[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4040":3,"related-4040":124},{"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":39,"search_phrases":91,"slug":94,"view_count":71,"doi":95,"paper":96,"created_at":123},4040,"SPATIAL AND CLIMATE DATA ANALYSIS FOR MACHINE LEARNING-BASED CROP YIELD PREDICTION IN NORTHERN KAZAKHSTAN","https:\u002F\u002Fdoi.org\u002F10.32014\u002F2026.2518-1726.462","Crop yield prediction is important for food security, agricultural planning, and effective resource management, particularly in Northern Kazakhstan, where agricultural production is strongly influenced by climate variability. Changes in temperature and precipitation can affect crop productivity and cause considerable differences in yield between years. The aim of this study is to develop, compare, and evaluate machine learning regression models for wheat yield prediction in the North Kazakhstan Region using climatic data. A dataset covering 1990–2025 was prepared using official crop yield statistics from the Bureau of National Statistics of the Republic of Kazakhstan and climatic data from the NASA POWER database. Daily climatic data were collected from five representative geographical points across the North Kazakhstan Region. The climatic variables included average, minimum, and maximum air temperature and precipitation. Daily temperature values were aggregated into annual mean values, while precipitation was summed to obtain annual totals. The annual values from the five geographical points were then averaged to obtain representative regional indicators. Several regression algorithms were compared, including Linear Regression, Random Forest, Gradient Boosting, Bagging Regressor, Decision Tree, and XGBoost. A hybrid model combining XGBoost and Gradient Boosting was also evaluated. Wheat yield was used as the target variable, while climatic variables were used as predictors. To preserve the temporal structure of the data and avoid information leakage, walk-forward validation was applied for 2020–2025. Model performance was evaluated using R², RMSE, and MAE. XGBoost demonstrated the best predictive performance, achieving R² = 0.811, RMSE = 1.436 c\u002Fha, and MAE = 1.160 c\u002Fha. The results demonstrate the potential of machine learning and climatic data for wheat yield prediction and agricultural decision support in Northern Kazakhstan.","作物产量预测对粮食安全、农业规划和有效资源管理具有重要意义，尤其是在哈萨克斯坦北部，该地区农业生产受气候变异性影响显著。气温和降水的变化会影响作物生产力，并导致年际间产量差异较大。本研究旨在利用气候数据，开发、比较和评估用于哈萨克斯坦北部地区小麦产量预测的机器学习回归模型。研究使用哈萨克斯坦共和国国家统计局提供的官方作物产量统计数据和NASA POWER数据库的气候数据，构建了覆盖1990—2025年的数据集。每日气候数据采集自哈萨克斯坦北部地区五个具有代表性的地理点位。气候变量包括平均气温、最低气温、最高气温和降水量。每日气温值被聚合为年均值，降水量则累加得到年总量。随后，对五个地理点位的年度值取平均，以获得具有代表性的区域指标。研究比较了多种回归算法，包括线性回归、随机森林、梯度提升、Bagging回归器、决策树和XGBoost，并评估了XGBoost与梯度提升相结合的混合模型。小麦产量作为目标变量，气候变量作为预测因子。为保持数据的时间结构并避免信息泄漏，研究对2020—2025年采用了前向滚动验证。模型性能采用R²、RMSE和MAE进行评估。XGBoost表现出最佳的预测性能，达到R² = 0.811、RMSE = 1.436 c\u002Fha、MAE = 1.160 c\u002Fha。结果表明，机器学习和气候数据在哈萨克斯坦北部小麦产量预测和农业决策支持方面具有潜力。",null,"NEWS OF THE NATIONAL ACADEMY OF SCIENCES OF THE REPUBLIC OF KAZAKHSTAN","2026-10-01T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"基于1990—2025年气候数据与多种机器学习模型的小麦产量预测研究，方法规范、结论可靠，但区域局限于哈萨克斯坦北部，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","产量预测","小麦","农业气象",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,54,61,69,76,81,86],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":53},18,true,[49],"machine learning",[51,49,52],"机器学习","decision support",[28],{"code":55,"score":56,"supported":47,"title":57,"abstract":58,"tags":60},"A2",7,[],[30,59],"wheat",[30],{"code":62,"score":63,"supported":47,"title":64,"abstract":65,"tags":68},"A8",6,[],[66,67],"粮食安全","food security",[],{"code":70,"score":71,"supported":47,"title":72,"abstract":73,"tags":75},"J1",3,[],[74],"农业规划",[],{"code":77,"score":22,"supported":14,"title":78,"abstract":79,"tags":80},"H7",[],[],[31],{"code":82,"score":22,"supported":14,"title":83,"abstract":84,"tags":85},"I1",[],[],[27],{"code":87,"score":22,"supported":14,"title":88,"abstract":89,"tags":90},"I3",[],[],[29],[92,93],"哈萨克斯坦 小麦 产量预测","NASA POWER 气候数据 机器学习","哈萨克斯坦小麦产量预测-4040","10.32014\u002F2026.2518-1726.462",{"doi":95,"openalex_id":97,"authors":98,"venue":10,"cited_by_count":114,"oa_url":115,"card":116,"direction":120,"ingested_from":122},"W7215105964",[99,102,105,108,111],{"name":100,"orcid":101},"Aigul Mimenbayeva","https:\u002F\u002Forcid.org\u002F0000-0003-4652-470X",{"name":103,"orcid":104},"A A Naizagarayeva","https:\u002F\u002Forcid.org\u002F0000-0001-6888-1092",{"name":106,"orcid":107},"Tleugaisha Ospanova","https:\u002F\u002Forcid.org\u002F0000-0002-1729-1321",{"name":109,"orcid":110},"D. K. Koikelova","https:\u002F\u002Forcid.org\u002F0009-0003-6644-9345",{"name":112,"orcid":113},"Raikhan Kudabayeva","https:\u002F\u002Forcid.org\u002F0009-0002-0827-9395",0,"https:\u002F\u002Fjournals.nauka-nanrk.kz\u002Fphysics-mathematics\u002Farticle\u002Fdownload\u002F8926\u002F5764",{"tldr":117,"method":118,"finding":119,"direction":120,"opportunity":121},"用1990–2025年气候数据与机器学习模型预测哈萨克斯坦北部小麦产量。","NASA POWER气候数据+官方产量统计，比较XGBoost等回归模型并采用前","XGBoost预测效果最佳，R²=0.811，RMSE=1.436 c\u002Fha，MAE=1.160 c","农业人工智能与决策模型","可引入遥感植被指数与土壤数据，构建多源融合模型并迁移至其他气候敏感区。","openalex","2026-10-02T23:30:45.440623Z",{"total":63,"page":22,"page_size":63,"items":125},[126,182,235,303,376,442],{"id":127,"title":128,"url":129,"summary":130,"summary_zh":131,"content":9,"source_name":132,"source_url":129,"published_at":133,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":134,"score_detail":135,"sources":137,"tags":139,"primary_topic":142,"secondary_topics":143,"classification":144,"search_phrases":162,"slug":165,"view_count":114,"doi":166,"paper":167,"created_at":181},5587,"Calibration-Shift Inference for Computer Vision Agriculture Yield Models Under Retrofit Sensor Replacement: An Artificial Intelligence Post-Deployment Recalibration Guarantee","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544195","Computer vision yield models deployed in agricultural fields are routinely paired with retrofit sensor packages that replace or supplement the original imaging hardware, and the resulting calibration shift can silently invalidate the model's predictive guarantees. The analysis characterises the operating characteristics of the design under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, using 2000 replications per design cell across cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The design attains 80% power at a 5 percentage point effect with 54 clusters. The paper states a formal guarantee: under stated assumptions on the stability of the calibration map, the before-after-control-impact estimator yields a consistent and asymptotically normal estimate of the calibration shift, and the associated confidence interval covers the true shift at the nominal rate. The contribution is a design-theoretic account of how retrofit-induced calibration shift can be detected and bounded without observational data, together with the sample-size requirements that follow.","部署在农田中的计算机视觉产量模型通常与改装传感器组件配合使用，这些组件用于替换或补充原始成像硬件，由此产生的校准偏移可能悄然使模型的预测保证失效。该分析在声明的方差结构下刻画了设计的工作特性，其中组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64，每个设计单元采用2000次重复，聚类数分别为8、16、24和32，效应量为3、5和8个百分点。该设计在54个聚类、5个百分点效应下达到80%的检验力。论文给出了一项形式化保证：在关于校准映射稳定性的既定假设下，前后对照影响（before-after-control-impact）估计量给出校准偏移的一致且渐近正态的估计，且相关置信区间以名义覆盖率覆盖真实偏移。其贡献在于从设计理论角度说明了如何在没有观测数据的情况下检测并界定改装引起的校准偏移，以及随之而来的样本量要求。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",65,{"impact":21,"substance":46,"depth":19,"authority":17,"freshness":13,"relevant":22,"comment":136},"方法学扎实、统计设计严谨的预印本论文，但偏理论设计层面，缺乏田间实证数据，产业影响有限，适合作为技术参考而非每日精选头条。",[138],{"name":132,"url":129},[27,28,140,29,141],"计算机视觉","传感器校准",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":145},{"candidates":146,"agricultural_evidence":47},[147,154,158],{"code":33,"score":148,"supported":47,"title":149,"abstract":152,"tags":153},24,[150,151],"artificial intelligence","computer vision",[140,151],[28,140],{"code":82,"score":22,"supported":14,"title":155,"abstract":156,"tags":157},[],[],[27],{"code":87,"score":22,"supported":14,"title":159,"abstract":160,"tags":161},[],[],[29],[163,164],"计算机视觉 产量预测 传感器校准","农业人工智能 传感器校准 计算机视觉 产量预测","计算机视觉产量预测传感器校准-5587","10.5281\u002Fzenodo.23544195",{"doi":166,"openalex_id":168,"authors":169,"venue":132,"cited_by_count":114,"oa_url":129,"card":176,"direction":120,"ingested_from":122},"W7223104380",[170,172,174],{"name":171,"orcid":9},"Tigist Alemu Gebremariam",{"name":173,"orcid":9},"Hawi Tesfaye Desta",{"name":175,"orcid":9},"Mulugeta Bekele Wolde",{"tldr":177,"method":178,"finding":179,"direction":120,"opportunity":180},"提出改造传感器替换后视觉产量模型校准漂移的检测与置信区间保证方法。","用前后对照影响估计量，基于方差结构做2000次重复的模拟设计分析。","5个百分点效应下54个集群可达80%检验力，估计量一致且渐近正态。","可将该设计理论扩展到多传感器异构替换与在线校准监测，填补真实田间验证空白。","2026-10-22T11:21:01.554995Z",{"id":183,"title":184,"url":185,"summary":186,"summary_zh":187,"content":9,"source_name":132,"source_url":185,"published_at":133,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":188,"score_detail":189,"sources":191,"tags":193,"primary_topic":196,"secondary_topics":197,"classification":202,"search_phrases":218,"slug":221,"view_count":114,"doi":222,"paper":223,"created_at":234},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。",67,{"impact":21,"substance":18,"depth":19,"authority":17,"freshness":13,"relevant":22,"comment":190},"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[192],{"name":132,"url":185},[27,28,29,194,195],"遥感","可解释性",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[198],{"code":87,"slug":199,"name":200,"path":201,"parent_code":37},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":203},{"candidates":204,"agricultural_evidence":47},[205,209,214],{"code":33,"score":17,"supported":47,"title":206,"abstract":207,"tags":208},[151],[140],[28],{"code":87,"score":21,"supported":47,"title":210,"abstract":211,"tags":213},[],[194,212],"remote sensing",[29,194],{"code":82,"score":22,"supported":14,"title":215,"abstract":216,"tags":217},[],[],[27],[219,220],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":222,"openalex_id":224,"authors":225,"venue":132,"cited_by_count":114,"oa_url":185,"card":228,"direction":232,"ingested_from":122},"W7223114002",[226],{"name":227,"orcid":9},"Kadiatou Barry",{"tldr":229,"method":230,"finding":231,"direction":232,"opportunity":233},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","农业遥感与作物表型","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":236,"title":237,"url":238,"summary":239,"summary_zh":240,"content":9,"source_name":241,"source_url":238,"published_at":242,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":243,"score_detail":244,"sources":249,"tags":251,"primary_topic":253,"secondary_topics":254,"classification":255,"search_phrases":280,"slug":283,"view_count":114,"doi":284,"paper":285,"created_at":302},4994,"Deep learning-based estimation of Kent mango yield by commercial export category under real field conditions in northern Peru","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1943711","Manual visual counting remains the standard procedure for estimating Kent mango ( Mangifera indica L.) yield in northern Peru, an inconsistent practice that compromises harvest planning, transport dimensioning and commercial negotiation. Existing computer vision approaches to mango detection resolve fruit-versus-background discrimination but rarely classify fruit into the commercial categories that determine its market value. This study developed and validated a deep learning method that simultaneously detects and classifies Kent mango fruit into three export categories (air freight, sea freight and reject) from RGB images acquired under real field conditions in the Motupe district, Lambayeque. A purpose-built dataset of 400 photographs was compiled from 200 trees across ten commercial farms using two opposite views per tree; 6,544 patches of 1,280 × 1,280 pixels with 20% overlap were generated, containing 66,465 manually annotated instances. Five architectures were trained under identical experimental conditions: YOLOv8m, YOLO11m, YOLO26m, RT-DETR-l and Mango-YOLO, the latter a proposed architecture built on YOLO26m through the incorporation of a CBAM attention module, a BiFPN neck and the MPDIoU regression loss. Mango-YOLO achieved the best performance across all five metrics, with a precision of 0.930, a recall of 0.940, an F1-score of 0.930, a mAP@0.5 of 0.940 and a mAP@0.5:0.95 of 0.730, at an inference time of 114.94 ms per image. Per-category analysis revealed heterogeneous behaviour, with F1-scores of 0.960, 0.845 and 0.792 for sea freight, air freight and reject respectively. The selected model was integrated into a three-tier web application that scales fruit counts from sampled trees to the whole farm and converts them into kilograms through Monte Carlo simulation with category mean weights, returning a 90% interval. Validation against harvested production recorded on the processing-plant scale across the ten farms yielded a mean absolute percentage error of 2.63% and a coefficient of determination of 0.9993, outperforming the field supervisor’s manual estimate by a factor of 3.3.","在秘鲁北部，人工目视计数仍是估算肯特芒果（Mangifera indica L.）产量的标准方法，但这种做法缺乏一致性，影响了采收计划、运输规模测算和商业谈判。现有的芒果检测计算机视觉方法解决了果实与背景的区分问题，但很少将果实归入决定其市场价值的商业类别。本研究开发并验证了一种深度学习方法，能够从兰巴耶克省莫图佩地区真实田间条件下采集的RGB图像中，同时检测肯特芒果并将其分为三个出口类别（空运、海运和拒收）。研究构建了一个专用数据集，来自十个商业果园的200棵果树，每棵树采集两个相对视角，共400张照片；生成了6,544个1,280 × 1,280像素、重叠率20%的图像块，包含66,465个人工标注实例。在相同实验条件下训练了五种架构：YOLOv8m、YOLO11m、YOLO26m、RT-DETR-l和Mango-YOLO，后者是在YOLO26m基础上引入CBAM注意力模块、BiFPN颈部和MPDIoU回归损失而提出的架构。Mango-YOLO在全部五项指标上表现最佳，精确率为0.930，召回率为0.940，F1分数为0.930，mAP@0.5为0.940，mAP@0.5:0.95为0.730，每张图像推理时间为114.94 ms。分类别分析显示出异质性表现，海运、空运和拒收类别的F1分数分别为0.960、0.845和0.792。所选模型被集成到一个三层Web应用程序中，可将采样果树的果实计数扩展至整个果园，并通过使用类别平均权重的蒙特卡洛模拟将其转换为千克，返回90%区间。在十个果园中，以加工厂地磅记录的采收产量进行验证，平均绝对百分比误差为2.63%，决定系数为0.9993，比田间主管的人工估算优3.3倍。","Frontiers in Plant Science","2026-10-13T00:00:00Z",82,{"impact":46,"substance":245,"depth":46,"authority":246,"freshness":247,"relevant":22,"comment":248},23,14,9,"深度学习实现芒果出口分级与产量估算，MAPE仅2.63%，方法新颖、数据扎实，对果园智能测产有参考价值。",[250],{"name":241,"url":238},[27,28,140,29,252],"芒果",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":256},{"candidates":257,"agricultural_evidence":47},[258,266,272,276],{"code":33,"score":259,"supported":47,"title":260,"abstract":262,"tags":265},19,[261],"deep learning",[263,140,261,151,264],"深度学习","YOLO",[28,140],{"code":267,"score":56,"supported":47,"title":268,"abstract":269,"tags":271},"B2",[],[270,252],"果树",[252],{"code":82,"score":22,"supported":14,"title":273,"abstract":274,"tags":275},[],[],[27],{"code":87,"score":22,"supported":14,"title":277,"abstract":278,"tags":279},[],[],[29],[281,282],"秘鲁 Kent 芒果 产量预测","Mango-YOLO 芒果 分级","秘鲁Kent芒果产量预测-4994","10.3389\u002Ffpls.2026.1943711",{"doi":284,"openalex_id":286,"authors":287,"venue":241,"cited_by_count":114,"oa_url":295,"card":296,"direction":301,"ingested_from":122},"W7221685456",[288,290,293],{"name":289,"orcid":9},"Víctor Yoel Huamán Asencio",{"name":291,"orcid":292},"Heber I. Mejía-Cabrera","https:\u002F\u002Forcid.org\u002F0000-0002-0007-0928",{"name":294,"orcid":9},"Juan Carlos Arcila Diaz","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1943711\u002Fpdf",{"tldr":297,"method":298,"finding":299,"direction":120,"opportunity":300},"开发深度学习模型在真实田间条件下检测并分类肯特芒果为三个出口等级，实现产量估计。","构建400张田间RGB图像数据集，提出Mango-YOLO（YOLO26m+CB","Mango-YOLO最优，mAP@0.5达0.940，产量估计MAPE为2.63%，比人工估计准确3","可探索多品种、多生长阶段及不同光照条件下的泛化能力，并融合时序遥感数据提升区域产量预测精度。","智慧农业 \u002F 农业物联网","2026-10-15T23:30:11.559035Z",{"id":304,"title":305,"url":306,"summary":307,"summary_zh":308,"content":9,"source_name":309,"source_url":306,"published_at":242,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":310,"score_detail":311,"sources":313,"tags":315,"primary_topic":318,"secondary_topics":324,"classification":326,"search_phrases":345,"slug":348,"view_count":22,"doi":349,"paper":350,"created_at":375},4993,"Effects of within-season temporal aggregation of weather variables on performance and interpretability in rice yield machine learning models","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-75646-2","While crop responses are inherently stage-dependent, machine learning yield models often rely on weather variables aggregated over the entire growing season. This study evaluates how within-season temporal aggregation of weather variables affects both predictive performance and interpretability in machine learning-based rice yield modeling. Using CYGMA (Crop Yield Growth Model with Assumptions on Climate and Socioeconomics)-simulated potential yield as a synthetic response variable, we minimized confounding effects from observational noise and management variability, enabling a clearer evaluation of the role of within-season weather aggregation. Daily weather variables were averaged over the rice growing period after dividing each season into multiple equal-length segments, and several machine learning algorithms were trained and evaluated using temporally independent validation. Increasing within-season temporal resolution improved model performance up to a moderate level, after which gains diminished. Interpretation using SHAP (SHapley Additive exPlanations) and response diagnostics consistently indicated that yield sensitivity concentrates in specific windows of the season, with temperature-related effects emerging most strongly early in the season and humidity-related effects later. Finer temporal aggregation sharpened the identification of window-specific nonlinear and threshold-like responses that were obscured under coarse seasonal averages. Overall, moderate within-season aggregation provides a practical balance between predictive skill and mechanistic interpretability, supporting more reliable identification of phenology-relevant meteorological risks for climate-impact assessment and decision support.","尽管作物响应本质上具有阶段依赖性，但机器学习产量模型往往依赖于整个生长季聚合的天气变量。本研究评估了天气变量的季节内时间聚合如何影响基于机器学习的水稻产量建模的预测性能与可解释性。以CYGMA（Crop Yield Growth Model with Assumptions on Climate and Socioeconomics，气候与社会经济假设下的作物产量生长模型）模拟的潜在产量作为合成响应变量，我们最大限度地减少了观测噪声和管理变异性带来的混杂效应，从而能够更清晰地评估季节内天气聚合的作用。将每个生长季划分为多个等长时段后，对水稻生长期内的逐日天气变量进行平均，并采用时间独立验证对多种机器学习算法进行训练和评估。提高季节内时间分辨率可提升模型性能，直至达到中等水平，此后增益递减。利用SHAP（SHapley Additive exPlanations，沙普利加性解释）和响应诊断进行的解释一致表明，产量敏感性集中在季节的特定窗口，温度相关效应在季节早期最为显著，湿度相关效应则在后期出现。更精细的时间聚合增强了对窗口特异性非线性和阈值型响应的识别，而这些响应在粗粒度季节平均下被掩盖。总体而言，中等程度的季节内聚合在预测能力与机制可解释性之间提供了实用平衡，有助于更可靠地识别与物候相关的气象风险，以支持气候影响评估和决策支持。","Scientific Reports",72,{"impact":17,"substance":18,"depth":46,"authority":246,"freshness":21,"relevant":22,"comment":312},"该研究通过CYGMA模拟数据系统评估了生长季内气象变量时间聚合对水稻产量机器学习模型性能与可解释性的影响，方法新颖、结论可靠，对农业气象风险识别与决策支持有参考价值，但属学术论文，公共影响范围有限。",[314],{"name":309,"url":306},[27,28,316,31,317],"可解释AI","水稻产量预测",{"code":319,"slug":320,"name":321,"path":322,"parent_code":323},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[325],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":327},{"candidates":328,"agricultural_evidence":47},[329,333,337,341],{"code":33,"score":259,"supported":47,"title":330,"abstract":331,"tags":332},[49],[51,49,52],[28,316],{"code":319,"score":246,"supported":47,"title":334,"abstract":335,"tags":336},[320],[321,320],[],{"code":77,"score":22,"supported":14,"title":338,"abstract":339,"tags":340},[],[],[31],{"code":82,"score":22,"supported":14,"title":342,"abstract":343,"tags":344},[],[],[27],[346,347],"水稻产量 机器学习 气象","SHAP 水稻 产量预测","水稻产量机器学习气象-4993","10.1038\u002Fs41598-026-75646-2",{"doi":349,"openalex_id":351,"authors":352,"venue":309,"cited_by_count":114,"oa_url":369,"card":370,"direction":301,"ingested_from":122},"W7221657053",[353,355,357,359,361,363,366],{"name":354,"orcid":9},"Noh-Hyun Lee",{"name":356,"orcid":9},"Wonjae Jeong",{"name":358,"orcid":9},"Hyeon-Ji Yang",{"name":360,"orcid":9},"Hana Cho",{"name":362,"orcid":9},"Hyeon-Yeong Ju",{"name":364,"orcid":365},"Toshichika Iizumi","https:\u002F\u002Forcid.org\u002F0000-0002-0611-4637",{"name":367,"orcid":368},"Ki‐Tae Kim","https:\u002F\u002Forcid.org\u002F0000-0002-8249-5283","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75646-2_reference.pdf",{"tldr":371,"method":372,"finding":373,"direction":120,"opportunity":374},"评估生长季内天气变量时间聚合粒度对水稻产量机器学习模型预测与可解释性的影响。","用CYGMA模拟潜在产量作响应变量，按等长时段聚合逐日天气，训练多种机器学习模型","适度提高季内时间分辨率可提升性能，产量敏感性集中在特定窗口，温度效应偏早、湿度效应偏晚。","可探索不同作物与气候区下最优聚合粒度，并将窗口特异性气象风险嵌入气候影响评估与决策支持系统。","2026-10-15T23:30:10.483881Z",{"id":377,"title":378,"url":379,"summary":380,"summary_zh":381,"content":9,"source_name":382,"source_url":379,"published_at":383,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":384,"score_detail":385,"sources":387,"tags":389,"primary_topic":392,"secondary_topics":393,"classification":394,"search_phrases":418,"slug":421,"view_count":422,"doi":423,"paper":424,"created_at":441},4990,"Smart Crop Advisory System","https:\u002F\u002Fdoi.org\u002F10.55041\u002Fijcope.v2i10.081","The Smart Crop Advisory System is a web-based agricultural decision-support platform that uses Artificial Intelligence (AI) and Machine Learning (ML) technologies to assist farmers in making informed farming decisions. Traditional agriculture faces several challenges, including unsuitable crop selection, unpredictable weather conditions, crop diseases, and fluctuations in market prices. The proposed system integrates essential agricultural services, including crop recommendation, weather forecasting, crop disease detection, agricultural market price information, and an AI-based multilingual voice assistant. It also provides farmer profile management, crop price trend analysis, and rainfall trend visualization through an interactive dashboard. The crop recommendation module helps farmers identify suitable crops based on relevant agricultural parameters, while the disease detection module supports the identification of potential crop diseases. Weather and market information help farmers plan agricultural activities and make informed selling decisions. The multilingual voice assistant aims to improve accessibility by enabling farmers to interact with the system through voice-based communication. Overall, the Smart Crop Advisory System aims to improve access to agricultural information, support effective decision-making, promote efficient resource utilization, and encourage sustainable farming practices. Keywords: Smart Agriculture, Crop Recommendation, Machine Learning, Crop Disease Detection, Weather Forecasting, Market Price Analysis, Voice Assistant, Sustainable Agriculture.","智能作物咨询系统是一个基于网络的农业决策支持平台，利用人工智能（AI）和机器学习（ML）技术帮助农民做出明智的农作决策。传统农业面临诸多挑战，包括作物选择不当、天气条件不可预测、作物病害以及市场价格波动。所提出的系统整合了基本农业服务，包括作物推荐、天气预报、作物病害检测、农产品市场价格信息以及基于AI的多语言语音助手。它还通过交互式仪表板提供农民档案管理、作物价格趋势分析和降雨趋势可视化。作物推荐模块帮助农民根据相关农业参数识别适宜作物，而病害检测模块支持识别潜在作物病害。天气和市场信息帮助农民规划农业活动并做出明智的销售决策。多语言语音助手旨在通过使农民能够以语音方式与系统交互来提高可及性。总体而言，智能作物咨询系统旨在改善农业信息的获取，支持有效决策，促进资源高效利用，并鼓励可持续农业实践。关键词：智慧农业、作物推荐、机器学习、作物病害检测、天气预报、市场价格分析、语音助手、可持续农业。","International Journal of Creative and Open Research in Engineering and Management","2026-10-14T00:00:00Z",48,{"impact":21,"substance":246,"depth":17,"authority":63,"freshness":21,"relevant":22,"comment":386},"面向农户的AI农业决策支持系统论文，功能集成度较高但方法新颖性与数据规模有限，属细分领域进展，可作为智慧农业主题聚合素材。",[388],{"name":382,"url":379},[27,28,390,31,391],"病虫害识别","作物推荐",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":395},{"candidates":396,"agricultural_evidence":47},[397,402,407,414],{"code":33,"score":398,"supported":47,"title":399,"abstract":400,"tags":401},11,[],[51,49,150],[28,390],{"code":82,"score":56,"supported":47,"title":403,"abstract":404,"tags":406},[],[27,405],"smart agriculture",[27],{"code":408,"score":63,"supported":47,"title":409,"abstract":410,"tags":413},"H8",[],[411,412],"可持续农业","sustainable agriculture",[],{"code":77,"score":22,"supported":14,"title":415,"abstract":416,"tags":417},[],[],[31],[419,420],"AI 作物推荐 语音助手","农业人工智能 病虫害识别 作物推荐 农业气象","AI作物推荐语音助手-4990",2,"10.55041\u002Fijcope.v2i10.081",{"doi":423,"openalex_id":425,"authors":426,"venue":382,"cited_by_count":114,"oa_url":435,"card":436,"direction":301,"ingested_from":122},"W7221803029",[427,429,431,433],{"name":428,"orcid":9},"Bhuvana H P",{"name":430,"orcid":9},"Kavya C M",{"name":432,"orcid":9},"Manjula S",{"name":434,"orcid":9},"Priyanka A","https:\u002F\u002Fijcope.org\u002Fwp-content\u002Fuploads\u002F2026\u002F10\u002FSmart-Crop-Advisory-System.pdf",{"tldr":437,"method":438,"finding":439,"direction":120,"opportunity":440},"构建基于AI\u002FML的Web农业决策支持平台，为农民提供作物推荐、病害检测、天气与市场价格等服务。","集成机器学习模型、多语言语音助手与交互式仪表盘，整合天气、市场及农业参数数据。","系统可提升农业信息获取与决策效率，促进资源高效利用和可持续耕作。","可探索多源数据融合的轻量化模型与本地化语音交互，提升小农户采纳率与实时决策精度。","2026-10-15T23:30:09.048921Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":9,"source_name":241,"source_url":445,"published_at":383,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":448,"score_detail":449,"sources":452,"tags":454,"primary_topic":456,"secondary_topics":457,"classification":463,"search_phrases":514,"slug":517,"view_count":22,"doi":518,"paper":519,"created_at":540},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p",81,{"impact":46,"substance":450,"depth":46,"authority":246,"freshness":247,"relevant":22,"comment":451},22,"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[453],{"name":241,"url":445},[27,28,29,455,194],"多模态融合",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[458,462],{"code":267,"slug":459,"name":270,"path":460,"parent_code":461},"fruit","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":87,"slug":199,"name":200,"path":201,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":464},{"candidates":465,"agricultural_evidence":47},[466,470,477,483,489,496,503,509],{"code":33,"score":398,"supported":47,"title":467,"abstract":468,"tags":469},[],[263,51,49,261],[28,455],{"code":267,"score":247,"supported":47,"title":471,"abstract":472,"tags":476},[],[473,252,474,475],"苹果","orchard","apple",[],{"code":87,"score":21,"supported":47,"title":478,"abstract":479,"tags":482},[],[480,481],"无人机多光谱","multispectral",[29,194],{"code":82,"score":56,"supported":47,"title":484,"abstract":485,"tags":488},[],[486,487],"精准农业","precision agriculture",[27],{"code":490,"score":63,"supported":47,"title":491,"abstract":492,"tags":495},"H2",[],[493,494],"土壤","soil",[],{"code":497,"score":63,"supported":47,"title":498,"abstract":499,"tags":502},"I5",[],[500,501],"物联网","IoT",[],{"code":504,"score":71,"supported":47,"title":505,"abstract":506,"tags":508},"H6",[],[507],"农业生态",[],{"code":77,"score":71,"supported":47,"title":510,"abstract":511,"tags":513},[],[512],"气候适应",[],[515,516],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":518,"openalex_id":520,"authors":521,"venue":241,"cited_by_count":114,"oa_url":445,"card":535,"direction":301,"ingested_from":122},"W7221795850",[522,525,527,529,531,533],{"name":523,"orcid":524},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":526,"orcid":9},"Umarfarooque Momin",{"name":528,"orcid":9},"Sudeep Kumar E",{"name":530,"orcid":9},"Itfaq Ahmad Mir",{"name":532,"orcid":9},"Ab Rouf Khan",{"name":534,"orcid":9},"Ghulam Mohammad Mir",{"tldr":536,"method":537,"finding":538,"direction":120,"opportunity":539},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","2026-10-15T23:30:08.750140Z"]