[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3325":3,"related-3325":46},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"search_phrases":31,"slug":34,"view_count":35,"doi":8,"paper":36,"created_at":45},3325,"MBF-HybridNet：在极端气候下仍可提前一月预测冬小麦产量的多分支AI模型——Qingdao六县R² 0.756-0.765 MAPE 4.2%","https:\u002F\u002Fbioengineer.org\u002Fnew-multi-branch-ai-model-predicts-winter-wheat-yields-weeks-before-harvest-even-under-extreme-weather\u002F","MBF-HybridNet由青岛六县研究团队开发和测试：采用多分支并行架构，包括处理日常遥感和气象数据的动态变量模块、处理年度尺度极端气候指数数据的动态ECI模块以及处理土壤属性的静态变量模块。动态模块堆叠三个二维卷积层，插入自注意力机制；静态模块独立处理土壤有机碳、阳离子交换容量、pH、砂和粘土含量。研究团队计算了九个极端气候指数（热日、热应力强度、连续热日、霜日、冷应力强度、连续冷日、强降水日、连续湿日和连续干日）用于每个生长阶段。2004至2019年留一年交叉验证，MBF-HybridNet在三个累积生长阶段的R²达到0.756-0.765，平均绝对百分比误差约为4.2%。",null,"MBF-HybridNet 2026 (Qingdao)","2026-09-17T00:00:00Z","论文",10,false,78,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,12,8,1,"多分支AI融合遥感气象与极端气候指数，提前一月预测冬小麦产量且精度可靠，方法新颖、数据扎实，对农业信息化与智慧农业有较高参考价值。",[23],{"name":9,"url":6},[25,26,27,28,29,30],"智慧农业","农业人工智能","产量预测","遥感监测","冬小麦","极端气候",[32,33],"MBF-HybridNet 冬小麦 产量预测","青岛 冬小麦 遥感 极端气候","MBF-HybridNet冬小麦产量预测-3325",0,{"doi":8,"openalex_id":8,"authors":37,"venue":8,"cited_by_count":35,"oa_url":8,"card":38,"direction":42,"ingested_from":44},[],{"tldr":39,"method":40,"finding":41,"direction":42,"opportunity":43},"提出多分支AI模型MBF-HybridNet，融合遥感、气象与土壤数据，提前一月预测冬小麦产量。","多分支并行架构，含2D卷积、自注意力与极端气候指数，2004-2019年留一年交","在青岛六县三个累积生长阶段R²达0.756-0.765，MAPE约4.2%，极端气候下仍可提前一月预","农业人工智能与决策模型","可探索极端气候指数与深度学习结合在其他作物或区域的泛化能力，并提升可解释性。","agent","2026-09-24T00:04:02.748442Z",{"total":47,"page":20,"page_size":47,"items":48},6,[49,80,120,146,207,233],{"id":50,"title":51,"url":52,"summary":53,"summary_zh":8,"content":8,"source_name":54,"source_url":8,"published_at":55,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":56,"score_detail":57,"sources":62,"tags":64,"search_phrases":67,"slug":70,"view_count":35,"doi":71,"paper":72,"created_at":79},2213,"《分层跨模态时空注意力网络用于复杂喜马拉雅农业生态系统作物产量预测》","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1933033\u002Ffull","Mir等提出全面的时空注意力框架,具有四项关键创新:在单树、地块、果园、区域尺度运行的分层注意力机制;融合异构数据流(物联网土壤传感器、气象站、植物生理监测仪、无人机多光谱图像)的跨模态注意力模块;显式建模土壤记忆、滞后和根区耦合的土壤感知注意力头;通过蒙特卡洛Dropout和分位数回归实现不确定性量化。在2023-2026年喜马拉雅苹果园数据集(1247棵监测树)上验证,4周产量预测R²达0.891,RMSE较CNN-LSTM基线降低29.6%,芒果园零样本迁移R²达0.674。","Frontiers in Plant Science 2026年9月10日","2026-09-10T00:00:00Z",82,{"impact":16,"substance":58,"depth":59,"authority":60,"freshness":19,"relevant":20,"comment":61},23,19,14,"方法新颖、数据规模扎实且含跨作物迁移验证，属智慧农业细分领域高水平研究，值得精选。",[63],{"name":54,"url":52},[25,26,27,65,28,66],"多模态融合","苹果园",[68,69],"农业人工智能 多模态融合 产量预测 智慧农业","农业人工智能 多模态融合","农业人工智能多模态融合产量预测智慧农业-2213","10.3389\u002Ffpls.2026.1933033\u002Ffull",{"doi":71,"openalex_id":8,"authors":73,"venue":8,"cited_by_count":35,"oa_url":8,"card":74,"direction":42,"ingested_from":44},[],{"tldr":75,"method":76,"finding":77,"direction":42,"opportunity":78},"提出分层跨模态时空注意力网络，融合多源数据预测喜马拉雅果园作物产量。","分层注意力+跨模态融合物联网、气象、无人机多光谱数据，蒙特卡洛Dropout量化","4周产量预测R²达0.891，RMSE较CNN-LSTM降低29.6%，芒果园零样本迁移R²达0.6","可探索跨物种零样本迁移的域适应机制，以及轻量化模型在边缘设备上的实时部署。","2026-09-12T00:06:40.371547Z",{"id":81,"title":82,"url":83,"summary":84,"summary_zh":85,"content":8,"source_name":86,"source_url":83,"published_at":87,"category":11,"cover_url":8,"hotness":88,"is_selected":13,"score":89,"score_detail":90,"sources":94,"tags":98,"search_phrases":102,"slug":105,"view_count":35,"doi":106,"paper":107,"created_at":119},3357,"AI-Driven Precision Agriculture and Crop Resilience: Integrating Artificial Intelligence, IoT and Remote Sensing for Climate-Resilient Indian Agriculture: A Vision for Viksit Bharat 2047","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22914538","Abstract Agriculture is central to India's economic development, food security, rural employment, and the achievement of the Viksit Bharat@2047 vision. However, Indian agriculture faces increasingly complex challenges, including climate variability, water scarcity, soil degradation, pest and disease outbreaks, fragmented landholdings, market uncertainty, and unequal access to agricultural knowledge. These challenges require a transition from conventional, input-intensive agriculture towards data-driven, resource-efficient, climate-resilient and farmer-centric production systems. Agriculture in India is increasingly affected by climate variability, water scarcity, soil degradation, pest and disease outbreaks, and unpredictable weather conditions. These challenges threaten crop productivity and food security, particularly among small and marginal farmers. Artificial Intelligence (AI), Internet of Things (IoT), remote sensing, and machine learning offer new opportunities to transform conventional agricultural practices into data-driven precision agriculture systems. This paper presents a conceptual framework for AI-driven precision agriculture aimed at improving crop resilience under changing climatic conditions. Artificial Intelligence (AI), combined with precision agriculture, Internet of Things (IoT), remote sensing, satellite imagery, drones, machine learning, robotics and digital public infrastructure, offers significant opportunities to transform Indian agriculture. AI can support crop and yield prediction, disease and pest identification, weather-based advisories, irrigation optimisation, soil management, crop insurance, market intelligence and early-warning systems. The paper also discusses challenges related to digital inclusion, data governance, affordability, AI reliability, farmer skills, privacy and institutional coordination. It argues that India's objective should not simply be the digitisation of agriculture, but the creation of an intelligent, inclusive and resilient agricultural ecosystem in which technology augments farmer knowledge and decision-making. By 2047, India can aspire to establish globally competitive agriculture that produces more with fewer resources, withstands climate shocks, generates higher and more stable farm incomes, and ensures sustainable food and nutritional security.","摘要 农业对印度的经济发展、粮食安全、农村就业以及“发达印度@2047”愿景的实现至关重要。然而，印度农业面临日益复杂的挑战，包括气候变异性、水资源短缺、土壤退化、病虫害暴发、土地持有碎片化、市场不确定性以及农业知识获取不平等。这些挑战要求从传统的投入密集型农业向数据驱动、资源高效、气候韧性且以农民为中心的生产体系转型。印度农业日益受到气候变异性、水资源短缺、土壤退化、病虫害暴发及不可预测天气条件的影响。这些挑战威胁着作物生产力和粮食安全，尤其是对小农和边缘农民而言。人工智能（AI）、物联网（IoT）、遥感和机器学习为将传统农业实践转变为数据驱动的精准农业系统提供了新机遇。本文提出了一个AI驱动的精准农业概念框架，旨在改善气候变化条件下作物的韧性。人工智能（AI）与精准农业、物联网（IoT）、遥感、卫星影像、无人机、机器学习、机器人技术及数字公共基础设施相结合，为改造印度农业提供了重大机遇。AI可支持作物与产量预测、病虫害识别、基于天气的农事建议、灌溉优化、土壤管理、作物保险、市场情报及预警系统。本文还讨论了与数字包容、数据治理、可负担性、AI可靠性、农民技能、隐私及机构协调相关的挑战。文章认为，印度的目标不应仅仅是农业数字化，而应是创建一个智能、包容且有韧性的农业生态系统，使技术增强农民的知识与决策能力。到2047年，印度有望建立具有全球竞争力的农业，以更少资源生产更多产品，抵御气候冲击，创造更高且更稳定的农业收入，并确保可持续的粮食与营养安全。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-30T00:00:00Z",25,69,{"impact":17,"substance":16,"depth":91,"authority":92,"freshness":35,"relevant":20,"comment":93},16,13,"概念性框架论文，系统梳理AI、IoT与遥感在印度气候韧性农业中的应用与挑战，有参考价值但无实证数据，且发布日期在未来、时效性缺失，暂不宜进入每日精选。",[95,96],{"name":86,"url":83},{"name":86,"url":97},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22914539",[99,25,26,100,101,28],"数字乡村","农业物联网","气候韧性",[103,104],"印度 精准农业 AI","农业人工智能 农业物联网 数字乡村 智慧农业","印度精准农业AI-3357","10.5281\u002Fzenodo.22914538",{"doi":106,"openalex_id":108,"authors":109,"venue":86,"cited_by_count":35,"oa_url":83,"card":112,"direction":116,"ingested_from":118},"W7214083098",[110],{"name":111,"orcid":8},"Twinkal Prakash Sawant",{"tldr":113,"method":114,"finding":115,"direction":116,"opportunity":117},"提出AI+物联网+遥感驱动的精准农业概念框架，提升印度气候韧性作物生产。","概念框架分析，整合AI、IoT、遥感、卫星、无人机、机器学习与数字公共基础设施。","印度农业应构建智能、包容、有韧性的生态系统，而非仅数字化，以应对气候与资源挑战。","智慧农业 \u002F 农业物联网","可实证检验小农户场景下AI+IoT+遥感集成对作物韧性与收入的实际效果及数字包容机制。","openalex","2026-09-24T23:30:13.211525Z",{"id":121,"title":122,"url":123,"summary":124,"summary_zh":8,"content":8,"source_name":125,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":126,"sources":128,"tags":130,"search_phrases":134,"slug":137,"view_count":35,"doi":8,"paper":138,"created_at":145},3324,"Diag-STFN：全球收获前作物产量预测的诊断时空多模态融合网络——覆盖38国玉米29国小麦（Ecological Informatics 2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37354974?&&labelLang=hun","《Ecological Informatics》2026年第96期：Zhuang等提出Diag-STFN——一种诊断时空多模态融合网络，用于全球收获前作物产量预测。该网络基于数据集特征选择模型结构，以确定是否需要时间趋势耦合和空间模块激活。在三种前置期（早、中、晚季）下，基于覆盖38国玉米和29国小麦的CY-Bench基准数据集进行评估。结果表明，所提方法在所有前置期均实现了两种作物的最低汇总NRMSE，并在MAPE和KGE等补充指标上保持领先。消融研究表明诊断模块选择提供了主要的性能提升；方差分解显示性能差异在国家之间大于模型之间。","《Ecological Informatics》96 (2026) 103860",{"impact":16,"substance":17,"depth":16,"authority":60,"freshness":47,"relevant":20,"comment":127},"方法新颖、覆盖38国玉米与29国小麦的全球收获前产量预测研究，学术价值突出但产业落地尚早，适合作为前沿技术资讯收录。",[129],{"name":125,"url":123},[25,26,27,131,132,133],"小麦","玉米","遥感",[135,136],"Diag-STFN 作物产量预测","CY-Bench 玉米 小麦","Diag-STFN作物产量预测-3324",{"doi":8,"openalex_id":8,"authors":139,"venue":8,"cited_by_count":35,"oa_url":8,"card":140,"direction":42,"ingested_from":44},[],{"tldr":141,"method":142,"finding":143,"direction":42,"opportunity":144},"提出诊断式时空多模态融合网络Diag-STFN，实现全球收获前玉米小麦产量预测。","基于CY-Bench基准，按数据特征诊断选择时间趋势与空间模块，覆盖38国玉米2","各前置期均取得最低NRMSE，诊断模块选择贡献最大，国家间差异大于模型间差异。","可探索自适应诊断机制迁移至其他作物，并针对国家间差异开展区域化建模与不确定性量化。","2026-09-24T00:04:02.684732Z",{"id":147,"title":148,"url":149,"summary":150,"summary_zh":151,"content":8,"source_name":152,"source_url":149,"published_at":153,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":154,"score_detail":155,"sources":160,"tags":162,"search_phrases":165,"slug":168,"view_count":35,"doi":169,"paper":170,"created_at":206},3258,"Machine learning models combined with feature importance methods for honey yield classification: A replicable approach","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102575","Beekeepers require planning tools supported by modern technologies, such as machine learning and the Internet of Things, to address agricultural challenges such as the decrease and irregularity in honey production. To ensure replicability, this article presents a research workflow that begins with the creation of an open-access database, developed from annual production records and climatic variables (temperature and rainfall), integrating data construction, explainability analysis, and model evaluation. Then, feature importance methods and explainability techniques are applied, such as feature importance, the depth-wise frequency of each feature in random forest, and the Shapley Additive Explanations method. Finally, machine learning approaches are evaluated for honey yield prediction: logistic regression, k-nearest neighbors, support vector machine, decision tree, multilayer perceptron, random forest, linear discriminant analysis, gradient boosting, and Naive Bayes. These algorithms are compared considering: (1) a baseline corresponding to models without hyperparameter optimization, using leave-one-out cross-validation and stratified 10-fold cross-validation; (2) the baseline plus normalization\u002Fstandardization (div-max, min-max, and z-score); (3) the configuration in point 2 plus bagging; (4) evaluation of a data-augmentation and class-balancing strategy using SMOTE, together with model combination via the Voting Classifier. The results suggest that rainfall is one of the most important variables for honey yield prediction. By selecting certain features, the models improve in some cases or do not significantly degrade their performance. The min-max and z-score methods led to improved predictions in some algorithms; for example, support vector machine achieved an accuracy of 0.80, compared with the 0.67 accuracy reported in the reference study based on random forest, representing an increase of 13 percentage points. Finally, bagging techniques, SMOTE oversampling, and the Voting Classifier, using algorithms such as KNN and SVM, can achieve an ACC of 0.82. Overall, this study proposes a replicable data mining-based workflow that integrates machine learning techniques for predicting honey yield from climatic variables, including the use of an open-access dataset, explainability analysis, and a comparative evaluation of machine learning models, contributing to the development of future analysis and planning tools in the beekeeping sector.","养蜂人需要借助机器学习和物联网等现代技术支持的规划工具，以应对蜂蜜产量下降和波动等农业挑战。为确保可复现性，本文提出了一套研究流程：首先构建一个开放获取数据库，该数据库基于年度生产记录和气候变量（温度和降雨量）开发，并整合了数据构建、可解释性分析和模型评估。随后，应用特征重要性方法和可解释性技术，如特征重要性、随机森林中各特征的深度频率以及Shapley加性解释方法。最后，评估多种机器学习方法用于蜂蜜产量预测：逻辑回归、k近邻、支持向量机、决策树、多层感知机、随机森林、线性判别分析、梯度提升和朴素贝叶斯。这些算法在以下方面进行比较：（1）基线模型，即未进行超参数优化的模型，采用留一交叉验证和分层10折交叉验证；（2）基线加归一化\u002F标准化（最大值除法、最小-最大和z-score）；（3）第2点配置加装袋法；（4）使用SMOTE评估数据增强和类别平衡策略，并结合投票分类器进行模型组合。结果表明，降雨量是蜂蜜产量预测中最重要的变量之一。通过选择特定特征，模型在某些情况下性能得到提升，或性能未显著下降。最小-最大和z-score方法使部分算法的预测效果得到改善；例如，支持向量机达到了0.80的准确率，而参考研究中基于随机森林的准确率为0.67，提升了13个百分点。最后，使用KNN和SVM等算法结合装袋技术、SMOTE过采样和投票分类器，可以达到0.82的准确率。总体而言，本研究提出了一套可复现的、基于数据挖掘的工作流程，整合了机器学习技术以从气候变量预测蜂蜜产量，包括使用开放获取数据集、可解释性分析以及机器学习模型的比较评估，为养蜂领域未来分析和规划工具的开发做出了贡献。","Smart Agricultural Technology","2026-09-20T00:00:00Z",71,{"impact":18,"substance":156,"depth":157,"authority":92,"freshness":158,"relevant":20,"comment":159},20,17,9,"该论文提出可复现的机器学习工作流，结合开放数据集与可解释性方法预测蜂蜜产量，方法新颖、结论可靠，对养蜂业数字化规划有参考价值。",[161],{"name":152,"url":149},[25,26,27,163,164],"机器学习","蜂产业",[166,167],"蜂蜜产量 机器学习 预测","Smart Agricultural Technology 蜂蜜","蜂蜜产量机器学习预测-3258","10.1016\u002Fj.atech.2026.102575",{"doi":169,"openalex_id":171,"authors":172,"venue":152,"cited_by_count":35,"oa_url":149,"card":201,"direction":42,"ingested_from":118},"W7213773430",[173,176,179,182,184,187,190,193,195,198],{"name":174,"orcid":175},"Roberto Ahumada‐García","https:\u002F\u002Forcid.org\u002F0000-0003-1107-4606",{"name":177,"orcid":178},"David Zabala‐Blanco","https:\u002F\u002Forcid.org\u002F0000-0002-5692-5673",{"name":180,"orcid":181},"Víctor Hugo Monzón","https:\u002F\u002Forcid.org\u002F0000-0001-9729-7768",{"name":183,"orcid":8},"Iván Sánchez",{"name":185,"orcid":186},"Nádia Félix Felipe da Silva","https:\u002F\u002Forcid.org\u002F0000-0002-3875-2211",{"name":188,"orcid":189},"Thierson Couto Rosa","https:\u002F\u002Forcid.org\u002F0000-0001-7117-3994",{"name":191,"orcid":192},"Alef Iury Siqueira Ferreira","https:\u002F\u002Forcid.org\u002F0000-0002-9119-6357",{"name":194,"orcid":8},"Xaviera López-Cortés",{"name":196,"orcid":197},"Marco Javier Flores-Calero","https:\u002F\u002Forcid.org\u002F0000-0001-7507-3325",{"name":199,"orcid":200},"Philip Vásquez-Iglesias","https:\u002F\u002Forcid.org\u002F0009-0008-2109-8787",{"tldr":202,"method":203,"finding":204,"direction":42,"opportunity":205},"构建可复现工作流，用气候变量与机器学习分类蜂蜜产量。","开放数据库、特征重要性\u002FSHAP、9种ML模型、SMOTE与投票集成。","降雨是最重要变量；SVM准确率0.80，集成后达0.82。","可扩展至多源物联网数据与实时预测，开发养蜂决策支持工具。","2026-09-23T23:30:03.793669Z",{"id":208,"title":209,"url":210,"summary":211,"summary_zh":8,"content":8,"source_name":212,"source_url":8,"published_at":213,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":214,"score_detail":215,"sources":217,"tags":219,"search_phrases":221,"slug":224,"view_count":35,"doi":8,"paper":225,"created_at":232},3248,"Crop recommendation in precision agriculture: a systematic literature review of methods, trends, and challenges（精准农业中的作物推荐：方法、趋势与挑战系统综述）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37471110","MDPI 发表精准农业作物推荐方法系统综述：从183项研究中严格筛选129篇发表于2020-2026年的文章，使用PRISMA协议进行综合分析。研究表明集成学习方法（特别是随机森林和XGBoost）在各种农业数据集的预测性能上具有强大能力；支持向量机、决策树、k近邻等传统ML方法仍被广泛使用；同时CNN和LSTM被用于遥感和时间相关农业分析。最常用的数据集来源是Kaggle，典型输入包括土壤养分（NPK）、土壤pH、天气条件和NDVI、EVI等卫星指数。研究主要研究空白：有限的实时部署、低多数据源集成、低跨区域验证、低模型可解释性。研究表明可扩展、可解释的AI系统对农业实际应用具有重要意义。","MDPI","2026-09-22T00:00:00Z",81,{"impact":16,"substance":17,"depth":16,"authority":92,"freshness":12,"relevant":20,"comment":216},"基于PRISMA的129篇文献系统综述，梳理作物推荐主流方法与四大研究空白，对农业AI落地有参考价值。",[218],{"name":212,"url":210},[25,26,163,220,28],"作物推荐",[222,223],"精准农业 作物推荐 系统综述","XGBoost 随机森林 作物推荐","精准农业作物推荐系统综述-3248",{"doi":8,"openalex_id":8,"authors":226,"venue":8,"cited_by_count":35,"oa_url":8,"card":227,"direction":42,"ingested_from":44},[],{"tldr":228,"method":229,"finding":230,"direction":42,"opportunity":231},"系统综述129篇2020-2026年文献，梳理精准农业作物推荐的方法、趋势与挑战。","PRISMA协议系统综述，分析183项研究筛选出的129篇文献。","集成学习（随机森林、XGBoost）表现最强，主要空白为实时部署、多源集成、跨区域验证与可解释性。","可探索可解释、可跨区域泛化的实时作物推荐系统，并融合多源遥感与物联网数据。","2026-09-23T00:04:33.331160Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":238,"content":8,"source_name":239,"source_url":236,"published_at":240,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":241,"score_detail":242,"sources":244,"tags":246,"search_phrases":248,"slug":251,"view_count":35,"doi":252,"paper":253,"created_at":263},3197,"YieldVision: Model-Driven Decision Support System for Crop Yield Prediction","https:\u002F\u002Fdoi.org\u002F10.56201\u002Frjpst.vol.9.no1.2026.pg176.194","Agriculture, a cornerstone of global food security, faces unprecedented challenges in achieving sustainable productivity. Crop yield prediction, a crucial aspect of agricultural planning, suffers from inefficiencies rooted in technological and methodological gaps. While traditional approaches rely on historical data and empirical estimations, they often fail to address the complexity of environmental interactions because they lack real-time data integration and limited access to accurate data, leading to inaccuracies and resource mismanagement. Addressing these issues requires the development of advanced Machine Learning (ML) models-based system that can predict crop yield with high accuracy in dynamic environments. This paper presents YieldVision, a decision support system driven by advanced ML models for Crop Yield Prediction based on environmental, soil, and crop-specific factors. In this work, we proposed three crop prediction models: Random Forest (RF), Long Short Time Memory (LSTM) and Hybrid (RF LSTM). RF regressor effectively captured the complex, nonlinear relationships among soil nutrients, fertilizer application, and temperature. The LSTM network learned the way short-term weather fluctuations impact crop development over time, and the hybrid model combined LSTM for environmental-related factors, and RF for soil-related factors. Experimental results on the Crop Yield Prediction Dataset containing soil and weather parameters showed that RF has the highest accuracy 𝑅2 = 99.10% and outperforms both LSTM and hybrid which have 87.50% and 97.30% accuracy respectively, confirming its suitability for the dataset. RF has the lowest RMSE and MAE compared to LSTM and hybrid models. The models are integrated into a decision support system that is deployed to operationalize the models in real-world settings with user interfaces accessible via mobile or web-delivered real-time alerts and yield forecasts to farmers and agronomists.","农业作为全球粮食安全的基石，在实现可持续生产力方面面临着前所未有的挑战。作物产量预测作为农业规划的关键环节，因技术和方法上的不足而效率低下。传统方法依赖历史数据和经验估算，但由于缺乏实时数据集成且难以获取准确数据，往往无法应对环境相互作用的复杂性，导致预测不准确和资源管理不善。解决这些问题需要开发基于先进机器学习（ML）模型的系统，能够在动态环境中高精度地预测作物产量。本文提出了YieldVision，一个由先进机器学习模型驱动的决策支持系统，用于基于环境、土壤和作物特定因素的作物产量预测。在本研究中，我们提出了三种作物预测模型：随机森林（RF）、长短期记忆网络（LSTM）和混合模型（RF-LSTM）。随机森林回归器有效捕捉了土壤养分、施肥量和温度之间复杂的非线性关系。LSTM网络学习了短期天气波动如何随时间影响作物发育，而混合模型将LSTM用于环境相关因素，RF用于土壤相关因素。在包含土壤和天气参数的作物产量预测数据集上的实验结果表明，随机森林具有最高的准确率𝑅2 = 99.10%，优于LSTM和混合模型，后两者的准确率分别为87.50%和97.30%，证实了随机森林对该数据集的适用性。与LSTM和混合模型相比，随机森林具有最低的RMSE和MAE。这些模型被集成到一个决策支持系统中，该系统已部署用于在实际环境中运行这些模型，其用户界面可通过移动端或网页访问，向农民和农艺师提供实时警报和产量预测。","RESEARCH JOURNAL OF PURE SCIENCE AND TECHNOLOGY","2026-09-21T00:00:00Z",68,{"impact":18,"substance":156,"depth":91,"authority":18,"freshness":19,"relevant":20,"comment":243},"提出RF、LSTM及混合模型并集成决策支持系统，方法对比与精度数据扎实，对智慧农业产量预测有参考价值，但属单篇论文且来源期刊影响力有限。",[245],{"name":239,"url":236},[25,26,27,163,247],"决策支持系统",[249,250],"YieldVision 作物产量预测","RF LSTM 混合模型 产量预测","YieldVision作物产量预测-3197","10.56201\u002Frjpst.vol.9.no1.2026.pg176.194",{"doi":252,"openalex_id":254,"authors":255,"venue":239,"cited_by_count":35,"oa_url":8,"card":258,"direction":42,"ingested_from":118},"W7213883348",[256],{"name":257,"orcid":8},"D.J.S. Sako",{"tldr":259,"method":260,"finding":261,"direction":42,"opportunity":262},"提出YieldVision决策支持系统，用RF、LSTM及混合模型预测作物产量并部署应用。","基于土壤、环境与作物数据，构建RF、LSTM和RF-LSTM混合模型并集成到We","随机森林表现最佳，R²达99.10%，优于LSTM（87.50%）和混合模型（97.30%）。","可探索多源实时数据融合与模型可解释性，提升跨区域泛化能力并降低对高精度历史数据的依赖。","2026-09-22T23:30:43.591303Z"]