[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2974":3,"related-2974":80},{"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":75,"slug":78,"view_count":54,"doi":8,"paper":8,"created_at":79},2974,"人民日报海外版：神农大模型3.0+36个专项智能体 服务全国超10万农户","https:\u002F\u002Fnews.cau.edu.cn\u002Fmtndnew\u002Fcbf7a6637ffd4fffb20e26993670895d.htm","中国农业大学王耀君团队2023年12月发布神农大模型1.0版、2024年7月推出2.0版新增多模态识别、2025年10月升级至3.0版采用\"轻量化+多智能体\"架构同时推出36个针对具体农事问题的智能体。神农大模型已构建覆盖90%农业学科、80%农业场景的专属知识体系，核心知识库含1000万条农业知识图谱、2000万张标注图片、5000万条生产数据。辽宁杜连辉600亩玉米地使用后成本从480元\u002F亩降到不足400元\u002F亩，北京怀柔丹辉农业生菜基地育种智能体培育\"雁栖2号\"新品种。",null,"**李晨**\n\n“近几年人工智能底层技术和应用场景发展很快，在农业上已经出现由‘人工智能+智能机械+大模型+规模化生产’集成的无人工厂、智慧农业生产方式。现在我国部分地区，这类技术已经从示范阶段转向了一些大型新型经营主体的主要生产方案。”9月16日，中国工程院院士、中国农业大学教授孙其信在2026世界农业科技创新大会（WAFI）上接受媒体采访时指出，当前全球已形成共识，未来一次重大产业变革可能以新一代人工智能技术为重要引擎，农业同样如此。人工智能引导下一轮农业生产方式变革，已经不是一个梦想，而是变成了现实。\n\n![Image 1](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002Fb8dbe90d2f9144beb4ace03f32463a25.jpg)\n\n孙其信接受媒体采访。中国农大供图\n\n孙其信指出，智能育种可视为第四代育种技术方向——用智能体和大模型训练，承接过去依靠育种家下地、拿尺子、记本子的部分工作。\n\n以小麦为例，中国农业大学相关团队正在研发人工智能小麦大模型。首先是积累田间数据，用无人机、地面多光谱设备记录作物从出苗到收获全过程，预计三五年后大宗粮食和畜禽的基础数据可满足智能育种模型需要。\n\n其次是积累基因数据，随着测序技术的快速发展，现在获取小麦高质量基因组信息的成本大幅降低，效率也显著提升。\n\n然后用人工智能关联田间表型与基因信息，例如输入地块表现可推测基因、输入基因可预测田间表现，从而大部分替代育种家从成千上万个体中筛选少数优良材料的工作，效率提升几十到几百倍。\n\n孙其信还提到地下根系识别。他说，根系在地下，过去育种后期才知道产量和品质，现在用新设备加人工智能算法，可测算每个品种的根系构型，设计少施肥、抗干旱、高产的根型。他对其规模化应用给出了保守判断：部分专项小模型已经起步，整体5到10年可看到大规模应用，真正在田间替代多数人工筛选还需要约5年数据积累。\n\n如今，中国农业在人工智能方面的实践越来越多的与国际接轨。孙其信介绍，去年WAFI发布中国农业大学神农大模型，盖茨基金会曾将该模型与世界一流模型对比，其在农业问题解决方案方面位居参评模型首位。\n\n中国农大团队开发了服务于非洲农业的“神农ZAO”智能体，并首先落地肯尼亚——用肯尼亚当地语言提问，模型输出适应当地农业生产的技术方案，而不是直接套用中国方案。“ZAO”在肯尼亚当地语言斯瓦西里语是种植管理的意思。\n\n孙其信说，世界需要这样一个平台，WAFI的目标不是一年开一次会，而是持续聚合全球顶尖科技资源、研发机构、投资金融机构和农业企业，产生“乘法效应”，服务中国农业发展，也服务全球农食系统绿色健康转型。\n\n[科学网2026年9月19日](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571737.shtm)","中国农业大学·人民日报海外版","2026-09-18T01:00:00Z","报道",10,false,84,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},24,20,17,15,8,1,"院士在WAFI大会披露神农大模型3.0与智能育种进展，权威性与信息增量俱佳，值得进入每日精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","农业大模型","神农大模型","智能育种",{"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},[45,52,59,65,70],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},14,true,[49],"大模型",[49],[28,29,30],{"code":53,"score":54,"supported":47,"title":55,"abstract":56,"tags":58},"A3",3,[],[57],"玉米",[],{"code":60,"score":54,"supported":47,"title":61,"abstract":62,"tags":64},"B1",[],[63],"生菜",[],{"code":66,"score":22,"supported":14,"title":67,"abstract":68,"tags":69},"F2",[],[],[31],{"code":71,"score":22,"supported":14,"title":72,"abstract":73,"tags":74},"I1",[],[],[27],[76,77],"神农大模型 智能体 农户","中国农业大学 智能育种 小麦","神农大模型智能体农户-2974","2026-09-20T00:03:00.349769Z",{"total":81,"page":22,"page_size":81,"items":82},6,[83,128,166,230,327,368],{"id":84,"title":85,"url":86,"summary":87,"summary_zh":8,"content":8,"source_name":88,"source_url":8,"published_at":89,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":90,"sources":95,"tags":97,"primary_topic":99,"secondary_topics":100,"classification":101,"search_phrases":122,"slug":125,"view_count":126,"doi":8,"paper":8,"created_at":127},5331,"农民日报报道 WAFI 2026:AI 为农业注入新动能 推动智能育种精准种植全产业链转型","https:\u002F\u002Fszb.farmer.com.cn\u002Fnmrb\u002Fhtml\u002F2026\u002F20261014\u002F20261014_8\u002Fnmrb_20261014_13425_8_2110120867111473164.html","2026 世界农业科技创新大会(WAFI)在北京举行,中国农业大学校长陈卫表示 AI 正在推动智能育种、精准种植和全产业链转型,小农户迎来手机端病虫害预警、本地化气象预警等新机会。中国农业大学王耀君宣布在肯尼亚发布神农大模型,针对 250 个肯尼亚问题通用大语言模型准确率 70%、神农达 96%、平均成本仅 0.1 美分。盖茨基金会高级项目官斯图尔特·科里斯认为 AI 农技咨询有望在亚非 7 个重点地区触达 4200 万农户,每年带来超 30 亿美元收益。北大荒 2025 年粮食产量达 463 亿斤,数字农服平台服务60 万种植户。","农民日报 2026-10-14","2026-10-14T00:00:00Z",{"impact":91,"substance":92,"depth":19,"authority":46,"freshness":93,"relevant":22,"comment":94},26,22,5,"世界农业科技创新大会的权威报道，含神农大模型海外发布、AI农技咨询覆盖数据等实质增量，产业级影响，值得精选。",[96],{"name":88,"url":86},[27,28,30,31,98],"数字农服",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":102},{"candidates":103,"agricultural_evidence":47},[104,108,114,118],{"code":33,"score":93,"supported":47,"title":105,"abstract":106,"tags":107},[],[49],[28,30],{"code":109,"score":54,"supported":47,"title":110,"abstract":111,"tags":113},"G2",[],[112],"小农户",[],{"code":66,"score":22,"supported":14,"title":115,"abstract":116,"tags":117},[],[],[31],{"code":71,"score":22,"supported":14,"title":119,"abstract":120,"tags":121},[],[],[27],[123,124],"神农大模型 肯尼亚","WAFI 2026 中国农业大学","神农大模型肯尼亚-5331",0,"2026-10-20T02:47:36.680168Z",{"id":129,"title":130,"url":131,"summary":132,"summary_zh":8,"content":133,"source_name":134,"source_url":8,"published_at":135,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":136,"score_detail":137,"sources":140,"tags":142,"primary_topic":144,"secondary_topics":145,"classification":146,"search_phrases":161,"slug":164,"view_count":54,"doi":8,"paper":8,"created_at":165},2729,"WAFI2026世界农业科技创新大会在京举行——辽宁省农科院等亮相","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7686105927610630691\u002F","2026世界农业科技创新大会(WAFI2026)9月16—19日在北京平谷举行。中国农业大学校长孙其信指出,人工智能已经从过去的示范,变成了部分大型新型经营主体的主要生产方式。中国农业大学王耀君副教授介绍神农大模型3.0已在非洲落地。北京数智京园智慧设施管控技术体系亮相。","潮新闻 记者 沈爱群 侴雪妍\n\n2026世界农业科技创新大会，正在北京举行。\n\n9月16日上午，在大会举行的“人工智能与农业论坛”上，潮新闻记者捕捉到了一个话题：人工智能如何造福农民？\n\n这个话题，由中国农业大学全球食物经济与政策研究院院长樊胜根教授在论坛致辞中提出。\n\n会上，与会国内外专家学者、业界代表见仁见智给出了答案：通过农业人工智能，可以让农民种得好、种得起、种得稳、种得赚。其中，深谙东方智慧的“中国方案”得到了与会嘉宾的点赞与关注。\n\n世界农业科技创新大会（英文缩写WAFI），是以“创新农业 共享未来”为宗旨的世界农业盛会，致力于打造农业“达沃斯”。自2023年成功举办以来，WAFI赢得了国内外同行的高度认可，被誉为世界三大农业盛会之一。\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F59a79b9b009545259d6d2d50486c2167~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790208715&x-signature=Mbp32uTVtyQxX7rWipDc9RKtXnU%3D)\n活动现场（记者 沈爱群 摄）\n\n在这个世界级农业盛会上，与会嘉宾为何特别关注“人工智能与农民”？\n\n答案，可以从人工智能时代全球农民、小农户面临的挑战找到。\n\n农业人工智能论坛上，中国农业大学校长、中国工程院院士陈卫就谈到：当前全球农食系统面临前所未有的挑战，气候变化加剧了农业生产的风险，土地、水资源和生物多样性承受着越来越大的压力。“我们必须生产更多更有营养的食物，降低农业对环境的影响，为农村地区创造更好的发展机会。然而这些挑战在不同地区的分布并不均衡，一端是资本和技术高度密集的现代化农场，另一边是数以亿计、以有限的资源支撑全球重要粮食供给的农民与小农户。”\n\n挑战面前，人工智能为农业转型注入了新动能。正如与会嘉宾在本次论坛上提及，人工智能正在推动智能育种、精准种植和农业生产全产业链系统发生新的变化，以卫星遥感数据、气象预警数据、土壤变化数据、种子种植数据以及营销数据分析等，帮助农民实现种植方案自动生成、无人机出苗率检测、卫星遥感旱涝、摄像头自动巡田、智能拼车等农业生产及农事经营。\n\n推动这些新变化的“中国方案”中，有着力农业教育的中国高校，有从事农业生产的中国农业企业，也有站在消费端的中国城市设施农业。\n\n先看中国高校。会上，中国农业大学信息与电子工程学院副教授王耀君和中国农业大学全球食物经济与政策研究院教授张玉梅，分别在主旨演讲中提到了“神农大模型”以及“农业食物经济与政策AI模型”。\n\n神农大模型，去年就已做到了3.0版。作为国内首个实现农业系统智能的大模型，神农1.0版于2023年问世，可以实现农业专业知识的精准查询与问答。2024年迭代的神农2.0版，拓展了技术边界，可以整合文本、图像等多模态数据进行分析决策。2025年全球首发的神农3.0版，打破了农业学科壁垒，让AI成为汇聚农业智慧的载体。\n\n神农大模型3.0是“小麦育种智能助手”。它融合了国家级种质资源与专家知识，可以赋能育种决策，实现从“田间试错”到“精准育种”。\n\n神农3.0还是个农业病虫害智能体。可以识别70类、600余种病虫害，实现用一部手机就能获得如同多个专业植保专家的指导。\n\n值得一提的是，神农3.0还可以让全球农业科技人员和从业者自主构建，以最低成本推动AI应用，让农业AI在科研院所和田间地头普惠落地。“经过过去一年的推广，神农大模型已经跨越千山万水，在非洲落地了。”神农大模型团队负责人王耀君说。\n\n农业食物经济与政策AI模型，不仅面向政府、科研机构和企业，也面向广大农业生产者，旨在将数据、经济模型与人工智能相结合，为农业市场研判和科学决策提供支持。为此，张玉梅教授提醒：“对于农民和小农户来说，这个模型提供的国内外农产品价格监测与异常预警、农业生产成本收益分析、膳食营养评价和国际市场动态分析，可以帮助他们及时了解市场变化 、比较政策方案、评估生产经营收益与营养状况。”\n\n其次，看看农业企业端。会上，北大荒信息有限公司总经理任荣荣向大家介绍了“未来农场”这个各项农艺技术集成平台。以深耕智慧农业培育发展新动能为己任的北大荒信息有限公司，既自主研发了智能装备管理平台覆盖111个农场、接入8.4万台智能装备；也让“未来农场”为60万种植户提供产前、产中、产后服务，实现农业资金交易1000亿元。\n\n再看城市设施农业。会上，北京市数字农业农村促进中心副主任、正高级农艺师芦天罡，向大家展示了北京市“数智京园”智慧设施管控技术体系和连栋温室“赛马制”中试熟化场景。\n\n据芦天罡介绍，北京市目前正通过AI+城市设施农业，实现了连栋温室的国产化技术攻关和日光温室的数智场景改造，快速推动农业产业智能化。“从系统到装备到模型，人工智能可以帮助农户解放劳动力、提高精细化生产水平，还可以调节生产周期，助推农户增收。”芦天罡表示。\n\n“转载请注明出处”","今日头条 2026年9月16日","2026-09-16T00:00:00Z",78,{"impact":17,"substance":18,"depth":19,"authority":21,"freshness":138,"relevant":22,"comment":139},9,"世界级农业盛会现场报道，汇聚神农大模型3.0、未来农场、数智京园等多方实质进展，信息增量足，值得进入每日精选。",[141],{"name":134,"url":131},[27,28,143,30,31],"设施农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":147},{"candidates":148,"agricultural_evidence":47},[149,153,157],{"code":33,"score":93,"supported":47,"title":150,"abstract":151,"tags":152},[],[49],[28,30],{"code":66,"score":22,"supported":14,"title":154,"abstract":155,"tags":156},[],[],[31],{"code":71,"score":22,"supported":14,"title":158,"abstract":159,"tags":160},[],[],[27],[162,163],"农业人工智能 神农大模型 智慧农业 智能育种","农业人工智能 神农大模型","农业人工智能神农大模型智慧农业智能育种-2729","2026-09-17T00:04:39.330857Z",{"id":167,"title":168,"url":169,"summary":170,"summary_zh":171,"content":8,"source_name":172,"source_url":169,"published_at":173,"category":174,"cover_url":8,"hotness":13,"is_selected":14,"score":175,"score_detail":176,"sources":179,"tags":181,"primary_topic":184,"secondary_topics":185,"classification":186,"search_phrases":202,"slug":205,"view_count":126,"doi":206,"paper":207,"created_at":229},4695,"AgroNLP-SimAssist: a multilingual transformer-based decision support simulator for crop disease diagnosis, advisory generation, and market intelligence","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs12870-026-10040-8","Abstract There are three major shortcomings of agricultural NLP and need addressing, regardless of the recent developments in the field: (i) use of proprietary or small-scale datasets that affect reproducibility; (ii) one-task models that only focus on intent recognition but lack integration for crop disease diagnosis, advice, and market information; and (iii) the absence of simulators for evaluating the system’s performance during actual deployment. The application of precision agriculture is constrained by limitations in diverse farming environments. The study introduces AgroNLP-SimAssist, which represents a unified multilingual transformer architecture augmented by an easily deployable agricultural decision support simulator, as the proposed solution to overcome the challenges. The five major components constituting the proposed framework are: (1) domain-specific multilingual transformer embedding; (2) data collection and cleaning from publicly available agricultural datasets; (3) multiple prediction tasks including trend price estimation, crop disease detection, and advisory recommendation; (4) SHAP value explainability for expert validation; and (5) advisory simulation engine for evaluating latency and scalability. Multilingually available data sources, which include multilingual agricultural reports from the FAO organization, crop-disease descriptions from the PlantVillage knowledge base, and price-market narratives from the Agmarknet website, have been used for training and validation purposes. Among the 3,200 multilingual farmer queries dataset (in English, Hindi, and Kannada), there was an assignment of 70%, 15%, and 15% to the training, validation, and testing sets, respectively. In terms of accuracy compared to the existing classifiers, results from experiments yielded 96.1% disease classification, 94.3% advisory relevance, and 92.7% named entity recognition with F1-measure. The simulation system scaled up to 10,000 concurrent users with an inference latency of 0.35 s\u002Fquery. The proposed data-driven AgroNLP-SimAssist framework facilitates extension services and precision agriculture through providing a scalable, reproducible, and interpretable solution for intelligent agricultural advisory systems.","尽管近年来农业自然语言处理（NLP）领域取得了进展，但仍存在三个主要不足亟需解决：(i) 使用专有或小规模数据集，影响可复现性；(ii) 单任务模型仅关注意图识别，缺乏对作物病害诊断、建议和市场信息的整合；(iii) 缺乏用于评估系统实际部署性能的模拟器。精准农业的应用受到多样化农业环境的限制。本研究提出了AgroNLP-SimAssist，一种统一的多语言Transformer架构，并辅以易于部署的农业决策支持模拟器，作为克服上述挑战的解决方案。该框架由五个主要组件构成：(1) 领域特定的多语言Transformer嵌入；(2) 从公开农业数据集中进行数据收集与清洗；(3) 多预测任务，包括趋势价格估计、作物病害检测和咨询推荐；(4) SHAP值可解释性用于专家验证；(5) 咨询模拟引擎用于评估延迟和可扩展性。多语言可用数据源已用于训练和验证，包括联合国粮农组织（FAO）的多语言农业报告、PlantVillage知识库的作物病害描述以及Agmarknet网站的价格市场叙述。在包含3200条多语言农民查询数据集（英语、印地语和卡纳达语）中，训练集、验证集和测试集的分配比例分别为70%、15%和15%。与现有分类器相比，实验结果显示病害分类准确率达96.1%，咨询相关性达94.3%，命名实体识别的F1值为92.7%。模拟系统可扩展至10000名并发用户，推理延迟为0.35秒\u002F查询。所提出的数据驱动AgroNLP-SimAssist框架通过为智能农业咨询系统提供可扩展、可复现且可解释的解决方案，促进了推广服务和精准农业的发展。","BMC Plant Biology","2026-10-10T00:00:00Z","论文",81,{"impact":177,"substance":92,"depth":177,"authority":46,"freshness":138,"relevant":22,"comment":178},18,"多语言农业大模型整合病害诊断、农技咨询与市场情报，数据规模与仿真验证扎实，对智慧农业信息化有参考价值。",[180],{"name":172,"url":169},[27,28,29,182,183],"农业决策支持","作物病害诊断",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":187},{"candidates":188,"agricultural_evidence":47},[189,195],{"code":33,"score":190,"supported":47,"title":191,"abstract":193,"tags":194},13,[192],"decision support",[192],[28,29],{"code":71,"score":196,"supported":47,"title":197,"abstract":198,"tags":201},7,[],[199,200],"精准农业","precision agriculture",[27],[203,204],"AgroNLP-SimAssist 作物病害诊断","多语言农业大模型 农业决策支持","AgroNLP-SimAssist作物病害诊断-4695","10.1186\u002Fs12870-026-10040-8",{"doi":206,"openalex_id":208,"authors":209,"venue":172,"cited_by_count":126,"oa_url":169,"card":222,"direction":226,"ingested_from":228},"W7221339938",[210,212,214,216,218,220],{"name":211,"orcid":8},"Priya Thirugnanam",{"name":213,"orcid":8},"Sandeep kumar Mathivanan",{"name":215,"orcid":8},"Sundara Kumar M R",{"name":217,"orcid":8},"Sangeetha Ramaswamy",{"name":219,"orcid":8},"Shruthi T S",{"name":221,"orcid":8},"Sangeetha S.K.B",{"tldr":223,"method":224,"finding":225,"direction":226,"opportunity":227},"提出多语言Transformer农业决策支持模拟器，统一实现作物病害诊断、农技建议与市场情报。","基于FAO、PlantVillage、Agmarknet多语数据训练Transf","病害分类96.1%、建议相关性94.3%、NER F1 92.7%，万级并发延迟0.35秒。","农业人工智能与决策模型","可扩展至更多语种与作物，并引入真实田间部署反馈闭环优化模拟器。","openalex","2026-10-11T23:30:56.064196Z",{"id":231,"title":232,"url":233,"summary":234,"summary_zh":235,"content":8,"source_name":236,"source_url":233,"published_at":173,"category":174,"cover_url":8,"hotness":13,"is_selected":14,"score":175,"score_detail":237,"sources":239,"tags":241,"primary_topic":244,"secondary_topics":245,"classification":257,"search_phrases":302,"slug":305,"view_count":306,"doi":307,"paper":308,"created_at":326},4656,"Artificial Intelligence, Foundation Models, and Digital Twins for Climate-Resilient Agriculture: A Review","https:\u002F\u002Fdoi.org\u002F10.54963\u002Fia.v2i2.103039","Climate change, increasing food demand, and resource constraints are accelerating the transition from conventional precision agriculture toward smart, autonomous, and climate-resilient agricultural systems. Artificial intelligence (AI), foundation models, digital twins (DTs), the Internet of Things (IoT), remote sensing, edge–cloud computing, and big data analytics are emerging as key technologies for data-driven agricultural management. This review critically evaluates recent advances in AI-driven intelligent agriculture, with emphasis on machine learning, deep learning, explainable AI (XAI), generative and agentic AI, multimodal foundation models, and digital twins, together with the sensing and computing infrastructures required for their deployment. Relevant literature was identified using keywords related to AI, foundation models, digital twins, IoT, precision agriculture, and climate-resilient agriculture, with emphasis on recent peer-reviewed studies addressing technological applications, performance, limitations, challenges, and future prospects. The selected literature was critically synthesized to identify technological trends, knowledge gaps, and emerging research opportunities. The review highlights that the greatest potential of intelligent agriculture lies in integrating heterogeneous data from sensors, UAVs (unmanned aerial vehicles), satellites, weather systems, field operations, and agricultural knowledge to support context-aware prediction, decision-making, and autonomous action. However, data quality, model generalizability, explainability, interoperability, cybersecurity, computational requirements, and large-scale field validation remain major challenges. This review further develops an integrated perspective connecting AI, foundation models, multimodal data infrastructures, digital twins, and autonomous agricultural systems within a unified cyber-physical ecosystem. Future priorities include trustworthy AI, agentic decision-making, semantic interoperability, federated learning, continuous learning, and self-learning digital twins toward Agriculture 6.0.","气候变化、粮食需求增长与资源约束正加速推动传统精准农业向智能、自主且气候适应型的农业系统转型。人工智能（AI）、基础模型、数字孪生（DT）、物联网（IoT）、遥感、边缘—云计算和大数据分析正成为数据驱动农业管理的关键技术。本综述批判性地评估了人工智能驱动智能农业的最新进展，重点关注机器学习、深度学习、可解释人工智能（XAI）、生成式与代理式人工智能、多模态基础模型和数字孪生，以及其部署所需的传感与计算基础设施。相关文献通过人工智能、基础模型、数字孪生、物联网、精准农业和气候适应型农业等关键词检索获得，重点纳入近期同行评审研究，涵盖技术应用、性能、局限性、挑战与未来前景。对所选文献进行了批判性综合，以识别技术趋势、知识空白和新兴研究机遇。本综述强调，智能农业的最大潜力在于整合来自传感器、无人机（UAV）、卫星、气象系统、田间作业和农业知识的异构数据，以支持情境感知预测、决策和自主行动。然而，数据质量、模型泛化能力、可解释性、互操作性、网络安全、计算需求和大规模田间验证仍是主要挑战。本综述进一步提出了一种整合视角，将人工智能、基础模型、多模态数据基础设施、数字孪生和自主农业系统连接于统一的网络物理生态系统中。未来优先方向包括可信人工智能、代理式决策、语义互操作性、联邦学习、持续学习以及面向农业6.0的自学习数字孪生。","Intelligent Agriculture",{"impact":92,"substance":18,"depth":177,"authority":190,"freshness":21,"relevant":22,"comment":238},"系统综述AI、基础模型与数字孪生在气候韧性农业中的集成路径与挑战，学术价值高，对智慧农业方向有较强参考意义。",[240],{"name":236,"url":233},[27,28,29,242,243],"数字孪生","气候韧性农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[246,252],{"code":247,"slug":248,"name":249,"path":250,"parent_code":251},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"code":253,"slug":254,"name":255,"path":256,"parent_code":37},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":40,"locked":14,"version":41,"method":42,"evidence":258},{"candidates":259,"agricultural_evidence":47},[260,270,275,282,289,296],{"code":33,"score":261,"supported":47,"title":262,"abstract":264,"tags":269},19,[263],"artificial intelligence",[265,266,267,268,263],"深度学习","机器学习","machine learning","deep learning",[28,29],{"code":71,"score":271,"supported":47,"title":272,"abstract":273,"tags":274},11,[],[199,242,200],[242,27],{"code":247,"score":13,"supported":47,"title":276,"abstract":277,"tags":281},[],[278,279,280],"气候变化","气候适应","climate change",[243],{"code":253,"score":138,"supported":47,"title":283,"abstract":284,"tags":288},[],[285,286,287],"物联网","internet of things","IoT",[],{"code":290,"score":81,"supported":47,"title":291,"abstract":292,"tags":295},"I3",[],[293,294],"遥感","remote sensing",[],{"code":297,"score":54,"supported":47,"title":298,"abstract":299,"tags":301},"A7",[],[300],"间作",[],[303,304],"农业基础模型 数字孪生","气候韧性农业 人工智能","农业基础模型数字孪生-4656",2,"10.54963\u002Fia.v2i2.103039",{"doi":307,"openalex_id":309,"authors":310,"venue":236,"cited_by_count":126,"oa_url":233,"card":320,"direction":325,"ingested_from":228},"W7221321372",[311,314,317],{"name":312,"orcid":313},"Krishan Kumar","https:\u002F\u002Forcid.org\u002F0009-0005-7569-4590",{"name":315,"orcid":316},"Annu Khatri","https:\u002F\u002Forcid.org\u002F0009-0000-3103-9520",{"name":318,"orcid":319},"Indu Shekhar Thakur","https:\u002F\u002Forcid.org\u002F0000-0003-2382-1218",{"tldr":321,"method":322,"finding":323,"direction":226,"opportunity":324},"综述AI、基础模型与数字孪生如何支撑气候韧性农业，并指出关键挑战与未来方向。","文献综述，聚焦机器学习、深度学习、可解释AI、多模态基础模型与数字孪生。","最大潜力在于融合多源异构数据实现情境感知预测与自主决策，但数据质量与可解释性等仍是瓶颈。","可探索可信AI、联邦学习与自学习数字孪生在真实农田的规模化验证与语义互操作。","智慧农业 \u002F 农业物联网","2026-10-11T23:30:07.465569Z",{"id":328,"title":329,"url":330,"summary":331,"summary_zh":8,"content":332,"source_name":333,"source_url":8,"published_at":334,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":335,"score_detail":336,"sources":339,"tags":341,"primary_topic":344,"secondary_topics":345,"classification":346,"search_phrases":363,"slug":366,"view_count":306,"doi":8,"paper":8,"created_at":367},4615,"杭州诚邀全市创新力量共筑智慧农业——启动人工智能+农业应用场景征集","https:\u002F\u002Fwww.hangzhou.gov.cn\u002Fcol\u002Fcol812262\u002Fart\u002F2026\u002Fart_61fd9b1bd08e4756a87e25e3f296e645.html","根据《杭州市大力发展智慧农业打造人工智能+农业创新实践高地实施方案(2026—2030年)》部署,杭州启动人工智能+农业应用场景征集,聚焦农业大模型和智能体、智能农业设施装备、智慧管理服务平台三大方向。场景要求具备合规性、创新性、实效性、示范性、开放性,优先支持向中小企业、民营企业开放测试应用合作;入选场景将有机会在第二十三届中国国际农产品交易会智慧农业展区专题展示。","杭州智慧农业正呼唤更多“最强大脑”——根据《杭州市大力发展智慧农业 打造“人工智能+农业”创新实践高地实施方案（2026—2030年）》部署，杭州日前已启动“人工智能+农业”应用场景征集，面向全市发出“英雄帖”。\n\n本次征集聚焦三大方向：农业大模型和智能体，包括生物育种、生产管理、病虫害监测、疫病防治、产量预测，以及病虫害智能诊断、农事决策支持、智能植保作业规划、农情问答、农业知识智能检索等；智能农业设施装备，包括智能农机、无人驾驶作业、智能采摘、精准施肥施药、水肥一体化智能控制、物联网感知、卫星遥感与无人机监测等；智慧管理服务平台，覆盖智慧种植、智慧畜牧、智慧渔业和综合管理服务，如植物工厂、智慧大田、智慧茶园果园、畜禽体征监测、精准饲喂、疫病AI辅助诊断、陆基工厂化养殖、质量安全溯源、乡村数字治理等。\n\n场景要“上榜”，需满足合规性、创新性、实效性、示范性和开放性。比如，场景建设要符合国家、省相关产业政策、安全规范和行业标准；依托人工智能核心技术，具备技术创新、模式创新或应用创新；已落地或具备明确落地计划，能解决行业痛点、治理难点、民生堵点，降本增效成效可量化、可验证；具备较强的复制性、推广性和通用性；优先支持向中小企业、民营企业开放测试、应用、合作的场景项目。\n\n征集主体须为在杭州市注册或主要应用场景在杭州的企事业单位、科研院所、高等院校、新型农业经营主体、农业社会化服务组织等。可单一报送，也可联合报送，联合报送须明确1家牵头单位，参与单位原则上不超过5家。有意向的主体可先向所在区、县（市）农业农村部门提交材料，经区、县（市）初审推荐，由市级组织专家开展路演，确定首批应用场景名单。","杭州市政府门户网站 2026-10-09","2026-10-09T00:00:00Z",72,{"impact":337,"substance":18,"depth":20,"authority":190,"freshness":21,"relevant":22,"comment":338},16,"地市级政策落地动作，条款与征集方向具体，具备行业示范与可复制价值，值得进入每日精选。",[340],{"name":333,"url":330},[27,28,29,342,343],"智能农机","应用场景征集",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":347},{"candidates":348,"agricultural_evidence":47},[349,354,358],{"code":71,"score":350,"supported":47,"title":351,"abstract":352,"tags":353},12,[27],[27],[27],{"code":33,"score":93,"supported":47,"title":355,"abstract":356,"tags":357},[],[49],[28,29],{"code":359,"score":22,"supported":14,"title":360,"abstract":361,"tags":362},"F5",[],[],[342],[364,365],"杭州 人工智能 应用场景征集","杭州 智慧农业 实施方案","杭州人工智能应用场景征集-4615","2026-10-11T00:09:35.817480Z",{"id":369,"title":370,"url":371,"summary":372,"summary_zh":8,"content":373,"source_name":374,"source_url":8,"published_at":375,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":376,"score_detail":377,"sources":380,"tags":382,"primary_topic":385,"secondary_topics":389,"classification":391,"search_phrases":413,"slug":416,"view_count":93,"doi":8,"paper":8,"created_at":417},4464,"山东省农科院发布舜耕粮安农业遥感大模型 精度95%效率提升超100%","http:\u002F\u002Fwww.md2we.com\u002Fitems\u002F4263","山东省农科院发布舜耕粮安农业遥感大模型，基于20年来积累的2000万份人工样本的海量数据，覆盖山东全域全地貌、全物候周期，构建耕地智能提取—肥力墒情预测—作物精准识别—长势动态监测—病虫草害预警—作物智能估产全链条智能监测体系，精度高达95%，效率提升超100%；山东启动40个实数融合数字农业发展县建设，培育智慧农业应用场景近1000个。","每日热点 大众新闻 2026-10-04·10月4日 · 周日 报道\n\n阅读 0\n\nAI 评分\n\n精选\n\n影响力 24\n\n信息增量 22\n\n专业深度 18\n\n信源权威 10\n\n时效性 8\n\n省级“人工智能+农业”行动部署叠加舜耕·粮安遥感大模型95%精度等实质数据，信息增量与专业深度俱佳，值得进入每日精选。\n\n摘要\n\n山东省农科院发布舜耕粮安农业遥感大模型，基于20年2000万份人工样本，覆盖山东全域全地貌全物候周期，构建耕地智能提取-肥力墒情预测-作物精准识别-长势动态监测-病虫草害预警-作物智能估产全链条智能监测体系，精度95%、效率提升超100%。山东启动40个实数融合数字农业发展县建设，培育智慧农业应用场景近1000个。\n\n文 全文\n\n### 山东实施“人工智能+农业”行动：数据“种”进泥土，云端守护丰收\n\n2026-10-06 02:39:49\n\n![Image 1: Image 1](https:\u002F\u002Fwsrv.nl\u002F?url=https%3A%2F%2Fappimg.dzwww.com%2Fshare%2F2026%2F08%2F02%2Ff9c9a29336dd947_750.JPEG)\n\n麦田上空，无人机低空掠过，哪片麦苗缺氮、哪处有蚜虫，屏幕上即时标红；大棚内，人工智能（AI）算法值守，缺水、缺肥时，系统立刻报警；分拣车间里，AI视觉系统每秒“端详”上百颗苹果，按色泽、果径、瑕疵精准分级，误判率不到百分之一……\n\n从“靠天吃饭”到“知天而作”，当前人工智能正成为助力农业稳产提质、带动农民增收致富的“好帮手”，为农业农村现代化提供全新范式。\n\n2026年中央一号文件明确提出“因地制宜发展农业新质生产力，促进人工智能与农业发展相结合”，将AI技术从单点应用升级为贯穿农业全产业链的战略引擎。多家行业机构预测，2026年中国智慧农业市场规模将突破1340亿元，年复合增长率保持在15%以上。\n\n刚刚召开的省委十二届十一次全会，着眼把农业建成现代化大产业，推动农业数智化转型升级，明确提出实施“人工智能+农业”行动。何谓“人工智能+农业”？简言之，就是以人工智能技术为核心，驱动传统农业向智能化、高效化转型的新型生产体系。与会同志认为，从更深层次看，“人工智能+农业”不是简单的技术叠加，而是农业生产方式、组织形式和价值链条的系统性重塑。\n\n**AI种地，田野阡陌释放出更多可能**\n\n技术的生命力在于解决实际问题。放眼全国，农业面临着劳动力老龄化、气候变化风险加剧等压力，也存在特色产业附加值低、品牌力不强等问题。人工智能的介入推动农业从“靠经验”转向“靠数据”，为端牢“中国饭碗”、塑强农业产业注入确定性。在不少人看来，人工智能的应用推广，恰逢其时。\n\n“山东是农业大省，也是农业产业化发源地，产业规模大、业态全，生产者队伍素质高、接受新事物能力强。与此同时，山东工业基础雄厚，人工智能技术发展迅速。新技术在农业方面的转化推广具有显著的成本和效率优势。”省委党校（山东行政学院）教授、山东乡村振兴研究院院长刘岳认为，山东有着发展“人工智能+农业”的坚实基础，在完整的产业体系、可观市场规模、丰富应用场景等优势加持下，田野阡陌将释放出更多可能。\n\n夏日的鲁北平原，玉米拔节生长，一片生机盎然。在齐河县金穗粮食种植专业合作社的示范田里，一套黑色管网发挥着大作用。“这是我们铺设的水肥一体化设施。每30厘米有一个出水孔，能精准滴灌到玉米根底部位置。相比大水漫灌，它的灌溉速度快3倍，可省水30%，一人一天能管理200亩地。”合作社理事长袁本刚说。依托大数据平台，合作社还可在“云端”实施全程监管，动动手指就能依据检测数据制订分地块水肥管理方案，为各村玉米田定制个性化基肥配方，同步开展测土配方、作物叶绿素检测等服务。\n\n今年山东夏粮逆势丰收，连续4年实现面积、单产、总产“三增”，这离不开水肥一体化技术在大田的推广。数据显示，2025年，全省应用水肥一体化技术的粮油作物面积已达到630万亩。“水肥一体化与减垄增地、‘大小行’密植等结合，加速了良种、良法、良机、良田深度融合，有效提升了农田规模化、标准化种植水平。”袁本刚体会深切，水肥一体化的落地，让丰收有了更充实的底气。\n\n![Image 2: Image 2](https:\u002F\u002Fwsrv.nl\u002F?url=https%3A%2F%2Fappimg.dzwww.com%2Fshare%2F2026%2F08%2F02%2Ff9c9a2a30f6bab0_750.JPEG)\n\n种子是农业的“芯片”，也是保障粮食安全的关键，智能育种已成为育种科研人员聚焦的热点领域。\n\n今年4月，由中国农业科学院作物科学研究所与山东极智生物科技有限公司联合研发的“iWheat小麦智能设计育种平台”发布。对青岛农业大学小麦遗传育种团队来说，iWheat的应用正在帮助其攻克小麦育种“周期长、效率低、成本高”等行业难题。\n\n这一平台整合3万余份小麦种质资源的基因型、442个功能基因、6000余个功能位点及40余万条表型数据，为每一份种质建立起“数字身份证”，实现资源的精准检索与高效利用。“结合快速繁育体系，能将传统8年的育种周期压缩2至3年。”团队负责人张玉梅说，加速新品种的培育进程、降低育种成本，意味着更能提升整个种业行业的创新能力和竞争力，进而赋能小麦产业链上下游实现高质量发展。\n\n**让“技术盆景”真正落地为“产业风景”**\n\n农业大模型能够整合气象、土壤、作物生长等多维度数据，显著提升农业生产的精准性和预见性。我省明确，要加强农业大模型与人工智能体落地应用。\n\n在“中国蔬菜之乡”寿光，蔬菜大棚迎来了一批特殊“员工”。一群脚步灵活的机器狗，沿着田垄灵活穿梭，搭载的高清摄像头与传感器如同“火眼金睛”，精准识别病虫害迹象。巡检结束，数据实时传回后台，人工智能模型迅速给出种植决策。如今，寿光新建大棚已迭代升级至第七代智能物联网“云棚”，物联网应用率超过85%，劳动生产效率较以往翻倍。\n\n![Image 3: Image 3](https:\u002F\u002Fwsrv.nl\u002F?url=https%3A%2F%2Fappimg.dzwww.com%2Fshare%2F2026%2F08%2F02%2Ff9c9a2a2155c1ff_750.JPEG)\n\n就在一个多月前，省农科院发布“舜耕·粮安”农业遥感大模型。省农科院党委书记梁金光介绍，该模型基于20年来积累的2000万份人工样本的海量数据，覆盖山东全域全地貌、全物候周期，构建起“耕地智能提取—肥力墒情预测—作物精准识别—长势动态监测—病虫草害预警—作物智能估产”全链条智能监测体系，精度高达95%，效率提升超100%。\n\n在中游加工环节，大模型也能有效提升产品附加值与标准化水平。在烟台莱山区，由浪潮云洲旗下数农云（山东）信息科技有限公司联合中国农业大学计算中心、烟台葡乡农业开发有限公司共同打造的“莱山葡萄种植和酿造大模型”，一方面在种植端自动生成气候适应性调控方案，实现水肥精准配施、病虫害智能预警与防治，葡萄产量与品质同步提升；另一方面在酿造端用AI模拟发酵、陈酿全过程，动态优化关键参数，完成原料分级、发酵控制和酒体风味数字化建模。以此，让每一批葡萄酒的口感更稳定、品质更可控。\n\n当然，让人工智能与广袤乡村实现更深层次的双向赋能，还有很长的路要走——\n\n一套AI系统，传感终端、边缘计算、决策模型全算上，初始投入比较大。普通农户能不能用得起、用得好？\n\n农业生产周期长、环境复杂、区域差异大，怎样才能收集利用一批高质量农业数据，推动AI模型迭代？\n\n下沉到村、懂技术懂农业的青年人才较为短缺，农业人工智能技术人才怎样引育？\n\n让“技术盆景”真正落地为“产业风景”，刘岳认为，关键是鼓励龙头企业、高校院所与新型农业经营主体协同攻关，围绕粮食、果蔬、畜牧、水产等优势产业，打造一批“听得懂农事、算得清账本、管得了全程”的行业大模型。\n\n此外，刘岳还建议，要更加重视构建与农村新质生产力相适应的农村新型生产关系，盘活整合农村各类资产资源，为充分发挥数字化、智能化技术进步作用提供保障。“推动农村数字化从‘局域网’向‘互联网’转化，要破除长期存在的‘信息孤岛’，构建乡村振兴的数据底座。”\n\n（大众新闻记者 于新悦 刘兵）\n\n免责声明：以上数据来源于天眼查等平台，相关内容仅为传递更多信息之目的，不代表本网观点，亦不代表本网站赞同其观点或证实其内容的真实性。如有侵权请联系0531-85193563。  \n 本文来源：大众新闻·大众日报\n\n查看更多\n\n相关检索","大众新闻 2026-10-06","2026-10-06T00:00:00Z",76,{"impact":92,"substance":378,"depth":19,"authority":13,"freshness":81,"relevant":22,"comment":379},21,"省级农科院发布农业遥感大模型，含95%精度、2000万份样本等实质数据，信息增量与专业深度俱佳，值得进入每日精选。",[381],{"name":374,"url":371},[383,27,28,29,384],"数字乡村","遥感大模型",{"code":290,"slug":386,"name":387,"path":388,"parent_code":37},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[390],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":392},{"candidates":393,"agricultural_evidence":47},[394,399,403,408],{"code":290,"score":46,"supported":47,"title":395,"abstract":396,"tags":398},[293],[293,397],"估产",[],{"code":33,"score":190,"supported":47,"title":400,"abstract":401,"tags":402},[49],[49],[28,29],{"code":71,"score":196,"supported":47,"title":404,"abstract":405,"tags":407},[],[27,406],"数字农业",[27],{"code":409,"score":22,"supported":14,"title":410,"abstract":411,"tags":412},"I6",[],[],[383],[414,415],"山东省农科院 舜耕粮安 遥感大模型","舜耕粮安 农业遥感 精度95%","山东省农科院舜耕粮安遥感大模型-4464","2026-10-09T00:04:56.436776Z"]