[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3326":3,"related-3326":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":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":8,"paper":36,"created_at":45},3326,"Research on the Application of Agricultural Big Data in Plant Growth Prediction——基于多源数据同化与混合智能（MDA-HI）框架","https:\u002F\u002Fwww.icck.org\u002Ffilebob\u002Fuploads\u002Fstorage\u002FDIA_ANrbHOHS4uBBpnVQ6.pdf","《Digital Intelligence in Agriculture》2026年第2卷第2期。Wei Yongqiang等提出Multi-source Data Assimilation and Hybrid Intelligence（MDA-HI）框架，将基于过程的作物模型与集成机器学习算法（包括基于Transformer的架构和物理信息神经网络）相结合。在2023—2025年中国多生态区主要作物（水稻、小麦、玉米、番茄）的实证验证中：MDA-HI模型实现了产量预测RMSE平均减少42.7%、关键物候期预测减少38.1%。水稻-小麦轮作系统大规模案例研究显示数据驱动处方可将氮肥使用减少22.5%、灌溉水减少18.3%，同时产量增加5.1%。",null,"《Digital Intelligence in Agriculture》2026; 2(2):54-67","2026-09-17T00:00:00Z","论文",10,false,85,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},22,24,19,14,6,1,"多源数据同化与混合智能框架在四大作物上验证，减肥节水增产数据扎实，方法新颖且具产业推广价值。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","精准施肥","农业大数据","作物生长预测",[32,33],"MDA-HI 多源数据同化 作物模型","水稻小麦轮作 氮肥减量 产量预测","MDA-HI多源数据同化作物模型-3326",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MDA-HI框架，融合过程模型与混合智能，用于作物生长与产量预测。","多源数据同化结合Transformer与物理信息神经网络，在中国多生态区验证。","产量预测RMSE降42.7%，氮肥减22.5%、灌溉水减18.3%，产量增5.1%。","农业人工智能与决策模型","可探索轻量化MDA-HI在边缘设备部署及跨区域迁移能力，降低小农户应用门槛。","agent","2026-09-24T00:04:02.947080Z",{"total":20,"page":21,"page_size":20,"items":47},[48,72,118,169,206,240],{"id":49,"title":50,"url":51,"summary":52,"summary_zh":8,"content":53,"source_name":54,"source_url":8,"published_at":55,"category":56,"cover_url":8,"hotness":12,"is_selected":13,"score":57,"score_detail":58,"sources":62,"tags":64,"search_phrases":67,"slug":70,"view_count":35,"doi":8,"paper":8,"created_at":71},3224,"刘永红：人工智能应用时不我待，以数智科技引领四川农业农村现代化——四川农科院将建设农业大数据中心破解农业AI数据难题","https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7979522","9-19 川观新闻报道：四川省农业科学院党委书记、院长刘永红在2026天府国际种业展暨第六届\"藏粮于技\"院士专家大讲堂上接受专访。\"人工智能在农业科技创新中有两大核心落地载体和应用方向。首要载体是智能农机，能够把数字化、智能化技术真正用到田间地头。另一大核心方向是生产方式与生产技术的智能化升级，相较于通用大模型，贴合具体作物、具体产业、具体生产环节的细分小模型更适配农业生产实际。\"刘永红坦言，农业AI发展滞后于工业，核心痛点是数据分散、采集困难，省农科院已明确系统性推进路径：搭建省级农业大数据中心；以AI变革农业科研范式；设立\"青年科学家工作室\"配套专项资金扶持科研。","[![Image 1](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250922\u002F1758523866060089130.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_MQ==Q)[![Image 2](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20251016\u002F1760585508939077059.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzE2z)[![Image 3](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174766036254.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzEwz)[![Image 4](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174830074273.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA5z)[![Image 5](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174869099498.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA4z)[![Image 6](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174893016987.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA3z)[![Image 7](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174711052611.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA2z)[![Image 8](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174796000290.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA1z)[![Image 9](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174778052174.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzA0z)[![Image 10](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250929\u002F1759129410912059070.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzAzz)[![Image 11](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174847056374.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzAyz)[![Image 12](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174907036931.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzAxz)[![Image 13](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174687068832.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_NzAwz)[![Image 14](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250917\u002F1758098174751023070.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_Njk5j)[![Image 15](https:\u002F\u002Fcbgccdn.thecover.cn\u002F@\u002Fimages\u002F20250922\u002F1758523866076055764.png)](https:\u002F\u002Fcbgc.scol.com.cn\u002Fmediachannel_Njk4j)\n\n[拍客作品上传](https:\u002F\u002Fcbgc.scol.com.cn\u002Fworks\u002FuploadWorks)[APP 下载川观新闻客户端(苹果、安卓) ![Image 16](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002FcbgcAPP.png) 下载川观新闻客户端(鸿蒙) ![Image 17](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fharmony-download.png) 建议使用浏览器扫码下载](javascript:void(0);)[微信 关注四川日报公众号 ![Image 18](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002FcbgcWX_new.jpg)](javascript:void(0);)\n\n举报\n\n[中央网信办违法和不良信息举报中心](http:\u002F\u002Fwww.12377.cn\u002F)[四川省互联网不良与违法信息举报中心](http:\u002F\u002Fwww.scjb.gov.cn\u002Findex.jsp)\n\n[川观新闻](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MQ==Q)[政声](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_LTY2Ng==T)[热评](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Njkyj)[思想](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NQ==Q)[问政](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_OQ==Q)[四川](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NA==A)[天下](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MjM=j)[鸽子花](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Njc0j)[川观号](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NTY2T)\n\n更多 \n\n\u003C\n\n[文化](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Ng==g)[智库](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Njk2j)[生活](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTA=T)[视觉](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_OA==A)[拍客](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NTg2T)[体育](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Njk=j)[旅游](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NTkxT)[双城记](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NTU3T)[专题](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MjU=j)[和美](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjAzj)[巩固脱贫成果](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NzU=z)[制造强省](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjIyj)[绵阳科技城](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjIzj)[天府新青年](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzM1z)[成都新区](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjAyj)[成都治理](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjAxj)[四川林草](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjI1j)[德阳政企通](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjI0j)[廉洁四川](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjYyj)[四川交通](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjYzj)[四川商务](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NjY0j)[巾帼四川](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Njcwj)[成都](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTE=T)[自贡](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTU=T)[攀枝花](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_Mjg=j)[泸州](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MjE=j)[德阳](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzM2z)[绵阳](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzM3z)[广元](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzM4z)[遂宁](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzI=z)[内江](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTI=T)[乐山](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_NTQ=T)[南充](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQwz)[宜宾](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQxz)[广安](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzIzz)[达州](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzE4z)[巴中](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQyz)[雅安](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzA1z)[眉山](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTM=T)[资阳](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MTY=T)[阿坝](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQzz)[甘孜](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQ0z)[凉山](https:\u002F\u002Fcbgc.scol.com.cn\u002Fchannel_MzQ1z)\n\n>\n\n>\n\n![Image 19](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fqrcode\u002Fnews\u002Fk5bFFKFvAItZhM91=7979522.jpg)\n\n扫码查看\n\n# 刘永红：人工智能应用时不我待，以数智科技引领四川农业农村现代化\n\n四川农村日报 2026-09-21 16:51\n\n四川农村日报\n\n2026-09-21 16:51\n\n![Image 20](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fai_reporter_avatar.png)\n全文播报\n\n该页面为预览地址，请勿公开转发。\n\n当前，人工智能正深刻重塑现代农业发展模式，成为农业科技创新的重要风口。针对人工智能在四川农业领域的应用价值、落地路径、现存短板以及省农科院相关布局成效，9月19日，四川省农业科学院党委书记、院长刘永红接受记者采访时表示，人工智能在农业领域的推广应用“等不起，也不能等”，必须加快推进，推动四川农业科研从“支撑产业”向“引领产业”转型升级。\n\n在刘永红看来，人工智能在农业科技创新中有两大核心落地载体和应用方向。首要载体是智能农机。“智能农机是人工智能算法、技术体系落地田间最好、最直接的承载平台，能够把数字化、智能化技术真正用到田间地头，是农业AI落地的基础支撑。”刘永红说。\n\n另一大核心方向是生产方式与生产技术的智能化升级。刘永红介绍，当前社会普遍关注通用大模型，但农业科研和一线应用更依赖“大模型+行业小模型”协同发力。相较于通用大模型，贴合具体作物、具体产业、具体生产环节的细分小模型，更适配农业生产实际。通过长期田间数据积累、生长过程建模、场景仿真模拟，能够智能研判田间情况，自动生成科学管理方案。\n\n据介绍，依托省级相关工作部署，省农科院已组建专家团队，在全省多个重点县域开展数字种业AI赋能试点工作。聚焦种业园区管理、灾害应急处置、田间技术配套、产量品质预判等关键环节，运用AI技术实现智能感知、快速反馈、精准施策，以数字赋能推动种业生产管理提质增效。\n\n在谈及四川农业人工智能发展的突出短板时，刘永红直指核心问题在于农业数据体系薄弱。他坦言，工业领域的人工智能应用成熟度远超农业，关键差距在数据。目前，四川农业数据呈现分散化、片段化特征，散落于各科研单位、市场主体、生产环节之间，缺乏统一汇交、整合与共享机制。同时，田间数据传感采集设备不足、采集方式传统、现代化布局滞后，导致农业可用数据量少、质量不高，无法有效支撑AI模型训练和智能决策，制约了农业人工智能落地见效。\n\n针对现存短板，省农科院已明确系统性推进路径，从数据基础、科研范式、科研基地三个维度全面发力。首先是搭建省级农业大数据中心，整合归集省农科院及全省农业科研系统的各类监测数据、试验数据、成果数据，实现数据统一管理、集中分析、高效利用，为农业人工智能研发应用筑牢基础底座。\n\n其次，是以AI变革农业科研范式。刘永红表示，传统农业科研高度依赖资深专家的经验积累，存在局限性。依托大数据中心，可整合以往科研成果、同行研究数据、各类试验数据，让科研人员能够精准摸清行业研究现状，快速找准创新发力点，实现从“经验科研”向“数字科研”转型。为适配新型科研模式，省农科院专门启动青年科学家工作室建设，专项赋能35岁以下青年科研团队，给予专项资金和平台支持，激活青年科创力量。\n\n最后，是推进科研基地现代化、智能化升级。刘永红认为，农业科研现代化必须走在农业生产现代化前面，不能出现“产业在升级、科研靠人工”的滞后局面。要全面升级科研基地设施设备，提升科研基地栽种、管护等环节的机械化、智能化水平，以现代化、智能化科研平台，保障农业科技创新先行一步。\n\n“农业现代化，关键是农业科技现代化。”刘永红表示，作为全省规模最大的省级农业科研单位，省农科院的定位不能止步于“支撑”农业农村现代化，更要主动引领农业农村现代化。下一步，该院将持续攻坚农业人工智能关键技术，补齐数据短板、迭代科研模式、升级科创平台，以数智化科技创新，持续赋能四川农业高质量发展和乡村全面振兴。\n\n记者 洪瑜 刘佳  \n四川农村日报全媒体出品\n\n**【未经授权，严禁转载！联系电话028-86968276】**\n\n![Image 21](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcopyright_74_32.png)\n\n![Image 22](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Finteraction_number.png)\n\n![Image 23](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Finteraction_comment.png)\n\n![Image 24](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fhistogram-logo.png)\n\n投票\n\n编辑：何璇 校对：刘佳 责编：王爱琳 审核：余普\n\n![Image 25](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fdetails_more_icon.png)\n\n[打开川观新闻，阅读全文](javascript:;)\n\n未经授权，严禁转载！\n\n如需转载，请私信小编，或致电：028-86968693 028-86968276\n\n转载须在正文开头显著位置注明稿件来源及作者，违者必究\n\n[川观新闻官方网址：https:\u002F\u002Fcbgc.scol.com.cn](https:\u002F\u002Fcbgc.scol.com.cn\u002F)\n\n扫描或长按关注川观新闻微信号(微信号:cbgc2014)\n\n![Image 26: 川观新闻二维码](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcopyright-qrcode.jpg)\n\n![Image 27](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcopyright_74_32.png)\n\n### 精彩评论 0\n\n查看更多评论\n\n我要评论\n\n![Image 28](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002FcbgcAPP.png)\n去APP中热议吧\n\n![Image 29](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002FcbgcAPP.png)\n去APP查看\n\n![Image 30](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fqrcode\u002Fnews\u002Fk5bFFKFvAItZhM91=7979522.jpg)\n去APP查看全文\n\n相关新闻\n\n热新闻\n\n[天](javascript:void(0);)[周](javascript:void(0);)[月](javascript:void(0);)\n\n[![Image 31](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-0ae08b42-806b-466b-8325-3d0db3077adb-1747298732623.jpeg)1 中秋到江安赴一场南瓜宴，坐乐至观光小火车漫游乡间丨川观号加新时刻 09.22](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F6094993)[![Image 32](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-53c8dd65-75fc-4b1b-98d8-65afa1e78749-1775807469164.jpeg)2 9月22日题库已更新，欢迎来战！](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7476454)[![Image 33](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-fc418db7-e3d1-46a8-b04f-1f0a82ba02f4-1789529514973.png)3 有氧运动第6课：4分钟燃脂操，带你甩掉多余脂肪 | 医起练 益健康](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7839670)[![Image 34](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-1c08995e-3bf7-4cd4-acd5-a473cf2d66d3-1790069064175.jpeg) 08:49 4 王晓晖在四川农业大学作形势政策报告时强调：勇担时代使命潜心治学育人，为推进四川农业农村现代化贡献更多力量](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7983466)[![Image 35](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-9ececf7c-9dcb-4809-b027-b4e36aa647cc-1790080084643.jpeg)5 第五届中国（四川）国际熊猫消费节在蓉启动 王晓晖施小琳出席](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7984762)[![Image 36](https:\u002F\u002Fcbgccdn.thecover.cn\u002F8711df6d-e0f4-43c5-a698-b83b8b3bb9e9_1790015801250?imageMogr2\u002Fgravity\u002FCenter\u002Fcrop\u002F527x395)6 铁翼破晓！歼-16夜训最新现场图→](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7981456)[![Image 37](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-f869c4c8-fc3b-460f-bef5-15cc5892fcd9-1790044797531.jpeg)7 贵州省毕节市人大常委会原一级巡视员罗昌琪接受审查调查](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7982344)[![Image 38](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-c891c73f-e2d9-4b26-be98-ac056cce8379-1790047501437.jpeg)8 郭莉夺得亚运会公路自行车女子公路赛金牌](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7982398)[![Image 39](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-e1f8c44e-9e86-4dbf-9875-88031acca29c-1790070617805.jpeg?imageslim\u002Fzlevel\u002F6) 01:06 9 90年前巧渡金沙，如今筑坝安澜丨史诗之路](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7983723)[![Image 40](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-1ea1dce9-b2bd-491c-bdb0-8dce20fd2cbc-1790072010550.png) 01:15 10 快来看！四川技术总师，享受什么政策 | 二胖探才记](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7983960)\n\n[![Image 41](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-0ae08b42-806b-466b-8325-3d0db3077adb-1747298732623.jpeg)1 中秋到江安赴一场南瓜宴，坐乐至观光小火车漫游乡间丨川观号加新时刻 09.22](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F6094993)[![Image 42](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-6fe6f3a1-6d5c-4125-8f3c-a9d302daaab9-1755152927789.jpeg)2 沉醉川内秋韵，品读古镇山水如画风光丨川观号聚焦时刻（09.10-09.17）](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F6630419)[![Image 43](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-53c8dd65-75fc-4b1b-98d8-65afa1e78749-1775807469164.jpeg)3 9月22日题库已更新，欢迎来战！](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7476454)[![Image 44](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-fc418db7-e3d1-46a8-b04f-1f0a82ba02f4-1789529514973.png)4 有氧运动第6课：4分钟燃脂操，带你甩掉多余脂肪 | 医起练 益健康](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7839670)[![Image 45](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-ef1ee71b-d523-4a29-9119-50d50a2e4ea0-1789975786536.jpeg) 01:26 5 我省与中国广核集团签署战略合作协议 王晓晖施小琳会见杨长利庞松涛并共同见证协议签署](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7979172)[![Image 46](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fapp\u002Fimg\u002FnewsDefault43-14.png)6 四川发布干部任前公示，涉多个市（州）领导班子候选人](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7962158)[![Image 47](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-da912a8d-7a4f-4f6b-a17c-9682357063fb-1789614401442.jpeg) 00:50 7 新编川剧《官衣梦》亮相成都 本届汇演再添新作](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7963475)[![Image 48](https:\u002F\u002Fcbgccdn.thecover.cn\u002FHzrnhgxyCjkZoMGNtIh1789896597117.jpg)8 黄山西海大峡谷发生野猴伤人事件，游客被咬缝6针](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7974615)[![Image 49](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-e9acd51a-4501-4aa5-8721-3202b555144c-1789898624273.jpeg) 06:30 9 央地共建成渝地区区域科技创新中心工作推进会在成都召开 阴和俊王晓晖陈新武讲话 施小琳主持](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7974912)[![Image 50](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fapp\u002Fimg\u002FnewsDefault43-16.png)10 四川发布干部任前公示，涉多个厅级领导职务](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7962159)\n\n[![Image 51](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-0ae08b42-806b-466b-8325-3d0db3077adb-1747298732623.jpeg)1 中秋到江安赴一场南瓜宴，坐乐至观光小火车漫游乡间丨川观号加新时刻 09.22](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F6094993)[![Image 52](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-6fe6f3a1-6d5c-4125-8f3c-a9d302daaab9-1755152927789.jpeg)2 沉醉川内秋韵，品读古镇山水如画风光丨川观号聚焦时刻（09.10-09.17）](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F6630419)[![Image 53](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-53c8dd65-75fc-4b1b-98d8-65afa1e78749-1775807469164.jpeg)3 9月22日题库已更新，欢迎来战！](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7476454)[![Image 54](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-314dd805-b127-407d-92dc-6c2d48086b50-1789451150246.jpeg)4 黎明当选雅安市人民政府市长](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7956547)[![Image 55](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-fc418db7-e3d1-46a8-b04f-1f0a82ba02f4-1789529514973.png)5 有氧运动第6课：4分钟燃脂操，带你甩掉多余脂肪 | 医起练 益健康](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7839670)[![Image 56](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-27507e4a-9cf7-4829-9c1e-7284b034ec35-1775550418442.jpeg)6 宜周观澜](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7465290)[![Image 57](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-ef1ee71b-d523-4a29-9119-50d50a2e4ea0-1789975786536.jpeg) 01:26 7 我省与中国广核集团签署战略合作协议 王晓晖施小琳会见杨长利庞松涛并共同见证协议签署](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7979172)[![Image 58](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-e7f48b9f-d2f5-4b90-bbcf-da88d95206b5-1789028579539.jpeg) 05:11 8 废品堆里，他捡出一字一句的诗行丨天府周末](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7929508)[![Image 59](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-16601f09-dd1a-477a-b5bb-a49ab7aef246-1788150902395.jpeg)9 网安知识大闯关！四川省网络安全知识有奖竞答活动今日开启！](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7905788)[![Image 60](https:\u002F\u002Fcbgccdn.thecover.cn\u002Fnewscontent-d4baeb8e-adbc-4c73-a8a7-e793747a23e2-1788054490088.jpeg) 00:52 10 机甲狂欢燃动夜色 解锁成都多元新潮夜间玩法](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7901926)\n\n### _精彩_ 评论\n\n### _小观_ 推荐\n\n![Image 61](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcomment-zan-normal.png)\n6\n\n![Image 62](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcomment-collect.png)![Image 63](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fcomment-share.png)\n\n![Image 64](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Ffollow-mask-close.png)\n### 关注我们\n\n![Image 65](https:\u002F\u002Fwapcdn.chuanbaoguancha.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Ffollow-mask-qrcode.jpg)\n\n[](https:\u002F\u002Fm.weibo.cn\u002Fu\u002F3167104922)\n\n友情链接\n\n[四川省人民政府](https:\u002F\u002Fwww.sc.gov.cn\u002F)[人民网](http:\u002F\u002Fwww.people.com.cn\u002F)[新华网](http:\u002F\u002Fwww.xinhuanet.com\u002F)[中国日报网](http:\u002F\u002Fwww.chinadaily.com.cn\u002F)[国际在线](http:\u002F\u002Fwww.cri.cn\u002F)[央广网](http:\u002F\u002Fwww.cnr.cn\u002F)[中青在线](http:\u002F\u002Fwww.cyol.net\u002F)[环球网](http:\u002F\u002Fwww.huanqiu.com\u002F)[未来网](http:\u002F\u002Fwww.k618.cn\u002F)[参考消息](http:\u002F\u002Fwww.cankaoxiaoxi.com\u002F)[中国网](http:\u002F\u002Fwww.china.com.cn\u002Fchinese\u002Findex.htm)[央视网](http:\u002F\u002Fwww.cctv.com\u002F)[中新网](http:\u002F\u002Fwww.chinanews.com.cn\u002F)[中青网](http:\u002F\u002Fwww.youth.cn\u002F)[中国经济网](http:\u002F\u002Fwww.ce.cn\u002F)[安徽网](http:\u002F\u002Fwww.ahwang.cn\u002F)[新华报业](http:\u002F\u002Fwww.xhby.net\u002F)[大众网](http:\u002F\u002Fwww.dzwww.com\u002F)[大江网](http:\u002F\u002Fwww.jxcn.cn\u002F)[北方网](http:\u002F\u002Fwww.enorth.com.cn\u002F)[东北网](http:\u002F\u002Fwww.dbw.cn\u002F)[金羊网](http:\u002F\u002Fwww.ycwb.com\u002F)[四川在线](http:\u002F\u002Fwww.scol.com.cn\u002F)[广西新闻网](http:\u002F\u002Fwww.gxnews.com.cn\u002F)[闽南网](http:\u002F\u002Fwww.mnw.cn\u002F)[华龙网](http:\u002F\u002Fwww.cqnews.net\u002F)[南海网](http:\u002F\u002Fwww.hinews.cn\u002F)[天山网](http:\u002F\u002Fwww.ts.cn\u002F)[荆楚网](http:\u002F\u002Fwww.cnhubei.com\u002F)[华商网](http:\u002F\u002Fwww.hsw.cn\u002F)[中国江苏网](http:\u002F\u002Fwww.jschina.com.cn\u002F)[中国江西网](http:\u002F\u002Fwww.jxnews.com.cn\u002F)[深圳新闻网](http:\u002F\u002Fwww.sznews.com\u002F)[宁夏新闻网](http:\u002F\u002Fwww.nxnews.net\u002F)[齐鲁网](http:\u002F\u002Fwww.iqilu.com\u002F)[每日甘肃](http:\u002F\u002Fwww.gansudaily.com.cn\u002F)[亚心网](http:\u002F\u002Fwww.iyaxin.com\u002F)[云南网](http:\u002F\u002Fwww.yunnan.cn\u002F)[东北新闻网](http:\u002F\u002Fwww.nen.com.cn\u002F)[南方网](http:\u002F\u002Fwww.southcn.com\u002F)[湖南在线](http:\u002F\u002Fhunan.voc.com.cn\u002F)[浙江在线](http:\u002F\u002Fwww.zjol.com.cn\u002F)[中安在线](http:\u002F\u002Fwww.anhuinews.com\u002F)[多彩贵州](http:\u002F\u002Fwww.gog.cn\u002F)[黄河新闻网](http:\u002F\u002Fwww.sxgov.cn\u002F)[内蒙古新闻网](http:\u002F\u002Fwww.nmgnews.com.cn\u002F)[山西新闻网](http:\u002F\u002Fwww.sxrb.com\u002F)[红网](http:\u002F\u002Fwww.rednet.cn\u002F)[东方网](http:\u002F\u002Fwww.eastday.com\u002F)[南方网](http:\u002F\u002Fwww.southcn.com\u002F)[海外网](http:\u002F\u002Fwww.haiwainet.cn\u002F)[法制网](http:\u002F\u002Fwww.legaldaily.com.cn\u002F)[吉网](http:\u002F\u002Fwww.cnjiwang.com\u002F)[北国网](http:\u002F\u002Fwww.lnd.com.cn\u002F)[财新网](http:\u002F\u002Fwww.caixin.com\u002F)[千龙网](http:\u002F\u002Fwww.qianlong.com\u002F)[青海新闻网](http:\u002F\u002Fwww.qhnews.com\u002F)[中国甘肃网](http:\u002F\u002Fwww.gscn.com.cn\u002F)[西部网](http:\u002F\u002Fwww.cnwest.com\u002F)[大洋网](http:\u002F\u002Fwww.dayoo.com\u002F)[中国山东网](http:\u002F\u002Fwww.sdchina.com\u002F)[东南网](http:\u002F\u002Fwww.fjsen.com\u002F)[新民网](http:\u002F\u002Fwww.xinmin.cn\u002F)[上观](http:\u002F\u002Fwww.jfdaily.com\u002F)[澎湃](http:\u002F\u002Fwww.thepaper.cn\u002F)[陕西传媒网](http:\u002F\u002Fwww.sxdaily.com.cn\u002F)\n\n[关于我们](https:\u002F\u002Fcbgc.scol.com.cn\u002Fabout.html) | [广告业务](http:\u002F\u002Fwww.scdaily.cn\u002Fadvert.htm) | [联系我们](http:\u002F\u002Fwww.scdaily.cn\u002Fcontactus.htm)[![Image 66](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002Fa_biaoshi.gif)](http:\u002F\u002Fwww.hd315.gov.cn\u002Fbeian\u002Fview.asp?bianhao=031202001042600006)\n四川日报社版权所有 未经书面授权 不得复制或建立镜像  \n Copyright ©2011-2019 SICHUAN DAILY All rights reserved.  \n 四川日报报业集团 四川日报网[蜀ICP备12028253号-2](http:\u002F\u002Fwww.miibeian.gov.cn\u002F)\n互联网新闻信息服务许可证：51120170001\n[川观新闻跟帖评论自律管理承诺书](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F279795)\n\n*   [![Image 67](https:\u002F\u002Fwww.scol.com.cn\u002Fmainpic\u002Fjbzx_cn.jpg)](http:\u002F\u002Fwww.12377.cn\u002F)[![Image 68](https:\u002F\u002Fwww.scol.com.cn\u002Fmainpic\u002Fjbzx_12377.jpg)](http:\u002F\u002Fwww.12377.cn\u002F)[![Image 69](https:\u002F\u002Fwww.scol.com.cn\u002Fmainpic\u002Fjbzx_sc.jpg)](http:\u002F\u002Fwww.scjb.gov.cn\u002F)\n\n![Image 70](https:\u002F\u002Fcbgc.scol.com.cn\u002Fnews\u002F7979522)\n\n![Image 71](https:\u002F\u002Fwapcdn.thecover.cn\u002Fcdn\u002Fcbgc\u002Fstatic\u002Fimg\u002F20lc_r1_c1.png)\n\n温馨提示\n\n打开川观新闻客户端听全文\n\n关闭\n\n打开\n\n温馨提示\n\n是否在川观新闻客户端中打开这篇文章\n\n取消\n\n打开\n\n温馨提示\n\n还想查看更多评论请在客户端中查看\n\n取消\n\n打开","川观新闻","2026-09-19T00:00:00Z","报道",60,{"impact":59,"substance":19,"depth":60,"authority":12,"freshness":20,"relevant":21,"comment":61},18,12,"省级科研机构布局农业AI与大数据中心的报道，方向明确但以表态和规划为主，缺少具体数据与实施细节，时效性一般。",[63],{"name":54,"url":51},[65,26,66,27,29],"数字乡村","四川",[68,69],"四川农科院 农业大数据中心","刘永红 农业人工智能","四川农科院农业大数据中心-3224","2026-09-23T00:04:29.881810Z",{"id":73,"title":74,"url":75,"summary":76,"summary_zh":77,"content":8,"source_name":78,"source_url":75,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":79,"score_detail":80,"sources":85,"tags":87,"search_phrases":90,"slug":93,"view_count":35,"doi":94,"paper":95,"created_at":117},2805,"Synergistic effects of spectral preprocessing and machine learning algorithms for nitrogen estimation in tomato using hyperspectral spectral data","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71908-1","Abstract Accurate estimation of leaf nitrogen content is essential for optimizing fertilization management and improving crop productivity. This study proposes a nondestructive hyperspectral imaging framework combined with advanced machine learning algorithms to classify nitrogen levels in tomato leaves (Solanum lycopersicum L., Royal variety). A total of 300 hyperspectral samples were collected from plants subjected to three nitrogen treatments (N-30%, N-60%, and N-90%) under controlled conditions. Reflectance data (400–1000 nm) were calibrated and preprocessed using Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Savitzky–Golay (SG) filtering. Both unsupervised and supervised algorithms were systematically evaluated. Clustering results demonstrated that preprocessing substantially influenced class separability. The MSC + GMM combination yielded the best unsupervised results, with the lowest Davies–Bouldin index (0.443) and the highest silhouette coefficient (0.975), indicating improved cluster compactness and separation. In supervised learning, Neural Networks (NN) consistently outperformed the other models, achieving 100% accuracy and an ROC–AUC of 1.00 under SNV, MSC, and SG preprocessing. Gradient Boosting (GB) and Support Vector Machine (SVM) also demonstrated strong predictive capability, whereas conventional models, including LDA, LR, KNN, and NB, showed moderate improvements following preprocessing. Statistical analysis confirmed the significant effect of spectral preprocessing on both clustering and classification outcomes ( p \u003C 0.05). Overall, integrating hyperspectral imaging with appropriate preprocessing and nonlinear machine learning models provided strong classification performance under the controlled experimental conditions. However, the exceptionally high performance observed for some models should be interpreted cautiously because of the relatively small dataset and experimentally controlled nitrogen treatments. Moreover, the absence of an independent external validation dataset limits the assessment of generalizability across growing conditions, cultivars, and field environments. Therefore, independent validation using larger and more diverse datasets is required before broader application of the proposed framework in practical precision agriculture.","摘要 准确估算叶片氮含量对于优化施肥管理和提高作物生产力至关重要。本研究提出了一种无损高光谱成像框架，结合先进的机器学习算法对番茄叶片（Solanum lycopersicum L.，Royal品种）的氮水平进行分类。在受控条件下，从接受三种氮处理（N-30%、N-60%和N-90%）的植株中共采集了300个高光谱样本。反射率数据（400–1000 nm）经标准正态变量变换（SNV）、多元散射校正（MSC）和Savitzky–Golay（SG）滤波进行校准和预处理。系统评估了无监督和有监督算法。聚类结果表明，预处理对类别可分性产生了显著影响。MSC + GMM组合取得了最佳无监督结果，具有最低的Davies–Bouldin指数（0.443）和最高的轮廓系数（0.975），表明聚类紧密度和分离度得到改善。在有监督学习中，神经网络（NN）始终优于其他模型，在SNV、MSC和SG预处理下均达到100%的准确率和1.00的ROC–AUC。梯度提升（GB）和支持向量机（SVM）也表现出较强的预测能力，而传统模型（包括LDA、LR、KNN和NB）在预处理后表现出中等程度的改善。统计分析证实了光谱预处理对聚类和分类结果均有显著影响（p \u003C 0.05）。总体而言，将高光谱成像与适当的预处理及非线性机器学习模型相结合，在受控实验条件下提供了较强的分类性能。然而，由于数据集相对较小且氮处理为实验受控条件，某些模型所表现出的极高性能应谨慎解读。此外，缺乏独立的外部验证数据集限制了对跨生长条件、品种和田间环境泛化能力的评估。因此，在将该框架广泛应用于实际精准农业之前，需要使用更大规模、更多样化的数据集进行独立验证。","Scientific Reports",77,{"impact":81,"substance":82,"depth":83,"authority":19,"freshness":12,"relevant":21,"comment":84},15,21,17,"高光谱结合机器学习实现番茄叶片氮素无损估测，方法系统、结论明确，但样本量小且缺乏外部验证，属细分领域方法学进展。",[86],{"name":78,"url":75},[26,27,28,88,89],"番茄种植","高光谱遥感",[91,92],"农业人工智能 高光谱遥感 智慧农业 番茄种植","农业人工智能 高光谱遥感","农业人工智能高光谱遥感智慧农业番茄种植-2805","10.1038\u002Fs41598-026-71908-1",{"doi":94,"openalex_id":96,"authors":97,"venue":78,"cited_by_count":35,"oa_url":75,"card":110,"direction":42,"ingested_from":116},"W7213472002",[98,101,104,107],{"name":99,"orcid":100},"Mohammad Vahedi Torshizi","https:\u002F\u002Forcid.org\u002F0000-0003-3648-1515",{"name":102,"orcid":103},"Sajad Sabzi","https:\u002F\u002Forcid.org\u002F0000-0003-2439-5329",{"name":105,"orcid":106},"Mohsen Azadbakht","https:\u002F\u002Forcid.org\u002F0000-0002-5726-9321",{"name":108,"orcid":109},"Razieh Pourdarbani","https:\u002F\u002Forcid.org\u002F0000-0003-0766-8305",{"tldr":111,"method":112,"finding":113,"direction":114,"opportunity":115},"用高光谱成像结合预处理与机器学习，对番茄叶片氮素水平进行分类。","300个高光谱样本，SNV、MSC、SG预处理，聚类与多种监督分类算法对比。","MSC+GMM聚类最优，神经网络在三种预处理下均达100%准确率。","农业遥感与作物表型","样本少且无外部验证，可扩展多品种、多环境田间数据并做独立验证以提升泛化性。","openalex","2026-09-17T23:30:59.361085Z",{"id":119,"title":120,"url":121,"summary":122,"summary_zh":8,"content":8,"source_name":123,"source_url":121,"published_at":124,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":125,"score_detail":126,"sources":129,"tags":131,"search_phrases":134,"slug":137,"view_count":21,"doi":138,"paper":139,"created_at":168},2622,"Synergizing process-based modeling and data-driven learning for precision nitrogen optimization in winter wheat","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104983","Synergizing process-based modeling and data-driven learning for precision nitrogen optimization in winter wheat。Agricultural Systems","Agricultural Systems","2026-09-16T00:00:00Z",79,{"impact":59,"substance":127,"depth":83,"authority":19,"freshness":12,"relevant":21,"comment":128},20,"将过程模型与数据驱动学习融合用于冬小麦精准氮肥优化，方法新颖、发表于核心期刊且时效性强，具备进入每日精选的价值。",[130],{"name":123,"url":121},[26,27,28,132,133],"作物模型","冬小麦",[135,136],"农业人工智能 作物模型 智慧农业 精准施肥","农业人工智能 作物模型","农业人工智能作物模型智慧农业精准施肥-2622","10.1016\u002Fj.agsy.2026.104983",{"doi":138,"openalex_id":140,"authors":141,"venue":123,"cited_by_count":35,"oa_url":121,"card":8,"direction":8,"ingested_from":116},"W7213352238",[142,144,147,150,152,154,156,158,160,162,164,166],{"name":143,"orcid":8},"Yuru Ye",{"name":145,"orcid":146},"Qian Wang","https:\u002F\u002Forcid.org\u002F0000-0003-0750-7843",{"name":148,"orcid":149},"Davide Cammarano","https:\u002F\u002Forcid.org\u002F0000-0003-0918-550X",{"name":151,"orcid":8},"Kang Yu",{"name":153,"orcid":8},"Siva K. Balasundram",{"name":155,"orcid":8},"Wei Li",{"name":157,"orcid":8},"Xiuli Li",{"name":159,"orcid":8},"Xiaojun Liu",{"name":161,"orcid":8},"Yongchao Tian",{"name":163,"orcid":8},"Yan Zhu",{"name":165,"orcid":8},"Weixing Cao",{"name":167,"orcid":8},"Qiang Cao","2026-09-16T23:30:05.340754Z",{"id":170,"title":171,"url":172,"summary":173,"summary_zh":174,"content":8,"source_name":175,"source_url":172,"published_at":176,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":177,"score_detail":178,"sources":181,"tags":183,"search_phrases":186,"slug":189,"view_count":35,"doi":190,"paper":191,"created_at":205},2517,"Artificial Intelligence-Based Intelligent Fertigation Recommendation Systems for Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.64388\u002Firev10i3-1722972","Artificial-intelligence-enabled fertilizer and fertigation recommendation has progressed from single-task crop or fertilizer classification toward integrated decision-support architectures. However, predictive classification, agronomic dose calculation, irrigation scheduling, explainability, real-time sensing, and farmer-facing delivery are often studied separately. This paper presents a structured narrative review of these strands and an applied machine-learning case study using the publicly available Crop and Fertilizer Dataset for Western Maharashtra. The case study contains 4,513 records spanning five districts, 16 crops, and 19 fertilizer classes. Seven classifiers were compared using an 80:20 stratified train-test split with five-fold stratified cross-validation on the training set. XGBoost achieved 97.34% test accuracy and 94.21% ± 1.15% cross-validated accuracy, while Random Forest achieved 93.58% and 90.89% ± 0.80%, respectively. TreeSHAP analysis of Random Forest identified crop identity, potassium, and nitrogen as the leading predictors of the historical fertilizer class. These results are interpreted as a computational baseline rather than proof of agronomic optimality because the target label represents recorded fertilizer choices. The review also incorporates evidence on IoT\u002Fedge-cloud sensing, multilingual agricultural advisory, and federated learning. It concludes that RF\u002FSHAP, IoT sensing, and multilingual interfaces are established capabilities; a more defensible research direction is an auditable pipeline that separates fertilizer identity, nutrient dose, and application timing, connects explainable prediction to sequential scheduling, and independently benchmarks outputs against authoritative agronomic guidance. The proposed Intelligent Fertigation Recommendation System (IFRS) is therefore presented as a research framework requiring multi-season and field validation before claims of yield, water, nutrient-use-efficiency, or adoption benefits.","人工智能驱动的肥料与灌溉施肥推荐已从单一任务的作物或肥料分类，发展为集成式决策支持架构。然而，预测性分类、农艺用量计算、灌溉调度、可解释性、实时感知以及面向农户的交付往往被分别研究。本文对这些研究脉络进行了结构化叙述性综述，并基于公开的“西马哈拉施特拉邦作物与肥料数据集”开展了一项应用机器学习案例研究。该案例研究包含4，513条记录，涵盖五个地区、16种作物和19个肥料类别。采用80：20分层训练-测试划分，并在训练集上进行五折分层交叉验证，比较了七种分类器。XGBoost取得了97.34%的测试准确率和94.21% ± 1.15%的交叉验证准确率，而随机森林分别取得了93.58%和90.89% ± 0.80%。对随机森林的TreeSHAP分析表明，作物身份、钾和氮是历史肥料类别的主要预测因子。这些结果被解释为计算基线，而非农艺最优性的证明，因为目标标签代表的是有记录的肥料选择。该综述还纳入了关于物联网\u002F边缘-云感知、多语言农业咨询和联邦学习的证据。结论认为，随机森林\u002FSHAP、物联网感知和多语言界面已是成熟能力；更具可辩护性的研究方向是构建一条可审计的流水线，将肥料身份、养分用量和施用时机分离，将可解释预测与序贯调度相连接，并依据权威农艺指南对输出进行独立基准测试。因此，所提出的智能灌溉施肥推荐系统（IFRS）被作为一个研究框架提出，在声称产量、水分、养分利用效率或采用效益之前，仍需进行多季和田间验证。","Iconic Research and Engineering Journals","2026-09-14T00:00:00Z",62,{"impact":60,"substance":59,"depth":83,"authority":20,"freshness":179,"relevant":21,"comment":180},9,"对AI水肥推荐研究进行系统综述并给出可复现的机器学习基线，方法透明、结论审慎，但来源为普通工程类期刊且属综述性论文，产业影响有限，适合作为技术参考而非每日精选头条。",[182],{"name":175,"url":172},[26,27,28,184,185],"可解释AI","水肥一体化",[187,188],"农业人工智能 水肥一体化 智慧农业 精准施肥","农业人工智能 水肥一体化","农业人工智能水肥一体化智慧农业精准施肥-2517","10.64388\u002Firev10i3-1722972",{"doi":190,"openalex_id":192,"authors":193,"venue":175,"cited_by_count":35,"oa_url":198,"card":199,"direction":204,"ingested_from":116},"W7212934364",[194,196],{"name":195,"orcid":8},"Shraddha S. Tayade",{"name":197,"orcid":8},"Yogesh V. Chimate","https:\u002F\u002Fwww.irejournals.com\u002Fformatedpaper\u002F1722972.pdf",{"tldr":200,"method":201,"finding":202,"direction":42,"opportunity":203},"综述AI施肥推荐研究，并用马哈拉施特拉数据集比较七种分类器，提出可审计智能施肥推荐框架。","结构化综述加机器学习案例，4513条记录，七分类器对比，XGBoost与Tree","XGBoost测试准确率97.34%，但标签仅为历史施肥选择，不能证明农艺最优。","可研究分离肥料种类、养分剂量与施用时序的可审计推荐流水线，并进行多季田间验证。","智慧农业 \u002F 农业物联网","2026-09-15T23:30:12.675690Z",{"id":207,"title":208,"url":209,"summary":210,"summary_zh":211,"content":8,"source_name":212,"source_url":209,"published_at":213,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":79,"score_detail":214,"sources":218,"tags":220,"search_phrases":222,"slug":225,"view_count":35,"doi":226,"paper":227,"created_at":239},2036,"Smart crop recommendation: fusing nutrient and climate data with Krill Herd Optimization and explainable AI","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrai.2026.1910196","Crop recommendation is a vital part of precision agriculture as it helps farmers choose appropriate crops according to the nutrient profile and environmental conditions. This paper presents a crop recommendation framework in which Multi-Layer Perceptron (MLP), XGBoost, and Tab Transformer are first evaluated as baseline prediction models, followed by the proposed Krill Herd Optimization (KHO)-based explainable framework integrated with Explainable Artificial Intelligence (XAI). These eleven parameters are created based on agronomic and environmental aspects, namely: Nitrogen, Phosphorus, Potassium, Copper, Iron, Magnesium, Sulphur, Temperature, Rainfall, pH and Humidity. For better model transparency and to aid informed decision-making, model explanations with SHAP (SHapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) are used to identify feature contributions to crop predictions both locally and globally. The experimental results showed that Tab Transformer significantly outperformed the other models, with an accuracy of 0.99, precision of 0.98, recall of 0.99 and F1-score of 0.98. The proposed framework further incorporates Krill Herd Optimization (KHO) to generate optimized nutrient and climate profiles, while Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) are used for comparative evaluation of optimization performance. By combining explainable AI with optimization methods, the framework improves crop suitability prediction and provides transparent insights into the factors influencing crop recommendations, ensuring reliable decision support for practical farming applications. The proposed framework supports precision agriculture by enabling data-driven crop selection, reducing unnecessary fertilizer usage, optimizing crop productivity, and promoting sustainable farming practices.","作物推荐是精准农业的重要组成部分，有助于农民根据养分状况和环境条件选择适宜的作物。本文提出了一个作物推荐框架，首先评估多层感知机（MLP）、XGBoost和Tab Transformer作为基线预测模型，随后提出基于磷虾群优化（KHO）的可解释框架，并集成可解释人工智能（XAI）。基于农艺和环境因素构建了十一个参数，即：氮、磷、钾、铜、铁、镁、硫、温度、降雨量、pH值和湿度。为提高模型透明度并辅助知情决策，采用SHAP（SHapley加性解释）和LIME（局部可解释模型无关解释）进行模型解释，以在局部和全局层面识别特征对作物预测的贡献。实验结果表明，Tab Transformer显著优于其他模型，准确率为0.99，精确率为0.98，召回率为0.99，F1分数为0.98。所提框架进一步引入磷虾群优化（KHO）以生成优化的养分和气候方案，同时使用遗传算法（GA）、粒子群优化（PSO）和模拟退火（SA）对优化性能进行比较评估。通过将可解释人工智能与优化方法相结合，该框架提高了作物适宜性预测能力，并提供了影响作物推荐因素的透明洞察，确保为实际农业应用提供可靠的决策支持。所提框架通过实现数据驱动的作物选择、减少不必要的肥料使用、优化作物生产力并促进可持续农业实践，为精准农业提供支持。","Frontiers in Artificial Intelligence","2026-09-09T00:00:00Z",{"impact":215,"substance":82,"depth":59,"authority":216,"freshness":179,"relevant":21,"comment":217},16,13,"融合营养与气候数据、Krill Herd优化与可解释AI的作物推荐框架，方法新颖、结论可靠，对精准农业决策有参考价值。",[219],{"name":212,"url":209},[26,27,28,184,221],"作物推荐",[223,224],"农业人工智能 作物推荐 智慧农业 精准施肥","农业人工智能 作物推荐","农业人工智能作物推荐智慧农业精准施肥-2036","10.3389\u002Ffrai.2026.1910196",{"doi":226,"openalex_id":228,"authors":229,"venue":212,"cited_by_count":35,"oa_url":209,"card":234,"direction":204,"ingested_from":116},"W7211994206",[230,232],{"name":231,"orcid":8},"P. Latha",{"name":233,"orcid":8},"P. Kumaresan",{"tldr":235,"method":236,"finding":237,"direction":42,"opportunity":238},"提出融合养分与气候数据、KHO优化和可解释AI的作物推荐框架，Tab Transformer精度达0","用MLP、XGBoost、Tab Transformer建模，结合KHO优化与S","Tab Transformer预测最优（准确率0.99），KHO优化养分气候方案，XAI提升推荐透明","可探索将可解释AI与优化算法嵌入真实农田物联网实时数据流，验证跨区域泛化与农户采纳效果。","2026-09-10T23:30:09.054372Z",{"id":241,"title":242,"url":243,"summary":244,"summary_zh":245,"content":8,"source_name":246,"source_url":243,"published_at":247,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":125,"score_detail":248,"sources":251,"tags":253,"search_phrases":257,"slug":260,"view_count":35,"doi":261,"paper":262,"created_at":292},3371,"Optimizing nitrogen fertilization in mustard through GreenSeeker-based precision agriculture: Impacts on productivity, economics, and environmental sustainability","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0358762","Excessive nitrogen (N) fertilization is a major challenge to sustainable agriculture, adversely affecting crop productivity, soil quality, and environmental health, emits a potent greenhouse gas nitrous oxide (N 2 O), and nearly 80% of sectoral emissions linked to nutrient inputs applied during crop production. The escalating use of N fertilizers further amplifies N 2 O emissions, undermining soil sustainability and contributing to environmental degradation. So, the hypothesis used behind the study is increasing nitrogen use efficiency from its current level (approx. 30–40%) would reduce the need for N fertilizer requirement, resulting in more cost-effective and environmentally sustainable production system with no yield penalty. With this objective, a field study was executed in rabi 2021–2024, consisting of nine N management treatments and one unfertilized treatment as control, randomized in complete block design in three replicates. To overcome this problem, first we standardized NDVI based N application and developed a Nitrogen Estimation Rate Chart (NERC) for precision N management in real time for specific set target yield. Results showed that sensor based N application enhanced growth and yield attributes, registered 22.75% seed yield enhancement with 18.7% N saving over RDF and 34.4 & 30.2% increment in NMR and BCR. This treatment augmented AE N and PFP N by 14.18 to 124.7% and 1.78 to 51.1%, respectively achieved higher NRE (35–69.5%). The per cent enrichment in SOC content was found superior in RDN 100 + 2% Urea FS (52.6%) followed by RDN 100 + 1.5% KNO 3 FS (39.4%) statistically comparable to RDF (38.1%). The fertilizers contributed largest share of total carbon emissions, accounting for 45.6–52.3%. NDVI based N management reduced GHGs emissions by approximately 11.23% over RDF. The mean biological yield (seed + stover) unveiled positive correlation to total nitrogen (r 2 = 98), total phosphorus (r 2 = 95) and total potassium (r 2 = 98) uptake. This innovative technology enables farmers to prevent excessive N fertilization, thereby reducing resource wastage and minimizing nitrous oxide emission. This technology provides insight on N need of crop in real time in right quantity.","过量施氮是可持续农业面临的一项重大挑战，会对作物生产力、土壤质量和环境健康产生不利影响，并排放强效温室气体氧化亚氮（N₂O），而该领域近80%的排放与作物生产过程中投入的养分有关。氮肥用量的不断攀升进一步加剧了N₂O排放，削弱土壤可持续性并导致环境退化。因此，本研究提出的假设是：将氮利用效率从当前水平（约30%–40%）提高，可减少对氮肥的需求，从而在不造成产量损失的前提下，实现更具成本效益和环境可持续性的生产体系。基于此目标，于2021—2024年rabi季开展了一项田间研究，包括9个氮管理处理和1个不施肥对照处理，采用完全随机区组设计，3次重复。为解决上述问题，首先标准化了基于NDVI的氮肥施用方法，并开发了氮估算速率表（NERC），用于针对特定目标产量进行实时精准氮管理。结果表明，基于传感器的氮肥施用促进了生长和产量性状，种子产量较推荐施肥量（RDF）提高22.75%，节省氮肥18.7%，净收益（NMR）和效益成本比（BCR）分别提高34.4%和30.2%。该处理使氮农学效率（AE N）和氮偏生产力（PFP N）分别提高14.18%–124.7%和1.78%–51.1%，并实现了更高的氮回收效率（NRE，35%–69.5%）。土壤有机碳（SOC）含量的提升幅度以RDN 100 + 2%尿素叶面喷施（52.6%）最优，其次为RDN 100 + 1.5% KNO₃叶面喷施（39.4%），与RDF（38.1%）在统计上相当。肥料对总碳排放的贡献最大，占45.6%–52.3%。基于NDVI的氮管理较RDF减少温室气体排放约11.23%。平均生物产量（种子+秸秆）与总氮（r² = 98）、总磷（r² = 95）和总钾（r² = 98）吸收量呈正相关。这项创新技术使农民能够避免过量施氮，从而减少资源浪费并降低氧化亚氮排放。该技术可实时提供作物氮需求信息，并指导适宜用量的施用。","PLoS ONE","2026-09-23T00:00:00Z",{"impact":59,"substance":16,"depth":59,"authority":216,"freshness":249,"relevant":21,"comment":250},8,"基于NDVI传感器的实时精准施氮研究，四年田间试验数据扎实，兼具增产、节肥与减排价值，对智慧农业施肥决策有参考意义。",[252],{"name":246,"url":243},[26,28,254,255,256],"氮肥管理","NDVI遥感","绿色低碳农业",[258,259],"GreenSeeker NDVI 氮肥管理","芥菜型油菜 精准施氮","GreenSeekerNDVI氮肥管理-3371","10.1371\u002Fjournal.pone.0358762",{"doi":261,"openalex_id":263,"authors":264,"venue":246,"cited_by_count":35,"oa_url":243,"card":286,"direction":291,"ingested_from":116},"W7214115167",[265,268,270,272,274,276,278,280,282,284],{"name":266,"orcid":267},"V. D. Meena","https:\u002F\u002Forcid.org\u002F0000-0001-9528-4832",{"name":269,"orcid":8},"M.L. Dotaniya",{"name":271,"orcid":8},"M.D. Meena",{"name":273,"orcid":8},"R. S. Jat",{"name":275,"orcid":8},"MK Meena",{"name":277,"orcid":8},"R. L. Choudhary",{"name":279,"orcid":8},"H. V. Singh",{"name":281,"orcid":8},"HS MEENA",{"name":283,"orcid":8},"B.L. Meena",{"name":285,"orcid":8},"V. V. Singh",{"tldr":287,"method":288,"finding":289,"direction":204,"opportunity":290},"基于GreenSeeker的NDVI实时氮肥管理优化芥菜施氮，提升产量并减少氮肥与温室气体排放。","2021-2024年田间试验，9个氮处理+对照，用GreenSeeker NDV","传感器施氮使种子产量增22.75%、节氮18.7%，NRE达35-69.5%，温室气体减排约11.2","可将NDVI实时氮管理扩展至其他作物与区域，并结合碳足迹模型量化减排经济价值。","农业绿色发展与碳","2026-09-24T23:30:41.022035Z"]