[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3597":3,"related-3597":38},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":8,"paper":8,"created_at":37},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。",null,"[![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",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,20,17,14,8,1,"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。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","病虫害识别","视觉语言模型","枸杞",[33,34],"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",0,"2026-09-27T00:05:17.078840Z",{"total":39,"page":22,"page_size":39,"items":40},6,[41,74,97,123,159,193],{"id":42,"title":43,"url":44,"summary":45,"summary_zh":8,"content":8,"source_name":46,"source_url":8,"published_at":47,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":49,"score_detail":50,"sources":55,"tags":57,"search_phrases":60,"slug":63,"view_count":22,"doi":8,"paper":64,"created_at":73},3048,"基于双路径注意力与多尺度融合的作物病虫害识别网络DPMFNet","https:\u002F\u002Fwww.mdpi.com\u002F1099-4300\u002F28\u002F9\u002F1032","盐城工学院Hong Zhang、Fagen Song等联合江苏开放大学提出DPMFNet轻量级双路径网络，集成空间-通道双注意力（SCDA）与多尺度深度可分离卷积（MDSC）模块，构建AttMDSCBlock残差结构。在PlantVillage与AI Challenger 2018数据集上DPMFNet仅14.24M参数和2.55G FLOPs，跨注意力机制融合局部细节与全局上下文，轻量化金字塔策略自适应整合多分辨率特征，在复杂农田场景下兼顾精度与可部署性，为嵌入式田间设备提供高性价比方案。","MDPI Entropy 28(9):1032","2026-09-20T00:00:00Z","论文",79,{"impact":51,"substance":52,"depth":17,"authority":53,"freshness":13,"relevant":22,"comment":54},16,22,13,"轻量级双路径注意力网络在两大公开数据集上兼顾精度与可部署性，对嵌入式田间设备落地有实质参考价值。",[56],{"name":46,"url":44},[27,28,29,58,59],"作物监测","轻量化模型",[61,62],"盐城工学院 DPMFNet 病虫害识别","PlantVillage AI Challenger 作物病害","盐城工学院DPMFNet病虫害识别-3048",{"doi":8,"openalex_id":8,"authors":65,"venue":8,"cited_by_count":36,"oa_url":8,"card":66,"direction":70,"ingested_from":72},[],{"tldr":67,"method":68,"finding":69,"direction":70,"opportunity":71},"提出轻量级双路径网络DPMFNet，实现复杂农田场景下的作物病虫害高精度识别。","空间-通道双注意力与多尺度深度可分离卷积，构建AttMDSCBlock残差结构。","仅14.24M参数、2.55G FLOPs，在PlantVillage与AI Challenger ","农业人工智能与决策模型","可探索真实田间多病虫害并发与边缘设备实时推理的轻量化自适应识别研究。","agent","2026-09-21T00:04:39.305757Z",{"id":75,"title":76,"url":77,"summary":78,"summary_zh":8,"content":8,"source_name":79,"source_url":8,"published_at":80,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":81,"score_detail":82,"sources":86,"tags":88,"search_phrases":92,"slug":95,"view_count":22,"doi":8,"paper":8,"created_at":96},2815,"WAFI2026人工智能与农业论坛:中国方案助力农民种得好、种得起、种得稳、种得赚","https:\u002F\u002Fbaike.baidu.com\u002Fitem\u002F2026%E4%B8%96%E7%95%8C%E5%86%9C%E4%B8%9A%E7%A7%91%E6%8A%80%E5%88%9B%E6%96%B0%E5%A4%A7%E4%BC%9A\u002F68651190","9月16日WAFI2026举行\"人工智能与农业论坛\",中国农业大学全球食物经济与政策研究院院长樊胜根提出\"人工智能如何造福农民\"议题。论坛介绍神农大模型(2023年1.0版到2025年3.0版,3.0版为\"小麦育种智能助手\",可识别70类、600余种病虫害,已在非洲落地)、农业食物经济与政策AI模型、北大荒\"未来农场\"平台(覆盖111个农场、接入8.4万台智能装备、为60万种植户服务)、北京市\"智京园\"智慧设施管控技术体系等案例。","百度百科 \u002F 中国农业大学","2026-09-16T00:00:00Z",86,{"impact":83,"substance":84,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":85},26,21,"国际论坛上集中展示神农大模型、北大荒未来农场等中国AI农业方案，案例数据具体、信源权威，时效性强，值得进入每日精选。",[87],{"name":79,"url":77},[27,28,89,90,91,29],"未来农场","智能育种","大模型",[93,94],"农业人工智能 病虫害识别 智慧农业 智能育种","农业人工智能 病虫害识别","农业人工智能病虫害识别智慧农业智能育种-2815","2026-09-18T00:03:24.639818Z",{"id":98,"title":99,"url":100,"summary":101,"summary_zh":8,"content":8,"source_name":102,"source_url":8,"published_at":103,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":104,"sources":106,"tags":108,"search_phrases":111,"slug":114,"view_count":22,"doi":8,"paper":115,"created_at":122},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":17,"substance":52,"depth":17,"authority":53,"freshness":39,"relevant":22,"comment":105},"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。",[107],{"name":102,"url":100},[27,28,30,109,110],"病害识别","农业基准数据集",[112,113],"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":116,"venue":8,"cited_by_count":36,"oa_url":8,"card":117,"direction":70,"ingested_from":72},[],{"tldr":118,"method":119,"finding":120,"direction":70,"opportunity":121},"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":124,"title":125,"url":126,"summary":127,"summary_zh":128,"content":8,"source_name":129,"source_url":126,"published_at":130,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":131,"score_detail":132,"sources":135,"tags":137,"search_phrases":140,"slug":142,"view_count":22,"doi":143,"paper":144,"created_at":158},2158,"EfficientNet-CBAM-prototype: an attention-guided EfficientNet framework with dynamic prototype representation for tomato disease classification","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1918175","Introduction In the field of precision agriculture, one of the major hurdles is the early and accurate identification of plant diseases. Farmers may face serious irreversible loss in yield if there is a delay in diagnosis by even a few days. The CNN model has helped in improving the classification of plant diseases but faces difficulty in distinguishing fine-grained symptoms, has limited generalizability, and is not easily interpretable. Though the deep CNN model performs well in classifying plant diseases, the current methods have several flaws. Most importantly, existing algorithms misclassify visually complex samples due to their limited spatial differentiation of disease-specific morphological features, including lesion borders and necrotic regions. Classification reliability is further compromised by low inter-class embedding separability for visually comparable illness phenotypes. Apart from these representational problems, training instability is still a major problem for attention-based models. Combining randomly initialized attention modules with pretrained backbone networks causes this instability, which still limits practical application. Methods We suggest EfficientNet-CBAM-Prototype (ECP-Net), a unique end-to-end deep learning architecture, to overcome these constraints. Three complementary techniques are combined into a single framework by ECP-Net. First, parameter-efficient multi-scale feature extraction is done using an EfficientNetB0 backbone. Second, joint channel-wise and spatial feature recalibration is performed using a stabilized convolutional block attention module (CBAM). Third, a dynamic prototype memory layer uses cosine similarity-based categorization and exponential moving average (EMA) updates to maintain class-representative embedding vectors. To overcome the instability caused by randomly initialized attention weights, we further propose a two-phase training strategy wherein CBAM is frozen during phase 1 to allow prototype stabilization and then jointly fine-tuned with the learning rate in phase 2. Results Evaluated on the PlantVillage tomato subset comprising 10 disease classes across a class-balanced split of 10,000 training, 500 validation, and 500 test samples, ECP-Net achieves 98.6% test accuracy, 98.59% F1-score, and 98.65% precision with only 4.80M parameters and 85.04 ms average inference time. These results outperformed baselines including VGG16 (97.00%), ResNet50 (81.20%), MobileNetV2 (81.20%), and CNN (70.00%). Discussion Generalization is further validated on 35 real-field tomato leaf images captured under natural, uncontrolled conditions, confirming practical deployment potential.","引言 在精准农业领域，植物病害的早期准确识别是主要难题之一。若诊断延迟哪怕几天，农民可能面临严重的不可逆产量损失。CNN模型有助于改进植物病害分类，但在区分细粒度症状方面存在困难，泛化能力有限，且不易解释。尽管深度CNN模型在植物病害分类中表现良好，当前方法仍存在若干缺陷。最重要的是，现有算法由于对病害特异性形态特征（包括病斑边缘和坏死区域）的空间区分能力有限，会对视觉上复杂的样本产生误分类。对于视觉上相似的病害表型，类间嵌入可分性低，进一步损害了分类可靠性。除这些表征问题外，训练不稳定性仍是基于注意力模型的主要问题。随机初始化的注意力模块与预训练骨干网络相结合会导致这种不稳定性，这仍然限制了实际应用。方法 我们提出EfficientNet-CBAM-Prototype（ECP-Net），一种新颖的端到端深度学习架构，以克服这些限制。ECP-Net将三种互补技术结合到一个统一框架中。首先，使用EfficientNetB0骨干网络进行参数高效的多尺度特征提取。其次，使用稳定化的卷积块注意力模块（CBAM）进行通道与空间的联合特征重校准。第三，动态原型记忆层使用基于余弦相似度的分类和指数移动平均（EMA）更新来维护类代表性嵌入向量。为克服随机初始化注意力权重引起的不稳定性，我们进一步提出两阶段训练策略，其中CBAM在第一阶段冻结以使原型稳定，然后在第二阶段以学习率联合微调。结果 在PlantVillage番茄子集上评估，该子集包含10个病害类别，按类别均衡划分的10,000个训练样本、500个验证样本和500个测试样本，ECP-Net达到98.6%的测试准确率、98.59%的F1分数和98.65%的精确率，仅需4.80M参数和85.04 ms平均推理时间。这些结果优于基线，包括VGG16（97.00%）、ResNet50（81.20%）、MobileNetV2（81.20%）和CNN（70.00%）。","Frontiers in Plant Science","2026-09-10T00:00:00Z",81,{"impact":17,"substance":52,"depth":17,"authority":20,"freshness":133,"relevant":22,"comment":134},9,"提出注意力引导与动态原型结合的番茄病害识别框架，在公开数据集上取得98.6%准确率并完成真实田间图像验证，方法新颖、数据扎实，对作物病害智能诊断有实用参考价值。",[136],{"name":129,"url":126},[27,28,138,29,139],"深度学习","番茄种植",[141,94],"农业人工智能 病虫害识别 智慧农业 深度学习","农业人工智能病虫害识别智慧农业深度学习-2158","10.3389\u002Ffpls.2026.1918175",{"doi":143,"openalex_id":145,"authors":146,"venue":129,"cited_by_count":36,"oa_url":126,"card":151,"direction":156,"ingested_from":157},"W7212120374",[147,149],{"name":148,"orcid":8},"E Jansi",{"name":150,"orcid":8},"Kavitha BR",{"tldr":152,"method":153,"finding":154,"direction":70,"opportunity":155},"提出ECP-Net，用注意力与动态原型提升番茄病害分类精度与可解释性。","EfficientNetB0+稳定CBAM+动态原型记忆层，两阶段训练策略。","在PlantVillage番茄10类上达98.6%准确率，仅4.80M参数，优于多个基线。","可探索原型可解释性在田间复杂背景与跨域病害识别中的泛化能力。","农业遥感与作物表型","openalex","2026-09-11T23:30:25.043704Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":8,"source_name":165,"source_url":162,"published_at":166,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":167,"score_detail":168,"sources":171,"tags":173,"search_phrases":175,"slug":177,"view_count":36,"doi":178,"paper":179,"created_at":192},2048,"Optimized Inception-v4 CNN Combined with YOLOv8 andXGBoost for Tomato Plant Disease Recognition and Classification","https:\u002F\u002Fdoi.org\u002F10.38094\u002Fjastt711230","This study proposes an integrated hybrid pipeline approach which is the combination of an optimized Inception-v4 Convolutional Neural Network (CNN), YOLOv8 (You Only Look Once version 8) and extreme gradient boosting (XG Boost) models to detect and classify Tomato plant diseases effectively and accurately. The proposed methodology is based on the fine-grained localization ability of the YOLOv8 model to accurately localize the affected area of the leaf, multi-scale deep feature extraction ability of the optimized Inceptionv4 CNN, and XG Boost to reduce dimensions and optimize features. The hybrid model combines the Inception-v4 CNN, YOLOv8, and XG Boost models with an average CPU processing time of about 200 milliseconds per image, the model performs better in terms of computational efficiency, robustness, and faster prediction. Experimental tests on Plant Village show that the model outperforms the state of the art in 10 disease categories. Specifically, the integrated hybrid system achieved high precision, recall, F1-score, mean Average Precision (m AP), and its training accuracy was more than 0.98 (up to 0.9969), and the testing accuracy was more than 0.96 (up to 0.9695). The hybrid framework shows good reliability even for diseases that are visually similar, such as bacterial spot, early blight, late blight, mosaic virus and yellow leaf curl virus. The optimization of batch size to 32, along with the tuning of the learning rate further improved the stability of training, convergence speed and the generalization of the overall model. The proposed system holds promise for real-time, scalable, and sustainable precision agriculture, aiming for early disease detection and yield protection. Future work includes incorporating Internet of Things (IoT) edge devices, in field environmental monitoring, multimodal data integration and applying Explainable Artificial Intelligence (EAI) techniques to enhance model interpretability for end-users.","本研究提出了一种集成的混合流水线方法，将优化的Inception-v4卷积神经网络（CNN）、YOLOv8（You Only Look Once version 8）和极端梯度提升（XG Boost）模型相结合，以有效且准确地检测和分类番茄植株病害。所提方法基于YOLOv8模型的细粒度定位能力来准确定位叶片受感染区域、优化的Inception-v4 CNN的多尺度深层特征提取能力，以及XG Boost用于降维和特征优化。该混合模型将Inception-v4 CNN、YOLOv8和XG Boost模型结合在一起，每幅图像的平均CPU处理时间约为200毫秒，模型在计算效率、鲁棒性和更快预测方面表现更优。在Plant Village上的实验测试表明，该模型在10个病害类别上优于现有最先进方法。具体而言，该集成混合系统实现了较高的精确率、召回率、F1分数、平均精度均值（mAP），其训练准确率超过0.98（最高达0.9969），测试准确率超过0.96（最高达0.9695）。即使对于视觉上相似的病害，如细菌性斑点病、早疫病、晚疫病、花叶病毒和黄花叶卷曲病毒，该混合框架也表现出良好的可靠性。将批量大小优化为32，并调整学习率，进一步提高了训练稳定性、收敛速度和整体模型的泛化能力。所提系统有望用于实时、可扩展和可持续的精准农业，旨在实现早期病害检测和产量保护。未来工作包括整合物联网（IoT）边缘设备、田间环境监测、多模态数据融合，以及应用可解释人工智能（EAI）技术以增强模型对最终用户的可解释性。","Journal of Applied Science and Technology Trends","2026-09-09T00:00:00Z",75,{"impact":51,"substance":18,"depth":17,"authority":169,"freshness":133,"relevant":22,"comment":170},12,"提出YOLOv8+Inception-v4+XGBoost混合模型用于番茄病害识别，准确率与效率数据扎实，对农业AI病害检测有参考价值。",[172],{"name":165,"url":162},[27,28,29,174,139],"精准农业",[176,94],"农业人工智能 病虫害识别 智慧农业 番茄种植","农业人工智能病虫害识别智慧农业番茄种植-2048","10.38094\u002Fjastt711230",{"doi":178,"openalex_id":180,"authors":181,"venue":165,"cited_by_count":36,"oa_url":162,"card":186,"direction":191,"ingested_from":157},"W7212078878",[182,184],{"name":183,"orcid":8},"Sowmya B",{"name":185,"orcid":8},"Guruprasad S",{"tldr":187,"method":188,"finding":189,"direction":70,"opportunity":190},"提出YOLOv8+Inception-v4+XGBoost混合模型，实现番茄叶片病害精准检测与分类。","YOLOv8定位病斑，Inception-v4提取多尺度特征，XGBoost降维","10类病害识别精度超现有方法，训练准确率0.9969，测试0.9695，单图CPU约200毫秒。","可探索IoT边缘部署、多模态数据融合与可解释AI，提升田间实时病害诊断可信度。","智慧农业 \u002F 农业物联网","2026-09-10T23:30:14.735468Z",{"id":194,"title":195,"url":196,"summary":197,"summary_zh":8,"content":8,"source_name":198,"source_url":8,"published_at":199,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":200,"score_detail":201,"sources":205,"tags":207,"search_phrases":209,"slug":211,"view_count":22,"doi":8,"paper":8,"created_at":212},1551,"神农大模型 4.0 路演落地湘湖实验室：病虫害识别拓展至 1016 种、准确率超 93%，覆盖全国 31 省超 500 万亩农田","https:\u002F\u002Fwww.xiaoshan.gov.cn\u002Fcol\u002Fcol1302903\u002Fart\u002F2026\u002Fart_51407f23df244519a64db25c4b0ea0b5.html","近日，\"神农大模型\"路演暨场景应用交流会在杭州市萧山区湘湖实验室举办。最新发布的神农大模型 4.0 病虫害识别种类拓展至 1016 种、识别准确率超 93%，可适配大田、设施农业、畜禽养殖等多元场景；同步推出的\"神农·农业世界模型 1.0\"能搭建数字孪生仿真田块，不用下地试种便可模拟预判施肥、温控等对作物长势的影响。这套农业\"超级大脑\"已覆盖全国 31 个省份超 500 万亩农田，惠及百万农户。","杭州市萧山区人民政府","2026-09-03T00:00:00Z",80,{"impact":202,"substance":52,"depth":203,"authority":13,"freshness":21,"relevant":22,"comment":204},25,15,"神农大模型4.0覆盖全国31省500万亩农田，病虫害识别准确率超93%，具有产业级影响，信息增量大，信源为地方政府官网，时效性佳。",[206],{"name":198,"url":196},[27,28,91,208,29],"数字孪生",[210,94],"农业人工智能 病虫害识别 数字孪生 智慧农业","农业人工智能病虫害识别数字孪生智慧农业-1551","2026-09-04T00:05:30.291011Z"]