[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2076":3,"related-2076":77},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":72,"slug":75,"view_count":53,"doi":8,"paper":8,"created_at":76},2076,"农业农村部信息中心主任王小兵调研四川仪陇智慧农业建设","https:\u002F\u002Fwww.yilong.gov.cn\u002Fxwdt\u002Fylyw\u002Ft_2359288.html","9月8日农业农村部信息中心主任、党委书记王小兵赴四川仪陇专题调研智慧农业发展与人工智能赋能农事服务中心建设。王小兵指出,仪陇基层农事服务阵地基础扎实、体系完善,具备打造丘陵山区智慧农业示范样板的良好条件,要紧扣农业生产全链条,聚焦水稻关键生产环节推动数字技术、人工智能与农事作业深度融合,打造可复制可推广的丘陵山区智慧农事服务示范标杆。",null,"农业农村部信息中心主任、党委书记王小兵专题调研我县智慧农业建设工作\n\n![Image 1](http:\u002F\u002Fwww.yilong.gov.cn\u002Fimages\u002Fxl-info-date.png)发布时间：2026-09-10 12:00:00\n\n![Image 2](http:\u002F\u002Fwww.yilong.gov.cn\u002Fimages\u002Fxl-info-source.png)来源：仪陇融媒\n\n![Image 3](http:\u002F\u002Fwww.yilong.gov.cn\u002Fimages\u002Fxl-func-print.png)\n\n![Image 4](http:\u002F\u002Fwww.yilong.gov.cn\u002Fimages\u002Fxl-share.png)分享：[![Image 5](http:\u002F\u002Fwww.yilong.gov.cn\u002Fimages\u002Fxl-share-weixin.png)](https:\u002F\u002Fwww.yilong.gov.cn\u002Fxwdt\u002Fylyw\u002Ft_2359288.html#div_div)\n\n仪陇融媒（记者 牛榆）9月8日，农业农村部信息中心主任、党委书记王小兵到我县专题调研智慧农业发展、人工智能赋能农事服务中心建设工作，市、县相关负责人参加调研。\n\n座谈会上，王小兵对我县农业社会化服务及智慧农业建设成效给予充分肯定。他指出，仪陇基层农事服务阵地基础扎实、体系完善，具备打造丘陵山区智慧农业示范样板的良好条件。他强调，要紧扣农业生产全链条，聚焦水稻关键生产环节，推动数字技术、人工智能与农事作业深度融合，切实破解农业生产痛点难点，实现降本增效、助农增收。要系统整合现有服务阵地资源，统筹硬件升级与数字平台迭代，联动科技企业优化建设方案，全力打造可复制、可推广的丘陵山区智慧农事服务示范标杆。要立足本地产业特色，分步推进AI技术在粮食、特色果蔬产业落地应用，简化操作场景、降低农户使用门槛。同时坚持数智建设、品质提升、品牌培育一体推进，依托数字赋能擦亮仪陇农业特色品牌。\n\n![Image 6: b8bfe234173ec02bffa92a405ac6fc9e.jpg](https:\u002F\u002Fwww.yilong.gov.cn\u002Fxwdt\u002Fylyw\u002FW020260910725635248814_ORIGIN.jpg)\n\n会前，调研组实地走访我县农业社会化服务中心及相关分中心，详细查看智慧农业平台运行、智能设备配置、农事服务开展等情况，细致了解我县农业社会化服务体系建设成效与运营模式。\n\n![Image 7: c9fe13e330d0238205c8bd05d885e3e3.jpg](https:\u002F\u002Fwww.yilong.gov.cn\u002Fxwdt\u002Fylyw\u002FW020260910725635460667_ORIGIN.jpg)\n\n会上，市、县相关部门汇报了智慧农业建设、农业社会化服务体系构建及特色农业产业发展工作。参会人工智能科技企业介绍了自身技术研发、农业数字化应用及场景落地等相关情况。\n\n副县长熊挺参加会议。\n\n扫一扫用手机打开","仪陇县人民政府","2026-09-08T00:00:00Z","报道",10,false,56,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},14,15,13,6,8,1,"部委信息中心负责人赴县级丘陵山区调研智慧农业与AI农事服务，提出打造可复制示范样板，方向性信号明确但属地方动态，适合作为主题聚合素材而非头条精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"数字乡村","智慧农业","农业人工智能","丘陵山区","农事服务",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":48},[45,52,57,62,67],{"code":46,"score":47,"supported":48,"title":49,"abstract":50,"tags":51},"I1",12,true,[28],[28],[28],{"code":33,"score":53,"supported":48,"title":54,"abstract":55,"tags":56},3,[],[35],[],{"code":58,"score":22,"supported":14,"title":59,"abstract":60,"tags":61},"G2",[],[],[31],{"code":63,"score":22,"supported":14,"title":64,"abstract":65,"tags":66},"I2",[],[],[29],{"code":68,"score":22,"supported":14,"title":69,"abstract":70,"tags":71},"I6",[],[],[27],[73,74],"农业人工智能 丘陵山区 农事服务 数字乡村","农业人工智能 丘陵山区","农业人工智能丘陵山区农事服务数字乡村-2076","2026-09-11T00:04:18.265495Z",{"total":20,"page":22,"page_size":20,"items":78},[79,154,219,297,373,446],{"id":80,"title":81,"url":82,"summary":83,"summary_zh":8,"content":84,"source_name":85,"source_url":8,"published_at":86,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":87,"score_detail":88,"sources":92,"tags":94,"primary_topic":97,"secondary_topics":98,"classification":104,"search_phrases":148,"slug":151,"view_count":152,"doi":8,"paper":8,"created_at":153},4275,"四川眉山科技慧种田 水稻单产品质双提升 AI大模型试点亩产863.6公斤","https:\u002F\u002Fwww.sctv.com\u002Fnews\u002F2105963737230815234","四川眉山洪雅县止戈镇水稻百亩超高产攻关片三台联合收割机同步作业，水稻实测亩产824.6公斤。东坡区太和镇永丰村300亩首次应用水稻专属AI大模型管理，超高产籼粳杂交稻昇两优222亩产达863.6公斤。彭山区公义镇数智水稻示范基地通过物联网监测智能灌溉实现水稻耕种管收全流程精准管控。","金秋时节，稻谷飘香。眼下，眉山市水稻收获接近尾声，良种良法配套、人工智能赋能、数智化管理等农业新技术落地田间，助力今年水稻单产提升、品质向好。\n\n在洪雅县止戈镇五龙社区，水稻百亩超高产攻关片的试验田里三台联合收割机同步完成割稻、脱粒、秸秆还田作业，现场水稻实测亩产达824.6公斤。\n\n眉山市洪雅县止戈镇五龙社区种粮大户 张雪勤：今天测产的品种是去年我们通过评比试验筛选出来的“荃优879”，全程按照标准化、科学化的方式进行管理，长势和产量效果都非常好。\n\n良种是粮食增产增收的关键，当地针对盆周山区多雨高湿、病虫害多发的气候特点，建成100亩水稻中试熟化基地，精准筛选适配本地水土、抗逆性强的水稻品种。\n\n眉山市洪雅县农业农村局农技站站长 白蓉钢：常态化开展粮油新品种引进、试验、筛选与示范推广，同时持续推广良种良法配套技术，持续提升粮食综合生产能力，全力稳住全县粮食生产基本盘。\n\n在东坡区太和镇永丰村，千亩高标准农田刚刚完成了收割。其中，300亩首次应用水稻专属AI大模型管理的试点田格外引人注目。\n\n眉山市东坡区太和镇永丰村种粮大户 赵友勇：现在的话我们更多会用这个无人机来巡田，也会及时地给我们推送水稻里面的一个病虫害的情况，根据这个推送的情况我们做针对性地处理。\n\n经过现场实测，超高产籼粳杂交稻“昇两优222”亩产达863.6公斤。稳产丰产的底气，源自科技赋能。通过无人机航拍采集田间数据，AI大模型可实现水稻全生长周期智慧管控，预测最佳收割时间、预判粮食产量，种植管理更精细科学。\n\n四川农业大学教授 马均：我们从田间的长势长相的情况来看，表现还是挺不错的，智慧化的精准条播技术，还包括我们AI技术的运用，初步显示出来一些就是好的效果。\n\n走进彭山区公义镇的数智水稻示范基地，刚刚收割完成的稻谷直接送进现代化烘干车间。通过物联网监测、智能灌溉等智慧设备，实现水稻耕种管收全流程精准管控。\n\n眉山市彭山区公义镇欣荣村种粮大户 王程淋：我们现在种田不但要靠经验、更要靠数据。土壤湿度、田间温度、病虫害情况，手机上实时就能看到。智能设备自动管控水肥，产量和品质都比往年更好。","四川新闻联播 2026-10-04","2026-10-04T11:00:00Z",71,{"impact":89,"substance":90,"depth":18,"authority":13,"freshness":21,"relevant":22,"comment":91},18,20,"四川眉山AI大模型水稻试点实测亩产863.6公斤，数据具体、多方信源，具智慧农业示范价值。",[93],{"name":85,"url":82},[27,28,29,95,96],"良种良法","水稻单产",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[99],{"code":63,"slug":100,"name":101,"path":102,"parent_code":103},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":105},{"candidates":106,"agricultural_evidence":48},[107,112,117,123,129,135,140,144],{"code":33,"score":17,"supported":48,"title":108,"abstract":109,"tags":111},[35],[35,110],"杂交稻",[],{"code":63,"score":47,"supported":48,"title":113,"abstract":115,"tags":116},[114],"大模型",[114],[29],{"code":118,"score":53,"supported":48,"title":119,"abstract":120,"tags":122},"F5",[],[121],"收割机",[],{"code":124,"score":53,"supported":48,"title":125,"abstract":126,"tags":128},"H3",[],[127],"灌溉",[],{"code":130,"score":53,"supported":48,"title":131,"abstract":132,"tags":134},"I5",[],[133],"物联网",[],{"code":136,"score":22,"supported":14,"title":137,"abstract":138,"tags":139},"F1",[],[],[95],{"code":46,"score":22,"supported":14,"title":141,"abstract":142,"tags":143},[],[],[28],{"code":68,"score":22,"supported":14,"title":145,"abstract":146,"tags":147},[],[],[27],[149,150],"眉山 永丰村 AI大模型 水稻","昇两优222 亩产863.6公斤","眉山永丰村AI大模型水稻-4275",0,"2026-10-06T00:05:02.998709Z",{"id":155,"title":156,"url":157,"summary":158,"summary_zh":8,"content":159,"source_name":160,"source_url":8,"published_at":161,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":162,"score_detail":163,"sources":169,"tags":171,"primary_topic":174,"secondary_topics":175,"classification":176,"search_phrases":213,"slug":216,"view_count":217,"doi":8,"paper":8,"created_at":218},4273,"黑龙江不断强化农业科技装备支撑 智慧农业聚木成林","https:\u002F\u002Fstcn.com\u002Farticle\u002Fdetail\u002F4206344.html","佳木斯国家农业高新技术产业示范区崖州湾国家实验室粮油作物创新平台试验田，借助AI算法，水稻品种稳定性和抗性提升明显加快，育种周期从5-8年缩短到3-5年。桦川县玉成现代农机专业合作社6000亩定制稻田签约总额达3318万元，带动合作社社员户均增收2300元。富锦市万亩水稻公园变量施肥地图让水稻底肥减少10%增产超3%。","中央网信办、农业农村部、工业和信息化部联合印发《数字乡村高质量发展行动计划（2026—2030年）》。其中提到，加快建设智慧农业。加快良田良种良机良法与数字化有机融合，聚焦重点区域重点品种，集成推广一批主要作物大面积单产提升数智化解决方案。建立智慧农（牧、渔）场数字化场景认证体系，因地制宜建设一批智慧农（牧、渔）场。推动智能育种技术研发应用，建设一批智能化现代化的农作物优势制种区和畜禽、水产核心育种场。研究完善农业人工智能标准体系，推广人工智能与农业融合应用场景。发挥现代农事综合服务中心等作用，","证券时报 人民日报 2026-10-05","2026-10-05T00:26:00Z",88,{"impact":164,"substance":165,"depth":166,"authority":17,"freshness":167,"relevant":22,"comment":168},27,22,16,9,"三部委联合印发数字乡村新五年行动计划，含智慧农业、智能育种、AI标准等实质条款，政策层级高、时效性强，值得进入每日精选。",[170],{"name":160,"url":157},[27,28,29,172,173],"智能育种","农业装备",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":177},{"candidates":178,"agricultural_evidence":48},[179,183,188,194,200,205,209],{"code":46,"score":167,"supported":48,"title":180,"abstract":181,"tags":182},[28],[],[28],{"code":33,"score":20,"supported":48,"title":184,"abstract":185,"tags":187},[],[35,186],"稻田",[],{"code":118,"score":189,"supported":48,"title":190,"abstract":191,"tags":193},4,[],[192],"农机",[173],{"code":195,"score":53,"supported":48,"title":196,"abstract":197,"tags":199},"F3",[],[198],"施肥",[],{"code":201,"score":22,"supported":14,"title":202,"abstract":203,"tags":204},"F2",[],[],[172],{"code":63,"score":22,"supported":14,"title":206,"abstract":207,"tags":208},[],[],[29],{"code":68,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},[],[],[27],[214,215],"智慧农场 数字化认证","农业人工智能 农业装备 数字乡村 智慧农业","智慧农场数字化认证-4273",2,"2026-10-06T00:05:02.838245Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":224,"content":8,"source_name":225,"source_url":222,"published_at":226,"category":227,"cover_url":8,"hotness":13,"is_selected":14,"score":228,"score_detail":229,"sources":231,"tags":233,"primary_topic":236,"secondary_topics":237,"classification":243,"search_phrases":276,"slug":279,"view_count":152,"doi":280,"paper":281,"created_at":296},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z","论文",78,{"impact":89,"substance":165,"depth":89,"authority":47,"freshness":21,"relevant":22,"comment":230},"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[232],{"name":225,"url":222},[28,29,35,234,235],"产量预测","遥感",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[238],{"code":239,"slug":240,"name":241,"path":242,"parent_code":103},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":244},{"candidates":245,"agricultural_evidence":48},[246,250,255,262,268,272],{"code":33,"score":18,"supported":48,"title":247,"abstract":248,"tags":249},[34],[35,34],[35],{"code":239,"score":21,"supported":48,"title":251,"abstract":252,"tags":254},[],[235,253],"remote sensing",[234,235],{"code":256,"score":20,"supported":48,"title":257,"abstract":258,"tags":261},"A8",[],[259,260],"粮食安全","food security",[],{"code":263,"score":53,"supported":48,"title":264,"abstract":265,"tags":267},"J1",[],[266],"农业规划",[],{"code":46,"score":22,"supported":14,"title":269,"abstract":270,"tags":271},[],[],[28],{"code":63,"score":22,"supported":14,"title":273,"abstract":274,"tags":275},[],[],[29],[277,278],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":280,"openalex_id":282,"authors":283,"venue":225,"cited_by_count":152,"oa_url":222,"card":289,"direction":293,"ingested_from":295},"W7222942064",[284,286],{"name":285,"orcid":8},"Nayana Venkatesh",{"name":287,"orcid":288},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":290,"method":291,"finding":292,"direction":293,"opportunity":294},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","农业遥感与作物表型","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","openalex","2026-10-20T23:30:19.292634Z",{"id":298,"title":299,"url":300,"summary":301,"summary_zh":302,"content":8,"source_name":303,"source_url":300,"published_at":304,"category":227,"cover_url":8,"hotness":13,"is_selected":14,"score":305,"score_detail":306,"sources":308,"tags":310,"primary_topic":313,"secondary_topics":314,"classification":315,"search_phrases":353,"slug":356,"view_count":152,"doi":357,"paper":358,"created_at":372},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","2026-10-19T00:00:00Z",80,{"impact":89,"substance":165,"depth":89,"authority":19,"freshness":167,"relevant":22,"comment":307},"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。",[309],{"name":303,"url":300},[28,29,35,311,312],"数字孪生","病虫害预警",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":316},{"candidates":317,"agricultural_evidence":48},[318,326,331,338,343,348],{"code":46,"score":319,"supported":48,"title":320,"abstract":322,"tags":325},19,[321],"digital twin",[323,311,324,321],"精准农业","precision agriculture",[311,28],{"code":33,"score":89,"supported":48,"title":327,"abstract":329,"tags":330},[328],"paddy",[35,186,34,328],[35],{"code":332,"score":20,"supported":48,"title":333,"abstract":334,"tags":337},"F4",[],[335,336],"农药","pesticide",[],{"code":124,"score":20,"supported":48,"title":339,"abstract":340,"tags":342},[],[127,341],"irrigation",[],{"code":130,"score":20,"supported":48,"title":344,"abstract":345,"tags":347},[],[133,346],"IoT",[],{"code":63,"score":189,"supported":48,"title":349,"abstract":350,"tags":352},[],[351],"decision support",[29],[354,355],"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":357,"openalex_id":359,"authors":360,"venue":303,"cited_by_count":152,"oa_url":8,"card":365,"direction":371,"ingested_from":295},"W7222969403",[361,363],{"name":362,"orcid":8},"Jyoti Rani",{"name":364,"orcid":8},"Dr.  Narendra S.  Jadhav",{"tldr":366,"method":367,"finding":368,"direction":369,"opportunity":370},"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。","智慧农业 \u002F 农业物联网","2026-10-20T23:30:12.636299Z",{"id":374,"title":375,"url":376,"summary":377,"summary_zh":378,"content":8,"source_name":379,"source_url":376,"published_at":380,"category":227,"cover_url":8,"hotness":13,"is_selected":14,"score":381,"score_detail":382,"sources":384,"tags":386,"primary_topic":390,"secondary_topics":391,"classification":393,"search_phrases":415,"slug":418,"view_count":22,"doi":419,"paper":420,"created_at":445},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","2026-10-13T00:00:00Z",72,{"impact":47,"substance":90,"depth":89,"authority":17,"freshness":21,"relevant":22,"comment":383},"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。",[385],{"name":379,"url":376},[28,29,387,388,389],"可解释AI","农业气象","水稻产量预测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[392],{"code":63,"slug":100,"name":101,"path":102,"parent_code":103},{"status":40,"locked":14,"version":41,"method":42,"evidence":394},{"candidates":395,"agricultural_evidence":48},[396,402,406,411],{"code":63,"score":319,"supported":48,"title":397,"abstract":399,"tags":401},[398],"machine learning",[400,398,351],"机器学习",[29,387],{"code":33,"score":17,"supported":48,"title":403,"abstract":404,"tags":405},[34],[35,34],[],{"code":407,"score":22,"supported":14,"title":408,"abstract":409,"tags":410},"H7",[],[],[388],{"code":46,"score":22,"supported":14,"title":412,"abstract":413,"tags":414},[],[],[28],[416,417],"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":419,"openalex_id":421,"authors":422,"venue":379,"cited_by_count":152,"oa_url":439,"card":440,"direction":371,"ingested_from":295},"W7221657053",[423,425,427,429,431,433,436],{"name":424,"orcid":8},"Noh-Hyun Lee",{"name":426,"orcid":8},"Wonjae Jeong",{"name":428,"orcid":8},"Hyeon-Ji Yang",{"name":430,"orcid":8},"Hana Cho",{"name":432,"orcid":8},"Hyeon-Yeong Ju",{"name":434,"orcid":435},"Toshichika Iizumi","https:\u002F\u002Forcid.org\u002F0000-0002-0611-4637",{"name":437,"orcid":438},"Ki‐Tae Kim","https:\u002F\u002Forcid.org\u002F0000-0002-8249-5283","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75646-2_reference.pdf",{"tldr":441,"method":442,"finding":443,"direction":369,"opportunity":444},"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":447,"title":448,"url":449,"summary":450,"summary_zh":8,"content":451,"source_name":452,"source_url":8,"published_at":380,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":162,"score_detail":453,"sources":457,"tags":459,"primary_topic":462,"secondary_topics":463,"classification":464,"search_phrases":487,"slug":490,"view_count":152,"doi":8,"paper":8,"created_at":491},4950,"'袁稻思源'杂交水稻智能育种平台发布 业界首个智能育种平台落户湖南","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7696096616441774642\u002F","10月11日,'袁稻思源'杂交水稻智能育种平台发布会在岳麓山实验室举行,由中国科学院自动化研究所联合湖南省农业科学院、北京中科闻歌科技股份有限公司共同研发。平台集成'问答助手''育种资源库''知识图谱''文献库'四大功能模块,收纳35570个水稻品种、689项性状、28648条基因数据和624757篇中英文文献。中国科学院院士李家洋、钱前、谢道昕,中国工程院院士柏连阳等共同见证。","来源：环球网\n\n水稻育种专家过去最头疼的是什么？翻资料。查一个品种亲本、找一个性状基因，动辄耗费大量时间。近期，中科闻歌带着决策智能入场了。10月11日，由湖南省农科院、中科院自动化所与中科闻歌联合打造的“袁稻思源”杂交水稻智能育种平台正式发布，把海量育种数据和AI决策能力送进育种一线。\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F2397644cc26144379c7e432950a2deec~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1792627757&x-signature=o8pNXOWnEqlIl4mnK12LZ8rHkeA%3D)\n**水稻育种：一个“数据富矿”**\n\n杂交水稻育种是一个典型的“数据富矿、决策洼地”领域。全球积累了海量品种、性状、基因和文献数据，但长期分散、难以检索，育种更多依赖科研人员的经验与记忆。为破解这一难题，今年7月2日，中国科学院自动化研究所、北京中科闻歌科技股份有限公司与湖南省农业科学院正式签约，围绕“人工智能+农业科研”开展联合攻关。“袁稻思源”正是这一合作的阶段性成果，平台名称取自袁隆平杂交水稻创新团队，寓意“饮水思源”，感怀袁隆平院士对中国水稻杂交育种作出的突出贡献。\n\n湖南省农科院院长余应弘介绍，“袁稻思源”是湖南落实国家种业振兴行动、推进育种数字化智能化转型的关键举措，旨在传承袁隆平院士科学精神，把数据资源和智能技术转化为育种创新的现实生产力。在中科闻歌的战略版图里，这次入局农业科研，是其“决策大模型”“AI国家队”能力向产业纵深的又一次延伸。\n\n![Image 2](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002F328723c57ddce965a8efda71ad02f21a~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1792627757&x-signature=0csP6GpZya22ien7EebcU64%2FxRw%3D)\n**“袁稻思源”四大核心功能**\n\n“袁稻思源”平台构建四大核心功能模块，形成完整的智能育种知识和能力。\n\n数据资源库，将散落的育种数据统一“上牌”。目前平台收纳35570个水稻品种、689项性状、28648条基因数据和624757篇中英文文献。不育系按光敏、温敏、光温敏等维度精细分类，支持育种专种家像检索商品一样，快速定位目标种质。该数据资源库是“袁稻思源”平台的核心底座。\n\n基于资源库建立图谱，让品种、基因、文献等彼此“建联”。品种图谱勾画出每个品种的选育谱系和材料关系，基因图谱把基因、性状、品种与文献证据编织成一张可推理的网络。例如输入Y58S，系统可直接呈现该品种的千粒重、抗病性及相关基因。\n\n智能问答“小稻”，作为育种专家的对话式检索入口。专业科研人员只需自然语言，也可向平台提出专业问题，系统从文献和真实数据中生成答案，每条结论都标明来源，不凭空编造。在发布会现场，专家提问“第三代杂交水稻产业化有哪些障碍”，“小稻”当即从监管、生物安全、成本、知识产权等维度给出专业分析，并提示品种审定前需补充哪些数据。\n\n最后一个能力模块是育种智能体。品种审定智能体可根据品种性状，帮助科研人员预判审定通过率，杂交配组智能体可基于基因型数据预测候选组合的表现。育种家从“翻资料猜结果”变成“让AI算概率”，大幅提升工作效率。\n\n湖南省农科院副院长李莉现场演示了平台在育种资源查询、品种系谱呈现、基因关联展示等方面的能力，一套组合下来，育种专家从“盲试”变成“有据可依”。目前，平台已在第三代杂交水稻育种中开展应用示范，取得良好成效。\n\n**专家视角：这场变革会改变什么**\n\n平台发布当天，中国工程院院士、湖南省农科院党委书记柏连阳直言，“拥抱人工智能，是今天科研人员的必答题”。平台目前虽为初级版本，但已迈出AI赋能杂交水稻育种关键而可喜的一步。\n\n中国科学院院士、崖州湾国家实验室主任李家洋的判断更为前瞻：当前全球种业竞争加剧，育种正从“经验驱动”转向“数据驱动、设计育种”，“谁率先突破智能育种，谁就赢得下一轮农业产业革命的主动”。李家洋建议，平台可强化智能决策、深化协同创新、坚持服务产业，最终建设成为面向全国乃至全球的水稻智能育种公共产品。\n\n据中科闻歌方面表示，“袁稻思源”是决策智能第一次系统嵌入国家粮食安全的核心环节。从金融到政务，再到农业科研，AI行业正在把“数据决策”能力，嵌入更多关乎国计民生的领域。对育种行业而言，当AI助力科研人员更快、更准地“排雷”和“选路”，中国水稻育种的效率天花板或许才刚刚被打开。（心月）","环球网 今日头条 2026 年 10 月 13 日",{"impact":454,"substance":455,"depth":89,"authority":19,"freshness":21,"relevant":22,"comment":456},26,23,"业界首个杂交水稻智能育种平台落地湖南，数据规模与AI决策功能具体，属种业数字化标志性进展，值得入选每日精选。",[458],{"name":452,"url":449},[28,29,460,172,461],"种业振兴","杂交水稻",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":465},{"candidates":466,"agricultural_evidence":48},[467,471,475,479,483],{"code":33,"score":47,"supported":48,"title":468,"abstract":469,"tags":470},[35],[35],[461],{"code":136,"score":22,"supported":14,"title":472,"abstract":473,"tags":474},[],[],[460],{"code":201,"score":22,"supported":14,"title":476,"abstract":477,"tags":478},[],[],[172],{"code":46,"score":22,"supported":14,"title":480,"abstract":481,"tags":482},[],[],[28],{"code":63,"score":22,"supported":14,"title":484,"abstract":485,"tags":486},[],[],[29],[488,489],"袁稻思源 杂交水稻 智能育种平台","湖南省农科院 中科闻歌 智能育种","袁稻思源杂交水稻智能育种平台-4950","2026-10-15T00:06:02.857637Z"]