[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1682":3,"related-1682":75},{"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":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":69,"slug":72,"view_count":73,"doi":8,"paper":8,"created_at":74},1682,"山东农田迎生产方式变革：从\"人跑眼看\"到\"卫星巡田\"——天空地一体化遥感监测","https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html","山东省农业科学院农业信息与经济研究所构建起一套\"天空地\"一体化的遥感数据采集处理体系。天上是多源卫星数据——以国产高分系列为主、开源卫星数据为辅；团队于 2024 年开始研发一款面向县域的大型无人机，搭载专为农业设计的波段载荷；地上在肥城等地布设了一批农业物联网设备。三者叠加形成监测网络，为县级政府提供作物长势、产能、农机分配、水源调配等宏观决策数据支撑。",null,"![Image 1](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n![Image 2](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n![Image 3](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fcode.png)\n\n[![Image 4](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Flilun.png)![Image 5](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Flilun-1.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fcomment\u002F \"理论\")[![Image 6](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Ffuzhi.png)![Image 7](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Ffuzhi-1.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_15.html \"重庆日报网专题\")\n\n![Image 8](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Ffenxiang.png)![Image 9](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Ffenxiang-1.png)\n\n[![Image 10](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fwx.png) 用微信扫描二维码](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)[![Image 11](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fwb.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)[![Image 12](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FQQ.png) 用QQ扫描二维码](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n[![Image 13](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FTOP.png)![Image 14](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FTOP2.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n[![Image 15](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Flogo.png)![Image 16](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Flogo-white.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_1.html)\n\n[![Image 17](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fpc-renminlaixing.png)![Image 18](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fpc-renminlaixing-skin.png)](https:\u002F\u002Fwap.cqrb.cn\u002Fxcq\u002FlaiXin\u002Findex\u002Findex)[![Image 19](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fwx.png)微信 ![Image 20](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FwxCode.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)[![Image 21](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fwb.png)微博](https:\u002F\u002Fweibo.com\u002Fcqrb)[![Image 22](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fcqh.png)重庆号](https:\u002F\u002Fmp.cqrb.cn\u002Flogin)\n\n![Image 23](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fsousuo.png)![Image 24](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fsousuo1.png)搜索\n\n[深读](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_3.html)[推荐](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_1.html)[重庆](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_2.html)[观点](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_4.html)[视频](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_24.html)[区县](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_8.html)[视觉重庆](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_10.html)[乡村振兴](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_9.html)[双城](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_7.html)[经济](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_11.html)\n\n更多![Image 25](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fzhankai.png)\n\n[科教](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_16.html)[人文](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_12.html)[民生](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_13.html)[清廉重庆](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_5.html)[红岩](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_6.html)[专题](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_15.html)\n\n重庆日报网>正文\n\n向遥感要数据，向数据要答案，山东农田迎生产方式变革——从“人跑眼看”到“卫星巡田”\n\n新重庆-重庆日报精选\n2026-09-03 11:13\n\n卫星上天，数据落地。\n\n在距离地面数百公里的高空上，一颗颗遥感卫星正掠过齐鲁大地。它们“看”到的，不只是山川轮廓，更是每一块地上种了什么、长势如何、墒情怎样。而在山东省农业科学院农业信息与经济研究所，映入大屏的是全省耕地的各项数据——哪里缺水、哪片田进入灌浆期，一目了然。\n\n天和地，曾经是两个遥不可及的存在，在现代信息技术的链接下正碰撞出奇妙的“火花”。当卫星“天眼”遇上万亩良田，能带来怎样的改变？作为农业大省，山东1亿多亩耕地靠一双脚跑不过来，也盯不全。如何守住每一寸耕地、管好每一季庄稼？\n\n向遥感要数据，向数据要答案。从凭经验施肥到按数据管田，从人跑眼看到卫星巡田，一场农业生产方式的变革正在山东万千农田间上演。\n\n**数据赋能：从“采得到”到“用得好”**\n\n数据，是遥感技术的核心资源。数据的采集与处理的质量，往往是决定遥感监测结果优劣的关键。\n\n为实现高频、精准的监测，该研究所构建起一套“天空地”一体化的遥感数据采集处理体系。该研究所副研究员李乔宇介绍，不同于一般的遥感采集系统，他们自研的这套系统，是个集合体。天上是多源卫星数据——以国产高分系列为主、开源卫星数据为辅，目标是实现“县域2米、5天”和“省域10米、7天”的高频立体监测。但卫星有过境周期，遇到阴雨天卫星影像质量无法满足要求。\n\n为此，团队于2024年开始，耗时2年，与中国科学院空天信息创新研究院、中国农业科学院等团队合作研发了一款面向县域的大型无人机，搭载专为农业设计的波段载荷，航程长、响应快，可随时巡航补充影像。地上，在肥城等地布设了一批农业物联网设备。联合中国农业大学研发的“地面布网算法”，提供不受天气和卫星周期影响的连续地面数据。天、空、地三者叠加，形成了一张密而不漏的监测网络。\n\n有了高质量的数据支撑，遥感服务便从生产端延伸到了县域治理层面。通过构建和应用县域农情监测与服务系统，不仅监测作物生长，还能实现农机智能调度。“农忙时，农机在系统里统一调配，自动分配给最需要的地方。”李乔宇说。\n\n在数据应用层面，系统为县级政府提供了另一维度的决策价值。“县领导关心的是全县作物长得怎么样、产能大约有多少，收获时农机怎么分配、水源怎么调配，哪个地方墒情不好需要重点保障——这些宏观决策都需要数据支撑。”李乔宇表示。从作物分布到产量预估，从墒情监测到应急调度，遥感数据正在成为县域农业治理的“数字参谋”。\n\n目前，这套模式已在山东省省域和县域进行了规模化示范应用。从生产端的“指尖处方”到管理端的“决策参谋”，遥感数据正在山东的田野上完成从“采”到“算”到“用”的完整闭环。\n\n**智能决策：从“看得到”到“管得住”**\n\n耕地是粮食生产的命根子。守住耕地红线，首先要看得清、管得住。\n\n“哪块地上种的是小麦、玉米或是大豆；作物长势怎么样；土壤墒情如何，是缺水干旱还是涝情严重，同时还能实现产量预估——这是一整套的监测流程。”该研究所副研究员侯学会一边操作鼠标，一边向记者介绍。\n\n以往，判断一块地种了什么、长势如何，靠的是基层干部和农技人员一双脚、一双眼。遥感技术让耕地监管从“人跑眼看”走向“智慧决策”，但“看得到”不等于“看得清”“管得准”——如何从海量影像中精准提取地块边界、识别作物类型、动态监测用途变化，才是真正的技术难点。\n\n2026年6月，由该研究所主导研发的黄淮海区域首个农业遥感大模型——“舜耕·粮安”在济南正式发布。这套大模型依托覆盖山东全域、全地貌、全物候期的海量高质量卫星影像，叠加20年来2000万份人工样本，训练出6个垂直模型：AI耕地智能提取、AI肥力墒情预测、AI作物精准识别、AI长势动态监测、AI病虫草害预警、AI作物智能估产，监测精度最高可达95%。\n\n与传统遥感目视识别不同，这套系统靠的是AI算法。“过去地块提取边界需要大量人工描点，现在通过算法，点击鼠标，边界自然就出来了。”侯学会说。6个垂直模型如同不知疲倦的“数字哨兵”，24小时扫描着齐鲁大地每寸耕地的变化。\n\n技术突破，最终要落在应用实效上。在耕地保护领域，依托高频次卫星遥感影像的自动比对，系统能够主动捕捉耕地边界变化，变“被动接报”为“主动发现”，为主管部门监管耕地用途提供了精准靶标。在高标准农田建设领域，模型同样发挥着重要作用——它可以不间断收集“建、管、用”全过程数据，让建设进度可视、工程质量可评、种植用途可查，真正实现“建得好、管得住、用得实”。\n\n**数字处方：从“老经验”到“精准化”**\n\n在泰安肥城市安驾庄镇双北农业种植专业合作社的万亩麦田里，一场“精准农业”的试验已持续3年。当地种粮大户武海荣见证了“数字农业”带来的改变，也彻底颠覆了对传统种地的认知。\n\n过去，合作社种地靠的是“老经验”：到了施肥节点，不管哪块地、不管长势如何，统一配方、统一用量。“统防统治，不管有没有病虫害、不管程度怎么样，都统一打药。”侯学会坦言，这是一种粗放的管理方式。\n\n2023年，研究所技术团队走进双北合作社，为这片2000亩小麦量身定制了一套“数字处方”。这套处方遵循一个逻辑：遥感监测作物真实长势，结合作物自身需水需肥规律，综合得出建议数。“作物在不同生长期对水肥需求不一样，比如小麦返青期和灌浆期，施肥策略就截然不同。”侯学会说。\n\n方案覆盖了小麦生产的关键节点：播种期建议基肥用量，返青期根据卫星影像显示的苗情决定追肥多少。整个生长季，“监测—诊断—处方—评估”闭环持续运转。3年下来，在按处方管理的地块，节水率、节肥率可达10%以上，产量不降反增。\n\n虽然“数字处方”在田间种植中精准有效，但要真正走进千家万户，并不像专家最初设想的那么顺利。“技术上的突破只是第一步，怎么让农户愿意用、用得上，才是真正的考验。”李乔宇坦言，为了解决“最后一公里”的落地难题，研究所在实践中摸索出两条路径，对应着两类不同的服务对象。\n\n一条是面向农户的“指尖服务”。团队开发了“云农集”微信小程序，农户登记自家地块后，系统通过遥感监测长势和墒情，自动推送水肥处方、病虫害预警。然而推广中也有现实难题，“我们推送的主要是氮含量建议，但农户买的大多是复合肥，需要自己换算配比，对普通农户来说有些复杂。”李乔宇介绍。\n\n另一条是面向农服公司的“标准化对接”。在邹平，研究所对接山东诚丰农化科技有限公司——这家公司服务2000户农户、覆盖4.5万亩土地。团队把遥感处方推给公司，技术人员根据自有肥料配方和管理方案，将建议换算优化后直接落地。\n\n两种模式，本质区别在于数据服务的“接口”不同，但价值相通——让每一个农事决策有据可依，让每一滴水肥用得更精准、更高效。\n\n卢德成 农民日报全媒体记者 吕兵兵 蒋欣然\n\n来源： 农民日报\n\n编辑： 宜安 审核： 邹密 主编：颜安 \n\n版权声明：\n凡注明来源重庆日报的作品，版权均属重庆日报所有，未经授权不得转载、摘编或利用其它方式使用上述作品。已经本网授权使用作品的，应在授权范围内使用，并注明“来源：重庆日报网”。违反上述声明者，本网将追究其相关法律责任。\n\n除来源署名为重庆日报稿件外，其他所转载内容之原创性、真实性、完整性、及时性本站不作任何保证或承诺，请读者仅作参考并自行核实。\n\n相关新闻\n\n[![Image 26](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F07\u002F24\u002Fbrowser\u002F207\u002F17848844947821v5b1b5ix78.png) 6图 台风、暴雨预警有望提速 AI气象卫星“星火传明号”成功发射 ![Image 27](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fxcq_logo.png) 精选 2026-07-24 09:13:26 ![Image 28](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fview.png)0](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-07-24\u002F2734201_pc.html)\n\n[![Image 29](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F08\u002F05\u002Fbrowser\u002F467\u002F1785939940004bxl30l8k45f.png) 15图 “AI双星”上太空，“天感天算”的新本领是如何练成的？ ![Image 30](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fxcq_logo.png) 精选 2026-08-05 14:23:50 ![Image 31](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fview.png)0](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-08-05\u002F2744180_pc.html)\n\n[![Image 32](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F07\u002F22\u002Fbrowser\u002F317\u002F178468620105263181189534186310.jpeg) 水利部：到2035年基本形成完备的水利遥感卫星应用体系 ![Image 33](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fxcq_logo.png) 精选 2026-07-22 01:06:31 ![Image 34](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fview.png)0](https:\u002F\u002Fwww.cqrb.cn\u002Fdisijii\u002F2026-07-22\u002F2731452_pc.html)\n\n[水利部：到2035年基本形成完备的水利遥感卫星应用体系 ![Image 35](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fxcq_logo.png) 精选 2026-07-21 03:49:36 ![Image 36](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fview.png)0](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-07-21\u002F2730545_pc.html)\n\n[![Image 37](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fnewspaper-title.png)](https:\u002F\u002Fepaper.cqrb.cn\u002Fcqrb\u002F)[更多![Image 38](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FmoreWhite.png)](https:\u002F\u002Fwww.cqrb.cn\u002FreadMoreEpaper.html)\n\n[![Image 39](https:\u002F\u002Fm.cqrb.cn\u002Fcqrb\u002F2026-09\u002F05\u002F001\u002Fcqrb20260905001_s.jpg)](https:\u002F\u002Fepaper.cqrb.cn\u002Fcqrb\u002F)\n\n![Image 40](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fcqlwtitle.png)[更多![Image 41](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fmore.png)](https:\u002F\u002Fwww.cqrb.cn\u002F2023cqlw\u002F)\n\n[• 重庆瞭望｜常态化开展政绩观教育，用好这三招](https:\u002F\u002Fwww.cqrb.cn\u002F2023cqlw\u002F2026-09-03\u002F2766815_pc.html)[• 重庆瞭望｜8D重庆，激活“立体”消费新动能](https:\u002F\u002Fwww.cqrb.cn\u002F2023cqlw\u002F2026-09-02\u002F2765942_pc.html)\n\n![Image 42](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002F24hottitle.png)[更多![Image 43](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fmore.png)](https:\u002F\u002Fwww.cqrb.cn\u002F24hourList.html)\n\n[• 需求回暖 8月大宗商品市场运行向好](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-09-05\u002F2767688_pc.html)[• 央行将开展5000亿元买断式逆回购操作](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-09-05\u002F2767687_pc.html)[• 美网：吴易昺不敌阿尔卡拉斯 止步32强](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-09-05\u002F2767685_pc.html)[• 从卖车到提供方案 中国电动卡车走向世界](https:\u002F\u002Fwww.cqrb.cn\u002Fshishi\u002F2026-09-05\u002F2767666_pc.html)\n\n![Image 44](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fcbjp.png)\n\n重报深一度 ![Image 45](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n重报观察 ![Image 46](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n重报圆桌会 ![Image 47](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n理响青年 ![Image 48](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\nYouth Insights ![Image 49](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n思想周刊 ![Image 50](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n理响少年 ![Image 51](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n红岩周刊 ![Image 52](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n双城周刊 ![Image 53](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n融媒工作室 ![Image 54](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n新重庆夜读 ![Image 55](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fdown.png)\n\n[• 重报深一度｜以智能化为牵引 重庆与中国长安合作跑出“加速度”](https:\u002F\u002Fwww.cqrb.cn\u002Fjingji\u002Fguancha\u002F2026-09-02\u002F2765924_pc.html)[• 重报深一度｜薄雾里的“希望专线” 让山里娃的上学路从两小时变为半小时](https:\u002F\u002Fwww.cqrb.cn\u002Fjingji\u002Fguancha\u002F2026-09-01\u002F2764948_pc.html)[• 重报深一度｜频频加码落子 中国电气装备为何坚定看好重庆](https:\u002F\u002Fwww.cqrb.cn\u002Fjingji\u002Fguancha\u002F2026-08-31\u002F2764103_pc.html)[• 重报深一度｜聚合力 盯隐患 快处置 提能力 百日攻坚织密群防群治“安全网”](https:\u002F\u002Fwww.cqrb.cn\u002Fminshengdongxian\u002F2026-08-25\u002F2759535_pc.html)[• 重报深一度｜从“两院一湾”加速崛起看重庆人工智能布局的三重逻辑](https:\u002F\u002Fwww.cqrb.cn\u002Fjingji\u002Fguancha\u002F2026-08-21\u002F2755991_pc.html)\n\n[查看更多![Image 56](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002FrighIcon.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002F2024cbsyd\u002F)\n\n[![Image 57](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F05\u002F26\u002Fbrowser\u002F203\u002F17797957132411434383939928740.5.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fkaijuqibushiwuwu%C2%B7jianshexiandaihuaxinzhongqing)\n\n[![Image 58](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F08\u002F04\u002Fbrowser\u002F528\u002F178581919667268519610241353470.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fqunfangqunzhibairigongjian)\n\n[![Image 59](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F07\u002F14\u002Fbrowser\u002F203\u002F178399625844763230628127145416.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fxiangxinerxing%E2%80%94%E2%80%94gaoshuipingjianshechuangxinqiangshi)\n\n[![Image 60](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F07\u002F02\u002Fbrowser\u002F203\u002F178297729550675545040406868270.png)](https:\u002F\u002Fact.cqrb.cn\u002F2026h1\u002F07byxsd\u002Fhome)\n\n[![Image 61](https:\u002F\u002Fimage.cqrb.cn\u002F2025-10-24\u002F1761285958134_qge8d5j6lq.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fshenruxuexiguanchedangdeershijiesizhongquanhuijingshen)\n\n[![Image 62](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F05\u002F26\u002Fbrowser\u002F203\u002F17797957132411434383939928740.5.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fkaijuqibushiwuwu%C2%B7jianshexiandaihuaxinzhongqing)\n\n[![Image 63](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F08\u002F04\u002Fbrowser\u002F528\u002F178581919667268519610241353470.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fqunfangqunzhibairigongjian)\n\n[![Image 64](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fcountry.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_8.html)\n\n[铜梁](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Ftongliangpczhuanti\u002F)[綦江](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fqijiangpczhuanti\u002F)[大足](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fdazupczhuanti\u002F)[璧山](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fbishanpczhuanti\u002F)[南川](https:\u002F\u002Fwww.cqrb.cn\u002Fcontry\u002Fdy50\u002F)[北碚](https:\u002F\u002Fwww.cqrb.cn\u002Fcontry\u002Fdy16\u002F)\n\n[更多![Image 65](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fmore.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Flist_8.html)\n\n[视频｜百亩大棚迎丰收！ 云阳县泥溪镇无花果挂满枝头](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Fnongpin\u002F2026-09-04\u002F2767517_pc.html)\n\n[群防群治百日攻坚·一线蹲点｜山体出现裂缝 武隆赵家乡应急转移3户10人](https:\u002F\u002Fwww.cqrb.cn\u002Fdisijii\u002F2026-09-04\u002F2767497_pc.html)\n\n[群防群治百日攻坚·滚动发布｜守护市民“头顶上的安全” 涪陵打响高空广告设施专项排查整治攻坚战](https:\u002F\u002Fwww.cqrb.cn\u002Fdisijii\u002F2026-09-04\u002F2767494_pc.html)\n\n[群防群治百日攻坚·滚动发布｜万盛经开区石林镇 153个“十户联防体”把安全防线扎进村组院坝](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-04\u002F2767487_pc.html)\n\n[![Image 66](https:\u002F\u002Fimage.cqrb.cn\u002F2024-11-23\u002F1732334613390_0.059875330458617926.jpeg)](https:\u002F\u002Fact.cqrb.cn\u002F2024h1\u002F1128dwgk\u002Fhome)\n\n[![Image 67](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F08\u002F12\u002Fbrowser\u002F203\u002F178651932255319481328884828364.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fyujianwangluowenmingxingdong)\n\n[![Image 68](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F06\u002F30\u002Fbrowser\u002F203\u002F178279039357020134769717062960.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fjizhongzhengzhi%C2%B7bianhuakandejian)\n\n[![Image 69](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F03\u002F11\u002Fbrowser\u002F203\u002F177321988167734696320003991212.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fgenzhedangankanzhongqing)\n\n[![Image 70](https:\u002F\u002Fimage.cqrb.cn\u002F2025-06-24\u002F1750724448197_8ebk3jddmm.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fdangbaojizheyixiandundian)\n\n[![Image 71](https:\u002F\u002Fimage.cqrb.cn\u002F2025-12-10\u002F1765356091840_lwyqjf3d98.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fquanweifabu)\n\n[![Image 72](https:\u002F\u002Fimage.cqrb.cn\u002F2025-07-17\u002F1752744385009_s2xydg6je7.jpeg)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fminshengweida)\n\n[![Image 73](https:\u002F\u002Fimage.cqrb.cn\u002F2024-11-23\u002F1732334613390_0.059875330458617926.jpeg)](https:\u002F\u002Fact.cqrb.cn\u002F2024h1\u002F1128dwgk\u002Fhome)\n\n[![Image 74](https:\u002F\u002Fimage2.cqrb.cn\u002Fpublic\u002F2026\u002F08\u002F12\u002Fbrowser\u002F203\u002F178651932255319481328884828364.png)](https:\u002F\u002Fwww.cqrb.cn\u002Ftopics\u002Fyujianwangluowenmingxingdong)\n\n[![Image 75](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fqiza.png)](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n[友情链接](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html) | [区县圈](https:\u002F\u002Fwww.cqrb.cn\u002Fxiangcun\u002Ffabu\u002F2026-09-03\u002F2766119_pc.html)\n\n[新华网](https:\u002F\u002Fwww.xinhuanet.com\u002F)[人民网](https:\u002F\u002Fwww.people.com.cn\u002F)[央视网](https:\u002F\u002Fwww.cntv.cn\u002F)[中新网](https:\u002F\u002Fwww.chinanews.com\u002F)[中国日报网](https:\u002F\u002Fwww.chinadaily.com.cn\u002F)[中国青年网](https:\u002F\u002Fwww.youth.cn\u002F)[中国经济网](https:\u002F\u002Fwww.ce.cn\u002F)[光明网](https:\u002F\u002Fwww.gmw.cn\u002F)[中国政府网](https:\u002F\u002Fwww.gov.cn\u002F)[国新办](https:\u002F\u002Fwww.scio.gov.cn\u002F)[求是理论网](https:\u002F\u002Fwww.qstheory.cn\u002F)\n\n[南岸](http:\u002F\u002Fwww.cqna.com.cn\u002F)[大渡口](http:\u002F\u002Fwww.ddknews.gov.cn\u002F)[长寿](https:\u002F\u002Fwww.ccs.cn\u002F)[南川](https:\u002F\u002Fwww.cqncnews.com\u002F)[璧山](https:\u002F\u002Fwww.bswxw.com\u002F)[城口](https:\u002F\u002Fwww.cqck.gov.cn\u002F)[丰都](http:\u002F\u002Fwww.cqfd.cn\u002F)[忠县](http:\u002F\u002Fwww.zzxw.net\u002F)[云阳](https:\u002F\u002Fwww.yunyangwang.com\u002F)[奉节](http:\u002F\u002Fwww.xfjw.net\u002F)[酉阳](https:\u002F\u002Fwww.yyxww.net\u002F)[武隆](http:\u002F\u002Fwww.cqwulong.cn\u002F)[彭水](http:\u002F\u002Fwww.cqps.gov.cn\u002F)\n\n[网站首页](https:\u002F\u002Fwww.cqrb.cn\u002F)| [重报集团](https:\u002F\u002Fwww.cqrb.cn\u002Fwangzhanxinxi\u002F2025-08-08\u002F2377615_pc.html)| [关于我们](https:\u002F\u002Fwww.cqrb.cn\u002Fwangzhanxinxi\u002F2025-08-08\u002F2377614_pc.html)| [广告业务](https:\u002F\u002Fwww.cqrb.cn\u002Fwangzhanxinxi\u002F2025-08-08\u002F2377613_pc.html)| [联系我们](https:\u002F\u002Fwww.cqrb.cn\u002Fwangzhanxinxi\u002F2025-08-11\u002F2379034_pc.html)\n\nCopyright © 2000-2022 CQNEWS Corporation, All Rights Reserved.\n\n重庆日报版权所有 未经书面授权 不得复制或建立镜像\n\n地址：重庆市两江新区同茂大道416号 邮编：401120 广告招商：023-63907707 传真：023-63907104 [违法和不良信息举报中心热线：12377](http:\u002F\u002Fwww.12377.cn\u002F)\n\n互联网新闻信息服务许可证编号50120180001 互联网出版许可证号：（署）网出证（渝）字002号 [渝ICP备17015920号](http:\u002F\u002Fbeian.miit.gov.cn\u002F)\n\n![Image 76](https:\u002F\u002Fwww.cqrb.cn\u002Fchannel\u002Fxcq_resource\u002Fstatic\u002Fimg\u002Fgabei2017@2x.png)渝公网安备 50011202500747号\n\n[站长统计](https:\u002F\u002Fwww.cnzz.com\u002Fstat\u002Fwebsite.php?web_id=5047942 \"站长统计\")","重庆日报","2026-09-03T00:00:00Z","报道",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},24,20,16,7,1,"报道山东农田遥感监测应用，展现生产方式变革，具省级影响力和实质内容。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","山东","农业遥感","天空地一体化","卫星巡田",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51,58,64],{"code":32,"score":45,"supported":46,"title":47,"abstract":49,"tags":50},12,true,[48],"遥感",[48],[28],{"code":52,"score":53,"supported":46,"title":54,"abstract":55,"tags":57},"F5",3,[],[56],"农机",[],{"code":59,"score":53,"supported":46,"title":60,"abstract":61,"tags":63},"I5",[],[62],"物联网",[],{"code":65,"score":21,"supported":14,"title":66,"abstract":67,"tags":68},"I1",[],[],[26],[70,71],"天空地一体化 农业遥感 卫星巡田 智慧农业","天空地一体化 农业遥感","天空地一体化农业遥感卫星巡田智慧农业-1682",2,"2026-09-05T00:04:38.299799Z",{"total":76,"page":21,"page_size":76,"items":77},6,[78,184,247,298,371,450],{"id":79,"title":80,"url":81,"summary":82,"summary_zh":83,"content":8,"source_name":84,"source_url":81,"published_at":85,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":87,"score_detail":88,"sources":93,"tags":95,"primary_topic":99,"secondary_topics":105,"classification":113,"search_phrases":149,"slug":152,"view_count":153,"doi":154,"paper":155,"created_at":183},5573,"Improving alfalfa nitrogen estimation with canopy structural priors from DSSAT–PROSAIL and UAV hyperspectral data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128375","Accurate estimation of nitrogen (N) concentration in alfalfa ( Medicago sativa L .) supports forage quality assessment and harvest scheduling. Empirical remote sensing models often overfit because of confounding effects of three-dimensional canopy structure. Incorporating structural parameters can stabilize biochemical inversions, but concurrent in situ morphological measurements are difficult to acquire at scale. We developed the Morphology-Aware Latent Embedding Network (MALENet), a hybrid framework integrating physiological and morphological mechanisms with hyperspectral data. The Decision Support System for Agrotechnology Transfer (DSSAT), coupled with the PROSAIL radiative transfer model, generated a structurally rich synthetic hyperspectral prior. A convolutional neural network (CNN) with a Squeeze-and-Excitation (SE) attention mechanism, was pre-trained on these data to distill ecophysiological knowledge into a dense latent representation. This mechanistically derived embedding was then fused with empirical hyperspectral measurements collected under diverse field conditions. Evaluation using multi-year field quadrats in the Hexi Corridor showed improved predictive performance ( R² = 0.71, RMSE = 0.30%) relative to conventional machine learning and deep learning models (LASSO-ANN: R² = 0.61; CNN: R² = 0.66). Feature attribution indicated that MALENet used near-infrared multiple scattering (58.3% attribution) as a structural proxy to calibrate nitrogen concentration retrieval against the confounding effects of canopy architecture. Despite constraints imposed by sample size and PROSAIL's 1D canopy assumption, these findings demonstrate the potential of physically guided deep learning to use structural information for agricultural trait retrieval in precision forage management.","准确估算紫花苜蓿（Medicago sativa L.）的氮浓度有助于饲草品质评估和收获期安排。经验性遥感模型常因三维冠层结构的混杂效应而出现过拟合。引入结构参数可以稳定生化反演，但同步开展原位形态学测量难以大规模获取。我们开发了形态感知潜在嵌入网络（Morphology-Aware Latent Embedding Network，MALENet），这是一个将生理与形态机制同高光谱数据相结合的混合框架。农业技术转移决策支持系统（Decision Support System for Agrotechnology Transfer，DSSAT）与PROSAIL辐射传输模型耦合，生成了结构信息丰富的合成高光谱先验数据。在此基础上，预训练了一个带有挤压—激励（Squeeze-and-Excitation，SE）注意力机制的卷积神经网络（convolutional neural network，CNN），将生态生理学知识提炼为稠密潜在表征。随后，将这一机制性导出的嵌入与在不同田间条件下采集的经验性高光谱测量数据相融合。利用河西走廊多年田间样方进行的评估显示，相较于传统机器学习和深度学习模型（LASSO-ANN：R² = 0.61；CNN：R² = 0.66），预测性能有所提升（R² = 0.71，RMSE = 0.30%）。特征归因表明，MALENet利用近红外多次散射（归因占比58.3%）作为结构代理，以校准氮浓度反演，抵御冠层结构的混杂效应。尽管受样本量和PROSAIL一维冠层假设的限制，这些发现表明，物理引导的深度学习有潜力利用结构信息，在精准饲草管理中进行农业性状反演。","European Journal of Agronomy","2026-10-21T00:00:00Z","论文",80,{"impact":19,"substance":89,"depth":90,"authority":91,"freshness":13,"relevant":21,"comment":92},22,18,14,"该研究将作物模型与辐射传输模型耦合生成结构先验，并结合无人机高光谱数据反演苜蓿氮素，方法新颖、田间验证扎实，对精准饲草管理有参考价值，值得进入每日精选。",[94],{"name":84,"url":81},[26,96,28,97,98],"农业人工智能","氮素监测","紫花苜蓿",{"code":100,"slug":101,"name":102,"path":103,"parent_code":104},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[106,107],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":108,"slug":109,"name":110,"path":111,"parent_code":112},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":39,"locked":14,"version":40,"method":41,"evidence":114},{"candidates":115,"agricultural_evidence":46},[116,122,129,135,145],{"code":32,"score":90,"supported":46,"title":117,"abstract":119,"tags":121},[118],"hyperspectral",[48,120,118],"remote sensing",[28],{"code":100,"score":123,"supported":46,"title":124,"abstract":126,"tags":128},15,[125],"alfalfa",[127,125],"苜蓿",[98],{"code":108,"score":13,"supported":46,"title":130,"abstract":131,"tags":134},[],[132,127,133],"饲草","forage",[98],{"code":136,"score":13,"supported":46,"title":137,"abstract":138,"tags":144},"I2",[],[139,140,141,142,143],"深度学习","机器学习","machine learning","deep learning","decision support",[96],{"code":65,"score":21,"supported":14,"title":146,"abstract":147,"tags":148},[],[],[26],[150,151],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573",0,"10.1016\u002Fj.eja.2026.128375",{"doi":154,"openalex_id":156,"authors":157,"venue":84,"cited_by_count":153,"oa_url":81,"card":176,"direction":180,"ingested_from":182},"W7223154576",[158,160,162,164,166,169,171,174],{"name":159,"orcid":8},"Shuai Fu",{"name":161,"orcid":8},"Yunhao Li",{"name":163,"orcid":8},"Chunli Miao",{"name":165,"orcid":8},"Jie Liu",{"name":167,"orcid":168},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":170,"orcid":8},"Yongjia Hu",{"name":172,"orcid":173},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":175,"orcid":8},"吴彩霞",{"tldr":177,"method":178,"finding":179,"direction":180,"opportunity":181},"构建MALENet融合DSSAT-PROSAIL结构先验与无人机高光谱，提升苜蓿氮浓度估算精度。","DSSAT耦合PROSAIL生成合成高光谱先验，预训练CNN-SE网络，再融合田","MALENet精度优于传统机器学习和深度学习模型，R²达0.71，近红外多次散射作为结构代理贡献58","农业遥感与作物表型","可探索将作物模型结构先验迁移至其他牧草或作物生化参数反演，并缓解PROSAIL一维冠层假设局限。","openalex","2026-10-22T11:20:39.622844Z",{"id":185,"title":186,"url":187,"summary":188,"summary_zh":8,"content":8,"source_name":189,"source_url":8,"published_at":85,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":190,"score_detail":191,"sources":193,"tags":195,"primary_topic":199,"secondary_topics":204,"classification":212,"search_phrases":234,"slug":237,"view_count":21,"doi":8,"paper":238,"created_at":246},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21",82,{"impact":90,"substance":89,"depth":90,"authority":91,"freshness":13,"relevant":21,"comment":192},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[194],{"name":189,"url":187},[26,28,196,197,198],"作物表型","无人机多光谱","小麦渍害",{"code":200,"slug":201,"name":202,"path":203,"parent_code":104},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[205,206],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":207,"slug":208,"name":209,"path":210,"parent_code":211},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":39,"locked":14,"version":40,"method":41,"evidence":213},{"candidates":214,"agricultural_evidence":46},[215,220,224,230],{"code":200,"score":216,"supported":46,"title":217,"abstract":218,"tags":219},11,[202],[202],[],{"code":32,"score":216,"supported":46,"title":221,"abstract":222,"tags":223},[197],[],[196,28,197],{"code":207,"score":225,"supported":46,"title":226,"abstract":228,"tags":229},8,[227],"渍害",[],[],{"code":65,"score":21,"supported":14,"title":231,"abstract":232,"tags":233},[],[],[26],[235,236],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":8,"openalex_id":8,"authors":239,"venue":8,"cited_by_count":153,"oa_url":8,"card":240,"direction":180,"ingested_from":245},[],{"tldr":241,"method":242,"finding":243,"direction":180,"opportunity":244},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z",{"id":248,"title":249,"url":250,"summary":251,"summary_zh":8,"content":8,"source_name":252,"source_url":8,"published_at":253,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":254,"score_detail":255,"sources":259,"tags":261,"primary_topic":262,"secondary_topics":263,"classification":266,"search_phrases":286,"slug":289,"view_count":153,"doi":8,"paper":290,"created_at":297},5296,"雷添杰研究员团队《基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别》","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-16\u002Fdoc-inivmprm8363597.shtml","《智慧农业(中英文)》2026年第8卷第4期刊载梁万杰、刘晓君、雷添杰等论文,在小麦拔节—抽穗和抽穗—灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控、氨基酸调控控制试验;利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像建立数据集,基于VGG21模型构建识别模型,发现硅肥调控样本识别性能最好,识别精度最高,具良好鲁棒性和可扩展性,可为小麦渍害综合防控提供理论与技术支持。","智慧农业(中英文)(2026,8(4))","2026-10-16T00:00:00Z",76,{"impact":19,"substance":256,"depth":257,"authority":91,"freshness":225,"relevant":21,"comment":258},21,17,"核心期刊论文，方法新颖、结论可靠，对小麦渍害防控有实用价值，值得进入每日精选。",[260],{"name":252,"url":250},[26,28,196,197,198],{"code":200,"slug":201,"name":202,"path":203,"parent_code":104},[264,265],{"code":207,"slug":208,"name":209,"path":210,"parent_code":211},{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":267},{"candidates":268,"agricultural_evidence":46},[269,273,277,281],{"code":200,"score":216,"supported":46,"title":270,"abstract":271,"tags":272},[202],[202],[],{"code":207,"score":216,"supported":46,"title":274,"abstract":275,"tags":276},[227],[227],[],{"code":32,"score":216,"supported":46,"title":278,"abstract":279,"tags":280},[197],[],[196,28,197],{"code":65,"score":282,"supported":46,"title":283,"abstract":284,"tags":285},4,[],[26],[26],[287,288],"雷添杰 小麦渍害 无人机多光谱","VGG21 小麦渍害 识别模型","雷添杰小麦渍害无人机多光谱-5296",{"doi":8,"openalex_id":8,"authors":291,"venue":8,"cited_by_count":153,"oa_url":8,"card":292,"direction":180,"ingested_from":245},[],{"tldr":293,"method":294,"finding":295,"direction":180,"opportunity":296},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4采集冠层多光谱图像，构建VGG21识别模型。","硅肥调控样本识别性能最好、精度最高，模型鲁棒可扩展。","可探索多生育期多光谱特征与不同调控措施的耦合机制，并扩展到其他作物渍害监测。","2026-10-19T00:07:48.071055Z",{"id":299,"title":300,"url":301,"summary":302,"summary_zh":303,"content":8,"source_name":304,"source_url":301,"published_at":253,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":305,"score_detail":306,"sources":309,"tags":311,"primary_topic":314,"secondary_topics":315,"classification":320,"search_phrases":343,"slug":346,"view_count":21,"doi":347,"paper":348,"created_at":370},5165,"Proximal Remote Sensing of Oil Palm Basal Stem Rot Using Deep Learning Vision Algorithms and Ground-based Images","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.31","Basal Stem Rot (BSR), caused by Ganoderma boninense, threatens oil palm productivity in Southeast Asia.This study develops and benchmarks a low-cost remote sensing framework for BSR severity diagnosis from smartphone-captured RGB trunk images, evaluating two pathways for future field deployment.The first pairs YOLO detection with a Random Forest classifier: YOLO26n gave the best accuracy-to-cost trade-off among three nanovariants for localizing BSR symptoms (mushroom, rot, white-button), and the end-to-end YOLO26n+RF pipeline achieved 0.83 accuracy and macro-F1 of 0.79 across Healthy, Mild, Moderate, and Severe classes.Rot was consistently the hardest symptom to localize, owing to its diffuse, boundary-ambiguous appearance.The second pathway trained four image classifiers (EfficientNet-B0, MobileNetV2, Swin-Tiny, and ConvNeXt-V2-Tiny) directly on severity labels, with ConvNeXt-V2-Tiny performing best (0.83 accuracy, 0.83 macro-F1).Both pathways performed well at severity extremes but struggled with Moderate, reflecting visual overlap between stages.SHAP analysis identified rot-area ratio and fruiting-body count as top predictors.These offline results show accurate BSR diagnosis is potentially achievable from smartphone imagery, laying groundwork for future on-device deployment.","由灵芝（Ganoderma boninense）引起的基茎腐病（Basal Stem Rot, BSR）威胁着东南亚油棕的生产力。本研究开发并基准测试了一个低成本遥感框架，用于从智能手机拍摄的RGB树干图像中诊断基茎腐病的严重程度，并评估了未来田间部署的两条技术路径。第一条路径将YOLO检测与随机森林分类器相结合：在三种纳米变体中，YOLO26n在定位基茎腐病症状（蘑菇、腐烂、白钮）方面实现了最佳的精度-成本权衡，端到端的YOLO26n+RF流程在健康、轻度、中度和重度四个类别上达到了0.83的准确率和0.79的宏F1值。腐烂始终是最难定位的症状，原因在于其弥散且边界模糊的外观。第二条路径直接在严重程度标签上训练了四个图像分类器（EfficientNet-B0、MobileNetV2、Swin-Tiny和ConvNeXt-V2-Tiny），其中ConvNeXt-V2-Tiny表现最佳（准确率0.83，宏F1值0.83）。两条路径在严重程度极端类别上表现良好，但在中度类别上表现欠佳，反映出各阶段之间存在视觉重叠。SHAP分析确定腐烂面积比和子实体数量为最重要的预测因子。这些离线结果表明，利用智能手机图像有望实现准确的基茎腐病诊断，为未来设备端部署奠定了基础。","International journal of intelligent engineering and systems",69,{"impact":45,"substance":18,"depth":19,"authority":45,"freshness":307,"relevant":21,"comment":308},9,"该研究利用智能手机图像与深度学习实现油棕基腐病严重度诊断，方法新颖、结论可靠，但属细分作物研究，产业影响有限，适合作为技术类精选。",[310],{"name":304,"url":301},[26,28,139,312,313],"油棕","病害诊断",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[316],{"code":136,"slug":317,"name":318,"path":319,"parent_code":36},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":39,"locked":14,"version":40,"method":41,"evidence":321},{"candidates":322,"agricultural_evidence":46},[323,327,332,339],{"code":32,"score":123,"supported":46,"title":324,"abstract":325,"tags":326},[120],[48,120],[28],{"code":136,"score":45,"supported":46,"title":328,"abstract":329,"tags":331},[142],[330],"YOLO",[139],{"code":333,"score":76,"supported":46,"title":334,"abstract":335,"tags":338},"B5",[],[336,337],"蘑菇","mushroom",[],{"code":65,"score":21,"supported":14,"title":340,"abstract":341,"tags":342},[],[],[26],[344,345],"油棕 基腐病 遥感","Ganoderma boninense 智能手机 检测","油棕基腐病遥感-5165","10.22266\u002Fijies2026.1130.31",{"doi":347,"openalex_id":349,"authors":350,"venue":304,"cited_by_count":153,"oa_url":301,"card":365,"direction":180,"ingested_from":182},"W7222626135",[351,354,357,359,362],{"name":352,"orcid":353},"Wan Siu Hong","https:\u002F\u002Forcid.org\u002F0000-0002-8254-4962",{"name":355,"orcid":356},"Jonathan Yong Chung Ee","https:\u002F\u002Forcid.org\u002F0000-0003-4079-8005",{"name":358,"orcid":8},"Jin Yuan Chan",{"name":360,"orcid":361},"Mohamad Izzuddin Anuar","https:\u002F\u002Forcid.org\u002F0000-0002-4929-5175",{"name":363,"orcid":364},"Mahmud Iwan Solihin","https:\u002F\u002Forcid.org\u002F0000-0002-5293-7466",{"tldr":366,"method":367,"finding":368,"direction":180,"opportunity":369},"用手机拍摄油棕树干图像，结合深度学习检测与分类，实现基腐病严重度诊断。","YOLO26n+随机森林与四种图像分类器，基于手机RGB图像，SHAP解释。","两条路径准确率均约0.83，中度病级最难区分，腐区比例与子实体数为关键预测因子。","可探索轻量化模型在手机端离线部署，并扩充多地区、多品种数据以提升中度病级辨识。","2026-10-17T23:30:28.307953Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":376,"content":8,"source_name":377,"source_url":374,"published_at":378,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":379,"score_detail":380,"sources":383,"tags":385,"primary_topic":388,"secondary_topics":389,"classification":396,"search_phrases":421,"slug":424,"view_count":153,"doi":425,"paper":426,"created_at":449},4898,"An Interpretable Deep Learning Framework for Spatial Prediction of Soil Salinity Using Multi-Source Remote Sensing and Environmental Data: A Case Study of Cangzhou, Hebei Province, China","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206465","Soil salinity poses a significant challenge to agricultural productivity and sustainable land management in coastal and semi-arid regions. Soil salinity in coastal agricultural regions is controlled by complex interactions among surface conditions, groundwater processes, soil properties, and terrain characteristics. Accurate spatial prediction requires integrating remote sensing observations with environmental information that represents these processes. This study presents a multi-source deep learning framework that integrates Sentinel-2-derived spectral indices with environmental covariates for regional soil salinity spatial prediction under the environmental conditions of the 2024 sampling period. SHapley Additive exPlanations (SHAP) is employed to quantify the contribution of environmental variables within the prediction framework and improve model interpretability. A convolutional neural network (CNN) incorporating a squeeze-and-excitation (SE) attention mechanism is developed as a nonlinear feature representation framework for integrating heterogeneous predictors, while the Crested Porcupine Optimizer (CPO) is used to optimize model hyperparameters. The proposed framework achieved the highest predictive performance among the benchmark models, with an R2 of 0.785, an RMSE of 0.928, and an MAE of 0.720. Integrating environmental covariates with spectral features further improves the prediction performance, increasing the R2 from 0.701 to 0.785. The results indicate the potential of integrating multi-source environmental information with interpretable deep learning for spatial prediction of near-surface soil salinity under similar coastal agricultural conditions.","土壤盐渍化对沿海和半干旱地区的农业生产力和可持续土地管理构成了重大挑战。沿海农业区域的土壤盐渍化受地表条件、地下水过程、土壤属性和地形特征之间复杂相互作用的控制。准确的空间预测需要将遥感观测与表征这些过程的环境信息相结合。本研究提出了一种多源深度学习框架，该框架将Sentinel-2衍生的光谱指数与环境协变量相结合，用于2024年采样期环境条件下的区域土壤盐渍化空间预测。采用SHapley加法解释（SHAP）方法量化预测框架中环境变量的贡献并提高模型可解释性。开发了一种融合压缩-激励（SE）注意力机制的卷积神经网络（CNN）作为非线性特征表示框架，用于整合异质性预测因子，同时使用冠豪猪优化器（CPO）优化模型超参数。所提出的框架在基准模型中取得了最高的预测性能，R²为0.785，RMSE为0.928，MAE为0.720。将环境协变量与光谱特征相结合进一步提高了预测性能，R²从0.701提升至0.785。结果表明，在类似的沿海农业条件下，将多源环境信息与可解释深度学习相结合用于近地表土壤盐渍化空间预测具有潜力。","Sensors","2026-10-13T00:00:00Z",75,{"impact":19,"substance":256,"depth":257,"authority":381,"freshness":225,"relevant":21,"comment":382},13,"方法新颖、指标可靠，将多源遥感与可解释深度学习结合用于盐渍化空间预测，对沿海农业区土壤治理有参考价值。",[384],{"name":377,"url":374},[26,28,386,139,387],"可解释AI","土壤盐渍化",{"code":136,"slug":317,"name":318,"path":319,"parent_code":36},[390,391],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":392,"slug":393,"name":394,"path":395,"parent_code":211},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"status":39,"locked":14,"version":40,"method":41,"evidence":397},{"candidates":398,"agricultural_evidence":46},[399,403,407,412,417],{"code":136,"score":19,"supported":46,"title":400,"abstract":401,"tags":402},[142],[139,142],[386,139],{"code":32,"score":123,"supported":46,"title":404,"abstract":405,"tags":406},[120],[48,120],[28],{"code":392,"score":91,"supported":46,"title":408,"abstract":409,"tags":411},[393],[410,393],"土壤",[],{"code":207,"score":53,"supported":46,"title":413,"abstract":414,"tags":416},[],[415],"干旱",[],{"code":65,"score":21,"supported":14,"title":418,"abstract":419,"tags":420},[],[],[26],[422,423],"沧州 土壤盐渍化 遥感","Sentinel-2 土壤盐分 预测","沧州土壤盐渍化遥感-4898","10.3390\u002Fs26206465",{"doi":425,"openalex_id":427,"authors":428,"venue":377,"cited_by_count":153,"oa_url":374,"card":444,"direction":180,"ingested_from":182},"W7221715654",[429,432,435,437,440,442],{"name":430,"orcid":431},"Mingyuan Ye","https:\u002F\u002Forcid.org\u002F0009-0001-6434-5505",{"name":433,"orcid":434},"Peng Chen","https:\u002F\u002Forcid.org\u002F0000-0002-2549-6765",{"name":436,"orcid":8},"Junchi Ma",{"name":438,"orcid":439},"Bingxia Liu","https:\u002F\u002Forcid.org\u002F0000-0001-7958-7112",{"name":441,"orcid":8},"Jiahao Qi",{"name":443,"orcid":8},"Yuan Jing",{"tldr":445,"method":446,"finding":447,"direction":180,"opportunity":448},"构建融合多源遥感与环境变量的可解释深度学习框架，预测沧州土壤盐分空间分布。","Sentinel-2光谱指数+环境协变量，CNN-SE注意力，CPO优化超参数，","环境协变量与光谱特征结合将R²从0.701提升至0.785，模型性能最优。","可迁移至其他滨海盐渍区，并探索时序动态预测与多深度土壤盐分协同反演。","2026-10-14T23:30:27.313838Z",{"id":451,"title":452,"url":453,"summary":454,"summary_zh":455,"content":8,"source_name":456,"source_url":453,"published_at":457,"category":86,"cover_url":8,"hotness":13,"is_selected":14,"score":87,"score_detail":458,"sources":461,"tags":463,"primary_topic":466,"secondary_topics":467,"classification":468,"search_phrases":497,"slug":500,"view_count":21,"doi":501,"paper":502,"created_at":520},4563,"Seeing Crops in 3D: Remote Sensing for Smarter Precision Farming","https:\u002F\u002Fdoi.org\u002F10.12688\u002Fopenreseurope.25171.1","The growing adoption of digital technologies in agriculture is opening new opportunities for improving productivity, sustainability and resource efficiency through data-driven decision making. This paper presents the integrated precision-agriculture framework developed by RFSAT Limited within the H2020 AgriBIT project and currently being further enhanced through the ENACT project. The framework combines Internet-of-Things (IoT) sensing, centimetre-accuracy Global Navigation Satellite System (GNSS) positioning, high-resolution multispectral remote sensing and Artificial Intelligence (AI) analytics into a single smart-farming solution. A key enabler is a low-cost, centimetre-accurate GNSS receiver developed by RFSAT, which allows precise georeferencing of aerial and ground observations and, in turn, the generation of high-resolution multispectral 3D models of crop canopies with spatial resolution exceeding 1 cm\u002Fpixel. These digital representations support detailed monitoring of crop growth, canopy development, biomass distribution and plant health throughout the season. Fused with an IoT monitoring infrastructure of environmental and microclimatic sensors, the georeferenced remote-sensing products form a comprehensive digital twin of the agricultural environment, over which machine-learning techniques automatically identify and localise crop anomalies including water stress, nutrient deficiencies, disease outbreaks and pest infestations. The technologies have been validated at operational pilot sites across Greece, Portugal and Italy, spanning orchards, vineyards and other high-value crops, where the combination of centimetre positioning, multispectral 3D modelling, IoT monitoring and AI analytics substantially improved monitoring accuracy, reduced input consumption and enhanced management decisions.","数字技术在农业中的日益普及，正通过数据驱动的决策为提升生产力、可持续性和资源效率开辟新的机遇。本文介绍了RFSAT有限公司在H2020 AgriBIT项目中开发的综合精准农业框架，该框架目前正通过ENACT项目进一步完善。该框架将物联网（IoT）传感、厘米级精度的全球导航卫星系统（GNSS）定位、高分辨率多光谱遥感以及人工智能（AI）分析整合为一个智慧农业解决方案。一个关键的使能因素是由RFSAT开发的低成本、厘米级精度GNSS接收器，它能够对航空和地面观测进行精确的地理参照，进而生成空间分辨率超过1厘米\u002F像素的作物冠层高分辨率多光谱三维模型。这些数字表示支持在整个生长季对作物生长、冠层发育、生物量分布和植物健康进行详细监测。通过与由环境和小气候传感器组成的物联网监测基础设施相融合，地理参照的遥感产品形成了农业环境的综合数字孪生，机器学习技术在此基础上自动识别和定位作物异常，包括水分胁迫、养分缺乏、病害暴发和虫害侵扰。这些技术已在希腊、葡萄牙和意大利的运营试点基地进行了验证，涵盖果园、葡萄园和其他高价值作物，其中厘米级定位、多光谱三维建模、物联网监测和AI分析的结合大幅提高了监测精度、降低了投入品消耗并改善了管理决策。","Open Research Europe","2026-10-09T00:00:00Z",{"impact":90,"substance":89,"depth":459,"authority":381,"freshness":225,"relevant":21,"comment":460},19,"欧盟H2020项目论文，融合厘米级GNSS、多光谱3D建模与AI分析，方法新颖且多国验证，对智慧农业技术路线有参考价值。",[462],{"name":456,"url":453},[26,96,28,464,465],"数字孪生","精准农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":469},{"candidates":470,"agricultural_evidence":46},[471,476,481,486,491],{"code":32,"score":90,"supported":46,"title":472,"abstract":473,"tags":475},[120],[48,120,474],"multispectral",[28],{"code":65,"score":45,"supported":46,"title":477,"abstract":478,"tags":480},[],[26,465,464,479],"digital twin",[464,26,465],{"code":136,"score":20,"supported":46,"title":482,"abstract":483,"tags":485},[],[140,484],"artificial intelligence",[96],{"code":59,"score":76,"supported":46,"title":487,"abstract":488,"tags":490},[],[62,489],"IoT",[],{"code":492,"score":53,"supported":46,"title":493,"abstract":494,"tags":496},"B2",[],[495],"葡萄",[],[498,499],"AgriBIT 精准农业 遥感","GNSS 多光谱 3D 作物","AgriBIT精准农业遥感-4563","10.12688\u002Fopenreseurope.25171.1",{"doi":501,"openalex_id":503,"authors":504,"venue":456,"cited_by_count":153,"oa_url":453,"card":514,"direction":519,"ingested_from":182},"W7221178461",[505,508,511],{"name":506,"orcid":507},"Artur Krukowski","https:\u002F\u002Forcid.org\u002F0000-0002-6635-7585",{"name":509,"orcid":510},"Emmanouela Vogiatzaki","https:\u002F\u002Forcid.org\u002F0000-0001-9239-2045",{"name":512,"orcid":513},"İzzet Kale","https:\u002F\u002Forcid.org\u002F0000-0001-5562-6885",{"tldr":515,"method":516,"finding":517,"direction":180,"opportunity":518},"提出融合物联网、厘米级GNSS、多光谱遥感和AI的精准农业框架，构建作物数字孪生。","低成本厘米级GNSS、多光谱3D建模、IoT传感器与机器学习，在希腊、葡萄牙、意","厘米定位与多光谱3D建模结合AI可提升监测精度、减少投入并改善管理决策。","可探索低成本厘米级GNSS与多光谱3D数字孪生在更多作物和区域的可扩展性及实时决策优化。","智慧农业 \u002F 农业物联网","2026-10-10T23:30:07.913557Z"]