[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4567":3,"related-4567":115},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":45,"search_phrases":89,"slug":92,"view_count":69,"doi":93,"paper":94,"created_at":114},4567,"An embedded deep learning–fuzzy logic framework for intelligent and automated irrigation in smart farming","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72706-5","Water scarcity and the need to improve resource efficiency have made intelligent and automated irrigation management an important research challenge in smart farming. This study proposes IrrigaDL-FL, a low-cost automated smart irrigation framework based on the internet of things, integrating intelligent data routing with adaptive irrigation decision-making. The proposed framework consists of two complementary components. First, a Deep Learning–Fuzzy Logic (DL-FL) framework is integrated with the Open Shortest Path First (OSPF) protocol to enhance data routing efficiency in the network. The DL-FL framework combines these heterogeneous characteristics to identify suitable next-hop nodes and establish energy-efficient routing paths. Second, irrigation decision-making is performed using a lightweight Convolutional Neural Network–Fuzzy Logic Controller (CNN-FLC). The CNN-FLC processes sensor-derived and crop-related information, including air temperature, relative humidity, soil moisture, evapotranspiration rate, crop growth coefficient, crop water requirement, planting date, cumulative rainfall, recent rainfall, irrigation history, crop growth stage, and the difference between actual and target soil moisture. These inputs are used to characterize crop hydration stress and dynamically determine the appropriate irrigation program and sprinkler activation duration. The proposed IrrigaDL-FL framework is evaluated through simulations with different numbers of sensor nodes over predefined routing rounds and is compared with several existing approaches. The results demonstrate that IrrigaDL-FL achieves superior performance in terms of network lifetime, residual energy, energy variance, number of transmitted packets, and average path length.","水资源短缺与提高资源效率的需求，使智能化和自动化灌溉管理成为智慧农业中的重要研究挑战。本研究提出IrrigaDL-FL，一种基于物联网的低成本自动化智能灌溉框架，将智能数据路由与自适应灌溉决策相结合。该框架由两个互补部分组成。首先，将深度学习-模糊逻辑（DL-FL）框架与开放最短路径优先（OSPF）协议集成，以提高网络中的数据路由效率。DL-FL框架结合这些异构特征来识别合适的下一跳节点并建立节能路由路径。其次，灌溉决策通过轻量级卷积神经网络-模糊逻辑控制器（CNN-FLC）执行。CNN-FLC处理来自传感器的信息和作物相关信息，包括空气温度、相对湿度、土壤湿度、蒸散速率、作物生长系数、作物需水量、种植日期、累计降雨量、近期降雨量、灌溉历史、作物生长阶段以及实际土壤湿度与目标土壤湿度之间的差值。这些输入用于表征作物水分胁迫，并动态确定合适的灌溉方案和喷灌器启动时长。所提出的IrrigaDL-FL框架通过在预定义路由轮次下对不同数量传感器节点进行仿真评估，并与若干现有方法进行比较。结果表明，IrrigaDL-FL在网络寿命、剩余能量、能量方差、传输数据包数量和平均路径长度方面均取得了更优性能。",null,"Scientific Reports","2026-10-08T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,21,18,14,8,1,"提出低成本物联网智能灌溉框架，融合深度学习与模糊逻辑优化路由与灌溉决策，方法新颖、仿真验证充分，对智慧农业节水研究有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","农业物联网","智能灌溉","节水农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[39],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":46,"locked":14,"version":47,"method":48,"evidence":49},"classified","2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":53},[51,60,67,75,83],{"code":33,"score":52,"supported":53,"title":54,"abstract":55,"tags":59},19,true,[34],[56,57,34,58],"灌溉","水资源","evapotranspiration",[30,31],{"code":40,"score":61,"supported":53,"title":62,"abstract":64,"tags":66},15,[63],"deep learning",[65,63],"深度学习",[28],{"code":68,"score":69,"supported":53,"title":70,"abstract":71,"tags":74},"I5",7,[],[72,73],"物联网","internet of things",[29],{"code":76,"score":77,"supported":53,"title":78,"abstract":79,"tags":82},"H2",6,[],[80,81],"土壤","soil",[],{"code":84,"score":85,"supported":53,"title":86,"abstract":87,"tags":88},"I1",4,[],[27],[27],[90,91],"IrrigaDL-FL 智能灌溉","CNN-FLC 灌溉决策","IrrigaDL-FL智能灌溉-4567","10.1038\u002Fs41598-026-72706-5",{"doi":93,"openalex_id":95,"authors":96,"venue":10,"cited_by_count":105,"oa_url":106,"card":107,"direction":111,"ingested_from":113},"W7221040139",[97,99,101,103],{"name":98,"orcid":9},"Ze Luo",{"name":100,"orcid":9},"Zhuo Yang",{"name":102,"orcid":9},"Yi Hu",{"name":104,"orcid":9},"Jun Wang",0,"https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72706-5_reference.pdf",{"tldr":108,"method":109,"finding":110,"direction":111,"opportunity":112},"提出IrrigaDL-FL低成本物联网智能灌溉框架，融合深度学习与模糊逻辑优化路由和灌溉决策。","用CNN-模糊逻辑控制器处理多源传感器与作物数据，结合OSPF协议做节能路由。","在仿真中网络寿命、剩余能量、能耗方差、传输包数和平均路径长度均优于现有方法。","智慧农业 \u002F 农业物联网","可探索真实农田部署下多作物、多气候场景的泛化能力与边缘计算资源约束优化。","openalex","2026-10-10T23:30:11.306685Z",{"total":77,"page":22,"page_size":77,"items":116},[117,195,271,350,429,487],{"id":118,"title":119,"url":120,"summary":121,"summary_zh":122,"content":9,"source_name":123,"source_url":120,"published_at":124,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":125,"sources":129,"tags":131,"primary_topic":133,"secondary_topics":134,"classification":141,"search_phrases":169,"slug":172,"view_count":21,"doi":173,"paper":174,"created_at":194},3355,"AI and Sustainable Agriculture Through Cost–Benefit Analysis of Smart Irrigation Systems","https:\u002F\u002Fdoi.org\u002F10.22004\u002Fag.econ.412813","The advancing role of Artificial Intelligence (AI) and its application in agriculture have disrupted traditional agricultural practices, with smart irrigation systems representing one of the leading technologies enabling sustainable agriculture. Smart irrigation systems utilize real–time data, machine learning algorithms, and predictive analytics to better optimize irrigation water use, limit wasted resources, and improve the yields of crop products. The proposed research will assess the economic and environmental impacts of AI smart irrigation systems with a full costs–benefits analysis. The proposed research considers both the capital cost and operating cost of smart irrigation systems and compares these traditional irrigation practices while also examining the long–term benefits of potential water savings from Smart Irrigation Systems, expanded agricultural production, and reduced human labour. This will give context for measuring the impacts of Smart Irrigation Systems on farm businesses, including both opportunities and barriers to adoption. Additionally, using a formal literature review to lock down existing research and surveys of irrigation farmers to collect a field data set will provide the proposed researchers a collective sample to measure the efficacy of AI smart irrigation systems, identify barriers, compare opportunities, and measure performance under differing climate and soil properties. The research will find high and substantial respective levels of benefits from the implementation of AI–based smart systems, particularly in water–stressed systems with positive impacts on farm profitability, private, and environmental conservation. This research is essential for informing stakeholders of actions and the delivery of AI–enabled solutions in support of more sustainable agricultural practices.","人工智能（Artificial Intelligence, AI）的不断发展及其在农业中的应用已经颠覆了传统的农业实践，其中智能灌溉系统是实现可持续农业的领先技术之一。智能灌溉系统利用实时数据、机器学习算法和预测分析，更好地优化灌溉用水、减少资源浪费并提高作物产量。拟议研究将通过全面的成本效益分析，评估AI智能灌溉系统的经济和环境影响。该研究将综合考虑智能灌溉系统的资本成本和运营成本，并将其与传统灌溉实践进行比较，同时考察智能灌溉系统在潜在节水、扩大农业生产和减少人力劳动方面的长期效益。这将为衡量智能灌溉系统对农场经营的影响提供背景，包括采用的机会和障碍。此外，通过正式文献综述锁定现有研究成果，并对灌溉农户进行调查以收集实地数据集，将为拟议研究者提供一个集体样本，用以衡量AI智能灌溉系统的效能、识别障碍、比较机会，并评估在不同气候和土壤条件下的表现。研究发现，实施基于AI的智能系统可带来显著且可观的效益，尤其是在水资源紧张的地区，对农场盈利能力、私人利益和环境保护均有积极影响。这项研究对于向利益相关者通报行动方案以及推动AI赋能解决方案以支持更可持续的农业实践至关重要。","AgEcon Search (University of Minnesota, USA)","2026-09-23T00:00:00Z",{"impact":19,"substance":126,"depth":19,"authority":127,"freshness":21,"relevant":22,"comment":128},20,13,"该研究以成本效益分析评估AI智能灌溉的经济与环境效益，方法系统、结论具参考价值，但属学术论文而非政策或产业事件，适合作为智慧农业主题的深度补充。",[130],{"name":123,"url":120},[27,28,30,31,132],"成本效益分析",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[135,140],{"code":136,"slug":137,"name":138,"path":139,"parent_code":37},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":142},{"candidates":143,"agricultural_evidence":53},[144,148,154,161,165],{"code":33,"score":52,"supported":53,"title":145,"abstract":146,"tags":147},[34],[56,57,34],[30,31],{"code":136,"score":20,"supported":53,"title":149,"abstract":151,"tags":153},[150],"sustainable agriculture",[152,150],"可持续农业",[],{"code":40,"score":13,"supported":53,"title":155,"abstract":156,"tags":160},[],[157,158,159],"机器学习","machine learning","artificial intelligence",[28],{"code":76,"score":77,"supported":53,"title":162,"abstract":163,"tags":164},[],[80,81],[],{"code":84,"score":22,"supported":14,"title":166,"abstract":167,"tags":168},[],[],[27],[170,171],"AI 智能灌溉 成本效益","AgEcon Search 智能灌溉","AI智能灌溉成本效益-3355","10.22004\u002Fag.econ.412813",{"doi":173,"openalex_id":175,"authors":176,"venue":123,"cited_by_count":105,"oa_url":120,"card":189,"direction":111,"ingested_from":113},"W7214115789",[177,179,181,183,185,187],{"name":178,"orcid":9},"Venkata Suman Jami",{"name":180,"orcid":9},"Purushotham Prasad Kalisetti",{"name":182,"orcid":9},"Sampath Dakshina Murthy A.",{"name":184,"orcid":9},"Gurunadha R.",{"name":186,"orcid":9},"Hema Mamidipaka",{"name":188,"orcid":9},"Gurrapu Omprakash",{"tldr":190,"method":191,"finding":192,"direction":111,"opportunity":193},"通过成本效益分析评估AI智能灌溉系统的经济与环境影响。","文献综述结合灌溉农户调查数据，进行成本效益分析。","AI智能灌溉在水资源紧张地区效益显著，提升利润并促进环保。","可针对不同气候土壤条件，量化AI灌溉的长期采纳障碍与推广机制。","2026-09-24T23:30:10.558578Z",{"id":196,"title":197,"url":198,"summary":199,"summary_zh":200,"content":9,"source_name":201,"source_url":198,"published_at":202,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":203,"score_detail":204,"sources":207,"tags":209,"primary_topic":212,"secondary_topics":216,"classification":219,"search_phrases":252,"slug":255,"view_count":85,"doi":9,"paper":256,"created_at":270},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":17,"substance":205,"depth":19,"authority":127,"freshness":77,"relevant":22,"comment":206},22,"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。",[208],{"name":201,"url":198},[27,28,29,210,211],"精准灌溉","土壤墒情",{"code":68,"slug":213,"name":214,"path":215,"parent_code":44},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[217,218],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":46,"locked":14,"version":47,"method":48,"evidence":220},{"candidates":221,"agricultural_evidence":53},[222,227,231,235,239,245],{"code":68,"score":19,"supported":53,"title":223,"abstract":225,"tags":226},[224],"IoT",[72,73,224],[29],{"code":40,"score":61,"supported":53,"title":228,"abstract":229,"tags":230},[158],[157,158],[28],{"code":33,"score":13,"supported":53,"title":232,"abstract":233,"tags":234},[],[56,34,58],[210],{"code":76,"score":69,"supported":53,"title":236,"abstract":237,"tags":238},[],[80,81],[211],{"code":84,"score":69,"supported":53,"title":240,"abstract":241,"tags":244},[],[242,243],"精准农业","precision agriculture",[27],{"code":246,"score":77,"supported":53,"title":247,"abstract":248,"tags":251},"G2",[],[249,250],"小农户","smallholder",[],[253,254],"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":9,"openalex_id":257,"authors":258,"venue":201,"cited_by_count":105,"oa_url":198,"card":265,"direction":111,"ingested_from":113},"W7217836036",[259,261,263],{"name":260,"orcid":9},"Christian Athanas Mwakyusa",{"name":262,"orcid":9},"Allen Deogratius Mwalekwa",{"name":264,"orcid":9},"Gift Geofrey Mushi",{"tldr":266,"method":267,"finding":268,"direction":111,"opportunity":269},"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":272,"title":273,"url":274,"summary":275,"summary_zh":276,"content":9,"source_name":277,"source_url":274,"published_at":278,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":279,"score_detail":280,"sources":285,"tags":287,"primary_topic":288,"secondary_topics":289,"classification":292,"search_phrases":326,"slug":329,"view_count":330,"doi":331,"paper":332,"created_at":349},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",72,{"impact":281,"substance":18,"depth":282,"authority":127,"freshness":283,"relevant":22,"comment":284},12,17,9,"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。",[286],{"name":277,"url":274},[27,28,157,72,30],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[290,291],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":68,"slug":213,"name":214,"path":215,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":293},{"candidates":294,"agricultural_evidence":53},[295,299,303,307,311,318,322],{"code":33,"score":19,"supported":53,"title":296,"abstract":297,"tags":298},[34],[56,57,34],[30],{"code":40,"score":127,"supported":53,"title":300,"abstract":301,"tags":302},[159],[157],[28,157],{"code":68,"score":283,"supported":53,"title":304,"abstract":305,"tags":306},[224],[],[72],{"code":76,"score":77,"supported":53,"title":308,"abstract":309,"tags":310},[],[80,81],[],{"code":312,"score":313,"supported":53,"title":314,"abstract":315,"tags":317},"H7",3,[],[316],"干旱",[],{"code":136,"score":313,"supported":53,"title":319,"abstract":320,"tags":321},[],[152],[],{"code":84,"score":22,"supported":14,"title":323,"abstract":324,"tags":325},[],[],[27],[327,328],"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":331,"openalex_id":333,"authors":334,"venue":277,"cited_by_count":105,"oa_url":274,"card":344,"direction":111,"ingested_from":113},"W7213546497",[335,338,341],{"name":336,"orcid":337},"Sarra Gourari","https:\u002F\u002Forcid.org\u002F0009-0005-1846-0886",{"name":339,"orcid":340},"Wafa Difallah","https:\u002F\u002Forcid.org\u002F0000-0002-6181-0395",{"name":342,"orcid":343},"Belkacem Draoui","https:\u002F\u002Forcid.org\u002F0000-0001-5490-3991",{"tldr":345,"method":346,"finding":347,"direction":111,"opportunity":348},"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":351,"title":352,"url":353,"summary":354,"summary_zh":9,"content":9,"source_name":355,"source_url":353,"published_at":356,"category":12,"cover_url":9,"hotness":357,"is_selected":14,"score":358,"score_detail":359,"sources":361,"tags":371,"primary_topic":373,"secondary_topics":374,"classification":377,"search_phrases":408,"slug":411,"view_count":85,"doi":412,"paper":413,"created_at":428},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.","Frontiers in Sustainable Food Systems","2026-08-25T00:00:00Z",55,74,{"impact":19,"substance":205,"depth":19,"authority":127,"freshness":313,"relevant":22,"comment":360},"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。",[362,363,366,368],{"name":355,"url":353},{"name":364,"url":365},"Zenodo (CERN European Organization for Nuclear Research)","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22790399",{"name":364,"url":367},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22790398",{"name":369,"url":370},"Journal of Animal Science","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fjas\u002Fskag311",[27,28,372,72,30],"边缘计算",{"code":68,"slug":213,"name":214,"path":215,"parent_code":44},[375,376],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":378},{"candidates":379,"agricultural_evidence":53},[380,386,390,394,400,404],{"code":68,"score":381,"supported":53,"title":382,"abstract":384,"tags":385},27,[224,383],"edge computing",[73,224,383],[72,372],{"code":33,"score":281,"supported":53,"title":387,"abstract":388,"tags":389},[34],[34],[30],{"code":40,"score":281,"supported":53,"title":391,"abstract":392,"tags":393},[158],[158],[28],{"code":395,"score":313,"supported":53,"title":396,"abstract":397,"tags":399},"A8",[],[398],"food security",[],{"code":76,"score":313,"supported":53,"title":401,"abstract":402,"tags":403},[],[81],[],{"code":84,"score":22,"supported":14,"title":405,"abstract":406,"tags":407},[],[],[27],[409,410],"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","10.3389\u002Ffsufs.2026.1827416",{"doi":412,"openalex_id":414,"authors":415,"venue":355,"cited_by_count":105,"oa_url":422,"card":423,"direction":111,"ingested_from":113},"W7204189894",[416,419],{"name":417,"orcid":418},"Mohammed Sulaiman Mustafa","https:\u002F\u002Forcid.org\u002F0000-0002-2920-9428",{"name":420,"orcid":421},"Hakan Kutucu","https:\u002F\u002Forcid.org\u002F0000-0001-7144-7246","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1827416\u002Fpdf",{"tldr":424,"method":425,"finding":426,"direction":111,"opportunity":427},"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。","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。","2026-09-01T04:03:09.639788Z",{"id":430,"title":431,"url":432,"summary":433,"summary_zh":434,"content":9,"source_name":364,"source_url":432,"published_at":435,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":436,"score_detail":437,"sources":439,"tags":441,"primary_topic":445,"secondary_topics":446,"classification":448,"search_phrases":468,"slug":471,"view_count":105,"doi":472,"paper":473,"created_at":486},5591,"Hierarchical Conformal Risk Control for Artificial Intelligence Agriculture Irrigation Scheduling Under Unmodeled Infiltration: A Computer Safety-Guarantee Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543665","Irrigation scheduling algorithms that rely on soil-moisture forecasts are vulnerable to unmodeled infiltration, the process by which water bypasses the root zone through preferential pathways that resistance-based soil models cannot represent. The framework is evaluated through a replication-based design study that characterises the operating characteristics of the before-after-control-impact estimator used to audit scheduler performance, under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 54 clusters are required to detect a 5-percentage-point effect at 80% power, and that the minimum detectable effect declines steeply as cluster count rises from 8 to 32. The contribution is a formal safety guarantee for irrigation decision support that remains valid when the infiltration model is wrong, together with an audit design that makes the guarantee empirically checkable.","依赖土壤湿度预报的灌溉调度算法容易受到未建模入渗的影响，即水分通过优先路径绕过根区的过程，而基于阻力的土壤模型无法表征这一过程。该框架通过一项基于重复的设计研究进行评估，该研究刻画了用于审计调度器性能的前后对照影响估计量的运行特性，其所依据的声明方差结构为：组间标准差6.0、残差标准差4.5、组内相关系数0.64。功效估计覆盖2000个设计单元，涵盖聚类数8、16、24和32以及效应量3、5和8个百分点。分析表明，在80%功效下检测5个百分点效应需要54个聚类，且最小可检测效应随聚类数从8增至32而急剧下降。本文的贡献在于为灌溉决策支持提供了一种正式的安全保证，该保证在入渗模型错误时仍然有效，同时提出了一种使该保证可经实证检验的审计设计。","2026-10-21T00:00:00Z",69,{"impact":21,"substance":205,"depth":19,"authority":281,"freshness":283,"relevant":22,"comment":438},"该研究提出在入渗模型失配条件下仍有效的灌溉决策安全保证框架，并给出可审计的试验设计，方法新颖、结论可靠，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[440],{"name":364,"url":432},[27,28,442,443,444],"灌溉决策","安全保证","试验设计",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[447],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":449},{"candidates":450,"agricultural_evidence":53},[451,455,460,464],{"code":33,"score":61,"supported":53,"title":452,"abstract":453,"tags":454},[34],[56,34],[442],{"code":40,"score":281,"supported":53,"title":456,"abstract":457,"tags":459},[159],[458],"decision support",[28],{"code":76,"score":77,"supported":53,"title":461,"abstract":462,"tags":463},[],[80,81],[],{"code":84,"score":22,"supported":14,"title":465,"abstract":466,"tags":467},[],[],[27],[469,470],"灌溉调度 安全保证","农业人工智能 安全保证 智慧农业 灌溉决策","灌溉调度安全保证-5591","10.5281\u002Fzenodo.23543665",{"doi":472,"openalex_id":474,"authors":475,"venue":364,"cited_by_count":105,"oa_url":432,"card":480,"direction":484,"ingested_from":113},"W7223131205",[476,478],{"name":477,"orcid":9},"Nassima Benkhelifa",{"name":479,"orcid":9},"Yacine Aït Ahmed",{"tldr":481,"method":482,"finding":483,"direction":484,"opportunity":485},"提出分层保形风险控制，为未建模入渗下的灌溉调度提供安全保证。","分层保形风险控制与基于重复设计的BACI审计，2000个设计单元功效分析。","检测5个百分点效应需54个集群，最小可检测效应随集群数增加陡降。","农业人工智能与决策模型","可将保形风险控制扩展到其他未建模扰动下的农业决策安全保证与审计设计。","2026-10-22T11:21:10.283561Z",{"id":488,"title":489,"url":490,"summary":491,"summary_zh":492,"content":9,"source_name":493,"source_url":490,"published_at":435,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":494,"score_detail":495,"sources":497,"tags":499,"primary_topic":502,"secondary_topics":503,"classification":506,"search_phrases":560,"slug":563,"view_count":105,"doi":564,"paper":565,"created_at":589},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":19,"substance":205,"depth":19,"authority":281,"freshness":283,"relevant":22,"comment":496},"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。",[498],{"name":493,"url":490},[27,28,500,501,210],"遥感","作物水分胁迫",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[504,505],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":68,"slug":213,"name":214,"path":215,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":507},{"candidates":508,"agricultural_evidence":53},[509,513,517,521,527,533,540,547,554],{"code":33,"score":61,"supported":53,"title":510,"abstract":511,"tags":512},[34],[56,34],[210],{"code":40,"score":13,"supported":53,"title":514,"abstract":515,"tags":516},[],[157,158,159],[28],{"code":68,"score":283,"supported":53,"title":518,"abstract":519,"tags":520},[],[72,73,224],[],{"code":84,"score":69,"supported":53,"title":522,"abstract":523,"tags":526},[],[524,525],"数字孪生","digital twin",[27],{"code":528,"score":69,"supported":53,"title":529,"abstract":530,"tags":532},"I3",[],[500,531],"remote sensing",[500],{"code":534,"score":77,"supported":53,"title":535,"abstract":536,"tags":539},"A2",[],[537,538],"小麦","wheat",[],{"code":541,"score":77,"supported":53,"title":542,"abstract":543,"tags":546},"A3",[],[544,545],"玉米","maize",[],{"code":548,"score":77,"supported":53,"title":549,"abstract":550,"tags":553},"A5",[],[551,552],"马铃薯","potato",[],{"code":555,"score":313,"supported":53,"title":556,"abstract":557,"tags":559},"B2",[],[558],"葡萄",[],[561,562],"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":564,"openalex_id":566,"authors":567,"venue":493,"cited_by_count":105,"oa_url":490,"card":583,"direction":111,"ingested_from":113},"W7223088921",[568,571,574,577,580],{"name":569,"orcid":570},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":572,"orcid":573},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":575,"orcid":576},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":578,"orcid":579},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":581,"orcid":582},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":584,"method":585,"finding":586,"direction":587,"opportunity":588},"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"]