[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3130":3,"related-3130":100},{"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":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":61,"slug":64,"view_count":65,"doi":66,"paper":67,"created_at":99},3130,"Closed-loop autonomous scheduling of multi-level irrigation canal-gate systems using an LLM-agent framework: prompting strategies and model heterogeneity","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112444","Closed-loop autonomous scheduling of multi-level irrigation canal-gate systems using an LLM-agent framework: prompting strategies and model heterogeneity。Computers and Electronics in Agriculture","基于LLM-agent框架的多级灌溉渠闸系统闭环自主调度：提示策略与模型异质性。《农业计算机与电子》",null,"Computers and Electronics in Agriculture","2026-09-22T00:00:00Z","论文",10,false,80,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":20,"comment":21},18,20,14,1,"核心期刊论文，将大模型智能体框架用于多级灌溉渠系闸门闭环自主调度，方法新颖、时效性强，对智慧灌溉有参考价值。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","智能灌溉","大模型","渠系闸门",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,50,56],{"code":31,"score":44,"supported":45,"title":46,"abstract":47,"tags":49},15,true,[32],[48,32],"灌溉",[27],{"code":51,"score":52,"supported":14,"title":53,"abstract":54,"tags":55},"I2",2,[],[],[26,28],{"code":57,"score":20,"supported":14,"title":58,"abstract":59,"tags":60},"I1",[],[],[25],[62,63],"LLM-agent 灌溉渠系 闸门调度","Computers and Electronics in Agriculture 智能灌溉","LLM-agent灌溉渠系闸门调度-3130",9,"10.1016\u002Fj.compag.2026.112444",{"doi":66,"openalex_id":68,"authors":69,"venue":10,"cited_by_count":91,"oa_url":6,"card":92,"direction":96,"ingested_from":98},"W7213982866",[70,72,74,77,79,82,84,86,88],{"name":71,"orcid":9},"Chen Junyu",{"name":73,"orcid":9},"Wang Haiyu",{"name":75,"orcid":76},"Junzeng Xu","https:\u002F\u002Forcid.org\u002F0000-0003-1467-7883",{"name":78,"orcid":9},"Zhang Binyang",{"name":80,"orcid":81},"Haoyang Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-9253-5824",{"name":83,"orcid":9},"Ye ZiJian",{"name":85,"orcid":9},"Zhang Zhonglili",{"name":87,"orcid":9},"Liu Xiaoyin",{"name":89,"orcid":90},"Rong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-8680-184X",0,{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"提出LLM智能体框架实现多级灌溉渠闸系统闭环自主调度，并比较提示策略与模型异质性。","基于LLM智能体框架，采用不同提示策略与多种大模型进行渠闸调度实验。","提示策略和模型选择显著影响多级渠闸闭环调度的自主决策效果。","农业人工智能与决策模型","可探索LLM智能体与水文模型耦合、多闸协同实时调度及鲁棒性验证。","openalex","2026-09-22T23:30:01.931736Z",{"total":101,"page":20,"page_size":101,"items":102},6,[103,180,256,347,414,473],{"id":104,"title":105,"url":106,"summary":107,"summary_zh":108,"content":9,"source_name":109,"source_url":106,"published_at":110,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":111,"score_detail":112,"sources":117,"tags":119,"primary_topic":122,"secondary_topics":128,"classification":130,"search_phrases":155,"slug":158,"view_count":91,"doi":159,"paper":160,"created_at":179},4888,"A MATLAB-based AI-IoT simulation framework for LSTM-driven smart solar irrigation and renewable energy management","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-74935-0","Smart irrigation offers a great avenue for better water use efficiency, and farming sustainability. However, most of the studies conducted so far tend to concentrate on the monitoring systems and platforms of the Internet of Things (IoT) or on the prediction models based on Artificial Intelligence (AI) (but not on both). To address this gap, this research study proposes an Artificial Intelligence (AI)-Internet of Things (IoT) system to predict the water consumption requirements and control the energy produced by a PV system along with a battery State of Charge (SOC) management system, Maximum Power Point Tracking (MPPT) algorithm, adaptive pump-speed control, and conceptual IoT communication architecture. A dataset of real environmental data from the NASA POWER database was used to test the framework for Egypt’s New Delta region. The LSTM model was able to classify the irrigation pump operating states with an accuracy of 96.11%, a recall of 0.9820, a precision of 0.9100, and an F1-score of 0.9446. It had a better performance than the two models, Artificial Neural Network (ANN) and Support Vector Machine (SVM) when compared and robustness testing with various independent training runs showed a stable performance in predicting. An estimated annual water-saving rate of 28.57% was obtained relative to the assumed conventional fixed-schedule baseline, while motor energy use was reduced by 74.74% through adaptive pump-speed control. A sensitivity analysis was also performed, showing that the model was stable to moderate variations in environmental and operating conditions. Combined, these findings suggest that the use of AI-based modelling for renewable energy management in the context of an irrigation simulation model built in MATLAB could be a valuable asset in improving irrigation efficiency and lowering water and energy use, which is a promising start for future implementation of hardware versions of intelligent, solar-powered irrigation devices.","智能灌溉为提高用水效率和农业可持续性提供了重要途径。然而，迄今为止大多数研究倾向于集中在物联网（IoT）的监测系统和平台，或基于人工智能（AI）的预测模型（但很少两者兼顾）。为弥补这一空白，本研究提出了一种人工智能（AI）-物联网（IoT）系统，用于预测用水需求并控制光伏系统产生的能量，同时包含电池荷电状态（SOC）管理系统、最大功率点跟踪（MPPT）算法、自适应泵速控制以及概念性物联网通信架构。研究采用NASA POWER数据库中的真实环境数据集，在埃及新三角洲地区对该框架进行了测试。LSTM模型能够对灌溉泵运行状态进行分类，准确率达到96.11%，召回率为0.9820，精确率为0.9100，F1分数为0.9446。与人工神经网络（ANN）和支持向量机（SVM）两个模型相比，该模型表现更优，且通过多次独立训练运行进行的鲁棒性测试表明其在预测方面具有稳定性能。相对于假设的传统固定调度基线，估计年节水率为28.57%，而通过自适应泵速控制，电机能耗降低了74.74%。研究还进行了敏感性分析，表明该模型对环境和运行条件的中等程度变化具有稳定性。综合来看，这些发现表明，在MATLAB中构建的灌溉仿真模型背景下，将基于AI的建模用于可再生能源管理，可能是提高灌溉效率、降低水和能源消耗的有价值手段，这为未来实现智能太阳能灌溉设备的硬件版本提供了一个有前景的开端。","Scientific Reports","2026-10-12T00:00:00Z",78,{"impact":113,"substance":114,"depth":17,"authority":19,"freshness":115,"relevant":20,"comment":116},16,22,8,"该研究提出AI-IoT融合的太阳能灌溉仿真框架，LSTM预测精度达96.11%，节水28.57%、节能74.74%，方法新颖且数据可靠，对智慧农业与农业能源管理有参考价值。",[118],{"name":109,"url":106},[25,26,27,120,121],"节水农业","光伏农业",{"code":123,"slug":124,"name":125,"path":126,"parent_code":127},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot","I",[129],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":131},{"candidates":132,"agricultural_evidence":45},[133,141,145,151],{"code":123,"score":134,"supported":45,"title":135,"abstract":137,"tags":140},17,[136],"IoT",[138,139,136],"物联网","internet of things",[],{"code":31,"score":113,"supported":45,"title":142,"abstract":143,"tags":144},[32],[48,32],[27,120],{"code":51,"score":146,"supported":45,"title":147,"abstract":148,"tags":150},4,[],[149],"artificial intelligence",[26],{"code":57,"score":20,"supported":14,"title":152,"abstract":153,"tags":154},[],[],[25],[156,157],"MATLAB AI-IoT 太阳能灌溉","LSTM 智能灌溉 埃及新三角洲","MATLABAI-IoT太阳能灌溉-4888","10.1038\u002Fs41598-026-74935-0",{"doi":159,"openalex_id":161,"authors":162,"venue":109,"cited_by_count":91,"oa_url":172,"card":173,"direction":177,"ingested_from":98},"W7221571268",[163,166,169],{"name":164,"orcid":165},"Ahmed Mashaly","https:\u002F\u002Forcid.org\u002F0009-0007-7009-4531",{"name":167,"orcid":168},"Ragab Abdelaziz El-Sehiemy","https:\u002F\u002Forcid.org\u002F0000-0002-3340-4031",{"name":170,"orcid":171},"Mohamed M. Elgohary","https:\u002F\u002Forcid.org\u002F0000-0003-4441-7812","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-74935-0.pdf",{"tldr":174,"method":175,"finding":176,"direction":177,"opportunity":178},"提出MATLAB中AI-IoT仿真框架，用LSTM预测灌溉需水并管理光伏与电池。","NASA POWER环境数据，LSTM对比ANN\u002FSVM，含MPPT与自适应泵速","LSTM分类准确率96.11%，节水28.57%，电机能耗降74.74%。","智慧农业 \u002F 农业物联网","可延伸至真实硬件部署与多区域验证，并融合实时气象与土壤墒情数据。","2026-10-14T23:30:13.060384Z",{"id":181,"title":182,"url":183,"summary":184,"summary_zh":185,"content":9,"source_name":109,"source_url":183,"published_at":186,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":187,"score_detail":188,"sources":191,"tags":193,"primary_topic":195,"secondary_topics":196,"classification":201,"search_phrases":233,"slug":236,"view_count":101,"doi":237,"paper":238,"created_at":255},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。","2026-10-08T00:00:00Z",77,{"impact":113,"substance":189,"depth":17,"authority":19,"freshness":115,"relevant":20,"comment":190},21,"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。",[192],{"name":109,"url":183},[25,26,194,27,120],"农业物联网",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[197],{"code":51,"slug":198,"name":199,"path":200,"parent_code":127},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":38,"locked":14,"version":39,"method":40,"evidence":202},{"candidates":203,"agricultural_evidence":45},[204,211,217,222,229],{"code":31,"score":205,"supported":45,"title":206,"abstract":207,"tags":210},19,[32],[48,208,32,209],"水资源","evapotranspiration",[27,120],{"code":51,"score":44,"supported":45,"title":212,"abstract":214,"tags":216},[213],"deep learning",[215,213],"深度学习",[26],{"code":123,"score":218,"supported":45,"title":219,"abstract":220,"tags":221},7,[],[138,139],[194],{"code":223,"score":101,"supported":45,"title":224,"abstract":225,"tags":228},"H2",[],[226,227],"土壤","soil",[],{"code":57,"score":146,"supported":45,"title":230,"abstract":231,"tags":232},[],[25],[25],[234,235],"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":237,"openalex_id":239,"authors":240,"venue":109,"cited_by_count":91,"oa_url":249,"card":250,"direction":177,"ingested_from":98},"W7221040139",[241,243,245,247],{"name":242,"orcid":9},"Ze Luo",{"name":244,"orcid":9},"Zhuo Yang",{"name":246,"orcid":9},"Yi Hu",{"name":248,"orcid":9},"Jun Wang","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72706-5_reference.pdf",{"tldr":251,"method":252,"finding":253,"direction":177,"opportunity":254},"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。","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。","2026-10-10T23:30:11.306685Z",{"id":257,"title":258,"url":259,"summary":260,"summary_zh":261,"content":9,"source_name":262,"source_url":259,"published_at":263,"category":12,"cover_url":9,"hotness":13,"is_selected":45,"score":264,"score_detail":265,"sources":267,"tags":269,"primary_topic":272,"secondary_topics":278,"classification":280,"search_phrases":319,"slug":322,"view_count":20,"doi":323,"paper":324,"created_at":346},4371,"Intelligent greenhouse irrigation control via multilayer perceptron neural network climate prediction integrated with fuzzy logic control","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compeleceng.2026.111587","Conventional irrigation methods rely on indoor sensor feedback, which fails to anticipate rapid microclimate fluctuations and often leads to over-irrigation or water stress. Additionally, traditional controllers used in the watering process lack the ability to adjust water flow rate dynamically, resulting in inefficient water usage and energy waste. Intelligent Greenhouse Irrigation Management (IGIM) remains a critical challenge for achieving sustainable, high-yield greenhouse agriculture. Precise irrigation management is especially important for crops like tomatoes, where both timing and quantity directly influence productivity and energy consumption. To address these challenges, this paper proposes a hybrid intelligent system that integrates a Multi-Layer Perceptron Artificial Neural Network (MLP-ANN) with an Adaptive Fuzzy Logic Controller (AFLC). The MLP-ANN forecasts key indoor variables such as temperature, humidity, and soil moisture, achieving R² values of 0.999. The Root Mean Square Errors of 0.266 °C, 0.254%, and 0.808%, respectively. These predictions directly feed into the AFLC, which employs an adaptive rule base to dynamically adjust irrigation flow rates in real time (0–18 LPH), significantly enhancing water-use efficiency and reducing waste to save energy consumption in the watering process. The key novelty of this work is the direct integration of MLP-predicted microclimate variables into the antecedent of adaptive fuzzy rules, enabling the controller to anticipate and respond to climate variations before they affect crop conditions. Unlike conventional reactive or static rule-based systems, the proposed MLP-AFLC framework creates a closed-loop coupling between forecasting and actuation, allowing predictive, rather than threshold-based, irrigation decisions. By integrating predictive intelligence with adaptive control, the proposed MLP-AFLC framework provides a robust, autonomous, and sustainable solution for greenhouse management, advancing precision agriculture in highly dynamic environments.","传统灌溉方法依赖室内传感器反馈，无法预判微气候的快速波动，常导致过度灌溉或水分胁迫。此外，灌溉过程中使用的传统控制器缺乏动态调节流速的能力，造成水资源利用效率低下和能源浪费。智能温室灌溉管理（IGIM）仍是实现可持续、高产温室农业的关键挑战。对于番茄等作物而言，精准灌溉管理尤为重要，因为灌溉时机和水量直接影响产量和能耗。为解决这些挑战，本文提出了一种将多层感知器人工神经网络（MLP-ANN）与自适应模糊逻辑控制器（AFLC）相集成的混合智能系统。MLP-ANN预测温度、湿度和土壤湿度等关键室内变量，R²值达到0.999，均方根误差分别为0.266 °C、0.254%和0.808%。这些预测结果直接输入AFLC，后者采用自适应规则库实时动态调节灌溉流速（0–18 LPH），显著提高水资源利用效率并减少浪费，从而在灌溉过程中节约能耗。本工作的关键创新在于将MLP预测的微气候变量直接集成到自适应模糊规则的前件中，使控制器能够在气候变化影响作物状况之前进行预判和响应。与传统反应式或静态规则系统不同，所提出的MLP-AFLC框架在预测与执行之间建立了闭环耦合，实现了基于预测而非基于阈值的灌溉决策。通过将预测智能与自适应控制相结合，所提出的MLP-AFLC框架为温室管理提供了一种稳健、自主且可持续的解决方案，推动了高度动态环境下的精准农业发展。","Computers & Electrical Engineering","2026-10-06T00:00:00Z",81,{"impact":17,"substance":114,"depth":17,"authority":19,"freshness":65,"relevant":20,"comment":266},"提出MLP-ANN与自适应模糊控制融合的温室预测性灌溉框架，R²达0.999，方法新颖且数据可靠，对精准农业节水节能有实质参考价值。",[268],{"name":262,"url":259},[25,26,27,270,271],"精准农业","温室种植",{"code":273,"slug":274,"name":275,"path":276,"parent_code":277},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture","B",[279],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":281},{"candidates":282,"agricultural_evidence":45},[283,287,293,298,302,309,315],{"code":31,"score":17,"supported":45,"title":284,"abstract":285,"tags":286},[32],[48,208,32],[27],{"code":273,"score":44,"supported":45,"title":288,"abstract":290,"tags":292},[289],"greenhouse",[291,289],"温室",[271],{"code":57,"score":115,"supported":45,"title":294,"abstract":295,"tags":297},[],[270,296],"precision agriculture",[25,270],{"code":223,"score":101,"supported":45,"title":299,"abstract":300,"tags":301},[],[226,227],[],{"code":303,"score":304,"supported":45,"title":305,"abstract":306,"tags":308},"B1",3,[],[307],"番茄",[],{"code":310,"score":304,"supported":45,"title":311,"abstract":312,"tags":314},"H7",[],[313],"气候变化",[],{"code":51,"score":20,"supported":14,"title":316,"abstract":317,"tags":318},[],[],[26],[320,321],"MLP-AFLC 温室灌溉","神经网络 模糊控制 灌溉","MLP-AFLC温室灌溉-4371","10.1016\u002Fj.compeleceng.2026.111587",{"doi":323,"openalex_id":325,"authors":326,"venue":262,"cited_by_count":91,"oa_url":259,"card":341,"direction":96,"ingested_from":98},"W7220746994",[327,330,333,335,338],{"name":328,"orcid":329},"Jamel Riahi","https:\u002F\u002Forcid.org\u002F0009-0006-1434-4367",{"name":331,"orcid":332},"Hamza Nasri","https:\u002F\u002Forcid.org\u002F0009-0008-7343-4199",{"name":334,"orcid":9},"Abdelkader Mami",{"name":336,"orcid":337},"Mario Carpentieri","https:\u002F\u002Forcid.org\u002F0000-0001-5165-5873",{"name":339,"orcid":340},"Silvano Vergura","https:\u002F\u002Forcid.org\u002F0000-0002-0826-9237",{"tldr":342,"method":343,"finding":344,"direction":177,"opportunity":345},"提出MLP-ANN预测温室微气候并驱动自适应模糊控制器，实现预测性智能灌溉。","MLP神经网络预测温湿度与土壤水分，结合自适应模糊逻辑控制流量。","预测R²达0.999，模糊控制器动态调节0-18 LPH流量，显著节水节能。","可探索多作物多环境迁移学习与边缘部署，降低预测模型算力需求。","2026-10-07T23:30:43.848308Z",{"id":348,"title":349,"url":350,"summary":351,"summary_zh":352,"content":9,"source_name":353,"source_url":354,"published_at":355,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":356,"score_detail":357,"sources":360,"tags":362,"primary_topic":364,"secondary_topics":365,"classification":366,"search_phrases":396,"slug":399,"view_count":52,"doi":400,"paper":401,"created_at":413},4209,"AI-Driven Smart Irrigation System Using Edge-Based Embedded Controllers","https:\u002F\u002Fdoi.org\u002F10.31838\u002Fece\u002F03.02.04","This study brings out a new AI-based smart irrigation device aimed at solving the increasing problem of water shortage and poor agricultural procedures using emulated edge-based controllers. This combination of environmental sensing, lightweight machine learning algorithms and actuation on microcontrollers enables the system to do real time, adaptive irrigation scheduling. Their implementation of important parts like Raspberry Pi 4 as an AI inference module and an STM32 microcontroller as an actuator controller accelerates the responsiveness, increases security, and saves energy consumption since there is no need in cloud computing. Using the local climatic and soil moisture data the machine learning model identifies optimum irrigation time and duration looking at various parameters such as temperature, humidity, rain and crop-specific thresholds. The whole decision-making process is automated and carried out at the edge that makes it functional even without interruption in areas with poor or no internet connection. This was done by conducting extensive field tests within the semi-arid agricultural areas to prove the efficacy of the recommended solution. The findings show that there is a considerable gain in the efficiency of resources, with up to 38 percent of reduction of water use and 20 percent of increase in the yield of the crops contrasted to the conventional time-based irrigation schemes. Also, the system averaged a latency of only 34millisecs and consumed power at less than 2.5W which became very handy in deployment in rural areas. TinyML and its compatibility with cheap edge hardware are scalable and sustainable, which creates an efficient path to modernize the irrigation infrastructure in the developing world. This article does not only highlight the revolutionary nature of embedded AI in precision agriculture, but it precondition the further innovative development of the field of data-driven farm management and autonomous farm management. The one suggested is one of the options that could be implemented to achieve environmental sustainability, enhance the productivity of agriculture, and make smart and local decisions to use water intelligently.","本研究提出了一种基于人工智能的新型智能灌溉装置，采用模拟边缘控制器，旨在解决日益严重的缺水问题和农业操作不当问题。该系统将环境传感、轻量级机器学习算法和微控制器上的执行器相结合，能够实现实时自适应灌溉调度。其关键部分的实现方式包括将树莓派4（Raspberry Pi 4）作为AI推理模块，将STM32微控制器作为执行器控制器，从而提升了响应速度、增强了安全性并降低了能耗，因为无需依赖云计算。利用当地气候和土壤湿度数据，机器学习模型根据温度、湿度、降雨和作物特定阈值等多种参数，确定最佳灌溉时间和时长。整个决策过程自动化并在边缘端执行，使其即使在互联网连接较差或无互联网连接的地区也能不间断运行。通过在半干旱农业区进行广泛的田间测试，验证了所推荐方案的有效性。研究结果表明，资源效率有显著提升，与传统基于时间的灌溉方案相比，用水量减少了高达38%，作物产量增加了20%。此外，该系统平均延迟仅为34毫秒，功耗低于2.5瓦，在农村地区部署中非常实用。TinyML及其与低成本边缘硬件的兼容性具有可扩展性和可持续性，为发展中国家灌溉基础设施的现代化开辟了一条高效路径。本文不仅强调了嵌入式AI在精准农业中的革命性，还为数据驱动农场管理和自主农场管理领域的进一步创新发展奠定了基础。所提出的方案是实现环境可持续性、提高农业生产力以及做出智能本地化决策以合理用水的一种可行选择。","Progress in Electronics and Communication Engineering","https:\u002F\u002Fecejournals.in\u002Findex.php\u002FPECE\u002Farticle\u002Fview\u002F427","2026-10-19T00:00:00Z",74,{"impact":17,"substance":114,"depth":17,"authority":358,"freshness":304,"relevant":20,"comment":359},13,"边缘AI灌溉系统实测节水38%、增产20%，方法新颖数据扎实，但论文发表于两周后、时效性偏弱，适合作为技术类精选。",[361],{"name":353,"url":354},[25,26,363,27,270],"边缘计算",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":367},{"candidates":368,"agricultural_evidence":45},[369,373,377,383,387,392],{"code":31,"score":44,"supported":45,"title":370,"abstract":371,"tags":372},[32],[48,32],[27],{"code":57,"score":115,"supported":45,"title":374,"abstract":375,"tags":376},[],[270,296],[25,270],{"code":51,"score":218,"supported":45,"title":378,"abstract":379,"tags":382},[],[380,381],"机器学习","machine learning",[26],{"code":223,"score":101,"supported":45,"title":384,"abstract":385,"tags":386},[],[226,227],[],{"code":310,"score":304,"supported":45,"title":388,"abstract":389,"tags":391},[],[390],"干旱",[],{"code":123,"score":20,"supported":14,"title":393,"abstract":394,"tags":395},[],[],[363],[397,398],"Raspberry Pi STM32 智能灌溉","TinyML 边缘计算 节水灌溉","RaspberryPiSTM32智能灌溉-4209","10.31838\u002Fece\u002F03.02.04",{"doi":400,"openalex_id":402,"authors":403,"venue":353,"cited_by_count":20,"oa_url":354,"card":408,"direction":177,"ingested_from":98},"W7219822766",[404,406],{"name":405,"orcid":9},"Fahad Al-Jame",{"name":407,"orcid":9},"Perera Manthila",{"tldr":409,"method":410,"finding":411,"direction":177,"opportunity":412},"提出基于边缘嵌入式控制器的AI智能灌溉系统，实现实时自适应灌溉调度。","Raspberry Pi 4做AI推理、STM32做执行控制，结合环境传感与轻量","半干旱区试验显示节水38%、增产20%，延迟34毫秒、功耗低于2.5W。","可探索TinyML模型在多种作物与土壤气候下的泛化能力及低成本边缘节点组网协同。","2026-10-05T23:30:08.862496Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":9,"source_name":420,"source_url":421,"published_at":422,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":423,"score_detail":424,"sources":426,"tags":428,"primary_topic":430,"secondary_topics":431,"classification":432,"search_phrases":457,"slug":460,"view_count":146,"doi":461,"paper":462,"created_at":472},4164,"SMART IRRIGATION STRATEGY RECOMMENDED SYSTEM USING ML","https:\u002F\u002Fdoi.org\u002F10.64751\u002Fqbkrtp46","Water used for irrigation forms the largest share of freshwater consumption in agriculture, and much of it is wasted because fields are watered on a fixed schedule rather than according to the actual needs of the crop. Over-irrigation leaches nutrients, raises pumping cost, and can damage roots, while under-irrigation reduces yield during critical growth stages. This paper presents a Smart Irrigation Strategy Recommendation System that uses soil and weather sensing together with machine learning to recommend when to irrigate, how much water to apply, and which irrigation method suits the field and crop. The sensing part of the system consists of field nodes built around an ESP32 microcontroller that read a capacitive soil moisture sensor at two depths, a soil temperature probe, and an air temperature and humidity sensor. Each node samples these values at regular intervals, averages several readings to reduce noise, and sends them over Wi-Fi or a LoRa link to a gateway. The nodes are powered by a small solar panel and battery, and they spend most of their time in deep sleep to extend battery life. Weather forecast data for the location, including expected rainfall, temperature, and wind speed, is obtained from a public service and merged with the sensor readings. The machine learning part of the system operates in two stages. In the first stage, a regression model predicts the soil moisture level expected over the next twenty-four hours using current sensor readings, reference evapotranspiration computed from weather data, crop type, and growth stage. Linear Regression, Random Forest, Gradient Boosting, and Support Vector Regression were compared for this task using RMSE and MAE. In the second stage, a classification model recommends one of several irrigation actions, namely no irrigation, light irrigation, normal irrigation, or deferral because rain is expected. Decision Tree, Random Forest, K-Nearest Neighbours, and XGBoost classifiers were compared using accuracy, precision, recall, and F1-score. The recommendations are presented through a web dashboard that shows live soil moisture for each field zone, the predicted moisture curve, the recommended action with the estimated water volume and pump running time, and a record of past irrigation events. The system can also switch a relay-controlled pump or solenoid valve automatically when the farmer chooses automatic mode, while manual confirmation remains the default. In trials using collected and public agronomic data, the Random Forest models gave the best results, and the recommended schedules used noticeably less water than a fixed daily schedule while keeping moisture within the desired range. The system is intended for small and medium farms, kitchen gardens, polyhouses, and institutional campuses where water availability is limited and labour for manual checking is scarce. It combines inexpensive electronics, low-power wireless communication, and interpretable machine learning in a single practical tool. Future work includes crop-specific models trained on local field trials, integration of satellite vegetation indices, and support for drip fertigation scheduling.","农业灌溉用水占农业淡水消耗量的最大份额，而其中大量水资源被浪费，原因在于农田按固定日程灌溉，而非根据作物的实际需求进行灌溉。过度灌溉会淋失养分、增加抽水成本，并可能损伤根系；而灌溉不足则会在关键生长期降低产量。本文提出了一种智能灌溉策略推荐系统，利用土壤与气象传感技术结合机器学习，推荐何时灌溉、灌多少水，以及哪种灌溉方式适合该田块和作物。系统的传感部分由基于ESP32微控制器构建的田间节点组成，这些节点读取两个深度的电容式土壤水分传感器、一个土壤温度探头以及一个空气温湿度传感器。每个节点按固定间隔采样这些数值，对多次读数取平均以降低噪声，并通过Wi-Fi或LoRa链路发送至网关。节点由小型太阳能板和电池供电，大部分时间处于深度睡眠状态以延长电池寿命。该地点的天气预报数据（包括预期降雨量、温度和风速）从公共服务获取，并与传感器读数融合。系统的机器学习部分分两个阶段运行。第一阶段，回归模型利用当前传感器读数、根据气象数据计算的参考蒸散量、作物类型和生长阶段，预测未来二十四小时内预期的土壤水分水平。针对该任务，使用RMSE和MAE对线性回归、随机森林、梯度提升和支持向量回归进行了比较。第二阶段，分类模型推荐若干灌溉措施之一，即不灌溉、轻度灌溉、正常灌溉或因预期降雨而推迟灌溉。使用准确率、精确率、召回率和F1分数对决策树、随机森林、K近邻和XGBoost分类器进行了比较。推荐结果通过一个网页仪表板呈现，显示每个田块分区的实时土壤水分、预测水分曲线、推荐措施及估计水量和泵运行时间，以及过往灌溉事件记录。当农民选择自动模式时，系统还可自动切换继电器控制的泵或电磁阀，而手动确认仍为默认方式。在利用收集数据和公共农业","International Journal of AI Electronics and Nexus Energy","https:\u002F\u002Fzesterapublications.com\u002Fjournals\u002Findex.php\u002Fijaene\u002Farticle\u002Fview\u002F1085","2026-10-02T00:00:00Z",56,{"impact":115,"substance":17,"depth":113,"authority":101,"freshness":115,"relevant":20,"comment":425},"论文提出基于ESP32传感与机器学习两阶段模型的智能灌溉推荐系统，方法完整、对比实验充分，但属学术研究且期刊影响力有限，公共价值偏细分领域。",[427],{"name":420,"url":421},[25,26,27,429,120],"土壤墒情",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":433},{"candidates":434,"agricultural_evidence":45},[435,439,443,447,453],{"code":31,"score":205,"supported":45,"title":436,"abstract":437,"tags":438},[32],[48,208,32,209],[27,120],{"code":223,"score":218,"supported":45,"title":440,"abstract":441,"tags":442},[],[226,227],[429],{"code":51,"score":218,"supported":45,"title":444,"abstract":445,"tags":446},[],[380,381],[26],{"code":448,"score":304,"supported":45,"title":449,"abstract":450,"tags":452},"F3",[],[451],"fertigation",[],{"code":57,"score":20,"supported":14,"title":454,"abstract":455,"tags":456},[],[],[25],[458,459],"ESP32 土壤湿度 智能灌溉","机器学习 灌溉决策 推荐系统","ESP32土壤湿度智能灌溉-4164","10.64751\u002Fqbkrtp46",{"doi":461,"openalex_id":463,"authors":464,"venue":420,"cited_by_count":91,"oa_url":421,"card":467,"direction":177,"ingested_from":98},"W7218574975",[465],{"name":466,"orcid":9},"1 Dr.M.Mahesh, 2 Kesagoni Akshika, 3 Bandari Sandeep, 4 Dumpati Akshitha, 5 Thadem Pranay",{"tldr":468,"method":469,"finding":470,"direction":177,"opportunity":471},"提出基于ESP32传感与两阶段机器学习的智能灌溉推荐系统，预测土壤湿度并推荐灌溉动作。","ESP32土壤温湿度传感+LoRa\u002FWiFi，回归预测湿度、分类推荐灌溉，比较多","两阶段ML可预测未来24小时土壤湿度并给出灌溉建议，支持自动或手动控制水泵。","可探索多深度土壤传感与天气预报融合的轻量级边缘ML模型，降低部署成本并提升推荐精度。","2026-10-04T23:30:08.843055Z",{"id":474,"title":475,"url":476,"summary":477,"summary_zh":478,"content":9,"source_name":479,"source_url":476,"published_at":480,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":187,"score_detail":481,"sources":483,"tags":485,"primary_topic":487,"secondary_topics":488,"classification":495,"search_phrases":520,"slug":523,"view_count":115,"doi":524,"paper":525,"created_at":545},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":17,"substance":18,"depth":17,"authority":358,"freshness":115,"relevant":20,"comment":482},"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。",[484],{"name":479,"url":476},[25,26,27,120,486],"成本效益分析",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[489,494],{"code":490,"slug":491,"name":492,"path":493,"parent_code":35},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture",{"code":51,"slug":198,"name":199,"path":200,"parent_code":127},{"status":38,"locked":14,"version":39,"method":40,"evidence":496},{"candidates":497,"agricultural_evidence":45},[498,502,508,512,516],{"code":31,"score":205,"supported":45,"title":499,"abstract":500,"tags":501},[32],[48,208,32],[27,120],{"code":490,"score":19,"supported":45,"title":503,"abstract":505,"tags":507},[504],"sustainable agriculture",[506,504],"可持续农业",[],{"code":51,"score":13,"supported":45,"title":509,"abstract":510,"tags":511},[],[380,381,149],[26],{"code":223,"score":101,"supported":45,"title":513,"abstract":514,"tags":515},[],[226,227],[],{"code":57,"score":20,"supported":14,"title":517,"abstract":518,"tags":519},[],[],[25],[521,522],"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":524,"openalex_id":526,"authors":527,"venue":479,"cited_by_count":91,"oa_url":476,"card":540,"direction":177,"ingested_from":98},"W7214115789",[528,530,532,534,536,538],{"name":529,"orcid":9},"Venkata Suman Jami",{"name":531,"orcid":9},"Purushotham Prasad Kalisetti",{"name":533,"orcid":9},"Sampath Dakshina Murthy A.",{"name":535,"orcid":9},"Gurunadha R.",{"name":537,"orcid":9},"Hema Mamidipaka",{"name":539,"orcid":9},"Gurrapu Omprakash",{"tldr":541,"method":542,"finding":543,"direction":177,"opportunity":544},"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"]