[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2879":3,"related-2879":37},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":8,"paper":8,"created_at":36},2879,"中国咖啡的品质根基与创新驱动论坛在昆明举办:云南省农科院聚焦全产业链标准体系","https:\u002F\u002Fnews.qq.com\u002Frain\u002Fa\u002F20260918A07YT800","9月17日,2026中国热带作物产业大会分论坛在昆明举行,来自中国标准化研究院、云南省农业科学院等单位的80余名代表参会。论坛以标准筑基科技赋能为主线,中国农业大学副教授李想作AI助力种好咖啡报告,介绍AI农技大脑一田一策精准决策、AI撮合平台、田间移动服务站、智慧农场ERP等农事服务新模式,提出AI-农业服务人员-农民服务路径。",null,"中国新闻网\u002F腾讯新闻","2026-09-18T00:00:00Z","报道",10,false,68,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},18,16,14,11,9,1,"省级科研机构主导的咖啡全产业链标准与AI农技服务论坛，行业细分进展有实质信息，但影响层级限于产业与省级范围。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","咖啡产业","热带作物","农业标准体系",[32,33],"云南省农科院 咖啡 标准体系","AI农技大脑 咖啡","云南省农科院咖啡标准体系-2879",0,"2026-09-19T00:06:04.718237Z",{"total":38,"page":21,"page_size":38,"items":39},6,[40,73,102,130,158,187],{"id":41,"title":42,"url":43,"summary":44,"summary_zh":8,"content":8,"source_name":45,"source_url":8,"published_at":46,"category":47,"cover_url":8,"hotness":12,"is_selected":13,"score":48,"score_detail":49,"sources":53,"tags":55,"search_phrases":59,"slug":62,"view_count":35,"doi":8,"paper":63,"created_at":72},2904,"Decoupled Foundation Models:基于YOLO26m+SAM2+DINOv2的湿度诱导番茄叶坏死实例分割与检测,登MDPI Agriculture 16(18)1997","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F1997","本研究针对温室番茄相对湿度过高引发的非生物胁迫(生理性叶坏死,与生物感染症状相似),提出多步AI管道自动化分割与分类坏死叶斑。采集218张RGB图像、3218个标注(棕色坏死斑\u002F黄色坏死斑\u002F无坏死),系统评估6种端到端实例分割管道(YOLO26m检测+SAM2零样本分割+微调DINOv2或EfficientNet-B3分类);微调DINOv2宏F1达0.926,优于EfficientNet-B3、ResNet-50、Swin-Small基线(0.886-0.901);最佳配置mAP@50=0.828,较YOLO26m单模型提升约8%。","MDPI Agriculture","2026-09-17T00:00:00Z","论文",78,{"impact":17,"substance":50,"depth":16,"authority":51,"freshness":20,"relevant":21,"comment":52},22,13,"方法组合新颖、数据规模与对比基线扎实，对温室番茄生理性叶坏死自动识别有实用价值，值得进入每日精选。",[54],{"name":45,"url":43},[26,27,56,57,58],"设施农业","番茄","病害识别",[60,61],"番茄叶坏死 实例分割","农业人工智能 智慧农业 病害识别 设施农业","番茄叶坏死实例分割-2904",{"doi":8,"openalex_id":8,"authors":64,"venue":8,"cited_by_count":35,"oa_url":8,"card":65,"direction":69,"ingested_from":71},[],{"tldr":66,"method":67,"finding":68,"direction":69,"opportunity":70},"用YOLO26m+SAM2+DINOv2多步管道分割并分类高湿诱导的番茄叶坏死斑。","218张RGB图像、3218个标注，评估6种实例分割管道并微调DINOv2分类。","微调DINOv2宏F1达0.926，最佳配置mAP@50=0.828，较单模型提升约8%。","农业人工智能与决策模型","可探索零样本基础模型在多种非生物胁迫症状上的泛化与轻量化温室部署。","agent","2026-09-19T00:06:09.021594Z",{"id":74,"title":75,"url":76,"summary":77,"summary_zh":8,"content":8,"source_name":78,"source_url":8,"published_at":10,"category":47,"cover_url":8,"hotness":12,"is_selected":13,"score":79,"score_detail":80,"sources":82,"tags":84,"search_phrases":88,"slug":91,"view_count":35,"doi":92,"paper":93,"created_at":101},2903,"基于QYmax叶绿素荧光成像和改进LCRNet模型的小麦白粉病智能识别与诊断,登Frontiers in Plant Science","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1837843\u002Ffull","本研究整合叶绿素荧光成像与深度学习算法,刻画小麦白粉病发展过程中QYmax等关键荧光参数的时序动态;构建基于QYmax的小麦白粉病叶绿素荧光图像数据集;提出LCRNet智能识别模型,通过LSAF大型选择性自适应融合和CA坐标注意力模块的协同处理机制,实现高效病害识别。在独立测试集上模型准确率达98.0%、F1-score达98.3%,显著优于对比模型,为作物病害预防控制系统的智能化与精准化绿色转型提供高精度方案。","Frontiers in Plant Science",82,{"impact":16,"substance":50,"depth":16,"authority":18,"freshness":12,"relevant":21,"comment":81},"方法新颖、数据扎实且时效性强，但属细分领域论文，产业影响有限，适合进入每日精选。",[83],{"name":78,"url":76},[26,27,85,86,87],"作物病害识别","小麦白粉病","叶绿素荧光成像",[89,90],"小麦白粉病 叶绿素荧光成像 LCRNet","QYmax 小麦白粉病 智能识别","小麦白粉病叶绿素荧光成像LCRNet-2903","10.3389\u002Ffpls.2026.1837843\u002Ffull",{"doi":92,"openalex_id":8,"authors":94,"venue":8,"cited_by_count":35,"oa_url":8,"card":95,"direction":99,"ingested_from":71},[],{"tldr":96,"method":97,"finding":98,"direction":99,"opportunity":100},"用QYmax叶绿素荧光成像与改进LCRNet实现小麦白粉病高精度识别。","构建QYmax荧光图像数据集，提出含LSAF与CA模块的LCRNet模型。","独立测试集准确率98.0%、F1-score 98.3%，显著优于对比模型。","农业遥感与作物表型","可探索多病害、多生育期与田间自然光下的荧光成像泛化及轻量化部署。","2026-09-19T00:06:08.843770Z",{"id":103,"title":104,"url":105,"summary":106,"summary_zh":8,"content":8,"source_name":107,"source_url":8,"published_at":108,"category":47,"cover_url":8,"hotness":12,"is_selected":13,"score":48,"score_detail":109,"sources":112,"tags":114,"search_phrases":118,"slug":121,"view_count":35,"doi":8,"paper":122,"created_at":129},2902,"TSAFI-DT:可持续性感知花生产量预测数字孪生框架,登MDPI AI 7(9)364","https:\u002F\u002Fwww.mdpi.com\u002F2673-2688\u002F7\u002F9\u002F364","本研究提出TSAFI-DT可回顾验证的、数据驱动的Digital Twin原型,集成时空数据重建、可持续状态表征、分层产量预测、反事实分析与情景模拟。基于1997-2023年印度地区级花生数据,采用贝叶斯优化的XGBoost模型进行一步前瞻产量预测,RMSE=0.171 t\u002Fha,显著优于基线;结合固定效应与合成控制分析,eRAI扩展再生农业指数整合作物多样性、生产力稳定性、土地利用效率和产量趋势,预测产量在可持续性扰动下可提升12.4%。","MDPI AI","2026-09-14T00:00:00Z",{"impact":16,"substance":50,"depth":110,"authority":51,"freshness":38,"relevant":21,"comment":111},19,"方法新颖、数据规模扎实的农业数字孪生研究，对智慧农业与产量预测领域有参考价值，但属细分学术进展，非产业级事件。",[113],{"name":107,"url":105},[26,27,115,116,117],"数字孪生","可持续农业","花生产量预测",[119,120],"TSAFI-DT 花生 数字孪生","印度 花生 产量预测","TSAFI-DT花生数字孪生-2902",{"doi":8,"openalex_id":8,"authors":123,"venue":8,"cited_by_count":35,"oa_url":8,"card":124,"direction":69,"ingested_from":71},[],{"tldr":125,"method":126,"finding":127,"direction":69,"opportunity":128},"提出可持续性感知数字孪生框架TSAFI-DT，用于印度花生产量预测与情景模拟。","基于1997-2023年印度地区级数据，用贝叶斯优化XGBoost和合成控制分析","XGBoost预测RMSE为0.171 t\u002Fha，可持续性扰动下产量可提升12.4%。","可探索将数字孪生与实时物联网数据结合，实现动态可持续性评估与决策支持。","2026-09-19T00:06:08.754978Z",{"id":131,"title":132,"url":133,"summary":134,"summary_zh":8,"content":8,"source_name":135,"source_url":8,"published_at":46,"category":47,"cover_url":8,"hotness":12,"is_selected":13,"score":136,"score_detail":137,"sources":140,"tags":142,"search_phrases":146,"slug":149,"view_count":35,"doi":8,"paper":150,"created_at":157},2901,"AgriScope:面向农业图像的像素级多模态理解统一框架,arXiv 2609.20325(预印本)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.20325","Boudiaf、Alanssari、Hussain、Javed提出AgriScope,一个统一的像素级多模态农业图像理解框架,联合支持图像级、区域级、像素级理解,可实现接地描述生成、指代表达分割、多轮多模态交互等任务。集成生物专用语义表征、密集空间表征与像素解码;引入大规模像素级农业多模态指令调优数据集AgriGround,包含50万+图像和1100万+指令跟随样本,涵盖植物病害分析、作物与杂草识别、昆虫识别、细粒度植物理解。实验表明AgriScope在多项农业视觉语言任务上有效。","arXiv (preprint)",75,{"impact":16,"substance":50,"depth":16,"authority":138,"freshness":20,"relevant":21,"comment":139},8,"提出统一像素级农业多模态理解框架并开源50万图像、1100万指令样本的大规模数据集，方法新颖、数据规模突出，但为arXiv预印本、未经同行评审，权威性有限，值得作为前沿技术动态精选。",[141],{"name":135,"url":133},[26,27,143,144,145],"农业遥感","植物病害识别","多模态大模型",[147,148],"AgriScope 农业图像 多模态","AgriGround 像素级 农业数据集","AgriScope农业图像多模态-2901",{"doi":8,"openalex_id":8,"authors":151,"venue":8,"cited_by_count":35,"oa_url":8,"card":152,"direction":69,"ingested_from":71},[],{"tldr":153,"method":154,"finding":155,"direction":69,"opportunity":156},"提出AgriScope统一框架，实现农业图像像素级多模态理解与多任务交互。","构建AgriGround数据集（50万+图像、1100万+指令样本），融合语义与","AgriScope在接地描述、指代分割、多轮交互等农业视觉语言任务上有效。","可探索像素级多模态模型在田间实时病害诊断与精准施药决策中的落地与轻量化。","2026-09-19T00:06:08.678379Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":8,"content":8,"source_name":163,"source_url":8,"published_at":108,"category":47,"cover_url":8,"hotness":12,"is_selected":13,"score":164,"score_detail":165,"sources":168,"tags":170,"search_phrases":175,"slug":178,"view_count":35,"doi":8,"paper":179,"created_at":186},2900,"Crop-GPA 2.0:安徽农业大学团队发布跨物种基因-表型预测深度学习工具,登The Crop Journal","https:\u002F\u002Fwww.global-agriculture.com\u002Fag-tech-research-news\u002Fchinese-researchers-launch-ai-tool-that-predicts-crop-gene-trait-links-across-species\u002F","安徽农业大学岳振宇教授团队(第一作者高玉佳)开发的Crop-GPA 2.0跨物种基因-表型预测深度学习工具于2026年9月10日发表在The Crop Journal。该工具通过分层基因组表征、跨物种预训练、性状感知学习三种联动技术,在水稻、玉米、小麦测试中跨性状(产量、抗病性、抗逆性、籽粒品质)均优于现有方法,且能在新物种或训练数据有限时保持较好性能,在线平台为育种者提供免费SNP排名服务,极大降低标记辅助选择门槛。","Global Agriculture \u002F The Crop Journal",83,{"impact":50,"substance":166,"depth":16,"authority":18,"freshness":38,"relevant":21,"comment":167},23,"跨物种基因-表型预测工具登核心期刊，方法新颖、结论可靠，对智能育种有实质推动，值得进入每日精选。",[169],{"name":163,"url":161},[26,27,171,172,173,174],"水稻","智能育种","玉米","基因-表型预测",[176,177],"安徽农业大学 Crop-GPA 2.0","Crop-GPA 2.0 基因-表型预测","安徽农业大学Crop-GPA2.0-2900",{"doi":8,"openalex_id":8,"authors":180,"venue":8,"cited_by_count":35,"oa_url":8,"card":181,"direction":69,"ingested_from":71},[],{"tldr":182,"method":183,"finding":184,"direction":69,"opportunity":185},"安徽农业大学团队发布跨物种基因-表型预测深度学习工具Crop-GPA 2.0，并在水稻、玉米、小麦中","分层基因组表征、跨物种预训练、性状感知学习，基于多物种SNP与表型数据。","跨性状预测均优于现有方法，新物种或小样本下仍表现良好，并提供免费在线SNP排名服务。","可探索将跨物种预训练模型与田间表型组、环境数据融合，提升复杂性状预测与育种决策的可解释性。","2026-09-19T00:06:08.595080Z",{"id":188,"title":189,"url":190,"summary":191,"summary_zh":8,"content":8,"source_name":192,"source_url":8,"published_at":108,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":193,"score_detail":194,"sources":200,"tags":202,"search_phrases":206,"slug":209,"view_count":35,"doi":8,"paper":8,"created_at":210},2899,"佳木斯国家农高区伏羲大脑智慧农服APP累计服务600多万亩:覆盖6万多户农民","https:\u002F\u002Fwww.gskjb.cn\u002Fgskjb\u002F20260914\u002Fhtml\u002Fcontent_20260914003003.htm","在黑龙江佳木斯国家农业高新技术产业示范区,中国科学院研发的伏羲大脑农业大模型搭建的普惠式智慧农业服务体系正在改变传统农耕模式。农事综合服务手机APP成为农户的新农具,涵盖农事指导、农资直供、农机呼叫、卖粮、补贴、培训、金融保险等10项功能。农户上传地块信息后系统自动地块智能体检;系统每3-7天更新一次遥感数据。去年服务佳木斯100多万亩农田,一年半时间扩大到600多万亩,覆盖佳木斯6万多户农民。","甘肃科技报\u002F农民日报",74,{"impact":50,"substance":195,"depth":196,"authority":197,"freshness":198,"relevant":21,"comment":199},20,15,12,5,"国家级科研机构大模型落地农业社会化服务的规模化案例，数据具体、可复制性强，值得进入每日精选。",[201],{"name":192,"url":190},[203,26,27,204,205],"数字乡村","农业大模型","农业社会化服务",[207,208],"佳木斯农高区 伏羲大脑 智慧农服APP","中国科学院 伏羲大脑 农业大模型","佳木斯农高区伏羲大脑智慧农服APP-2899","2026-09-19T00:06:07.688523Z"]