","title":"KRUSHIDHAN: IoT-Enabled Cattle Health Monitoring and Disease Risk Detection Dataset","abstract":"This dataset is associated with the KRUSHIDHAN project, an Internet of Things (IoT)-enabled cattle health monitoring and disease risk detection system. The dataset contains multi-parameter time-series sensor data collected using a wearable smart collar designed for continuous monitoring of cattle health.The dataset includes physiological, behavioral, and environmental parameters such as body temperature (°C), heart rate (bpm), ambient humidity (%), motion data from accelerometer and gyroscope sensors (Ax, Ay, Az, Gx, Gy, Gz), and timestamp information. Each record represents real-time sensor readings captured at regular intervals.Health condition labels are included to indicate normal and early-risk states of cattle, based on threshold-based physiological observations and expert validation. The dataset is stored in structured format using comma-separated values (CSV), making it suitable for data analysis and machine learning applications.Basic preprocessing such as noise filtering and normalization was applied during runtime to ensure data reliability. The dataset is primarily maintained in raw structured form, supporting real-time analytics and classification.This dataset can be used for research in precision livestock farming, IoT-based monitoring systems, and predictive health analytics. It enables the development and evaluation of machine learning models for early disease detection and decision-support systems in smart agriculture.","author":[{"family":"Pujari","given":"Shishir"}],"issued":{"date-parts":[[2026]]},"DOI":"10.6084/m9.figshare.31881616","URL":"https://doi.org/10.6084/m9.figshare.31881616","source":"datacite"},{"id":"doi:10.6084/m9.figshare.30853271","type":"article-journal","title":"Smart Cultivation and Marketing of Indigenous Fruit Crops: An AI-Driven Approach","abstract":"This preprint presents the project “Smart Cultivation and Marketing of Indigenous Fruit Crops,” a system designed to support farmers in cultivating and promoting traditional Indian fruits such as Ramphala, Lakshmanphala, and Wood Apple. The work integrates Artificial Intelligence and Machine Learning to provide three major functionalities: AI-based Crop Recommendation: A Random Forest model analyzes soil parameters including pH, NPK composition, moisture, and organic content to suggest the most suitable indigenous fruit crop for a given region. Deep Learning–based Disease Detection: A Convolutional Neural Network (CNN) processes uploaded leaf images to identify plant diseases at an early stage, helping reduce yield loss and enabling timely intervention. Data-Driven Marketing Insights: Market trends, nutritional analysis, and cultivation patterns are visualized to help farmers and consumers understand the economic and health value of native fruit crops.The project highlights the potential of AI-driven agriculture to improve crop productivity, reduce losses, and enhance sustainable farming practices. It also emphasizes the importance of indigenous fruit conservation, biodiversity, and farmer profitability. This preprint includes the full project methodology, system design, implementation details, test cases, and future enhancements.","author":[{"family":"M S","given":"Suraj"}],"issued":{"date-parts":[[2025]]},"DOI":"10.6084/m9.figshare.30853271","URL":"https://doi.org/10.6084/m9.figshare.30853271","source":"datacite"},{"id":"doi:10.6084/m9.figshare.30094414","type":"article-journal","title":"The business case for grasspea in Ethiopia: An action plan to provide Ethiopian farmers with a safe, nutritious and climate-smart protein source.","abstract":"This document provides an overview and action plan for the scale-up and use of low-ODAP grasspea across Ethiopia to complement nutritious and resilient climate-smart agriculture. Grasspea has a long history in Ethiopia as one of the most widely cultivated legumes, yet it remains underutilised and marginal within formal seed systems and value chains. The presence of the neurotoxin β-ODAP in traditional varieties has discouraged widespread consumption and investment, despite the crop’s adaptability, regenerative qualities, and importance to smallholder farmers.Recent advances in bioscience have enabled more targeted and rapid breeding progress, resulting in low-ODAP varieties with improved agronomic performance. These developments offer an opportunity to realise the full potential of grasspea for Ethiopian farming systems, particularly in areas prone to climate stress. However, questions remain about how to ensure that improved grasspea seed reaches farmers at scale, in ways that are timely, inclusive, and sustainable.In this document, we present a synthesis of recent developments in grasspea research and use this to outline three action plans for the expansion of improved grasspea use in Ethiopia. One approach follows the traditional Ethiopian model of government seed purchase and distribution. A second outlines how integrated seed systems involving local seed businesses (LSBs) and farmer organisations could support a more decentralised and sustainable model of seed delivery. A third, phased approach combines the strengths of the previous two and offers a pathway for both immediate and longer-term uptake. Each approach is described with reference to its actor landscape, implementation considerations, and embedded theory of change.We argue that while the phased approach may provide a pragmatic starting point for rapid expansion, it is the integrated seed system model that holds the greatest potential for sustained delivery of improved grasspea across Ethiopia’s diverse farming landscapes. We conclude with a set of recommendations for the partnerships, capacities, and enabling conditions needed to ensure that improved grasspea can contribute meaningfully to food and nutrition security, climate resilience, and rural livelihoods.","author":[{"family":"Heaton","given":"Matt"},{"family":"Chole","given":"Hileena"}],"issued":{"date-parts":[[2025]]},"DOI":"10.6084/m9.figshare.30094414","URL":"https://doi.org/10.6084/m9.figshare.30094414","source":"datacite"},{"id":"doi:10.6084/m9.figshare.29964485","type":"article-journal","title":"BIG DATA ANALYTICS FOR SMART FARMING (1).pdf","abstract":"The rapid advancement of big data analytics is transforming agriculture into a highly data-driven industry, enabling farmers to optimize productivity, sustainability, and profitability. Smart farming integrates multiple technologies such as cloud computing, Internet of Things (IoT), machine learning, and predictive modeling to collect, process, and analyze massive amounts of agricultural data. This paper explores the critical role of big data analytics in smart farming, including its applications in crop monitoring, soil health analysis, yield prediction, pest management, and resource optimization. Drawing from Vedantham (2024) and other recent scholarly sources, the paper also discusses methodologies for data collection and processing, presents real-world case studies, highlights challenges such as data privacy, interoperability, and cost, and identifies future directions in precision agriculture. Tables are provided to illustrate applications, challenges, and comparative tools in big data–driven agriculture. The analysis underscores how big data analytics contributes to addressing global food security while advancing sustainable","author":[{"family":"Robin","given":"Nico"}],"issued":{"date-parts":[[2025]]},"DOI":"10.6084/m9.figshare.29964485","URL":"https://doi.org/10.6084/m9.figshare.29964485","source":"datacite"},{"id":"doi:10.6084/m9.figshare.29964437","type":"article-journal","title":"AI AND MACHINE LEARNING IN PRECISION AGRICULTURE.pdf","abstract":"The global agricultural sector is undergoing a technological transformation driven by Artificial Intelligence (AI) and Machine Learning (ML). Precision agriculture integrates data analytics, remote sensing, and automation to enhance food security, reduce resource waste, and address environmental concerns. AI and ML algorithms enable predictive modeling, disease detection, smart irrigation, and yield forecasting, making farming more efficient and sustainable. Building on prior works such as Vedantham (2024), which emphasized the role of cloud and IoT technologies in revolutionizing precision agriculture, this study reviews the synergistic application of AI and ML across farming systems. The paper examines the methodological frameworks, applications, case studies, challenges, and future prospects of AI in agriculture. By analyzing both global and local perspectives, the research highlights how AI not only improves crop productivity but also fosters sustainability and resilience in farming practices.","author":[{"family":"Chals Daniel","given":"Anthony"}],"issued":{"date-parts":[[2025]]},"DOI":"10.6084/m9.figshare.29964437","URL":"https://doi.org/10.6084/m9.figshare.29964437","source":"datacite"},{"id":"doi:10.5281/zenodo.19285090","type":"article-journal","title":"Al and Automation in Daily Life","abstract":"Artificial Intelligence (AI) and automation have become integral parts of everyday life, transforming how people work, communicate, learn, shop, and manage their homes. From voice assistants and personalised recommendations on streaming platforms to smart home devices and automated customer service, these technologies enhance convenience, efficiency, and decision-making. AI-driven applications analyse large amounts of data to provide tailored experiences, improve healthcare diagnostics, optimise transportation systems, and support online education through adaptive learning tools. Automation reduces the need for repetitive manual tasks, increasing productivity in both household and professional environments. In banking, AI enables fraud detection and facilitates digital payments; in retail, it powers inventory management and targeted marketing; and in agriculture, it supports precision farming. However, the growing presence of AI also raises concerns about data privacy, job displacement, algorithmic bias, and the ethical use of technology. Despite these challenges, AI and automation continue to offer significant opportunities for innovation and an improved quality of life. By promoting responsible development, digital literacy, and inclusive policies, societies can harness these technologies to support economic growth and human well-being.","author":[{"family":"Bajpeyi","given":"Shreya"},{"family":"Bajpeyi","given":"Tejaswini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19285090","URL":"https://doi.org/10.5281/zenodo.19285090","source":"datacite"},{"id":"doi:10.5281/zenodo.19285089","type":"article-journal","title":"Al and Automation in Daily Life","abstract":"Artificial Intelligence (AI) and automation have become integral parts of everyday life, transforming how people work, communicate, learn, shop, and manage their homes. From voice assistants and personalised recommendations on streaming platforms to smart home devices and automated customer service, these technologies enhance convenience, efficiency, and decision-making. AI-driven applications analyse large amounts of data to provide tailored experiences, improve healthcare diagnostics, optimise transportation systems, and support online education through adaptive learning tools. Automation reduces the need for repetitive manual tasks, increasing productivity in both household and professional environments. In banking, AI enables fraud detection and facilitates digital payments; in retail, it powers inventory management and targeted marketing; and in agriculture, it supports precision farming. However, the growing presence of AI also raises concerns about data privacy, job displacement, algorithmic bias, and the ethical use of technology. Despite these challenges, AI and automation continue to offer significant opportunities for innovation and an improved quality of life. By promoting responsible development, digital literacy, and inclusive policies, societies can harness these technologies to support economic growth and human well-being.","author":[{"family":"Bajpeyi","given":"Shreya"},{"family":"Bajpeyi","given":"Tejaswini"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19285089","URL":"https://doi.org/10.5281/zenodo.19285089","source":"datacite"},{"id":"doi:10.5281/zenodo.19205625","type":"article-journal","title":"An Assessment of Global Climate Change Impacts and Local Adaptation and Mitigation Strategies","abstract":"Climate change is a pressing concern of the twenty-first century, largely driven by anthropogenic greenhouse gas (GHG) emissions from burning of fossil fuels, land and sea-use change, industrialization and intensive farming. The global warming is happening at an unprecedented scale with far-reaching implications on natural ecosystems, economies, and human societies all over the world. Rising sea levels, altered precipitation patterns, high temperature and increased frequency and intensity of extreme weather conditions are among the most significant global changes, amplifying the risks across regions and populations. Climate change impacts food and water security, human health, infra-structure and economic stability. Biodiversity loss and ecosystem degradation are other important repercussions of climate change disturbing the core of Biosphere. The global nature of climate change demands coordinated international action, as exemplified by multilateral frameworks such as the United Nations Framework Convention on Climate Change (UNFCCC) and the Paris Agreement. But the success of this coordinated international action depends on localized strategies customized to specific environmental, social, and economic contexts. Local responses at panchayat, municipal and other sub national levels play a critical role in both climate mitigation and climate adaptations. India, being one of the country’s most vulnerable to climate risks, recent research highlights numerous visible signs of climatic shifts, including prolonged heatwaves, monsoon variability, coastal flooding and increasing water stress, with far-reaching health and socio-economic consequences [10]. The 2025 India–Pakistan heatwave saw temperatures exceeding 48°C, resulting in hundreds of heat-related deaths and widespread agricultural disruptions. Local adaptation measures such as heat Action Plans are being implemented in several Indian cities, while other regions invest in early warning systems and climate-smart agricultural practices. The current chapter amalgamate the evidences from global climate change and recent Indian case studies to illustrate the multifaceted nature of climate change and the necessity for integrated collaborative governance frameworks that align international policy with local solutions, emphasizing sustainability and resilience for most affected communities.","author":[{"family":"Shetty","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19205625","URL":"https://doi.org/10.5281/zenodo.19205625","source":"datacite"},{"id":"doi:10.5281/zenodo.19205624","type":"article-journal","title":"An Assessment of Global Climate Change Impacts and Local Adaptation and Mitigation Strategies","abstract":"Climate change is a pressing concern of the twenty-first century, largely driven by anthropogenic greenhouse gas (GHG) emissions from burning of fossil fuels, land and sea-use change, industrialization and intensive farming. The global warming is happening at an unprecedented scale with far-reaching implications on natural ecosystems, economies, and human societies all over the world. Rising sea levels, altered precipitation patterns, high temperature and increased frequency and intensity of extreme weather conditions are among the most significant global changes, amplifying the risks across regions and populations. Climate change impacts food and water security, human health, infra-structure and economic stability. Biodiversity loss and ecosystem degradation are other important repercussions of climate change disturbing the core of Biosphere. The global nature of climate change demands coordinated international action, as exemplified by multilateral frameworks such as the United Nations Framework Convention on Climate Change (UNFCCC) and the Paris Agreement. But the success of this coordinated international action depends on localized strategies customized to specific environmental, social, and economic contexts. Local responses at panchayat, municipal and other sub national levels play a critical role in both climate mitigation and climate adaptations. India, being one of the country’s most vulnerable to climate risks, recent research highlights numerous visible signs of climatic shifts, including prolonged heatwaves, monsoon variability, coastal flooding and increasing water stress, with far-reaching health and socio-economic consequences [10]. The 2025 India–Pakistan heatwave saw temperatures exceeding 48°C, resulting in hundreds of heat-related deaths and widespread agricultural disruptions. Local adaptation measures such as heat Action Plans are being implemented in several Indian cities, while other regions invest in early warning systems and climate-smart agricultural practices. The current chapter amalgamate the evidences from global climate change and recent Indian case studies to illustrate the multifaceted nature of climate change and the necessity for integrated collaborative governance frameworks that align international policy with local solutions, emphasizing sustainability and resilience for most affected communities.","author":[{"family":"Shetty","given":"Dr"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19205624","URL":"https://doi.org/10.5281/zenodo.19205624","source":"datacite"},{"id":"doi:10.5281/zenodo.19179309","type":"article-journal","title":"An Integrated Mobile Application for Agricultural Schemes, Weather Forecasting, and Fertilizer Prediction","abstract":"The growing demand for technology-driven farming has prompted the development of intelligent digital platforms to support farmers in effective decision-making. This paper presents an integrated web-based Smart Agriculture Assistance Application that combines agricultural scheme information, weather forecasting, and soil-based fertilizer recommendations into a unified digital platform. The system provides comprehensive details about central and state government agricultural schemes, including eligibility criteria, benefits, and application procedures, enabling farmers to make informed financial and developmental decisions. The weather forecasting module retrieves historical climate data and generates accurate five-day predictions using a trusted meteorological API. A key feature is the Fertilizer Recommendation Module, which employs the Decision Tree algorithm to analyze soil nutrient content—Nitrogen, Phosphorus, and Potassium—and recommends the most suitable fertilizer type and optimal application quantity. The application is developed using HTML, CSS, JavaScript for the frontend and Python-Flask for the backend, offering a practical and accessible decision-support tool aimed at enhancing agricultural productivity and sustainability.","author":[{"family":"Kanishka S","given":"Madhumitha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19179309","URL":"https://doi.org/10.5281/zenodo.19179309","source":"datacite"},{"id":"doi:10.5281/zenodo.19179308","type":"article-journal","title":"An Integrated Mobile Application for Agricultural Schemes, Weather Forecasting, and Fertilizer Prediction","abstract":"The growing demand for technology-driven farming has prompted the development of intelligent digital platforms to support farmers in effective decision-making. This paper presents an integrated web-based Smart Agriculture Assistance Application that combines agricultural scheme information, weather forecasting, and soil-based fertilizer recommendations into a unified digital platform. The system provides comprehensive details about central and state government agricultural schemes, including eligibility criteria, benefits, and application procedures, enabling farmers to make informed financial and developmental decisions. The weather forecasting module retrieves historical climate data and generates accurate five-day predictions using a trusted meteorological API. A key feature is the Fertilizer Recommendation Module, which employs the Decision Tree algorithm to analyze soil nutrient content—Nitrogen, Phosphorus, and Potassium—and recommends the most suitable fertilizer type and optimal application quantity. The application is developed using HTML, CSS, JavaScript for the frontend and Python-Flask for the backend, offering a practical and accessible decision-support tool aimed at enhancing agricultural productivity and sustainability.","author":[{"family":"Kanishka S","given":"Madhumitha"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.19179308","URL":"https://doi.org/10.5281/zenodo.19179308","source":"datacite"},{"id":"doi:10.57945/manara.hbku.30693932.v1","type":"article-journal","title":"Modeling Smart Green Sukuk for Green Financing of Agriculture in the GCC Region","abstract":"This research aims to combine Islamic finance principles with modern technologies to help solve the challenges faced by the agriculture sector in the Gulf Cooperation Council (GCC) region. It introduces a new financial tool called Smart Green Sukuk, which relies on blockchain technology to raise funds for sustainable agricultural projects. The study emphasizes the importance of eco-friendly practices for increasing food security in the dry GCC region, where climate change, water shortages, and limited farmland exacerbate the challenges. Smart Green Sukuk leverages blockchain technology and Shari’ah-compliant financial structures to provide a transparent, efficient, and accountable way to finance projects that align with both Islamic principles and environmental sustainability goals. Case studies in successful vertical farming, sustainable irrigation, and organic agriculture demonstrate how this innovative instrument can promote economic diversification, protect the environment, and promote social equity.The research offers practical guidance for governments, investors, and stakeholders, highlighting the importance of innovative financial tools in fostering sustainable farming and food stability in the region. Future studies can build on this foundation by investigating the feasibility of Smart Green Sukuk in industries such as renewable energy and waste disposal, assessing the social and economic effects of these instruments, and examining opportunities for international cooperation among Islamic finance organizations to harmonize and advance green investment practices worldwide.","author":[{"family":"Musalman","given":"Abdur"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.30693932.v1","URL":"https://doi.org/10.57945/manara.hbku.30693932.v1","source":"datacite"},{"id":"doi:10.57945/manara.hbku.30693932","type":"article-journal","title":"Modeling Smart Green Sukuk for Green Financing of Agriculture in the GCC Region","abstract":"This research aims to combine Islamic finance principles with modern technologies to help solve the challenges faced by the agriculture sector in the Gulf Cooperation Council (GCC) region. It introduces a new financial tool called Smart Green Sukuk, which relies on blockchain technology to raise funds for sustainable agricultural projects. The study emphasizes the importance of eco-friendly practices for increasing food security in the dry GCC region, where climate change, water shortages, and limited farmland exacerbate the challenges. Smart Green Sukuk leverages blockchain technology and Shari’ah-compliant financial structures to provide a transparent, efficient, and accountable way to finance projects that align with both Islamic principles and environmental sustainability goals. Case studies in successful vertical farming, sustainable irrigation, and organic agriculture demonstrate how this innovative instrument can promote economic diversification, protect the environment, and promote social equity.The research offers practical guidance for governments, investors, and stakeholders, highlighting the importance of innovative financial tools in fostering sustainable farming and food stability in the region. Future studies can build on this foundation by investigating the feasibility of Smart Green Sukuk in industries such as renewable energy and waste disposal, assessing the social and economic effects of these instruments, and examining opportunities for international cooperation among Islamic finance organizations to harmonize and advance green investment practices worldwide.","author":[{"family":"Musalman","given":"Abdur"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.30693932","URL":"https://doi.org/10.57945/manara.hbku.30693932","source":"datacite"},{"id":"doi:10.57945/manara.hbku.30477824.v1","type":"article-journal","title":"Empowering syrian refugees through environmental development: a case study in Jordan","abstract":"Jordan is located within a region frequently afflicted by political unrest. This strategic location in the Middle East and its political stability have made it a refugee heaven for decades. Today, the country hosts the second-highest number of refugees per capita in the world, primarily from Syria (World Food Programme, n.d.). Over 1.3 million Syrian refugees have significantly strained Jordan's already fragile environment and socio-economy. The prolonged nature and the number of refugees make exploring sustainable solutions that empower refugees while mitigating the host countries environmental pressures. The study analyzed five ecological initiatives that engage refugees in employment and skill-building. For instance, Oxfam's waste management project has turned the refugee camps' waste into opportunities, creating numerous job opportunities. The Smart DESERT Project, led by the International Union for Conservation of Nature (IUCN), has increased food safety by training Syrian refugees in climate-resilient farming techniques. Meanwhile, the solar power project led by the United Nations High Commissioner for Refugees (UNHCR) has reduced the gender gap by engaging women in home-based businesses. It has also reduced dependency on fossil fuels and firewood. The findings indicate that these projects in Jordan significantly empower Syrian refugees to varying degrees by providing socioeconomic opportunities and skill training. The initiatives acknowledge refugees as valuable partners in development and reduce their reliance on aid. Despite these multidimensional successes, challenges, including funding limitations, restricted market access, and the absence of a binding framework, hinder the sustainability of these projects. This study analyzes the cases using thematic analysis of secondary data resources and the Humanitarian Development Nexus (HDN) framework. Special attention is paid to initiatives targeting women to understand how they promote inclusive development. Based on the findings, recommendations are suggested. For example, these employment opportunities disappear once funding ends. Thus, expanding skills training and capacity-building at the onset of projects is recommended to enable refugees to transition into independent, sustainable careers.","author":[{"family":"Al Rafi","given":"Obydullah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.30477824.v1","URL":"https://doi.org/10.57945/manara.hbku.30477824.v1","source":"datacite"},{"id":"doi:10.57945/manara.hbku.30477824","type":"article-journal","title":"Empowering syrian refugees through environmental development: a case study in Jordan","abstract":"Jordan is located within a region frequently afflicted by political unrest. This strategic location in the Middle East and its political stability have made it a refugee heaven for decades. Today, the country hosts the second-highest number of refugees per capita in the world, primarily from Syria (World Food Programme, n.d.). Over 1.3 million Syrian refugees have significantly strained Jordan's already fragile environment and socio-economy. The prolonged nature and the number of refugees make exploring sustainable solutions that empower refugees while mitigating the host countries environmental pressures. The study analyzed five ecological initiatives that engage refugees in employment and skill-building. For instance, Oxfam's waste management project has turned the refugee camps' waste into opportunities, creating numerous job opportunities. The Smart DESERT Project, led by the International Union for Conservation of Nature (IUCN), has increased food safety by training Syrian refugees in climate-resilient farming techniques. Meanwhile, the solar power project led by the United Nations High Commissioner for Refugees (UNHCR) has reduced the gender gap by engaging women in home-based businesses. It has also reduced dependency on fossil fuels and firewood. The findings indicate that these projects in Jordan significantly empower Syrian refugees to varying degrees by providing socioeconomic opportunities and skill training. The initiatives acknowledge refugees as valuable partners in development and reduce their reliance on aid. Despite these multidimensional successes, challenges, including funding limitations, restricted market access, and the absence of a binding framework, hinder the sustainability of these projects. This study analyzes the cases using thematic analysis of secondary data resources and the Humanitarian Development Nexus (HDN) framework. Special attention is paid to initiatives targeting women to understand how they promote inclusive development. Based on the findings, recommendations are suggested. For example, these employment opportunities disappear once funding ends. Thus, expanding skills training and capacity-building at the onset of projects is recommended to enable refugees to transition into independent, sustainable careers.","author":[{"family":"Al Rafi","given":"Obydullah"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.30477824","URL":"https://doi.org/10.57945/manara.hbku.30477824","source":"datacite"},{"id":"doi:10.57945/manara.hbku.29324528.v1","type":"article-journal","title":"Optimization of Design and Operation of Hydroponic Sprouted Fodder Systems : A New Approach to Feeding Livestock","abstract":"This thesis discusses the challenges faced by countries in maintaining food security due to factors such as population growth, climate change, and resource depletion. To address these challenges, a partial Decision Support System (DSS) is proposed to assist farmers in optimizing their resources and achieving profitability through advanced farming methods known as Hydroponic farming. The study begins with a bibliometric analysis of 1305 articles in smart agriculture, followed by a review of 40 articles focused on harvest planning to identify research gaps and scholarly contributions. Farmers are reluctant to adopt newer and smart farming methods such as Hydroponic farming to their obstacles in terms of high investment and operational cost, and also their scalability. In order to assist farmers, a one stage part of Decision Support System (DSS) is then proposed for optimizing dairy cattle feed management using a mathematical model applied to Hydroponic units. Finally, the study proposes future research directions to benefit the research community based on the insights gained from the study.","author":[{"family":"Yousaf","given":"Arslan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.29324528.v1","URL":"https://doi.org/10.57945/manara.hbku.29324528.v1","source":"datacite"},{"id":"doi:10.57945/manara.hbku.29324528","type":"article-journal","title":"Optimization of Design and Operation of Hydroponic Sprouted Fodder Systems : A New Approach to Feeding Livestock","abstract":"This thesis discusses the challenges faced by countries in maintaining food security due to factors such as population growth, climate change, and resource depletion. To address these challenges, a partial Decision Support System (DSS) is proposed to assist farmers in optimizing their resources and achieving profitability through advanced farming methods known as Hydroponic farming. The study begins with a bibliometric analysis of 1305 articles in smart agriculture, followed by a review of 40 articles focused on harvest planning to identify research gaps and scholarly contributions. Farmers are reluctant to adopt newer and smart farming methods such as Hydroponic farming to their obstacles in terms of high investment and operational cost, and also their scalability. In order to assist farmers, a one stage part of Decision Support System (DSS) is then proposed for optimizing dairy cattle feed management using a mathematical model applied to Hydroponic units. Finally, the study proposes future research directions to benefit the research community based on the insights gained from the study.","author":[{"family":"Yousaf","given":"Arslan"}],"issued":{"date-parts":[[2025]]},"DOI":"10.57945/manara.hbku.29324528","URL":"https://doi.org/10.57945/manara.hbku.29324528","source":"datacite"},{"id":"doi:10.5281/zenodo.18973674","type":"article-journal","title":"CAMERA CALIBRATION BASED DISTANCE ESTIMATION FOR SMART POULTRY MONITORING USING DEEP LEARNING","abstract":"Poultry monitoring plays an important role in modern smart farming systems. Accurate detection and distanceestimation of poultry can help improve automated monitoring, feeding management. This paper presents acomputer vision–based approach for poultry detection and distance estimation using deep learning techniques.In the proposed system, input images are first preprocessed to enhance image quality and reduce noise. Alightweight deep learning model based on MobileNetV2 is then used to detect poultry objects from the inputimages. After detecting the poultry, the bounding box around the object is extracted to measure the width of theobject in pixels. A chessboard calibration method is used to obtain camera parameters required for distanceestimation. Using these parameters and the measured pixel width, the distance between the camera and thepoultry is estimated using a geometric relationship derived from the pinhole camera model. Experimental resultsdemonstrate that the system can successfully detect poultry and estimate the approximate distance between thecamera and the object.","author":[{"family":"Hemawathi Somasundaram","given":"RAMS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18973674","URL":"https://doi.org/10.5281/zenodo.18973674","source":"datacite"},{"id":"doi:10.5281/zenodo.18973675","type":"article-journal","title":"CAMERA CALIBRATION BASED DISTANCE ESTIMATION FOR SMART POULTRY MONITORING USING DEEP LEARNING","abstract":"Poultry monitoring plays an important role in modern smart farming systems. Accurate detection and distanceestimation of poultry can help improve automated monitoring, feeding management. This paper presents acomputer vision–based approach for poultry detection and distance estimation using deep learning techniques.In the proposed system, input images are first preprocessed to enhance image quality and reduce noise. Alightweight deep learning model based on MobileNetV2 is then used to detect poultry objects from the inputimages. After detecting the poultry, the bounding box around the object is extracted to measure the width of theobject in pixels. A chessboard calibration method is used to obtain camera parameters required for distanceestimation. Using these parameters and the measured pixel width, the distance between the camera and thepoultry is estimated using a geometric relationship derived from the pinhole camera model. Experimental resultsdemonstrate that the system can successfully detect poultry and estimate the approximate distance between thecamera and the object.","author":[{"family":"Hemawathi Somasundaram","given":"RAMS"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18973675","URL":"https://doi.org/10.5281/zenodo.18973675","source":"datacite"},{"id":"doi:10.5281/zenodo.18931199","type":"article-journal","title":"IoT-Enabled Precision Irrigation Management Using Soil Moisture Sensor Networks and Machine Learning-Based Evapotranspiration Prediction","abstract":"Irrigated agriculture accounts for approximately 70% of global freshwater withdrawals, yet irrigation water use efficiency in traditional flood irrigation seldom exceeds 40–50%. The convergence of IoT sensor technology, wireless communication, cloud computing, and machine learning presents a transformative opportunity to improve agricultural water use efficiency through real-time precision irrigation management. This study presents the design, implementation, and two-season field validation of an IoT-enabled precision irrigation management system (IoT-PIMS) for rain-fed rice cultivation in semi-arid agro-climatic zones of Telangana, India. The system integrates a wireless sensor network of 144 soil moisture sensors, automated weather stations, LoRaWAN communication, and a cloud-hosted Random Forest ET₀ prediction model trained on 12 years of IMD weather data, with a fuzzy logic irrigation decision engine delivering recommendations via SMS and Android app. Two-season field trials (Kharif 2023 and Rabi 2023–24) across three sites demonstrated: 31.4% water use reduction relative to conventional flood irrigation; paddy yield improvement from 5.21 to 5.84 t/ha; water use efficiency improvement from 0.41 to 0.67 kg grain/m³ (+63.4%); ET₀ prediction RMSE of 0.31 mm/day (NSE=0.89); and system uptime of 97.4%. Farmer perception surveys indicate 84.6% willingness to continue using IoT-PIMS.","author":[{"family":"Padma Reddy Narayanappa","given":"Suryanarayana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18931199","URL":"https://doi.org/10.5281/zenodo.18931199","source":"datacite"},{"id":"doi:10.5281/zenodo.18931200","type":"article-journal","title":"IoT-Enabled Precision Irrigation Management Using Soil Moisture Sensor Networks and Machine Learning-Based Evapotranspiration Prediction","abstract":"Irrigated agriculture accounts for approximately 70% of global freshwater withdrawals, yet irrigation water use efficiency in traditional flood irrigation seldom exceeds 40–50%. The convergence of IoT sensor technology, wireless communication, cloud computing, and machine learning presents a transformative opportunity to improve agricultural water use efficiency through real-time precision irrigation management. This study presents the design, implementation, and two-season field validation of an IoT-enabled precision irrigation management system (IoT-PIMS) for rain-fed rice cultivation in semi-arid agro-climatic zones of Telangana, India. The system integrates a wireless sensor network of 144 soil moisture sensors, automated weather stations, LoRaWAN communication, and a cloud-hosted Random Forest ET₀ prediction model trained on 12 years of IMD weather data, with a fuzzy logic irrigation decision engine delivering recommendations via SMS and Android app. Two-season field trials (Kharif 2023 and Rabi 2023–24) across three sites demonstrated: 31.4% water use reduction relative to conventional flood irrigation; paddy yield improvement from 5.21 to 5.84 t/ha; water use efficiency improvement from 0.41 to 0.67 kg grain/m³ (+63.4%); ET₀ prediction RMSE of 0.31 mm/day (NSE=0.89); and system uptime of 97.4%. Farmer perception surveys indicate 84.6% willingness to continue using IoT-PIMS.","author":[{"family":"Padma Reddy Narayanappa","given":"Suryanarayana"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.18931200","URL":"https://doi.org/10.5281/zenodo.18931200","source":"datacite"},{"id":"doi:10.5281/zenodo.19880101","type":"article-journal","title":"D6.2 Dissemination, communication and exploitation plan and reports","abstract":"The main reference document for communication activities within the Smart Droplets project, providing guidelines for partners to disseminate and exploit results. It includes an action plan detailing planned liaisons with complementary AI, Data, and Robotics initiatives.","author":[{"family":"Vouroutzis","given":"George"},{"family":"Papadopoulou","given":"Marialena"},{"family":"Fotakidis","given":"Dimitris"}],"issued":{"date-parts":[[2023]]},"DOI":"10.5281/zenodo.19880101","URL":"https://doi.org/10.5281/zenodo.19880101","source":"datacite"},{"id":"doi:10.5281/zenodo.19880102","type":"article-journal","title":"D6.2 Dissemination, communication and exploitation plan and reports","abstract":"The main reference document for communication activities within the Smart Droplets project, providing guidelines for partners to disseminate and exploit results. It includes an action plan detailing planned liaisons with complementary AI, Data, and Robotics initiatives.","author":[{"family":"Vouroutzis","given":"George"},{"family":"Papadopoulou","given":"Marialena"},{"family":"Fotakidis","given":"Dimitris"}],"issued":{"date-parts":[[2023]]},"DOI":"10.5281/zenodo.19880102","URL":"https://doi.org/10.5281/zenodo.19880102","source":"datacite"},{"id":"doi:10.5281/zenodo.21414904","type":"article-journal","title":"Urgent Data Transmission in Wireless Sensor Network","abstract":"Paper wireless sensor networks is a growing class of highly dynamic, complex network environment on top of which a wide range of applications, such as habitat monitoring, object tracking, precision agriculture, building monitoring and military systems are built. The real time applications often generate urgent data and one-time event notifications that need to be communicated reliably. The successful delivery of such information has a direct effect on the overall performance of the system. Reliable communication is important for sensor networks. Urgent data transmission has been a serious problem for Wireless sensor networks. WSN face difficulties in handling urgent data like congestion and reliability due to their unique requirements and constraints. Various protocols for congestion avoidance and reliability achievement for WSN have been proposed recently. Few of them have also worked on congestion elimination. These protocols try to minimize the problem using different mechanism. This paper explores these mechanisms and tries to find their features and limitations which directed us for our research.","author":[{"family":"D Karanjawane","given":"Ashwini"},{"family":"W Rohankar","given":"Atul"},{"family":"Mali","given":"SD"},{"family":"Agarkar","given":"AA"}],"issued":{"date-parts":[[2013]]},"DOI":"10.5281/zenodo.21414904","URL":"https://doi.org/10.5281/zenodo.21414904","source":"datacite"},{"id":"doi:10.5281/zenodo.21414905","type":"article-journal","title":"Urgent Data Transmission in Wireless Sensor Network","abstract":"Paper wireless sensor networks is a growing class of highly dynamic, complex network environment on top of which a wide range of applications, such as habitat monitoring, object tracking, precision agriculture, building monitoring and military systems are built. The real time applications often generate urgent data and one-time event notifications that need to be communicated reliably. The successful delivery of such information has a direct effect on the overall performance of the system. Reliable communication is important for sensor networks. Urgent data transmission has been a serious problem for Wireless sensor networks. WSN face difficulties in handling urgent data like congestion and reliability due to their unique requirements and constraints. Various protocols for congestion avoidance and reliability achievement for WSN have been proposed recently. Few of them have also worked on congestion elimination. These protocols try to minimize the problem using different mechanism. This paper explores these mechanisms and tries to find their features and limitations which directed us for our research.","author":[{"family":"D Karanjawane","given":"Ashwini"},{"family":"W Rohankar","given":"Atul"},{"family":"Mali","given":"SD"},{"family":"Agarkar","given":"AA"}],"issued":{"date-parts":[[2013]]},"DOI":"10.5281/zenodo.21414905","URL":"https://doi.org/10.5281/zenodo.21414905","source":"datacite"},{"id":"doi:10.5281/zenodo.21564162","type":"article-journal","title":"Crop Recommendation System to Maximize Crop Yield in Ramtek region using Machine Learning","abstract":"In Indian economy and employment agriculture plays major role. The most common problem faced by the Indian farmers is they do not opt crop based on the necessity of soil, as a result they face serious setback in productivity. This problem can be addressed through precision agriculture. This method takes three parameters into consideration, viz: soil characteristics, soil types and crop yield data collection based on these parameters suggesting the farmer suitable crop to be cultivated. Precision agriculture helps in reduction of non suitable crop which indeed increases productivity, apart from the following advantages like efficacy in input as well as output and better decision making for farming. This method gives solutions like proposing a recommendation system through an ensemble model with majority voting techniques using random tree, CHAID, K _ Nearest Neighbour and Naive Bayes as learner to recommend suitable crop based on soil parameters with high specific accuracy and efficiency. The classified image generated by these techniques consists of ground truth statistical data and parameters of it are weather, crop yield, state and district wise crops to predict the yield of a particular crop under particular weather condition.","author":[{"family":"Reddy","given":"DA"},{"family":"Dadore","given":"Bhagyashri"},{"family":"Watekar","given":"Aarti"}],"issued":{"date-parts":[[2019]]},"DOI":"10.5281/zenodo.21564162","URL":"https://doi.org/10.5281/zenodo.21564162","source":"datacite"},{"id":"doi:10.5281/zenodo.21564163","type":"article-journal","title":"Crop Recommendation System to Maximize Crop Yield in Ramtek region using Machine Learning","abstract":"In Indian economy and employment agriculture plays major role. The most common problem faced by the Indian farmers is they do not opt crop based on the necessity of soil, as a result they face serious setback in productivity. This problem can be addressed through precision agriculture. This method takes three parameters into consideration, viz: soil characteristics, soil types and crop yield data collection based on these parameters suggesting the farmer suitable crop to be cultivated. Precision agriculture helps in reduction of non suitable crop which indeed increases productivity, apart from the following advantages like efficacy in input as well as output and better decision making for farming. This method gives solutions like proposing a recommendation system through an ensemble model with majority voting techniques using random tree, CHAID, K _ Nearest Neighbour and Naive Bayes as learner to recommend suitable crop based on soil parameters with high specific accuracy and efficiency. The classified image generated by these techniques consists of ground truth statistical data and parameters of it are weather, crop yield, state and district wise crops to predict the yield of a particular crop under particular weather condition.","author":[{"family":"Reddy","given":"DA"},{"family":"Dadore","given":"Bhagyashri"},{"family":"Watekar","given":"Aarti"}],"issued":{"date-parts":[[2019]]},"DOI":"10.5281/zenodo.21564163","URL":"https://doi.org/10.5281/zenodo.21564163","source":"datacite"},{"id":"doi:10.7910/dvn/k6jqxc","type":"article-journal","title":"Household Survey Data on Cost Benefit Analysis of Climate-Smart Soil Practices in Western Kenya","abstract":"This household survey was conducted among 88 respondents by CIAT in three counties of western Kenya (Bungoma, Kakamega, and Siaya) in 2016. The main aim of the project was to conduct a cost benefit analysis of eight climate-smart soil (CSS) practices, as a step toward understanding whether they were beneficial or not both from a private and social point of view. This knowledge could then be potentially used to enlighten farmers, policy makers and development practitioners about soil protection and rehabilitation practices that are most cost-effective when implemented on farms. Such knowledge also provides a rationale that can be used as a basis for promoting selected CSS practices. Farm practices were considered as “climate smart” if they could improve the soil-nitrogen cycle, enhance soil fertility, improve crop productivity, improve soil biodiversity, promote soil conservation, increase soil biomass, reduce soil erosion, reduce volatility in crop and livestock production, and reduce water pollution. These practices could, in turn, boost food production, income, and households’ ability to adapt to climate change. Variables collected include: 1) general information about each site, 2) household age, gender, education level, and farming experience, 3) farm activities (without intervention), 4) implemented CSS practices such as the use of improved seeds, agroforestry, inorganic fertilisers, liming, and organic manure socio economic characteristics, and farm output, 5) crop and livestock yields, prices for farm inputs and outputs, the cost of implementing farm activities (both before and after intervention), 7) household financial information and, 8) environmental effects. Identifying variables such household head information, contact details and geographical locations of the households have not been provided in the data but they can be availed upon request.","author":[{"family":"Nganga","given":"Stanley"},{"family":"Mwungu","given":"Chris"},{"family":"Mwongera","given":"Caroline"},{"family":"Kinyua","given":"Ivy"},{"family":"Notenbaert","given":"An"},{"family":"Girvetz","given":"Evan"}],"issued":{"date-parts":[[2017]]},"DOI":"10.7910/dvn/k6jqxc","URL":"https://doi.org/10.7910/dvn/k6jqxc","source":"datacite"},{"id":"doi:10.7910/dvn/hpmkaw","type":"article-journal","title":"Household Survey Data on Nutritional Resilience and Agricultural Shocks Among Arable Farmers in Northern Uganda","abstract":"&lt;p&gt;This household survey was conducted across 322 households in the four sub counties of Nwoya district (Anaka, Alero, Purongo and Kochgoma) in December 2017. This was an end line survey that was conducted as part of the project increasing food security and farming systems resilience through wide scale adoption of climate smart agricultural (CSA) technologies. The main aim for this survey was to link CSA adoption with nutrition and resilience. This knowledge could potentially policy makers and development practitioners about the influence of CSA on nutrition and livelihoods of farmers in Nwoya district. Since CSA technologies as well as dissemination methods are context specific, such knowledge would provide information on promoting the most relevant CSA technologies. That is CSA technologies that have a positive impact on nutrition, resilience and other livelihood indicators.&lt;/p&gt; &lt;p&gt;Types of data collected include: &lt;/p&gt; &lt;ol&gt; &lt;li value=\"1\"&gt;Geographical location of the farmers, &lt;/li&gt; &lt;li&gt;Shocks that affected farmers economically, &lt;/li&gt; &lt;li&gt; Market Access, &lt;/li&gt; &lt;li&gt; Food household basket and food expenditure,&lt;/li&gt; &lt;li&gt; Non-food expenditure,&lt;/li&gt; &lt;li&gt; Food insecurity experience scale,&lt;/li&gt; &lt;li&gt; Food scarcity and seasonality. &lt;/li&gt; &lt;li&gt; Market Access, &lt;/li&gt; &lt;/ol&gt;","author":[{"family":"Mwungu","given":"Chris"},{"family":"Shikuku","given":"Kelvin"},{"family":"Atibo","given":"Christopher"},{"family":"Mwongera","given":"Caroline"}],"issued":{"date-parts":[[2019]]},"DOI":"10.7910/dvn/hpmkaw","URL":"https://doi.org/10.7910/dvn/hpmkaw","source":"datacite"},{"id":"doi:10.7910/dvn/0zexkc","type":"article-journal","title":"Intra-household and farm production decision making survey in rural Tanzania and Uganda","abstract":"This intra-household survey was conducted by CCAFS in Northern Uganda and Southern Tanzania in 2014 and 2015 respectively. The main aim of the project is to increase farm production and farming system resilience of small scale farmers in Uganda and Tanzania while mitigating climate change through wide-scale adoption of climate-smart agriculture (CSA) technologies. Household identification variables including GPS coordinates, names of respondents and household members, phone numbers, and village names have been removed as part of anonymization efforts. This information is, however, available upon request.","author":[{"family":"Winowiecki","given":"Leigh"},{"family":"Mwongera","given":"Caroline"},{"family":"Twyman","given":"Jennifer"},{"family":"Shikuku","given":"Kelvin"},{"family":"Ampaire","given":"Edidah"},{"family":"Mwungu","given":"Chris"},{"family":"Acosta","given":"Mariola"},{"family":"Okolo","given":"Wendy"},{"family":"Läderach","given":"Peter"}],"issued":{"date-parts":[[2016]]},"DOI":"10.7910/dvn/0zexkc","URL":"https://doi.org/10.7910/dvn/0zexkc","source":"datacite"},{"id":"doi:10.34657/394","type":"article-journal","title":"Strategy for the development of a smart NDVI camera system for outdoor plant detection and agricultural embedded systems","abstract":"The application of (smart) cameras for process control, mapping, and advanced imaging in agriculture has become an element of precision farming that facilitates the conservation of fertilizer, pesticides, and machine time. This technique additionally reduces the amount of energy required in terms of fuel. Although research activities have increased in this field, high camera prices reflect low adaptation to applications in all fields of agriculture. Smart, low-cost cameras adapted for agricultural applications can overcome this drawback. The normalized difference vegetation index (NDVI) for each image pixel is an applicable algorithm to discriminate plant information from the soil background enabled by a large difference in the reflectance between the near infrared (NIR) and the red channel optical frequency band. Two aligned charge coupled device (CCD) chips for the red and NIR channel are typically used, but they are expensive because of the precise optical alignment required. Therefore, much attention has been given to the development of alternative camera designs. In this study, the advantage of a smart one-chip camera design with NDVI image performance is demonstrated in terms of low cost and simplified design. The required assembly and pixel modifications are described, and new algorithms for establishing an enhanced NDVI image quality for data processing are discussed.","author":[{"family":"Dworak","given":"Volker"},{"family":"Selbeck","given":"Joern"},{"family":"Dammer","given":"Karl"},{"family":"Hoffmann","given":"Matthias"},{"family":"Zarezadeh","given":"Ali"},{"family":"Bobda","given":"Christophe"}],"issued":{"date-parts":[[2013]]},"DOI":"10.34657/394","URL":"https://doi.org/10.34657/394","source":"datacite"},{"id":"doi:10.14279/depositonce-8553","type":"article-journal","title":"Evaluating system of rice intensification using a modified transplanter: A smart farming solution toward sustainability of paddy fields in Malaysia","abstract":"This paper presents the study reports on evaluating a new transplanting operation by taking into accounts the interactions between soil, plant, and machine in line with the System of Rice Intensification (SRI) practices. The objective was to modify planting claw (kuku-kambing) of a paddy transplanter in compliance with SRI guidelines to determine the best planting spacing (S), seed rate (G) and planting pattern that results in a maximum number of seedling, tillers per hill, and yield. Two separate experiments were carried out in two different paddy fields, one to determine the best planting spacing (S=4 levels: s1=0.16 m×0.3 m, s2= 0.18 m×0.3 m, s3=0.21 m×0.3 m, and s4=0.24 m×0.3 m) for a specific planting pattern (row mat or scattered planting pattern), and the other to determine the best combination of spacing with seed rate treatments (G=2 levels: g1=75 g/tray, and g2= 240 g/tray). Main SRI management practices such as soil characteristics of the sites, planting depth, missing hill, hill population, the number of seedling per hill, and yield components were evaluated. Results of two-way analysis of variance with three replications showed that spacing, planting pattern and seed rate affected the number of one-seedling in all experiment. It was also observed that the increase in spacing resulted in more tillers and more panicle per plant, however hill population and sterility ratio increased with the decrease in spacing. While the maximum number of panicles were resulted from scattered planting at s4=0.24 m×0.3 m spacing with the seed rate of g1=75 g/tray, the maximum number of one seedling were observed at s4=0.16 m×0.3 m. The highest and lowest yields were obtained from 75 g seeds per tray scattered and 70 g seeds per tray scattered treatment respectively. For all treatments, the result clearly indicates an increase in yield with an increase in spacing.","author":[{"family":"Shamshiri","given":"Redmond"},{"family":"Ibrahim","given":"Bala"},{"family":"Balasundram","given":"Siva"},{"family":"Taheri","given":"Sima"},{"family":"Weltzien","given":"Cornelia"}],"issued":{"date-parts":[[2019]]},"DOI":"10.14279/depositonce-8553","URL":"https://doi.org/10.14279/depositonce-8553","source":"datacite"},{"id":"doi:10.6084/m9.figshare.5793300.v1","type":"article-journal","title":"Additional file 1: of Cropping practices manipulate abundance patterns of root and soil microbiome members paving the way to smart farming","abstract":"A PDF containing supplementary methods, results, discussion, references, figures and tables. The Supplementary Methods contain the details about the chemical soil analysis, PCR setup, library preparation and sequencing. The Supplementary Results comprise the global taxonomic profiles of soil and root bacterial and fungal communities and the taxonomic patterns of csOTUs. We discuss the cropping system effects on soil microbial communities and on microbial α-diversity in the Supplementary Discussion. Supplementary Figures: Figure S1. - Experimental layout of the FAST experiment. Figure S2. - Graphical overview of data analysis. Figure S3. - Taxonomic profiles at phylum level. Figure S4. - Unconstrained PCoA ordinations. Figure S5. - Rarefaction curves. Figure S6. - Defining cropping sensitive bacteria and fungi in soil and root samples. Figure S7. and Figure S8. - Mean relative abundances of cropping sensitive OTUs at phylum and OTU level, respectively. Figure S9. - Abundant cropping sensitive bacteria bOTUs in soil. Figure S10. - Abundant cropping sensitive fungi fOTUs in soil. Figure S11. - Abundant cropping sensitive bacteria bOTUs in roots. Figure S12. - Abundant cropping sensitive fungi fOTUs in roots. Figure S13. - Separate co-occurrence networks of bacteria and fungi in soil and root samples. Figure S14. - Defining modules in root and soil networks. Supplementary Tables: Table S1. - PCR cycling conditions. Table S2. - PERMANOVA results for testing the effects of Block, Sample type and Cropping System. Table S3. - Statistic results testing for differences in α-diversity. Table S4. - PERMANOVA results testing the effects of Block and Cropping System on bacterial and fungal communities in soil and root samples. Table S5. - Characteristics of keystone OTUs. (PDF 2862 kb)","author":[{"family":"Hartman","given":"Kyle"},{"family":"Van Der Heijden","given":"Marcel"},{"family":"Wittwer","given":"Raphaël"},{"family":"Banerjee","given":"Samiran"},{"family":"Walser","given":"Jean"},{"family":"Schlaeppi","given":"Klaus"}],"issued":{"date-parts":[[2018]]},"DOI":"10.6084/m9.figshare.5793300.v1","URL":"https://doi.org/10.6084/m9.figshare.5793300.v1","source":"datacite"},{"id":"doi:10.6084/m9.figshare.5793300","type":"article-journal","title":"Additional file 1: of Cropping practices manipulate abundance patterns of root and soil microbiome members paving the way to smart farming","abstract":"A PDF containing supplementary methods, results, discussion, references, figures and tables. The Supplementary Methods contain the details about the chemical soil analysis, PCR setup, library preparation and sequencing. The Supplementary Results comprise the global taxonomic profiles of soil and root bacterial and fungal communities and the taxonomic patterns of csOTUs. We discuss the cropping system effects on soil microbial communities and on microbial α-diversity in the Supplementary Discussion. Supplementary Figures: Figure S1. - Experimental layout of the FAST experiment. Figure S2. - Graphical overview of data analysis. Figure S3. - Taxonomic profiles at phylum level. Figure S4. - Unconstrained PCoA ordinations. Figure S5. - Rarefaction curves. Figure S6. - Defining cropping sensitive bacteria and fungi in soil and root samples. Figure S7. and Figure S8. - Mean relative abundances of cropping sensitive OTUs at phylum and OTU level, respectively. Figure S9. - Abundant cropping sensitive bacteria bOTUs in soil. Figure S10. - Abundant cropping sensitive fungi fOTUs in soil. Figure S11. - Abundant cropping sensitive bacteria bOTUs in roots. Figure S12. - Abundant cropping sensitive fungi fOTUs in roots. Figure S13. - Separate co-occurrence networks of bacteria and fungi in soil and root samples. Figure S14. - Defining modules in root and soil networks. Supplementary Tables: Table S1. - PCR cycling conditions. Table S2. - PERMANOVA results for testing the effects of Block, Sample type and Cropping System. Table S3. - Statistic results testing for differences in α-diversity. Table S4. - PERMANOVA results testing the effects of Block and Cropping System on bacterial and fungal communities in soil and root samples. Table S5. - Characteristics of keystone OTUs. (PDF 2862 kb)","author":[{"family":"Hartman","given":"Kyle"},{"family":"Van Der Heijden","given":"Marcel"},{"family":"Wittwer","given":"Raphaël"},{"family":"Banerjee","given":"Samiran"},{"family":"Walser","given":"Jean"},{"family":"Schlaeppi","given":"Klaus"}],"issued":{"date-parts":[[2018]]},"DOI":"10.6084/m9.figshare.5793300","URL":"https://doi.org/10.6084/m9.figshare.5793300","source":"datacite"},{"id":"doi:10.5281/zenodo.18951688","type":"article-journal","title":"Climate-Smart Agriculture in Ethiopian Wheat Zones: A Two-Year Yield Variability Analysis","abstract":"Agricultural productivity in Ethiopia's southern wheat-growing zones is influenced by climate variability, necessitating the adoption of climate-smart agricultural practices. The study employed ethnographic methods to document farmers' perceptions and practices related to climate-smart agriculture, focusing on wheat cultivation in six villages across four districts. Over two growing seasons, there was a consistent trend towards higher yields (up to 15% increase) when farmers adopted recommended crop management techniques, such as improved irrigation and fertilization strategies. The findings suggest that climate-smart agricultural practices can significantly enhance wheat yield stability in the studied regions, providing economic benefits for farmers. Farmers should be encouraged to integrate these climate-smart agriculture methods into their farming systems to mitigate risks associated with climate change and improve overall productivity. climate-smart agriculture, wheat cultivation, yield variability, ethnography, Ethiopian agricultural practices","author":[{"family":"Woldehanna","given":"Mekuria"},{"family":"Gebregiorgis","given":"Wolde"},{"family":"Tekle","given":"Seyoum"},{"family":"Tesema","given":"Gebru"}],"issued":{"date-parts":[[2012]]},"DOI":"10.5281/zenodo.18951688","URL":"https://doi.org/10.5281/zenodo.18951688","source":"datacite"},{"id":"doi:10.5281/zenodo.18951689","type":"article-journal","title":"Climate-Smart Agriculture in Ethiopian Wheat Zones: A Two-Year Yield Variability Analysis","abstract":"Agricultural productivity in Ethiopia's southern wheat-growing zones is influenced by climate variability, necessitating the adoption of climate-smart agricultural practices. The study employed ethnographic methods to document farmers' perceptions and practices related to climate-smart agriculture, focusing on wheat cultivation in six villages across four districts. Over two growing seasons, there was a consistent trend towards higher yields (up to 15% increase) when farmers adopted recommended crop management techniques, such as improved irrigation and fertilization strategies. The findings suggest that climate-smart agricultural practices can significantly enhance wheat yield stability in the studied regions, providing economic benefits for farmers. Farmers should be encouraged to integrate these climate-smart agriculture methods into their farming systems to mitigate risks associated with climate change and improve overall productivity. climate-smart agriculture, wheat cultivation, yield variability, ethnography, Ethiopian agricultural practices","author":[{"family":"Woldehanna","given":"Mekuria"},{"family":"Gebregiorgis","given":"Wolde"},{"family":"Tekle","given":"Seyoum"},{"family":"Tesema","given":"Gebru"}],"issued":{"date-parts":[[2012]]},"DOI":"10.5281/zenodo.18951689","URL":"https://doi.org/10.5281/zenodo.18951689","source":"datacite"},{"id":"doi:10.5281/zenodo.18924087","type":"article-journal","title":"Seasonal Implementation and Evaluation of Climate-Smart Agriculture Practices by Maize Farmers in Semi-Arid Kenya,","abstract":"Climate-smart agriculture (CSA) practices are being implemented to enhance agricultural productivity in semi-arid regions of Kenya, particularly among maize farmers facing increasing climate variability. Qualitative data were collected through structured interviews with a sample of maize farmers from three semi-arid counties, focusing on their perceptions and experiences during different seasons. Farmers reported significant improvements in crop yields (up to 30%) when implementing CSA practices tailored for the dry season, compared to traditional farming methods. The study concludes that seasonal implementation of CSA practices can substantially enhance maize production in semi-arid Kenya, with noticeable yield increases observed during specific seasons. Local extension services should promote targeted CSA interventions for different seasons to maximise benefits and address the unique challenges faced by farmers. Climate-Smart Agriculture, Maize Farmers, Semi-Arid Kenya, Seasonal Implementation","author":[{"family":"Mutai","given":"Githinji"},{"family":"Nyaga","given":"Kibet"},{"family":"Mativo","given":"Ojwang"}],"issued":{"date-parts":[[2011]]},"DOI":"10.5281/zenodo.18924087","URL":"https://doi.org/10.5281/zenodo.18924087","source":"datacite"},{"id":"doi:10.5281/zenodo.18924088","type":"article-journal","title":"Seasonal Implementation and Evaluation of Climate-Smart Agriculture Practices by Maize Farmers in Semi-Arid Kenya,","abstract":"Climate-smart agriculture (CSA) practices are being implemented to enhance agricultural productivity in semi-arid regions of Kenya, particularly among maize farmers facing increasing climate variability. Qualitative data were collected through structured interviews with a sample of maize farmers from three semi-arid counties, focusing on their perceptions and experiences during different seasons. Farmers reported significant improvements in crop yields (up to 30%) when implementing CSA practices tailored for the dry season, compared to traditional farming methods. The study concludes that seasonal implementation of CSA practices can substantially enhance maize production in semi-arid Kenya, with noticeable yield increases observed during specific seasons. Local extension services should promote targeted CSA interventions for different seasons to maximise benefits and address the unique challenges faced by farmers. Climate-Smart Agriculture, Maize Farmers, Semi-Arid Kenya, Seasonal Implementation","author":[{"family":"Mutai","given":"Githinji"},{"family":"Nyaga","given":"Kibet"},{"family":"Mativo","given":"Ojwang"}],"issued":{"date-parts":[[2011]]},"DOI":"10.5281/zenodo.18924088","URL":"https://doi.org/10.5281/zenodo.18924088","source":"datacite"},{"id":"doi:10.5281/zenodo.18914988","type":"article-journal","title":"Evaluating Technological Uptake in Smart Agriculture Among Smallholder Farmers in Northern Nigerian Villages: Dynamics and Economic Performance Six Months On","abstract":"The adoption of smart agriculture technologies among smallholder farmers in northern Nigerian villages is a growing area of interest due to its potential to enhance productivity and profitability. A mixed-methods approach combining qualitative interviews with quantitative data analysis was employed to assess farmers' perceptions and actual usage patterns post-intervention. Smart agriculture technologies were adopted at a moderate rate (45%) by smallholder farmers, with significant variance in uptake between different socio-economic groups. The study highlights the importance of tailored training programmes and supportive policies to facilitate wider technology adoption and sustainable economic benefits for farmers. Farmers' needs should be prioritised through ongoing engagement and infrastructure support, while policymakers must consider incentives that encourage tech investment in agriculture.","author":[{"family":"Salihu","given":"Usman"},{"family":"Abdullahi","given":"Gambo"},{"family":"Musa","given":"Abubakar"}],"issued":{"date-parts":[[2010]]},"DOI":"10.5281/zenodo.18914988","URL":"https://doi.org/10.5281/zenodo.18914988","source":"datacite"},{"id":"doi:10.5281/zenodo.18914989","type":"article-journal","title":"Evaluating Technological Uptake in Smart Agriculture Among Smallholder Farmers in Northern Nigerian Villages: Dynamics and Economic Performance Six Months On","abstract":"The adoption of smart agriculture technologies among smallholder farmers in northern Nigerian villages is a growing area of interest due to its potential to enhance productivity and profitability. A mixed-methods approach combining qualitative interviews with quantitative data analysis was employed to assess farmers' perceptions and actual usage patterns post-intervention. Smart agriculture technologies were adopted at a moderate rate (45%) by smallholder farmers, with significant variance in uptake between different socio-economic groups. The study highlights the importance of tailored training programmes and supportive policies to facilitate wider technology adoption and sustainable economic benefits for farmers. Farmers' needs should be prioritised through ongoing engagement and infrastructure support, while policymakers must consider incentives that encourage tech investment in agriculture.","author":[{"family":"Salihu","given":"Usman"},{"family":"Abdullahi","given":"Gambo"},{"family":"Musa","given":"Abubakar"}],"issued":{"date-parts":[[2010]]},"DOI":"10.5281/zenodo.18914989","URL":"https://doi.org/10.5281/zenodo.18914989","source":"datacite"},{"id":"doi:10.5281/zenodo.18898853","type":"article-journal","title":"Climate Shock Resilience in Zimbabwe's Agricultural Supply Chains: A Scholarly Review of Recent Literature","abstract":"Climate shocks have increasingly affected agricultural supply chains in Zimbabwe, necessitating a review of resilience strategies. The review synthesizes empirical studies using critical analysis and thematic synthesis methods. Recent research highlights the vulnerability of smallholder farmers to erratic rainfall patterns, with a notable proportion experiencing yield losses exceeding 30% during droughts. Current literature emphasizes the need for diversified farming practices and improved infrastructure to enhance resilience against climate shocks in Zimbabwe's agricultural sector. The review suggests integrating climate-smart agriculture initiatives into existing policies, alongside enhanced insurance schemes and early warning systems.","author":[{"family":"Nyagwedza","given":"Mangwana"},{"family":"Mabvuto","given":"Chisweni"},{"family":"Katsanda","given":"Musore"}],"issued":{"date-parts":[[2009]]},"DOI":"10.5281/zenodo.18898853","URL":"https://doi.org/10.5281/zenodo.18898853","source":"datacite"},{"id":"doi:10.5281/zenodo.18898854","type":"article-journal","title":"Climate Shock Resilience in Zimbabwe's Agricultural Supply Chains: A Scholarly Review of Recent Literature","abstract":"Climate shocks have increasingly affected agricultural supply chains in Zimbabwe, necessitating a review of resilience strategies. The review synthesizes empirical studies using critical analysis and thematic synthesis methods. Recent research highlights the vulnerability of smallholder farmers to erratic rainfall patterns, with a notable proportion experiencing yield losses exceeding 30% during droughts. Current literature emphasizes the need for diversified farming practices and improved infrastructure to enhance resilience against climate shocks in Zimbabwe's agricultural sector. The review suggests integrating climate-smart agriculture initiatives into existing policies, alongside enhanced insurance schemes and early warning systems.","author":[{"family":"Nyagwedza","given":"Mangwana"},{"family":"Mabvuto","given":"Chisweni"},{"family":"Katsanda","given":"Musore"}],"issued":{"date-parts":[[2009]]},"DOI":"10.5281/zenodo.18898854","URL":"https://doi.org/10.5281/zenodo.18898854","source":"datacite"},{"id":"doi:10.5281/zenodo.18881766","type":"article-journal","title":"Urban Farming Communities' Adoption Rates of Smart Agriculture Technologies in Lagos, Nigeria: Performance Evaluations","abstract":"Urban farming in Lagos, Nigeria has gained prominence as a sustainable solution to food security challenges. Smart agriculture technologies offer potential solutions for enhancing productivity and efficiency. A mixed-methods approach was employed, including a survey questionnaire distributed to 200 urban farmers across various locations in Lagos. Quantitative data were analysed using descriptive statistics. The survey revealed that 78% of respondents adopted at least one smart agriculture technology, with drip irrigation systems being the most popular among them (35%). Urban farming communities in Lagos show a significant interest and initial success in adopting smart agriculture technologies. Further research is recommended to explore long-term impacts. Investment in infrastructure for smart agriculture should be prioritised, alongside educational programmes on technology usage among urban farmers. urban farming, Lagos, smart agriculture, adoption rates, performance outcomes","author":[{"family":"Obinzeiji","given":"Obiakọ"},{"family":"Nkechi","given":"Nkwo"},{"family":"Chukwuma","given":"Chinedu"},{"family":"Edemah","given":"Ejiije"}],"issued":{"date-parts":[[2008]]},"DOI":"10.5281/zenodo.18881766","URL":"https://doi.org/10.5281/zenodo.18881766","source":"datacite"},{"id":"doi:10.5281/zenodo.18881767","type":"article-journal","title":"Urban Farming Communities' Adoption Rates of Smart Agriculture Technologies in Lagos, Nigeria: Performance Evaluations","abstract":"Urban farming in Lagos, Nigeria has gained prominence as a sustainable solution to food security challenges. Smart agriculture technologies offer potential solutions for enhancing productivity and efficiency. A mixed-methods approach was employed, including a survey questionnaire distributed to 200 urban farmers across various locations in Lagos. Quantitative data were analysed using descriptive statistics. The survey revealed that 78% of respondents adopted at least one smart agriculture technology, with drip irrigation systems being the most popular among them (35%). Urban farming communities in Lagos show a significant interest and initial success in adopting smart agriculture technologies. Further research is recommended to explore long-term impacts. Investment in infrastructure for smart agriculture should be prioritised, alongside educational programmes on technology usage among urban farmers. urban farming, Lagos, smart agriculture, adoption rates, performance outcomes","author":[{"family":"Obinzeiji","given":"Obiakọ"},{"family":"Nkechi","given":"Nkwo"},{"family":"Chukwuma","given":"Chinedu"},{"family":"Edemah","given":"Ejiije"}],"issued":{"date-parts":[[2008]]},"DOI":"10.5281/zenodo.18881767","URL":"https://doi.org/10.5281/zenodo.18881767","source":"datacite"},{"id":"doi:10.5281/zenodo.1090754","type":"article-journal","title":"Identification Of An Unstable Nonlinear System: Quadrotor","abstract":"In the following article we begin from a multi-parameter unstable nonlinear model of a Quadrotor. We design a control to stabilize and assure the attitude of the device, starting off a linearized system at the equilibrium point of the null angles of Euler (hover), which provides us a control with limited capacities at small angles of rotation of the vehicle in three dimensions. In order to clear this obstacle, we propose the identification of models in different angles by means of simulations and the design of a controller specifically implemented for the identification task, that in future works will allow the development of controllers according to fast and agile angles of Euler for Quadrotor.","author":[{"family":"Pena","given":"Mauricio"},{"family":"Luna","given":"Adriana"},{"family":"Rodrıguez","given":"Carol"}],"issued":{"date-parts":[[2014]]},"DOI":"10.5281/zenodo.1090754","URL":"https://doi.org/10.5281/zenodo.1090754","source":"datacite"},{"id":"doi:10.5281/zenodo.1090755","type":"article-journal","title":"Identification Of An Unstable Nonlinear System: Quadrotor","abstract":"In the following article we begin from a multi-parameter unstable nonlinear model of a Quadrotor. We design a control to stabilize and assure the attitude of the device, starting off a linearized system at the equilibrium point of the null angles of Euler (hover), which provides us a control with limited capacities at small angles of rotation of the vehicle in three dimensions. In order to clear this obstacle, we propose the identification of models in different angles by means of simulations and the design of a controller specifically implemented for the identification task, that in future works will allow the development of controllers according to fast and agile angles of Euler for Quadrotor.","author":[{"family":"Pena","given":"Mauricio"},{"family":"Luna","given":"Adriana"},{"family":"Rodrıguez","given":"Carol"}],"issued":{"date-parts":[[2014]]},"DOI":"10.5281/zenodo.1090755","URL":"https://doi.org/10.5281/zenodo.1090755","source":"datacite"},{"id":"doi:10.6084/m9.figshare.7074860.v1","type":"article-journal","title":"G2F NIFA FACT Workshop: High Throughput, Field-based Phenotyping Technologies for the Genomes to Fields (G2F) Initiative","abstract":"The U.S. has long played a leading role in developing advanced agricultural technology. We must continue to develop novel approaches to increase the production of food, fiber and fuel while protecting our natural resources and ensuring an economically vibrant agriculture sector. The Genomes to Fields (G2F) Initiative strives to take advantage of new technologies to improve the productivity and stability of maize. In particular, this initiative seeks to connect advances in our understanding of crop genomes with new robotics, high-throughput sensing technologies, and other data gathering devices to understand how plant traits are influenced by genetics and the environment with a long-term aim of developing crops that will exhibit sustainable enhanced productivity across diverse sets of environments and years. In January 2018, G2F hosted a meeting in Ames, Iowa to consider trajectories for research in field-based phenotyping and how best to support those trajectories, and informing USDA NIFA and other federal agencies of our findings and conclusions. For four years, a distributed network of G2F field sites and public-sector collaborators has been generating the data needed to develop predictive models. Generating a vibrant community of researchers from diverse disciplines including the breadth of the plant sciences (e.g., genetics, agronomy, physiology, modeling, and breeding), engineering, computational sciences, and climatology is critical to the full success of the initiative. Many topics were discussed over the course of the three-day workshop, but four themes emerged as areas ripe for focused effort in the coming years: (1) support for ongoing community experiments; (2) development and use of field sensors and plant imaging platforms, (3) creation of data management, sharing, and analytics platforms especially for making effective use of large scale image sets, and (4) engaging additional scientific disciplines in G2F and training the next generation of agricultural scientists. It was suggested that these topics were of interest to advance not only the goals of the G2F initiative, but also the field of predictive plant phenomics more generally. The group supported the idea to enhance coordination efforts across all four themes by designating and/or creating a number of (5) High-Intensity Phenotyping Sites (HIPS) where individualized research areas and local expertise could develop alongside intentional, coordinated linkages focused on advancing topics within the four shared themes. While community experiments are necessarily extensive, these HIPS experiments can be embedded within the G2F testing network and allow for more intensive investigation and development of predictive phenomics tools. Tools and learnings from the HIPS could then be deployed more broadly.","author":[{"family":"Lawrence-Dill","given":"Carolyn"},{"family":"Schnable","given":"Patrick"},{"family":"Springer","given":"Nathan"},{"family":"Leon","given":"Natalia"},{"family":"Edwards","given":"Jode"},{"family":"Ertl","given":"David"},{"family":"Kaeppler","given":"Shawn"},{"family":"Lauter","given":"Nick"},{"family":"Mckay","given":"John"},{"family":"Munoz-Arriola","given":"Francisco"},{"family":"Murray","given":"Seth"},{"family":"Pauli","given":"Duke"},{"family":"Cruzato","given":"Nathalia"},{"family":"Ratcliff","given":"Colby"},{"family":"Schnable","given":"James"},{"family":"Silverstein","given":"Kevin"},{"family":"Spalding","given":"Edgar"},{"family":"Thompson","given":"Addie"},{"family":"Swanson-Wagner","given":"Ruth"},{"family":"Wallace","given":"Jason"},{"family":"Walley","given":"Justin"},{"family":"Yu","given":"Jianming"}],"issued":{"date-parts":[[2018]]},"DOI":"10.6084/m9.figshare.7074860.v1","URL":"https://doi.org/10.6084/m9.figshare.7074860.v1","source":"datacite"},{"id":"doi:10.22004/ag.econ.296492","type":"article-journal","title":"The impact of swarm robotics on arable farm size and structure in the UK","abstract":"Swarm robotics has the potential to radically change the economies of size in agriculture and this will impact farm size and structure in the UK. This study uses a systematic review of the economics of agricultural robotics literature, data from the Hands Free Hectare (HFH) demonstration project which showed the technical feasibility of robotic grain production, and farm-level linear programming (LP) to estimate changes in the average cost curve for wheat and oilseed rape from swarm robotics. The study shows that robotic grain production is technically and economically feasible. A preliminary analysis suggests that robotic production allows medium size farms to approach minimum per unit production cost levels and that the UK costs of production can compete with imported grain. The ability to achieve minimum production costs at relatively small farm size means that the pressure to “get big or get out” will diminish. Costs of production that are internationally competitive will mean reduced need for government subsidies and greater independence for farmers. The ability of swarm robotics to achieve minimum production costs even on small, irregularly shaped fields will reduce pressure to tear out hedges, cut infield trees and enlarge fields.","author":[{"family":"Lowenberg-Deboer","given":"James"},{"family":"Behrendt","given":"Karl"},{"family":"Godwin","given":"Richard"},{"family":"Franklin","given":"Kit"},{"family":"Lowenberg-Deboer","given":"James"},{"family":"Behrendt","given":"Karl"},{"family":"Godwin","given":"Richard"},{"family":"Franklin","given":"Kit"}],"issued":{"date-parts":[[2019]]},"DOI":"10.22004/ag.econ.296492","URL":"https://doi.org/10.22004/ag.econ.296492","source":"datacite"},{"id":"doi:10.22004/ag.econ.262351","type":"article-journal","title":"Stakeholders involvement on establishing public-private partnerships through innovation in agricultural mechanization: a case study","abstract":"Agricultural production has to increase drastically for the next years in order to meet societies' needs. At the same time, using sustainable ways to produce this huge amount of food and resources is becoming increasingly critical. Innovation, both in technologies and in uses/ practices, is strongly encouraged in Europe as a solution to these challenges. As this process remains very complex to manage, analysing it in real conditions seems crucial, especially to improve it. Then, in this paper, we will present and analyse an experimental Public-Private Partnerships Action launched at the European level. This one-year action aimed to gather together all the players involved at the European level for crop protection and to boost concrete innovation in ICT (Information and communication technology) to reduce the use of pesticides, especially around three types of technologies using ICT and robotics. For small and medium-sized enterprises, the particular area of agricultural machinery, solutions have to be found to offset the necessary confidentiality of private stakeholders' interests, and also to give them some reassurance, or at least advantages, on the results of such partnerships.","author":[{"family":"Wermeille","given":"A"},{"family":"Chanet","given":"JP"},{"family":"Berducat","given":"M"},{"family":"Didelot","given":"D"},{"family":"Wermeille","given":"A"},{"family":"Chanet","given":"JP"},{"family":"Berducat","given":"M"},{"family":"Didelot","given":"D"}],"issued":{"date-parts":[[2015]]},"DOI":"10.22004/ag.econ.262351","URL":"https://doi.org/10.22004/ag.econ.262351","source":"datacite"},{"id":"doi:10.24411/0131-5226-2019-10144","type":"article-journal","title":"Цифровые технологии обеспечения экологической безопасности сельскохозяйственного производства","abstract":"В Институте агроинженерных и экологических проблем сельскохозяйственного производства (ИАЭП) филиале ФГБНУ ФНАЦ ВИМ (г. Санкт-Петербург-Пушкин) 6 декабря 2018 года проведена секция 6 «Цифровые технологии обеспечения экологической безопасности сельскохозяйственного производства» Международной научно-технической конференции «Цифровые технологии и роботизированные технические средства для сельского хозяйства» (организатор ФГБНУ ФНАЦ ВИМ). На заседании секции были доложены результаты более 20 работ по тематике секции. В статье приведены основные результаты работ ИАЭП, научных и производс��венных организаций с которыми институт сотрудничает по созданию цифровых технологий обеспечения экологической безопасности сельскохозяйственного производства. Направления работ: экологические проблемы сельскохозяйственного производства, методы их решения; методы разработки и реализации цифровых технологий; цифровые технологии и технические средства их осуществления; нетрадиционная энергетика в цифровых технологиях. Анализ результатов завершенных и поисковых работ свидетельствует о больших потенциальных возможностях ИАЭП и сотрудничающих с нами научных и производственных организаций в области разработки цифровых технологий. Организация научных исследований по программе «Цифровое сельское хозяйство (Умное сельское хозяйство)» требует создания условий для плодотворного междисциплинарного сотрудничества в решении наиболее острых проблем развития АПК России, в том числе проблем обеспечения экологической безопасности. Материалы конференции являются подтверждением возможности и целесообразности междисциплинарного сотрудничества, начало которого положено ИАЭП.","author":[{"family":"Аю","given":"Брюханов"},{"family":"Вн","given":"Судаченко"},{"family":"Аф","given":"Эрк"}],"issued":{"date-parts":[[2019]]},"DOI":"10.24411/0131-5226-2019-10144","URL":"https://doi.org/10.24411/0131-5226-2019-10144","source":"datacite"},{"id":"doi:10.24411/0131-5226-2018-10091","type":"article-journal","title":"Анализ применения автоматизированных и роботизированных комплексов в сельском хозяйстве","abstract":"Количество сельскохозяйственных роботов ежегодно увеличивается на фоне интенсификации производства сельскохозяйственной продукции. Развитие сельскохозяйственной робототехники обеспечивает снижение трудозатрат, а, следовательно, и риски производства, связанные с человеческим фактором. На сегодняшний день наиболее актуальны роботы способные выполнять трудоемкие операции при производстве сельскохозяйственной продукции, но, по дальнейшим прогнозам, планируется проектирование и строительство сельскохозяйственных предприятий, полностью роботизированных без присутствия человека. В связи с этим ежегодно растет производство роботов и роботизированных устройств для аграрного сектора России. Данный показатель в 2017 году составил 73 тысячи единиц с прогнозируемым на 2024 год ростом в восемь раз и численным показателем 595 тысяч единиц, соответственно. Наибольшее количество роботов задействовано при производстве молока крупного рогатого скота 55%, на втором месте находятся роботы для других животноводческих ферм 22%, далее следуют роботы по уходу за посевами 11%, доля роботов для почвообработки составляет 7% и 5 % приходится на роботов, задействованных при уборке урожая. На основе анализа существующих сельскохозяйственных роботов проведена их классификация, учитывающая отрасль работы робота, характер его перемещения, тип управления и специализацию агробота. Проведенные исследования позволили определить перспективные направления в сфере сельскохозяйственной робототехники, а именно: выкармливание поросят сосунов, создание интеллектуальных систем изменения и управления производственной площадью станков свиноводческих предприятий, разработки роботизированных систем корректировки рациона животных и птиц в зависимости от их физиологического состояния, а также создание роботизированных технологических модулей для мелкотоварных сельхозпроизводителей, позволяющих производить конкурентоспособную и экологически безопасную продукцию.","author":[{"family":"Плаксин","given":"ИЕ"},{"family":"Трифанов","given":"АВ"},{"family":"Плаксин","given":"СИ"}],"issued":{"date-parts":[[2018]]},"DOI":"10.24411/0131-5226-2018-10091","URL":"https://doi.org/10.24411/0131-5226-2018-10091","source":"datacite"},{"id":"doi:10.24411/2413-046x-2018-14029","type":"article-journal","title":"Целесообразность использования робототехники в сельском хозяйстве","abstract":"Роботизация сельского хозяйстве должна осуществляться с учетом различных факторов – технических, технологических, организационных и социальных, характеризующих соответствующие процессы аграрного производства. Дело в том, что организации сельского хозяйства функционируют в совершенно разных условиях. Предлагается методика разносторонней оценки целесообразности роботизации производства сельскохозяйственных организаций. Предполагается, что на первом этапе осуществляется определение наиболее значимых факторов, влияющих на внедрение и использование робототехники. Далее эксперты осуществляют оценку значения каждого из данных факторов. Предварительный отбор завершается определением предпочтений для использования той или иной робототехники на рабочих местах. Методика определения целесообразности использования робототехники протестирована в сельскохозяйственных организациях. Использование ее позволяет повысить обоснованность решений по роботизации сельскохозяйственных организаций.","author":[{"family":"Иннокентьевич","given":"Набоков"},{"family":"Викторович","given":"Некрасов"},{"family":"Артёмович","given":"Скворцов"}],"issued":{"date-parts":[[2018]]},"DOI":"10.24411/2413-046x-2018-14029","URL":"https://doi.org/10.24411/2413-046x-2018-14029","source":"datacite"},{"id":"oa:W2056872149","type":"article-journal","title":"Detection of aquifer system compaction and land subsidence using interferometric synthetic aperture radar, Antelope Valley, Mojave Desert, California","abstract":"Interferometric synthetic aperture radar (InSAR) has great potential to detect and quantify land subsidence caused by aquifer system compaction. InSAR maps with high spatial detail and resolution of range displacement (±10 mm in change of land surface elevation) were developed for a groundwater basin (∼10 3 km 2 ) in Antelope Valley, California, using radar data collected from the ERS‐1 satellite. These data allow comprehensive comparison between recent (1993–1995) subsidence patterns and those detected historically (1926–1992) by more traditional methods. The changed subsidence patterns are generally compatible with recent shifts in land and water use. The InSAR‐detected patterns are generally consistent with predictions based on a coupled model of groundwater flow and aquifer system compaction. The minor inconsistencies may reflect our imperfect knowledge of the distribution and properties of compressible sediments. When used in conjunction with coincident measurements of groundwater levels and other geologic information, InSAR data may be useful for constraining parameter estimates in simulations of aquifer system compaction.","author":[{"family":"Galloway","given":"Devin"},{"family":"Hudnut","given":"KW"},{"family":"Ingebritsen","given":"SE"},{"family":"Phillips","given":"Steven"},{"family":"Peltzer","given":"G"},{"family":"Rogez","given":"F"},{"family":"Rosen","given":"PA"}],"issued":{"date-parts":[[1998]]},"DOI":"10.1029/98wr01285","URL":"https://doi.org/10.1029/98wr01285","source":"openalex"},{"id":"doi:10.3920/9789086867783_098","type":"article-journal","title":"Precision analysis of the effect of ephemeral gully erosion on vine vigour using NDVI images","abstract":"The aim of this study was to evaluate the effect of ephemeral gully erosion on vine vigour. The vine vigour was estimated through the Normalized Difference Vegetation Index (NDVI) derived from a detailed multispectral aerial image acquired August 11, 2010. An analysis of variance and a Duncan’s multiple range test was performed to compare NDVI values in areas around the axis of gully incision and in control areas not affected by gullies. The soil eroded volume was measured from a 0.1 m resolution digital elevation model acquired by an unmanned aerial vehicle (UAV) on May 07, 2012. The results demonstrate the utility of multispectral images to determine the area affected by gully erosion in vineyards, as well as of the digital elevation models derived from UAVs for precision conservation projects.","author":[{"family":"Martínez-Casasnovas","given":"JA"},{"family":"Ramos","given":"MC"},{"family":"Balasch","given":"C"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086867783_098","URL":"https://doi.org/10.3920/9789086867783_098","source":"crossref"},{"id":"doi:10.1007/s11119-023-09995-7","type":"article-journal","title":"Within-field yield stability and gross margin variations across corn fields and implications for precision conservation","abstract":"Abstract Soil spatial variability is a primary contributor to within-field yield variation across farms. Spatio-temporal yield stability and variability can be assessed through multi-year yield monitor data and geostatistical techniques. Our objective was to delineate yield stability zones using multi-year yield data coupled with gross margins to plan precision conservation prescriptions. This study employed corn yield measurements from 2018, 2019, 2020 and farm economics data to compile yield stability and gross margin maps for nine Texas Blackland Prairie corn fields, and identified nonprofitable areas in each field that may be unsuitable for crop production. Yield stability zones were delineated using mean and coefficient of variation of multi-year yield maps (Zone A: high yield, stable; Zone B: high yield, unstable; Zone C: low yield, unstable; and Zone D: low yield, stable). Approximately 57% of the area in the fields was classified as unstable and, nearly 29% of the area yielded consistently below the field mean (Zone D). Gross margin for stability zones ranged from − $693 to $775/ha. Stability zones A and B generally had positive gross margins, whereas zones C and D had negative margins. Based on yield and gross margin assessment, yield stability zone D could be removed from row crop production. As a part of the Long-Term Agroecosystem Research Network Common Cropland Experiment, Zone D was removed from production (fields Y-8 and Y-13) or received reduced inputs (field SW-16 and W-13). Further study is needed to verify the farm-level economic benefits to producers and to evaluate the environmental benefits of precision conservation.","author":[{"family":"Adhikari","given":"Kabindra"},{"family":"Smith","given":"Douglas"},{"family":"Hajda","given":"Chad"},{"family":"Kharel","given":"Tulsi"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-09995-7","URL":"https://doi.org/10.1007/s11119-023-09995-7","source":"crossref"},{"id":"doi:10.3920/9789086866649_048","type":"article-journal","title":"Agri yield management: practical solutions for profitable and sustainable agriculture based on advanced technology","abstract":"The globally increasing demand for food and crops for bio fuels is outpacing the agricultural production capacity. Farm input costs are related to the ever rising costs of energy, forcing the economic need to minimize inputs for crop production. Environmental concerns and the availability of usable irrigation water put pressure on sustainable crop production. Growing more food with fewer resources poses a great challenge for the agricultural sector. Agri Yield Management (AYM) systems provide the farmer with the necessary tools to achieve this goal. This paper will explain how AYM systems can contribute to provide a solution to grow more food with fewer recourses. This will be done by an explanation of the AYM system developed by Dacom in the Netherlands. This system makes use of advanced technologies like intelligent sensors, internet and GPS. Software combines the collected information into practical solutions that supports the farmer in his daily operations. This AYM system is unique because it integrates multiple aspects of the crop production such as water, chemicals and fertilizer in relation to the yield. Precision timing and using the right product has proven to be profitable through the years. Challenges are the real-time collection of reliable crop environment information and methods for adaptation of these innovative systems by farmers to change from traditional practices to new AYM methods.","author":[{"family":"Hadders","given":"J"},{"family":"Hadders","given":"JWM"},{"family":"Raatjes","given":"P"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_048","URL":"https://doi.org/10.3920/9789086866649_048","source":"crossref"},{"id":"doi:10.1016/j.aiia.2024.06.004","type":"article-journal","title":"Computer vision in smart agriculture and precision farming: Techniques and applications","abstract":"The transformation of age-old farming practices through the integration of digitization and automation has sparked a revolution in agriculture that is driven by cutting-edge computer vision and artificial intelligence (AI) technologies. This transformation not only promises increased productivity and economic growth, but also has the potential to address important global issues such as food security and sustainability. This survey paper aims to provide a holistic understanding of the integration of vision-based intelligent systems in various aspects of precision agriculture. By providing a detailed discussion on key areas of digital life cycle of crops, this survey contributes to a deeper understanding of the complexities associated with the implementation of vision-guided intelligent systems in challenging agricultural environments. The focus of this survey is to explore widely used imaging and image analysis techniques being utilized for precision farming tasks. This paper first discusses various salient crop metrics used in digital agriculture. Then this paper illustrates the usage of imaging and computer vision techniques in various phases of digital life cycle of crops in precision agriculture, such as image acquisition, image stitching and photogrammetry, image analysis, decision making, treatment, and planning. After establishing a thorough understanding of related terms and techniques involved in the implementation of vision-based intelligent systems for precision agriculture, the survey concludes by outlining the challenges associated with implementing generalized computer vision models for real-time deployment of fully autonomous farms.","author":[{"family":"Ghazal","given":"Sumaira"},{"family":"Munir","given":"Arslan"},{"family":"Qureshi","given":"Waqar"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1016/j.aiia.2024.06.004","URL":"https://doi.org/10.1016/j.aiia.2024.06.004","source":"crossref"},{"id":"doi:10.1007/s11119-024-10217-x","type":"article-journal","title":"Transfer learning for plant disease detection model based on low-altitude UAV remote sensing","abstract":"The global attention to the utilization of unmanned aerial vehicle remote sensing drones in crop disease-wide detection has led to the urgent need to find an adapted model for different environmental conditions. Therefore, the current study has focused on spatiotemporal usage of different multispectral cameras in acquiring spectral reflectance models of in-field rice bacterial blight stresses. Where, long short-term memory (LSTM) model was compared with the other models in transfer learning strategy for assessing the blight stress severity. The results revealed that by extracting 30% of the data from the target domain and transferring it to the source domain, the adaptability of the model across different sites was effectively enhanced. Besides, LSTM showed high tuning transfer efficiency that demonstrated optimal predictive performance and the shortest training time in transfer tasks. Its coefficient of the prediction set was 0.82, and its residual prediction deviation has reached 2.26. In practice, LSTM enabled the acquisition of reliable prediction results at a minimal sample collection cost while circumventing feature reduction resulting from inter-domain data alignment. When the transfer ratio reached 20%, the coefficient of determination of the prediction set reached 0.71, and the residual prediction deviation reached 1.79. The novelty of this study came from the transfer learning efficiency in improving the model’s application capabilities across the different sites, environment, and unmanned aerial vehicle in farmland disease detection.","author":[{"family":"Huang","given":"Zhenyu"},{"family":"Bai","given":"Xiulin"},{"family":"Gouda","given":"Mostafa"},{"family":"Hu","given":"Hui"},{"family":"Yang","given":"Ningyuan"},{"family":"He","given":"Yong"},{"family":"Feng","given":"Xuping"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10217-x","URL":"https://doi.org/10.1007/s11119-024-10217-x","source":"crossref"},{"id":"doi:10.2174/9789815274349124010012","type":"article-journal","title":"Transforming Agriculture with IoT for Precision Agriculture and Sustainable Crop Management","abstract":"The Internet of Things (IoT) technology is making a radical transition in the agricultural business, resulting in the creation of precision agriculture and sustainable crop management practices. This study inspects how Internet of Things (IoT) technology is revolutionizing agriculture, with a particular emphasis on sustainable crop management techniques and precision agriculture. The study explores the extent and significance of using sensors, IoT devices, and data analytics for improved crop monitoring and management, empowering farmers to make data-driven choices. Farmers are able to allocate resources more efficiently and produce less waste due to the real-time data collecting on soil moisture, temperature, humidity, and crop health. We go into great detail on the essential elements of IoT-based precision agriculture, such as decision support systems, data collecting, analytics, and sensor technology. The study also looks at the benefits of using IoT in agriculture, highlighting how technology might completely transform farming methods for more sustainability and efficiency. A thorough literature study adds to our understanding of the status of research in Internet of Things applications for sustainable crop management and precision agriculture.","author":[{"family":"Bhardwaj","given":"Suyash"},{"family":"Venkatesan","given":"Sasirekha"},{"family":"Rawat","given":"Swati"},{"family":"Nath","given":"Pashupati"}],"issued":{"date-parts":[[2024]]},"DOI":"10.2174/9789815274349124010012","URL":"https://doi.org/10.2174/9789815274349124010012","source":"crossref"},{"id":"doi:10.3390/agriculture13081467","type":"article-journal","title":"A Cost-Effective Portable Multiband Spectrophotometer for Precision Agriculture","abstract":"The United Nations marks responsible consumption and production as one of the 17 key goals to fulfill the 2030 Agenda for Sustainable Development. In this context, affordable precision instruments can play a significant role in the optimization of crops in developing countries where precision agriculture tools are barely available. In this work, a simple to use, cost-effective instrument for spectral analysis of plants and fruits based on open-source hardware and software has been developed. The instrument is a 7-band spectrophotometer equipped with a microprocessor that allows one to acquire the reflectance spectrum of samples and compute up to 9 vegetation indices. The accuracy in reflectance measurements is between 0.4% and 1.4% full scale, just above that of high-end spectrophotometers, while the precision at determining the normalized difference vegetation index (NDVI) is 0.61%, between 3 and 6 times better than more expensive commercial instruments. Some use cases of this instrument have been tested, and the prototype has proven to be able to precisely monitor minute spectral changes of different plants and fruits under different conditions, most of them before they were perceptible to the bare eye. This kind of information is essential in the decision-making process regarding harvesting, watering, or pest control, allowing precise control of crops. Given the low cost (less than USD 100) and open-source architecture of this instrument, it is an affordable tool to bring precision agriculture techniques to small farmers in developing countries.","author":[{"family":"Fernández-Alonso","given":"Francisco"},{"family":"Hernández","given":"Zulimar"},{"family":"Torres-Costa","given":"Vicente"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13081467","URL":"https://doi.org/10.3390/agriculture13081467","source":"crossref"},{"id":"doi:10.21203/rs.3.rs-4677379/v1","type":"article-journal","title":"Precision Agriculture Advisor","abstract":"Abstract An AI-driven system revolutionizing crop selection and yield prediction in modern agriculture. By leveraging AI algorithms and IoT technologies, the system provides actionable insights to farmers for informed decision-making. Analyzing soil data from IoT sensors, including pH levels, moisture content, and nutrient composition, the system tailors crop recommendations to specific soil types, environmental conditions, and historical yield patterns. Predictive analytics accurately estimate crop yields based on diverse factors, including weather forecasts and agronomic indicators. Key components include data acquisition, preprocessing modules, and a user-friendly interface for real-time monitoring and analysis. Real-world validation demonstrates enhanced crop productivity and profitability, with broader implications for sustainable farming practices and food security.","author":[{"family":"Kothuri","given":"Sai"},{"family":"Tanusree","given":"Mandala"},{"family":"Chaitanya","given":"Nimmakayala"},{"family":"Chaitanya","given":"SMK"}],"issued":{"date-parts":[[2024]]},"DOI":"10.21203/rs.3.rs-4677379/v1","URL":"https://doi.org/10.21203/rs.3.rs-4677379/v1","source":"europepmc"},{"id":"doi:10.1007/s11119-023-10002-2","type":"article-journal","title":"Identification of management zones with different potential moisture availability for sustainable intensification of dryland agriculture","abstract":"In semiarid environments moisture availability is the primary factor that controls land productivity, however, no method to differentiate landscape portions with high moisture availability has yet been proposed for delimitation of crop management zones for precision agriculture. The objective of the present study was to develop a methodology to determine sites with different soil potential moisture availability to improve the delimitation of homogeneous crop management zones in semiarid environments. An altimetric survey was carried out in the field to obtain a DEM with a spatial resolution of 5 m. Subsequently, maps of slopes, area of ​​flow accumulation, sub-basins of the Topographic Wetness index (TWI) were made. A potential moisture availability (PMA) map was generated by linking the TWI map with a map of previously reclassified sub-basins and homogeneous PMA zones were delineated. Soil profiles were sampled on transects through the PMA zones, and during three growing seasons soil moisture contents were recorded. The PMA zones had homogeneous soil types and moisture contents and differed from each other in soil profile depth and available moisture contents, especially in the more humid season. Soil moisture correlated well with the antecedent precipitation index (API) during crop growth and in the PMA zones with higher altimetry, while only weak relationships were found during fallow periods and for the lowest altimetry PMA zone. The proposed methodology was useful for identifying landscape portions with differences in potential moisture availability as the spatial-temporal variability was represented. The use of the API combined with the potential moisture availability allowed a better fit in its relationship with the soil available moisture contents (AMC).","author":[{"family":"Farrell","given":"Mauricio"},{"family":"Leizica","given":"Emmanuel"},{"family":"Gili","given":"Adriana"},{"family":"Noellemeyer","given":"Elke"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10002-2","URL":"https://doi.org/10.1007/s11119-023-10002-2","source":"crossref"},{"id":"doi:10.1007/s11119-022-09986-0","type":"article-journal","title":"Detection of soil-borne wheat mosaic virus using hyperspectral imaging: from lab to field scans and from hyperspectral to multispectral data","abstract":"Abstract Hyperspectral imaging allows for rapid, non-destructive and objective assessments of crop health. Narrowband-hyperspectral data was used to select wavelength regions that can be exploited to identify wheat infected with soil-borne mosaic virus. First, leaf samples were scanned in the lab to investigate spectral differences between healthy and diseased leaves, including non-symptomatic and symptomatic areas within a diseased leaf. The potential of 84 commonly used vegetation indices to find infection was explored. A machine-learning approach was used to create a classification model to automatically separate pixels into symptomatic, non-symptomatic and healthy classes. The success rate of the model was 69.7% using the full spectrum. It was very encouraging that by using a subset of only four broad bands, sampled to simulate a data set from a much simpler and less costly multispectral camera, accuracy increased to 71.3%. Next, the classification models were validated on field data. Infection in the field was successfully identified using classifiers trained on the entire spectrum of the hyperspectral data acquired in a lab setting, with the best accuracy being 64.9%. Using a subset of wavelengths, simulating multispectral data, the accuracy dropped by only 3 percentage points to 61.9%. This research shows the potential of using lab scans to train classifiers to be successfully applied in the field, even when simultaneously reducing the hyperspectral data to multispectral data.","author":[{"family":"Haagsma","given":"Marja"},{"family":"Hagerty","given":"Christina"},{"family":"Kroese","given":"Duncan"},{"family":"Selker","given":"John"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-022-09986-0","URL":"https://doi.org/10.1007/s11119-022-09986-0","source":"crossref"},{"id":"doi:10.3920/9789086865147_085","type":"article-journal","title":"Error propagation in agricultural models","abstract":"Spatially distributed agricultural models rely for their operation on a number of value surfaces representing their various input parameters. Each of these surfaces will contain some error, due in part to the sampling and interpolation techniques used to generate the surfaces. The degree to which those errors are propagated through the model, often with amplifying effects, depends on the magnitude of the input errors and on the mathematical form of the model. This work investigates the effects of sample spacing and interpolation on model input error and illustrates the effects of propagation through a simple fertiliser recommendation model using sample spacing and interpolation methods such as those that might be used in practice.","author":[{"family":"Purnomo","given":"D"},{"family":"Corner","given":"RJ"},{"family":"Adams","given":"ML"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_085","URL":"https://doi.org/10.3920/9789086865147_085","source":"crossref"},{"id":"doi:10.1007/s11119-023-10035-7","type":"article-journal","title":"Small-target weed-detection model based on YOLO-V4 with improved backbone and neck structures","abstract":"In field weed detection tasks, achieving accurate identification of crops and weeds is the primary target. However, since small target weeds among crops are not easily detected, this undoubtedly increases the difficulty of detection. In order to solve this problem, based on the YOLO-V4 network, this paper modifies the residual block of the backbone network into a Res2block residual block with a hierarchical residual mode, and constructs a new backbone network Csp2Darknet53 to enhance fine-grained feature detection; In addition, receptive field enlargement and multi-scale fusion are achieved by using the I-SPP structure with multi-branch structure and dilated convolution; Finally, a depthwise separable convolution block with residual mode (IDSC-X) is proposed to replace the original 5-time convolution block in the path aggregation network (PANet) to ensure that the original features are not completely lost and reduce the amount of parameters. Compared with FasterR-CNN, SSD, MaskR-CNN, YOLO-V3 and YOLO-V4, the improved network detection accuracy is significantly better than other networks. Compared with YOLO-V4, the AP value of small target weeds increased by 15.1%, the mAP value increased by 4.2%, and the model parameters and training weight file size decreased by 34%. The results show that the method is feasible to improve the accurate detection of small target weeds, and can be extended to weed detection tasks of different crops.","author":[{"family":"Wu","given":"Haoyu"},{"family":"Wang","given":"Yongshang"},{"family":"Zhao","given":"Pengfei"},{"family":"Qian","given":"Mengbo"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10035-7","URL":"https://doi.org/10.1007/s11119-023-10035-7","source":"crossref"},{"id":"doi:10.1007/s11119-024-10180-7","type":"article-journal","title":"Estimation of corn crop damage caused by wildlife in UAV images","abstract":"Abstract Purpose This paper proposes a low-cost and low-effort solution for determining the area of corn crops damaged by the wildlife facility utilising field images collected by an unmanned aerial vehicle (UAV). The proposed solution allows for the determination of the percentage of the damaged crops and their location. Methods The method utilises image segmentation models based on deep convolutional neural networks (e.g., UNet family) and transformers (SegFormer) trained on over 300 hectares of diverse corn fields in western Poland. A range of neural network architectures was tested to select the most accurate final solution. Results The tests show that despite using only easily accessible RGB data available from inexpensive, consumer-grade UAVs, the method achieves sufficient accuracy to be applied in practical solutions for agriculture-related tasks, as the IoU (Intersection over Union) metric for segmentation of healthy and damaged crop reaches 0.88. Conclusion The proposed method allows for easy calculation of the total percentage and visualisation of the corn crop damages. The processing code and trained model are shared publicly.","author":[{"family":"Aszkowski","given":"Przemysław"},{"family":"Kraft","given":"Marek"},{"family":"Drapikowski","given":"Pawel"},{"family":"Pieczyński","given":"Dominik"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10180-7","URL":"https://doi.org/10.1007/s11119-024-10180-7","source":"crossref"},{"id":"doi:10.3920/9789086866649_105","type":"article-journal","title":"Development of a small agricultural field inspection vehicle","abstract":"Weed mapping is a valuable tool when it comes to optimizing the use of resources in managing the attempts made to control weeds. Weed mapping has traditionally been done by using random sampling techniques, amongst others, with a team of experts working in the field. One alternative to this tedious task, which requires moving the experts with the consequent associated cost, is the use of photographic samples, with and without controlled lighting. Once in the laboratory an expert can estimate the amount of weeds and the growth state of the crop on the basis of the set of photos that have been taken at the geo-referenced sampling points. This method can be used to observe the photos several times and correct errors in estimation, this in view of the fact that visual assessment of the photos is a subjective process in which it is easy to adapt observation to an overall situation; for example, average density can be estimated as high if the set of photos is not very dense and as low if the opposite is the case. This paper presents the first vehicle prototype developed at the IAICSIC that is able to move autonomously across agricultural fields, taking high-resolution photos, at sampling points defined by the user for the generation of a weed distribution map. The autonomous vehicle was tested successfully in an agricultural environment without controlled lighting.","author":[{"family":"Gottschalk","given":"R"},{"family":"Burgos-Artizzu","given":"XP"},{"family":"Ribeiro","given":"A"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_105","URL":"https://doi.org/10.3920/9789086866649_105","source":"crossref"},{"id":"doi:10.2139/ssrn.4930688","type":"manuscript","title":"A Discrete Sliding Mode Control Strategy for Precision Agriculture Irrigation Management","abstract":"Control theory has been showing progress in its evolving exercise in precision agriculture for the search for optimized irrigation schemes regarding water saving. Nevertheless, implementations have been limited to on-off and PID (proportional-integral-derivative) controllers, with the more sophisticated variations being fuzzy controllers. To improve this, a robust model-based irrigation controller using a discrete sliding mode approach is taken. The work presented in this paper aims to evaluate whether the proposed controller improves irrigation performance in a pecan crop subject to uncertainties, perturbations, and delays. The paper describes the development and implementation of a discrete sliding mode controller, including system identification, model validation, stability analysis, controller parameter selection, and system response analysis. The proposed approach is compared, in terms of water consumption and irrigation accuracy, with two widely used watering schemes: open-loop time-based control and closed-loop on-off control. The results indicate that the proposed controller effectively improves water efficiency while ensuring the feasibility of implementation in common irrigation infrastructure.","author":[{"family":"Garcia","given":"Leonardo"},{"family":"Lozoya","given":"Camilo"},{"family":"Castañeda","given":"Herman"},{"family":"Favela-Contreras","given":"Antonio"}],"issued":{"date-parts":[[2024]]},"DOI":"10.2139/ssrn.4930688","URL":"https://doi.org/10.2139/ssrn.4930688","source":"crossref"},{"id":"doi:10.1109/ieeeconf58110.2023.10520651","type":"article-journal","title":"Precision Agriculture for Indian Farms using AIOT","abstract":"This research explores the transformative potential of precision agriculture, a fusion of Artificial Intelligence (AI) and the Internet of Things (Io'T), to address the burgeoning global demand for sustainable food production. The study encompasses various facets of precision agriculture, including crop recommendation (using soil classification), yield prediction, plant disease detection and gets promising results for all. For soil classification a CNN model has been prepared which achieves an accuracy of 95.5%. An IoT sensor based solution has been proposed for rice yield prediction and regression analysis has been performed to find the best model. The proposed random forest method has been able to achieve an R2 value of 0.945. Transfer learning approach has been employed to find the best deep neural network model for plant disease detection and an accuracy of 99.6%has been achieved after fine tuning. To make these solutions easily accessible and available a flask based web app has been designed with a user friendly interface.","author":[{"family":"Jha","given":"Anurag"},{"family":"Jha","given":"Ashish"},{"family":"Shetty","given":"Sujala"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/ieeeconf58110.2023.10520651","URL":"https://doi.org/10.1109/ieeeconf58110.2023.10520651","source":"crossref"},{"id":"doi:10.3920/9789086866649_044","type":"article-journal","title":"Evolution of agricultural machinery: the third way","abstract":"The innovations in agricultural equipments have always been an important stimulator to the development of agriculture. For several years, we were witnesses of an irremediable increase in the size of agricultural machines. If this ‘first way’, encouraged by farm machinery industry, is synonymous of high outputs, a lot of disadvantages can nevertheless be identified in term of soil compaction, difficulty to control large width implements on irregular soils, or to integrate the traffic on rural roads. A ‘second way’ has recently been proposed by several research laboratories (Europe, Japan), based on light weight robots for a small scale farming at the plant level. This approach is well suited for high added value product such as market garden produce or flower productions. However, for crops like cereals which represent the first productive sector in Europe, previous smart robot machines even in swarm working configuration, would certainly not be able to assume harvest operations in large production areas. Thereby, another scenario, called the ‘third way’, could consist to propose machines medium in size and power but always integrating a high degree of technologies. Medium power could mean the possibility for agricultural machines to easier benefit of future car component developments in term of transmission (engine-wheel pack) or energy motorization (electric fuel cell). For preservation of economic competitiveness, these machines could compensate the decreasing of the work width by an increase of the forward speed. A high degree of modularity could also authorize the cooperation of machines, with a leader machine always driven by an operator, and one or several other following. The paper underlines main advantages and limitations of each way and gives some cost comparison elements about the first and third ways.","author":[{"family":"Berducat","given":"M"},{"family":"Debain","given":"C"},{"family":"Lenain","given":"R"},{"family":"Cariou","given":"C"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_044","URL":"https://doi.org/10.3920/9789086866649_044","source":"crossref"},{"id":"doi:10.3920/9789086865147_116","type":"article-journal","title":"Selecting the optimum locations for soil investigations","abstract":"A site selection algorithm has been developed/optimised, that identifies measurement sites which are spatially representative of the entire survey area as well as suitable from a statistical point of view. Electrical conductivity data (ECa) are measured by electromagnetic induction scanning. The coverage of the whole field is obtained by Kriging interpolation and divided into clusters according to the Ward Cluster algorithm. Locations are selected according to their even distribution across the field and their ECa data conforming to a response surface design. The sampling sites selected are spatially and statistically representative and well suited for point measurements and model applications.","author":[{"family":"Zimmermann","given":"Hilde"},{"family":"Plöchl","given":"Matthias"},{"family":"Luckhaus","given":"Christoph"},{"family":"Domsch","given":"Horst"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_116","URL":"https://doi.org/10.3920/9789086865147_116","source":"crossref"},{"id":"doi:10.3920/978-90-8686-947-3_15","type":"article-journal","title":"Farmer-led on-farm experimentation enhanced with digital agronomy","abstract":"Agriculture puts pressure on ecosystems, and practices need to evolve towards a more sustainable way of producing food. Farmers are changing their practices by conducting on-farm experimentation with their own objectives and experimental designs. While endogenous experimentation is considered as not being scientific, there is an opportunity for a paradigm shift by using digital agronomy to contextualize farmers' observations. This project supported farmer-centric experimentation on nine sites testing the use of biological additives to enhance N supply to maize crops. While farmers compare side-by-side treatments on a yield and profit basis, additional data can help farmers better interpret their observations.","author":[{"family":"Longchamps","given":"L"},{"family":"Lanza","given":"P"},{"family":"Cambouris","given":"AN"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/978-90-8686-947-3_15","URL":"https://doi.org/10.3920/978-90-8686-947-3_15","source":"crossref"},{"id":"doi:10.3920/9789086866649_115","type":"article-journal","title":"Future GNSS - Farmers navigate towards trusted farming","abstract":"Nowadays, European farmers have to comply with numerous rules and directives concerning a diverse range of production issues. The EU requires farmers more and more to comply with legislative rules concerning farm management that focus on sustainability and environmental issues. Non compliancy might result in subsidy reductions or even fines. On the other hand, consumers and government demand that farmers produce ‘safe food’ and they expect that reliable information regarding the production process is available through the agri-food chain all the way to the origin of the primary product. GNSS supported (precision) agriculture can support both the implementation of these demands on the farm and facilitate the associated control process that is required. If reliable and trusted documentation on farm operations could be collected, these could also serve as a proof of compliance with regulations or certification procedures. This requires the concept of trusted farming, where the farmer would be allowed to use registered data, automatically collected during field work, as a rightful proof of compliance with regulations or certification procedures. The European GNSS (Galileo and EGNOS) that is currently under development might bring an important step towards trusted farming. In the FieldFact project, opportunities of Galileo, the new European GNSS, have been examined. Galileo will provide its users in the agricultural sector with key features that will improve the reliability of recorded information. The combination of an authenticated signal and an integrity message will provide a hallmark for the measured location and time. Thus, the generation of authenticated or trusted documentation on the farm, a basis for trusted farming, will become possible.","author":[{"family":"Lokers","given":"RM"},{"family":"Krause","given":"A"},{"family":"Wal","given":"TVD"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_115","URL":"https://doi.org/10.3920/9789086866649_115","source":"crossref"},{"id":"doi:10.3920/978-90-8686-947-3_58","type":"article-journal","title":"Optimizing agricultural coverage path to minimize soil compaction","abstract":"The Coverage Path Planning (CPP) problem is the optimization problem of finding the best path that covers a complete area. In agriculture, the coverage path defines the path that the tractor follows, which is directly related with soil compaction. Despite the consequences of soil compaction, using the disturbed soil as a cost function for the CPP problem has been little explored. This paper compares three methods to compute the disturbed soil for wheeled and caterpillar tracked vehicles. The methods are tested on simulation and compared visually on a real field. The experiments show that the presented methods can compute the disturbed soil area on a 3 km path accurately in less than 12 s","author":[{"family":"Mier","given":"G"},{"family":"Valente","given":"J"},{"family":"Bruin","given":"SD"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/978-90-8686-947-3_58","URL":"https://doi.org/10.3920/978-90-8686-947-3_58","source":"crossref"},{"id":"doi:10.3920/9789086866038_051","type":"article-journal","title":"GPS-based auto-guidance test program development","abstract":"Auto-guidance based on Global Positioning System (GPS) navigation is a rapidly expanding technology in modern agriculture. Because of many discrepancies in testing methods, there is a need to establish a standardized test procedure to quantify the performance of different autoguidance systems. This publication presents results from two different methods employed to determine guidance error using a pull-type test cart. The test cart was equipped with a specially designed linear potentiometer sensor (LPS) and a real time kinematic (RTK) GPS receiver. The instruments were simultaneously used to track the relative position of the cart while being pulled by an agricultural tractor operated with the automated steering mode engaged. Two systems with different claimed levels of accuracy were tested using two parallel passes at the Nebraska Tractor Test Laboratory’s (NTTL) test track. Both the LPS and GPS-based methods were able to distinguish between two levels of auto-guidance systems and provided guidance error estimates compatible with the expected values. Although the GPS-based measurements were accomplished with a relatively high frequency, the corresponding error estimates were slightly higher than those based on the LPSbased measurements. In contrast, the LPS represented a simple and robust system, but provided a number of mechanical uncertainties limiting measurement reliability. Therefore, it was concluded that another measurement tool conceptually similar to LPS might be developed to provide high frequency measurements of relative position with respect to the set of ground markers.","author":[{"family":"Adamchuk","given":"VI"},{"family":"Hoy","given":"RM"},{"family":"Meyer","given":"GE"},{"family":"Kocher","given":"MF"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866038_051","URL":"https://doi.org/10.3920/9789086866038_051","source":"crossref"},{"id":"doi:10.3920/9789086867783_086","type":"article-journal","title":"Obtaining yield maps in orchards by tracking machine behavior","abstract":"In hand harvested citrus orchards, fruits are usually stored in big bags or containers in the fields until they are picked by a crane and loaded into a truck. Yield maps for this type of harvest are mostly based on geo-referencing the position of bags and later calculating yield at these points. A method of tracking the loading machine movement with low cost GPS receivers and post-processing data using filters is herein proposed to locate bag position, and allow reliable yield mapping without the need of human interaction in the existing harvest procedure. Up to 86% accuracy on locating bags was obtained by tracking the difference in altitude of the crane’s lifting arm while loading bags.","author":[{"family":"Colaço","given":"AF"},{"family":"Spekken","given":"M"},{"family":"Molin","given":"JP"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086867783_086","URL":"https://doi.org/10.3920/9789086867783_086","source":"crossref"},{"id":"doi:10.1109/africon55910.2023.10293435","type":"article-journal","title":"A Survey on Internet of Things for Precision Agriculture","abstract":"Technology is advancing ever so steadily and all efforts are geared towards the automation of processes to make human life easier. The fourth industrial revolution is driving the use of technology in production processes and organizations such as health, agriculture and manufacturing among others to improve the functionalities of said processes. Machine learning and artificial intelligence, as well as the Internet of Things and cloud computing, are some of the current hot technologies. Agriculture is one of the most crucial areas in human survival and has therefore seen more technological resources directed towards improving production while minimizing costs. The process of realizing this vision however hasn't been a hurdle free and this paper strives to take a peek into the situation of technology use (Internet of Things) in agriculture to understand some of the successes, challenges and gaps that need filling. To effectively shed some light on the situation this paper reviews research work from scholars in the field of precision agriculture with a focus on their proposed solutions, Equipment and technologies employed such as (ZigBee, Low PAN, Bluetooth, GSM, Wi-Fi, AI and Cloud computing) and compares between solutions offered by the researchers by identifying gaps","author":[{"family":"Ochiel","given":"Michael"},{"family":"Kitauka","given":"Innocent"},{"family":"Tuyambaze","given":"Thacianne"},{"family":"Sinde","given":"Ramadhani"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1109/africon55910.2023.10293435","URL":"https://doi.org/10.1109/africon55910.2023.10293435","source":"crossref"},{"id":"doi:10.5194/egusphere-egu24-19319","type":"article-journal","title":"Advances in monitoring vineyard with multiscale and multiplatform data for precision agriculture systems","abstract":"Within a vineyard, the variation in plant water status is intricately tied to the spatial variability of the soil, where the physical attributes of the soil govern the processes shaping the soil water balance. As the soil and its characteristics exhibit inhomogeneity, horizontally and vertically, the productivity and qualitative response within the vineyard become less uniform. In this context, employing proximal sensing to gauge the apparent soil Electrical Conductivity (ECa) and monitoring it throughout the growing season becomes instrumental in understanding the nature of spatial variability within the vineyard. This not only aids in viticultural microzoning, identifying Homogeneous and functional Homogeneous Zones (HZs and fHZs), but also supports field experiments.We propose a machine learning approach that works as a predictive model for soil ECa, involving spatially predicting ECa based on discrete measurements obtained from a network of Time Domain Reflectometry (TDR) probes capable of measuring ECa. This methodology enables the spatial prediction of ECa values across the surveyed area. The main purpose is to create a process that using multiscale and multiplatform measurements helps the farmer monitoring and interacting with the crop in a better way, reducing resources and improving the crop productivity.Records on soil and atmosphere systems, in-vivo plant monitoring of eco-physiological parameters in 2020 and 2021, and spatial variability of plant status monitored through UAV multispectral images were used to test this approach, on a Greco di Tufo grapevines (white) in southern Italy. The apparent EC measurements were obtained using a PROFILER EMP 400 in both dipole modes and with 3 different frequencies (5, 10 and 15 kHz), exploring different depths of the soil.The predictive model shown a good performance, with results that are in good agreement with previous knowledge of the area.","author":[{"family":"Vitale","given":"Andrea"},{"family":"Cutaneo","given":"Carmine"},{"family":"Buonanno","given":"Maurizio"},{"family":"Bonfante","given":"Antonello"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5194/egusphere-egu24-19319","URL":"https://doi.org/10.5194/egusphere-egu24-19319","source":"crossref"},{"id":"doi:10.3920/9789086866649_056","type":"article-journal","title":"Mapping traffic patterns for soil compaction studies using GIS","abstract":"Soil compaction is a common problem in the southeastern United States, and can lead to a host of soil and plant growth problems. Since one of the main causes of soil compaction is equipment traffic in fields, the idea of limiting traffic to certain rows can help alleviate the onset of soil compaction. The objective of this study is to determine the amount of traffic occurring in North Carolina fields and the effect that the level of traffic (number of vehicle passes) had on soil compaction. GPS was used to map all traffic on these fields in 2006. Using measurements of tire widths and wheel spacings, a series of processes in a GIS was performed to generate a map representing the level of traffic that occurred at each point of the field. After all field operations were complete, fields were sampled for bulk density. Sample locations were based on the number of tire passes that had occurred. Samples were taken where there had been 0, 1, 2, and 4 passes of equipment tires. Initial results showed that 65-85% of the field’s area was tracked at least once. Bulk density ranged from 0.5 to 0.8 g/cm3 in the organic soil, and from 1.6 to 1.8 g/cm3 in the sandy soils. Initial results show that in the organic soil, areas of the field that were tracked at least four times had significantly higher bulk density in the 0-10 cm depth than the areas that received no tracks. The study is continuing on research stations in 2008 and 2009 to better look at the influence of vehicle traffic on soil bulk density.","author":[{"family":"Meijer","given":"AD"},{"family":"Heiniger","given":"RW"},{"family":"Crozier","given":"CR"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_056","URL":"https://doi.org/10.3920/9789086866649_056","source":"crossref"},{"id":"doi:10.3920/9789086866038_067","type":"article-journal","title":"Apple yield mapping using hyperspectral machine vision","abstract":"For orchard growers, it is important to estimate the quantity of fruit on the trees at different stages of their growth. This study proposes a method of automatically detecting apples in digital images that can be used for automating the yield estimation of apples on trees at different stages of their growth by means of machine vision. This investigation concentrates on estimating yield of green varieties of apples. To achieve this goal, hyperspectral imaging was applied. A multistage algorithm was developed which utilizes PCA and ECHO as well as machine vision techniques. The overall correct detection rate was 87.0% with an overall error rate of 14.9%.","author":[{"family":"Alchanatis","given":"V"},{"family":"Safren","given":"O"},{"family":"Levi","given":"O"},{"family":"Ostrovsky","given":"V"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866038_067","URL":"https://doi.org/10.3920/9789086866038_067","source":"crossref"},{"id":"doi:10.1007/s11119-023-10101-0","type":"article-journal","title":"Within-season vegetation indices and yield stability as a predictor of spatial patterns of Maize (Zea mays L) yields","abstract":"Abstract Accurate evaluation of crop performance and yield prediction at a sub-field scale is essential for achieving high yields while minimizing environmental impacts. Two important approaches for improving agronomic management and predicting future crop yields are the spatial stability of historic crop yields and in-season remote sensing imagery. However, the relative accuracies of these approaches have not been well characterized. In this study, we aim to first, assess the accuracies of yield stability and in-season remote sensing for predicting yield patterns at a sub-field resolution across multiple fields, second, investigate the optimal satellite image date for yield prediction, and third, relate bi-weekly changes in GCVI through the season to yield levels. We hypothesize that historical yield stability zones provide high accuracies in identifying yield patterns compared to within-season remote sensing images. To conduct this evaluation, we utilized biweekly Planet images with visible and near-infrared bands from June through September (2018–2020), along with observed historical yield maps from 115 maize fields located in Indiana, Iowa, Michigan, and Minnesota, USA. We compared the yield stability zones (YSZ) with the in-season remote sensing data, specifically focusing on the green chlorophyll vegetative index (GCVI). Our analysis revealed that yield stability maps provided more accurate estimates of yield within both high stable (HS) and low stable (LS) yield zones within fields compared to any single-image in-season remote sensing model. For the in-season remote sensing predictions, we used linear models for a single image date, as well as multi-linear and random forest models incorporating multiple image dates. Results indicated that the optimal image date for yield prediction varied between and within fields, highlighting the instability of this approach. However, the multi-image models, incorporating multiple image dates, showed improved prediction accuracy, achieving R 2 values of 0.66 and 0.86 by September 1st for the multi-linear and random forest models, respectively. Our analysis revealed that most low or high GCVI values of a pixel were consistent across the season (77%), with the greatest instability observed at the beginning and end of the growing season. Interestingly, the historical yield stability zones provided better predictions of yield compared to the bi-weekly dynamics of GCVI. The historically high-yielding areas started with low GCVI early in the season but caught up, while the low-yielding areas with high initial GCVI faltered. In conclusion, the historical yield stability zones in the US Midwest demonstrated robust predictive capacity for in-field heterogeneity in stable zones. Multi-image models showed promise for assessing unstable zones during the season, but it is crucial to link these two approaches to fully capture both stable and unstable zones of crop yield. This study provides opportunities to achieve better precision management and yield prediction by integrating historical crop yields and remote sensing techniques.","author":[{"family":"Shuai","given":"Guanyuan"},{"family":"Fowler","given":"Ames"},{"family":"Basso","given":"Bruno"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10101-0","URL":"https://doi.org/10.1007/s11119-023-10101-0","source":"crossref"},{"id":"doi:10.1109/metroagrifor58484.2023.10424302","type":"article-journal","title":"Digital soil mapping for precision agriculture using multitemporal Sentinel-2 images of bare ground","abstract":"High-detail soil mapping is fundamental to apply precision agriculture approaches. Although, soil maps are available in many countries at a regional scale for land planning purposes, there is a need to increase the detail in the most important agricultural areas for application of site-specific agriculture practices and soil monitoring. New data from proximal and remote sensors, as well as quantitative digital methods provide the right tools to obtain these maps with sustainable costs. Digital soil mapping (DSM) includes many tools to generate spatial soil information and provides solutions for the growing demand for high-resolution soil maps worldwide.This study aims at producing soil property maps (organic carbon, clay, sand, total nitrogen, and total carbonates) at a local level (the Rieti agricultural plain, about 4000 ha), using digital soil mapping methods combining punctual soil observations, Digital Elevation Model (DEM) and related covariates (slope, topographic wetness index, etc.) and a Synthetic Soil Image (SYSI) derived by multitemporal derived bare-soil images from Sentinel-2 satellite. Regression kriging with forward stepwise regression provided reliable results for interpolation of clay, sand, soil organic carbon (SOC), whereas total carbonates $\\left(\\mathrm{CaCO}_{3}\\right)$ and nitrogen (TN) were better interpolated by universal kriging.","author":[{"family":"Zanini","given":"Monica"},{"family":"Priori","given":"Simone"},{"family":"Petito","given":"Matteo"},{"family":"Cantalamessa","given":"Silvia"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/metroagrifor58484.2023.10424302","URL":"https://doi.org/10.1109/metroagrifor58484.2023.10424302","source":"crossref"},{"id":"doi:10.3920/9789086866649_078","type":"article-journal","title":"Simulating the physiological dynamics of winter wheat after grazing","abstract":"Winter wheat can be grown for the dual purposes of livestock grazing and grain production. The development of cultivars capable of producing large quantities of both herbage and grain has recently increased the adoption of this farming practice in Australia. The objectives of this study were to (1) develop a model capable of accurately simulating the regrowth and grain production of winter wheat after grazing, and (2) apply the model to determine the primary mechanisms controlling crop growth rates after grazing. An existing crop model, SUCROS2 was extended with a defoliation subroutine. Dry matter accumulation was modified from leaf photosynthesis to a canopy radiationuse efficiency approach. Grazing was simulated as a reduction in shoot biomass and leaf area index. The proportion of shoot removed was weighted towards leaf biomass. Carbon allocation patterns following defoliation were shifted in favour of shoots and leaves, thus tending to restore genetically-determined ‘target’ root-shoot and leaf-shoot ratios. The model was calibrated using soil water, leaf, stem and kernel biomass measurements taken during an experiment conducted near Canberra, Australia. Simulations produced reliable estimates of leaf and stem biomass, however kernel biomass was underestimated when the crop was grazed. Simulated cumulative water use was greater than that observed for a period after grazing. This study revealed two main insights. First, compared to ungrazed wheat, grazed crops remained greener for longer, allowing them to continue growing much later in the season. Second, grazing delayed soil water use, allowing growth rates of grazed crops to exceed those of ungrazed crops. This occurred in late spring during a period of water stress, even though the leaf area and light interception of the grazed wheat was less than that of the ungrazed.","author":[{"family":"Harrison","given":"MT"},{"family":"Evans","given":"JR"},{"family":"Moore","given":"AD"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_078","URL":"https://doi.org/10.3920/9789086866649_078","source":"crossref"},{"id":"doi:10.3920/9789086866649_118","type":"article-journal","title":"Common Agricultural Policy and Spatial Data Infrastructures","abstract":"The European Common Agricultural Policy (CAP) is already for many years relying on geo-spatial applications in administering, managing and controlling farmers declarations. The CAP is under constant change and over the years it has become more spatial explicit with more emphasis on cross compliance to environmental regulations and the inclusion of landscape features in the subsidy system. The implementation of the CAP regulations is left to the member states. National choices have lead to different implementations of the same regulation. The INSPIRE directive provides a regulatory framework for harmonising the reference datasets of these national implementations and this leads to a reference model for land parcel information systems. Also Europe’s own satellite navigation system Galileo is an opportunity for the agricultural domain to harmonise methods and datasets for rapid field visits and On The Spot Control. The authors present the opportunities these European geo-spatial initiatives have to offer to the CAP and indicate how the agricultural domain for regulated applications adopts the INSPIRE directive and Galileo programme in both the single payment and the rural development schemes. The CAP can benefit and contribute to the European SDI. These developments and challenges will be presented.","author":[{"family":"Wal","given":"TVD"},{"family":"Devos","given":"W"},{"family":"Kay","given":"S"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_118","URL":"https://doi.org/10.3920/9789086866649_118","source":"crossref"},{"id":"doi:10.1007/s11119-024-10212-2","type":"article-journal","title":"On crop yield modelling, predicting, and forecasting and addressing the common issues in published studies","abstract":"Abstract There has been a recent surge in the number of studies that aim to model crop yield using data-driven approaches. This has largely come about due to the increasing amounts of remote sensing (e.g. satellite imagery) and precision agriculture data available (e.g. high-resolution crop yield monitor data), as well as the abundance of machine learning modelling approaches. However, there are several common issues in published studies in the field of precision agriculture (PA) that must be addressed. This includes the terminology used in relation to crop yield modelling, predicting, forecasting, and interpolating, as well as the way that models are calibrated and validated. As a typical example, many studies will take a crop yield map or several plots within a field from a single season, build a model with satellite or Unmanned Aerial Vehicle (UAV) imagery, validate using data-splitting or some kind of cross-validation (e.g. k-fold), and say that it is a ‘prediction’ or ‘forecast’ of crop yield. However, this poses a problem as the approach is not testing the forecasting ability of the model, as it is built on the same season that it is then validating with, thus giving a substantial overestimation of the value for decision-making, such as an application of fertiliser in-season. This is an all-too-common flaw in the logic construct of many published studies. Moving forward, it is essential that clear definitions and guidelines for data-driven yield modelling and validation are outlined so that there is a greater connection between the goal of the study, and the actual study outputs/outcomes. To demonstrate this, the current study uses a case study dataset from a collection of large neighbouring farms in New South Wales, Australia. The dataset includes 160 yield maps of winter wheat ( Triticum aestivum ) covering 26,400 hectares over a 10-year period (2014–2023). Machine learning crop yield models are built at 30 m spatial resolution with a suite of predictor data layers that relate to crop yield. This includes datasets that represent soil variation, terrain, weather, and satellite imagery of the crop. Predictions are made at both the within-field (30 m), and field resolution. Crop yield predictions are useful for an array of applications, so four different experiments were set up to reflect different scenarios. This included Experiment 1: forecasting yield mid-season (e.g. for mid-season fertilisation), Experiment 2: forecasting yield late-season (e.g. for late-season logistics/forward selling), Experiment 3: predicting yield in a previous season for a field with no yield data in a season, and Experiment 4: predicting yield in a previous season for a field with some yield data (e.g. two combine harvesters, but only one was fitted with a yield monitor). This study showcases how different model calibration and validation approaches clearly impact prediction quality, and therefore how they should be interpreted in data-driven crop yield modelling studies. This is key for ensuring that the wealth of data-driven crop yield modelling studies not only contribute to the science, but also deliver actual value to growers, industry, and governments.","author":[{"family":"Filippi","given":"Patrick"},{"family":"Han","given":"Si"},{"family":"Bishop","given":"Thomas"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10212-2","URL":"https://doi.org/10.1007/s11119-024-10212-2","source":"crossref"},{"id":"doi:10.3920/9789086865147_024","type":"article-journal","title":"Optimal path nutrient application using variable rate technology","abstract":"The error in nutrient application is increased in a variable rate environment when application rate is altered. The path an operator takes to apply nutrient material to the field has an influence on this application error, given it affects the rates of change in the desired application amount. In the light of this, a classical traveling salesperson integer programming framework was used to determine the optimal path for preplant fertilizer application. A simple illustrative example depicts that potash application errors can be reduced from 14% of the required amount to 9% of the amount required by actively considering the path of application. Results also suggest that some atypical concepts such as skipping parts of the field requiring application might be beneficial under some circumstances.","author":[{"family":"Dillon","given":"CR"},{"family":"Shearer","given":"S"},{"family":"Fulton","given":"J"},{"family":"Kanakasabai","given":"M"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_024","URL":"https://doi.org/10.3920/9789086865147_024","source":"crossref"},{"id":"doi:10.3920/9789086865147_115","type":"article-journal","title":"Hyperspectral image feature extraction and classification for soil nutrient mapping","abstract":"Aerial hyperspectral images were used for soil nutrient mapping and the image processing results were compared with the conventional field grid sampling and interpolation methods. A spatial low pass filter was applied to the hyperspectral imagery for enhancing soil nutrient property class separability. Image features were extracted from selective principal component transformed image space. Results showed that the supervised image classification could be implemented on a feature space with two features rather than on the original image space using all bands. It is concluded that using hyperspectral imagery for phosphorous and organic matter mapping could be a better approach than using the grid sampling and interpolation methods.","author":[{"family":"Yao","given":"Haibo"},{"family":"Tian","given":"Lei"},{"family":"Kaleita","given":"Amy"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_115","URL":"https://doi.org/10.3920/9789086865147_115","source":"crossref"},{"id":"doi:10.3390/agriculture14040620","type":"article-journal","title":"Precision Livestock Farming Technology: Applications and Challenges of Animal Welfare and Climate Change","abstract":"This study aimed to review recent developments in the agri-food industry, focusing on the integration of innovative digital systems into the livestock industry. Over the last 50 years, the production of animal-based foods has increased significantly due to the rising demand for meat. As a result, farms have increased their livestock numbers to meet consumer demand, which has exacerbated challenges related to environmental sustainability, human health, and animal welfare. In response to these challenges, precision livestock farming (PLF) technologies have emerged as a promising solution for sustainable livestock production. PLF technologies offer farmers the opportunity to increase efficiency while mitigating environmental impact, securing livelihoods, and promoting animal health and welfare. However, the adoption of PLF technologies poses several challenges for farmers and raises animal welfare concerns. Additionally, the existing legal framework for the use of PLF technologies is discussed. In summary, further research is needed to advance the scientific understanding of PLF technologies, and stakeholders, including researchers, policymakers, and funders, need to prioritize ethical considerations related to their implementation.","author":[{"family":"Papakonstantinou","given":"Georgios"},{"family":"Voulgarakis","given":"Nikolaos"},{"family":"Terzidou","given":"Georgia"},{"family":"Fotos","given":"Lampros"},{"family":"Giamouri","given":"Elisavet"},{"family":"Papatsiros","given":"Vasileios"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/agriculture14040620","URL":"https://doi.org/10.3390/agriculture14040620","source":"crossref"},{"id":"doi:10.1007/s11119-023-10019-7","type":"article-journal","title":"Adoption of precision agriculture technologies by sugarcane farmers in the state of São Paulo, Brazil","abstract":"This research aims at analyzing the determinants of the adoption and the intensity of adoption of precision agriculture technologies (PATs) by sugarcane farmers in the state of São Paulo, Brazil. A sample survey of 131 sugarcane farmers provided the data. Six adopted PATs were identified: GNSS and images for planting row orientation (52 adopters), tractor/harvester with automatic guidance system (32), georeferenced grids for soil sampling (15), images (satellite and/or drone) for mapping pests and yields (8), variable-rate applicators of fertilizers (8), and variable-rate applicators of pesticide (3). The adoption and adoption intensity (dependent variable) were measured as the number of PATs used by farmers. 53 farmers adopted at least one of these technologies, while 78 farmers did not adopt PATs. A count data model was used to test hypotheses on factors explaining both adoption and the intensity of adoption. The results suggested that the information provided by the sugarcane mills, the production scale and farmer perception that PATs would increase yield are determining factors for adoption. Information provided by private technical advisors and obtained at agricultural events plays an important role in the intensity of adoption. Such intensity is also affected by farmers’ previous experience with PATs, their perception that PATs would increase yield, and the availability of low-cost credit.","author":[{"family":"Mozambani","given":"Carlos"},{"family":"Filho","given":"Hildo"},{"family":"Vinholis","given":"Marcela"},{"family":"Carrer","given":"Marcelo"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10019-7","URL":"https://doi.org/10.1007/s11119-023-10019-7","source":"europepmc"},{"id":"doi:10.1186/s12859-024-05970-9","type":"article-journal","title":"Improving crop production using an agro-deep learning framework in precision agriculture.","abstract":"The study focuses on enhancing the effectiveness of precision agriculture through the application of deep learning technologies. Precision agriculture, which aims to optimize farming practices by monitoring and adjusting various factors influencing crop growth, can greatly benefit from artificial intelligence (AI) methods like deep learning. The Agro Deep Learning Framework (ADLF) was developed to tackle critical issues in crop cultivation by processing vast datasets. These datasets include variables such as soil moisture, temperature, and humidity, all of which are essential to understanding and predicting crop behavior. By leveraging deep learning models, the framework seeks to improve decision-making processes, detect potential crop problems early, and boost agricultural productivity.","author":[{"family":"Ks","given":"Kumar"},{"family":"Mj","given":"Rex"},{"family":"Bo","given":"Soufiene"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1186/s12859-024-05970-9","URL":"https://doi.org/10.1186/s12859-024-05970-9","source":"pubmed"},{"id":"doi:10.3389/fpls.2024.1485903","type":"article-journal","title":"Advancing precision agriculture with deep learning enhanced SIS-YOLOv8 for Solanaceae crop monitoring.","abstract":"Introduction Potatoes and tomatoes are important Solanaceae crops that require effective disease monitoring for optimal agricultural production. Traditional disease monitoring methods rely on manual visual inspection, which is inefficient and prone to subjective bias. The application of deep learning in image recognition has led to object detection models such as YOLO (You Only Look Once), which have shown high efficiency in disease identification. However, complex climatic conditions in real agricultural environments challenge model robustness, and current mainstream models struggle with accurate recognition of the same diseases across different plant species. Methods This paper proposes the SIS-YOLOv8 model, which enhances adaptability to complex agricultural climates by improving the YOLOv8 network structure. The research introduces three key modules: 1) a Fusion-Inception Conv module to improve feature extraction against complex backgrounds like rain and haze; 2) a C2f-SIS module incorporating Style Randomization to enhance generalization ability for different crop diseases and extract more detailed disease features; and 3) an SPPF-IS module to boost model robustness through feature fusion. To reduce the model’s parameter size, this study employs the Dep Graph pruning method, significantly decreasing parameter volume by 19.9% and computational load while maintaining accuracy. Results Experimental results show that the SIS-YOLOv8 model outperforms the original YOLOv8n model in disease detection tasks for potatoes and tomatoes, with improvements of 8.2% in accuracy, 4% in recall rate, 5.9% in mAP50, and 6.3% in mAP50-95. Discussion Through these network structure optimizations, the SIS-YOLOv8 model demonstrates enhanced adaptability to complex agricultural environments, offering an effective solution for automatic crop disease detection. By improving model efficiency and robustness, our approach not only advances agricultural disease monitoring but also contributes to the broader adoption of AI-driven solutions for sustainable crop management in diverse climates.","author":[{"family":"Qin","given":"Ruiqian"},{"family":"Wang","given":"Yiming"},{"family":"Liu","given":"Xiaoyan"},{"family":"Yu","given":"Helong"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3389/fpls.2024.1485903","URL":"https://doi.org/10.3389/fpls.2024.1485903","source":"europepmc"},{"id":"doi:10.1038/s41598-024-80924-y","type":"article-journal","title":"A technical survey on practical applications and guidelines for IoT sensors in precision agriculture and viticulture.","abstract":"Climate change pose significant challenges to modern agriculture management systems, threatening food production and security. Therefore, tackling its effects has never been so imperative to attain sustainable food access and nutrition worldwide. In the case of viticulture, besides jeopardizing grape production, climate change has severe impact in quality, which has becoming more challenging to manage, due to the increasingly frequent fungal contamination, with consequences for relevant quality parameters such as the aromatic profiles of grapes and wines and their phenolic compounds. This has been leading to a reconfiguration of the wine industry geostrategic landscape and economy dynamics, particularly in Southern Europe. To address these and other emerging challenges, in-field deployable proximity-based precision technologies have been enabling real-time monitoring of crops ecosystems, including climate, soil and plants, by performing relevant data gathering and storage, paving the way for advanced decision support under the Internet of Things (IoT) paradigm. This paper explores the integration of agronomic and technological knowledge, emphasizing the proper selection of IoT-capable sensors for viticulture, while considering more general ones from agriculture to fill gaps when specialized options are unavailable. Moreover, advisable practices for sensor installation are provided, according to respective types, data acquisition capabilities and applicability.","author":[{"family":"Rd","given":"Lopes"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1038/s41598-024-80924-y","URL":"https://doi.org/10.1038/s41598-024-80924-y","source":"pubmed"},{"id":"doi:10.1155/2024/2126734","type":"article-journal","title":"Application of Precision Agriculture Technologies for Sustainable Crop Production and Environmental Sustainability: A Systematic Review.","abstract":"Precision agriculture technologies (PATs) transform crop production by enabling more sustainable and efficient agricultural practices. These technologies utilize data‐driven approaches to optimize the management of crops, soil, and resources, thus enhancing both productivity and environmental sustainability. This article reviewed the application of PATs for sustainable crop production and environmental sustainability around the globe. Key components of PAT include remote sensing, GPS‐guided equipment, variable rate technology (VRT), and Internet of Things (IoT) devices. Remote sensing and drones deliver high‐resolution imagery and data, enabling precise monitoring of crop health, soil conditions, and pest activity. GPS‐guided machinery ensures accurate planting, fertilizing, and harvesting, which reduces waste and enhances efficiency. VRT optimizes resource use by allowing farmers to apply inputs such as water, fertilizers, and pesticides at varying rates across a field based on real‐time data and specific crop requirements. This reduces over‐application and minimizes environmental impact, such as nutrient runoff and greenhouse gas emissions. IoT devices and sensors provide continuous monitoring of environmental conditions and crop status, enabling timely and informed decision‐making. The application of PAT contributes significantly to environmental sustainability by promoting practices that conserve water, reduce chemical usage, and enhance soil health. By enhancing the precision of agricultural operations, these technologies reduce the environmental impact of farming, while simultaneously boosting crop yields and profitability. As the global demand for food increases, precision agriculture offers a promising pathway to achieving sustainable crop production and ensuring long‐term environmental health.","author":[{"family":"Getahun","given":"Sewnet"},{"family":"Kefale","given":"Habtamu"},{"family":"Gelaye","given":"Yohannes"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1155/2024/2126734","URL":"https://doi.org/10.1155/2024/2126734","source":"europepmc"},{"id":"doi:10.32388/wqe6dz","type":"article-journal","title":"Modelling of Quadcopter for Precision Agriculture and Surveillance Purposes","abstract":"This article presents the modelling of a quadcopter with a payload of 7 kg and the general overview of its use for precision crop spraying. The paper reviews the current state of the art in precision crop spraying and provides a comprehensive overview of the various types of unmanned aerial vehicles (UAVs) available, their capabilities, and their potential applications in precision crop spraying. It also provides a detailed analysis of the challenges and opportunities associated with the use of UAVs for precision crop spraying. The UAV used in the study was integrated with a liquid payload and a sprayer system that is controlled remotely by a flight controller radio. The objective was achieved by developing a mathematics-based model for the quadcopter. Subsequently, the quadcopter was physically fabricated in accordance with the computer model, tested, and evaluated. The modeling outcome gives a quadcopter with dimensions of 1140.28 mm by 767.11 mm by 267.37 mm and with each of the four propellers having a length of 457.2 mm. This was simulated, and the results show a stable trajectory flight and a uniformly distributed pattern of discharge of its content.","author":[{"family":"Dahunsi","given":"Olurotimi"},{"family":"Oguntuase","given":"Oluseye"},{"family":"Udeh","given":"Benedict"},{"family":"Adeyeri","given":"Micheal"},{"family":"Dahunsi","given":"Folasade"}],"issued":{"date-parts":[[2024]]},"DOI":"10.32388/wqe6dz","URL":"https://doi.org/10.32388/wqe6dz","source":"europepmc"},{"id":"doi:10.5281/zenodo.21302538","type":"article-journal","title":"HerdSense: A low cost IoT-Based Non-Invasive Cattle Health and Activity Monitoring Collar","abstract":"An IoT-based non-invasive wearable collar for monitoring the health and activity of native cattle using an ESP32-S3, MLX90614 infrared temperature sensor, MAX30102 PPG sensor, MPU6050 inertial sensor, VL53L0X time-of-flight sensor, and cloud-based data logging.","author":[{"family":"Adedokun","given":"Ayobami"},{"family":"Ogundipe","given":"Victor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21302538","URL":"https://doi.org/10.5281/zenodo.21302538","source":"datacite"},{"id":"doi:10.5281/zenodo.21302539","type":"article-journal","title":"HerdSense: A low cost IoT-Based Non-Invasive Cattle Health and Activity Monitoring Collar","abstract":"An IoT-based non-invasive wearable collar for monitoring the health and activity of native cattle using an ESP32-S3, MLX90614 infrared temperature sensor, MAX30102 PPG sensor, MPU6050 inertial sensor, VL53L0X time-of-flight sensor, and cloud-based data logging.","author":[{"family":"Adedokun","given":"Ayobami"},{"family":"Ogundipe","given":"Victor"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21302539","URL":"https://doi.org/10.5281/zenodo.21302539","source":"datacite"},{"id":"doi:10.5281/zenodo.21280965","type":"article-journal","title":"Corn and Weed Semantic Segmentation Test Dataset","abstract":"This dataset contains 325 RGB images and 325 corresponding pixel-wise semantic segmentation masks for corn and weed detection. The image files are named img0 to img324, and the corresponding masks are named mask0 to mask324. Each image and mask pair share the same numeric index. The dataset was prepared for testing and qualitative evaluation of a semantic segmentation model for corn and weed detection in top-down agricultural images. The masks were generated and preprocessed for the classes background, corn, and weed.","author":[{"family":"Marinas","given":"Vlad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21280965","URL":"https://doi.org/10.5281/zenodo.21280965","source":"datacite"},{"id":"doi:10.5281/zenodo.21280966","type":"article-journal","title":"Corn and Weed Semantic Segmentation Test Dataset","abstract":"This dataset contains 325 RGB images and 325 corresponding pixel-wise semantic segmentation masks for corn and weed detection. The image files are named img0 to img324, and the corresponding masks are named mask0 to mask324. Each image and mask pair share the same numeric index. The dataset was prepared for testing and qualitative evaluation of a semantic segmentation model for corn and weed detection in top-down agricultural images. The masks were generated and preprocessed for the classes background, corn, and weed.","author":[{"family":"Marinas","given":"Vlad"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21280966","URL":"https://doi.org/10.5281/zenodo.21280966","source":"datacite"},{"id":"doi:10.5281/zenodo.21335444","type":"article-journal","title":"AgriVerse Synthetic Agricultural Dataset (Preview Sample): Procedurally Generated Maize and Weed Imagery for Crop-Weed Detection","abstract":"This is a preview sample (150 images) of a larger, fully procedurally generated synthetic dataset for crop-versus-weed object detection in maize fields. The images are top-down RGB renders (1024x1024 PNG) produced by a domain-randomized procedural field generator: parametric maize and weed plant models are instantiated with randomized morphology, count, placement, soil appearance, and lighting, then rendered and automatically annotated with bounding boxes derived from the scene geometry (so annotation is exact and cost-free).","author":[{"family":"Esfandiyar","given":"Iman"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21335444","URL":"https://doi.org/10.5281/zenodo.21335444","source":"datacite"},{"id":"doi:10.5281/zenodo.21335445","type":"article-journal","title":"AgriVerse Synthetic Agricultural Dataset (Preview Sample): Procedurally Generated Maize and Weed Imagery for Crop-Weed Detection","abstract":"This is a preview sample (150 images) of a larger, fully procedurally generated synthetic dataset for crop-versus-weed object detection in maize fields. The images are top-down RGB renders (1024x1024 PNG) produced by a domain-randomized procedural field generator: parametric maize and weed plant models are instantiated with randomized morphology, count, placement, soil appearance, and lighting, then rendered and automatically annotated with bounding boxes derived from the scene geometry (so annotation is exact and cost-free).","author":[{"family":"Esfandiyar","given":"Iman"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21335445","URL":"https://doi.org/10.5281/zenodo.21335445","source":"datacite"},{"id":"doi:10.5281/zenodo.21037821","type":"article-journal","title":"End-to-End Intelligent Maize Plant Height Estimation: A Geometry-Constrained Single View Metrology Framework","abstract":"For the latest updates, raw source code, and interactive usage instructions, please visit our GitHub repository: https://github.com/sherman6931/Single-View-Metrology-for-Maize-Height-Estimation This repository contains the samples, the demo app, and 3D simulator supporting the findings of the manuscript \"End-to-End Intelligent Maize Plant Height Estimation: A Geometry-Constrained Single View Metrology Framework\". Contents: Dataset, demo app, 3D Simulator For usage instructions please refer to the included README file.","author":[{"family":"Li","given":"Yizhe"},{"family":"Tang","given":"Feiyu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21037821","URL":"https://doi.org/10.5281/zenodo.21037821","source":"datacite"},{"id":"doi:10.5281/zenodo.21037822","type":"article-journal","title":"End-to-End Intelligent Maize Plant Height Estimation: A Geometry-Constrained Single View Metrology Framework","abstract":"For the latest updates, raw source code, and interactive usage instructions, please visit our GitHub repository: https://github.com/sherman6931/Single-View-Metrology-for-Maize-Height-Estimation This repository contains the samples, the demo app, and 3D simulator supporting the findings of the manuscript \"End-to-End Intelligent Maize Plant Height Estimation: A Geometry-Constrained Single View Metrology Framework\". Contents: Dataset, demo app, 3D Simulator For usage instructions please refer to the included README file.","author":[{"family":"Li","given":"Yizhe"},{"family":"Tang","given":"Feiyu"}],"issued":{"date-parts":[[2026]]},"DOI":"10.5281/zenodo.21037822","URL":"https://doi.org/10.5281/zenodo.21037822","source":"datacite"},{"id":"doi:10.20944/preprints202309.0277.v1","type":"manuscript","title":"Wireless Sensor Networks for Precision Agriculture: A Review of NPK Sensor Implementations","abstract":"The integration of Wireless Sensor Networks (WSNs) into agricultural areas has had a significant impact and has provided new, more complex, efficient, and structured solutions for enhancing crop production. This research reviews the role of Wireless Sensor Networks (WSNs) in monitoring the macro-nutrient content of plants. The review study focuses on identifying the types of sensors used to measure macro-nutrients, determining sensor placement within agricultural areas, implementing wireless technology for sensor communication, and selecting device transmission intervals and ratings. The study of NPK (Nitrogen, Phosphorus, Potassium) monitoring using sensor technology in precision agriculture is of high significance in efforts to improve agricultural productivity and efficiency. In addition to fostering technological innovations and precision farming solutions, in future this research aims to increase agricultural yields, particularly by enabling the cultivation of certain crops in locations different from their original ones.","author":[{"family":"Musa","given":"Purnawarman"},{"family":"Sugeru","given":"Herik"},{"family":"Wibowo","given":"Eri"}],"issued":{"date-parts":[[2023]]},"DOI":"10.20944/preprints202309.0277.v1","URL":"https://doi.org/10.20944/preprints202309.0277.v1","source":"preprints"},{"id":"doi:10.21203/rs.3.rs-2263078/v1","type":"article-journal","title":"Deep Learning based Automated Disease Detection and Classification Model for Precision Agriculture","abstract":"Abstract Plant phenotyping and Precision agriculture are information-and technology-oriented fields with specific challenges and demands for the detection and diagnosis of plant disease. Precision agriculture can be referred as a crop management method related to the spatial and temporal variability in soil and crop factors within a field. Accurate and early diagnosis and detection of plant diseases were major factors in plant production and the reduction of quantitative and qualitative losses in crop yield. Advancement of automatic disease detection and classification system is significantly explored in precision agriculture. In recent times, research workers have investigated numerous cultures leveraging dissimilar parts of a plant. This article develops a new Deep Learning based Automated Plant Disease Detection and Classification (DL-APDDC) Model for Precision Agriculture. The presented DL-APDDC algorithm concentrates on the recognition and classification of plant diseases in leaf and fruit regions. In the initial stage, the leaf and fruit regions are extracted by the use of U2Net based background removal. Next, the Adam optimizer with SqueezeNet model is exploited as feature extractor and the hyperparameters are tuned by Adam optimizer. Finally, the extreme gradient boosting (XGBoost) classifier performs classification of plant diseases. The experimental validation of the DL-APDDC technique is tested on benchmark plant disease dataset. The simulation values indicated the enhanced outcomes of the DL-APDDC approach over other models.","author":[{"family":"Pavithra","given":"A"},{"family":"Vigneswaran","given":"T"}],"issued":{"date-parts":[[2023]]},"DOI":"10.21203/rs.3.rs-2263078/v1","URL":"https://doi.org/10.21203/rs.3.rs-2263078/v1","source":"preprints"},{"id":"doi:10.3390/ani14223307","type":"article-journal","title":"Validating Ultra-Wideband Positioning System for Precision Cow Tracking in a Commercial Free-Stall Barn","abstract":"UWB positioning systems offer innovative solutions for precision monitoring dairy cow behaviour and social dynamics, yet their performance in complex commercial barn environments requires thorough validation. This study evaluated the TrackLab 2.13 (Noldus) UWB system in a dairy barn housing 44–49 cows. We assessed stationary tag positioning using ten fixed tags over seven days, proximity detection between eight cows and ten stationary tags, and moving tag positioning using three tags on a stick to simulate cow movement. System performance varied by tag location, with reliability ranging from 4.09% to 96.73% and an overall mean accuracy of 0.126 ± 0.278 m for stationary tags. After the provider updated the software, only 0.62% of measures exceeded the declared accuracy of 0.30 m. Proximity detection between moving cows and stationary tags showed 81.42% accuracy within a 2-m range. While generally meeting specifications, spatial variations in accuracy and reliability were observed, particularly near barn perimeters. These findings highlight UWB technology’s potential for precision livestock farming, welfare assessment, and behaviour research, including social interactions and space use patterns. Results emphasise the need for careful system setup, regular updates, and context-aware data interpretation in commercial settings to maximise benefits in animal welfare monitoring.","author":[{"family":"Moravcsíková","given":"Ágnes"},{"family":"Vyskočilová","given":"Zuzana"},{"family":"Šustr","given":"Pavel"},{"family":"Bartošová","given":"Jitka"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/ani14223307","URL":"https://doi.org/10.3390/ani14223307","source":"crossref"},{"id":"doi:10.3920/9789086865147_083","type":"article-journal","title":"Technical solutions for variable rate fertilisation","abstract":"The aim of variable rate fertilisation is to fulfil local requirements in the field in order to optimise the production for quantity or quality reasons. The choice of spreading technique and working width influences the possibilities of performing variable rate fertilisation. Based on two-dimensional (2-D) measurement of distribution patterns from different fertiliser distributors at different working widths and application rates, the overall distribution pattern may be calculated for fields in which variable rate is intended. Based on the calculations, decisions on whether or not to do variable rate fertilisation and which spreader to use may be made. Calculations that have been carried out based on distribution patterns from common types of mineral fertiliser distributors show that the bigger the spatial variability in the field, the smaller the working width that should be used.","author":[{"family":"Persson","given":"K"},{"family":"Skovsgaard","given":"H"},{"family":"Weltzien","given":"C"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_083","URL":"https://doi.org/10.3920/9789086865147_083","source":"crossref"},{"id":"doi:10.4018/979-8-3693-2069-3.ch006","type":"article-journal","title":"Applications of Sensors in Precision Agriculture for a Sustainable Future","abstract":"The advent of precision agriculture has revolutionized the agricultural sector, emphasizing the utilization of data-driven strategies for decision-making and the optimization of resources. Sensors, encompassing soil, crop, weather, and drone sensors, offer real-time data to facilitate informed decision-making and enhance agricultural outcomes. These sensors facilitate the optimization of irrigation and fertilization and the timely identification of soil-related problems. In addition, they contribute to the surveillance of plant health, the detection of weed infestations, and the monitoring of meteorological conditions. The gathering and management of data play a crucial role in precision agriculture. The advantages encompass decreased utilization of resources, heightened agricultural productivity, a diminished ecological footprint, and better economic viability. Nevertheless, persistent obstacles like technological problems, concerns around data security, and the imperative for advancements in artificial intelligence and machine learning persist.","author":[{"family":"Saleem","given":"Muhammad"},{"family":"Raza","given":"Ali"},{"family":"Sabir","given":"Rehan"},{"family":"Safdar","given":"Muhammad"},{"family":"Faheem","given":"Muhammad"},{"family":"Ansari","given":"Mohammed"}],"issued":{"date-parts":[[2024]]},"DOI":"10.4018/979-8-3693-2069-3.ch006","URL":"https://doi.org/10.4018/979-8-3693-2069-3.ch006","source":"crossref"},{"id":"doi:10.3390/environsciproc2022023038","type":"article-journal","title":"Application of Sensor-Based Precision Irrigation Methods for Improving Water Use Efficiency of Maize Crop","abstract":"Soil moisture sensors and hydraulic modeling play a vital role in managing surface irrigation systems. Crop water productivity can be improved by managing the inflow cut-off time and optimizing the other field scale measurements. As such, hydraulic modelling and field experiments were carried out at the University of Agriculture Faisalabad-Pakistan. The soil moisture sensor (SEN-13322) and the WinSRFR model were used for this purpose. In total, nineteen treatments including eighteen simulated treatments and one conventional treatment were designed at two levels of discharge (Q1:0.0025 and Q2:0.0035 m3s−1), at three sensor positions (S1:55%, S2:65%, and S3:75%) across the field length, as well as with three different border widths (B1:6.4m, B2:8.5m, and B3:10.7m) after successful sensor and model calibration during the two growing seasons of 2016–2017 and 2017–2018. The results revealed a significant difference between the means and the treatment T10 i.e., Q2S1B1 that were found to be highly efficient and uniform.","author":[{"family":"Aslam","given":"Muhammad"},{"family":"Cheema","given":"Muhammad"},{"family":"Saleem","given":"Shoaib"},{"family":"Basit","given":"Abdul"},{"family":"Hussain","given":"Saddam"},{"family":"Waqas","given":"Muhammad"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/environsciproc2022023038","URL":"https://doi.org/10.3390/environsciproc2022023038","source":"crossref"},{"id":"doi:10.3920/978-90-8686-947-3_132","type":"article-journal","title":"Modeling the canopy reflectance to predict tomato biomass for precision nitrogen management","abstract":"Biomass is strictly related to nitrogen (N) status, and its non-destructive estimation can be of interest to precision N management. Some spectral vegetation indices (SVIs) were monitored at five growth stages under different N rates to assess if canopy reflectance can be used to estimate tomato biomass. Given that linear relationships between SVI and biomass are calibrated only at the specific growth stage, a new approach for biomass estimation across the entire growing cycle is proposed. The slopes and intercepts of linear relationships between NDRE (normalized difference on red edge vegetation index) and biomass were retrieved as a function of the growing degree days (GDDs), making the estimation of biomass feasible across the entire growing season. However, because of the poor reliability observed during the early and late stages of the life cycle, the dynamic adoption of different SVIs at the single growth stages is recommended.","author":[{"family":"Cerasola","given":"VA"},{"family":"Marco","given":"AD"},{"family":"Pennisi","given":"G"},{"family":"Orsini","given":"F"},{"family":"Bona","given":"S"},{"family":"Gianquinto","given":"G"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/978-90-8686-947-3_132","URL":"https://doi.org/10.3920/978-90-8686-947-3_132","source":"crossref"},{"id":"doi:10.14302/issn.2998-1506.jpa-24-5058","type":"article-journal","title":"Automated Grassweed Detection in Wheat Cropping System: Current Techniques and Future Scope","abstract":"Wheat is a staple grain crop in the United States and around the world. Weed infestation, particularly grass weeds, poses significant challenges to wheat production, competing for resources and reducing grain yield and quality. Effective weed management practices, including early identification and targeted herbicide application are essential to avoid economic losses. Recent advancements in unmanned aerial vehicles (UAVs) and artificial intelligence (AI), offer promising solutions for early weed detection and management, improving efficiency and reducing negative environment impact. The integration of robotics and information technology has enabled the development of automated weed detection systems, reducing the reliance on manual scouting and intervention. Various sensors in conjunction with proximal and remote sensing techniques have the capability to capture detailed information about crop and weed characteristics. Additionally, multi-spectral and hyperspectral sensors have proven highly effective in weed vs crop detection, enabling early intervention and precise weed management. The data from various sensors consecutively processed with the help of machine learning and deep learning models (DL), notably Convolutional Neural Networks (CNNs) method have shown superior performance in handling large datasets, extracting intricate features, and achieving high accuracy in weed classification at various growth stages in numerous crops. However, the application of deep learning models in grass weed detection for wheat crops remains underexplored, presenting an opportunity for further research and innovation. In this review we underscore the potential of automated grass weed detection systems in enhancing weed management practices in wheat cropping systems. Future research should focus on refining existing techniques, comparing ML and DL models for accuracy and efficiency, and integrating UAV-based mapping with AI algorithms for proactive weed control strategies. By harnessing the power of AI and machine learning, automated weed detection holds the key to sustainable and efficient weed management in wheat cropping systems.","author":[{"family":"Shrestha","given":"Swati"},{"family":"Ojha","given":"Grishma"},{"family":"Sharma","given":"Gourav"},{"family":"Mainali","given":"Raju"},{"family":"Galvin","given":"Liberty"}],"issued":{"date-parts":[[2024]]},"DOI":"10.14302/issn.2998-1506.jpa-24-5058","URL":"https://doi.org/10.14302/issn.2998-1506.jpa-24-5058","source":"crossref"},{"id":"doi:10.1079/cabireviews.2024.0042","type":"article-journal","title":"Precision livestock farming in the 21st century: Challenges and opportunities for sustainable agriculture","abstract":"Abstract This study aimed to review the recent development of different technologies in precision livestock farming (PLF), along with their scopes and challenges. PLF is an innovative, contemporary, and fast-expanding approach to agriculture that aims to improve sustainable livestock farming. The growing global population has increased the demand for animal products. To meet this demand, farmers have to increase their production, so without the integration of precision technology, this cannot be achieved. PLF currently employs a variety of technologies. Some of these methods include vision-based solutions, load cells, accelerometers, microphones, thermal cameras, photoelectric sensors, and radio-frequency identification (RFID). Despite the availability of different PLF technologies, their adoption by farmers varies widely on the basis of the cost of investment, ease of operation, availability, and accessibility. These technologies are used to track different activities of livestock farming, such as feeding, drinking, physical behavior, temperature regulation, tracking and identification, estrus detection, disease detection, and milking. PLF contributes significantly to technological advancement, human-animal relationships, environmental sustainability, and increased productivity. It does, however, present a number of obstacles and eventual advantages.","author":[{"family":"Chapagaee","given":"Pawan"},{"family":"Nainabasti","given":"Anjal"},{"family":"Kunwar","given":"Adhiraj"},{"family":"Bist","given":"Dipak"},{"family":"Khatri","given":"Lokendra"},{"family":"Mandal","given":"Ashmita"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1079/cabireviews.2024.0042","URL":"https://doi.org/10.1079/cabireviews.2024.0042","source":"crossref"},{"id":"doi:10.3390/agriculture13081593","type":"article-journal","title":"The Path to Smart Farming: Innovations and Opportunities in Precision Agriculture","abstract":"Precision agriculture employs cutting-edge technologies to increase agricultural productivity while reducing adverse impacts on the environment. Precision agriculture is a farming approach that uses advanced technology and data analysis to maximize crop yields, cut waste, and increase productivity. It is a potential strategy for tackling some of the major issues confronting contemporary agriculture, such as feeding a growing world population while reducing environmental effects. This review article examines some of the latest recent advances in precision agriculture, including the Internet of Things (IoT) and how to make use of big data. This review article aims to provide an overview of the recent innovations, challenges, and future prospects of precision agriculture and smart farming. It presents an analysis of the current state of precision agriculture, including the most recent innovations in technology, such as drones, sensors, and machine learning. The article also discusses some of the main challenges faced by precision agriculture, including data management, technology adoption, and cost-effectiveness.","author":[{"family":"Karunathilake","given":"EMBM"},{"family":"Le","given":"Anh"},{"family":"Heo","given":"Seong"},{"family":"Chung","given":"Yong"},{"family":"Mansoor","given":"Sheikh"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13081593","URL":"https://doi.org/10.3390/agriculture13081593","source":"crossref"},{"id":"doi:10.1007/s11119-023-09988-6","type":"article-journal","title":"Development and field performance evaluation of hole-fertilizing planter and dynamic alignment control system for precision planting of corn","abstract":"The hole fertilization is an effective means of saving fertilizer and increasing yields by applying the fertilizer needed for crop growth to a certain area below the seed during the seed fertilizing stage. In response to the current issues of low fertilizer utilization and soil non-point source pollution caused by strip fertilization, a hole-fertilizing corn planter was designed, which mainly consists of the hole-fertilizing unit, electro-driven seeding unit, and speed measuring device. A dynamic alignment control system with low cost was developed for intermittent fertilization and seeding as well as for precise alignment of the seed and fertilizer. By analyzing the movement process of the seed and fertilizer, a dynamic alignment algorithm was developed to dynamically adjust the alignment and precisely control the placement. In addition, a novel image-based fertilizer detection method was used to study the fertilizer distribution in the soil and evaluate the operating performance of the prototype in the field. Field trials were conducted to investigate the seeding quality, hole-fertilizing effect, and alignment precision of the seed and fertilizer at different operating speeds. Results indicate that (1) the feed index ([Formula: see text]), miss index ([Formula: see text]), and multiple index ([Formula: see text]) are 91.9%, 6.8%, and 1.3%, respectively. (2) 85.4% of the fertilizer distances are greater than 60 mm in the soil, and the amount of fertilizer applied increases progressively with increasing soil depth. (3) The mean value of the offset distances is 28.1 mm, and 94% of the offset distances are less than 50 mm. Moreover, the offset distance increases as the operating speed rises.","author":[{"family":"Gao","given":"Jin"},{"family":"Zhang","given":"Fan"},{"family":"Zhang","given":"Junxiong"},{"family":"Zhou","given":"Hang"},{"family":"Yuan","given":"Ting"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-09988-6","URL":"https://doi.org/10.1007/s11119-023-09988-6","source":"crossref"},{"id":"doi:10.1016/b978-0-443-15315-0.00002-x","type":"article-journal","title":"Precision Nutrition in Female Reproductive Health","abstract":"Nutritional and lifestyle-related factors, including overweight and obesity, nutrient deficiencies , smoking, excessive consumption of caffeine and alcohol, stress, chronic exposure to environmental pollutants , diabetes, and hyperlipidemia associated with excess calorie intake , poor diet quality , and a sedentary lifestyle can influence female reproductive health . These factors can affect female reproductive health by direct damage to ovarian function , or by indirectly interfering with the pituitary-hypothalamic reproductive axis. Two-thirds of American women and increasing numbers of women globally are overweight and obese. Obesity and overweight also are involved in the phenotypic expression of polycystic ovarian syndrome (PCOS), which is the most common reproductive disorder in women. Precision Nutrition through the integration of nutritional, genetic, epigenetic, metabolomic , microbiome , and environmental factors can improve our understanding of the role of diet and lifestyle in PCOS . PCOS favors abdominal fat deposition and altered energy utilization so that nutrition interacts with genetic predisposition through hyperandrogenism and insulin resistance. Precision Nutrition promises to improve the prevention and treatment of PCOS.","author":[{"family":"Dumesic","given":"Daniel"},{"family":"Chazenbalk","given":"Gregorio"},{"family":"Heber","given":"David"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1016/b978-0-443-15315-0.00002-x","URL":"https://doi.org/10.1016/b978-0-443-15315-0.00002-x","source":"crossref"},{"id":"doi:10.1007/s11119-023-10070-4","type":"article-journal","title":"Spatial and dynamic distribution of Chrysoperla spp. and Leucoptera coffeella populations in coffee Coffea arabica L","abstract":"Leucoptera coffeella (Guérin-Mèneville, 1842) (Lepidoptera: Lyonetiidae) is one of the main pests of coffee. Controlling this insect requires effective management methods, prevention of insecticide resistance from overuse and an understanding of the pest’s spatial distribution and natural enemies. Thus, our objectives were to (1) determine the spatial distribution of Chrysoperla spp. and L. coffeella; (2) evaluate the effects of biological control by analyzing the dynamics of Chrysoperla spp. and L. coffeella populations in the presence of predators; and (3) compare the quality of Arabica coffee beverages produced from areas employing chemical controls to those with biological controls. To this end, a commercial plot of C. arabica coffee (Catuaí 144) in Rio Paranaíba (MG, Brazil) was monitored. The population of Chrysoperla spp. and L. coffeella was evaluated every two weeks. The data were submitted to descriptive and geostatistical analysis. The population of L. coffeella remained low in February and March with the release of Chrysoperla spp. Moderate to strong spatial dependence was observed in the semivariograms, indicating that population aggregation occurred in both the pest and the predator. No change in the quality of the coffee beverages was observed between the biological control and pyrethroid insecticide treatments.","author":[{"family":"Silva","given":"Brenda"},{"family":"Malaquias","given":"Monique"},{"family":"Filho","given":"Reynaldo"},{"family":"Santos","given":"Artur"},{"family":"Fernandes","given":"Flávio"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10070-4","URL":"https://doi.org/10.1007/s11119-023-10070-4","source":"crossref"},{"id":"doi:10.1002/pro6.1219","type":"article-journal","title":"Precision radiotherapy for nasopharyngeal carcinoma","abstract":"Abstract Nasopharyngeal carcinoma(NPC) occurs frequently in Southern China, and radiotherapy is the main treatment method. At present, intensity‐modulated radiotherapy is widely used, which has improved efficacy in patients with NPC and reduced toxicity and side effects. Recently, helical tomography radiotherapy, proton radiotherapy, carbon particle radiotherapy, and other radiotherapy techniques have been used for the clinical treatment of NPC. Individualized nasopharyngeal cancer targets have also been explored. This paper reviews the research progress in radiotherapy techniques and target volume for NPC","author":[{"family":"Zhang","given":"Zhenyu"},{"family":"Chen","given":"Xiangzhou"},{"family":"Yuan","given":"Taize"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1002/pro6.1219","URL":"https://doi.org/10.1002/pro6.1219","source":"crossref"},{"id":"doi:10.3390/agriculture13020360","type":"article-journal","title":"Spatio-Temporal Semantic Data Model for Precision Agriculture IoT Networks","abstract":"In crop and livestock management within the framework of precision agriculture, scenarios full of sensors and devices are deployed, involving the generation of a large volume of data. Some solutions require rapid data exchange for action or anomaly detection. However, the administration of this large amount of data, which in turn evolves over time, is highly complicated. Management systems add long-time delays to the spatio-temporal data injection and gathering. This paper proposes a novel spatio-temporal semantic data model for agriculture. To validate the model, data from real livestock and crop scenarios, retrieved from the AFarCloud smart farming platform, are modeled according to the proposal. Time-series Database (TSDB) engine InfluxDB is used to evaluate the model against data management. In addition, an architecture for the management of spatio-temporal semantic agricultural data in real-time is proposed. This architecture results in the DAM&amp;DQ system responsible for data management as semantic middleware on the AFarCloud platform. The approach of this proposal is in line with the EU data-driven strategy.","author":[{"family":"Parte","given":"Mario"},{"family":"Serrano","given":"Sara"},{"family":"Elduayen","given":"Marta"},{"family":"Martínez-Ortega","given":"José"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13020360","URL":"https://doi.org/10.3390/agriculture13020360","source":"crossref"},{"id":"doi:10.3920/9789086865147_082","type":"article-journal","title":"A variable rate pivot irrigation control system","abstract":"A Variable-Rate Irrigation (VRI) control system that enables a center pivot irrigation system (CP) to supply water at rates relative to the needs of individual areas within fields was developed through collaboration between the Farmscan group (Perth, Western Australia) and The University of Georgia Precision Farming Team. The VRI system varies application rate by cycling sprinklers on and off and by varying the CP travel speed. Desktop PC software is used to define application maps which are loaded into the VRI controller. The VRI system uses GPS to determine pivot position/angle of the CP mainline. Results from VRI system performance testing indicate good correlation between actual and target application rates and also shows that sprinkler cycling on/off does not alter the CP uniformity","author":[{"family":"Perry","given":"C"},{"family":"Pocknee","given":"S"},{"family":"Hansen","given":"O"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_082","URL":"https://doi.org/10.3920/9789086865147_082","source":"crossref"},{"id":"doi:10.20944/preprints202408.0747.v1","type":"manuscript","title":"Smart Agriculture: IoT and Deep Learning for Precision Crop Management","abstract":"Pakistan is an agricultural country, and an exporter of crops in many countries. The crop production is an important factor to earn revenue for the country. But the agriculture of Pakistan is still not revolutionized and no modern system has been deployed commonly. Whereas the farmers face difficulty in growing some crops because those crops needs more care and calculated steps. Moreover the farmers face difficulty at different stages of the crop growth like to check fertility of soil and if the soil is non-fertile then which chemical property is lacking. The objective of this research is to provide digitize the agriculture of Pakistan. An emerging technology IoT and Deep learning based system will be developed. The IoT part contains some devices like sensors,gateways and communication technologies whereas the software part consists of Deep learning models that can make predictions about the fertility of the soil. The motive of this system is to provide best results in term of accuracy. Whereas the dataset used is publicly available on kaggle but it was of non-fertile values, so data augmentation is also performed to generate data for fertile values. We have implemented LSTM,RNN,CNN among them LSTM performed best for the prediction of soil fertility.","author":[{"family":"Najeeb","given":"Hooriya"},{"family":"Naseer","given":"Asma"},{"family":"Tamoor","given":"Maria"}],"issued":{"date-parts":[[2024]]},"DOI":"10.20944/preprints202408.0747.v1","URL":"https://doi.org/10.20944/preprints202408.0747.v1","source":"preprints"},{"id":"doi:10.20944/preprints202401.0957.v1","type":"manuscript","title":"Precision Farming: A New Era of Antibiotic-Free Agriculture","abstract":"Precision farming is transforming how antibiotics get used on farms. It fights the overuse that creates superbugs and harms nature. Farmers now have high-tech tools to use antibiotics ultra-precisely. Drones, AI, and advanced watering equipment help them pinpoint only sick plants and animals needing treatment. This shields crops while avoiding environmental damage. More careful antibiotic use makes livestock healthier and boosts harvests too. And it prevents resistant germs, where antibiotics stop working altogether. The approach helps farms in multiple ways, using fewer resources for even better results. There are some growing pains, like high costs for small farms. And questions around data privacy also cause concern. But overcoming these hurdles could help precision farming spread far and wide. This technology promises safer, greener, and more productive agriculture. Targeted use of antibiotics protects both crops and people from drug-proof germs. And nature benefits when less medicine spreads into soil and water. The future looks bright for farming with precision.","author":[{"family":"Bothe","given":"Hemant"},{"family":"Kamble","given":"Laxmikant"},{"family":"Bothe","given":"Santosh"}],"issued":{"date-parts":[[2024]]},"DOI":"10.20944/preprints202401.0957.v1","URL":"https://doi.org/10.20944/preprints202401.0957.v1","source":"preprints"},{"id":"doi:10.1002/9781394186686.ch7","type":"article-journal","title":"An Advanced Application of UAV – Drone Technologies in Precision Agriculture for Seed Dropping, Fertilizers and Pesticides Spraying and Field Monitoring","abstract":"In precision agriculture, too much advancement has been made to boost crop output. Almost 70% of rural residents in nations like India depend mostly on agriculture for their income. Sensors and the Internet of Things are crucial for creating a more environment-friendly and fruitful global agriculture. Large volumes of data may be intelligently monitored and analyzed to provide deeper understanding and information that can then be used to improve forecasting, judgment, and sensor management. Unmanned aerial vehicles (UAVs), that could potentially quickly be deployed for monitoring reasons, have considerably benefitted precision agriculture. The World Health Organization (WHO) has reported adverse effects from manual fertilizer and pesticide spraying, causing a million cases. To address this issue, drones are being used to spray fertilizers and pesticides at different densities. These UAVs can assist farmers in increasing crop production by monitoring crop health and soil health, reducing environmental harm, and using resources efficiently. Finally, the UAVs are used to spray fertilizer and pesticides as per the observed data results. Drones are used in the majority of applications as a movable aerial platform for high-resolution image capture to determine the impact of pest, disease and weed patches in a cultivated field. The temperature, humidity, light intensity, pressure, and soil moisture of an agriculture field environment is collected through sensors. Importantly, the former can identify the crop health and weed patches through aerial captured images and soil moisture and environment conditions by sensors. Especially, the drone use for precise crop health monitoring is economical, less time-consuming process. The study emphasizes the importance of novel technologies in achieving sustainable pest management in modern agriculture and how this will require collaboration between experts from multiple disciplines, including agronomy, ecology, software development, and engineering.","author":[{"family":"Lawrence","given":"ID"},{"family":"Pavitra","given":"ARR"},{"family":"Karu","given":"Ragupathy"},{"family":"Saravanan","given":"MP"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1002/9781394186686.ch7","URL":"https://doi.org/10.1002/9781394186686.ch7","source":"crossref"},{"id":"doi:10.3390/agriculture13122287","type":"article-journal","title":"Precision Corn Pest Detection: Two-Step Transfer Learning for Beetles (Coleoptera) with MobileNet-SSD","abstract":"Using neural networks on low-power mobile systems can aid in controlling pests while preserving beneficial species for crops. However, low-power devices require simplified neural networks, which may lead to reduced performance. This study was focused on developing an optimized deep-learning model for mobile devices for detecting corn pests. We propose a two-step transfer learning approach to enhance the accuracy of two versions of the MobileNet SSD network. Five beetle species (Coleoptera), including four harmful to corn crops (belonging to genera Anoxia, Diabrotica, Opatrum and Zabrus), and one beneficial (Coccinella sp.), were selected for preliminary testing. We employed two datasets. One for the first transfer learning procedure comprises 2605 images with general dataset classes ‘Beetle’ and ‘Ladybug’. It was used to recalibrate the networks’ trainable parameters for these two broader classes. Furthermore, the models were retrained on a second dataset of 2648 images of the five selected species. Performance was compared with a baseline model in terms of average accuracy per class and mean average precision (mAP). MobileNet-SSD-v2-Lite achieved an mAP of 0.8923, ranking second but close to the highest mAP (0.908) obtained by MobileNet-SSD-v1 and outperforming the baseline mAP by 6.06%. It demonstrated the highest accuracy for Opatrum (0.9514) and Diabrotica (0.8066). Anoxia it reached a third-place accuracy (0.9851), close to the top value of 0.9912. Zabrus achieved the second position (0.9053), while Coccinella was reliably distinguished from all other species, with an accuracy of 0.8939 and zero false positives; moreover, no pest species were mistakenly identified as Coccinella. Analyzing the errors in the MobileNet-SSD-v2-Lite model revealed good overall accuracy despite the reduced size of the training set, with one misclassification, 33 non-identifications, 7 double identifications and 1 false positive across the 266 images from the test set, yielding an overall relative error rate of 0.1579. The preliminary findings validated the two-step transfer learning procedure and placed the MobileNet-SSD-v2-Lite in the first place, showing high potential for using neural networks on real-time pest control while protecting beneficial species.","author":[{"family":"Maican","given":"Edmond"},{"family":"Iosif","given":"Adrian"},{"family":"Maican","given":"Sanda"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13122287","URL":"https://doi.org/10.3390/agriculture13122287","source":"crossref"},{"id":"doi:10.1007/s11119-023-10104-x","type":"article-journal","title":"Thermal imaging for identification of malfunctions in subsurface drip irrigation in orchards","abstract":"Leaks and clogs in drip-irrigated orchards lead to variable yields, reduced efficiency and profitability. Frequent monitoring of irrigation systems by farmers is important but costly, labor-intensive, and not easily implementable on a regular basis. Moreover, in subsurface drip-irrigation systems, it is difficult to visually detect malfunctions. The objective of this study was to develop processing methodologies based on thermal remote sensing, to produce classification models for detecting irrigation malfunctions in orchards, and distinguish between different types of malfunctions. A thermal camera mounted on an unmanned aerial vehicle platform was used to acquire thermal images in three commercial almond and jojoba plantations with subsurface drip irrigation. An image-processing pipeline was developed to extract plant-specific features, and classification models were used to detect malfunctions in individual plants. Plants were segmented using four algorithms: Otsu, continuous max-flow and min-cut, full-width-half-max, and watershed. Thirty-two features were extracted from the canopy temperature of each plant and normalized with meteorological data. The most significant features were selected using a recursive feature elimination method. Three classification models (multiclass, binary, hierarchical) were constructed using five classification algorithms. Performance was evaluated with k-fold cross-validation and an independent test set. In the almond plants orchard, the hierarchical classification approach with support vector machine (SVM) algorithms yielded 68% accuracy and 33% false-positive rate (FPR) for clog detection and 2.8% FPR for leak detection. In the jojoba plantation, the multiclass classification approach with SVM algorithms gave 82% accuracy for clog and leak detection with 0% FPR.","author":[{"family":"Rozenfeld","given":"Stav"},{"family":"Kalo","given":"Noy"},{"family":"Naor","given":"Amos"},{"family":"Dag","given":"Arnon"},{"family":"Edan","given":"Yael"},{"family":"Alchanatis","given":"Victor"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-023-10104-x","URL":"https://doi.org/10.1007/s11119-023-10104-x","source":"crossref"},{"id":"doi:10.1016/j.compag.2023.107970","type":"article-journal","title":"Filling the maize yield gap based on precision agriculture – A MaxEnt approach","abstract":"Precision agriculture (PA) and yield gap (Yg) analysis are promising strategies to achieve the desired sustainable intensification of agricultural production systems. Current crop Yg approaches do not consider the internal field yield variability caused by soil properties. Topographic and edaphic characteristics causing consistent high and low yield patterns in time and space can be interpreted as an ecological niche and used as proxies for potential yield (Yp) and Yg. Ecological niche models (ENMs) are statistical models originally developed to forecast a species’ niche. However, its application to analyse crop yield spatio-temporal variability has never been made. This study aimed to fill this void by developing a novel approach: i) to quantify the magnitude and spatio-temporal distribution of Yp and Yg, ii) to identify the main factors that cause the Yg, and iii) to provide statistical and agronomical interpretation of the data to reduce the Yg. We performed this work using high-resolution maize yield maps from three seasons, with an ancillary dataset composed of soil electrical conductivity, soil properties and digital elevation models provided by “Quinta da Cholda”, Portugal. The yield maps were averaged, resulting in a standardised multiyear yield map. The 90th and 10th yield percentiles were interpreted as proxies for Yp and Yg, and analysed by an ENM machine learning algorithm – maximum entropy (MaxEnt). The average Yg and Yp were quantified as 1.5 and 19.1 ton/ha. Yp was characterised by having silty, richer soils and lower elevations, with several nutritional factors above the critical limits to maintain higher yields. Yg had loam soils coupled with higher relative elevations and lower nutrition content. This innovative modelling approach can efficiently manage high-dimensional spatio-temporal data to support advanced PA solutions, allowing detailed support for narrowing the Yg.","author":[{"family":"Norberto","given":"M"},{"family":"Sillero","given":"N"},{"family":"Coimbra","given":"J"},{"family":"Cunha","given":"M"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1016/j.compag.2023.107970","URL":"https://doi.org/10.1016/j.compag.2023.107970","source":"crossref"},{"id":"doi:10.3920/9789086865147_091","type":"article-journal","title":"Data management for transborder-farming","abstract":"Transborder-farming means to farm small farm plots, which are situated side by side, crossing the existing boundaries of cultivation. This results in a more efficient production process and in increased gross margin. A precondition is an agreement between the participating farmers regarding common crop rotations and cultivation dates. In a research project, transborder-farming has been put into practice to investigate the economic effects and to develop a convenient management system. To document all field work, an automated data acquisition system is needed. It is made up of an automatic process data acquisition system, which has been developed at the Technical University Munich and includes a DGPS receiver and the data processing software, which has been developed within this project. This system delivers process data at a high spatiotemporal resolution and the data management software enables transborder-farming without the noticeable requirement for extra management tasks. Beyond handling transborder-farming the collected data are used for an initial verification that increasing field sizes result in decreasing labour and machinery costs.","author":[{"family":"Rothmund","given":"M"},{"family":"Demmel","given":"M"},{"family":"Auernhammer","given":"H"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_091","URL":"https://doi.org/10.3920/9789086865147_091","source":"crossref"},{"id":"doi:10.1201/9781003541165-10","type":"article-journal","title":"Remote Sensing for Precision Agriculture","abstract":"Research applications of remote sensing in precision agriculture are numerous, and include techniques for detecting water stress, nitrogen stress, weed infestations, fungal disease, and insect damage. Significant advances have been made in identifying key wavelengths and spectral indices at which these stresses influence the reflectance or fluorescence properties of plant pigments and crop canopy architecture. However, little research has been conducted on detecting locations affected by crop stress and simultaneously distinguishing between different types of crop stress. A basic problem is that remote sensing does not typically respond directly to water, nutrient, weed, insect, or disease stresses, rather it responds indirectly to the changes in chlorophyll or crop canopy architecture caused by these crop stresses. For this reason, remote sensing has not yet been widely adopted by farmers for routine use in precision agriculture. The main reasons include the difficulty in interpreting spectral signatures, the slow processing time for data, the high expense, and the need to collect confirmatory data from ground surveys to diagnose causative factors for anomalous spectral reflectance data. Clearly, there is a significant scope for improving the interpretation and utility of remote sensing data for precision agriculture.","author":[{"family":"Miao","given":"Yuxin"},{"family":"Mulla","given":"David"},{"family":"Huang","given":"Yanbo"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1201/9781003541165-10","URL":"https://doi.org/10.1201/9781003541165-10","source":"crossref"},{"id":"doi:10.1007/s11119-024-10172-7","type":"article-journal","title":"From pen and paper to digital precision: a comprehensive review of on-farm recordkeeping","abstract":"Abstract In the present era of agricultural digitalization, documenting on-farm operations is critical. These records contextualize other layers of data and underpin economic analysis and informed decision-making. On-farm recordkeeping is rooted in an ancient tradition and has evolved from pen and paper to digital means integrating diverse tools and methods. These tools vary widely in mode of data recording and this presents challenges in achieving complete, accurate and interoperable data. Assessing this diversity of existing recordkeeping systems is a key step toward the improvement in recordkeeping systems that enhance data quality and interoperability. Despite the importance, as of present, comprehensive studies addressing this challenge are lacking. A systematic review of existing on-farm recordkeeping systems was carried out to address their advantages and weaknesses and to analyze their features and traits, focusing on interoperability and adherence to efficient and comprehensive on-farm recordkeeping. Paper-based recordkeeping, a longstanding and reliable method, is gradually being replaced by digital platforms. Many universities and agencies have released farm management spreadsheets and interactive database forms representing the initial step toward intuitive recordkeeping. Furthermore, farm management software, web apps, and user-friendly smartphone apps are increasingly crucial for handling agricultural big data. Notably, among the surveyed software packages and apps, most of them are not free and only a few support data interoperability. The survey also indicates a scope for further development in open-source tools with automation in recordkeeping. Adopting digital on-farm recordkeeping tools can positively impact both on and off the farm, fostering data interoperability, controlled yet flexible data access, completeness, and appropriate accuracy.","author":[{"family":"Basir","given":"Md"},{"family":"Buckmaster","given":"Dennis"},{"family":"Raturi","given":"Ankita"},{"family":"Zhang","given":"Yaguang"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10172-7","URL":"https://doi.org/10.1007/s11119-024-10172-7","source":"crossref"},{"id":"doi:10.1007/s11119-023-10024-w","type":"article-journal","title":"Statistical diagnostics for sensing spatial residue cover","abstract":"Timely information on within field soil quality spatial variability is pertinent for sustainable agroecosystem management. Although, plant residues constitute a critical input influencing soil quality dynamic, robust baseline residue maps to inform agricultural policy are nonexistent. Remote sensing-based indices can be used to generate maps that can provide timely information on within-field spatial distribution of residue cover. However, heavily used indices such as the Cellulose Absorption Index (CAI), Lignin Cellulose Absorption (LCA) index, or the Shortwave Infrared Normalized Difference Residue Index (SINDRI) rely on data scanned within the 2000 to 2500 nm spectral wavelength window, thus are impractical for mapping because most freely accessible spaceborne sensors collect significant data within the 450 to 1750 nm wavelength range. Here, insitu line transect residue cover measurements were integrated with spectral reflectance data scanned by Cropscan handheld multispectral radiometer (MSR) and satellite sensors, to identify alternative indices within the 450 to 1750 nm wavelength range suitable for monitoring residue cover. The green band reflectance had the highest correlation with spatial variability in residue cover, followed closely by the blue band. Analyzed data shows that Normalized Difference Vegetation Indexwᵢdₑ bₐₙd (NDVIw), preeminently mapped corn (Zea mays) residue cover, with an R² of 0.95 between residue mapped by satellite vis a vis in situ field measurements. The line transect residue measurements from field plots sampled at Aurora (48%) and Badger (57%) fell within the range estimated by satellite (30 to 60%), but this was not true for the Lennox site (72%).","author":[{"family":"Obade","given":"Vincent"},{"family":"Gaya","given":"Charles"},{"family":"Obade","given":"Paul"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10024-w","URL":"https://doi.org/10.1007/s11119-023-10024-w","source":"crossref"},{"id":"doi:10.3920/978-90-8686-947-3_19","type":"article-journal","title":"Follow the leader: a path generator and controller for precision tree scanning with a robotic manipulator","abstract":"This paper presents an algorithm and controller for selectively scanning the vertical elements of fruit trees with a robotic manipulator. The algorithm first segments the foreground tree from the background trees and then fits a sequence of Bezier curves to the output masks on the fly. The velocity controller combines the gradient and a proportional term to keep the branch centred in the image, performing all mathematical operations in pixel space. The algorithm was evaluated on videos from commercial orchards, and the controller was evaluated in a lab environment. The controller was able to maintain a centring accuracy of at least 0.5 cm during most experimental trials.","author":[{"family":"Parayil","given":"N"},{"family":"You","given":"A"},{"family":"Grimm","given":"C"},{"family":"Davidson","given":"JR"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/978-90-8686-947-3_19","URL":"https://doi.org/10.3920/978-90-8686-947-3_19","source":"crossref"},{"id":"doi:10.1007/s11119-024-10198-x","type":"article-journal","title":"Assessing plant traits derived from Sentinel-2 to characterize leaf nitrogen variability in almond orchards: modeling and validation with airborne hyperspectral imagery","abstract":"INTRODUCTION: Optimizing fruit quality and yield in agriculture requires accurately monitoring leaf nitrogen (N) status spatially and temporally throughout the growing season. Standard remote sensing approaches for assessing leaf N rely on proxies like vegetation indices or leaf chlorophyll a + b (Cₐb) content. However, limitations exist due to the Cₐb-N relationship’s saturation and early nutrient deficiency insensitivity. METHODS: The study utilized Sentinel-2 satellite imagery to estimate a set of plant biochemical traits in large almond orchards in a two-year study. These traits, including leaf dry matter, leaf water content, and leaf Cₐb retrieved from the radiative transfer model, were used to explain the observed variability of leaf N. Airborne hyperspectral imagery-derived leaf N using Cₐb and solar-induced fluorescence served as a benchmark for validation. RESULTS: Results demonstrate that plant traits quantified from Sentinel-2 were strongly associated with leaf N variability across the orchard, with a strong contribution from the estimated leaf Cₐb content and leaf dry matter biochemical constituent, outperforming the consistency of vegetation indices. The Sentinel-2 model explaining leaf N variability yielded r² = 0.82 and nRMSE = 13% in a two-year dataset, obtaining consistent performance and trait contribution across both years. CONCLUSION: This study highlights the potential application of Sentinel-2 satellite imagery for monitoring leaf N variability in almond tree orchards. Incorporating plant biochemical traits allows for a more consistent and reliable prediction of leaf N compared to traditional vegetation indices over two years, making it a promising method for precision agriculture applications.","author":[{"family":"Wang","given":"Yue"},{"family":"Suarez","given":"Lola"},{"family":"Hornero","given":"Alberto"},{"family":"Poblete","given":"Tomas"},{"family":"Ryu","given":"Dongryeol"},{"family":"Gonzalez-Dugo","given":"Victoria"},{"family":"Zarco-Tejada","given":"Pablo"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10198-x","URL":"https://doi.org/10.1007/s11119-024-10198-x","source":"crossref"},{"id":"doi:10.1007/s11119-024-10204-2","type":"article-journal","title":"Integration of machine learning models with real-time global positioning data to automate the wild blueberry harvester","abstract":"Efficient mechanical harvesting of wild blueberries across uneven topographies calls for precise header height adjustments to optimize fruit picking. Conventionally, an operator requires manual adjustment of the harvester header to accommodate the spatial variations in plant height, fruit zone, and field terrain. This can result in inadequate header positioning, which leads to berry losses and increased operator stress. This study aimed to investigate the integration of machine learning techniques with real-time geo-location data to develop an innovative system to automate harvesting operations. A supervised machine learning Random Forest (RF) model was trained based on pre-defined header setting data and integrated with the harvester’s controller to predict and position the header height using real-time geo-location data from the Starfire (SF) 6000 Global Positioning System (GPS) receiver. During harvesting, the system’s performance was evaluated at tractor ground speeds (0.31, 0.45, and 0.58 ms⁻¹) and segment lengths (5, 10, and 15 m). Results indicated that segment size minimally affected the system’s ability to adjust header height. However, at the lowest segment length, 5 m, the coefficient of determination was 97.24, 98.12, and 82.71% for the 0.31, 0.45, and 0.58 ms⁻¹, respectively. This study provided convincing results for automating the harvester header based on pre-defined settings, marking a significant step toward complete automation of the wild blueberry harvester. Automation of wild blueberry harvesting can help to increase picking efficiency and enhance profit margins for growers to justify the ever-increasing cost of production.","author":[{"family":"Haydar","given":"Zeeshan"},{"family":"Esau","given":"Travis"},{"family":"Farooque","given":"Aitazaz"},{"family":"Abbas","given":"Farhat"},{"family":"Fraser","given":"Andrew"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10204-2","URL":"https://doi.org/10.1007/s11119-024-10204-2","source":"crossref"},{"id":"doi:10.3390/agriculture13071417","type":"article-journal","title":"Global Navigation Satellite Systems as State-of-the-Art Solutions in Precision Agriculture: A Review of Studies Indexed in the Web of Science","abstract":"Global Navigation Satellite Systems (GNSS) in precision agriculture (PA) represent a cornerstone for field mapping, machinery guidance, and variable rate technology. However, recent improvements in GNSS components (GPS, GLONASS, Galileo, and BeiDou) and novel remote sensing and computer processing-based solutions in PA have not been comprehensively analyzed in scientific reviews. Therefore, this study aims to explore novelties in GNSS components with an interest in PA based on the analysis of scientific papers indexed in the Web of Science Core Collection (WoSCC). The novel solutions in PA using GNSS were determined and ranked based on the citation topic micro criteria in the WoSCC. The most represented citation topics micro based on remote sensing were “NDVI”, “LiDAR”, “Harvesting robot”, and “Unmanned aerial vehicles” while the computer processing-based novelties included “Geostatistics”, “Precise point positioning”, “Simultaneous localization and mapping”, “Internet of things”, and “Deep learning”. Precise point positioning, simultaneous localization and mapping, and geostatistics were the topics that most directly relied on GNSS in 93.6%, 60.0%, and 44.7% of the studies indexed in the WoSCC, respectively. Meanwhile, harvesting robot research has grown rapidly in the past few years and includes several state-of-the-art sensors, which can be expected to improve further in the near future.","author":[{"family":"Radočaj","given":"Dorijan"},{"family":"Plaščak","given":"Ivan"},{"family":"Jurišić","given":"Mladen"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13071417","URL":"https://doi.org/10.3390/agriculture13071417","source":"crossref"},{"id":"doi:10.1007/978-3-031-43548-5_7","type":"article-journal","title":"Remote Sensing in Precision Agriculture","abstract":"Agriculture plays a vital role in feeding the world’s growing population despite facing challenges such as dwindling arable land, water scarcity, changing climatic conditions, and the need for sustainable resource management. To address these challenges and to optimize agricultural productivity, the integration of remote sensing technologies has emerged as a transformative approach within the realm of precision agriculture. Remote sensing, encompassing satellite imagery, drones, and ground-based sensors, provides invaluable data and insights for informed decision-making, resource allocation, and yield optimization. This chapter explores the significance of remote sensing applications in modern agriculture. Satellite imagery, acquired at various spatial and temporal scales, allows farmers, agronomists, and researchers to monitor crop health, identify areas of stress, and assess the impact of environmental factors. Drones equipped with high-resolution cameras and multispectral sensors enable localized data collection, facilitating detailed field-level analysis. Ground-based sensors complement these technologies by providing real-time data on soil moisture, nutrient levels, and weather conditions. The integration of remote sensing data with geographic information systems (GIS) and data analytics tools empowers stakeholders to make precise interventions, leading to reduced resource wastage and increased efficiency. Through the identification of variability within fields, growers can implement site-specific management strategies, tailoring irrigation, fertilization, and pest control practices to the unique needs of each area. This targeted approach not only maximizes crop yield but also minimizes the environmental impact of agricultural operations. Furthermore, remote sensing fosters early detection of disease outbreaks, pest infestations, and nutrient deficiencies. Timely interventions based on accurate and up-to-date information result in improved crop health and reduced reliance on chemical inputs. Additionally, remote sensing assists in monitoring land-use changes, assessing soil erosion, and promoting sustainable land management practices. To conclude, remote sensing applications are revolutionizing agriculture by enabling precise and data-driven decision-making. By harnessing the power of satellite imagery, drones, and ground-based sensors, the agricultural sector can achieve enhanced productivity, resource efficiency, and environmental sustainability.","author":[{"family":"Surendran","given":"U"},{"family":"Nagakumar","given":"KCV"},{"family":"Samuel","given":"Manoj"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/978-3-031-43548-5_7","URL":"https://doi.org/10.1007/978-3-031-43548-5_7","source":"crossref"},{"id":"doi:10.3920/9789086866649_060","type":"article-journal","title":"iSOIL: exploring the soil as the basis for sustainable crop production and precision farming","abstract":"Precision farming is based on the concept of optimising crop production and increasing profit margins by taking into account the spatial within-field variation in soil, soil moisture and other environmental conditions that influence crop growth. To be able to adjust crop and soil management to this natural variation, the type and extent of the variation should be known to the farmer. Ideally in a format that enables him and his machinery to adapt his crop management to the relevant variation in such a way that he can optimise his crop production process in an easy and semiautomated way. This requires reliable and coherent high resolution digital maps of relevant variation such as soil texture, soil organic matter, soil nutrients, soil moisture, slope, aspect, compaction (risk) and erosion risk. The focus of the iSOIL project is on improving fast and reliable mapping of soil properties, soil functions and soil degradation threats. This requires the improvement as well as the integration of geophysical and spectroscopic measurement techniques in combination with advanced soil sampling approaches, digital soil mapping and pedophysical approaches. The outputs of iSOIL encompass methodologies, reliabilities, standards and possibilities for mapping all the above mentioned and can therefore be of great value to precision agriculture. The project aims to supply tools and standards for mapping e.g. to precision agriculture end-users to enable fast, easy and reliable mapping of all relevant soil, hydrological and environmental parameters. The resulting soil property maps can e.g. be used for precision agriculture applications such as variable planting distance of potatoes, variable liming and variable fertiliser application. The soil degradation threats studies, e.g. erosion, compaction and soil organic matter decline can be used to improve the sustainability of current farming practices to ensure fertile and sufficient quality lands for crop production in the future.","author":[{"family":"Egmond","given":"FMV"},{"family":"Nüsch","given":"AK"},{"family":"Werban","given":"U"},{"family":"Sauer","given":"U"},{"family":"Dietrich","given":"P"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_060","URL":"https://doi.org/10.3920/9789086866649_060","source":"crossref"},{"id":"doi:10.1007/s11119-024-10114-3","type":"article-journal","title":"Using mid-infrared spectroscopy as a tool to monitor responses of acidic soil properties to liming: case study from a dryland agricultural soil trial site in South Australia","abstract":"Abstract Soil acidification is an issue for agriculture that requires effective management, typically in the form of lime (calcium carbonate, CaCO 3 ), application. Mid infrared (MIR) spectroscopy methods offer an alternative to conventional laboratory methods, that may enable cost-effective and improved measurement of soil acidity and responses to liming, including detection of small–scale heterogeneity through the profile. Properties of an acidic soil following lime application were measured using both MIR spectroscopy with Partial Least Squares Regression (MIR-PLSR) and laboratory measurements to (a) compare the ability of each method to detect lime treatment effects on acidic soil, and (b) assess effects of the different treatments on selected soil properties. Soil properties including soil pH (in H 2 O and CaCl 2 ), Aluminium (Al, exchangeable and extractable), cation exchange capacity (CEC) and organic carbon (OC) were measured at a single field trial receiving lime treatments differing in rate, source and incorporation. Model performance of MIR-PLSR prediction of the soil properties ranged from R 2 = 0.582, RMSE = 2.023, RPIQ = 2.921 for Al (extractable) to R 2 = 0.881, RMSE = 0.192, RPIQ = 5.729 for OC. MIR-PLSR predictions for pH (in H 2 O and CaCl 2 ) were R 2 = 0.739, RMSE = 0.287, RPIQ = 2.230 and R 2 = 0.788, RMSE = 0.311, RPIQ = 1.897 respectively, and could detect a similar treatment effect compared to laboratory measurements. Treatment effects were not detected for MIR-PLSR-predicted values of CEC and both exchangeable and extractable Al. Findings support MIR-PLSR as a method of measuring soil pH to monitor effects of liming treatments on acidic soil to help inform precision agricultural management strategies, but suggests that some nuance and important information about treatment effects of lime on CEC and Al may be lost. Improvements to prediction model performance should be made to realise the full potential of this approach.","author":[{"family":"Hume","given":"Ruby"},{"family":"Marschner","given":"Petra"},{"family":"Mason","given":"Sean"},{"family":"Schilling","given":"Rhiannon"},{"family":"Mosley","given":"Luke"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10114-3","URL":"https://doi.org/10.1007/s11119-024-10114-3","source":"crossref"},{"id":"doi:10.1007/s11119-024-10176-3","type":"article-journal","title":"Predicting on-farm soybean yield variability using texture measures on Sentinel-2 image","abstract":"Yield forecasting and within-field yield variation is essential information that helps farmers develop sustainable agriculture. However, such information still needs to be included for most of them, and remote sensing is an alternative to provide it. Our objective was to assess Random Forest regression models composed of unique GLCM texture measures as an alternative to usual empirical models that use spectral response and auxiliary data, which is complex and reaches varied results. Eleven GLCM texture models based on eight texture measures of a single spectral layer were assessed to represent soybean field yield variation in two sites and seasons. Several models achieved satisfactory results, reaching R² from 0.90 to 0.95 and RMSE from 0.06 to 0.26 t/ha. Models above 15-window size are recommended for the soybean yield prediction as window size is an essential attribute to GLCM performance. Models derived from the bands individually (red, red-edge, near-infrared, and short wavelength infrared) were more sensitive to the window size than those derived from vegetation indices (EVI, GNDVI, GRNDVI, NDMI, NDRE, NDVI, SFDVI). The data aggregated by texture measures improve the individual spectral responses, providing alternatives to predict soybean within-field yield variation using random forest models.","author":[{"family":"Freitas","given":"Rodrigo"},{"family":"Oldoni","given":"Henrique"},{"family":"Joaquim","given":"Lucas"},{"family":"Pozzuto","given":"João"},{"family":"Amaral","given":"Lucas"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10176-3","URL":"https://doi.org/10.1007/s11119-024-10176-3","source":"crossref"},{"id":"doi:10.1007/s11119-023-10027-7","type":"article-journal","title":"A W-shaped convolutional network for robust crop and weed classification in agriculture","abstract":"Abstract Agricultural image and vision computing are significantly different from other object classification-based methods because two base classes in agriculture, crops and weeds, have many common traits. Efficient crop, weeds, and soil classification are required to perform autonomous (spraying, harvesting, etc.) activities in agricultural fields. In a three-class (crop–weed–background) agricultural classification scenario, it is usually easier to accurately classify the background class than the crop and weed classes because the background class appears significantly different feature-wise than the crop and weed classes. However, robustly distinguishing between the crop and weed classes is challenging because their appearance features generally look very similar. To address this problem, we propose a framework based on a convolutional W-shaped network with two encoder–decoder structures of different sizes. The first encoder–decoder structure differentiates between background and vegetation (crop and weed), and the second encoder–decoder structure learns discriminating features to classify crop and weed classes efficiently. The proposed W network is generalizable for different crop types. The effectiveness of the proposed network is demonstrated on two crop datasets—a tobacco dataset and a sesame dataset, both collected in this study and made available publicly online for use by the community—by evaluating and comparing the performance with existing related methods. The proposed method consistently outperforms existing related methods on both datasets.","author":[{"family":"Moazzam","given":"Syed"},{"family":"Nawaz","given":"Tahir"},{"family":"Qureshi","given":"Waqar"},{"family":"Khan","given":"Umar"},{"family":"Tiwana","given":"Mohsin"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1007/s11119-023-10027-7","URL":"https://doi.org/10.1007/s11119-023-10027-7","source":"crossref"},{"id":"doi:10.3920/9789086866649_062","type":"article-journal","title":"Optimal path planning for field operations","abstract":"Path planning for field operations becomes more and more important. More work is done by workers not knowing the field from experience. A second reason is that in the future more and more operations will done by autonomous vehicles and they require a path. Path planning for rectangular fields is rather simple but for more complex shaped fields tools are needed to support the planning process. GPS developments also enable that more difficult solutions can be realised in practice. With Matlab a tool is developed that reads the boundary coordinates of a field, determines the real vertices, divides the field into convex subfields if necessary, and calculates the costs for different operating directions to find the direction with the lowest costs incurred. Working time is converted to costs to enable the choice to not operate a part of the field for some reason, for example too small in relation to the effort. The tool is tested on some real fields. The results for simple fields are expected. The most optimal direction is the direction parallel to the longest side of the field. For more complex fields that are divided in two or more subfields the solutions are optimal for the individual subfields but the solution for the whole set of subfields is not necessarily optimal because for this interactions between subfields have to be taken into account too. Also, situations where tramlines are not perpendicular to headlands, resulting in small parts of the field either operated twice or not operated at all, have to be taken into account. The developed tool is a good first start but has to be elaborated more to be able to handle more complex field situations and to deliver for these fields also realistic optimal solutions.","author":[{"family":"Hofstee","given":"JW"},{"family":"Spätjens","given":"LEEM"},{"family":"Ijken","given":"H"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_062","URL":"https://doi.org/10.3920/9789086866649_062","source":"crossref"},{"id":"doi:10.3920/9789086865147_066","type":"article-journal","title":"Evaluation of fertiliser spreading strategies","abstract":"The added value using crop status information from adjacent tramlines in fertiliser spreading was investigated for both a centrifugal and pneumatic spreader. For this purpose, a simulation model for virtual fertiliser spreading was developed. The research showed that there was no advantage from using crop status information from adjacent tramlines. This was due to the fact that the compound spread patterns were not able to approximate the crop requirement curve. The best approximation was obtained when compound spread patterns had a shape that corresponded with the crop requirement curve in both longitudinal and transverse directions.","author":[{"family":"Nieuwenhuizen","given":"AT"},{"family":"Hofstee","given":"JW"},{"family":"Lokhorst","given":"C"},{"family":"Müller","given":"J"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_066","URL":"https://doi.org/10.3920/9789086865147_066","source":"crossref"},{"id":"doi:10.1109/icrito61523.2024.10522433","type":"article-journal","title":"Precision Phytopathology in Agriculture: A Federated Learning CNN Framework for Banana Leaf Disease Classification","abstract":"The outbreak of several panicle and foliage diseases causes a major threat to agricultural production and sustainability. This article introduces the disease categorization method for three types of leaf disease that uses the CNN architecture through a federated learning framework to classify them into four dryness levels. In this, four stakeholders, who are data centers that contribute to this collaborative learning, demonstrate its effectiveness in tackling agriculture domains in a wide range of fields of agribusiness. Through profound experiments that we have illustrated and intensive studies of the resulting model, we found that this model is capable of coping with the local variations and transforming them into a highly global learning model. The results of our study shown remarkable accuracy in categorising diseases into four categories of severity: grade, class, grade, and critical. The proof that the macro critical point, micro critical point, and train approaches at the same time was given by the best performance of the model, which had the highest accuracy values. zs_1, zs_2, zs_3, and zs_4 customers mean percentages were 92.74%, 95.79%, 95.9%, and 96.22%, respectively, indicating uniform quality from all categories. The weighted averages, which also consider the distribution structure, broadly resulted in a similar pattern; the scores were 92.74%, 95.81%, 95.88%, and 96.2%. The aggregate individual classes of Micro were almost the same as the Weighted averages, making an indication that Micro's model was accurate in this way. The task shows that federated learning can be successfully applied to solving agriculture problems related to plant disease recognition and thus is closely tied to the broader discussion of sustainable farming strategies.","author":[{"family":"Shukla","given":"Ajay"},{"family":"Joshi","given":"Kireet"},{"family":"Yadav","given":"Ajay"},{"family":"Kukreja","given":"Vinay"},{"family":"Mehta","given":"Shiva"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/icrito61523.2024.10522433","URL":"https://doi.org/10.1109/icrito61523.2024.10522433","source":"crossref"},{"id":"doi:10.53766/rgv/2024.65.1.14","type":"article-journal","title":"Agricultural advantages in soil management practices generated from the use of precision agriculture techniques. Literature review","abstract":"The growing demand for food production, the economic importance of agricultural activities, and the concern with preserving natural resources justify the use of new technologies intended to increase productivity per unit area, reduce production costs, and minimize environmental impacts. Given this, in recent decades, the use of technologies related to Precision Agriculture (AP) became a viable alternative, spreading frantically in the various agricultural activities, encompassing, above all, the great cultures of agribusiness crops such as sugar cane, soy, corn, and cotton highlighting the tools and input application techniques at variable rates on the ground. Therefore, this work aimed to carry out a literature review of the last ten years' main technical/scientific publications related to soil fertility management from application techniques of input at variable rates, emphasizing agronomic results from the use of AP tools.","author":[{"family":"Batista","given":"Jessé"},{"family":"Basilio","given":"Felipe"},{"family":"Souza","given":"Amanda"},{"family":"Fonseca","given":"Elaine"}],"issued":{"date-parts":[[2024]]},"DOI":"10.53766/rgv/2024.65.1.14","URL":"https://doi.org/10.53766/rgv/2024.65.1.14","source":"crossref"},{"id":"doi:10.3390/agriculture13010163","type":"article-journal","title":"Exploring Barriers to the Adoption of Internet of Things-Based Precision Agriculture Practices","abstract":"The production of row crops in the Midwestern (Indiana) region of the US has been facing environmental and economic sustainability issues. There has been an increase in trend for the application of fertilizers (nitrogen &amp; phosphorus), farm machinery fuel costs and decreasing labor productivity leading to non-optimized usage of farm inputs. Literature describes how sustainable practices such as profitability (return on investments), operational cost reduction, hazardous waste reduction, delivery performance and overall productivity might be adopted in the context of precision agriculture technologies (variable rate irrigation, variable rate fertilization, cloud-based analytics, and telematics for farm machinery navigation). The literature review describes low adoption of Internet of Things (IoT)-based precision agriculture technologies, such as variable rate fertilizer (39%), variable rate pesticide (8%), variable rate irrigation (4%), cloud-based data analytics (21%) and telematics (10%) amongst Midwestern row crop producers. Barriers to the adoption of IoT-based precision agriculture technologies cited in the literature include cost effectiveness, power requirements, wireless communication range, data latency, data scalability, data storage, data processing and data interoperability. Therefore, this study focused on exploring and understanding decision-making variables related to barriers through three focus group interview sessions conducted with eighteen (n = 18) subject matter experts (SME) in IoT- based precision agriculture practices. Dependency relationships described between cost, data latency, data scalability, power consumption, communication range, type of wireless communication and precision agriculture application is one of the main findings. The results might inform precision agriculture practitioners, producers and other stakeholders about variables related to technical and operational barriers for the adoption of IoT-based precision agriculture practices.","author":[{"family":"Hundal","given":"Gaganpreet"},{"family":"Laux","given":"Chad"},{"family":"Buckmaster","given":"Dennis"},{"family":"Sutton","given":"Mathias"},{"family":"Langemeier","given":"Michael"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13010163","URL":"https://doi.org/10.3390/agriculture13010163","source":"crossref"},{"id":"doi:10.5958/0974-4576.2024.00070.6","type":"article-journal","title":"Drone technology in precision agriculture for insect pest management : A short review","abstract":"AbstractRecently, crops cultivated in India have been threatened by invasive pests like fall army worm (Spodoptera frugiperda) in corn and Rugose spiraling whitefly in coconut (Aleurodicus rugiperculatous Martin); these pests caused extensive damage during the years 2018 and 2019. The plant protection measures are to be taken on a community basis so as to ensure effective management of pests. In India, more than 80% of farmlands are in the category of small and marginal (&lt;1 ha), so it is very difficult to manage the invasive pests. Drones become indispensable in addressing this problem. Unmanned aerial vehicles, or drones, are used in a variety of fields, including defense, monitoring systems, and disaster relief, but their application in agricultural sciences is still in its infancy. Drones come in three main varieties: fixed-wing, multirotor, and hybrid. Which type is used depends on the application. Size, weight, power source, and automation level determine the other categories. It is necessary to optimize the specified operational parameters, such as flying speed, height, and endurance, in order to employ drones in agriculture and related industries. Furthermore, while putting drone-based mitigation measures into practice, consideration should be given to aspects associated with drone-based spraying, such as droplet size, spread, density, homogeneity, deposition, and penetrability. Despite the fact that drone technology is highly relevant and appropriate for pest management, the adoption of the technology is restricted. Regulatory guidelines have been set across the globe to perform site-specific farm management with higher precision at a very high resolution.","author":[{"family":"Matre","given":"Yogesh"},{"family":"Lad","given":"Anant"},{"family":"Neharkar","given":"Purushottam"},{"family":"Sonkamble","given":"Milind"}],"issued":{"date-parts":[[2024]]},"DOI":"10.5958/0974-4576.2024.00070.6","URL":"https://doi.org/10.5958/0974-4576.2024.00070.6","source":"crossref"},{"id":"doi:10.18280/jesa.570302","type":"article-journal","title":"Game Theory-Based Multi-Hop Routing Protocol with Metaheuristic Optimization-Based Clustering Process in WSN for Precision Agriculture","abstract":"In precision agriculture, a wireless sensor network (WSN) is employed to gather data pertaining to atmospheric conditions.WSN consists of sensor nodes installed at multiple points in a greenhouse for monitoring soil properties like moisture, pesticide levels, air temperature, humidity level and so on.Sensor nodes transmit the measured parametric digital information to a sink node.It further transmits the sensed data to a decision support system.The decision system uses a crop development model to effectively manage irrigation, fertilization, and climate control systems in a greenhouse.This allows for exact control over temperature and humidity levels.By using appropriate inputs, crops may be effectively managed, resulting in improved crop health and increased yield.Reliable transmission data is a crucial design objective for WSN in precision agriculture as the presence of foliage in the transmission channel causes significant attenuation of the radiated waves.Additionally, it may cause scattering and diffraction of signals as well.A dynamic data routing protocol selects the optimum data paths for node data transmission in a WSN.This paper presents a novel energy-efficient multi-hop data routing protocol for WSN precision agriculture applications.The proposed method is named Grey Wolf Optimized Coalitional Game Theory-based (GO_CGT) multi-hop routing protocol is adopted for selecting the required features to measure the importance of the corresponding fitness and dilate the feature map containing less information.Moreover, a rapid and highly which achieves 78.2% of PDR, 12% of energy consumption, 34.7% of end-to-end delay, and 247kbps of throughput.","author":[{"family":"Mohammed","given":"Bilal"},{"family":"Alsaadi","given":"Mahmood"},{"family":"Khalaf","given":"Mohammed"},{"family":"Awad","given":"Alaa"}],"issued":{"date-parts":[[2024]]},"DOI":"10.18280/jesa.570302","URL":"https://doi.org/10.18280/jesa.570302","source":"crossref"},{"id":"doi:10.1109/ic2sdt62152.2024.10696104","type":"article-journal","title":"Soil Analysis Using Deep Learning for Precision Agriculture","abstract":"This research explores the application of deep learning techniques for soil analysis in precision agriculture, focusing on the classification of soil types using convolutional neural networks (CNNs). The study addresses the limitations of traditional soil classification methods, which are often labor-intensive and reliant on expert judgment. The proposed approach involves collecting soil image data, preprocessing it using techniques such as Gabor filtering, and classifying the images with a CNN model. The methodology includes data acquisition, feature extraction, and model training, aiming to accurately predict soil parameters using diverse input data sources like sensor readings and satellite imagery. The potential benefits of this approach include real-time monitoring, optimal fertilizer application, and enhanced crop management, which can contribute to sustainable agricultural practices and food security.","author":[{"family":"Fotabong","given":"Thierry"},{"family":"Muhammad","given":"Abdullahi"},{"family":"Keisham","given":"Murphy"},{"family":"Mehrotra","given":"Tushar"},{"family":"Singh","given":"Rajneesh"},{"family":"Singh","given":"SP"},{"family":"Agrawal","given":"Arun"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/ic2sdt62152.2024.10696104","URL":"https://doi.org/10.1109/ic2sdt62152.2024.10696104","source":"crossref"},{"id":"doi:10.1051/e3sconf/202454013002","type":"article-journal","title":"Harnessing Nanotechnology and Artificial Intelligence for Precision Agriculture in Smart Cities","abstract":"This short review article, titled “Harnessing Nanotechnology and Artificial Intelligence for Precision Agriculture in Smart Cities,” delves into the fusion of nanotechnology, artificial intelligence (AI), and precision farming to drive sustainable agriculture in alignment with the United Nations’ 2030 Sustainable Development Goals. It spotlights the transformative potential of nanotechnology, encompassing both natural and man-made nanoparticles, to enhance crop growth and mitigate environmental impacts. Nano-fertilizers and nano-pesticides are unveiled as promising strategies for optimizing nutrient availability while minimizing harm to ecosystems. The integration of AI into precision farming, supported by cutting-edge nanoinformatics, emerges as a linchpin for the establishment of safe and sustainable agricultural practices, enabling smart and resilient agriculture. However, as this integrated approach accelerates progress and provides vital insights for addressing contemporary agricultural challenges, it also underscores the paramount importance of scrutinizing nanotechnology’s effects on soil microbial communities and plant health. The phytotoxicity of nanoparticles, contingent upon size, concentration, and plant species, necessitates further examination. In conclusion, this comprehensive article calls for interdisciplinary collaboration to fully exploit the potential of nanotechnology and AI in transforming agriculture, all the while ensuring the preservation of environmental and human health and advancing the global sustainability agenda for agriculture in smart cities by 2030.","author":[{"family":"Singh","given":"Swati"},{"family":"Jakhar","given":"Sunil"},{"family":"Kulhar","given":"Kuldeep"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1051/e3sconf/202454013002","URL":"https://doi.org/10.1051/e3sconf/202454013002","source":"crossref"},{"id":"doi:10.26634/jfet.19.2.20481","type":"article-journal","title":"Advancing precision agriculture through multi-objective optimization using butterfly algorithm","abstract":"Wireless Sensor Networks (WSNs) are transforming precision agriculture by enabling seamless monitoring and control of key factors such as temperature, humidity, solar radiation, soil moisture, and various dissolved compounds. This technology enhances efficiency and productivity while reducing costs. However, optimizing coverage area and energy efficiency in precision agriculture WSNs presents significant challenges. To address these challenges, our work focuses on developing innovative solutions inspired by advanced algorithms and state-of-the-art techniques for WSNs. Our primary objective is to improve area coverage and reduce energy consumption in precision agriculture WSNs. We are developing algorithms that can adapt to diverse agricultural landscapes. Through simulations, we aim to evaluate the performance and impact of our novel algorithm on precision agriculture applications. These simulations will provide valuable insights into the effectiveness of our algorithm in enhancing coverage area and energy efficiency in WSNs. Furthermore, our research aims to contribute to the broader field of WSNs by providing a detailed analysis of the challenges and opportunities in optimizing coverage area and energy efficiency in agricultural settings. By leveraging advanced algorithms and techniques, we aim to enhance the capabilities of WSNs in precision agriculture, leading to more sustainable and efficient farming practices.","author":[{"family":"Grandhimi","given":"Lahari"},{"family":"Tejaswini","given":"Thokachichu"},{"family":"Sivalasetty","given":"Sindhu"},{"family":"Nandigama","given":"Induja"},{"family":"Saida","given":"Rao"},{"family":"Chintalapudi","given":"VS"}],"issued":{"date-parts":[[2024]]},"DOI":"10.26634/jfet.19.2.20481","URL":"https://doi.org/10.26634/jfet.19.2.20481","source":"crossref"},{"id":"doi:10.9734/jeai/2024/v46i22309","type":"article-journal","title":"Performance Evaluation of Manual Seeder Machine for Precision Farming","abstract":"Proper placement of seeds in the field is the most important operation to obtain an optimum yield of the crop. In India, about 75% of the landholders are small and have marginal land-holding capacity. Considering the limitations due to costly seed, the traditional method of manual dibbling, labor shortage, and small marginal land holding pattern there is a need for small manual planters for small and marginal landholders. Cotton, the white gold, is the king of textile, fibers and it is an important worldwide cash crop. The sowing of cotton is labor intensive as its planting requires 3-4 man-days/ha. Because of the above, the manual seeder was tested in the laboratory as well as in the field as per IS code: 6316-1993 with specific objectives. Laboratory analysis of manual seeder as seed rate (2.85 kg/ha and 2.88 kg/ha), seed damage (7.84% and 7.74%), and seed uniformity (62 cm and 64 cm) of cotton and castor crop respectively. Field analysis of manual seeder as coefficient of uniformity (91.63% and 93.23%), depth of seed placement (5.7 cm and 5.9 cm), speed of operation (1.82 km/h 1.84 km/h), theoretical field capacity (0.93 ha/h and 0.93 ha/h), effective field capacity (0.166 ha/h 0.171 ha/h), field efficiency (86.01% and 88.60%), draft (9.54 kgf and 10.46 kgf), energy consumption (10.93 MJ/ha and 10.04 MJ/ha) and cost of operation (440 Rs/ha and 445 Rs/ha) of cotton and castor crop respectively.","author":[{"family":"Balas","given":"PR"},{"family":"Lakhani","given":"AL"},{"family":"Pargi","given":"SJ"},{"family":"Mehta","given":"TD"},{"family":"Makavana","given":"JM"}],"issued":{"date-parts":[[2024]]},"DOI":"10.9734/jeai/2024/v46i22309","URL":"https://doi.org/10.9734/jeai/2024/v46i22309","source":"crossref"},{"id":"doi:10.48175/ijarsct-17860","type":"article-journal","title":"IOT Based Automated Hydroponics System for Precision Agriculture","abstract":"Growing plants hydroponically can be a great option for plants that are traditionally hard to grow in soil due to specific requirements. The aim of this work is to design and construct an indoor automatic vertical hydroponic system that does not depend on the outside climate. The designed system is capable to grow common type of crops that can be used as a food source inside homes without the need of large space. The design of the system was made after studying different types of vertical hydroponic systems in terms of price, power consumption and suitability to be built as an indoor automated system. A microcontroller was working as a brain of the system, which communicates with different types of sensors to control all the system parameters and to minimize the human intervention. An open internet of things (IoT) platform was used to store and display the system parameters and graphical interface for remote access. The designed system is capable of maintaining healthy growing parameters for the plants with minimal input from the user. The functionality of the overall system was confirmed by evaluating the response from individual system components and monitoring them in the IoT platform","author":[{"family":"Kavitha","given":"Mrs"},{"family":"Sivabalan","given":"Mr"},{"family":"Pahalavan","given":"Mr"},{"family":"Boominathan","given":"Mr"},{"family":"Logeswaran","given":"Mr"}],"issued":{"date-parts":[[2024]]},"DOI":"10.48175/ijarsct-17860","URL":"https://doi.org/10.48175/ijarsct-17860","source":"crossref"},{"id":"doi:10.1016/j.cles.2024.100132","type":"article-journal","title":"Smart agriculture technology: An integrated framework of renewable energy resources, IoT-based energy management, and precision robotics","abstract":"Modern agricultural practices encounter challenges related to operational efficiency and environmental effects. This prompts a demand for innovative solutions to foster sustainability in farming while emphasizing the limitations of conventional farming methods. To address these challenges in modern agriculture systems, this research proposes a comprehensive framework for smart farming. The proposed framework comprises of three technology integrations: 1) an efficient integration of renewable energy resources (RERs) with solar panels and battery energy storage systems (BESS), 2) an IoT-based environmental monitoring for precision irrigation, and 3) an android application-controlled precision robotic system for targeted chemical application. The proposed framework investigates a case study on Sharjah, United Arab Emirates (UAE) to explore and analyze optimal scenarios of multiple energy resources. Results demonstrate successful cross-prototype integration through the Blynk IoT platform providing users with a unified interface. Furthermore, the results provide a comprehensive analysis and investigation into the interactions between RERs and the grid across various combinations. The findings indicate the potential of this framework to revolutionize agriculture and thus offer a sustainable, efficient, and technologically advanced approach. It also represents the contribution of a complete solution to modern agricultural challenges presenting tangible results for a promising future in smart and sustainable farming practices.","author":[{"family":"Rehman","given":"Anis"},{"family":"Alamoudi","given":"Yasser"},{"family":"Khalid","given":"Haris"},{"family":"Morchid","given":"Abdennabi"},{"family":"Muyeen","given":"SM"},{"family":"Abdelaziz","given":"Almoataz"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1016/j.cles.2024.100132","URL":"https://doi.org/10.1016/j.cles.2024.100132","source":"crossref"},{"id":"doi:10.23919/splitech61897.2024.10612377","type":"article-journal","title":"Design of a Low-Cost Wireless Communication System for Driving Precision Agriculture Through RTK Integration","abstract":"Precision agriculture optimizes farming practices by minimizing resource use through site-specific measurements and treatments, with georeferencing machinery playing a crucial role for precise navigation and safety. The SIRTRACK project, funded by INAIL, aims to enhance unmanned agricultural tractor safety by integrating ultra-wideband localizers, LIDARs, depth cameras, and real-time kinematics navigation systems. This multi-technology approach addresses visibility challenges in agricultural environments and improves obstacle detection by cross-verifying data from multiple sources. The paper discusses the development of a communication system critical for transmitting RTK data from a base station to agricultural vehicles in the field, ensuring accurate positioning and operational efficiency. By selecting an appropriate radio propagation model, the study aims to determine which cost-effective and reliable communication device can be used to ensure a precise vehicle navigation and a long-term project sustainability.","author":[{"family":"Chietera","given":"Francesco"},{"family":"Rossi","given":"Pierluigi"},{"family":"Assettati","given":"Leonardo"},{"family":"Vita","given":"Leonardo"},{"family":"Gattamelata","given":"Davide"},{"family":"Puri","given":"Daniele"},{"family":"Monarca","given":"Danilo"},{"family":"Catarinucci","given":"Luca"}],"issued":{"date-parts":[[2024]]},"DOI":"10.23919/splitech61897.2024.10612377","URL":"https://doi.org/10.23919/splitech61897.2024.10612377","source":"crossref"},{"id":"doi:10.1109/iceca63461.2024.10800784","type":"article-journal","title":"Enhanced Detection of Brinjal Diseases using YOLOv8: A High-Accuracy Real-Time Model for Precision Agriculture","abstract":"The rapid and accurate identification of diseases in brinjal (eggplant) crops is essential for ensuring high agricultural productivity and reducing losses. Traditional methods of disease detection are often time-consuming, require expert knowledge, and can be prone to human error. To address these challenges, this study proposes an automatic brinjal disease identification system utilizing the YOLOv8 (You Only Look Once version 8) algorithm, which is known for its superior performance in object detection tasks.The methodology involved training the YOLOv8 model on a comprehensive dataset comprising images of brinjal leaves affected by various diseases. The dataset was annotated to ensure accurate labelling of disease symptoms. The model’s performance was evaluated on the basis of key metrics, including accuracy, precision, recall, and F1 score. The YOLOv8 algorithm demonstrated a significant improvement over previous models, achieving an impressive accuracy of $95 \\%$. Comparative analysis with earlier versions of YOLO and other state-of-the-art object detection algorithms revealed that YOLOv8 not only outperformed these models in accuracy but also offered faster processing times, making it suitable for real-time applications. The results indicate that the proposed system can effectively identify and classify brinjal diseases with a high degree of accuracy, thus enabling timely interventions. This system has the potential to be integrated into precision agriculture practices, where continuous monitoring of crops is necessary to optimize yield and minimize the use of pesticides. Future research will focus on expanding the training dataset to include a wider variety of disease conditions and environmental factors and exploring the integration of this system with other agricultural technologies to increase its practical applicability.","author":[{"family":"Sandhya","given":"Annevena"},{"family":"Babu","given":"Pottapinjara"},{"family":"Srinivas","given":"UM"},{"family":"Sravanthi","given":"B"},{"family":"Kumar","given":"Ksv"},{"family":"Rajeswaran","given":"N"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/iceca63461.2024.10800784","URL":"https://doi.org/10.1109/iceca63461.2024.10800784","source":"crossref"},{"id":"doi:10.1109/iciptm59628.2024.10563259","type":"article-journal","title":"Towards Precision Agriculture: A Unified CNN and Random Forest Framework for Jasmine Leaf Disease Recognition","abstract":"The model's abstract performance characteristics of categorization across several classes are highlighted, with special attention paid to accuracy, F1-Score, recall, encouragement, and support percentage. The model is tested using ten distinct classes, known to be Significant Levels 1 through 10. Remember that accuracy and the F1-Score were recognized parameters for determining if a model was suitable for classification. Out of all the affirmative predictions, the accuracy percentages for each category vary between 89.87% to 93.49%, showing that the model can accurately recognize instances of each class. Recall values also span from 89.65% to 92.89%, indicating the percentage of true positive occurrences that the model correctly recognizes. The F1-Score, or harmonic average of accuracy and recall, indicates an acceptable assessment of the model's overall accuracy, ranging from 90.96% to 92.89%. Every class's frequency of occurrences is shown in the support column, which has values between 785 and 915. In the support % column, you can see the percentage of every class throughout the whole dataset. Overall model precision is represented by the percentage of successfully recognized occurrences (81.83%) across all classes. These three figures—Macro, Weighted, or Micro Average—indicate the overall effectiveness of the model. Macro Average yields 91.77% for the unweighted median of precision, recall, along with F1-Score. The weighted average produces a standard deviation of 91.79% by weighing the contribution of each class based on its support. At the score of 91.79%, the Micro Average displays the average accuracy over all instances. Across multiple classes, the model shows good accuracy, recall, or F1- Score; weighted averages highlight the balanced contribution of each class to overall performance. The model's claimed accuracy of 81.83% suggests that it can correctly classify cases over the whole dataset.","author":[{"family":"Kumar","given":"Ravi"},{"family":"Jain","given":"Anuj"},{"family":"Sharma","given":"Vikrant"},{"family":"Das","given":"Purushottam"},{"family":"Midha","given":"Manu"},{"family":"Singh","given":"Mukesh"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/iciptm59628.2024.10563259","URL":"https://doi.org/10.1109/iciptm59628.2024.10563259","source":"crossref"},{"id":"doi:10.13005/bbra/3324","type":"article-journal","title":"Precision Agriculture Monitoring System","abstract":"ABSTRACT: Smart agriculture systems leverage advanced versions such as the Internet of Things, sensor networks, and data visualisation methods to optimize farming practices, improve crop yield, and reduce resource consumption. These systems integrate various sensors to monitor environmental parameters such as soil moisture, temperature, humidity, and light intensity. The data which is collected data is analyzed in real-time to provide actionable insights for farmers, enabling precision agriculture. Automated irrigation systems can adjust watering schedules based on soil moisture levels, ensuring optimal water usage. Additionally, smart agriculture systems can include pest detection and weather forecasting capabilities, allowing for timely interventions and better risk management. By utilizing these technologies, farmers can enhance productivity, minimize waste, and promote sustainable farming practices, ultimately contributing to food security and environmental conservation. The paper's feature involves creating a system that can monitor temperature, humidity, moisture, and animal movement in agricultural fields using Arduino sensors. It will send SMS and app notifications to the farmer's smartphone in case of any issues, using Wi-Fi/3G/4G.","author":[{"family":"Naidu","given":"Kuriti"},{"family":"Babu","given":"Kannipamula"},{"family":"Sai","given":"Chinthala"},{"family":"Ganesh","given":"Pediredla"},{"family":"Sai","given":"Tenkani"},{"family":"Naidu","given":"Nadupuru"},{"family":"Praneeth","given":"Chargundla"},{"family":"Sumanth","given":"Gudimalla"}],"issued":{"date-parts":[[2024]]},"DOI":"10.13005/bbra/3324","URL":"https://doi.org/10.13005/bbra/3324","source":"crossref"},{"id":"doi:10.59613/global.v2i7.243","type":"article-journal","title":"The Role of Precision Agriculture, Climate-Smart Farming, and Sustainable Supply Chain Management in Boosting Agricultural Productivity in 2024","abstract":"This study explores the role of precision agriculture, climate-smart farming, and sustainable supply chain management in boosting agricultural productivity in 2024. The primary objective is to qualitatively analyze the literature to understand how these innovative practices contribute to enhancing agricultural productivity and sustainability. The research employs a qualitative literature review methodology, synthesizing findings from academic articles, industry reports, case studies, and empirical studies to provide a comprehensive overview of the current state of knowledge in this field. The literature review methodology involves systematically collecting and analyzing scholarly sources that discuss various aspects of precision agriculture, climate-smart farming, and sustainable supply chain management. The study categorizes the literature into key themes, such as the technological advancements in precision agriculture, the principles and practices of climate-smart farming, and the impact of sustainable supply chain management on agricultural productivity and sustainability. Thematic analysis is used to identify patterns and trends in how these practices interact to influence agricultural outcomes. The findings indicate that precision agriculture, through the use of advanced technologies like GPS, IoT, and AI, enables farmers to optimize field-level management regarding crop farming. This leads to increased yield, reduced waste, and better resource utilization. Climate-smart farming practices, including crop diversification, improved irrigation techniques, and soil health management, are essential for adapting to climate change and mitigating its impacts on agriculture. Sustainable supply chain management ensures that agricultural products are produced, processed, and distributed in ways that minimize environmental impact and enhance economic viability.","author":[{"family":"Ansar","given":"Muh"},{"family":"Maemunah","given":"Maemunah"},{"family":"Said","given":"Sadly"},{"family":"Rahmadani","given":"Elfi"},{"family":"Dahliana","given":"AB"}],"issued":{"date-parts":[[2024]]},"DOI":"10.59613/global.v2i7.243","URL":"https://doi.org/10.59613/global.v2i7.243","source":"crossref"},{"id":"doi:10.7160/aol.2024.160304","type":"article-journal","title":"A Multi-Method Approach to Assess the Adoption of Precision Agriculture Technology in Brazil","abstract":"Precision Agriculture (PA) application aims to increase crop productivity while minimizing environmental impacts. We analyzed the topics most studied in the advancement of crop production in Brazil by applying the concepts of PA using the systematic literature review (SLR). A multi-method approach combined an SLR applying the PRISMA method and secondary data analysis. We found five clusters of technologies using the PA concept related to hardware development and four clusters related to applying technologies to software development in the PA concept. Most topics focused on using sensors to control water (soil and environment), soil electrical conductivity, and data communication. The focus on sustainability led researchers to reduce chemical products related to fertilizers and pesticides using Variable Rate Fertilizers (VRT) and reducing the environmental loading. According to the research results, it was evident that PA technology might help farmers make more accurate decisions about cultivation, production, harvest, and soil management. The availability of decision support systems powered by big data and artificial intelligence to select the best crop for a given season and soil might assist Brazil's sustainable growth of food production.","author":[{"family":"Ivale","given":"André"},{"family":"Nããs","given":"Irenilza"},{"family":"Jani","given":"Marcelo"}],"issued":{"date-parts":[[2024]]},"DOI":"10.7160/aol.2024.160304","URL":"https://doi.org/10.7160/aol.2024.160304","source":"crossref"},{"id":"doi:10.1109/iciteics61368.2024.10625281","type":"article-journal","title":"Advanced Deep Learning Model for Multi-Disease Prediction in Potato Crops: A Precision Agriculture Approach","abstract":"Potato farming is a crucial aspect of global agriculture, playing a pivotal role in ensuring food security and economic stability. However, the impact of diseases on potato plants poses a significant threat to both crop yield and quality. This study concentrates on the early identification and categorization of seven common potato diseases, including Early Blight, Late Blight, Blackleg, Potato Virus Y, Potato Cyst Nematode, along with two additional diseases. The proposed model employs deep learning techniques and consists of a complicated blend of three layers of convolutional learning, three maximally pooled layers, and two layers that are completely interconnected. The study consists of four phases. dataset preparation, model architecture creation, testing and evaluation, and comparison analysis. The goal is to improve our awareness of potato illnesses and help establish effective disease control techniques.","author":[{"family":"Kumar","given":"Ravi"},{"family":"Jain","given":"Anuj"},{"family":"Sharma","given":"Vikrant"},{"family":"Jain","given":"Nitin"},{"family":"Das","given":"Purushottam"},{"family":"Sahni","given":"Pooja"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/iciteics61368.2024.10625281","URL":"https://doi.org/10.1109/iciteics61368.2024.10625281","source":"crossref"},{"id":"doi:10.37394/232017.2024.15.5","type":"article-journal","title":"Internet of Things: Agriculture Precision Monitoring System based on Low Power Wide Area Network","abstract":"Nowadays, many people around the world depend mostly on agriculture for their livelihood. In the majority of countries around the world, it is the most significant occupation for many families. Unfortunately, farmers, particularly in oil palm plantations, continue to rely on age-old practices. One of the key elements in achieving high and long-term oil palm production on peat is the adoption of efficient precision water management. In essence, this means maintaining the water table at the necessary depth. Because of the peat's persistently low water table, oil palm productivity has sharply decreased. In this work, an Internet of Things (IoT) for precision agriculture monitoring is developed using a long-range wide area network (LoRaWAN) algorithm. Based on an approach point of view, a LoRaWAN is a long-range, low-power, low-bitrate wireless telecommunications system meant to be used as part of the Internet of Things architecture. The end devices link to gateways through a single wireless hop using LoRaWAN. These gateways function as transparent bridges, relaying messages from the end devices to a central network server. The ultimate result is the creation of a precision water management assistance algorithm employing LoRaWAN and IoT that is both affordable and effective.","author":[{"family":"Roslee","given":"Mardeni"},{"family":"Woon","given":"Tim"},{"family":"Sudhamani","given":"Chilakala"},{"family":"Irawati","given":"Indrarini"},{"family":"Darlis","given":"Denny"},{"family":"Osma","given":"Anwar"},{"family":"Jusoh","given":"Mohamad"}],"issued":{"date-parts":[[2024]]},"DOI":"10.37394/232017.2024.15.5","URL":"https://doi.org/10.37394/232017.2024.15.5","source":"crossref"},{"id":"doi:10.1088/1755-1315/1308/1/012053","type":"article-journal","title":"A Cutting-Edge Precision Agriculture Technology to Support the Sustainable Oil Palm Industry","abstract":"Abstract One of the most important factors in attaining sustainability in oil palm plantations is proper production input management in accordance with Good Agronomic Practices. For controlling plant disease and fertilizing, it can be started with an accurate monitoring technique to identify disease infection and the level of leaf nutrients in the field. The monitoring method should also be inexpensive, rapid, less time-consuming, and repeatable. This study has demonstrated how image classification (remote sensing) can be used to locate oil palm trees that have the Basal Stem Rot (BSR) disease and to estimate the nutritional level of the leaves. The healthy and BSR-infected palms had been effectively recognized and mapped using the remote sensing approach, which was used in conjunction with machine learning as well as a multispectral camera from a satellite and UAV. Furthermore, the use of a UAV and Mapir camera had resulted in a good prediction of N, P, K, and Mg content in the palm leaves; therefore, it may be practical to monitor leaf nutrient status in the oil palm plantations.","author":[{"family":"Santoso","given":"H"},{"family":"Yusuf","given":"MA"},{"family":"Rahutomo","given":"S"},{"family":"Madiyuanto"},{"family":"Winarna"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1088/1755-1315/1308/1/012053","URL":"https://doi.org/10.1088/1755-1315/1308/1/012053","source":"crossref"},{"id":"doi:10.1088/1755-1315/1418/1/012054","type":"article-journal","title":"Integrating Remote Sensing and GIS for Precision Agriculture: Leveraging Google Earth Engine for Enhanced Agricultural Management","abstract":"Abstract This study aims to develop a plant health monitoring platform using Google Earth Engine and Sentinel-2 satellite imagery. This platform enables real-time and accurate monitoring of plant conditions in Ponorogo Regency, supporting better decision-making in agricultural management. The platform utilizes high-resolution multispectral data such as the NDVI, Chlorophyll Vegetation Index, and Normalized Difference Built-up Index to generate vegetation indices, providing comprehensive information about plant structure and condition. The Google Earth Engine platform offers a robust platform for monitoring and analysis functions within the platform, providing valuable insights for precision agriculture applications","author":[{"family":"Handoko","given":"Eko"},{"family":"Fahriza","given":"Achmad"},{"family":"Muryono","given":"Mukhamad"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1088/1755-1315/1418/1/012054","URL":"https://doi.org/10.1088/1755-1315/1418/1/012054","source":"crossref"},{"id":"doi:10.3920/9789086866649_054","type":"article-journal","title":"Comparison of different EC-mapping sensors","abstract":"Digital Soil Mapping becomes more and more important not only in Precision Farming. In the past, miscellaneous technologies and sensors, including geophysical techniques were tested to get information about the spatial variability of the soil properties. Especially the measurement of the electrical conductivity (EC) may be useful for delineating heterogeneity in soil parameters like texture, water content as well as fluid conductivity, compaction and organic matter. Conductivity measurements can be performed either using an electromagnetic method or working with capacitive or galvanic coupling electrodes. In this context, the EM38 (Geonics, Canada), the Ohmmapper (Geometrics, USA), the Veris 3100 (Veris technologies, USA) and the ARP (Geocarta, France) are recently the most popular devices. A new soil mapping system – the Geophilus electricus is based on rolling electrodes moved by a vehicle and combined with a special conductivity instrument as well with a GPS-system. All existing sensors differ not only concerning the working principle; also the depth range and the depth sensitivity are different. In this paper, the new sensor Geophilus electricus is presented. Measurements were performed at different scales and landscapes and they were compared with existing instruments. The conductivity data were quite similar. Because Geophilus is capable to measure ECa (apparent electrical conductivity) for five channels simultaneously, we get more detailed information also about the vertical structure that means about layers within the investigated depth range. Additional information about the spectral behaviour not only of EC but also of the phase shift is useful to characterize soil properties.","author":[{"family":"Lueck","given":"E"},{"family":"Spangenberg","given":"U"},{"family":"Ruehlmann","given":"J"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866649_054","URL":"https://doi.org/10.3920/9789086866649_054","source":"crossref"},{"id":"doi:10.1016/j.atech.2024.100483","type":"article-journal","title":"Enhancing precision agriculture: A comprehensive review of machine learning and AI vision applications in all-terrain vehicle for farm automation","abstract":"The automation of all-terrain vehicles (ATVs) through the integration of advanced technologies such as machine learning (ML) and artificial intelligence (AI) vision has significantly changed precision agriculture. This paper aims to analyse and develop trends to provide comprehensive knowledge of the current state of ATV-based precision agriculture and the future possibilities of ML and AI. A bibliometric analysis was conducted through network diagram with keywords taken from previous publications in the domain. This review comprehensively analyses the potential of machine learning and artificial intelligence in transforming farming operations through the automation of tasks and the deployment of all-terrain vehicles. The research extensively analyses how machine learning methods have influenced several aspects of agricultural activities, such as planting, harvesting, spraying, weeding, crop monitoring, and others. AI vision systems are being researched for their ability to enhance precise and prompt decision-making in ATV-driven agricultural automation. These technologies have been thoroughly tested to show how they can improve crop yield, reducing overall investment, and make farming more efficient. Examples include machine learning-based seeding accuracy, AI-enabled crop health monitoring, and the use of AI vision for accurate pesticide application. The assessment examines challenges such as data privacy problems and scalability constraints, along with potential advancements and future prospects in the field. This will assist researchers and practitioners in making well-informed judgments regarding farming practices that are efficient, sustainable, and technologically robust.","author":[{"family":"Padhiary","given":"Mrutyunjay"},{"family":"Saha","given":"Debapam"},{"family":"Kumar","given":"Raushan"},{"family":"Sethi","given":"Laxmi"},{"family":"Kumar","given":"Avinash"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1016/j.atech.2024.100483","URL":"https://doi.org/10.1016/j.atech.2024.100483","source":"crossref"},{"id":"doi:10.1109/metroagrifor58484.2023.10424090","type":"article-journal","title":"Bio-Inspired Complete Coverage Path Planner for Precision Agriculture in Dynamic Environments","abstract":"This paper proposes a bio-inspired Complete Coverage Path Planner suitable for several precision agriculture tasks, such as terrain and crop mapping, inspection, and crop spraying. This grid-based method reproduces the dynamics of the neural activity in a biological neural system to represent dynamically varying environments. By providing appropriate inputs to the neurons of the grid, their neural activity can be exploited to guide the robot towards uncovered regions of the area and enforce the desired coverage pattern. Both known and unexpected obstacles can be easily handled, since the sudden discovery of an obstacle simply modifies the local neural activity online. Thus, the need for complete re-planning phases is canceled. A deadlock-escaping mechanism is also proposed to efficiently recover from dead ends. Finally, simulation results are provided to show the flexibility and effectiveness of the method in dynamic environments.","author":[{"family":"Celestini","given":"Davide"},{"family":"Primatesta","given":"Stefano"},{"family":"Capello","given":"Elisa"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/metroagrifor58484.2023.10424090","URL":"https://doi.org/10.1109/metroagrifor58484.2023.10424090","source":"crossref"},{"id":"doi:10.13031/aim.202300729","type":"article-journal","title":"Barriers to Adoption of Precision Agriculture Competencies in Secondary Agriculture Education Programs: A Case Study","abstract":"Abstract. Precision agriculture has the ability to increase production, reduce costs, increase returns, and reduce environmental impacts if adopted and implemented successfully (Shannon et al., 2018). Which is why the successful adoption and implementation of precision agriculture technologies and practices is imperative to the future of agriculture. The future of the agriculture industry starts with secondary agriculture education students and learning about precision agriculture technologies and practices used within the agriculture industry throughout secondary agriculture education programs will better prepare them for the world they are to inherit (Heidenreich et al., 2018). The purpose of this study was to describe [STATE] secondary agriculture science teachers‘ barriers to adopting precision agriculture competencies. Ten secondary agriculture science teachers were selected for the study using purposeful sampling to ensure the participants purposefully provided information regarding the research problem. Semi-structured interviews were conducted, along with classroom observations and document analysis to ensure data triangulation. The constant comparative method of analysis was used based on the views of Stake (1995), to develop holistic themes. Teachers indicated the importance and relevance of precision agriculture, but none of the participants in the study have decided to fully adopt precision agriculture competencies in their curriculum. The decision-making process and the reasons teachers make the decision to adopt or not adopt precision agriculture competencies were explored. Four barriers to adoption of precision agriculture competencies were revealed and include the lack of time, the lack of equipment and/or funding, the lack of curriculum, and the lack of knowledge.","author":[{"family":"Reynolds","given":"Chad"},{"family":"Tummons","given":"John"},{"family":"Mott","given":"Rebecca"}],"issued":{"date-parts":[[2023]]},"DOI":"10.13031/aim.202300729","URL":"https://doi.org/10.13031/aim.202300729","source":"crossref"},{"id":"doi:10.1109/sceecs61402.2024.10481981","type":"article-journal","title":"IoT and IoE transformations in precision farming agriculture : Sensor based monitoring, Automated irrigation and Livestock monitoring","abstract":"The fusion of Internet of Things (IoT) and Internet of Everything (IoE) technologies is driving a significant revolution in the agricultural sector. The significant developments in precision agriculture enabled by sensor-based monitoring, automated irrigation systems, and livestock tracking via IoT and IoE are summarized in this abstract. By delivering real-time data on numerous environmental conditions, IoT-enabled sensor networks have transformed farming practices. With the help of these sensors, farmers can make informed decisions about things like soil moisture levels, temperature, humidity, and nutrient content. Automated irrigation systems, which have advanced thanks to IoT and IoE technology, are crucial to precision agriculture. To precisely supply the proper amount of irrigation, smart irrigation controllers use information from soil moisture sensors, weather forecasts, and crop requirements.","author":[{"family":"Shrivastav","given":"Varun"},{"family":"Yadav","given":"Mohit"},{"family":"Sharma","given":"Aman"},{"family":"Kumar","given":"Deepak"},{"family":"Sharma","given":"Sumit"},{"family":"Chauhan","given":"Amarjeet"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/sceecs61402.2024.10481981","URL":"https://doi.org/10.1109/sceecs61402.2024.10481981","source":"crossref"},{"id":"doi:10.1016/j.jclepro.2024.143724","type":"article-journal","title":"Cooperative performance and lead firm support in cleaner production adoption: SEM-fsQCA analysis of precision agriculture acceptance in Vietnam","abstract":"To drive sustainable agricultural development, farmers in developing countries must prioritize adoption of precision agriculture (PA) as a cleaner production practice. This study investigates factors influencing smallholder rice farmers' behavioral intention (BI) to adopt such technology in Vietnam. Data from 568 farmers was analyzed using Structural Equation Modeling (SEM) and fuzzy-set Qualitative Comparative Analysis (fsQCA). This study makes a significant contribution to extending the Unified Theory of Acceptance and Use of Technology (UTAUT) by demonstrating the substantial positive influence of lead firm support on the intention to adopt PA technology. Also, a key novelty of this research is its exploration of the moderating role of cooperatives’ performance in enhancing the effects of external support factors, such as government and lead firms. Additionally, the fsQCA indicates that the combination of strong external support from the government, lead firms, and cooperatives can foster high adoption intentions even under challenging internal facilitating conditions. The findings may be generalized beyond Vietnam to other developing countries to offer insights for policymakers, cooperatives, and lead firms to improve agricultural efficiency and productivity. • Performance expectancy (PE) is the key factor influencing the intention to adopt PA technology. • Internal facilitating conditions (FCs) do not affect the intention, but external support (government, lead firms) does. • Cooperatives significantly moderate the impact of government and lead firm on farmers' intention to adopt PA technology. • Despite unfavorable FCs, mixing lead firms and cooperatives roles with other factors can still boost adoption intention.","author":[{"family":"Nguyen","given":"Long"},{"family":"Halibas","given":"Alrence"},{"family":"Nguyen","given":"Trung"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1016/j.jclepro.2024.143724","URL":"https://doi.org/10.1016/j.jclepro.2024.143724","source":"crossref"},{"id":"doi:10.1109/incet61516.2024.10593318","type":"article-journal","title":"MobileNetV3 for Mango Leaf Disease Detection:An efficient Deep Learning Approach for Precision Agriculture","abstract":"India, renowned for its vast agricultural landscape, especially in mango cultivation, faces substantial challenges with leaf diseases that significantly affect mango yield and quality. These issues pose economic challenges for the agricultural sector. The task of accurately diagnosing these diseases is complex and time-intensive. Addressing this, our study leverages advanced machine learning techniques and high-processing computational resources. We utilize the publicly available MangoLeafBD(MBD) dataset, which contains 4000 high-resolution images of mango leaves, sourced from diverse orchards in Bangladesh using mobile phone cameras. This dataset, with its meticulously edited images, is crucial for effectively training machine learning models. Using the MobileNetV3(MV3) architecture, known for its enhanced accuracy and efficiency, we have developed a mobile application for real-time mango leaf disease diagnosis. This application, integrating Android's Camerax API, facilitates immediate, on-site disease detection. The retraining of MV3 on the MBD dataset has achieved an impressive accuracy of 98%, demonstrating its potential in agricultural technology. This advancement not only contributes significantly to plant pathology but also offers a practical solution for farmers, enhancing disease management and promoting sustainable agricultural practices.","author":[{"family":"Puranik","given":"Sukruth"},{"family":"Hanamakkanavar","given":"Siddharth"},{"family":"Bidargaddi","given":"Anupama"},{"family":"Ballur","given":"Vighnesh"},{"family":"Joshi","given":"Pratham"},{"family":"Kulkarni","given":"Uday"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/incet61516.2024.10593318","URL":"https://doi.org/10.1109/incet61516.2024.10593318","source":"crossref"},{"id":"doi:10.3920/9789086866038_019","type":"article-journal","title":"Physically-based modeling of photosynthetic processes","abstract":"For this study, a biochemical photosynthesis model was integrated into the hydrological land surface model PROMET. The combined model was adapted to simulate a variety of land cover types on the catchment scale. To investigate and evaluate the model accuracy, simulation runs for single land use classes on the field scale were performed. A winter wheat site (Triticum aestivum L., cultivar Achat) was chosen as a test field. A variety of physiological parameters such as biomass, LAI, plant height and yield were modeled for the vegetation period of the year 2004 and compared to field measurements. The results show that a highly effective tool for the modeling of plant physiology was created that is likely to improve the mapping of the corresponding water balance components.","author":[{"family":"Hank","given":"T"},{"family":"Oppelt","given":"N"},{"family":"Mauser","given":"W"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3920/9789086866038_019","URL":"https://doi.org/10.3920/9789086866038_019","source":"crossref"},{"id":"doi:10.29081/jesr.v29i4.006","type":"article-journal","title":"SOME POSSIBILITIES OF THE AERIAL DRONES USE IN PRECISION AGRICULTURE – A REVIEW","abstract":"Precision agriculture, together with remote sensing and vegetation indices, represents a modern correlation that maximizes efficiency and sustainability in farmland management, contributing to more efficient and responsible production. Remote sensing in agriculture is an important technology that uses data from sensors mounted on satellites, drones, and aircraft to monitor and evaluate agricultural land. Vegetation indices are needed in agricultural remote sensing and precision agriculture because they provide quantitative and objective information on agricultural crops contributing to more efficient, sustainable and cost-effective land management.","author":[{"family":"Ioja","given":"Iosif"},{"family":"Nedeff","given":"Valentin"},{"family":"Agop","given":"Maricel"},{"family":"Nedeff","given":"Florin"}],"issued":{"date-parts":[[2024]]},"DOI":"10.29081/jesr.v29i4.006","URL":"https://doi.org/10.29081/jesr.v29i4.006","source":"crossref"},{"id":"doi:10.48175/ijarsct-19945","type":"article-journal","title":"Precision Agriculture using ML for Soil and Weather Prediction","abstract":"Agriculture is the backbone of many economies and plays a critical role in global food security. However, with growing challenges posed by climate change, erratic weather patterns, and soil degradation, the need for precise and predictive techniques in agriculture has never been more urgent. This paper focuses on the application of machine learning (ML) techniques in soil fertility prediction and weather forecasting, two critical components that can significantly impact agricultural productivity. By analysing soil properties, such as moisture, pH, and nutrient levels, and combining them with accurate weather predictions, our system aims to help farmers make informed decisions regarding crop selection, irrigation scheduling, and pest control. Leveraging algorithms like Naive Bayes for soil classification and Long Short-Term Memory (LSTM) networks for weather prediction, we provide a comprehensive solution for precision agriculture. This system not only enhances productivity but also promotes sustainable agricultural practices by optimizing resource use and reducing wastage","author":[{"family":"Toke","given":"Tanuja"},{"family":"Chakre","given":"Samiksha"},{"family":"Jagtap","given":"Shreeya"},{"family":"Tekale","given":"Vaishnavi"},{"family":"Gosavi","given":"Prof"}],"issued":{"date-parts":[[2024]]},"DOI":"10.48175/ijarsct-19945","URL":"https://doi.org/10.48175/ijarsct-19945","source":"crossref"},{"id":"doi:10.1109/i-smac61858.2024.10714733","type":"article-journal","title":"Machine Learning for Enhanced Crop Management and Optimization of Yield in Precision Agriculture","abstract":"Precision agriculture, utilizing technology to monitor and control crop growth and resource intake, is revolutionizing the agricultural sector. This research focuses on applying machine learning techniques to enhance decision-making in precision agriculture. By combining data from weather forecasts, soil sensors, and satellite imagery, the study aims to estimate crop health, soil characteristics, and yield results. Various machine learning models, including ensemble approaches, regression, classification, and clustering, were employed to analyze these complex datasets. Support vector regression and linear regression were used to predict crop yields based on historical data and environmental factors. Decision Trees and Random Forests were applied to classify crop diseases using image data. Convolutional Neural Networks analyzed satellite and drone imagery to identify agricultural stress and illnesses. Clustering techniques, such as K-Means and DBSCAN, were utilized to segment fields into management zones and detect anomalies in sensor data. Ensemble methods, including AdaBoost and Gradient Boosting Machines, were employed to enhance prediction accuracy by combining multiple models. The research findings demonstrate the significant improvement in prediction accuracy and decision-making capabilities enabled by machine learning techniques. This study lays the groundwork for further research and development in precision agriculture, contributing to sustainable farming practices and food security. By integrating high-resolution data from multiple sources, precision agriculture can optimize resource allocation and maximize crop yields, leading to more efficient and productive agricultural practices.","author":[{"family":"Bachu","given":"Lahari"},{"family":"Kandibanda","given":"Ashish"},{"family":"Grandhi","given":"Nithin"},{"family":"Athina","given":"Durga"},{"family":"Ande","given":"Pavan"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/i-smac61858.2024.10714733","URL":"https://doi.org/10.1109/i-smac61858.2024.10714733","source":"crossref"},{"id":"doi:10.1016/b978-0-443-15315-0.00008-0","type":"article-journal","title":"Phenotyping, Body Composition, and Precision Nutrition","abstract":"Phenotypes include observed traits such as body shape, composition, and metabolic markers which unlike genotypes are not inherited intact but influenced by the genotype and other factors including nutrition , exercise, and the environment through epigenetics , metabolism, and the microbiome . An important phenotype relates to body composition and fat distribution, with body composition being an essential component of Precision Nutrition. Body composition, fat distribution, body protein, skeletal muscle mass, and body shape measures enable the study of subgroups with common physiological elements relevant to metabolism and Precision Nutrition.","author":[{"family":"Heymsfield","given":"Steve"},{"family":"Bell","given":"Jimmy"},{"family":"Heber","given":"David"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1016/b978-0-443-15315-0.00008-0","URL":"https://doi.org/10.1016/b978-0-443-15315-0.00008-0","source":"crossref"},{"id":"doi:10.3390/app14093738","type":"article-journal","title":"Precision Agriculture: Assessment of Ergonomic Risks of Assisted Driving System","abstract":"Background: the precision agriculture field optimizes resource use, enhancing performance. However, this leads to exposure to ergonomic risks for operators, in particular, tractor drivers, potentially causing musculoskeletal disorders (MSDs). This study investigates how the display position in a semi-automatic tractor system influences operator comfort and muscle activation during harrowing operations. Methods: the assessment of muscular strain involved the use of surface electromyographic devices, while posture was evaluated throughout the analysis of the distribution of pressure exerted by the operator’s body on the seat, which was observed using two barometric pads, each positioned on the backrest and base of the seat. Finally, infrared thermography (IRT), a non-invasive tool to assess muscle activation, was used to measure the surface temperature of the driver’s back. The results showed a significantly greater muscular activation display for the position of display in semi-automatic driving at 50° and 80°. Conclusions: this study showed how the position of the display on the vehicle negatively influences posture, exposing workers to the risk of developing fatigue and, therefore, discomfort, with the potential onset of MSDs. The combined use of sEMG and IRT allowed for a non-invasive, cheap, and repeatable mechanical and functionality analysis.","author":[{"family":"Vitale","given":"Ermanno"},{"family":"Vella","given":"Francesca"},{"family":"Matera","given":"Serena"},{"family":"Rizzo","given":"Giuseppe"},{"family":"Rapisarda","given":"Lucia"},{"family":"Roggio","given":"Federico"},{"family":"Musumeci","given":"Giuseppe"},{"family":"Rapisarda","given":"Venerando"},{"family":"Romano","given":"Elio"},{"family":"Filetti","given":"Veronica"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/app14093738","URL":"https://doi.org/10.3390/app14093738","source":"crossref"},{"id":"doi:10.3390/agriculture14010099","type":"article-journal","title":"A First View on the Competencies and Training Needs of Farmers Working with and Researchers Working on Precision Agriculture Technologies","abstract":"The penetration of precision agriculture technologies in agrifood systems generates the need for efficient upskilling programs targeted at farmers and other actors. A critical first step in this direction is to uncover the training needs of the actors involved in precision agriculture ecosystems. The present study aimed to identify and assess gaps in competencies related to precision agriculture technologies of Greek livestock farmers and researchers specialized in this field. For farmers, we followed a partially mixed research design. To uncover researchers’ training needs, we chose a qualitative-dominant mixed approach. The results revealed that farmers lack competencies concerning the exploitation of precision agriculture technologies. Depending on their area of expertise, researchers have needs associated with predicting how research affects the future of farming and understanding how precision agriculture artifacts interplay with socio-environmental and economic factors. Despite the limited generalizability of the findings, which represent a limitation associated with the reliance of data on two small sample sizes, our results indicate that, beyond technology-related competencies, it is essential to enhance the capacity of producers and researchers to foresight and shape potential (digital) futures.","author":[{"family":"Michailidis","given":"Anastasios"},{"family":"Charatsari","given":"Chrysanthi"},{"family":"Bournaris","given":"Thomas"},{"family":"Loizou","given":"Efstratios"},{"family":"Paltaki","given":"Aikaterini"},{"family":"Lazaridou","given":"Dimitra"},{"family":"Lioutas","given":"Evagelos"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3390/agriculture14010099","URL":"https://doi.org/10.3390/agriculture14010099","source":"crossref"},{"id":"doi:10.1016/j.compag.2024.109509","type":"article-journal","title":"Cost-efficient algorithm for autonomous cultivators: Implementing template matching with field digital twins for precision agriculture","abstract":"The paper focuses on the development of a vision system to automate the position control of a cultivator used for crop weeding. The vision algorithm allows monitoring of the cultivator’s misalignment with respect to crop rows, with real-time processing. The key content includes the introduction of a self-generated digital twin of the field model for numerical validation of different computer vision solutions and a comparison of three vision algorithms for measuring deviation. The objectives of the study are to improve the precision of misalignment measurements and ensure safe and accurate movement of the cultivator. The rationale behind the study is to address constraints such as camera installation and crop color, and to emphasize the importance of a confidence estimation feature for accurate measurement. The paper also provides an overview of related works in the literature, highlighting the two phases of plant identification and deviation measurement. Tests carried out on soybean and maize crops demonstrate the improvements allowed by the proposed algorithm in terms of higher measurement precision, even in the presence of high weed infestation or a significant number of missing plants. Additionally, the paper suggests analysis simplifications to enhance the algorithm’s speed while maintaining satisfactory measurement accuracy. • Computer vision-based real-time cultivator misalignment measurement. • Addresses camera installation and crop color constraints. • Incorporates a confidence estimation feature for accurate measurement. • Achieves higher precision than existing algorithms, even in challenging conditions.","author":[{"family":"Bortoli","given":"Luca"},{"family":"Marsi","given":"Stefano"},{"family":"Marinello","given":"Francesco"},{"family":"Gallina","given":"Paolo"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1016/j.compag.2024.109509","URL":"https://doi.org/10.1016/j.compag.2024.109509","source":"crossref"},{"id":"doi:10.1016/j.compag.2023.108270","type":"article-journal","title":"A mixed-autonomous robotic platform for intra-row and inter-row weed removal for precision agriculture","abstract":"The presence of weeds poses a common and persistent problem in crop cultivation, affecting both yield and overall agricultural productivity. Common solutions to the problem typically include chemical pesticides, mulching, or mechanical weeding performed by agricultural implements or humans. Even if effective, those techniques have several drawbacks, including soil and water pollution, high cost-effectiveness ratio or stress for operators. In recent years, novel robotic solutions have been proposed to overcome current limitations and to move towards more sustainable approaches to weeding. This work presents a mixed-autonomous, robotic, weeding system based on a fully integrated three-axis platform and a vision system mounted on a mobile rover. The rover’s motion is remotely controlled by a human operator, while weeds identification and removal is performed autonomously by the robotic system. Once in position, an RGB-D camera captures the portion of field to be treated. The acquired spatial, color and depth information is used to classify soil, the main crop, and the weeds to be removed using a pre-trained Deep Neural Network. Each target is then analyzed by a second RGB-D camera (mounted on the gripper) to confirm the correct classification before its removal. With the proposed approach, weeds are all the plants not classified as the main crop known a priori. The performance of the integrated robotic system has been tested in laboratory as well as in open field and in greenhouse conditions. The system was also tested under different light and shadowing conditions to evaluate the performance of the Deep Neural Network. Results show that the identification of the plants (both crop and weeds) is above 95%, increasing to 98% when additional information, such as the intra-row spacing, is provided. Nevertheless, the correct identification of the weeds remains above 97% ensuring an effective removal of weeds (up to 85%) with negligible crop damage (less than 5%).","author":[{"family":"Visentin","given":"Francesco"},{"family":"Cremasco","given":"Simone"},{"family":"Sozzi","given":"Marco"},{"family":"Signorini","given":"Luca"},{"family":"Signorini","given":"Moira"},{"family":"Marinello","given":"Francesco"},{"family":"Muradore","given":"Riccardo"}],"issued":{"date-parts":[[2023]]},"DOI":"10.1016/j.compag.2023.108270","URL":"https://doi.org/10.1016/j.compag.2023.108270","source":"crossref"},{"id":"doi:10.3390/agriculture13081603","type":"article-journal","title":"A Co-Simulation Virtual Reality Machinery Simulator for Advanced Precision Agriculture Applications","abstract":"Simulation systems have become essential tools for both researchers and virtual laboratory experiments. In the Agri-food-chain, SimAgri, a driving simulator for tractors and operating machines, has been developed for precision agriculture (PA) research and to train professional farm drivers. Using the virtual environment of the simulator, the influence and fine-tuning of PA operations logic may be evaluated by simulating existing systems, or designing new ones, in specially compared scenarios and setups. Current configurations include an agricultural tractor carrying or towing farm equipment such as sprayers, seeders and fertilizer, embedded sensors, human–machine interfaces that may be configured like a joystick, console and touchscreen, and four virtual environment monitors. The study describes the design choices that have made it possible to create a simulator aimed at precision agriculture, keeping auto guidance, geolocation, and operations with ISOBUS implements as pillars. This research aims to use a unique purpose-designed simulation platform, installed on a driver-in-the-loop simulator to provide data to objectify the benefits of PA criteria. Numerical and experimental data have been compared to ensure results reliability.","author":[{"family":"Cutini","given":"Maurizio"},{"family":"Bisaglia","given":"Carlo"},{"family":"Brambilla","given":"Massimo"},{"family":"Bragaglio","given":"Andrea"},{"family":"Pallottino","given":"Federico"},{"family":"Assirelli","given":"Alberto"},{"family":"Romano","given":"Elio"},{"family":"Montaghi","given":"Alessandro"},{"family":"Leo","given":"Elisabetta"},{"family":"Pezzola","given":"Marco"},{"family":"Maroni","given":"Claudio"},{"family":"Menesatti","given":"Paolo"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/agriculture13081603","URL":"https://doi.org/10.3390/agriculture13081603","source":"crossref"},{"id":"doi:10.3390/environsciproc2022023039","type":"article-journal","title":"Drone and Robotics Roadmap for Agriculture Crops in Pakistan: A Review","abstract":"Precision agriculture is getting immense attention from researchers and farmers across the world due to the threatening situation of the demand and production gap. Evolution in the electromechanical system and the emergence of intelligent monitoring and conditioning systems have enabled closing the gap to make agronomy quicker, lesser prone to infestations, and still profitable at the same time. Whereas the Internet of Things (IoT) has enabled access to relevant data remotely and automates essential response systems to any threat or requirement by a plant in a particular environment. This study concentrates on gathering such advanced mechatronic techniques in the agricultural sector and analyses of the benefits and disadvantages of the modern method.","author":[{"family":"Rehman","given":"Ubaid"},{"family":"Iqbal","given":"Tahir"},{"family":"Hussain","given":"Saddam"},{"family":"Cheema","given":"Muhammad"},{"family":"Iqbal","given":"Fahad"},{"family":"Basit","given":"Abdul"}],"issued":{"date-parts":[[2023]]},"DOI":"10.3390/environsciproc2022023039","URL":"https://doi.org/10.3390/environsciproc2022023039","source":"crossref"},{"id":"doi:10.1007/s11119-024-10144-x","type":"article-journal","title":"A new method for satellite-based remote sensing analysis of plant-specific biomass yield patterns for precision farming applications","abstract":"Abstract This study describes a new method for satellite-based remote sensing analysis of plant-specific biomass yield patterns for precision farming applications. The relative biomass potential (rel. BMP) serves as an indicator for multiyear stable and homogeneous yield zones. The rel. BMP is derived from satellite data corresponding to specific growth stages and the normalized difference vegetation index (NDVI) to analyze crop-specific yield patterns. The development of this methodology is based on data from arable fields of two research farms; the validation was conducted on arable fields of commercial farms in southern Germany. Close relationships (up to r &gt; 0.9) were found between the rel. BMP of different crop types and study years, indicating stable yield patterns in arable fields. The relative BMP showed moderate correlations (up to r = 0.64) with the yields determined by the combine harvester, strong correlations with the vegetation index red edge inflection point (REIP) (up to r = 0.88, determined by a tractor-mounted sensor system) and moderate correlations with the yield determined by biomass sampling (up to r = 0.57). The study investigated the relationship between the rel. BMP and key soil parameters. There was a consistently strong correlation between multiyear rel. BMP and soil organic carbon (SOC) and total nitrogen (TN) contents (r = 0.62 to 0.73), demonstrating that the methodology effectively reflects the impact of these key soil properties on crop yield. The approach is well suited for deriving yield zones, with extensive application potential in agriculture.","author":[{"family":"Hagn","given":"Ludwig"},{"family":"Schuster","given":"Johannes"},{"family":"Mittermayer","given":"Martin"},{"family":"Hülsbergen","given":"Kurt"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10144-x","URL":"https://doi.org/10.1007/s11119-024-10144-x","source":"crossref"},{"id":"doi:10.3920/9789086865147_062","type":"article-journal","title":"Tree shape and foliage volume guided precision orchard sprayer - the PRECISPRAY FP5 project","abstract":"The PRECISPRAY project was initiated as part of the precision horticulture concept, to reduce pesticide use by tree shape and volume specific precise application of agrochemicals. The spraying system consists of: 1.) A light and affordable digital aerial photography system, providing stereoscopic digital image sequences of the orchard. 2.) Digital photogrammetry program to provide tree position and volume (TPV) maps of the orchard and contour lines to be followed by the sprayer outlets. 3.) Variable rate segmented vertical boom cross flow sprayer with sliding arms, capable of keeping the outlets in constant distance from the tree contour line and changing airflow and spray volume according to the foliage volume in front of each outlet. 4.) Sprayer guidance and control system which receives the spray order, controls the sprayer arms and outlets using RTKGPS location and returns actual execution feedback. 5.) Orchard management GIS as the operational core of the system, containing the infrastructure, the TPV maps, a pest management decision support system (DSS) and a two-way interface to the sprayer, issuing spray orders and receiving feedback reports.","author":[{"family":"Meron","given":"M"},{"family":"Zande","given":"JVD"},{"family":"Zuydam","given":"RV"},{"family":"Heijne","given":"B"},{"family":"Shragai","given":"M"},{"family":"Liberman","given":"J"},{"family":"Hetzroni","given":"A"},{"family":"Andersen","given":"PG"},{"family":"Shimborsky","given":"E"}],"issued":{"date-parts":[[2024]]},"DOI":"10.3920/9789086865147_062","URL":"https://doi.org/10.3920/9789086865147_062","source":"crossref"},{"id":"doi:10.58532/v3bcag6p1ch3","type":"article-journal","title":"INTERNET OF THINGS (IOT) IN PRECISION AGRICULTURE","abstract":"Although only a few nations have implemented precision agriculture, India's agricultural sector still need modernization with improved technology participation for improved production, distribution, and cost management. Internet of Things (IoT) sensors may provide information about agricultural areas and then act on it depending on user input. IoT development gives rise to the concept of machine-to-machine technology, which allows two machines to communicate with one another. All data that was earlier stored on a private server can now also accessible remotely on internet. Almost all businesses may benefit from the use of IoT, especially those where connection speed is not a concern. To meet the need for food, difficulties like harsh weather and accelerating climate change must be solved. With the help of IoT technology, growers and farmers will be able to increase production and minimise waste in a variety of areas, from the amount of fertiliser used to the number of trips the farm vehicles have taken.","author":[{"family":"Boruah","given":"Sushruta"},{"family":"Pathak","given":"Mahesh"},{"family":"Sarmah","given":"Kasturi"},{"family":"Sahoo","given":"Bimal"}],"issued":{"date-parts":[[2024]]},"DOI":"10.58532/v3bcag6p1ch3","URL":"https://doi.org/10.58532/v3bcag6p1ch3","source":"crossref"},{"id":"doi:10.1109/metroagrifor58484.2023.10424132","type":"article-journal","title":"Adaptive Sliding Mode Control with Artificial Potential Field for Ground Robots in Precision Agriculture","abstract":"This work considers autonomous Guidance, Navigation and Control (GNC) of Unmanned Ground Vehicles (UGVs) for Precision Agriculture (PA) applications. In the agricultural environment, the GPS signal can be weak for various reasons, which makes GPS-based navigation unreliable. Therefore, we consider a GPS-denied situation and localise the robot with several sensors and an Extended Kalman Filter (EKF). The path planner exploits a suitably designed Artificial Potential Field (APF), which ensures attraction to the target while avoiding obstacles. The motion controller, on the other hand, is based on Sliding Mode Control (SMC) and proposes a new direct adaptive law to adjust a control parameter in real time and achieve better tracking of the reference path.The navigation strategy was validated in Matlab/Simulink through numerical simulations, employing simulation scenarios which reflect typical applications in precision agriculture.","author":[{"family":"Mancini","given":"Mauro"},{"family":"Trombetta","given":"Enza"},{"family":"Carminati","given":"Davide"},{"family":"Capello","given":"Elisa"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1109/metroagrifor58484.2023.10424132","URL":"https://doi.org/10.1109/metroagrifor58484.2023.10424132","source":"crossref"},{"id":"doi:10.1007/s11119-024-10125-0","type":"article-journal","title":"Mapping grape production parameters with low-cost vehicle tracking devices","abstract":"This study presents a method based on retrofitted low-cost and easy to implement tracking devices, used to monitor the whole harvesting process in viticulture, to map yield and harvest quality parameters in viticulture. The method consists of recording the geolocation of all the machines (harvest trailers and grape harvester) during the harvest to spatially re-allocate production parameters measured at the winery. The method was tested on a vineyard of 30 ha during the whole 2022 harvest season. It has identified harvest sectors (HS) associated with measured production parameters (grape mass and harvest quality parameters: sugar content, total acidity, pH, yeast assimilable nitrogen, organic nitrogen) and calculated production parameters (potential alcohol of grapes, yield, yield per plant) over the entire vineyard. The grape mass was measured at the vineyard cellar or at the wine-growing cooperative by calibrated scales. The harvest quality parameters were measured on grape must samples in a commercial laboratory specialized in oenological analysis and using standardized protocols. Results validate the possibility of making production parameters maps automatically solely from the time and location records of the vehicles. They also highlight the limitations in terms of spatial resolution (the mean area of the HS is 0.3 ha) of the resulting maps which depends on the actual yield and size of harvest trailers. Yield per plant and yeast assimilable nitrogen maps have been used, in collaboration with the vineyard manager, to analyze and reconsider the fertilization process at the vineyard scale, showing the relevance of the information.","author":[{"family":"Gras","given":"JP"},{"family":"Moinard","given":"S"},{"family":"Valloo","given":"Y"},{"family":"Girardot","given":"R"},{"family":"Tisseyre","given":"B"}],"issued":{"date-parts":[[2024]]},"DOI":"10.1007/s11119-024-10125-0","URL":"https://doi.org/10.1007/s11119-024-10125-0","source":"crossref"}]