[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2863":3,"related-2863":60},{"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,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":59},2863,"Smart energy transition in agricultural industrial parks for sustainable food systems: policy coordination pathways and dynamic evolution simulation","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1885233","Introduction Based on the profound evolution of global “dual carbon” goals and sustainable food systems, agri-food parks are key nodes with high energy consumption and high carbon emissions in the food supply chain. Their smart energy systems provide a feasible path for low-carbon transition, but face governance obstacles such as policy fragmentation, departmental silos, and instrument conflicts, which constrain sustainable food production. Methods This study constructs a system dynamics model encompassing four subsystems: energy technology, digital infrastructure, policy market, and environmental goals. It identifies six core feedback loops and, through simulation for the period 2025 to 2040, reveals the mechanisms of policy coordination, and use sensitivity analysis to ensure robustness. Meanwhile, the study adopts the micro-perspective of the agri-food park, incorporating the entire process of policy coordination into a systematic endogenous feedback structure. Results The results show that the smart energy system of agri-food park possesses endogenous growth potential. The cumulative installed capacity of smart energy increased from 50 MW to 885.269 MW, representing a nearly 16.7 fold growth over the 15 year period, with an average annual compound growth rate of approximately 20.6%.Compared with the no policy intervention scenario, the multi policy coordination scenario boosted installed capacity by about 229.8%, indicating that strong policy support is essential to overcome initial development thresholds; strengthening goal coordination, tool optimization, and departmental integration can reduce the technology lock in effect from 0.683 to 0.300, a decline of 56.1%, and lower carbon emission intensity from 2.498 tons\u002F10,000 yuan to 1.737 tons\u002F10,000 yuan, thereby effectively breaking through existing technological lock-in and institutional barriers; and an increase in the carbon emission factor of smart energy alters the trajectory of new investments in carbon-based energy, significantly curbing the expansion of high-carbon energy. Discussion The study confirms that policy coordination is a core lever for activating the system’s endogenous dynamics and driving the green transformation and upgrading of agri-food parks, thereby providing systematic scientific decision-making support for building a more resilient sustainable food supply chain and advancing the “dual carbon” goals.","引言 基于全球“双碳”目标与可持续食物系统的深刻变革，农业食品园区是食物供应链中高能耗、高碳排放的关键节点，其智慧能源系统为低碳转型提供了可行路径，但面临政策碎片化、部门壁垒与工具冲突等治理障碍，制约了可持续食物生产。方法 本研究构建涵盖能源技术、数字基础设施、政策市场与环境目标四个子系统的系统动力学模型，识别六条核心反馈回路，并通过2025—2040年的仿真模拟揭示政策协同的作用机制，同时采用敏感性分析保证稳健性。同时，本研究采用农业食品园区的微观视角，将政策协同的全过程纳入系统内生反馈结构。结果 结果表明，农业食品园区智慧能源系统具有内生增长潜力。智慧能源累计装机容量从50 MW增至885.269 MW，15年间增长近16.7倍，年均复合增长率约为20.6%。与无政策干预情景相比，多政策协同情景使装机容量提升约229.8%，表明强有力的政策支持对于跨越初期发展门槛至关重要；加强目标协同、工具优化与部门整合可将技术锁定效应从0.683降至0.300，下降56.1%，并将碳排放强度从2.498吨\u002F万元降至1.737吨\u002F万元，从而有效突破现有技术锁定与制度壁垒；智慧能源碳排放因子上升会改变碳基能源新增投资轨迹，显著抑制高碳能源扩张。讨论 研究证实，政策协同是激活系统内生动力、推动农业食品园区绿色转型升级的核心杠杆，从而为构建更具韧性的可持续食物供应链和推进“双碳”目标提供系统性科学决策支持。",null,"Frontiers in Sustainable Food Systems","2026-09-17T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,8,1,"系统动力学模拟农业园区智慧能源政策协同，数据详实、结论有决策参考价值，但属学术论文、时效性一般，可入精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","低碳转型","系统动力学","政策协同","农业园区",[32,33],"农业产业园 智慧能源 低碳转型","农食园区 政策协同 双碳","农业产业园智慧能源低碳转型-2863",0,"10.3389\u002Ffsufs.2026.1885233",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":6,"card":52,"direction":56,"ingested_from":58},"W7213496319",[40,43,46,48,50],{"name":41,"orcid":42},"Zhong Li","https:\u002F\u002Forcid.org\u002F0000-0001-9869-006X",{"name":44,"orcid":45},"Yixuan Chen","https:\u002F\u002Forcid.org\u002F0000-0002-4879-7165",{"name":47,"orcid":9},"Simiao Tong",{"name":49,"orcid":9},"Huabin Wu",{"name":51,"orcid":9},"Caijuan Hu",{"tldr":53,"method":54,"finding":55,"direction":56,"opportunity":57},"构建系统动力学模型，模拟农业产业园智慧能源转型的政策协同路径与动态演化。","系统动力学建模，含四个子系统与六个反馈回路，2025-2040年仿真及敏感性分析","多政策协同使智慧能源装机增229.8%，技术锁定降56.1%，碳排放强度降30.5%。","农业绿色发展与碳","可将园区级政策协同模型扩展到区域农业供应链，量化部门壁垒对减碳的阻滞效应。","openalex","2026-09-18T23:30:07.001188Z",{"total":61,"page":21,"page_size":61,"items":62},6,[63,95,126,154,181,210],{"id":64,"title":65,"url":66,"summary":67,"summary_zh":9,"content":9,"source_name":68,"source_url":9,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":69,"score_detail":70,"sources":74,"tags":76,"search_phrases":81,"slug":84,"view_count":35,"doi":9,"paper":85,"created_at":94},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",78,{"impact":71,"substance":18,"depth":17,"authority":19,"freshness":72,"relevant":21,"comment":73},16,9,"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。",[75],{"name":68,"url":66},[26,77,78,79,80],"农业人工智能","设施农业","番茄","病害识别",[82,83],"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":9,"openalex_id":9,"authors":86,"venue":9,"cited_by_count":35,"oa_url":9,"card":87,"direction":91,"ingested_from":93},[],{"tldr":88,"method":89,"finding":90,"direction":91,"opportunity":92},"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":96,"title":97,"url":98,"summary":99,"summary_zh":9,"content":9,"source_name":100,"source_url":9,"published_at":101,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":102,"score_detail":103,"sources":106,"tags":108,"search_phrases":112,"slug":115,"view_count":35,"doi":116,"paper":117,"created_at":125},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","2026-09-18T00:00:00Z",82,{"impact":17,"substance":18,"depth":17,"authority":104,"freshness":13,"relevant":21,"comment":105},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。",[107],{"name":100,"url":98},[26,77,109,110,111],"作物病害识别","小麦白粉病","叶绿素荧光成像",[113,114],"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":116,"openalex_id":9,"authors":118,"venue":9,"cited_by_count":35,"oa_url":9,"card":119,"direction":123,"ingested_from":93},[],{"tldr":120,"method":121,"finding":122,"direction":123,"opportunity":124},"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":127,"title":128,"url":129,"summary":130,"summary_zh":9,"content":9,"source_name":131,"source_url":9,"published_at":132,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":69,"score_detail":133,"sources":136,"tags":138,"search_phrases":142,"slug":145,"view_count":35,"doi":9,"paper":146,"created_at":153},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":17,"substance":18,"depth":134,"authority":19,"freshness":61,"relevant":21,"comment":135},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。",[137],{"name":131,"url":129},[26,77,139,140,141],"数字孪生","可持续农业","花生产量预测",[143,144],"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":9,"openalex_id":9,"authors":147,"venue":9,"cited_by_count":35,"oa_url":9,"card":148,"direction":91,"ingested_from":93},[],{"tldr":149,"method":150,"finding":151,"direction":91,"opportunity":152},"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":155,"title":156,"url":157,"summary":158,"summary_zh":9,"content":9,"source_name":159,"source_url":9,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":160,"score_detail":161,"sources":163,"tags":165,"search_phrases":169,"slug":172,"view_count":35,"doi":9,"paper":173,"created_at":180},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":17,"substance":18,"depth":17,"authority":20,"freshness":72,"relevant":21,"comment":162},"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。",[164],{"name":159,"url":157},[26,77,166,167,168],"农业遥感","植物病害识别","多模态大模型",[170,171],"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":9,"openalex_id":9,"authors":174,"venue":9,"cited_by_count":35,"oa_url":9,"card":175,"direction":91,"ingested_from":93},[],{"tldr":176,"method":177,"finding":178,"direction":91,"opportunity":179},"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":182,"title":183,"url":184,"summary":185,"summary_zh":9,"content":9,"source_name":186,"source_url":9,"published_at":132,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":187,"score_detail":188,"sources":191,"tags":193,"search_phrases":198,"slug":201,"view_count":35,"doi":9,"paper":202,"created_at":209},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":18,"substance":189,"depth":17,"authority":104,"freshness":61,"relevant":21,"comment":190},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。",[192],{"name":186,"url":184},[26,77,194,195,196,197],"水稻","智能育种","玉米","基因-表型预测",[199,200],"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":9,"openalex_id":9,"authors":203,"venue":9,"cited_by_count":35,"oa_url":9,"card":204,"direction":91,"ingested_from":93},[],{"tldr":205,"method":206,"finding":207,"direction":91,"opportunity":208},"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":211,"title":212,"url":213,"summary":214,"summary_zh":9,"content":9,"source_name":215,"source_url":9,"published_at":132,"category":216,"cover_url":9,"hotness":13,"is_selected":14,"score":217,"score_detail":218,"sources":224,"tags":226,"search_phrases":230,"slug":233,"view_count":35,"doi":9,"paper":9,"created_at":234},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","报道",74,{"impact":18,"substance":219,"depth":220,"authority":221,"freshness":222,"relevant":21,"comment":223},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。",[225],{"name":215,"url":213},[227,26,77,228,229],"数字乡村","农业大模型","农业社会化服务",[231,232],"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"]