[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2885":3,"related-2885":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},2885,"江苏省农科院召开2026年第一批中央预算内投资计划工作部署会:6方面要求强调科研在前面向AI与数据融合","https:\u002F\u002Fjaas.ac.cn\u002Fxww\u002Fnkyw\u002Fart\u002F2026\u002Fart_55cfb9e6aeac433b88a7c3bfed48ae97.html","9月17日,江苏农科院召开农业专项2026年第一批中央预算内投资计划工作部署会,党委委员、副院长孙洪武主持。涉及种质资源保护利用、生物安全评价、绿色防控和中试转化。要求科研在前、设施在后;全院统筹、开放共享;建管并重、运维同步;依法合规、廉洁贯穿;科研满意、智能融合;职责清晰、分工协作,推动人工智能、大数据等新技术与科研设施融合。",null,"9月17日，我院召开农业专项2026年第一批中央预算内投资计划工作部署会。党委委员、副院长孙洪武主持会议并传达院长朱艳工作要求，党委委员、副院长王冉、李爱宏出席会议。院项目建设单位负责人、项目负责人、相关职能部门负责人和管理人员，以及项目相关人员参加会议。\n\n会议指出，2026年第一批项目涉及种质资源保护利用、生物安全评价、绿色防控和中试转化，是我院支撑科技创新、服务国家粮食安全和农业科技自立自强的重要载体，必须统一思想、提高站位，作为重要政治任务和发展任务抓紧抓实。会议提出六个方面要求：一是科研在前、设施在后，方向不能倒置，科研设施必须围绕科研方向、重大任务和创新团队建设，不能建成形象工程；二是全院统筹、开放共享，资源不能分割，能共用的不重复建，大型仪器设备纳入院共享平台，种质资源、表型、监测、评价等数据互联互通；三是建管并重、运维同步，眼光不能短视，提前落实运维经费、组建运维团队、预留升级空间，把实验室安全、生物安全、数据安全、消防安全和施工安全贯穿始终；四是依法合规、廉洁贯穿，红线不能触碰，严格招标采购、资金管理、工程变更和廉洁自律，资金专款专用，审计提前介入，纪检监察加强监督；五是科研满意、智能融合，标准不能降低，把科研人员满不满意、好不好用、愿不愿意共享作为检验标准，推动人工智能、大数据等新技术与科研设施融合，注重绩效产出；六是职责清晰、分工协作，责任不能悬空，领导专班统筹抓总，管理专班具体协调，职能部门各负其责、主动服务，项目单位负责人和项目负责人履行第一责任人责任，实行月调度、季通报、年考核，对工作不力的严肃追责问责。\n\n会上，科研处解读了中央预算内投资项目工作实施方案，基建处、基地处、后勤保卫处、财务处分别作工作提示，各项目单位负责人作表态发言，各项目负责人分别介绍了项目情况，围绕设施用地、场地改造、温室网室建设、仪器设备采购、配套资金安排、旧房改造等提出需要协调解决的问题。\n\n[![Image 1: image001.jpg](https:\u002F\u002Fjaas.ac.cn\u002Fcms_files\u002Ffilemanager\u002F191335345\u002Fpicture\u002F20268\u002FSdb97cd401da4494ea44a620c412add6f-800.jpg)](https:\u002F\u002Fjaas.ac.cn\u002Fcms_files\u002Ffilemanager\u002F191335345\u002Fpicture\u002F20268\u002Fdb97cd401da4494ea44a620c412add6f.jpg)\n\n[![Image 2: image003.jpg](https:\u002F\u002Fjaas.ac.cn\u002Fcms_files\u002Ffilemanager\u002F191335345\u002Fpicture\u002F20268\u002FS8727f3e8b0d1429baab1bac1d53e5b22-800.jpg)](https:\u002F\u002Fjaas.ac.cn\u002Fcms_files\u002Ffilemanager\u002F191335345\u002Fpicture\u002F20268\u002F8727f3e8b0d1429baab1bac1d53e5b22.jpg)","江苏省农业科学院","2026-09-18T00:00:00Z","报道",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,18,15,13,9,1,"省级农科院投资部署会，六方面要求明确科研优先与AI数据融合导向，对农业科研设施建设有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","种质资源","中央预算内投资","科研设施共享",[33,34],"江苏省农科院 中央预算内投资","农业科研设施 智能融合","江苏省农科院中央预算内投资-2885",0,"2026-09-19T00:06:06.278959Z",{"total":39,"page":22,"page_size":39,"items":40},6,[41,73,103,131,159,188],{"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":53,"tags":55,"search_phrases":59,"slug":62,"view_count":36,"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":51,"depth":18,"authority":20,"freshness":21,"relevant":22,"comment":52},22,"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":46,"url":44},[27,28,56,57,58],"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":36,"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":11,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":79,"score_detail":80,"sources":83,"tags":85,"search_phrases":89,"slug":92,"view_count":36,"doi":93,"paper":94,"created_at":102},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":18,"substance":51,"depth":18,"authority":81,"freshness":13,"relevant":22,"comment":82},14,"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。",[84],{"name":78,"url":76},[27,28,86,87,88],"作物病害识别","小麦白粉病","叶绿素荧光成像",[90,91],"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":93,"openalex_id":8,"authors":95,"venue":8,"cited_by_count":36,"oa_url":8,"card":96,"direction":100,"ingested_from":71},[],{"tldr":97,"method":98,"finding":99,"direction":100,"opportunity":101},"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":104,"title":105,"url":106,"summary":107,"summary_zh":8,"content":8,"source_name":108,"source_url":8,"published_at":109,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":49,"score_detail":110,"sources":113,"tags":115,"search_phrases":119,"slug":122,"view_count":36,"doi":8,"paper":123,"created_at":130},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":18,"substance":51,"depth":111,"authority":20,"freshness":39,"relevant":22,"comment":112},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。",[114],{"name":108,"url":106},[27,28,116,117,118],"数字孪生","可持续农业","花生产量预测",[120,121],"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":124,"venue":8,"cited_by_count":36,"oa_url":8,"card":125,"direction":69,"ingested_from":71},[],{"tldr":126,"method":127,"finding":128,"direction":69,"opportunity":129},"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":132,"title":133,"url":134,"summary":135,"summary_zh":8,"content":8,"source_name":136,"source_url":8,"published_at":47,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":137,"score_detail":138,"sources":141,"tags":143,"search_phrases":147,"slug":150,"view_count":36,"doi":8,"paper":151,"created_at":158},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":18,"substance":51,"depth":18,"authority":139,"freshness":21,"relevant":22,"comment":140},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。",[142],{"name":136,"url":134},[27,28,144,145,146],"农业遥感","植物病害识别","多模态大模型",[148,149],"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":152,"venue":8,"cited_by_count":36,"oa_url":8,"card":153,"direction":69,"ingested_from":71},[],{"tldr":154,"method":155,"finding":156,"direction":69,"opportunity":157},"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":160,"title":161,"url":162,"summary":163,"summary_zh":8,"content":8,"source_name":164,"source_url":8,"published_at":109,"category":48,"cover_url":8,"hotness":13,"is_selected":14,"score":165,"score_detail":166,"sources":169,"tags":171,"search_phrases":176,"slug":179,"view_count":36,"doi":8,"paper":180,"created_at":187},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":51,"substance":167,"depth":18,"authority":81,"freshness":39,"relevant":22,"comment":168},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。",[170],{"name":164,"url":162},[27,28,172,173,174,175],"水稻","智能育种","玉米","基因-表型预测",[177,178],"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":181,"venue":8,"cited_by_count":36,"oa_url":8,"card":182,"direction":69,"ingested_from":71},[],{"tldr":183,"method":184,"finding":185,"direction":69,"opportunity":186},"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":189,"title":190,"url":191,"summary":192,"summary_zh":8,"content":8,"source_name":193,"source_url":8,"published_at":109,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":194,"score_detail":195,"sources":200,"tags":202,"search_phrases":206,"slug":209,"view_count":36,"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":51,"substance":196,"depth":19,"authority":197,"freshness":198,"relevant":22,"comment":199},20,12,5,"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":193,"url":191},[203,27,28,204,205],"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"]