[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4646":3,"related-4646":66},{"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,"primary_topic":8,"secondary_topics":31,"classification":32,"search_phrases":51,"slug":54,"view_count":21,"doi":8,"paper":55,"created_at":65},4646,"面向共存植物叶部病害多标签诊断的类别感知视觉-语言框架CA-CLIP(CA-CLIP for multi-label diagnosis of co-occurring plant leaf diseases: A class-aware vision-language framework)","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526002688","研究提出CA-CLIP类别感知视觉-语言框架用于症状混合叶片多标签诊断,构建CCPLD基准(5种作物、3400张合成图像、17种共存病害类型)。在CCPLD验证集子集准确率达0.8543、Macro-F1达0.9601;蒸馏至MobileNetV3(2.99M参数)子集准确率0.8066,自然背景外部评估mAP 0.5626。局限:数据集为受控合成,自然场景跨域迁移能力仍有限。",null,"Smart Agricultural Technology 7.1 2026-10-08","2026-10-08T00:00:00Z","论文",10,false,77,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,22,18,13,8,1,"提出类别感知视觉-语言框架并构建多标签病害基准，方法新颖、指标扎实，但数据集为受控合成、跨域迁移有限，属细分领域技术进展。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","视觉语言模型","植物病害诊断","多标签识别",[],{"status":33,"locked":13,"version":34,"method":35,"evidence":36},"unclassified","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":49,"reason":50},[38,44],{"code":39,"score":40,"supported":13,"title":41,"abstract":42,"tags":43},"I2",2,[],[],[27,28],{"code":45,"score":21,"supported":13,"title":46,"abstract":47,"tags":48},"I1",[],[],[26],true,"缺少足够的主题证据",[52,53],"CA-CLIP 植物叶部病害 多标签诊断","CCPLD 基准 共存病害","CA-CLIP植物叶部病害多标签诊断-4646",{"doi":8,"openalex_id":8,"authors":56,"venue":8,"cited_by_count":57,"oa_url":8,"card":58,"direction":62,"ingested_from":64},[],0,{"tldr":59,"method":60,"finding":61,"direction":62,"opportunity":63},"提出CA-CLIP视觉-语言框架，实现共存植物叶部病害的多标签诊断。","构建CCPLD合成基准（5作物、3400图、17类），用CLIP类感知框架并蒸馏","子集准确率0.8543、Macro-F1 0.9601，蒸馏后0.8066，但自然场景跨域mAP仅0","农业人工智能与决策模型","合成数据到自然场景的跨域迁移是空白，可研究域适应与真实田间多标签病害数据构建。","agent","2026-10-11T00:09:47.623718Z",{"total":67,"page":21,"page_size":67,"items":68},6,[69,135,176,214,277,340],{"id":70,"title":71,"url":72,"summary":73,"summary_zh":8,"content":8,"source_name":74,"source_url":72,"published_at":75,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":76,"score_detail":77,"sources":81,"tags":83,"primary_topic":86,"secondary_topics":92,"classification":93,"search_phrases":112,"slug":115,"view_count":116,"doi":117,"paper":118,"created_at":134},3876,"Agrivlm: integrating vision-language models into real-time remote sensing for smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11276-026-04228-x","Agrivlm: integrating vision-language models into real-time remote sensing for smart agriculture。Wireless Networks","Wireless Networks","2026-09-30T00:00:00Z",78,{"impact":18,"substance":78,"depth":18,"authority":19,"freshness":79,"relevant":21,"comment":80},20,9,"将视觉语言模型引入农业实时遥感，方法新颖且具应用潜力，值得关注。",[82],{"name":74,"url":72},[26,27,84,28,85],"实时监测","遥感",{"code":87,"slug":88,"name":89,"path":90,"parent_code":91},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":94,"locked":13,"version":34,"method":35,"evidence":95},"classified",{"candidates":96,"agricultural_evidence":49},[97,103,108],{"code":45,"score":98,"supported":49,"title":99,"abstract":101,"tags":102},12,[100],"smart agriculture",[100],[26],{"code":87,"score":98,"supported":49,"title":104,"abstract":106,"tags":107},[105],"remote sensing",[105],[85],{"code":39,"score":40,"supported":13,"title":109,"abstract":110,"tags":111},[],[],[27,28],[113,114],"Agrivlm 视觉语言模型 遥感","智慧农业 实时遥感","Agrivlm视觉语言模型遥感-3876",3,"10.1007\u002Fs11276-026-04228-x",{"doi":117,"openalex_id":119,"authors":120,"venue":74,"cited_by_count":57,"oa_url":8,"card":8,"direction":132,"ingested_from":133},"W7214888751",[121,123,126,128,130],{"name":122,"orcid":8},"Sasmita Padhy",{"name":124,"orcid":125},"Preetam Suman","https:\u002F\u002Forcid.org\u002F0000-0001-7607-1372",{"name":127,"orcid":8},"Naween Kumar",{"name":129,"orcid":8},"Akansha Singh",{"name":131,"orcid":8},"Krishna Kant Singh","智慧农业 \u002F 农业物联网","openalex","2026-10-01T23:30:08.990045Z",{"id":136,"title":137,"url":138,"summary":139,"summary_zh":8,"content":140,"source_name":141,"source_url":8,"published_at":142,"category":143,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":144,"sources":148,"tags":150,"primary_topic":153,"secondary_topics":157,"classification":158,"search_phrases":170,"slug":173,"view_count":174,"doi":8,"paper":8,"created_at":175},3597,"中国农科院农业信息研究所提出层次知识引导的枸杞害虫识别框架——Engineering Applications of Artificial Intelligence在线发表","https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571988.shtm","中国农业科学院农业信息研究所科学数据研究室科研团队近日提出一种层次知识引导的枸杞害虫识别框架，有效解决真实农业场景下样本稀缺与类间混淆的双重挑战，相关研究成果发表在《人工智能的工程应用》（Engineering Applications of Artificial Intelligence）上。研究团队依托长文本-图像检索模型，把专家撰写的长文本描述解析为粗、中、细三个语义层次，并与多尺度视觉特征实现精准跨模态对齐。同时设计知识引导的去混淆模块，通过构建文本和视觉双模态相似度图，明显降低容易混淆类别之间的预测误差。该研究得到国家重点研发计划、中国农业科学院科技创新工程等项目支持。","[![Image 2: 科学网新闻频道](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Fnews.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002F)\n\n[生命科学](https:\u002F\u002Fwww.sciencenet.cn\u002Flife\u002F) | [医学科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fmedicine\u002F) | [化学科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fchemistry\u002F) | [工程材料](https:\u002F\u002Fwww.sciencenet.cn\u002Fmaterial\u002F) | [信息科学](https:\u002F\u002Fwww.sciencenet.cn\u002Finformation\u002F) | [地球科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fearth\u002F) | [数理科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fmathematics\u002F) | [管理综合](https:\u002F\u002Fwww.sciencenet.cn\u002Fpolicy\u002F)[站内规定](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1064777.html) | [手机版](https:\u002F\u002Fwap.sciencenet.cn\u002F)\n\n[首页](https:\u002F\u002Fwww.sciencenet.cn\u002F) | [新闻](https:\u002F\u002Fnews.sciencenet.cn\u002F) | [博客](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php) | [院士](https:\u002F\u002Fnews.sciencenet.cn\u002Fys\u002F) | [人才](https:\u002F\u002Ftalent.sciencenet.cn\u002F) | [会议](https:\u002F\u002Fmeeting.sciencenet.cn\u002F) | [基金·项目](https:\u002F\u002Ffund.sciencenet.cn\u002F) | [论文](https:\u002F\u002Fpaper.sciencenet.cn\u002F) | [绘图](https:\u002F\u002Fvisual-web.sciencenet.cn\u002F) | [视频·直播](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=video) | [小柯机器人](https:\u002F\u002Fpaper.sciencenet.cn\u002FAInews) | [医学科普](https:\u002F\u002Fyxkp.sciencenet.cn\u002F)\n\n作者：李晨 来源：中国科学报 发布时间：2026\u002F9\u002F23 11:21:15 选择字号：小 中 大 新方法可智能识别枸杞害虫 近日，中国农业科学院农业信息研究所科学数据研究室科研团队，提出一种层次知识引导的枸杞害虫识别框架，有效解决真实农业场景下样本稀缺与类间混淆的双重挑战。相关研究成果发表在《人工智能的工程应用》（_**Engineering Applications of Artificial Intelligence**_）上。 ![Image 3](https:\u002F\u002Frmtzx.sciencenet.cn\u002Fkxwsprint\u002F6ab2a040e4b078fce44b0f9a.jpg)层次知识引导的枸杞害虫识别流程示意图。中国农科院供图 枸杞是高价值药用植物，虫害会对它的果实品质和药效造成很大影响。传统识别方法效率低且难以实现规模化应用。现有深度学习模型，面对外观高度相似的害虫种类时，常因标注样本不够，而识别效果不理想。 针对上述难题，科研团队依托长文本-图像检索模型，把专家撰写的长文本描述解析为粗、中、细三个语义层次，并与多尺度视觉特征实现精准跨模态对齐。同时，设计知识引导的去混淆模块，通过构建文本和视觉双模态相似度图，明显降低容易混淆类别之间的预测误差。该研究为枸杞等特色作物的虫害智能监测与精准防控提供新的技术路径，也为将农业专家知识融入视觉—语言模型提供参考。 该研究得到国家重点研发计划、中国农业科学院科技创新工程等项目支持。 相关论文信息：https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.engappai.2026.115342 版权声明：凡本网注明“来源：中国科学报、科学网、科学新闻杂志”的所有作品，网站转载，请在正文上方注明来源和作者，且不得对内容作实质性改动；微信公众号、头条号等新媒体平台，转载请联系授权。邮箱：shouquan@stimes.cn。\n\n打印 发E-mail给：\n\n以下评论只代表网友个人观点，不代表科学网观点。\n\n[![Image 4](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Fnewcomm.gif)](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtml\u002Fcomment.aspx?id=571988)\n\n相关新闻 相关论文\n*   1\n*   [陈文新：用后半生走遍中国“寻根”](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571931.shtm)\n\n*   2\n*   [上海市自然科学基金（启明星计划）项目申报指南发布](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571928.shtm)\n\n*   3\n*   [从实验室到生产线 高校以应用型科研对接产业升级](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571927.shtm)\n\n*   4\n*   [重点新材料研发及应用国家科技重大专项项目启动申报](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571926.shtm)\n\n*   5\n*   [一线治疗失败！晚期胃癌二线治疗有了“新标杆”](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571925.shtm)\n\n*   6\n*   [新策略助力有机室温磷光寿命大幅提升](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571909.shtm)\n\n*   7\n*   [AI绘制固态储氢材料全景导航 | 专家访谈](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571894.shtm)\n\n*   8\n*   [基金委发布1个国家自然科学基金专项项目申请指南](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571893.shtm)\n\n*   1\n*   [智能柔性传感器可原位实时监测植物体内激素](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923105644661155910.shtm)\n\n*   2\n*   [浙江大学刘明团队Angew.：利用“受挫堆积”调控多孔有机笼孔道结构](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F202692310372413155909.shtm)\n\n*   3\n*   [GCB | 华南植物园揭示长期高氮沉降驱动热带森林根系分泌物加速磷活化的机制](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923103553943155908.shtm)\n\n*   4\n*   [FEC | 土壤氮磷比调控高寒草地物种共存](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923103451833155907.shtm)\n\n*   5\n*   [前沿聚焦：为什么烤羊肉串香？合肥工大与渤海大学联合揭示“香气密码”](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923103345287155906.shtm)\n\n*   6\n*   [前沿聚焦：福州大学程树英-王伟煌联合河北大学高青：沉淀物回收策略助力 CBD 法 Sb2S3太阳电池提效](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923103218818155905.shtm)\n\n*   7\n*   [Angew. Chem.：本征近红外二区荧光纳米酶用于高分辨活体成像与肿瘤催化免疫治疗](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F2026923102125755155904.shtm)\n\n*   8\n*   [2型糖尿病不同临床亚型的分子异质性被揭示](https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F20269239501868155903.shtm)\n\n[图片新闻](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimgnews.aspx)\n\n[![Image 5: “鹏城首发星”成功入轨](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F20269231515219900.png)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571953.shtm)[![Image 6: 研究揭示甲烷部分氧化制合成气驱动因素](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F2026917125225680.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571610.shtm)\n[![Image 7: 科学家揭示火星大气物质运输规律](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F2026915174236470.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571503.shtm)[![Image 8: 超导双层镍氧化物薄膜的三维电子结构](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F20269151415154110.png)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571484.shtm)\n[>>更多](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimgnews.aspx)\n\n[一周新闻排行](https:\u002F\u002Fpaper.sciencenet.cn\u002Fzphnews.aspx)\n*   1\n*   [诺贝尔基金会宣布增加2026年诺奖奖金](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571724.shtm)\n\n*   2\n*   [直播回放｜新型铁基催化剂，为海水制氢提速](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fweibo.com\u002Fl\u002Fwblive\u002Fp\u002Fshow\u002F1022:2321325343837114990618)\n\n*   3\n*   [汪品先院士：年轻人应跳出人类中心论](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571776.shtm)\n\n*   4\n*   [从清华毕业做科普10年，我如何对抗AI](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571671.shtm)\n\n*   5\n*   [袁慧书：脊柱“一扫多查”，让AI成为影像医生得力助手](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571771.shtm)\n\n*   6\n*   [直播回放|马丁院士：共同追寻碳原子的“旅行路线”](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fweibo.com\u002Fl\u002Fwblive\u002Fp\u002Fshow\u002F1022:2321325344508505620608)\n\n*   7\n*   [新模型引爆AI圈：不生成文本，专为机器做快速决策](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571794.shtm)\n\n*   8\n*   [AI绘制固态储氢材料全景导航 | 专家访谈](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571894.shtm)\n\n*   9\n*   [AI正自主制造下一代AI？](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571716.shtm)\n\n*   10\n*   [一周热闻回顾（2026年9月20日）](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571820.shtm)\n\n[编辑部推荐博文](http:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=recommend)\n*   ![Image 9](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [封面文章 | 效应蛋白TseMt的毒性机制及递送通路](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1553810.html)\n\n*   ![Image 10](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [科学网2026年8月十佳博文榜单公布！](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1551789.html)\n\n*   ![Image 11](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [我爱路亚](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-1185605-1554044.html)\n\n*   ![Image 12](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [学者的中秋家国](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-575926-1554043.html)\n\n*   ![Image 13](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [CD1 如何\"看见\"脂质](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-41174-1554027.html)\n\n*   ![Image 14](https:\u002F\u002Fpaper.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [师傅领进门，修行在个人](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-729911-1553761.html)\n\n*   [更多>>](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=recommend)\n\n[关于我们](http:\u002F\u002Fwww.sciencenet.cn\u002Faboutus.aspx) | [网站声明](http:\u002F\u002Fwww.sciencenet.cn\u002Fshengming.aspx) | [服务条款](http:\u002F\u002Fwww.sciencenet.cn\u002Ftiaokuang.aspx) | [联系方式](http:\u002F\u002Fwww.sciencenet.cn\u002Fcontact.aspx) | [举报](https:\u002F\u002Fwww.sciencenet.cn\u002Fjubao.aspx) | [中国科学报社](https:\u002F\u002Fstimes.sciencenet.cn\u002F)  \n[京ICP备07017567号-12](http:\u002F\u002Fwww.beian.miit.gov.cn\u002F)互联网新闻信息服务许可证10120230008 京公网安备 11010802032783  \nCopyright @ 2007-2026 中国科学报社 All Rights Reserved  \n地址：北京市海淀区中关村南一条乙三号 电话：010-62580783","科学网（中国科学报）2026-09-23","2026-09-23T00:00:00Z","报道",{"impact":18,"substance":78,"depth":145,"authority":146,"freshness":20,"relevant":21,"comment":147},17,14,"国家级科研机构在农业AI顶刊发表的技术突破，方法新颖且直击样本稀缺与类间混淆痛点，对特色作物虫害智能监测有示范价值，值得进入每日精选。",[149],{"name":141,"url":138},[26,27,151,28,152],"病虫害识别","枸杞",{"code":39,"slug":154,"name":155,"path":156,"parent_code":91},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":94,"locked":13,"version":34,"method":35,"evidence":159},{"candidates":160,"agricultural_evidence":49},[161,166],{"code":39,"score":146,"supported":49,"title":162,"abstract":164,"tags":165},[163],"artificial intelligence",[163],[27,151,28],{"code":45,"score":21,"supported":13,"title":167,"abstract":168,"tags":169},[],[],[26],[171,172],"中国农科院 农业信息研究所 枸杞害虫","层次知识引导 害虫识别 视觉语言模型","中国农科院农业信息研究所枸杞害虫-3597",5,"2026-09-27T00:05:17.078840Z",{"id":177,"title":178,"url":179,"summary":180,"summary_zh":8,"content":8,"source_name":181,"source_url":8,"published_at":182,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":183,"sources":185,"tags":187,"primary_topic":8,"secondary_topics":190,"classification":191,"search_phrases":202,"slug":205,"view_count":116,"doi":8,"paper":206,"created_at":213},2394,"[预印本]Vision-language models know more about agriculture than they show and rubric-grounded verifications close the gap","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.09417","arXiv 2609.09417（2026-09-08）。基于116个数据集、834个类别、8324张图像基准测试，发现VLM视觉编码器已能编码与DINOv3基线相当可分离性的农业特征；通过Probabilistic Pivot Tournament（PPT）验证器结构化测试时推理，评判F1近两倍于下限，其中Gemma 4 E4B-it's病害F1达0.71，高于其自身上限0.60。但置信度分数与正确性负相关。","arXiv | 2026-09-08","2026-09-08T00:00:00Z",{"impact":18,"substance":17,"depth":18,"authority":19,"freshness":67,"relevant":21,"comment":184},"预印本以116数据集、8324张图像的规模系统评测农业视觉语言模型，并提出PPT验证器显著提升病害识别F1，方法新颖、数据扎实，对农业AI落地有参考价值，但尚未经同行评审。",[186],{"name":181,"url":179},[26,27,28,188,189],"病害识别","农业基准数据集",[],{"status":33,"locked":13,"version":34,"method":35,"evidence":192},{"candidates":193,"agricultural_evidence":49,"reason":50},[194,198],{"code":39,"score":116,"supported":13,"title":195,"abstract":196,"tags":197},[],[],[27,188,28],{"code":45,"score":21,"supported":13,"title":199,"abstract":200,"tags":201},[],[],[26],[203,204],"农业基准数据集 农业人工智能 视觉语言模型 智慧农业","农业基准数据集 农业人工智能","农业基准数据集农业人工智能视觉语言模型智慧农业-2394",{"doi":8,"openalex_id":8,"authors":207,"venue":8,"cited_by_count":57,"oa_url":8,"card":208,"direction":62,"ingested_from":64},[],{"tldr":209,"method":210,"finding":211,"direction":62,"opportunity":212},"构建农业图像基准，发现视觉语言模型已编码农业特征，但输出未充分体现。","116个数据集、8324张图像基准测试，用PPT验证器做结构化测试时推理。","PPT评判F1近两倍于下限，Gemma 4病害F1达0.71，但置信度与正确性负相关。","可研究农业VLM置信度校准与不确定性量化，提升病害诊断可靠性。","2026-09-14T00:06:32.815855Z",{"id":215,"title":216,"url":217,"summary":218,"summary_zh":219,"content":8,"source_name":220,"source_url":217,"published_at":221,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":222,"score_detail":223,"sources":225,"tags":227,"primary_topic":229,"secondary_topics":235,"classification":236,"search_phrases":252,"slug":255,"view_count":240,"doi":256,"paper":257,"created_at":276},1279,"Scene-graph-grounded vision–language reasoning to action for autonomous multipurpose agricultural robots","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112347","Scene-graph-grounded vision–language reasoning to action for autonomous multipurpose agricultural robots。Computers and Electronics in Agriculture","面向自主多用途农业机器人的场景图接地视觉-语言推理到行动。计算机与电子在农业中的应用","Computers and Electronics in Agriculture","2026-08-31T00:00:00Z",76,{"impact":78,"substance":17,"depth":18,"authority":146,"freshness":40,"relevant":21,"comment":224},"论文提出基于场景图的视觉-语言推理方法，提升农业机器人自主作业能力，方法新颖，数据详实，但发表于2026年8月，时效性较低。",[226],{"name":220,"url":217},[26,27,228,28],"农业机器人",{"code":230,"slug":231,"name":232,"path":233,"parent_code":234},"F6","agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots","F",[],{"status":94,"locked":13,"version":34,"method":35,"evidence":237},{"candidates":238,"agricultural_evidence":49},[239,244,248],{"code":230,"score":240,"supported":49,"title":241,"abstract":242,"tags":243},4,[],[228],[228],{"code":39,"score":40,"supported":13,"title":245,"abstract":246,"tags":247},[],[],[27,28],{"code":45,"score":21,"supported":13,"title":249,"abstract":250,"tags":251},[],[],[26],[253,254],"农业人工智能 视觉语言模型 农业机器人 智慧农业","农业人工智能 视觉语言模型","农业人工智能视觉语言模型农业机器人智慧农业-1279","10.1016\u002Fj.compag.2026.112347",{"doi":256,"openalex_id":258,"authors":259,"venue":220,"cited_by_count":57,"oa_url":8,"card":271,"direction":62,"ingested_from":133},"W7204843057",[260,263,265,268],{"name":261,"orcid":262},"Yonghyun Park","https:\u002F\u002Forcid.org\u002F0000-0001-6085-5957",{"name":264,"orcid":8},"Changjo Kim",{"name":266,"orcid":267},"Gangmin Kim","https:\u002F\u002Forcid.org\u002F0009-0007-3565-4900",{"name":269,"orcid":270},"Hyoung Il Son","https:\u002F\u002Forcid.org\u002F0000-0002-7249-907X",{"tldr":272,"method":273,"finding":274,"direction":62,"opportunity":275},"提出场景图增强的视觉-语言-行动模型，用于自主多功能农业机器人。","利用场景图、视觉-语言模型和推理到行动机制。","场景图提升农业机器人对复杂场景的理解和任务执行能力。","可探索场景图在农业机器人多任务协同、动态环境适应及人机交互中的进一步应用。","2026-09-01T23:30:01.788088Z",{"id":278,"title":279,"url":280,"summary":281,"summary_zh":282,"content":8,"source_name":283,"source_url":280,"published_at":284,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":285,"score_detail":286,"sources":289,"tags":291,"primary_topic":295,"secondary_topics":301,"classification":303,"search_phrases":320,"slug":323,"view_count":57,"doi":324,"paper":325,"created_at":339},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",69,{"impact":20,"substance":287,"depth":18,"authority":98,"freshness":12,"relevant":21,"comment":288},21,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[290],{"name":283,"url":280},[26,27,292,293,294],"小农户","植物病害识别","可解释性",{"code":296,"slug":297,"name":298,"path":299,"parent_code":300},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[302],{"code":39,"slug":154,"name":155,"path":156,"parent_code":91},{"status":94,"locked":13,"version":34,"method":35,"evidence":304},{"candidates":305,"agricultural_evidence":49},[306,311,316],{"code":296,"score":98,"supported":49,"title":307,"abstract":309,"tags":310},[308],"smallholder",[308],[292],{"code":39,"score":12,"supported":49,"title":312,"abstract":314,"tags":315},[313],"computer vision",[],[27,293],{"code":45,"score":21,"supported":13,"title":317,"abstract":318,"tags":319},[],[],[26],[321,322],"农业人工智能 植物病害识别 可解释性 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":324,"openalex_id":326,"authors":327,"venue":283,"cited_by_count":57,"oa_url":280,"card":334,"direction":62,"ingested_from":133},"W7223137323",[328,330,332],{"name":329,"orcid":8},"Akshay Ramgoolam",{"name":331,"orcid":8},"Priya Bundhoo Appadoo",{"name":333,"orcid":8},"Jean-Noël LEspérance",{"tldr":335,"method":336,"finding":337,"direction":62,"opportunity":338},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z",{"id":341,"title":342,"url":343,"summary":344,"summary_zh":345,"content":8,"source_name":283,"source_url":343,"published_at":284,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":285,"score_detail":346,"sources":348,"tags":350,"primary_topic":354,"secondary_topics":360,"classification":362,"search_phrases":387,"slug":390,"view_count":57,"doi":391,"paper":392,"created_at":404},5591,"Hierarchical Conformal Risk Control for Artificial Intelligence Agriculture Irrigation Scheduling Under Unmodeled Infiltration: A Computer Safety-Guarantee Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543665","Irrigation scheduling algorithms that rely on soil-moisture forecasts are vulnerable to unmodeled infiltration, the process by which water bypasses the root zone through preferential pathways that resistance-based soil models cannot represent. The framework is evaluated through a replication-based design study that characterises the operating characteristics of the before-after-control-impact estimator used to audit scheduler performance, under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 54 clusters are required to detect a 5-percentage-point effect at 80% power, and that the minimum detectable effect declines steeply as cluster count rises from 8 to 32. The contribution is a formal safety guarantee for irrigation decision support that remains valid when the infiltration model is wrong, together with an audit design that makes the guarantee empirically checkable.","依赖土壤湿度预报的灌溉调度算法容易受到未建模入渗的影响，即水分通过优先路径绕过根区的过程，而基于阻力的土壤模型无法表征这一过程。该框架通过一项基于重复的设计研究进行评估，该研究刻画了用于审计调度器性能的前后对照影响估计量的运行特性，其所依据的声明方差结构为：组间标准差6.0、残差标准差4.5、组内相关系数0.64。功效估计覆盖2000个设计单元，涵盖聚类数8、16、24和32以及效应量3、5和8个百分点。分析表明，在80%功效下检测5个百分点效应需要54个聚类，且最小可检测效应随聚类数从8增至32而急剧下降。本文的贡献在于为灌溉决策支持提供了一种正式的安全保证，该保证在入渗模型错误时仍然有效，同时提出了一种使该保证可经实证检验的审计设计。",{"impact":20,"substance":17,"depth":18,"authority":98,"freshness":79,"relevant":21,"comment":347},"该研究提出在入渗模型失配条件下仍有效的灌溉决策安全保证框架，并给出可审计的试验设计，方法新颖、结论可靠，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[349],{"name":283,"url":343},[26,27,351,352,353],"灌溉决策","安全保证","试验设计",{"code":355,"slug":356,"name":357,"path":358,"parent_code":359},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[361],{"code":39,"slug":154,"name":155,"path":156,"parent_code":91},{"status":94,"locked":13,"version":34,"method":35,"evidence":363},{"candidates":364,"agricultural_evidence":49},[365,371,376,383],{"code":355,"score":366,"supported":49,"title":367,"abstract":368,"tags":370},15,[356],[369,356],"灌溉",[351],{"code":39,"score":98,"supported":49,"title":372,"abstract":373,"tags":375},[163],[374],"decision support",[27],{"code":377,"score":67,"supported":49,"title":378,"abstract":379,"tags":382},"H2",[],[380,381],"土壤","soil",[],{"code":45,"score":21,"supported":13,"title":384,"abstract":385,"tags":386},[],[],[26],[388,389],"灌溉调度 安全保证","农业人工智能 安全保证 智慧农业 灌溉决策","灌溉调度安全保证-5591","10.5281\u002Fzenodo.23543665",{"doi":391,"openalex_id":393,"authors":394,"venue":283,"cited_by_count":57,"oa_url":343,"card":399,"direction":62,"ingested_from":133},"W7223131205",[395,397],{"name":396,"orcid":8},"Nassima Benkhelifa",{"name":398,"orcid":8},"Yacine Aït Ahmed",{"tldr":400,"method":401,"finding":402,"direction":62,"opportunity":403},"提出分层保形风险控制，为未建模入渗下的灌溉调度提供安全保证。","分层保形风险控制与基于重复设计的BACI审计，2000个设计单元功效分析。","检测5个百分点效应需54个集群，最小可检测效应随集群数增加陡降。","可将保形风险控制扩展到其他未建模扰动下的农业决策安全保证与审计设计。","2026-10-22T11:21:10.283561Z"]