[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1249":3,"related-1249":123},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":32,"primary_topic":38,"secondary_topics":44,"classification":56,"search_phrases":98,"slug":101,"view_count":102,"doi":103,"paper":104,"created_at":122},1249,"Enhancing water management with intelligent irrigation systems using edge computing, machine learning and IoT","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1827416","Agriculture is responsible for about 70% of freshwater withdrawals, and water scarcity and inefficient methods of water use remain threats to food security. The traditional way of irrigation causes more water loss and requires innovative solutions to optimize water distribution. This research provides an overview of an intelligent irrigation system, which combines the Internet of Things (IoT), machine learning (ML), and edge computing to optimize water usage and improve crop production. The system uses IoT sensors and edge devices to collect data on the environment and estimate the need for irrigation in real-time. It combines machine learning with system components like the Soil Monitoring Unit (SMU) and Water Management Unit (WMU) to provide scalable, real-time and efficient irrigation management. It is deployed locally at the edge, without the need for cloud computing, has the potential to integrate multi-sensor fusion for storm detection, and offers multiple ML models in a modular, low cost system that can be adapted to various agricultural settings. To optimize irrigation schedules, six supervised machine-learning models were used, such as Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Stochastic Gradient Descent (SGD) and Multi-Layer Perceptron (MLP). DT and RF had the highest classification accuracy of 93% and R 2 regression scores of 0.98 respectively, indicating high prediction reliability. However, Support Vector Machine (SVM) did not do that well, with an accuracy percentage of 58% and an R 2 score of 0.18. Although more complex, RF’s accuracy is a great option for larger applications and DT balances efficiency and scalability. The findings corroborate the utility of water efficient irrigation system and its prospect in augmenting productivity of agriculture. Future work will include expanding the field trials and developing hybrid models to further improve adaptability of the system in different agricultural environments. The findings of this research can offer understanding for sustainable farming practices, that are essential when it comes to water scarcity and food security in the global context.",null,"Frontiers in Sustainable Food Systems","2026-08-25T00:00:00Z","论文",55,false,74,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,13,3,1,"研究提出结合IoT、ML与边缘计算的智能灌溉系统，DT和RF模型精度高，对节水农业有实质参考价值。",[23,24,27,29],{"name":9,"url":6},{"name":25,"url":26},"Zenodo (CERN European Organization for Nuclear Research)","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22790399",{"name":25,"url":28},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22790398",{"name":30,"url":31},"Journal of Animal Science","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fjas\u002Fskag311",[33,34,35,36,37],"智慧农业","农业人工智能","边缘计算","物联网","智能灌溉",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot","I",[45,51],{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":57,"locked":13,"version":58,"method":59,"evidence":60},"classified","2026-10-22.2","rules",{"candidates":61,"agricultural_evidence":64},[62,71,76,81,87,93],{"code":39,"score":63,"supported":64,"title":65,"abstract":68,"tags":70},27,true,[66,67],"IoT","edge computing",[69,66,67],"internet of things",[36,35],{"code":46,"score":72,"supported":64,"title":73,"abstract":74,"tags":75},12,[47],[47],[37],{"code":52,"score":72,"supported":64,"title":77,"abstract":79,"tags":80},[78],"machine learning",[78],[34],{"code":82,"score":19,"supported":64,"title":83,"abstract":84,"tags":86},"A8",[],[85],"food security",[],{"code":88,"score":19,"supported":64,"title":89,"abstract":90,"tags":92},"H2",[],[91],"soil",[],{"code":94,"score":20,"supported":13,"title":95,"abstract":96,"tags":97},"I1",[],[],[33],[99,100],"农业人工智能 智慧农业 智能灌溉 边缘计算","农业人工智能 智慧农业","农业人工智能智慧农业智能灌溉边缘计算-1249",4,"10.3389\u002Ffsufs.2026.1827416",{"doi":103,"openalex_id":105,"authors":106,"venue":9,"cited_by_count":113,"oa_url":114,"card":115,"direction":119,"ingested_from":121},"W7204189894",[107,110],{"name":108,"orcid":109},"Mohammed Sulaiman Mustafa","https:\u002F\u002Forcid.org\u002F0000-0002-2920-9428",{"name":111,"orcid":112},"Hakan Kutucu","https:\u002F\u002Forcid.org\u002F0000-0001-7144-7246",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1827416\u002Fpdf",{"tldr":116,"method":117,"finding":118,"direction":119,"opportunity":120},"提出结合IoT、机器学习和边缘计算的智能灌溉系统，优化用水并提高作物产量。","使用IoT传感器和边缘设备，结合六种监督学习模型（如DT、RF）进行实时灌溉管理","决策树和随机森林表现最佳，准确率93%，R²为0.98，优于其他模型。","智慧农业 \u002F 农业物联网","可探索混合模型和扩展田间试验，提高系统在不同农业环境中的适应性。","openalex","2026-09-01T04:03:09.639788Z",{"total":124,"page":20,"page_size":124,"items":125},6,[126,212,305,410,480,543],{"id":127,"title":128,"url":129,"summary":130,"summary_zh":131,"content":8,"source_name":132,"source_url":129,"published_at":133,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":135,"score_detail":136,"sources":141,"tags":143,"primary_topic":145,"secondary_topics":146,"classification":149,"search_phrases":188,"slug":191,"view_count":192,"doi":193,"paper":194,"created_at":211},2926,"An artificial intelligence-based stacking ensemble framework for smart irrigation pump control using IoT sensor data","https:\u002F\u002Fdoi.org\u002F10.11591\u002Fijece.v16i5.pp2652-2663","Efficient water management is essential for sustainable agricultural production, particularly in arid and semi-arid regions where water resources are limited. Machine-learning-based irrigation systems can support automated pump-operation decisions using environmental and soil-related sensor data. However, most previous studies have focused on individual machine-learning models, while the application of stacked ensembles to binary irrigation pump-status prediction remains relatively limited. This study proposes a stacking-based framework for predicting irrigation pump operation in an ON\u002FOFF classification setting. The framework uses environmental and soil-related variables, including soil moisture, temperature, humidity, and a numerical time-related feature. Random forest (RF), extreme gradient boosting (XGBoost), and multilayer perceptron models were trained as base learners, and their out-of-fold (OOF) predictions were combined using a logistic-regression meta-learner. The models were evaluated on a held-out test set using accuracy, precision, recall, specificity, and F1-score. The individual models achieved accuracies ranging from 97.34% to 99.95%, with XGBoost providing the best individual performance. The proposed stacking ensemble achieved 99.97% accuracy, 99.94% precision, 100.00% recall, 99.94% specificity, and a 99.97% F1-score. Compared with XGBoost, the ensemble further refined predictive performance, improving accuracy by 0.02 percentage points and F1-score by 0.01 percentage points while achieving complete elimination of false negatives (100.00% recall). These results demonstrate the potential of stacked ensemble learning to improve binary pump-operation prediction and support data-driven irrigation management in water-limited environments.","高效的水资源管理对可持续农业生产至关重要，尤其是在水资源有限的干旱和半干旱地区。基于机器学习的灌溉系统可以利用环境和土壤相关传感器数据支持自动化水泵运行决策。然而，以往大多数研究集中于单一机器学习模型，而堆叠集成（stacked ensemble）在二元灌溉水泵状态预测中的应用仍相对有限。本研究提出了一种基于堆叠（stacking）的框架，用于在开\u002F关（ON\u002FOFF）分类场景下预测灌溉水泵运行状态。该框架使用环境和土壤相关变量，包括土壤湿度、温度、湿度和一个数值型时间相关特征。随机森林（RF）、极端梯度提升（XGBoost）和多层感知机模型被训练为基学习器，其折外（OOF）预测结果通过逻辑回归元学习器进行组合。模型在留出测试集上使用准确率、精确率、召回率、特异度和F1分数进行评估。单一模型的准确率范围为97.34%至99.95%，其中XGBoost的单一模型性能最佳。所提出的堆叠集成达到了99.97%的准确率、99.94%的精确率、100.00%的召回率、99.94%的特异度和99.97%的F1分数。与XGBoost相比，该集成进一步优化了预测性能，准确率提高了0.02个百分点，F1分数提高了0.01个百分点，同时实现了假阴性的完全消除（100.00%召回率）。这些结果表明，堆叠集成学习在改进二元水泵运行预测和支持水资源受限环境下的数据驱动灌溉管理方面具有潜力。","International Journal of Power Electronics and Drive Systems\u002FInternational Journal of Electrical and Computer Engineering","2026-09-18T00:00:00Z",10,72,{"impact":72,"substance":137,"depth":138,"authority":18,"freshness":139,"relevant":20,"comment":140},21,17,9,"提出基于IoT传感器数据的堆叠集成模型实现灌溉水泵开关预测，准确率达99.97%，方法新颖、结论可靠，但属实验室验证阶段，产业影响有限。",[142],{"name":132,"url":129},[33,34,144,36,37],"机器学习",{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},[147,148],{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":57,"locked":13,"version":58,"method":59,"evidence":150},{"candidates":151,"agricultural_evidence":64},[152,158,163,167,172,178,184],{"code":46,"score":16,"supported":64,"title":153,"abstract":154,"tags":157},[47],[155,156,47],"灌溉","水资源",[37],{"code":52,"score":18,"supported":64,"title":159,"abstract":161,"tags":162},[160],"artificial intelligence",[144],[34,144],{"code":39,"score":139,"supported":64,"title":164,"abstract":165,"tags":166},[66],[],[36],{"code":88,"score":124,"supported":64,"title":168,"abstract":169,"tags":171},[],[170,91],"土壤",[],{"code":173,"score":19,"supported":64,"title":174,"abstract":175,"tags":177},"H7",[],[176],"干旱",[],{"code":179,"score":19,"supported":64,"title":180,"abstract":181,"tags":183},"H8",[],[182],"可持续农业",[],{"code":94,"score":20,"supported":13,"title":185,"abstract":186,"tags":187},[],[],[33],[189,190],"智能灌溉 水泵控制 物联网","农业人工智能 智慧农业 智能灌溉 机器学习","智能灌溉水泵控制物联网-2926",2,"10.11591\u002Fijece.v16i5.pp2652-2663",{"doi":193,"openalex_id":195,"authors":196,"venue":132,"cited_by_count":113,"oa_url":129,"card":206,"direction":119,"ingested_from":121},"W7213546497",[197,200,203],{"name":198,"orcid":199},"Sarra Gourari","https:\u002F\u002Forcid.org\u002F0009-0005-1846-0886",{"name":201,"orcid":202},"Wafa Difallah","https:\u002F\u002Forcid.org\u002F0000-0002-6181-0395",{"name":204,"orcid":205},"Belkacem Draoui","https:\u002F\u002Forcid.org\u002F0000-0001-5490-3991",{"tldr":207,"method":208,"finding":209,"direction":119,"opportunity":210},"提出基于堆叠集成学习的灌溉泵ON\u002FOFF预测框架，用物联网传感器数据实现智能灌溉控制。","用RF、XGBoost、MLP作基学习器，逻辑回归元学习器融合OOF预测，基于土","堆叠集成达99.97%准确率和100%召回率，完全消除假阴性，优于单一XGBoost模型。","可探索多模态传感器融合与在线增量学习，提升堆叠集成在不同作物和气候区的泛化与实时部署能力。","2026-09-19T23:30:11.009076Z",{"id":213,"title":214,"url":215,"summary":216,"summary_zh":217,"content":8,"source_name":218,"source_url":215,"published_at":219,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":220,"score_detail":221,"sources":223,"tags":225,"primary_topic":228,"secondary_topics":229,"classification":232,"search_phrases":280,"slug":283,"view_count":113,"doi":284,"paper":285,"created_at":304},5553,"Artificial Intelligence–Driven Precision Agriculture Systems: Engineering Frameworks for Climate-Resilient Food Production","https:\u002F\u002Fdoi.org\u002F10.53982\u002Fajerd.2026.01.14-j","Climate change, soil issues, water scarcity, and the increasing need for food worldwide mean we need smart farming systems that can manage resources flexibly. Old farming methods used the same inputs and simple rules for decisions. AI can help us manage resources better by adapting and optimizing them as we deal with complex environmental factors. This paper looks closely at AI-powered precision agriculture systems designed to make food production more resilient to changing weather. The authors reviewed research from 2021 to 2026 in agricultural engineering, computer engineering, and environmental systems. The authors examined how machine learning, deep learning, reinforcement learning, computer vision, robotics, and IoT sensors are used for predicting crop yields, spotting diseases, improving irrigation, managing nutrients, and automating field tasks. Our analysis shows that hybrid deep learning models (CNN-LSTM) are better than single models for predicting crop yields over space and time. Reinforcement learning algorithms are also better at adjusting irrigation cycles when weather is unpredictable. Using edge computing for system design reduces delays and improves real-time decision-making compared to traditional cloud-based systems. However, there are still big challenges with understanding how AI models work, having enough diverse data, ensuring cybersecurity, setting common standards, and making these systems affordable, especially in developing countries. To tackle these problems, we suggest a framework that combines AI analysis, distributed sensor networks, adaptive controls, and climate risk assessments. The authors provided critical insights into essential research gaps and outline a technological roadmap towards achieving sustainable, resilient and intelligent agricultural systems.","气候变化、土壤问题、水资源短缺以及全球日益增长的粮食需求，意味着我们需要能够灵活管理资源的智能农业系统。传统农业方法对相同的投入采用固定模式，并依赖简单规则进行决策。人工智能可以帮助我们更好地管理资源，通过适应和优化资源利用来应对复杂的环境因素。本文深入探讨了人工智能驱动的精准农业系统，旨在使粮食生产对不断变化的天气更具韧性。作者综述了2021年至2026年间农业工程、计算机工程和环境系统领域的研究。作者考察了机器学习、深度学习、强化学习、计算机视觉、机器人技术及物联网传感器如何被用于作物产量预测、病害识别、灌溉优化、养分管理和田间作业自动化。我们的分析表明，混合深度学习模型（CNN-LSTM）在时空作物产量预测方面优于单一模型。在天气不可预测的情况下，强化学习算法在调整灌溉周期方面也表现更优。与传统基于云的系统相比，采用边缘计算进行系统设计可降低延迟并改善实时决策能力。然而，在理解人工智能模型的工作原理、获取足够多样化的数据、确保网络安全、制定通用标准以及使这些系统具备可负担性方面，仍存在重大挑战，尤其是在发展中国家。为应对这些问题，我们提出了一个融合人工智能分析、分布式传感器网络、自适应控制和气候风险评估的框架。作者对关键研究空白提供了重要见解，并勾勒了实现可持续、韧性和智能农业系统的技术路线图。","ABUAD Journal of Engineering Research and Development (AJERD)","2026-10-21T00:00:00Z",80,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":139,"relevant":20,"comment":222},"系统综述AI驱动精准农业的工程框架与技术路线，方法梳理扎实、结论有参考价值，但属综述类论文，产业落地影响有限。",[224],{"name":218,"url":215},[33,34,36,226,227],"精准农业","气候韧性",{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},[230,231],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},{"status":57,"locked":13,"version":58,"method":59,"evidence":233},{"candidates":234,"agricultural_evidence":64},[235,243,249,253,257,264,268,274],{"code":52,"score":16,"supported":64,"title":236,"abstract":237,"tags":242},[160],[238,144,239,78,240,241],"深度学习","计算机视觉","deep learning","computer vision",[34],{"code":94,"score":244,"supported":64,"title":245,"abstract":247,"tags":248},16,[246],"precision agriculture",[226,246],[33,226],{"code":39,"score":134,"supported":64,"title":250,"abstract":251,"tags":252},[],[36,35,66,67],[36],{"code":46,"score":139,"supported":64,"title":254,"abstract":255,"tags":256},[],[155,156,47],[],{"code":173,"score":258,"supported":64,"title":259,"abstract":260,"tags":263},7,[],[261,262],"气候变化","climate change",[227],{"code":88,"score":124,"supported":64,"title":265,"abstract":266,"tags":267},[],[170,91],[],{"code":269,"score":19,"supported":64,"title":270,"abstract":271,"tags":273},"A7",[],[272],"间作",[],{"code":275,"score":19,"supported":64,"title":276,"abstract":277,"tags":279},"F3",[],[278],"养分管理",[],[281,282],"AI 精准农业 气候韧性","CNN-LSTM 作物产量预测","AI精准农业气候韧性-5553","10.53982\u002Fajerd.2026.01.14-j",{"doi":284,"openalex_id":286,"authors":287,"venue":218,"cited_by_count":113,"oa_url":215,"card":298,"direction":119,"ingested_from":121},"W7223121456",[288,291,293,295],{"name":289,"orcid":290},"Olumayowa J. Iyanda","https:\u002F\u002Forcid.org\u002F0000-0002-5340-9884",{"name":292,"orcid":8},"Oluwadare OYEBODE",{"name":294,"orcid":8},"Iretiayo Adelaiye",{"name":296,"orcid":297},"Ayomide Afolabi","https:\u002F\u002Forcid.org\u002F0000-0002-5171-886X",{"tldr":299,"method":300,"finding":301,"direction":302,"opportunity":303},"综述2021-2026年AI驱动精准农业系统，提出气候韧性粮食生产工程框架。","综述机器学习、深度学习、强化学习、计算机视觉、机器人与物联网在精准农业中的应用。","CNN-LSTM混合模型和强化学习在产量预测与灌溉调度上优于单一方法，边缘计算提升实时性。","农业人工智能与决策模型","可研究边缘计算与强化学习结合的轻量级灌溉决策系统，并探索发展中国家低成本部署与标准化路径。","2026-10-22T11:20:18.151376Z",{"id":306,"title":307,"url":308,"summary":309,"summary_zh":310,"content":8,"source_name":311,"source_url":308,"published_at":219,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":312,"score_detail":313,"sources":315,"tags":317,"primary_topic":321,"secondary_topics":322,"classification":325,"search_phrases":380,"slug":383,"view_count":113,"doi":384,"paper":385,"created_at":409},5564,"Dynamic thermal imaging for crop water stress detection across phenological stages: Enhancing irrigation scheduling precision","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.17728","Thermal remote sensing and derived indices such as the crop water stress index (CWSI) can assess crop water status and support precision irrigation. However, most operational and artificial intelligence (AI)-based approaches rely on fixed, season-long thresholds to interpret canopy–air temperature differences and often overlook the influence of crop phenology. This review synthesises evidence from grapevine, wheat, maize, potato and several other crops on how developmental stage affects the non-water-stressed baseline (NWSB), CWSI thresholds and irrigation-scheduling algorithms. It covers CWSI theory and estimation practices; crop-specific, phenology-dependent behaviour of baselines and thresholds; a comparison of threshold-based, machine learning, Internet of Things (IoT), digital twin and Food and Agriculture Organization (FAO)-56 approaches with respect to crop phenology; and a conceptual framework for phenology-aware scheduling. Across the reviewed crops, baseline behaviour generally varied systematically across the growing season, the relationship between CWSI and crop water status generally strengthened after canopy closure and CWSI measured during reproductive stages was generally most closely related to yield. A quantitative audit of 56 AI-, thermal-imaging-, or CWSI-based studies found that 78.6 % either did not explicitly incorporate crop phenology or relied on day of year as a temporal proxy, whereas only 5.4 % explicitly encoded phenological stage. The proposed framework considers phenology explicitly in baseline estimation, threshold setting and data fusion or machine learning for irrigation scheduling; the framework will require multi-year, multi-site field validation before operational use. Future research should prioritise standardised phenology definitions and long-term, multi-location studies to establish and validate stage-specific parameters.","热红外遥感及其衍生的作物水分胁迫指数（crop water stress index, CWSI）等指标可评估作物水分状况并支持精准灌溉。然而，大多数业务化方法和基于人工智能（artificial intelligence, AI）的方法依赖固定的全生育期阈值来解释冠层—空气温差，且往往忽视作物物候的影响。本文综述了葡萄、小麦、玉米、马铃薯及其他若干作物在发育阶段如何影响非水分胁迫基线（non-water-stressed baseline, NWSB）、CWSI阈值和灌溉调度算法的相关证据。综述内容涵盖CWSI理论与估算实践；基线和阈值的作物特异性、物候依赖性行为；基于阈值、机器学习、物联网（Internet of Things, IoT）、数字孪生及联合国粮农组织（Food and Agriculture Organization, FAO）-56等方法在作物物候方面的比较；以及物候感知调度的概念框架。在所综述的作物中，基线行为在整个生长季通常呈系统性变化，CWSI与作物水分状况之间的关系在冠层封垄后总体增强，且在生殖阶段测得的CWSI与产量的关系总体最为密切。对56项基于AI、热成像或CWSI的研究进行的定量审查发现，78.6%的研究要么未明确纳入作物物候，要么依赖年积日作为时间代理变量，而仅5.4%的研究明确编码了物候阶段。所提出的框架在基线估算、阈值设定以及用于灌溉调度的数据融合或机器学习中明确考虑物候；该框架在投入业务应用前尚需多年、多站点的田间验证。未来研究应优先建立标准化的物候定义，并开展长期、多地点研究以建立和验证阶段特异性参数。","Plant Science Today",79,{"impact":16,"substance":17,"depth":16,"authority":72,"freshness":139,"relevant":20,"comment":314},"系统综述热成像与CWSI在物候期感知灌溉中的应用，含56项研究量化审计，方法学价值突出，但属综述类论文，影响偏学术层面。",[316],{"name":311,"url":308},[33,34,318,319,320],"遥感","作物水分胁迫","精准灌溉",{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},[323,324],{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":57,"locked":13,"version":58,"method":59,"evidence":326},{"candidates":327,"agricultural_evidence":64},[328,333,337,341,347,353,360,367,374],{"code":46,"score":329,"supported":64,"title":330,"abstract":331,"tags":332},15,[47],[155,47],[320],{"code":52,"score":134,"supported":64,"title":334,"abstract":335,"tags":336},[],[144,78,160],[34],{"code":39,"score":139,"supported":64,"title":338,"abstract":339,"tags":340},[],[36,69,66],[],{"code":94,"score":258,"supported":64,"title":342,"abstract":343,"tags":346},[],[344,345],"数字孪生","digital twin",[33],{"code":348,"score":258,"supported":64,"title":349,"abstract":350,"tags":352},"I3",[],[318,351],"remote sensing",[318],{"code":354,"score":124,"supported":64,"title":355,"abstract":356,"tags":359},"A2",[],[357,358],"小麦","wheat",[],{"code":361,"score":124,"supported":64,"title":362,"abstract":363,"tags":366},"A3",[],[364,365],"玉米","maize",[],{"code":368,"score":124,"supported":64,"title":369,"abstract":370,"tags":373},"A5",[],[371,372],"马铃薯","potato",[],{"code":375,"score":19,"supported":64,"title":376,"abstract":377,"tags":379},"B2",[],[378],"葡萄",[],[381,382],"热成像 作物水分胁迫","CWSI 灌溉调度","热成像作物水分胁迫-5564","10.14719\u002Fpst.17728",{"doi":384,"openalex_id":386,"authors":387,"venue":311,"cited_by_count":113,"oa_url":308,"card":403,"direction":119,"ingested_from":121},"W7223088921",[388,391,394,397,400],{"name":389,"orcid":390},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":392,"orcid":393},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":395,"orcid":396},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":398,"orcid":399},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":401,"orcid":402},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":404,"method":405,"finding":406,"direction":407,"opportunity":408},"综述物候期对热成像CWSI阈值的影响，提出物候感知灌溉调度框架。","综述葡萄、小麦、玉米等作物的热遥感CWSI研究，并审计56项AI\u002F热成像研究。","78.6%研究未显式纳入物候，仅5.4%编码物候期；CWSI与产量在生殖期关联最强。","农业遥感与作物表型","可开展多站点多年物候期特异性CWSI阈值标定与标准化物候定义研究。","2026-10-22T11:20:24.526683Z",{"id":411,"title":412,"url":413,"summary":414,"summary_zh":415,"content":8,"source_name":416,"source_url":413,"published_at":417,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":418,"score_detail":419,"sources":421,"tags":423,"primary_topic":426,"secondary_topics":427,"classification":430,"search_phrases":461,"slug":464,"view_count":102,"doi":8,"paper":465,"created_at":479},4076,"Automated System for Plant Health Monitoring and Stress Diagnosis Using IoT and Machine Learning","https:\u002F\u002Fwajes.isroset.org\u002Findex.php\u002Fj\u002Farticle\u002Fview\u002F208","Irrigation decisions on smallholder farms are still taken subjectively, and both root-zone dehydration and over-saturation measurably depress yield, making low-cost automated plant-stress diagnosis an urgent requirement in water-scarce agricultural regions. This study designs, implements and validates a decentralized system that closes the control loop between field sensing and irrigation actuation by combining Internet of Things (IoT) hardware with a cloud-hosted predictive Machine Learning (ML) model. The edge node is built on an ESP32 system-on-chip integrated with a calibrated capacitive soil-moisture probe and a DHT22 temperature and humidity array. Serialized telemetry is transmitted over a non-blocking, encrypted wireless channel to a Flask web service, where a 150-tree Random Forest classifier trained on 5,000 labelled multi-sensor records assigns the plant to one of three physiological states Optimal, Temperature Stress or Dehydration Stress and returns an actuator control bit that drives a micro-irrigation pump. An engineered Evapotranspiration Proxy Index couples ambient temperature and relative humidity into a single transpiration-sensitive feature. Capacitive calibration was validated against the gravimetric standard on ten soil cores, yielding a Pearson correlation coefficient of 0.948. Over a continuous forty-eight-hour open-air evaluation the classifier achieved an overall accuracy of 96.8%, with 98.2% precision and 97.9% recall on the critical Dehydration Stress class, and a mean end-to-end round-trip latency of 1.84 seconds. Deep-sleep duty cycling reduced the mean node current to 0.65 mA, corresponding to an estimated 159 days of unattended operation on a single 2,500 mAh cell. The results demonstrate that a low-cost edge–cloud architecture can deliver dependable, timely and energy-sustainable irrigation control for micro-precision agriculture without server-grade hardware.","小农户的灌溉决策仍依赖主观判断，而根区脱水和过度饱和均会显著降低产量，这使得低成本自动化植物胁迫诊断成为缺水农业地区的迫切需求。本研究设计、实现并验证了一种去中心化系统，通过将物联网（IoT）硬件与云端预测机器学习（ML）模型相结合，闭合了田间传感与灌溉执行之间的控制回路。边缘节点基于ESP32片上系统构建，集成了经过校准的电容式土壤水分探头和DHT22温湿度传感器阵列。序列化遥测数据通过非阻塞加密无线信道传输至Flask Web服务，在此处，一个基于5,000条带标签多传感器记录训练的150棵树的随机森林分类器将植物判定为三种生理状态之一——最优、温度胁迫或脱水胁迫——并返回驱动微灌泵的执行器控制位。所设计的蒸散代理指数将环境温度和相对湿度耦合为单一蒸腾敏感特征。电容校准在十个土芯上与重量法标准进行验证，得到皮尔逊相关系数为0.948。在连续四十八小时的户外评估中，分类器总体准确率达到96.8%，在关键的脱水胁迫类别上精确率为98.2%、召回率为97.9%，平均端到端往返延迟为1.84秒。深度睡眠占空比控制将节点平均电流降至0.65 mA，相当于在单节2,500 mAh电池上估计可无人值守运行159天。结果表明，低成本边缘—云架构无需服务器级硬件即可为微精准农业提供可靠、及时且能源可持续的灌溉控制。","World Academics Journal of Engineering Sciences","2026-09-30T00:00:00Z",75,{"impact":244,"substance":17,"depth":16,"authority":18,"freshness":124,"relevant":20,"comment":420},"低成本边缘-云架构实现植物胁迫自动诊断与灌溉闭环，数据扎实、结论可靠，对智慧农业节水灌溉有参考价值。",[422],{"name":416,"url":413},[33,34,424,320,425],"农业物联网","土壤墒情",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[428,429],{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},{"status":57,"locked":13,"version":58,"method":59,"evidence":431},{"candidates":432,"agricultural_evidence":64},[433,437,441,446,450,454],{"code":39,"score":16,"supported":64,"title":434,"abstract":435,"tags":436},[66],[36,69,66],[424],{"code":52,"score":329,"supported":64,"title":438,"abstract":439,"tags":440},[78],[144,78],[34],{"code":46,"score":134,"supported":64,"title":442,"abstract":443,"tags":445},[],[155,47,444],"evapotranspiration",[320],{"code":88,"score":258,"supported":64,"title":447,"abstract":448,"tags":449},[],[170,91],[425],{"code":94,"score":258,"supported":64,"title":451,"abstract":452,"tags":453},[],[226,246],[33],{"code":455,"score":124,"supported":64,"title":456,"abstract":457,"tags":460},"G2",[],[458,459],"小农户","smallholder",[],[462,463],"ESP32 土壤湿度 灌溉 机器学习","随机森林 植物胁迫 诊断","ESP32土壤湿度灌溉机器学习-4076",{"doi":8,"openalex_id":466,"authors":467,"venue":416,"cited_by_count":113,"oa_url":413,"card":474,"direction":119,"ingested_from":121},"W7217836036",[468,470,472],{"name":469,"orcid":8},"Christian Athanas Mwakyusa",{"name":471,"orcid":8},"Allen Deogratius Mwalekwa",{"name":473,"orcid":8},"Gift Geofrey Mushi",{"tldr":475,"method":476,"finding":477,"direction":119,"opportunity":478},"设计并验证了基于ESP32与随机森林的物联网闭环灌溉系统，实现植物胁迫自动诊断。","ESP32、电容式土壤湿度传感器、DHT22、随机森林分类器、Flask云服务。","48小时测试分类准确率96.8%，脱水胁迫召回率97.9%，节点续航约159天。","可探索多作物泛化、极端环境鲁棒性及边缘端轻量化模型部署以降低云依赖。","2026-10-03T23:30:18.857006Z",{"id":481,"title":482,"url":483,"summary":484,"summary_zh":485,"content":8,"source_name":486,"source_url":483,"published_at":487,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":12,"score_detail":488,"sources":491,"tags":493,"primary_topic":494,"secondary_topics":495,"classification":497,"search_phrases":522,"slug":525,"view_count":20,"doi":526,"paper":527,"created_at":542},4420,"AI-Enabled Sustainable Precision Farming Using Raspberry Pi and Coral Edge TPU with Cloud-Based Model Training","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85019","Precision Agriculture requires intelligent, adaptable and efficient technology that is capable of making decisions in agriculture at the right time, based on the condition of the plants and the environment. This paper proposes the development of an AI-based sustainable precision farming system based on computer vision, cloud based model training, Raspberry Pi, Coral Edge TPU and the Internet of Things (IoT) sensing. The proposed architecture's sensing layer, edge processing layer, cloud intelligence layer, and application layer enables a complete data processing pipeline from the field to real time decision support. Crop photos are collected for AI condition classification and agricultural conditions such as soil moisture, temperature, humidity and light intensity are collected by built-in sensors. After the above preprocessing, normalisation, image resizing and augmentation, the dataset is divided into training, validation and test sets. The trained deep learning models in a cloud environment are then quantized and converted to be optimized for the edge, following this step. Following this step, the trained deep learning models are quantized and converted for optimization on edge. The optimized model achieves an exemplary accuracy of 94.82%, precision of 94.47%, recall of 94.05% and F1-score of 94.26%. Deploying with the Coral Edge TPU reduces inference latency to approximately 38ms compared to Raspberry Pi-only processing, increases processing throughput to 26.3 pictures per second and reduces CPU usage. The edge-assisted architecture reduces the need for constant connection to the cloud, giving local decision making a leg up. Illustrative sustainability study estimates that condition based monitoring can save 22% of the irrigation water used every day. The findings indicated that the introduction of the edge AI and cloud intelligence in precision agricultural systems that are responsive, scalable, and resource-efficient is technically possible.","精准农业需要智能、自适应且高效的技术，能够根据植物和环境状况在恰当时机做出农业决策。本文提出开发一种基于人工智能的可持续精准农业系统，该系统依托计算机视觉、基于云端的模型训练、树莓派（Raspberry Pi）、Coral边缘TPU（Edge TPU）以及物联网（IoT）传感技术。所提出的架构包含感知层、边缘处理层、云智能层和应用层，实现了从田间到实时决策支持的完整数据处理流水线。系统采集作物照片用于AI状态分类，并通过内置传感器采集土壤湿度、温度、空气湿度和光照强度等农业环境条件。经过上述预处理、归一化、图像缩放和数据增强后，数据集被划分为训练集、验证集和测试集。随后，在云环境中训练好的深度学习模型经过量化和转换，针对边缘设备进行优化。优化后的模型达到了94.82%的准确率、94.47%的精确率、94.05%的召回率和94.26%的F1分数，表现优异。与仅使用树莓派处理相比，部署Coral边缘TPU将推理延迟降低至约38毫秒，将处理吞吐量提升至每秒26.3张图片，并降低了CPU占用率。该边缘辅助架构减少了对云端持续连接的需求，提升了本地决策能力。一项示例性可持续性研究估计，基于状态的监测可节省22%的每日灌溉用水量。研究结果表明，在精准农业系统中引入边缘AI和云智能，构建响应迅速、可扩展且资源高效的农业系统，在技术上是可行的。","International Journal for Research in Applied Science and Engineering Technology","2026-10-07T00:00:00Z",{"impact":489,"substance":16,"depth":329,"authority":124,"freshness":489,"relevant":20,"comment":490},8,"技术路线完整、指标具体，但属单篇学术论文，产业影响有限，可作为智慧农业技术参考而非每日精选头条。",[492],{"name":486,"url":483},[33,34,35,36,320],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[496],{"code":52,"slug":53,"name":54,"path":55,"parent_code":43},{"status":57,"locked":13,"version":58,"method":59,"evidence":498},{"candidates":499,"agricultural_evidence":64},[500,505,510,514,518],{"code":39,"score":501,"supported":64,"title":502,"abstract":503,"tags":504},11,[],[36,69,66],[36,35],{"code":52,"score":134,"supported":64,"title":506,"abstract":507,"tags":509},[],[238,239,240,241,508],"decision support",[34],{"code":46,"score":258,"supported":64,"title":511,"abstract":512,"tags":513},[],[155,47],[320],{"code":94,"score":258,"supported":64,"title":515,"abstract":516,"tags":517},[],[226,246],[33],{"code":88,"score":124,"supported":64,"title":519,"abstract":520,"tags":521},[],[170,91],[],[523,524],"Raspberry Pi Coral Edge TPU 精准农业","边缘AI 作物分类 灌溉节水","RaspberryPiCoralEdgeTPU精准农业-4420","10.22214\u002Fijraset.2026.85019",{"doi":526,"openalex_id":528,"authors":529,"venue":486,"cited_by_count":113,"oa_url":483,"card":537,"direction":119,"ingested_from":121},"W7220855887",[530,533,535],{"name":531,"orcid":532},"Prakash Kanade","https:\u002F\u002Forcid.org\u002F0000-0001-6296-9368",{"name":534,"orcid":8},"Shetty Chirag",{"name":536,"orcid":8},"Sunay Kanade",{"tldr":538,"method":539,"finding":540,"direction":119,"opportunity":541},"提出基于树莓派与Coral Edge TPU的边缘AI精准农业系统，实现作物状态分类与实时决策。","计算机视觉、云端模型训练与量化、边缘TPU部署、IoT多传感器融合。","模型准确率94.82%，推理延迟约38ms，条件监测可节水22%。","可探索多作物泛化、边缘模型自适应更新及水肥药协同优化，并量化长期可持续效益。","2026-10-08T23:30:09.663393Z",{"id":544,"title":545,"url":546,"summary":547,"summary_zh":548,"content":8,"source_name":486,"source_url":546,"published_at":549,"category":11,"cover_url":8,"hotness":134,"is_selected":13,"score":418,"score_detail":550,"sources":553,"tags":555,"primary_topic":557,"secondary_topics":558,"classification":563,"search_phrases":587,"slug":590,"view_count":591,"doi":592,"paper":593,"created_at":609},2140,"AIOT in Predictive Agriculture - IoT and AI Integration for Real-Time Soil Monitoring and Smart Irrigation in Predictive Agriculture","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.84727","Modern agriculture faces severe challenges due to climate volatility, accelerating groundwater depletion, and the global imperative to maximize crop production on diminishing arable land. Traditional irrigation frameworks rely predominantly on static schedules or reactive threshold switching, leading to substantial water waste, energy inefficiencies, and suboptimal crop yields. To overcome these limitations, this paper proposes an end-to-end Artificial Intelligence of Things (AIoT) framework designed for real-time multi-parameter soil tracking and predictive smart irrigation. The system architecture deploys low-power IoT field nodes driven by ESP32 microcontrollers, integrated with capacitive soil moisture sensors, environmental sensors, and soil pH probes that stream telemetry data over lightweight MQTT protocols. To transition from reactive monitoring to proactive resource allocation, a cloud-based predictive engine utilizes Long Short-Term Memory (LSTM) neural networks to forecast 24- to-48-hour soil moisture depletion dynamics based on historical moisture profiles and localized meteorological factors. Experimental validation across a 90-day testbed demonstrates that the proposed predictive framework achieves a to reduction in total water consumption while maintaining optimal volumetric soil water content. Furthermore, deep-sleep dynamic power profiling confirms node energy autonomy of up to 219 days on a single battery charge, presenting a scalable, sustainable, and economically viable solution for precision agriculture.","现代农业正面临气候波动、地下水加速枯竭以及全球在日益减少的耕地上最大化作物产量的迫切需求等严峻挑战。传统灌溉框架主要依赖静态调度或反应式阈值切换，导致大量水资源浪费、能源效率低下以及作物产量欠优。为克服这些局限，本文提出了一种端到端的人工智能物联网（AIoT）框架，专为实时多参数土壤监测与预测性智能灌溉而设计。该系统架构部署了由ESP32微控制器驱动的低功耗物联网田间节点，集成了电容式土壤水分传感器、环境传感器和土壤pH探头，通过轻量级MQTT协议传输遥测数据。为实现从反应式监测向主动式资源分配的转变，基于云的预测引擎利用长短期记忆（LSTM）神经网络，根据历史水分剖面和局部气象因素，预测24至48小时的土壤水分消耗动态。在为期90天的测试平台上进行的实验验证表明，所提出的预测框架在保持最优土壤体积含水量的同时，实现了总用水量的降低。此外，深度睡眠动态功耗分析证实，节点在单次电池充电下可实现长达219天的能量自主运行，为精准农业提供了一种可扩展、可持续且经济可行的解决方案。","2026-09-10T00:00:00Z",{"impact":16,"substance":551,"depth":138,"authority":72,"freshness":489,"relevant":20,"comment":552},20,"AIoT+LSTM 预测灌溉的完整实证研究，90 天试验与节水、能耗数据扎实，对精准农业落地有参考价值，但期刊层级与影响范围偏细分领域。",[554],{"name":486,"url":546},[33,34,36,37,226,556],"土壤监测",{"code":46,"slug":47,"name":48,"path":49,"parent_code":50},[559,560],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":88,"slug":91,"name":561,"path":562,"parent_code":50},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"status":57,"locked":13,"version":58,"method":59,"evidence":564},{"candidates":565,"agricultural_evidence":64},[566,570,574,579,583],{"code":46,"score":16,"supported":64,"title":567,"abstract":568,"tags":569},[47],[155,156,47],[37],{"code":39,"score":329,"supported":64,"title":571,"abstract":572,"tags":573},[66],[36,66],[36],{"code":88,"score":575,"supported":64,"title":576,"abstract":577,"tags":578},14,[91],[170,91],[],{"code":94,"score":489,"supported":64,"title":580,"abstract":581,"tags":582},[],[226,246],[33,226],{"code":52,"score":102,"supported":64,"title":584,"abstract":585,"tags":586},[],[160],[34],[588,589],"农业人工智能 土壤监测 智慧农业 智能灌溉","农业人工智能 土壤监测","农业人工智能土壤监测智慧农业智能灌溉-2140",5,"10.22214\u002Fijraset.2026.84727",{"doi":592,"openalex_id":594,"authors":595,"venue":486,"cited_by_count":113,"oa_url":546,"card":604,"direction":119,"ingested_from":121},"W7212115545",[596,598,600,602],{"name":597,"orcid":8},"Gowri M.",{"name":599,"orcid":8},"Boomika M.",{"name":601,"orcid":8},"S. Rakshana",{"name":603,"orcid":8},"Rubali R.",{"tldr":605,"method":606,"finding":607,"direction":119,"opportunity":608},"提出AIoT框架，用LSTM预测土壤湿度实现智能灌溉，节水并延长节点续航。","ESP32节点+电容湿度\u002FpH传感器，MQTT上云，LSTM预测24-48小时湿","90天试验节水显著，土壤含水量保持最优，单次电池续航达219天。","可探索多作物多气候下LSTM泛化能力，及边缘端轻量预测模型降低云依赖。","2026-09-11T23:30:10.173013Z"]