[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2119":3,"related-2119":105},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":44,"search_phrases":73,"slug":76,"view_count":77,"doi":78,"paper":79,"created_at":104},2119,"Visual measurement for forage maize stubble height fusing cascaded neural networks and robust tracking","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112413","Visual measurement for forage maize stubble height fusing cascaded neural networks and robust tracking。Computers and Electronics in Agriculture","融合级联神经网络与鲁棒跟踪的饲用玉米留茬高度视觉测量。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-10T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,20,14,8,1,"核心期刊论文，提出级联神经网络与鲁棒跟踪融合的青贮玉米留茬高度视觉测量方法，方法新颖且面向智能收获装备，专业价值较高，但属细分技术进展，影响范围有限。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","机器视觉","青贮玉米","目标跟踪",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,56,62,68],{"code":32,"score":51,"supported":52,"title":53,"abstract":54,"tags":55},15,true,[33],[34,33],[29],{"code":39,"score":57,"supported":52,"title":58,"abstract":60,"tags":61},12,[59],"forage",[59],[29],{"code":63,"score":64,"supported":14,"title":65,"abstract":66,"tags":67},"I2",2,[],[],[27,28],{"code":69,"score":21,"supported":14,"title":70,"abstract":71,"tags":72},"I1",[],[],[26],[74,75],"农业人工智能 智慧农业 机器视觉 目标跟踪","农业人工智能 智慧农业","农业人工智能智慧农业机器视觉目标跟踪-2119",6,"10.1016\u002Fj.compag.2026.112413",{"doi":78,"openalex_id":80,"authors":81,"venue":10,"cited_by_count":96,"oa_url":9,"card":97,"direction":101,"ingested_from":103},"W7212174723",[82,84,86,89,91,93],{"name":83,"orcid":9},"Shanda Li",{"name":85,"orcid":9},"Jiuxiang Dai",{"name":87,"orcid":88},"Yangfan Luo","https:\u002F\u002Forcid.org\u002F0000-0001-8456-1304",{"name":90,"orcid":9},"Hu Shiyun",{"name":92,"orcid":9},"Duanxiang Lin",{"name":94,"orcid":95},"Zuoxi Zhao","https:\u002F\u002Forcid.org\u002F0000-0002-1834-8609",0,{"tldr":98,"method":99,"finding":100,"direction":101,"opportunity":102},"提出融合级联神经网络与鲁棒跟踪的视觉方法，测量饲用玉米留茬高度。","级联神经网络检测与鲁棒跟踪算法，结合视觉图像测量留茬高度。","该方法能准确测量饲用玉米留茬高度，为收获质量评估提供视觉方案。","农业遥感与作物表型","可探索多作物、复杂田间光照下的留茬高度实时测量与收获机自适应调控。","openalex","2026-09-11T23:30:01.912694Z",{"total":77,"page":21,"page_size":77,"items":106},[107,172,216,310,354,436],{"id":108,"title":109,"url":110,"summary":111,"summary_zh":9,"content":112,"source_name":113,"source_url":9,"published_at":114,"category":115,"cover_url":9,"hotness":13,"is_selected":14,"score":116,"score_detail":117,"sources":121,"tags":123,"primary_topic":128,"secondary_topics":129,"classification":137,"search_phrases":167,"slug":170,"view_count":21,"doi":9,"paper":9,"created_at":171},5123,"盐碱地里青贮玉米「争气」了 黑龙江省农科院「龙育15」「龙育17」松嫩平原盐碱旱田亩产全株三四吨","https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597377.html","黑龙江省农业科学院草业研究所承担的青贮玉米新品种示范推广及产业化应用项目,围绕松嫩平原西部盐碱化旱田选育的「龙育15」「龙育17」两个品种,在盐碱地块上平均增产超一成,亩产全株三四吨,粗淀粉含量达32%。项目组围绕保全苗、稳产量、提品质给种植企业做全流程服务,留茬30公分平衡产量与品质。项目建成1.2万亩高产优质栽培示范,每年在安达市推广3万亩以上,还走进内蒙古等周边饲草产区。千亩套种示范田里玉米垄沟套种燕麦,青贮玉米产量持平,每亩多收600多公斤燕麦,亩增收300多元,燕麦蛋白含量高,混进青贮补齐蛋白短板。","![Image 3](https:\u002F\u002Fstatics.kjrb.com.cn\u002Fresource\u002Fkjw\u002Findex\u002Fimages\u002Fshare_logo.jpg)\n\n[![Image 4](https:\u002F\u002Fstatics.kjrb.com.cn\u002Fresource\u002Fkjw\u002Findex\u002Fimages\u002Flogo.png)](http:\u002F\u002Fwww.stdaily.com\u002F)\n\n*   [时政](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fszxw\u002Fnode_357.html)\n*   [热点](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Frdxw\u002Fnode_327.html)\n*   [政务](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fzwxw\u002Fnode_362.html)\n*   [深瞳](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fstbd\u002Fnode_434.html)\n*   [访谈](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Ffangtan\u002Fnode_441.html)\n*   [视频](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fspxw\u002Fnode_701.html)\n*   [国际](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgjxw\u002Fnode_381.html)\n*   [地方](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fdfxw\u002Fnode_368.html)\n*   [专题](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fztxw\u002Fnode_335.html)\n*   [English](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002FEnglish\u002Findex.html)\n*   [滚动](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fnode_324.html)\n\n[![Image 5](https:\u002F\u002Fstatics.kjrb.com.cn\u002Fresource\u002Fkjw\u002Fimages\u002Ffdj.png)](https:\u002F\u002Fsearch.stdaily.com:8888\u002Ffounder\u002FNewSearchServlet.do?siteID=1)[登录](https:\u002F\u002Fwww.stdaily.com\u002Fapi\u002Fwebsite\u002FpersonalCenter.html?url=https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597377.html)[-](https:\u002F\u002Fwww.stdaily.com\u002Fapi\u002Fwebsite\u002FpersonalCenter.html)\n\n 所在位置： [中国科技网首页](https:\u002F\u002Fwww.stdaily.com\u002Findex.html)>[滚动](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fnode_324.html)> 正文 \n\n# 盐碱地里，青贮玉米“争气”了\n\n 2026-10-16 15:09:54 来源: 科技日报 点击数：\n\n![Image 6](https:\u002F\u002Fstatics.kjrb.com.cn\u002Fresource\u002Fkjw\u002Fimg\u002F20240301dzv.png)0\n\n[](javascript:; \"新浪微博\")[](javascript:; \"微信\")\n\n**科技日报记者 朱虹**\n\n暮秋的黑龙江省安达市天高云淡，一垄垄盐碱旱田刚翻过土，泛着浅浅的白霜。10月13日，记者跟随黑龙江省农科院草业研究所研究员林红，穿过连片田块，走进安达绿生源现代养殖场。还没进牛舍，一股青贮特有的酸香就扑面而来。黑白花奶牛次第低头，把脑袋埋进食槽，咀嚼声此起彼伏。饲养员抄起一捧青贮料，深绿的茎叶裹着饱满的籽粒，“这就是咱们的‘龙育15’‘龙育17’。”\n\n![Image 7](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597377_a90e9d31-3cb7-4c4d-b464-ab39a784e19ccopy.jpg)\n\n安达素有“中国牛城”之名，可松嫩平原西部这片土地，盐碱是绕不开的坎。土壤碱化重、地力弱，青贮玉米一度种不出像样的品质，干物质、淀粉指标上不去，优质饲草供不应求，牛越养越“挑食”。能不能在盐碱地里种出合格的青贮玉米，成了当地草畜产业躲不开的考题。而由黑龙江省农科院草业研究所承担的黑龙江省农业科技创新跨越工程项目——青贮玉米新品种示范推广及产业化应用，正是冲着这道题来的。\n\n“高产、优质，适合青贮饲料用途，这是我们选育最核心的标尺。”站在牛舍边，林红介绍，青贮玉米拼的是高淀粉、高干物质，“龙育15”“龙育17”的培育目标就是“产量和品质两头都要”。它们在盐碱地块上，平均增产超一成，亩产全株三四吨，粗淀粉含量能到32%，肉牛吃、长肉快，奶牛吃、奶量高。\n\n良种到手，技术指导一路跟到地头。项目组围绕保全苗、稳产量、提品质，给种植企业做全流程服务。“青贮玉米每亩达不到5000株，高产就没有前提。”林红说，从整地保墒到精准播种，再到田间管护，环环盯紧。\n\n![Image 8](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597377_a95e303c-16eb-4ad2-bd50-703dac8cdb0acopy.jpg)\n\n最难拿捏的，是收割那一刀。收矮了，产量看着高，可地不平，土跟着卷进饲料，营养也打了折扣；收高了，品质上去了，种植户又心疼收入。此前绿生源养殖场总经理周现平就为这一刀找过项目组。林红最终给出折中方案——留茬30公分，“既保产量，又守品质，现在牧场都认这个数”。牛舍里的青贮窖已经装得满满当当，新收的料压得瓷实，来年开窖，又是一窖好饭。\n\n品种在田里扎根，推广也在向外铺开。“龙育15”“龙育17”两个品种，项目建成1.2万亩高产优质栽培示范，每年在安达市推广3万亩以上，还走进内蒙古等周边饲草产区，带动松嫩平原盐碱化旱田地力提升、绿色高效增收。千亩套种示范田里，项目组在玉米垄沟里套种燕麦，青贮玉米产量和常规种植持平，每亩却多收600多公斤燕麦，亩增收300多元；燕麦蛋白含量高，混进青贮正好补齐蛋白短板，饲料品质和喂饲效果都跟着上了台阶。\n\n一方面，项目把良种良法送进地里；另一方面，企业把产业链拉得更长。绿生源依托自有的一万多亩基地，从种到收，再到加工销售，一气呵成，牛吃不完的青贮还能外销；养殖产生的粪污经处理后还田，反哺盐碱地，把“种好草、养好牛、肥好地”串成了闭环。\n\n夕阳把草料场镀成金色，青贮裹包在田埂边排开，“龙育15”“龙育17”在这扎下根。牛槽里多了料，田里多了收成，松嫩平原的青贮玉米，在这片曾经的薄地上“争气”了。\n\n（科技日报记者 朱虹 摄）\n\n责任编辑：王倩\n\n相关稿件：\n\n![Image 9](https:\u002F\u002Fstatics.kjrb.com.cn\u002Fresource\u002Fkjw\u002Fimages\u002Fpinglun.png)网友评论\n\n评论\n\n最热评论\n\n没有更多评论了\n\n[热点](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Frdxw\u002Fnode_327.html)\n\n[![Image 10](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597668_d4a99e88-e07d-450c-80c3-e7d7e181928f_1000x6664743058copy.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597668.html)\n\n[我国粮食仓储技术达到世界先进水平](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597668.html)\n\n[![Image 11](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597677_3b44ffad-1988-42b6-ab42-9b537814a0f9_853x5684924501copy.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597677.html)\n\n[铁路车次编排调整 超350公里时速动车组新增X字头](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597677.html)\n\n[![Image 12](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597517_ba940bed-75f0-4b32-8066-3c4852b10287_561x3743621089copy.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597517.html)\n\n[第九届中国国际进口博览会将于11月5日至10日举办](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597517.html)\n\n[![Image 13](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597191_fda6b083-95f7-4ce4-9a6d-bab230097125.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597191.html)\n\n[研究团队在量子声学领域取得重大实验进展](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597191.html)\n\n[封面新闻](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Ffmxw\u002Fnode_334.html)\n\n*   [![Image 14](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2024-09\u002F10\u002F227211_t0_0X0X532X399_f37403ac-57e6-47f7-91e3-ba6e5e28a64d.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-09\u002F10\u002Fcontent_227211.html) \n[封面新闻丨第40个教师节，致敬这些良师益友](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-09\u002F10\u002Fcontent_227211.html)\n\n*   [![Image 15](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2024-09\u002F09\u002F226617_t0_0X3X515X389_c0de85fe-9e16-4131-98ff-9f011359aeb7.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-09\u002F09\u002Fcontent_226617.html) \n[亮点纷呈 氛围感拉满！2024年国家网络安全宣传周开启](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-09\u002F09\u002Fcontent_226617.html)\n\n*   [![Image 16](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2024-08\u002F29\u002F221287_t0_35X3X554X392_6088faa3-97fd-4574-bd90-3340514ec6c0.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-08\u002F29\u002Fcontent_221287.html) \n[封面新闻丨共赴十年之约 2024数博会引领数字经济发展新潮流](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-08\u002F29\u002Fcontent_221287.html)\n\n*   [![Image 17](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2024-08\u002F15\u002F214881_t1_11X0X583X322_f39b4a42-0f79-4c79-937c-02aa2572567c.JPG)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-08\u002F15\u002Fcontent_214881.html) \n[全国生态日丨我国生态环境和质量持续改善](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2024-08\u002F15\u002Fcontent_214881.html)\n\n[精彩视频](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fspxw\u002Fnode_701.html)\n\n*   [![Image 18](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F16\u002F597631_t1_2X0X600X336_740813dc-5335-41b1-a181-a272b3eb66f3.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597631.html) \n[科普一下丨狂刷屏的“喝大水”真能排毒养生吗？](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597631.html)\n\n*   [![Image 19](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fspxw\u002Fpic\u002F2026-10\u002F16\u002F597005_bd0200b1-7539-4945-ba8c-fa0e900689ed.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fspxw\u002F2026-10\u002F16\u002Fcontent_597005.html) \n[传薪火丨2026年全国老科技工作者日北京主场活动](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fspxw\u002F2026-10\u002F16\u002Fcontent_597005.html)\n\n*   [![Image 20](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F15\u002F596827_t1_0X0X600X338_1c604c1e-4d17-471e-b579-18d757ac72ba.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F15\u002Fcontent_596827.html) \n[高半米、重4斤！中国科学家发现蘑菇巨无霸](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F15\u002Fcontent_596827.html)\n\n*   [![Image 21](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002Fpic\u002F2026-10\u002F15\u002F596780_866ecd36-4c7f-449f-8430-bb2da352f063.jpg)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F15\u002Fcontent_596780.html) \n[为啥有人更招蚊子？科研人员在原子层面找到了答案](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F15\u002Fcontent_596780.html)\n\n[专题报道](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fztxw\u002Fnode_335.html)\n\n*   [科技新观察](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2025-06\u002F05\u002Fcontent_350698.html)\n*   [创新故事](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fzhuantiji\u002Fztcxgs.html)\n*   [科普一下](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fzhuantiji\u002Fztkpyx.html)\n*   [庆祝中国共产党成立105周年](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-06\u002F12\u002Fcontent_531282.html)\n\n![Image 22](https:\u002F\u002Fwww.stdaily.com\u002Fresource\u002FtemplateRes\u002F\u002F202403\u002F03\u002F228\u002Fimages\u002Fcode_img.png)\n\n### 友情链接\n\n*   [中国政府网](https:\u002F\u002Fwww.gov.cn\u002F)\n*   [国家发展和改革委员会](http:\u002F\u002Fwww.ndrc.gov.cn\u002F)\n*   [教育部](http:\u002F\u002Fwww.moe.gov.cn\u002F)\n*   [科学技术部](http:\u002F\u002Fwww.most.gov.cn\u002Findex.html)\n*   [工业和信息化部](https:\u002F\u002Fwww.miit.gov.cn\u002F)\n*   [公安部](https:\u002F\u002Fwww.mps.gov.cn\u002F)\n*   [民政部](http:\u002F\u002Fwww.mca.gov.cn\u002F)\n*   [司法部](http:\u002F\u002Fwww.moj.gov.cn\u002F)\n*   [自然资源部](http:\u002F\u002Fwww.mnr.gov.cn\u002F)\n*   [生态环境部](https:\u002F\u002Fwww.mee.gov.cn\u002F)\n*   [住房和城乡建设部](https:\u002F\u002Fwww.mohurd.gov.cn\u002F)\n*   [交通运输部](https:\u002F\u002Fwww.mot.gov.cn\u002F)\n*   [水利部](http:\u002F\u002Fwww.mwr.gov.cn\u002F)\n*   [农业农村部](http:\u002F\u002Fwww.moa.gov.cn\u002F)\n*   [国家卫生健康委员会](http:\u002F\u002Fwww.nhc.gov.cn\u002F)\n*   [国家市场监督管理总局](https:\u002F\u002Fwww.samr.gov.cn\u002F)\n*   [国家广播电视总局](http:\u002F\u002Fwww.nrta.gov.cn\u002F)\n*   [国家体育总局](https:\u002F\u002Fwww.sport.gov.cn\u002F)\n*   [国家互联网信息办公室](http:\u002F\u002Fwww.cac.gov.cn\u002F)\n*   [国务院新闻办公室](http:\u002F\u002Fwww.scio.gov.cn\u002Findex.htm)\n*   [中国科学院](https:\u002F\u002Fwww.cas.cn\u002F)\n*   [中国社会科学院](http:\u002F\u002Fwww.cass.cn\u002F)\n*   [中国工程院](https:\u002F\u002Fwww.cae.cn\u002F)\n*   [国家文物局](http:\u002F\u002Fwww.ncha.gov.cn\u002F)\n*   [国家知识产权局](https:\u002F\u002Fwww.cnipa.gov.cn\u002F)\n*   [人民网](http:\u002F\u002Fwww.people.com.cn\u002F)\n*   [新华网](http:\u002F\u002Fwww.news.cn\u002F)\n*   [中国网](http:\u002F\u002Fwww.china.com.cn\u002F)\n*   [国际在线](http:\u002F\u002Fwww.cri.cn\u002F)\n*   [中国日报网](https:\u002F\u002Fcn.chinadaily.com.cn\u002F)\n*   [央视网](https:\u002F\u002Fwww.cctv.com\u002F)\n*   [中国青年网](https:\u002F\u002Fwww.youth.cn\u002Findex.htm)\n*   [中国经济网](http:\u002F\u002Fwww.ce.cn\u002F)\n*   [中国台湾网](http:\u002F\u002Fwww.taiwan.cn\u002F)\n*   [中国西藏网](http:\u002F\u002Fwww.tibet.cn\u002F)\n*   [央广网](http:\u002F\u002Fwww.cnr.cn\u002F)\n*   [光明网](https:\u002F\u002Fwww.gmw.cn\u002F)\n*   [中国军网](http:\u002F\u002Fwww.81.cn\u002F)\n*   [中国新闻网](https:\u002F\u002Fwww.chinanews.com.cn\u002F)\n*   [人民政协网](http:\u002F\u002Fwww.rmzxb.com.cn\u002Findex.shtml)\n*   [法治网](http:\u002F\u002Fwww.legaldaily.com.cn\u002F)\n\n*   [科技日报社概况](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2019-07\u002F12\u002Fcontent_1790748.html)\n*   [科技日报概况](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2022-01\u002F26\u002Fcontent_1790749.html)\n*   [报社领导](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2017-07\u002F17\u002Fcontent_1790744.html)\n*   [关于中国科技网](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2022-03\u002F12\u002Fcontent_1790745.html)\n*   [联系我们](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2016-09\u002F02\u002Fcontent_1790743.html)\n*   [公示公告](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fnode_10787.html)\n*   [广告刊例](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2025-12\u002F26\u002Fcontent_453856.html)\n*   [科技日报社公开招聘公告](https:\u002F\u002Fwww.stdaily.com\u002Fnode_355.html)\n*   [互联网新闻信息服务许可证](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2022-06\u002F21\u002Fcontent_1790750.html)\n*   [信息网络传播视听节目许可证](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2021-12\u002F10\u002Fcontent_1790742.html)\n*   [举报平台](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2021-09\u002F10\u002Fcontent_1790741.html)\n*   [版权声明](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2017-01\u002F01\u002Fcontent_1790740.html)\n\nCopyright © Science and Technology Daily, All Rights Reserved 科技日报社 中国科技网 版权所有\n*   [京ICP备 06005116 号](https:\u002F\u002Fbeian.miit.gov.cn\u002F)\n*   [违法和不良信息举报电话：010-58884152](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002F2016-12\u002F05\u002Fcontent_1790739.html)\n*   [京公网安备11010802036145号](http:\u002F\u002Fwww.beian.gov.cn\u002Fportal\u002FregisterSystemInfo?recordcode=11010802036145)\n\n[![Image 23](https:\u002F\u002Fwww.stdaily.com\u002Fresource\u002FtemplateRes\u002F\u002F202408\u002F19\u002F345\u002Fimages\u002Fclose.png)](https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F16\u002Fcontent_597377.html)\n\n#### 抱歉，您使用的浏览器版本过低或开启了浏览器兼容模式，这会影响您正常浏览本网页\n\n### 您可以进行以下操作:\n\n## 1.将浏览器切换回极速模式\n\n![Image 24](https:\u002F\u002Fwww.stdaily.com\u002Fresource\u002FtemplateRes\u002F\u002F202408\u002F19\u002F345\u002Fimages\u002F360tip.png)\n\n## 2.点击下面图标升级或更换您的浏览器\n\n[![Image 25](https:\u002F\u002Fwww.stdaily.com\u002Fresource\u002FtemplateRes\u002F\u002F202408\u002F19\u002F345\u002Fimages\u002Ffirefox.jpg)](http:\u002F\u002Fwww.firefox.com.cn\u002Fdownload\u002F)[![Image 26](https:\u002F\u002Fwww.stdaily.com\u002Fresource\u002FtemplateRes\u002F\u002F202408\u002F19\u002F345\u002Fimages\u002Fchrome.jpg)](http:\u002F\u002Fwww.chromeliulanqi.com\u002F)\n\n## 3.暂不升级，继续浏览\n\n[继续浏览](javascript:;)","科技日报 黑龙江省农业科学院 2026 年 10 月 16 日","2026-10-16T00:00:00Z","报道",77,{"impact":17,"substance":18,"depth":118,"authority":19,"freshness":119,"relevant":21,"comment":120},16,9,"省级科研机构在盐碱旱田推出青贮玉米新品种并配套栽培技术，数据具体、多方信源，具行业推广价值。",[122],{"name":113,"url":110},[124,125,126,127,29],"种业振兴","盐碱地治理","饲草产业","良种良法",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[130,131],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":132,"slug":133,"name":134,"path":135,"parent_code":136},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":45,"locked":14,"version":46,"method":47,"evidence":138},{"candidates":139,"agricultural_evidence":52},[140,146,150,155,162],{"code":39,"score":118,"supported":52,"title":141,"abstract":143,"tags":145},[142],"青贮",[144,142],"饲草",[29,126],{"code":32,"score":57,"supported":52,"title":147,"abstract":148,"tags":149},[34],[34],[29],{"code":132,"score":57,"supported":52,"title":151,"abstract":153,"tags":154},[152],"盐碱地",[152],[125],{"code":156,"score":157,"supported":52,"title":158,"abstract":159,"tags":161},"A7",4,[],[160],"套种",[126],{"code":163,"score":64,"supported":14,"title":164,"abstract":165,"tags":166},"F1",[],[],[124,127],[168,169],"黑龙江农科院 龙育15 龙育17","松嫩平原 盐碱地 青贮玉米","黑龙江农科院龙育15龙育17-5123","2026-10-17T00:13:40.216554Z",{"id":173,"title":174,"url":175,"summary":176,"summary_zh":9,"content":177,"source_name":178,"source_url":9,"published_at":179,"category":115,"cover_url":9,"hotness":13,"is_selected":14,"score":180,"score_detail":181,"sources":186,"tags":188,"primary_topic":195,"secondary_topics":196,"classification":198,"search_phrases":211,"slug":214,"view_count":157,"doi":9,"paper":9,"created_at":215},531,"为饲料蛋白安全修新路:武汉高产高蛋白玉米打通全产业链","https:\u002F\u002Fwww.moa.gov.cn\u002Fxw\u002Fqg\u002F202608\u002Ft20260811_6486607.htm","8月5日,武汉高产高蛋白玉米现场观摩会暨湖北省玉米产业技术体系年度推进会在武汉市经开(汉南)区召开。湖北省农业科学院粮食作物研究所专家贺正华介绍,未玉002玉米品种田间亩产达699.6公斤,籽粒平均蛋白质含量达12.2%,与去年同期相比,蛋白含量提升1.4个百分点,亩产增加290公斤。会上未米生物科技与12家种植主体、2家饲料企业签订合作协议。","8月5日，武汉高产高蛋白玉米现场观摩会暨湖北省玉米产业技术体系年度推进会在武汉市经开（汉南）区召开。来自农业农村部、中国农业科学院、湖北省农业农村厅、武汉市农业农村局、华中农业大学等单位的200余名代表参会，聚焦高蛋白玉米“种质创制—品种选育—专种专收—饲料—饲养”全链条开展现场观摩与交流。\n\n在汉南区700余亩研发试验基地内，26个高产高蛋白玉米品种试种表现优异。专家组现场测产结果显示，“未玉002”玉米亩产达699.6公斤，籽粒平均蛋白质含量达12.2%。\n\n华中农业大学植物科学技术学院邱法展教授表示，今年武汉市高产高蛋白玉米实现了提质、增产、扩面。与去年同期相比，蛋白含量提升1.4个百分点，亩产增加290公斤，全市种植面积翻倍至2万余亩。该批品种平均蛋白含量比市场主流普通玉米高出3至4个百分点，亩产高出300余公斤。\n\n高产高蛋白玉米不仅要“种得好”，更要“用得好”。会上，作为高产高蛋白玉米的链主企业，未米生物科技（武汉）有限公司分别与12家种植主体、2家饲料企业签订合作协议。公司副总裁魏友伯介绍，未米生物创新打造了“专种—专收—专烘—专储—专用”全产业链闭环。通过“产学研+订单”双轮驱动模式，向上联合科研单位开展品种选育，向下精准对接饲料企业蛋白需求，中游协调合作社进行规模化订单种植，同时联合收储企业解决专用烘干与仓储难题，打通从种源到养殖端完整链条，挖掘高蛋白玉米产业价值。\n\n华中农业大学校长严建兵表示，发展高产高蛋白玉米是为国家的饲料蛋白安全修一条“新路”。高产高蛋白玉米新品种的大面积推广，有望减少大豆进口，减轻国内饲料蛋白对外依存压力。\n\n此次会议系统展示了高蛋白玉米在育种、栽培和产业化方面的最新科研成果。未来，随着政、产、学、研多方协同聚力与全产业链的进一步完善，高产高蛋白玉米将为保障国家粮食安全和重要农产品稳定供给注入新动能。（作者 李田锐 晏华华）","湖北省农业科学院","2026-08-12T03:11:00Z",81,{"impact":182,"substance":183,"depth":118,"authority":57,"freshness":184,"relevant":21,"comment":185},24,22,7,"报道高蛋白玉米全产业链进展，涉及国家饲料蛋白安全，数据详实，信源权威，时效性稍差。",[187],{"name":178,"url":175},[189,190,191,192,193,194],"观摩会","全产业链","未玉002","湖北省农科院","高蛋白玉米","饲料蛋白",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[197],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":199},{"candidates":200,"agricultural_evidence":52},[201,206],{"code":32,"score":202,"supported":52,"title":203,"abstract":204,"tags":205},13,[34],[34],[191,193],{"code":39,"score":57,"supported":52,"title":207,"abstract":209,"tags":210},[208],"饲料",[208],[194],[212,213],"湖北省农科院 高蛋白玉米 全产业链 饲料蛋白","湖北省农科院 高蛋白玉米","湖北省农科院高蛋白玉米全产业链饲料蛋白-531","2026-08-15T00:02:54.443670Z",{"id":217,"title":218,"url":219,"summary":220,"summary_zh":221,"content":9,"source_name":222,"source_url":219,"published_at":223,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":224,"score_detail":225,"sources":227,"tags":229,"primary_topic":233,"secondary_topics":237,"classification":245,"search_phrases":278,"slug":281,"view_count":96,"doi":282,"paper":283,"created_at":309},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",80,{"impact":118,"substance":183,"depth":17,"authority":19,"freshness":13,"relevant":21,"comment":226},"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。",[228],{"name":222,"url":219},[26,27,230,231,232],"农业遥感","氮素监测","紫花苜蓿",{"code":156,"slug":234,"name":235,"path":236,"parent_code":36},"forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping",[238,244],{"code":239,"slug":240,"name":241,"path":242,"parent_code":243},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":246},{"candidates":247,"agricultural_evidence":52},[248,255,261,265,274],{"code":239,"score":17,"supported":52,"title":249,"abstract":251,"tags":254},[250],"hyperspectral",[252,253,250],"遥感","remote sensing",[230],{"code":156,"score":51,"supported":52,"title":256,"abstract":258,"tags":260},[257],"alfalfa",[259,257],"苜蓿",[232],{"code":39,"score":13,"supported":52,"title":262,"abstract":263,"tags":264},[],[144,259,59],[232],{"code":63,"score":13,"supported":52,"title":266,"abstract":267,"tags":273},[],[268,269,270,271,272],"深度学习","机器学习","machine learning","deep learning","decision support",[27],{"code":69,"score":21,"supported":14,"title":275,"abstract":276,"tags":277},[],[],[26],[279,280],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573","10.1016\u002Fj.eja.2026.128375",{"doi":282,"openalex_id":284,"authors":285,"venue":222,"cited_by_count":96,"oa_url":219,"card":304,"direction":101,"ingested_from":103},"W7223154576",[286,288,290,292,294,297,299,302],{"name":287,"orcid":9},"Shuai Fu",{"name":289,"orcid":9},"Yunhao Li",{"name":291,"orcid":9},"Chunli Miao",{"name":293,"orcid":9},"Jie Liu",{"name":295,"orcid":296},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":298,"orcid":9},"Yongjia Hu",{"name":300,"orcid":301},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":303,"orcid":9},"吴彩霞",{"tldr":305,"method":306,"finding":307,"direction":101,"opportunity":308},"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","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。","2026-10-22T11:20:39.622844Z",{"id":311,"title":312,"url":313,"summary":314,"summary_zh":9,"content":315,"source_name":316,"source_url":9,"published_at":223,"category":115,"cover_url":9,"hotness":13,"is_selected":14,"score":317,"score_detail":318,"sources":320,"tags":322,"primary_topic":326,"secondary_topics":327,"classification":328,"search_phrases":349,"slug":352,"view_count":96,"doi":9,"paper":9,"created_at":353},5518,"河北农林科学院玉米抗病性鉴定开放日 AR智能眼镜助力分级定级","https:\u002F\u002Fwww.cfsn.cn\u002Fnews\u002Fdetail\u002F345\u002F371985.html","河北省农林科学院植物保护研究所主办2026年黄淮海玉米抗病性鉴定田间开放日。作为全国玉米抗病性鉴定牵头单位，该所推进智能化技术嫁接鉴定工作，引入AR智能眼镜拍照自动标注叶片病斑率并判定严重度等级，支持语音控制与后台批量导出，另探索无人机悬停拍照系统开展规模化快速调查。","金秋时节，冀中平原玉米长势喜人、丰收在望。近日，由河北省农林科学院植物保护研究所主办的“2026年黄淮海玉米抗病性鉴定田间开放日”活动在河北省保定市顺利举行。来自玉米育种、植保、种业企业等领域的领导、专家和同仁齐聚一堂，围绕玉米抗病性鉴定标准化、智能化与精准化展开深入交流与现场观摩。\n\n河北省农林科学院植物保护研究所副所长吴玉星表示，玉米抗病性鉴定是育种升级和品种审定推广的必要环节，对保障粮食安全具有重要意义。河北省农林科学院植物保护研究所作为全国玉米抗病性鉴定的牵头单位，严格按照国家标准规范布局、统一试验，全程实行标准化操作程序，确保每一项数据真实、准确、公正。他强调，团队将继续恪守公平、公正、科学、严谨的工作原则，不断优化试验方案，为各试验单位提供优质高效的抗病性鉴定服务，助力优良玉米品种替代升级和高质量发展。\n\n活动期间，河北省农林科学院植物保护研究所研究员石洁结合多年田间鉴定实践，介绍了当前玉米抗病性鉴定面临的现实挑战。她指出，黄淮海地区玉米病害种类多、调查面积大、工作强度高，仅靠人工逐品种、逐病害调查，骨干人员长期在田间超负荷工作，难以满足规模化、精准化鉴定需求。为此，团队积极推动智能化技术嫁接到抗病性鉴定工作中，着力实现数据实时采集、结果直接反馈和精准分级。\n\n北京金禾天成科技有限公司有关负责人介绍了通过AR智能眼镜识别玉米病害及判定严重度等级技术。该技术通过拍照识别，自动标注每片叶片的病斑率和整张图片的病斑率，并给出严重度等级判定，拍照后自动保存识别结果和原图，支持现场快速呈现结果和后台批量导出。系统还可按品种编号自动对应品种名称，支持人工校正和后续复核，有效减轻调查人员劳动强度，提升鉴定效率和标准化水平。\n\n石洁告诉记者，团队正在积极协助研发和应用AR智能眼镜技术，用于玉米叶斑病、穗腐病等病害的精准分级。该设备支持语音控制，可解放双手，在田间行走过程中即可完成“所见即所得”的病情定级，并实时反馈数据。相比传统人眼判断，智能眼镜能够提供更精细的数量化级别，满足抗性基因定位等研究对定量数据的需求。此外，团队还在积极探索无人机高空悬停拍照系统，用于茎腐病、矮花叶病等病害的规模化快速调查，进一步提升鉴定效率。\n\n活动现场还展示了快速检测技术在玉米病害防控中的应用。石洁介绍，该技术可在病害尚未发病的叶片上，通过棉签擦拭、裂解液处理和便携设备检测，30分钟内常温下判断叶片是否携带孢子或已被病原菌侵入。目前可检测病理上几乎所有病害（病毒病除外），包括南方锈病、穗腐病、弯孢叶斑病、瘤黑粉病等。荧光定量PCR版本一次可同时检测8种病原菌，帮助种植大户和种业企业据检测结果用药，实现“检防联动”，从普惠性预防用药转向按需防控、对靶施药、早防早治，大幅节省农药和飞防成本。\n\n本次开放日活动全面开放观摩现场，与会代表近距离了解了玉米抗病性鉴定从试验设计、田间管控、症状跟踪到数据调查的全流程。大家一致认为，智能化鉴定技术和快速检测技术的推广应用，将有力推动黄淮海玉米抗病性鉴定工作向精准化、标准化、高效化迈进，为玉米产业高质量发展保驾护航。（王田）","中国食品安全网 2026-10-21",73,{"impact":17,"substance":18,"depth":118,"authority":13,"freshness":119,"relevant":21,"comment":319},"省级科研机构开放日，AR智能眼镜与快速检测技术有实质信息增量，属细分领域智能化进展，值得精选。",[321],{"name":316,"url":313},[26,27,323,324,325],"智能装备","玉米病害","抗病性鉴定",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":329},{"candidates":330,"agricultural_evidence":52},[331,336,341,345],{"code":32,"score":332,"supported":52,"title":333,"abstract":334,"tags":335},11,[34],[34],[],{"code":337,"score":21,"supported":14,"title":338,"abstract":339,"tags":340},"F5",[],[],[323],{"code":69,"score":21,"supported":14,"title":342,"abstract":343,"tags":344},[],[],[26],{"code":63,"score":21,"supported":14,"title":346,"abstract":347,"tags":348},[],[],[27],[350,351],"河北农科院 玉米抗病性鉴定 AR智能眼镜","黄淮海 玉米 病害 快速检测","河北农科院玉米抗病性鉴定AR智能眼镜-5518","2026-10-22T00:07:04.176689Z",{"id":355,"title":356,"url":357,"summary":358,"summary_zh":359,"content":9,"source_name":360,"source_url":357,"published_at":114,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":361,"score_detail":362,"sources":364,"tags":366,"primary_topic":368,"secondary_topics":369,"classification":374,"search_phrases":396,"slug":399,"view_count":21,"doi":400,"paper":401,"created_at":435},5164,"Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.50","Early and accurate detection of maize leaf diseases is essential for improving crop productivity and supporting precision agriculture.However, deep learning models trained on controlled leaf-image datasets often experience performance degradation under real-world agricultural conditions because of illumination variation, background clutter, occlusion, leaf orientation, and imaging noise.To address these challenges, this study develops a lightweight deep learning framework for robust maize leaf disease classification and edge-oriented deployment.The framework employs MobileNetV3-Small for efficient extraction of disease-discriminative visual features and investigates lightweight feature-learning strategies for improving classification under challenging field conditions.Experiments were conducted using PlantVillage-Maize and Field-Maize datasets comprising 6,188 images from four categories: Maize Leaf Blight (MLB), Common Rust, Healthy, and Leaf Spot.The image-only MobileNetV3-Small model achieved 97.8% accuracy and a 97.4% F1-score on the controlled PlantVillage-Maize dataset, while its performance decreased to 86.1% accuracy and an 83.9% F1-score on Field-Maize, highlighting the domain gap between controlled and real-field imagery.Robustness was further evaluated under Gaussian noise, illumination variation, and partial occlusion, together with computational-efficiency and edge-deployment analyses.The findings demonstrate the importance of lightweight and robust visual feature learning for practical maize disease diagnosis under real-world agricultural imaging conditions.","早期准确检测玉米叶片病害对于提高作物生产力和支持精准农业至关重要。然而，在受控叶片图像数据集上训练的深度学习模型，在真实农业条件下往往会出现性能下降，原因包括光照变化、背景杂乱、遮挡、叶片朝向以及成像噪声。为应对这些挑战，本研究开发了一个轻量级深度学习框架，用于稳健的玉米叶片病害分类和面向边缘的部署。该框架采用MobileNetV3-Small高效提取具有病害判别力的视觉特征，并研究轻量级特征学习策略，以提升在复杂田间条件下的分类性能。实验使用PlantVillage-Maize和Field-Maize数据集进行，共包含来自四个类别的6，188张图像：玉米大斑病（Maize Leaf Blight，MLB）、普通锈病（Common Rust）、健康（Healthy）和叶斑病（Leaf Spot）。仅使用图像的MobileNetV3-Small模型在受控的PlantVillage-Maize数据集上达到了97.8%的准确率和97.4%的F1分数，而在Field-Maize上的性能下降至86.1%的准确率和83.9%的F1分数，凸显了受控图像与真实田间图像之间的域差距。研究进一步在高斯噪声、光照变化和部分遮挡条件下评估了稳健性，并进行了计算效率和边缘部署分析。研究结果表明，轻量级且稳健的视觉特征学习对于真实农业成像条件下的实际玉米病害诊断具有重要意义。","International journal of intelligent engineering and systems",69,{"impact":57,"substance":18,"depth":118,"authority":57,"freshness":119,"relevant":21,"comment":363},"该研究提出轻量级玉米叶病检测框架，并揭示受控数据集与田间数据之间的性能差距，方法扎实、结论有参考价值，但属细分技术论文，公共影响有限。",[365],{"name":360,"url":357},[26,27,367,268,324],"边缘计算",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[370],{"code":63,"slug":371,"name":372,"path":373,"parent_code":243},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":45,"locked":14,"version":46,"method":47,"evidence":375},{"candidates":376,"agricultural_evidence":52},[377,381,385,391],{"code":32,"score":19,"supported":52,"title":378,"abstract":379,"tags":380},[33],[34,33],[],{"code":63,"score":20,"supported":52,"title":382,"abstract":383,"tags":384},[],[268,271],[27,268],{"code":69,"score":184,"supported":52,"title":386,"abstract":387,"tags":390},[],[388,389],"精准农业","precision agriculture",[26],{"code":392,"score":21,"supported":14,"title":393,"abstract":394,"tags":395},"I5",[],[],[367],[397,398],"MobileNetV3 玉米叶部病害","玉米叶片病害 边缘部署","MobileNetV3玉米叶部病害-5164","10.22266\u002Fijies2026.1130.50",{"doi":400,"openalex_id":402,"authors":403,"venue":360,"cited_by_count":96,"oa_url":357,"card":429,"direction":101,"ingested_from":103},"W7222602850",[404,407,410,412,414,417,419,421,424,426],{"name":405,"orcid":406},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":408,"orcid":409},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":411,"orcid":9},"Bhavani K",{"name":413,"orcid":9},"Sailee N. Panchbhai",{"name":415,"orcid":416},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":418,"orcid":9},"Manoj Kumar S B",{"name":420,"orcid":9},"Dharamvir",{"name":422,"orcid":423},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":425,"orcid":9},"Rani Chhagan Dalvi",{"name":427,"orcid":428},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":430,"method":431,"finding":432,"direction":433,"opportunity":434},"构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。","MobileNetV3-Small，PlantVillage-Maize与Fie","受控数据准确率97.8%，田间降至86.1%，揭示明显域差距。","农业人工智能与决策模型","可研究跨域自适应与田间鲁棒特征学习，缩小受控与真实场景性能差距。","2026-10-17T23:30:28.248539Z",{"id":437,"title":438,"url":439,"summary":440,"summary_zh":441,"content":9,"source_name":442,"source_url":439,"published_at":443,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":444,"score_detail":445,"sources":447,"tags":449,"primary_topic":451,"secondary_topics":452,"classification":454,"search_phrases":470,"slug":473,"view_count":96,"doi":474,"paper":475,"created_at":489},4759,"Machine Learning-based Prediction of SVI Parameter in Maize: A Comparative Study and Feature Importance Analysis","https:\u002F\u002Fdoi.org\u002F10.24925\u002Fturjaf.v14i10.2870-2879.9043","Background: Accurate estimation of seedling vigor indices (SVI) is critical for monitoring plant health and predicting yields in precision agriculture. This study comparatively evaluates the performance of different machine learning algorithms in estimating the SVI parameter. Methods: Germination data were collected from 39 maize genotypes under three different salinity conditions (0 mM, 100 mM, and 200 mM NaCl), including the parameters Gmax, MGT, GI, SL, RL, SdL, SMR, RMR, and SVI. The dataset was preprocessed through normalization to the [0–1] range. The SVI parameter was estimated using four different machine learning methods: Random Forest, CatBoost, LightGBM, and Support Vector Regression (SVR). To evaluate the performance of the models, both 10-fold cross-validation and 80%–20% hold-out validation techniques were employed. The model performance was examined using RMSE, MSE, MAE, and R² metrics. Results: The findings show that all models have a high explanatory power in the training dataset. Specifically, the CatBoost model showed the highest success in the training phase (R²=0.9962), whereas the SVR model achieved the highest generalization performance on the test dataset (R²=0.9712, RMSE=0.0582). Feature importance analysis results revealed that the 'App' parameter had the highest impact on the target variable in most models, but different structural interactions were prominent in the LightGBM model. The results demonstrate that machine learning techniques provide high accuracy in SVI estimation and that the tendency towards overfitting is limited. Conclusions: In conclusion, this study confirms that machine learning techniques are powerful and reliable tools for estimating spectral indices in precision agriculture applications. The integration of SVR and ensemble-based models into agricultural decision support systems is expected to significantly contribute to optimizing resource use and improving yield predictions.","背景：准确估计幼苗活力指数（SVI）对于精准农业中监测植物健康和预测产量至关重要。本研究比较评估了不同机器学习算法在估计SVI参数方面的性能。方法：从39个玉米基因型在三种不同盐度条件（0 mM、100 mM和200 mM NaCl）下收集发芽数据，包括Gmax、MGT、GI、SL、RL、SdL、SMR、RMR和SVI等参数。数据集通过归一化至[0–1]范围进行预处理。采用四种不同的机器学习方法估计SVI参数：随机森林、CatBoost、LightGBM和支持向量回归（SVR）。为评估模型性能，采用了10折交叉验证和80%–20%留出验证技术。使用RMSE、MSE、MAE和R²指标检验模型性能。结果：研究结果表明，所有模型在训练数据集中均具有较高的解释力。具体而言，CatBoost模型在训练阶段表现出最高的成功率（R²=0.9962），而SVR模型在测试数据集上取得了最高的泛化性能（R²=0.9712，RMSE=0.0582）。特征重要性分析结果显示，在大多数模型中，“App”参数对目标变量的影响最大，但在LightGBM模型中不同的结构交互作用更为突出。结果表明，机器学习技术在SVI估计中提供了高精度，且过拟合倾向有限。结论：总之，本研究证实机器学习技术是精准农业应用中估计光谱指数的强大而可靠的工具。将SVR和基于集成的模型整合到农业决策支持系统中，预计将显著有助于优化资源利用和改善产量预测。","Turkish Journal of Agriculture - Food Science and Technology","2026-10-11T00:00:00Z",63,{"impact":20,"substance":17,"depth":118,"authority":57,"freshness":119,"relevant":21,"comment":446},"方法对比扎实、结论可靠，但属细分领域论文，产业影响有限，适合主题聚合而非头条精选。",[448],{"name":442,"url":439},[26,27,269,34,450],"耐盐育种",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[453],{"code":63,"slug":371,"name":372,"path":373,"parent_code":243},{"status":45,"locked":14,"version":46,"method":47,"evidence":455},{"candidates":456,"agricultural_evidence":52},[457,462,466],{"code":63,"score":458,"supported":52,"title":459,"abstract":460,"tags":461},19,[270],[269,270,272],[27,269],{"code":32,"score":51,"supported":52,"title":463,"abstract":464,"tags":465},[33],[34,33],[34],{"code":69,"score":184,"supported":52,"title":467,"abstract":468,"tags":469},[],[388,389],[26],[471,472],"玉米 SVI 机器学习","玉米 耐盐 幼苗活力指数","玉米SVI机器学习-4759","10.24925\u002Fturjaf.v14i10.2870-2879.9043",{"doi":474,"openalex_id":476,"authors":477,"venue":442,"cited_by_count":96,"oa_url":439,"card":484,"direction":433,"ingested_from":103},"W7221462188",[478,481],{"name":479,"orcid":480},"Mustafa Turan Arslan","https:\u002F\u002Forcid.org\u002F0000-0001-5498-6571",{"name":482,"orcid":483},"Gülay Zülkadir","https:\u002F\u002Forcid.org\u002F0000-0003-3488-4011",{"tldr":485,"method":486,"finding":487,"direction":433,"opportunity":488},"用四种机器学习模型基于39个玉米基因型盐胁迫发芽数据预测幼苗活力指数SVI。","39个玉米基因型在三种盐浓度下的发芽数据，归一化后用RF、CatBoost、Li","SVR泛化最优（R²=0.9712），CatBoost训练拟合最高；App参数对SVI影响最大。","可扩展到多作物多胁迫环境，结合光谱或图像表型数据提升SVI预测的田间适用性。","2026-10-12T23:30:44.762497Z"]