[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3152":3,"related-3152":97},{"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":24,"primary_topic":30,"secondary_topics":35,"classification":47,"search_phrases":79,"slug":82,"view_count":83,"doi":84,"paper":85,"created_at":96},3152,"An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23311932.2026.2725400","An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania。Cogent Food & Agriculture",null,"Cogent Food & Agriculture","2026-09-22T00:00:00Z","论文",10,false,69,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},12,18,16,13,1,"论文提出物联网与机器学习融合的玉米产量预测框架，方法有新意但属区域性应用研究，影响力有限，时效性强。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","产量预测","物联网","玉米",{"code":31,"slug":32,"name":29,"path":33,"parent_code":34},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[36,42],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":43,"slug":44,"name":45,"path":46,"parent_code":41},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":48,"locked":13,"version":49,"method":50,"evidence":51},"classified","2026-10-22.2","rules",{"candidates":52,"agricultural_evidence":54},[53,58,64,69,74],{"code":31,"score":16,"supported":54,"title":55,"abstract":56,"tags":57},true,[32],[32],[29],{"code":59,"score":16,"supported":54,"title":60,"abstract":62,"tags":63},"I1",[61],"smart agriculture",[61],[25],{"code":37,"score":16,"supported":54,"title":65,"abstract":67,"tags":68},[66],"machine learning",[66],[26],{"code":43,"score":16,"supported":54,"title":70,"abstract":72,"tags":73},[71],"IoT",[71],[28],{"code":75,"score":20,"supported":13,"title":76,"abstract":77,"tags":78},"I3",[],[],[27],[80,81],"坦桑尼亚 玉米 产量预测","物联网 机器学习 智慧农业","坦桑尼亚玉米产量预测-3152",4,"10.1080\u002F23311932.2026.2725400",{"doi":84,"openalex_id":86,"authors":87,"venue":9,"cited_by_count":93,"oa_url":6,"card":8,"direction":94,"ingested_from":95},"W7213978365",[88,91],{"name":89,"orcid":90},"Alcardo Alex Barakabitze","https:\u002F\u002Forcid.org\u002F0000-0001-8960-8415",{"name":92,"orcid":8},"Yasinta Nzogera",0,"智慧农业 \u002F 农业物联网","openalex","2026-09-22T23:30:10.178097Z",{"total":98,"page":20,"page_size":98,"items":99},6,[100,196,301,354,431,487],{"id":101,"title":102,"url":103,"summary":104,"summary_zh":105,"content":8,"source_name":106,"source_url":103,"published_at":107,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":108,"score_detail":109,"sources":115,"tags":117,"primary_topic":119,"secondary_topics":120,"classification":122,"search_phrases":154,"slug":157,"view_count":158,"doi":159,"paper":160,"created_at":195},2505,"A continually evolving knowledge-guided deep learning framework for daily maize yield formation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104981","CONTEXT As multi-source agricultural datasets expand, accurate and interpretable simulation of crop yield formation is increasingly feasible and important for food security. Process-based models are widely used for yield forecasting but require laborious regional calibration. Artificial intelligence models learn physiological patterns from large datasets but lack physiological consistency and generalize poorly under data-scarce conditions. OBJECTIVE We developed AgroEvoDeep-Yield, a knowledge-guided model that encodes mechanistic understanding through its neural architecture, enabling explicit and interpretable simulation of daily maize yield formation from flowering to maturity. We further established a framework that supports continual model evolution as new data become available. METHODS The model was pretrained on APSIM-simulated grain number and daily grain biomass sequences to impose physiological consistency. Following pretraining, the model evolved through two continual learning stages. First, field-level continual learning using 796 field observations reduced biases inherited from APSIM. The model was then adapted to regional-scale multi-source inputs using long-term records from 945 meteorological stations and expert-constrained cultivar-parameter optimization. RESULTS AND CONCLUSIONS After field-level continual learning, AgroEvoDeep-Yield reduced grain number and yield simulation errors by 29% and 24%, respectively, relative to APSIM, and outperformed conventional machine learning models in out-of-region prediction. Region-level continual learning reduced yield RMSE to 1.09 t\u002Fha, and expert-constrained cultivar-parameter optimization further reduced it to 0.80 t\u002Fha. SIGNIFICANCE This study demonstrates how a knowledge-guided model can be repeatedly adapted as new data become available, providing a practical framework for continual model evolution and a basis for future agricultural decision support.","背景 随着多源农业数据集的不断扩展，准确且可解释地模拟作物产量形成过程日益可行，对粮食安全也愈发重要。基于过程的模型广泛用于产量预测，但需要耗费大量精力进行区域校准。人工智能模型能够从大规模数据集中学习生理模式，但缺乏生理一致性，在数据稀缺条件下泛化能力较差。目标 我们开发了AgroEvoDeep-Yield，这是一种知识引导模型，通过其神经网络架构编码机理认识，能够对玉米从开花到成熟的逐日产量形成过程进行显式且可解释的模拟。我们还建立了一个框架，以支持在新数据可用时模型的持续演化。方法 该模型在APSIM模拟的粒数和逐日籽粒生物量序列上进行预训练，以施加生理一致性约束。预训练后，模型通过两个持续学习阶段进行演化。首先，利用796个田间观测数据进行田块级持续学习，以减少继承自APSIM的偏差。随后，利用945个气象站的长期记录和专家约束的品种参数优化，将模型适配到区域尺度多源输入。结果与结论 经过田块级持续学习后，AgroEvoDeep-Yield相对于APSIM将粒数和产量模拟误差分别降低了29%和24%，并在区域外预测中优于传统机器学习模型。区域级持续学习将产量RMSE降至1.09 t\u002Fha，专家约束的品种参数优化进一步将其降至0.80 t\u002Fha。意义 本研究表明，知识引导模型可以在新数据可用时被反复适配，为模型持续演化提供了实用框架，并为未来农业决策支持奠定了基础。","Agricultural Systems","2026-09-14T00:00:00Z",85,{"impact":110,"substance":111,"depth":17,"authority":112,"freshness":113,"relevant":20,"comment":114},22,23,14,8,"知识引导的深度学习框架实现玉米逐日产量形成模拟，误差显著低于APSIM且支持持续学习，方法新颖、数据规模扎实，对智慧农业决策支持有参考价值。",[116],{"name":106,"url":103},[25,26,27,29,118],"作物模型",{"code":31,"slug":32,"name":29,"path":33,"parent_code":34},[121],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":48,"locked":13,"version":49,"method":50,"evidence":123},{"candidates":124,"agricultural_evidence":54},[125,134,139,146,150],{"code":37,"score":126,"supported":54,"title":127,"abstract":129,"tags":133},19,[128],"deep learning",[130,66,131,132],"机器学习","artificial intelligence","decision support",[118,26],{"code":31,"score":135,"supported":54,"title":136,"abstract":137,"tags":138},15,[32],[29,32],[29],{"code":140,"score":98,"supported":54,"title":141,"abstract":142,"tags":145},"A8",[],[143,144],"粮食安全","food security",[],{"code":59,"score":20,"supported":13,"title":147,"abstract":148,"tags":149},[],[],[25],{"code":75,"score":20,"supported":13,"title":151,"abstract":152,"tags":153},[],[],[27],[155,156],"农业人工智能 产量预测 作物模型 智慧农业","农业人工智能 产量预测","农业人工智能产量预测作物模型智慧农业-2505",2,"10.1016\u002Fj.agsy.2026.104981",{"doi":159,"openalex_id":161,"authors":162,"venue":106,"cited_by_count":93,"oa_url":103,"card":189,"direction":193,"ingested_from":95},"W7212532256",[163,165,167,170,173,176,178,181,183,186],{"name":164,"orcid":8},"Junji Ou",{"name":166,"orcid":8},"Wenyao Yan",{"name":168,"orcid":169},"Fangzheng Chen","https:\u002F\u002Forcid.org\u002F0009-0006-5061-6227",{"name":171,"orcid":172},"Tao Ye","https:\u002F\u002Forcid.org\u002F0000-0002-5037-8410",{"name":174,"orcid":175},"Ke Liu","https:\u002F\u002Forcid.org\u002F0000-0002-8343-0449",{"name":177,"orcid":8},"Matthew Tom Harrison",{"name":179,"orcid":180},"William D. Batchelor","https:\u002F\u002Forcid.org\u002F0000-0002-3881-6246",{"name":182,"orcid":8},"Yong Chen",{"name":184,"orcid":185},"Kelin Hu","https:\u002F\u002Forcid.org\u002F0000-0001-9321-0821",{"name":187,"orcid":188},"Puyu Feng","https:\u002F\u002Forcid.org\u002F0000-0003-4845-9876",{"tldr":190,"method":191,"finding":192,"direction":193,"opportunity":194},"提出知识引导的深度学习框架AgroEvoDeep-Yield，实现玉米逐日产量形成的可解释模拟与持续","基于APSIM模拟数据预训练，结合796个田间观测和945个气象站数据持续学习。","田间持续学习使粒数和产量误差比APSIM降低29%和24%，区域优化后RMSE降至0.80 t\u002Fha","农业人工智能与决策模型","可探索将知识引导与持续学习框架迁移至其他作物，并融合实时遥感与物联网数据实现动态产量预测。","2026-09-15T23:30:04.611750Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":201,"content":8,"source_name":202,"source_url":199,"published_at":203,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":204,"score_detail":205,"sources":208,"tags":210,"primary_topic":213,"secondary_topics":214,"classification":222,"search_phrases":277,"slug":280,"view_count":93,"doi":281,"paper":282,"created_at":300},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":17,"substance":110,"depth":17,"authority":19,"freshness":206,"relevant":20,"comment":207},9,"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。",[209],{"name":202,"url":199},[25,26,28,211,212],"精准农业","气候韧性",{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},[215,216],{"code":43,"slug":44,"name":45,"path":46,"parent_code":41},{"code":217,"slug":218,"name":219,"path":220,"parent_code":221},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"status":48,"locked":13,"version":49,"method":50,"evidence":223},{"candidates":224,"agricultural_evidence":54},[225,232,237,243,249,257,264,271],{"code":37,"score":17,"supported":54,"title":226,"abstract":227,"tags":231},[131],[228,130,229,66,128,230],"深度学习","计算机视觉","computer vision",[26],{"code":59,"score":18,"supported":54,"title":233,"abstract":235,"tags":236},[234],"precision agriculture",[211,234],[25,211],{"code":43,"score":12,"supported":54,"title":238,"abstract":239,"tags":242},[],[28,240,71,241],"边缘计算","edge computing",[28],{"code":217,"score":206,"supported":54,"title":244,"abstract":245,"tags":248},[],[246,247,218],"灌溉","水资源",[],{"code":250,"score":251,"supported":54,"title":252,"abstract":253,"tags":256},"H7",7,[],[254,255],"气候变化","climate change",[212],{"code":258,"score":98,"supported":54,"title":259,"abstract":260,"tags":263},"H2",[],[261,262],"土壤","soil",[],{"code":265,"score":266,"supported":54,"title":267,"abstract":268,"tags":270},"A7",3,[],[269],"间作",[],{"code":272,"score":266,"supported":54,"title":273,"abstract":274,"tags":276},"F3",[],[275],"养分管理",[],[278,279],"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":281,"openalex_id":283,"authors":284,"venue":202,"cited_by_count":93,"oa_url":199,"card":295,"direction":94,"ingested_from":95},"W7223121456",[285,288,290,292],{"name":286,"orcid":287},"Olumayowa J. Iyanda","https:\u002F\u002Forcid.org\u002F0000-0002-5340-9884",{"name":289,"orcid":8},"Oluwadare OYEBODE",{"name":291,"orcid":8},"Iretiayo Adelaiye",{"name":293,"orcid":294},"Ayomide Afolabi","https:\u002F\u002Forcid.org\u002F0000-0002-5171-886X",{"tldr":296,"method":297,"finding":298,"direction":193,"opportunity":299},"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。","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":302,"title":303,"url":304,"summary":305,"summary_zh":306,"content":8,"source_name":307,"source_url":304,"published_at":308,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":309,"score_detail":310,"sources":312,"tags":314,"primary_topic":316,"secondary_topics":317,"classification":319,"search_phrases":334,"slug":337,"view_count":93,"doi":338,"paper":339,"created_at":353},4759,"Machine Learning-based Prediction of SVI Parameter in Maize: A Comparative Study and Feature Importance Analysis","https:\u002F\u002Fdoi.org\u002F10.24925\u002Fturjaf.v14i10.2870-2879.9043","Background: Accurate estimation of seedling vigor indices (SVI) is critical for monitoring plant health and predicting yields in precision agriculture. This study comparatively evaluates the performance of different machine learning algorithms in estimating the SVI parameter. Methods: Germination data were collected from 39 maize genotypes under three different salinity conditions (0 mM, 100 mM, and 200 mM NaCl), including the parameters Gmax, MGT, GI, SL, RL, SdL, SMR, RMR, and SVI. The dataset was preprocessed through normalization to the [0–1] range. The SVI parameter was estimated using four different machine learning methods: Random Forest, CatBoost, LightGBM, and Support Vector Regression (SVR). To evaluate the performance of the models, both 10-fold cross-validation and 80%–20% hold-out validation techniques were employed. The model performance was examined using RMSE, MSE, MAE, and R² metrics. Results: The findings show that all models have a high explanatory power in the training dataset. Specifically, the CatBoost model showed the highest success in the training phase (R²=0.9962), whereas the SVR model achieved the highest generalization performance on the test dataset (R²=0.9712, RMSE=0.0582). Feature importance analysis results revealed that the 'App' parameter had the highest impact on the target variable in most models, but different structural interactions were prominent in the LightGBM model. The results demonstrate that machine learning techniques provide high accuracy in SVI estimation and that the tendency towards overfitting is limited. Conclusions: In conclusion, this study confirms that machine learning techniques are powerful and reliable tools for estimating spectral indices in precision agriculture applications. The integration of SVR and ensemble-based models into agricultural decision support systems is expected to significantly contribute to optimizing resource use and improving yield predictions.","背景：准确估计幼苗活力指数（SVI）对于精准农业中监测植物健康和预测产量至关重要。本研究比较评估了不同机器学习算法在估计SVI参数方面的性能。方法：从39个玉米基因型在三种不同盐度条件（0 mM、100 mM和200 mM NaCl）下收集发芽数据，包括Gmax、MGT、GI、SL、RL、SdL、SMR、RMR和SVI等参数。数据集通过归一化至[0–1]范围进行预处理。采用四种不同的机器学习方法估计SVI参数：随机森林、CatBoost、LightGBM和支持向量回归（SVR）。为评估模型性能，采用了10折交叉验证和80%–20%留出验证技术。使用RMSE、MSE、MAE和R²指标检验模型性能。结果：研究结果表明，所有模型在训练数据集中均具有较高的解释力。具体而言，CatBoost模型在训练阶段表现出最高的成功率（R²=0.9962），而SVR模型在测试数据集上取得了最高的泛化性能（R²=0.9712，RMSE=0.0582）。特征重要性分析结果显示，在大多数模型中，“App”参数对目标变量的影响最大，但在LightGBM模型中不同的结构交互作用更为突出。结果表明，机器学习技术在SVI估计中提供了高精度，且过拟合倾向有限。结论：总之，本研究证实机器学习技术是精准农业应用中估计光谱指数的强大而可靠的工具。将SVR和基于集成的模型整合到农业决策支持系统中，预计将显著有助于优化资源利用和改善产量预测。","Turkish Journal of Agriculture - Food Science and Technology","2026-10-11T00:00:00Z",63,{"impact":113,"substance":17,"depth":18,"authority":16,"freshness":206,"relevant":20,"comment":311},"方法对比扎实、结论可靠，但属细分领域论文，产业影响有限，适合主题聚合而非头条精选。",[313],{"name":307,"url":304},[25,26,130,29,315],"耐盐育种",{"code":31,"slug":32,"name":29,"path":33,"parent_code":34},[318],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":48,"locked":13,"version":49,"method":50,"evidence":320},{"candidates":321,"agricultural_evidence":54},[322,326,330],{"code":37,"score":126,"supported":54,"title":323,"abstract":324,"tags":325},[66],[130,66,132],[26,130],{"code":31,"score":135,"supported":54,"title":327,"abstract":328,"tags":329},[32],[29,32],[29],{"code":59,"score":251,"supported":54,"title":331,"abstract":332,"tags":333},[],[211,234],[25],[335,336],"玉米 SVI 机器学习","玉米 耐盐 幼苗活力指数","玉米SVI机器学习-4759","10.24925\u002Fturjaf.v14i10.2870-2879.9043",{"doi":338,"openalex_id":340,"authors":341,"venue":307,"cited_by_count":93,"oa_url":304,"card":348,"direction":193,"ingested_from":95},"W7221462188",[342,345],{"name":343,"orcid":344},"Mustafa Turan Arslan","https:\u002F\u002Forcid.org\u002F0000-0001-5498-6571",{"name":346,"orcid":347},"Gülay Zülkadir","https:\u002F\u002Forcid.org\u002F0000-0003-3488-4011",{"tldr":349,"method":350,"finding":351,"direction":193,"opportunity":352},"用四种机器学习模型基于39个玉米基因型盐胁迫发芽数据预测幼苗活力指数SVI。","39个玉米基因型在三种盐浓度下的发芽数据，归一化后用RF、CatBoost、Li","SVR泛化最优（R²=0.9712），CatBoost训练拟合最高；App参数对SVI影响最大。","可扩展到多作物多胁迫环境，结合光谱或图像表型数据提升SVI预测的田间适用性。","2026-10-12T23:30:44.762497Z",{"id":355,"title":356,"url":357,"summary":358,"summary_zh":359,"content":8,"source_name":360,"source_url":357,"published_at":361,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":362,"score_detail":363,"sources":367,"tags":369,"primary_topic":371,"secondary_topics":376,"classification":379,"search_phrases":412,"slug":415,"view_count":20,"doi":416,"paper":417,"created_at":430},4660,"IoT-Based Automatic Cotton Leaf Disease Detection, Infection Percentage Estimation, and Treatment Recommendation Using Raspberry PI","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23280692","Cotton is one of the most important commercial crops worldwide, and its productivity is significantly affected by various leaf diseases such as bacterial blight, alter aria leaf spot, Cercospora leaf spot, powdery mildew, and leaf curl disease. Early and accurate identification of these diseases is essential to minimize crop losses and improve yield. Traditional disease diagnosis relies on manual field inspection by experts, which is time-consuming, labour-intensive, and often impractical for large agricultural fields. The proposed system integrates a Raspberry Pi5, a high-resolution camera module, environmental sensors, and wireless communication technologies to create an intelligent crop monitoring platform. Images of cotton leaves are captured using the Raspberry Pi camera and processed through computer vision techniques for leaf segmentation and feature extraction. A lightweight deep learning model based on MobileNetV2 is employed to automatically identify different cotton leaf diseases. In addition to disease classification, image segmentation techniques are used to calculate the percentage of infected leaf area, enabling the system to determine the severity level of infection. The system also collects environmental parameters such as temperature, humidity, soil moisture, and light intensity using IoT sensors. These parameters, along with disease diagnosis results, are transmitted to a cloud-based dashboard for real-time monitoring and analysis. Automated alerts can be sent to farmers through SMS or mobile notifications when severe infections are detected. Experimental evaluation is expected to achieve disease classification accuracy above 93%, infection area estimation error below 5%, and real-time inference within one second per image on the Raspberry Pi platform. The proposed solution offers a cost-effective, portable, and scalable approach for precision agriculture by combining artificial intelligence, image processing, and IoT technologies. The system enables early disease detection, accurate infection assessment, timely treatment recommendations, reduced pesticide usage, and improved cotton crop productivity, making it a valuable tool for smart farming applications.","棉花是全球最重要的经济作物之一，其产量受到多种叶部病害的显著影响，如细菌性枯萎病（bacterial blight）、链格孢叶斑病（alternaria leaf spot）、尾孢叶斑病（Cercospora leaf spot）、白粉病（powdery mildew）和卷叶病（leaf curl disease）。早期准确识别这些病害对于减少作物损失和提高产量至关重要。传统的病害诊断依赖专家进行人工田间巡检，这种方式耗时、费力，且对于大面积农田往往不切实际。所提出的系统集成了Raspberry Pi5、高分辨率摄像头模块、环境传感器和无线通信技术，构建了一个智能作物监测平台。利用Raspberry Pi摄像头采集棉花叶片图像，并通过计算机视觉技术进行叶片分割和特征提取。采用基于MobileNetV2的轻量级深度学习模型自动识别不同的棉花叶部病害。除病害分类外，还利用图像分割技术计算受感染叶面积百分比，使系统能够确定感染的严重程度。该系统还通过物联网传感器采集温度、湿度、土壤水分和光照强度等环境参数。这些参数连同病害诊断结果一起传输至基于云端的仪表板，用于实时监测和分析。当检测到严重感染时，可通过短信或移动通知向农民发送自动警报。实验评估预期在Raspberry Pi平台上实现高于93%的病害分类准确率、低于5%的感染面积估计误差，以及每张图像一秒以内的实时推理。所提出的解决方案结合了人工智能、图像处理和物联网技术，为精准农业提供了一种经济高效、便携且可扩展的方法。该系统能够实现病害早期检测、准确感染评估、及时治疗建议、减少农药使用并提高棉花作物产量，使其成为智慧农业应用中的一种有价值的工具。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-10T00:00:00Z",74,{"impact":18,"substance":364,"depth":365,"authority":16,"freshness":206,"relevant":20,"comment":366},20,17,"基于树莓派与轻量深度学习的棉花叶病检测与物联网监测方案，方法具体、指标明确，对智慧植保有参考价值。",[368],{"name":360,"url":357},[25,26,28,211,370],"棉花病害",{"code":372,"slug":373,"name":374,"path":375,"parent_code":34},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops",[377,378],{"code":43,"slug":44,"name":45,"path":46,"parent_code":41},{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":48,"locked":13,"version":49,"method":50,"evidence":380},{"candidates":381,"agricultural_evidence":54},[382,386,392,397,401,408],{"code":43,"score":135,"supported":54,"title":383,"abstract":384,"tags":385},[71],[28,71],[28],{"code":372,"score":112,"supported":54,"title":387,"abstract":389,"tags":391},[388],"cotton",[390,388],"棉花",[],{"code":59,"score":393,"supported":54,"title":394,"abstract":395,"tags":396},11,[],[25,211,234],[25,211],{"code":37,"score":12,"supported":54,"title":398,"abstract":399,"tags":400},[],[228,229,128,131,230],[26],{"code":402,"score":98,"supported":54,"title":403,"abstract":404,"tags":407},"F4",[],[405,406],"农药","pesticide",[],{"code":258,"score":98,"supported":54,"title":409,"abstract":410,"tags":411},[],[261,262],[],[413,414],"Raspberry Pi 棉花病害检测","MobileNetV2 棉花叶病识别","RaspberryPi棉花病害检测-4660","10.5281\u002Fzenodo.23280692",{"doi":416,"openalex_id":418,"authors":419,"venue":360,"cited_by_count":93,"oa_url":357,"card":425,"direction":94,"ingested_from":95},"W7221340722",[420,422],{"name":421,"orcid":8},"Deepak R Khadse",{"name":423,"orcid":424},"Pankaj Hiraman Zope","https:\u002F\u002Forcid.org\u002F0000-0003-3669-1440",{"tldr":426,"method":427,"finding":428,"direction":94,"opportunity":429},"基于树莓派与物联网，实现棉花叶病自动检测、感染率估算与防治推荐。","树莓派5+摄像头+环境传感器，MobileNetV2分类与图像分割，云端看板。","预期分类准确率超93%，感染面积误差低于5%，单图推理1秒内。","可探索边缘端轻量模型与多病害严重度分级、精准施药决策的闭环验证。","2026-10-11T23:30:07.876353Z",{"id":432,"title":433,"url":434,"summary":435,"summary_zh":436,"content":8,"source_name":437,"source_url":434,"published_at":361,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":438,"score_detail":439,"sources":441,"tags":443,"primary_topic":446,"secondary_topics":447,"classification":449,"search_phrases":473,"slug":476,"view_count":93,"doi":477,"paper":478,"created_at":486},4658,"Energy-Efficient Smart Agriculture Management Framework Using IoT and Ensemble Machine Learning for Intelligent Crop Health Monitoring and Resource Optimization","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.62s.32","Context: Smart agriculture plays an important role in addressing the challenges of food security, environmental sustainability, and sustainable farming through IoT.Farmers are facing many issues in traditional farming, such as inefficient monitoring and poor crop health detection.Traditional farming has a negative impact on crop production and sustainability.In this regard, the development of intelligent and energy-efficient agricultural monitoring systems has become crucial for contemporary precision farming applications.Objective: This study aims to monitor crop health and optimize resource use using machine learning techniques.Our proposed system intends to monitor crop conditions in real time, enhance agricultural management, and minimize unnecessary sensor utilization and communication overhead.Material\u002Fmethods: In this paper, we used five machine learning classifiers to monitor crop health using sensor data.The agricultural sensor data (soil moisture, soil temperature, soil pH, humidity, air temperature, solar radiation, wind speed, NDVI index, and 5G latency) were used for crop health monitoring.The models, such as RF, XGBoost, LightGBM, and CatBoost, and soft voting were used for crop health classification into the Healthy, High_Stress, and Moderate_Stress categories.The experimental observation revealed that soft voting achieved the highest accuracy of 94.5%, macro-F1 score of 0.945, weighted F1 score of 0.945, and AUC-ROC score of 0.988 compared to the other models.The cross-validation results further validated the robustness and stability of the proposed framework.The IoTenabled intelligent agriculture management system offers an efficient, scalable solution for real-time crop health monitoring, energy-efficient resource optimization, and sustainable smart farming.","背景：智慧农业在借助物联网（IoT）应对粮食安全、环境可持续性和可持续耕作等挑战方面发挥着重要作用。农民在传统耕作中面临诸多问题，例如监测效率低下和作物健康检测不佳。传统耕作对作物产量和可持续性产生负面影响。在此背景下，开发智能且节能的农业监测系统对于当代精准农业应用已变得至关重要。目标：本研究旨在利用机器学习技术监测作物健康并优化资源利用。我们提出的系统旨在实时监测作物状况、增强农业管理并最大限度减少不必要的传感器使用和通信开销。材料\u002F方法：在本文中，我们使用了五种机器学习分类器，利用传感器数据监测作物健康。农业传感器数据（土壤湿度、土壤温度、土壤pH值、湿度、空气温度、太阳辐射、风速、NDVI指数和5G延迟）被用于作物健康监测。RF、XGBoost、LightGBM和CatBoost等模型以及软投票被用于将作物健康分类为健康、高胁迫和中等胁迫类别。实验观察表明，与其他模型相比，软投票达到了最高的准确率94.5%、宏F1分数0.945、加权F1分数0.945和AUC-ROC分数0.988。交叉验证结果进一步验证了所提出框架的鲁棒性和稳定性。该物联网赋能的智能农业管理系统为实时作物健康监测、节能资源优化和可持续智慧农业提供了一种高效、可扩展的解决方案。","International Journal of Drug Delivery Technology",52,{"impact":113,"substance":18,"depth":112,"authority":98,"freshness":113,"relevant":20,"comment":440},"方法组合与多源传感器数据有一定新意，但期刊权威性弱、属实验室验证，公共价值有限，不宜进入每日精选。",[442],{"name":437,"url":434},[25,26,28,444,445],"作物健康监测","资源优化",{"code":43,"slug":44,"name":45,"path":46,"parent_code":41},[448],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":48,"locked":13,"version":49,"method":50,"evidence":450},{"candidates":451,"agricultural_evidence":54},[452,456,461,465,469],{"code":59,"score":17,"supported":54,"title":453,"abstract":454,"tags":455},[61],[25,211,61],[25],{"code":43,"score":17,"supported":54,"title":457,"abstract":458,"tags":460},[71],[28,459,71],"农业传感",[28],{"code":37,"score":135,"supported":54,"title":462,"abstract":463,"tags":464},[66],[130,66],[26],{"code":140,"score":98,"supported":54,"title":466,"abstract":467,"tags":468},[],[143,144],[],{"code":258,"score":98,"supported":54,"title":470,"abstract":471,"tags":472},[],[261,262],[],[474,475],"IoT 作物健康监测","集成学习 精准农业","IoT作物健康监测-4658","10.25258\u002Fijddt.16.62s.32",{"doi":477,"openalex_id":479,"authors":480,"venue":437,"cited_by_count":93,"oa_url":434,"card":481,"direction":94,"ingested_from":95},"W7221334384",[],{"tldr":482,"method":483,"finding":484,"direction":94,"opportunity":485},"用IoT传感器数据与集成机器学习实现作物健康分类与资源优化。","五种分类器（RF、XGBoost、LightGBM、CatBoost、软投票）结","软投票集成模型准确率达94.5%，AUC-ROC为0.988，优于单一模型。","可探索边缘端轻量化集成模型与能耗-精度联合优化，降低传感器通信开销。","2026-10-11T23:30:07.636015Z",{"id":488,"title":489,"url":490,"summary":491,"summary_zh":492,"content":8,"source_name":493,"source_url":490,"published_at":494,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":495,"score_detail":496,"sources":498,"tags":500,"primary_topic":502,"secondary_topics":503,"classification":505,"search_phrases":529,"slug":532,"view_count":20,"doi":533,"paper":534,"created_at":549},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",55,{"impact":113,"substance":17,"depth":135,"authority":98,"freshness":113,"relevant":20,"comment":497},"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。",[499],{"name":493,"url":490},[25,26,240,28,501],"精准灌溉",{"code":43,"slug":44,"name":45,"path":46,"parent_code":41},[504],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":48,"locked":13,"version":49,"method":50,"evidence":506},{"candidates":507,"agricultural_evidence":54},[508,513,517,521,525],{"code":43,"score":393,"supported":54,"title":509,"abstract":510,"tags":512},[],[28,511,71],"internet of things",[28,240],{"code":37,"score":12,"supported":54,"title":514,"abstract":515,"tags":516},[],[228,229,128,230,132],[26],{"code":217,"score":251,"supported":54,"title":518,"abstract":519,"tags":520},[],[246,218],[501],{"code":59,"score":251,"supported":54,"title":522,"abstract":523,"tags":524},[],[211,234],[25],{"code":258,"score":98,"supported":54,"title":526,"abstract":527,"tags":528},[],[261,262],[],[530,531],"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":533,"openalex_id":535,"authors":536,"venue":493,"cited_by_count":93,"oa_url":490,"card":544,"direction":94,"ingested_from":95},"W7220855887",[537,540,542],{"name":538,"orcid":539},"Prakash Kanade","https:\u002F\u002Forcid.org\u002F0000-0001-6296-9368",{"name":541,"orcid":8},"Shetty Chirag",{"name":543,"orcid":8},"Sunay Kanade",{"tldr":545,"method":546,"finding":547,"direction":94,"opportunity":548},"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"]