[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5317":3,"related-5317":79},{"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":9,"secondary_topics":30,"classification":31,"search_phrases":60,"slug":63,"view_count":64,"doi":65,"paper":66,"created_at":78},5317,"PLANT-GPK v4.0: A Unified Time-Discovery Framework for Multi-Stage Plant Phenotyping","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23460911","This paper presents a comprehensive extension to the PLANT-GPK framework, demonstrating its robust capability to analyze plants across entirely different developmental stages from single images. By formulating an inverse problem that simultaneously optimizes physiological parameters and the hidden time dimension (t), the model successfully discovered the exact age of two distinct wheat samples: a vegetative (green) stage and a senescent (golden) stage. The framework bridges computer vision, spatial heterogeneity analysis, and ODE-based physics to provide a complete digital twin capable of forecasting future harvest windows regardless of the plant's current state.","本文对PLANT-GPK框架进行了全面扩展，展示了其仅凭单张图像即可分析处于完全不同发育阶段植物的稳健能力。通过构建一个同时优化生理参数与隐藏时间维度（t）的反问题，该模型成功发现了两个不同小麦样本的精确年龄：一个处于营养期（绿色阶段），另一个处于衰老期（金色阶段）。该框架融合了计算机视觉、空间异质性分析以及基于常微分方程（ODE）的物理学，提供了一个完整的数字孪生体，无论植物当前处于何种状态，均能预测未来的收获窗口。",null,"Zenodo (CERN European Organization for Nuclear Research)","2026-10-19T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":20,"comment":21},18,22,13,1,"该研究提出统一时间发现框架，可从单幅图像反演植物生育阶段并预测收获窗口，方法新颖且具数字孪生应用潜力，值得进入每日精选。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","小麦","数字孪生","植物表型",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":35},"needs_review","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":40,"reason":59},[37,45,52],{"code":38,"score":39,"supported":40,"title":41,"abstract":42,"tags":44},"I1",8,true,[],[28,43],"digital twin",[28,25],{"code":46,"score":47,"supported":40,"title":48,"abstract":49,"tags":51},"A2",7,[],[27,50],"wheat",[27],{"code":53,"score":47,"supported":40,"title":54,"abstract":55,"tags":58},"I2",[],[56,57],"计算机视觉","computer vision",[26],"多个产业证据相当，需要确认主归属",[61,62],"PLANT-GPK 植物表型","小麦 数字孪生 生育期","PLANT-GPK植物表型-5317",0,"10.5281\u002Fzenodo.23460911",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":64,"oa_url":6,"card":71,"direction":75,"ingested_from":77},"W7222895088",[69],{"name":70,"orcid":9},"MOHAMMED TAHAR SAIM",{"tldr":72,"method":73,"finding":74,"direction":75,"opportunity":76},"扩展PLANT-GPK框架，从单张图像反演植物生理参数与隐藏时间维度，实现跨发育阶段表型分析。","基于ODE物理模型的反问题优化，联合估计生理参数与时间t，用两个小麦样本验证。","模型成功发现营养期与衰老期小麦的精确年龄，可预测收获窗口。","农业遥感与作物表型","单图跨阶段时间反演可延伸至多作物多生育期数字孪生与收获期预测的通用化研究。","openalex","2026-10-19T23:30:19.498798Z",{"total":80,"page":20,"page_size":80,"items":81},6,[82,131,177,242,323,401],{"id":83,"title":84,"url":85,"summary":86,"summary_zh":87,"content":9,"source_name":10,"source_url":85,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":88,"score_detail":89,"sources":93,"tags":95,"primary_topic":97,"secondary_topics":102,"classification":103,"search_phrases":117,"slug":119,"view_count":64,"doi":120,"paper":121,"created_at":130},5316,"PLANT-GPK v2.7: Spatial Heterogeneity and Predictive Digital Twin for Plant Phenotyping","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23460273","Traditional image-based plant phenotyping assumes spatial homogeneity, estimating a single set of physiological parameters for the entire plant. This paper introduces a novel extension to the PLANT-GPK framework: Spatial Physiological Heatmaps and Predictive Digital Twins. By dividing the plant image into a 3x3 grid and solving the inverse ODE problem for each spatial patch, we reveal the hidden spatial heterogeneity of resource allocation. Furthermore, the recovered parameters are extrapolated to predict the exact day of harvest using a continuous smooth-physics model, providing a powerful prescriptive tool for precision agriculture.","传统的基于图像的植物表型分析假设空间同质性，即对整个植株估计单一组生理参数。本文提出了对PLANT-GPK框架的一种新颖扩展：空间生理热图与预测性数字孪生。通过将植物图像划分为3×3网格并针对每个空间区块求解逆常微分方程（ODE）问题，我们揭示了资源分配中隐藏的空间异质性。此外，利用连续光滑物理模型对所恢复的参数进行外推，以预测确切的收获日期，为精准农业提供了强有力的规范性工具。",79,{"impact":17,"substance":18,"depth":17,"authority":90,"freshness":91,"relevant":20,"comment":92},12,9,"该论文提出植物表型空间异质性建模与预测性数字孪生方法，方法新颖、结论有实用价值，但属细分领域预印本成果，未达重大突破层级。",[94],{"name":10,"url":85},[25,26,28,96,29],"精准农业",{"code":38,"slug":98,"name":99,"path":100,"parent_code":101},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture","I",[],{"status":104,"locked":14,"version":33,"method":34,"evidence":105},"classified",{"candidates":106,"agricultural_evidence":40},[107,113],{"code":38,"score":108,"supported":40,"title":109,"abstract":110,"tags":112},20,[43],[96,28,111],"precision agriculture",[28,25,96],{"code":53,"score":20,"supported":14,"title":114,"abstract":115,"tags":116},[],[],[26],[61,118],"空间生理热图 数字孪生","PLANT-GPK植物表型-5316","10.5281\u002Fzenodo.23460273",{"doi":120,"openalex_id":122,"authors":123,"venue":10,"cited_by_count":64,"oa_url":85,"card":125,"direction":75,"ingested_from":77},"W7222885652",[124],{"name":70,"orcid":9},{"tldr":126,"method":127,"finding":128,"direction":75,"opportunity":129},"将植物图像分3x3网格反演ODE参数，构建空间生理热图与预测数字孪生。","基于PLANT-GPK框架，分块求解逆ODE问题，并用连续平滑物理模型外推。","揭示了植物资源分配的空间异质性，可预测精确收获日。","可探索更细粒度网格与多模态表型融合，提升数字孪生预测精度与田间适用性。","2026-10-19T23:30:19.414490Z",{"id":132,"title":133,"url":134,"summary":135,"summary_zh":136,"content":9,"source_name":10,"source_url":134,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":137,"sources":139,"tags":141,"primary_topic":143,"secondary_topics":147,"classification":148,"search_phrases":163,"slug":165,"view_count":64,"doi":166,"paper":167,"created_at":176},5315,"PLANT-GPK v4.0: Multi-Stage Plant Phenotyping with Time-Discovery and Harvest Prediction","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23461121","This paper presents a comprehensive extension to the PLANT-GPK framework, demonstrating its robust capability to analyze plants across entirely different developmental stages from single images. By formulating an inverse problem that simultaneously optimizes physiological parameters and the hidden time dimension (t), the model successfully discovered the exact age of two distinct wheat samples: a vegetative (green) stage and a senescent (golden) stage. The framework bridges computer vision, spatial heterogeneity analysis, and ODE-based physics to provide a complete digital twin capable of forecasting the exact day of harvest regardless of the plant's current state.","本文对PLANT-GPK框架进行了全面扩展，展示了其仅凭单张图像即可分析处于完全不同发育阶段植物的稳健能力。通过构建一个同时优化生理参数与隐藏时间维度（t）的反问题，该模型成功推断出两个不同小麦样本的精确年龄：一个处于营养期（绿色阶段），另一个处于衰老期（金色阶段）。该框架融合了计算机视觉、空间异质性分析以及基于常微分方程（ODE）的物理建模，提供了一个完整的数字孪生，无论植物当前处于何种状态，均能预测确切的收获日期。",{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":20,"comment":138},"该研究提出从单张图像反演植物生育阶段与收获日的数字孪生框架，方法新颖且具产业应用潜力，值得进入每日精选。",[140],{"name":10,"url":134},[25,26,28,29,142],"收获预测",{"code":53,"slug":144,"name":145,"path":146,"parent_code":101},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":104,"locked":14,"version":33,"method":34,"evidence":149},{"candidates":150,"agricultural_evidence":40},[151,155,159],{"code":38,"score":39,"supported":40,"title":152,"abstract":153,"tags":154},[],[28,43],[28,25],{"code":53,"score":47,"supported":40,"title":156,"abstract":157,"tags":158},[],[56,57],[26],{"code":46,"score":80,"supported":40,"title":160,"abstract":161,"tags":162},[],[27,50],[],[61,164],"小麦 收获期 预测","PLANT-GPK植物表型-5315","10.5281\u002Fzenodo.23461121",{"doi":166,"openalex_id":168,"authors":169,"venue":10,"cited_by_count":64,"oa_url":134,"card":171,"direction":75,"ingested_from":77},"W7222875391",[170],{"name":70,"orcid":9},{"tldr":172,"method":173,"finding":174,"direction":75,"opportunity":175},"扩展PLANT-GPK框架，从单张图像反演植物生理参数与隐藏时间维度，实现跨生育期表型分析与收获期预","基于ODE物理模型与逆问题优化，联合估计生理参数和隐藏时间t，用两个不同生育期小","模型能准确发现两个不同生育期小麦样本的精确年龄，并预测确切收获日期。","可将单图时间反演扩展到多作物多生育期，结合时序遥感构建大尺度数字孪生与收获期预报。","2026-10-19T23:30:19.267920Z",{"id":178,"title":179,"url":180,"summary":181,"summary_zh":182,"content":9,"source_name":183,"source_url":180,"published_at":184,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":185,"sources":188,"tags":190,"primary_topic":193,"secondary_topics":194,"classification":195,"search_phrases":208,"slug":211,"view_count":64,"doi":212,"paper":213,"created_at":241},5562,"pxGPT: A schema-constrained multimodal LLM framework for plant phenotyping","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fbioinformatics\u002Fbtag781","Abstract Summary Deep learning can scale image-based plant phenotyping but typically targets predefined traits, whereas manual phenotypic description is more flexible but difficult to scale. We present Phenotype eXplorer Generative Plant Traits (pxGPT), a Python framework that converts multi-view plant images into structured phenotype records. The workflow combines free-text description, dataset-specific schema generation with human review, and schema-constrained information extraction. We evaluated the extraction stage on three Brassica datasets using 78,973 annotations from ten annotators who had no access to pxGPT predictions. For 38-45 qualitative traits per dataset, pxGPT-human agreement ranged from 0.572 to 0.712, compared with 0.620 to 0.739 agreement among human annotators. All 32,736 required trait fields were present; 93 values were empty, and no qualitative descriptor violations were recorded. For selected morphological structures, pooled false-positive rates were 0.5-8.0%, while sensitivity varied across structure types in one mature-plant dataset (37.5-100%). The curated schemas were applied unchanged with two commercial models and one locally hosted open-weight model, with differences in mean accuracy of 0.03 or less. In the evaluated Brassica datasets, these results support schema-guided extraction of visible plant traits without separate model training for each trait. Human-guided schema development offers a path to extend pxGPT to other crops and imaging conditions, with accuracy requiring validation in each new setting. Availability and Implementation The software is available at https:\u002F\u002Fgithub.com\u002FYaoChengLab\u002Fpxgpt and an archival version of the source code is available on Zenodo (https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22931745). Curated schemas used in this study, annotation guides, phenotype records and human annotations are available at https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22907554. Supplementary information Supplementary data are available at Bioinformatics online.","摘要 深度学习能够扩展基于图像的植物表型分析，但通常针对预定义性状，而人工表型描述更为灵活却难以规模化。我们提出Phenotype eXplorer Generative Plant Traits（pxGPT），一个将多视角植物图像转换为结构化表型记录的Python框架。该工作流程结合了自由文本描述、数据集特定模式生成与人工审核，以及模式约束的信息提取。我们在三个芸薹属（Brassica）数据集上评估了提取阶段，使用了来自十名标注者的78,973条标注，这些标注者无法获取pxGPT的预测结果。对于每个数据集38-45个定性性状，pxGPT与人工标注者之间的一致性范围为0.572至0.712，而人工标注者之间的一致性为0.620至0.739。所有32,736个所需性状字段均已存在；93个值为空，未记录到定性描述符违规。对于选定的形态结构，合并假阳性率为0.5-8.0%，而在一个成熟植株数据集中，灵敏度因结构类型而异（37.5-100%）。经整理的模式在未作修改的情况下应用于两个商业模型和一个本地部署的开放权重模型，平均准确率差异不超过0.03。在所评估的芸薹属数据集中，这些结果支持在无需为每个性状单独训练模型的情况下，对可见植物性状进行模式引导的提取。人工引导的模式开发为将pxGPT扩展至其他作物和成像条件提供了途径，其准确性需在每个新设置中加以验证。可用性与实现 该软件可在https:\u002F\u002Fgithub.com\u002FYaoChengLab\u002Fpxgpt获取，源代码的存档版本可在Zenodo（https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22931745）获取。本研究中使用的经整理模式、标注指南、表型记录和人工标注可在https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22907554获取。补充信息 补充数据可在Bioinformatics在线获取。","Bioinformatics","2026-10-20T00:00:00Z",{"impact":17,"substance":18,"depth":17,"authority":186,"freshness":91,"relevant":20,"comment":187},14,"提出基于模式约束的多模态大模型植物表型提取框架，在近8万条标注上验证，方法新颖、数据规模可观，对智慧育种与表型自动化有参考价值。",[189],{"name":183,"url":180},[25,26,29,191,192],"多模态大模型","芸薹属",{"code":53,"slug":144,"name":145,"path":146,"parent_code":101},[],{"status":104,"locked":14,"version":33,"method":34,"evidence":196},{"candidates":197,"agricultural_evidence":40},[198,204],{"code":53,"score":39,"supported":40,"title":199,"abstract":200,"tags":203},[],[201,202],"深度学习","deep learning",[26,191],{"code":38,"score":20,"supported":14,"title":205,"abstract":206,"tags":207},[],[],[25],[209,210],"pxGPT 植物表型","Brassica 表型 多模态大模型","pxGPT植物表型-5562","10.1093\u002Fbioinformatics\u002Fbtag781",{"doi":212,"openalex_id":214,"authors":215,"venue":183,"cited_by_count":64,"oa_url":234,"card":235,"direction":240,"ingested_from":77},"W7223127960",[216,219,221,224,227,230,232],{"name":217,"orcid":218},"Po‐Xing Zheng","https:\u002F\u002Forcid.org\u002F0000-0001-5827-5865",{"name":220,"orcid":9},"Jheng-Yan Ou",{"name":222,"orcid":223},"Yu-Lin Wu","https:\u002F\u002Forcid.org\u002F0009-0003-8596-9047",{"name":225,"orcid":226},"Ruei-Shiuan Wang","https:\u002F\u002Forcid.org\u002F0009-0007-5159-1129",{"name":228,"orcid":229},"WU Ting-li","https:\u002F\u002Forcid.org\u002F0000-0001-7996-5515",{"name":231,"orcid":9},"Te-Chang Hsu",{"name":233,"orcid":9},"Yao-Cheng Lin","https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtag781\u002F72201337\u002Fbtag781.pdf",{"tldr":236,"method":237,"finding":238,"direction":75,"opportunity":239},"提出pxGPT框架，用多模态大模型将多视角植物图像转为结构化表型记录。","结合自由文本描述、人工审核的模式生成与模式约束信息抽取，在三个芸薹属数据集上评估","pxGPT与人工标注一致性0.572-0.712，接近人工间一致性，且无需逐性状训练模型。","可探索将模式引导抽取迁移至更多作物与复杂成像条件，并研究自动化模式生成以降低人工审核成本。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:22.173561Z",{"id":243,"title":244,"url":245,"summary":246,"summary_zh":247,"content":9,"source_name":248,"source_url":245,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":249,"score_detail":250,"sources":252,"tags":254,"primary_topic":257,"secondary_topics":262,"classification":263,"search_phrases":304,"slug":307,"view_count":64,"doi":308,"paper":309,"created_at":322},5388,"A digital twin framework for proactive disease management in paddy cultivation using spatio-temporal graph neural networks","https:\u002F\u002Fdoi.org\u002F10.1080\u002F20421338.2026.2707951","Rice production is highly affected by disease outbreaks, particularly in Asian agricultural systems, resulting in major yield losses and excessive pesticide usage. This study proposes a digital twin framework for paddy cultivation that integrates predictive disease modelling with real-time crop phenology simulation to support proactive disease management. The framework utilizes historical phenological records, IoT-based microclimatic sensor data, irrigation information, and field management records collected from 150 hectares of paddy fields in Maharashtra, India. A Spatio-Temporal Graph Neural Network (ST-GNN), integrating Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks, is employed to model spatial disease propagation and temporal crop dynamics for predicting blast, brown planthopper, and bacterial leaf blight outbreaks up to 14 days in advance. Experimental results demonstrate 87.3% prediction accuracy, 23.7% reduction in pesticide usage, and 31.2% reduction in crop losses, while outperforming traditional Random Forest and SVM models in F1-score performance. The proposed framework enables real-time decision support for sustainable precision agriculture and optimized resource management.","水稻生产极易受到病害暴发的影响，在亚洲农业体系中尤为突出，造成重大产量损失和农药过度使用。本研究提出一个水稻栽培数字孪生（digital twin）框架，将预测性病害建模与实时作物物候模拟相结合，以支持主动式病害管理。该框架利用从印度马哈拉施特拉邦150公顷稻田采集的历史物候记录、基于物联网的微气候传感器数据、灌溉信息及田间管理记录。采用融合图卷积网络（Graph Convolutional Networks, GCN）与长短期记忆网络（Long Short-Term Memory, LSTM）的时空图神经网络（Spatio-Temporal Graph Neural Network, ST-GNN），对病害空间传播与作物时序动态进行建模，以提前14天预测稻瘟病、褐飞虱和白叶枯病的暴发。实验结果表明，预测准确率达87.3%，农药使用量减少23.7%，作物损失减少31.2%，且在F1分数上优于传统随机森林（Random Forest）和支持向量机（SVM）模型。所提框架可为可持续精准农业和优化资源管理提供实时决策支持。","African Journal of Science Technology Innovation and Development",80,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":91,"relevant":20,"comment":251},"方法新颖、数据规模明确且量化效果显著，属智慧农业细分领域实质进展，值得进入每日精选。",[253],{"name":248,"url":245},[25,26,255,28,256],"水稻","病虫害预警",{"code":258,"slug":259,"name":255,"path":260,"parent_code":261},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":104,"locked":14,"version":33,"method":34,"evidence":264},{"candidates":265,"agricultural_evidence":40},[266,271,277,284,291,298],{"code":38,"score":267,"supported":40,"title":268,"abstract":269,"tags":270},19,[43],[96,28,111,43],[28,25],{"code":258,"score":17,"supported":40,"title":272,"abstract":274,"tags":276},[273],"paddy",[255,275,259,273],"稻田",[255],{"code":278,"score":80,"supported":40,"title":279,"abstract":280,"tags":283},"F4",[],[281,282],"农药","pesticide",[],{"code":285,"score":80,"supported":40,"title":286,"abstract":287,"tags":290},"H3",[],[288,289],"灌溉","irrigation",[],{"code":292,"score":80,"supported":40,"title":293,"abstract":294,"tags":297},"I5",[],[295,296],"物联网","IoT",[],{"code":53,"score":299,"supported":40,"title":300,"abstract":301,"tags":303},4,[],[302],"decision support",[26],[305,306],"水稻 病害预测 数字孪生","ST-GNN 水稻 病虫害","水稻病害预测数字孪生-5388","10.1080\u002F20421338.2026.2707951",{"doi":308,"openalex_id":310,"authors":311,"venue":248,"cited_by_count":64,"oa_url":9,"card":316,"direction":240,"ingested_from":77},"W7222969403",[312,314],{"name":313,"orcid":9},"Jyoti Rani",{"name":315,"orcid":9},"Dr.  Narendra S.  Jadhav",{"tldr":317,"method":318,"finding":319,"direction":320,"opportunity":321},"构建水稻数字孪生框架，用时空图神经网络提前14天预测病害。","融合物联网微气候、物候与管理数据，用GCN+LSTM的ST-GNN建模。","预测准确率87.3%，农药减23.7%、损失减31.2%，优于RF与SVM。","农业人工智能与决策模型","可探索多尺度时空图建模与数字孪生闭环决策，并迁移至其他作物与区域。","2026-10-20T23:30:12.636299Z",{"id":324,"title":325,"url":326,"summary":327,"summary_zh":328,"content":9,"source_name":329,"source_url":326,"published_at":330,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":331,"score_detail":332,"sources":334,"tags":336,"primary_topic":339,"secondary_topics":340,"classification":341,"search_phrases":384,"slug":387,"view_count":64,"doi":388,"paper":389,"created_at":400},5232,"Current applications of artificial intelligence for advancing agriculture, sustainability and climate mitigation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02540-1","Artificial intelligence (AI) is reshaping agriculture by enabling data-driven decision-making across crop production systems and supporting the transition toward more sustainable, resilient, and climate-smart farming. This review critically synthesizes advances in AI applications spanning precision irrigation, nutrient and soil management, yield prediction, pest and disease monitoring, computer vision, autonomous agricultural robotics, and large language model (LLM)-based decision support systems. Beyond summarizing technological developments, the review evaluates their practical deployment, emphasizing that successful agricultural AI depends not only on predictive accuracy but also on model generalizability, explainability, economic feasibility, interoperability, and integration with existing agronomic knowledge. Emerging technologies including Vision Transformers, foundation models, Digital Twins, multimodal AI, Retrieval-Augmented Generation, and federated and continual learning—are discussed as important directions for overcoming limitations related to data scarcity, environmental variability, and scalable field implementation. The review highlights that responsible AI adoption requires transparent governance frameworks addressing data ownership, privacy, algorithmic fairness, cybersecurity, and equitable access, particularly for smallholder farming systems. Although numerous AI models report outstanding performance, widespread agricultural adoption remains constrained by cross-region validation, fragmented datasets, infrastructure requirements, and insufficient real-world deployment. Future progress will depend on multidisciplinary collaboration integrating advances in artificial intelligence, sensing technologies, robotics, crop science, and agricultural engineering to develop robust, trustworthy, and farmer-centered decision-support systems. By critically evaluating technological innovations and implementation challenges, this review provides a framework for understanding the current state of AI in agriculture while identifying research priorities that will shape the next generation of sustainable and climate-resilient agricultural systems.","人工智能（AI）正在重塑农业，通过在作物生产系统中实现数据驱动的决策，并支持向更可持续、更具韧性和气候智能型农业转型。本综述批判性地综合了AI应用的进展，涵盖精准灌溉、养分与土壤管理、产量预测、病虫害监测、计算机视觉、自主农业机器人以及基于大语言模型（LLM）的决策支持系统。除总结技术发展外，本综述还评估了其实际部署情况，强调农业AI的成功不仅取决于预测准确性，还取决于模型泛化能力、可解释性、经济可行性、互操作性以及与现有农学知识的整合。文中讨论了包括视觉Transformer、基础模型、数字孪生、多模态AI、检索增强生成以及联邦学习和持续学习在内的新兴技术，将其视为克服数据稀缺、环境变异性和田间可扩展实施等局限的重要方向。本综述强调，负责任的AI采用需要透明的治理框架，以解决数据所有权、隐私、算法公平性、网络安全和公平获取等问题，尤其是对小农耕作系统而言。尽管众多AI模型报告了卓越的性能，但农业领域的广泛采用仍受限于跨区域验证、碎片化数据集、基础设施要求以及现实世界部署不足。未来的进展将取决于多学科协作，整合人工智能、传感技术、机器人技术、作物科学和农业工程领域的进展，以开发稳健、可信且以农民为中心的决策支持系统。通过批判性评估技术创新和实施挑战，本综述提供了一个理解AI在农业中现状的框架，同时确定了将塑造下一代可持续和气候韧性农业系统的研究优先事项。","Discover Artificial Intelligence","2026-10-17T00:00:00Z",83,{"impact":18,"substance":18,"depth":17,"authority":90,"freshness":91,"relevant":20,"comment":333},"该综述系统梳理了AI在农业中的应用与落地瓶颈，覆盖精准灌溉、机器人、大模型决策支持等方向，信息密度高，但属综述类论文，产业级突破性有限，可入精选。",[335],{"name":329,"url":326},[25,26,337,28,338],"大语言模型","气候智慧农业",{"code":53,"slug":144,"name":145,"path":146,"parent_code":101},[],{"status":104,"locked":14,"version":33,"method":34,"evidence":342},{"candidates":343,"agricultural_evidence":40},[344,350,357,361,366,373,379],{"code":53,"score":267,"supported":40,"title":345,"abstract":347,"tags":349},[346],"artificial intelligence",[56,346,57,348,302],"large language model",[26,337],{"code":351,"score":80,"supported":40,"title":352,"abstract":353,"tags":356},"H2",[],[354,355],"土壤","soil",[],{"code":285,"score":80,"supported":40,"title":358,"abstract":359,"tags":360},[],[288,289],[],{"code":38,"score":362,"supported":40,"title":363,"abstract":364,"tags":365},5,[],[28],[28,25],{"code":367,"score":368,"supported":40,"title":369,"abstract":370,"tags":372},"F6",3,[],[371],"农业机器人",[],{"code":374,"score":368,"supported":40,"title":375,"abstract":376,"tags":378},"G2",[],[377],"smallholder",[],{"code":380,"score":20,"supported":14,"title":381,"abstract":382,"tags":383},"H7",[],[],[338],[385,386],"气候智慧农业 AI","农业人工智能 气候智慧农业 大语言模型 数字孪生","气候智慧农业AI-5232","10.1007\u002Fs44163-026-02540-1",{"doi":388,"openalex_id":390,"authors":391,"venue":329,"cited_by_count":64,"oa_url":326,"card":395,"direction":240,"ingested_from":77},"W7222823256",[392],{"name":393,"orcid":394},"Mostafa Farajpour","https:\u002F\u002Forcid.org\u002F0000-0003-4223-502X",{"tldr":396,"method":397,"finding":398,"direction":320,"opportunity":399},"综述农业人工智能在精准灌溉、产量预测、病虫害监测等应用及落地挑战。","文献综述，覆盖视觉Transformer、基础模型、数字孪生、多模态AI与联邦学","农业AI落地受限于跨区域验证、数据碎片化与基础设施，需兼顾可解释性与公平治理。","可研究小农户场景下跨区域可泛化、可解释且低成本的农业大模型与联邦学习部署。","2026-10-18T23:30:07.666127Z",{"id":402,"title":403,"url":404,"summary":405,"summary_zh":406,"content":9,"source_name":407,"source_url":404,"published_at":408,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":409,"score_detail":410,"sources":412,"tags":414,"primary_topic":9,"secondary_topics":416,"classification":417,"search_phrases":436,"slug":439,"view_count":20,"doi":440,"paper":441,"created_at":454},4999,"Biology-aware association for identity-consistent leaf tracking in top-down plant phenotyping","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1881413","Reliable leaf-level trait trajectories require identity-consistent tracking across growth, overlap, and appearance change. We introduce a biology-aware association module combining one appearance cue and three biological\u002Fgeometric cues: spatial continuity, area-growth plausibility, and lifecycle plausibility. On CanolaTrack, adaptive weighting reduces ID switches from 228 to 126 ± 5 (44.7%; per-plant paired p = 1.6 × 10 −5 , n = 37) and improves HOTA from 88.17 to 89.69 ± 0.10. Difficulty-stratified analysis shows IDSW reductions across all 12 CanolaTrack strata, averaging 40.0% versus Appearance-only and 45.0% versus LeafTrackNet. External association-only Arabidopsis and KOMATSUNA tests identify clean low-displacement GT-box regimes where centroid matching or Fixed bio-constraints are more reliable than zero-shot adaptive-weight transfer. These results provide an operating-envelope recommendation: adaptive weighting is most useful in dense CanolaTrack-like sequences, whereas Fixed bio-constraints or centroid matching are more reliable in clean low-displacement external regimes—where nearest-centroid assignment already resolves most associations, so that even a predictor retrained on the target domain does not surpass it. The limiting factor is thus primarily the association difficulty of the regime rather than dataset size.","可靠的叶片级性状轨迹需要在生长、重叠和外观变化过程中进行身份一致的跟踪。我们引入了一个生物学感知关联模块，该模块结合了一个外观线索和三个生物学\u002F几何线索：空间连续性、面积增长合理性和生命周期合理性。在CanolaTrack上，自适应加权将ID切换从228降至126 ± 5（44.7%；每株配对p = 1.6 × 10⁻⁵，n = 37），并将HOTA从88.17提升至89.69 ± 0.10。难度分层分析显示，在全部12个CanolaTrack分层中IDSW均有降低，相较于仅外观方法平均降低40.0%，相较于LeafTrackNet平均降低45.0%。仅关联的外部拟南芥和KOMATSUNA测试识别出干净的低位移GT框情形，在这些情形下质心匹配或固定生物约束比零样本自适应权重迁移更可靠。这些结果提供了适用范围的建议：自适应加权在类似CanolaTrack的密集序列中最为有用，而固定生物约束或质心匹配在干净的低位移外部情形中更为可靠——在这些情形下最近质心分配已能解决大多数关联，因此即使在目标域上重新训练的预测器也无法超越它。因此，限制因素主要是该情形的关联难度，而非数据集大小。","Frontiers in Plant Science","2026-10-14T00:00:00Z",75,{"impact":90,"substance":18,"depth":17,"authority":186,"freshness":91,"relevant":20,"comment":411},"提出融合外观与生物几何线索的叶片身份一致追踪方法，在油菜数据集上显著降低ID切换，属农业人工智能与植物表型领域有实质增量的方法类论文。",[413],{"name":407,"url":404},[25,26,56,415,29],"油菜",[],{"status":418,"locked":14,"version":33,"method":34,"evidence":419},"unclassified",{"candidates":420,"agricultural_evidence":40,"reason":435},[421,426,431],{"code":53,"score":422,"supported":14,"title":423,"abstract":424,"tags":425},2,[],[],[26,56],{"code":427,"score":20,"supported":14,"title":428,"abstract":429,"tags":430},"A4",[],[],[415],{"code":38,"score":20,"supported":14,"title":432,"abstract":433,"tags":434},[],[],[25],"缺少足够的主题证据",[437,438],"CanolaTrack 叶片追踪","植物表型 叶片跟踪","CanolaTrack叶片追踪-4999","10.3389\u002Ffpls.2026.1881413",{"doi":440,"openalex_id":442,"authors":443,"venue":407,"cited_by_count":64,"oa_url":448,"card":449,"direction":75,"ingested_from":77},"W7221780154",[444,446],{"name":445,"orcid":9},"Dongze Zhou",{"name":447,"orcid":9},"Cong Zhang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1881413\u002Fpdf",{"tldr":450,"method":451,"finding":452,"direction":75,"opportunity":453},"提出融合外观与三种生物几何线索的关联模块，实现叶片身份一致跟踪。","在CanolaTrack等数据上，用自适应加权结合空间、面积生长与生命周期线索。","自适应加权将ID切换降低44.7%，HOTA提升至89.69，但外部干净场景下固定约束更可靠。","可探索按场景难度自适应切换关联策略，并研究跨物种迁移的泛化边界。","2026-10-15T23:30:20.609629Z"]