[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3478":3,"related-3478":113},{"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,"primary_topic":31,"secondary_topics":37,"classification":44,"search_phrases":77,"slug":80,"view_count":81,"doi":82,"paper":83,"created_at":112},3478,"Closed-loop artificial intelligence agents for animal epidemic prediction and decision support in livestock farming: a review","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffvets.2026.1968632","Animal diseases continuously threaten livestock production and public health, yet current surveillance approaches remain largely passive and fragmented. Conventional artificial intelligence models typically function as open-loop predictors, delivering static outputs that fail to accommodate the dynamic operational needs of veterinarians in real-world farm settings. This review explores an emerging paradigm of AI agents for animal disease monitoring, emphasizing how such agents can transition from passive observation to active intervention through a closed-loop perception–decision–feedback architecture. We first classify multi-scale sensing technologies: at the micro-scale, automated molecular diagnostics and biosensors; at the macro-scale, computer-vision-based phenotyping. These technologies collectively provide the data streams required for continuous surveillance. The review then discusses how multi-modal inputs, time-series forecasting, resource-aware decision-making, and reinforcement learning can be integrated into an agent-based workflow. Importantly, most current veterinary research evidence supports only the individual components of this framework, rather than the deployment of fully autonomous, iteratively evolving closed-loop agents in actual field environments. Translating closed-loop AI from a conceptual framework into a reliable veterinary decision-support tool will therefore require further advances in validation, standardization, governance, and human oversight.","动物疫病持续威胁着畜牧生产与公共卫生，然而当前的监测手段在很大程度上仍是被动且碎片化的。传统人工智能模型通常作为开环预测器运行，输出静态结果，无法满足兽医在真实养殖场景中动态的操作需求。本文综述了动物疫病监测中新兴的人工智能代理（AI agents）范式，重点探讨此类代理如何通过“感知—决策—反馈”的闭环架构，从被动观察转向主动干预。我们首先对多尺度传感技术进行分类：在微观尺度上，包括自动化分子诊断与生物传感器；在宏观尺度上，包括基于计算机视觉的表型分析。这些技术共同提供了持续监测所需的数据流。随后，本文讨论了多模态输入、时间序列预测、资源感知决策以及强化学习如何整合到基于代理的工作流程中。重要的是，当前大多数兽医研究证据仅支持该框架的各个独立组件，而非在实际现场环境中部署完全自主、迭代演化的闭环代理。因此，要将闭环人工智能从概念框架转化为可靠的兽医决策支持工具，还需在验证、标准化、治理和人工监督方面取得进一步进展。",null,"Frontiers in Veterinary Science","2026-09-23T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,20,14,8,1,"系统梳理闭环AI智能体在动物疫病监测与决策中的应用框架，指出落地瓶颈，对智慧畜牧有参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","动物疫病防控","畜牧养殖","智能决策",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"C5","animal-health","疫病防控与兽药","\u002Ftopic\u002Flivestock\u002Fanimal-health","C",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,59,65,72],{"code":32,"score":51,"supported":52,"title":53,"abstract":56,"tags":58},23,true,[54,55],"artificial intelligence","decision support",[57,54],"计算机视觉",[27],{"code":43,"score":19,"supported":52,"title":60,"abstract":62,"tags":64},[61],"livestock",[63,61],"畜牧",[],{"code":39,"score":13,"supported":52,"title":66,"abstract":67,"tags":71},[],[68,69,70],"动物疫病","veterinary","animal disease",[28],{"code":73,"score":21,"supported":14,"title":74,"abstract":75,"tags":76},"I1",[],[],[26],[78,79],"动物疫病 AI 预测","闭环智能体 畜牧","动物疫病AI预测-3478",5,"10.3389\u002Ffvets.2026.1968632",{"doi":82,"openalex_id":84,"authors":85,"venue":10,"cited_by_count":102,"oa_url":103,"card":104,"direction":110,"ingested_from":111},"W7214118204",[86,89,91,93,96,99],{"name":87,"orcid":88},"Yuzhi Wang","https:\u002F\u002Forcid.org\u002F0009-0001-8566-7810",{"name":90,"orcid":9},"Yingtong Zhou",{"name":92,"orcid":9},"Liyu Li",{"name":94,"orcid":95},"Huiling Xu","https:\u002F\u002Forcid.org\u002F0000-0001-8195-8648",{"name":97,"orcid":98},"Wangze Ni","https:\u002F\u002Forcid.org\u002F0000-0003-1438-1345",{"name":100,"orcid":101},"Xiaoliang Li","https:\u002F\u002Forcid.org\u002F0000-0002-2410-7545",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fveterinary-science\u002Farticles\u002F10.3389\u002Ffvets.2026.1968632\u002Fpdf",{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"综述闭环AI智能体用于畜禽疫病预测与决策支持，提出感知-决策-反馈架构。","综述多尺度传感、多模态输入、时序预测与强化学习集成。","现有证据仅支持框架组件，闭环智能体尚未在真实农场部署。","农业人工智能与决策模型","可研究闭环智能体在真实农场的验证、标准化与人机协同治理。","智慧农业 \u002F 农业物联网","openalex","2026-09-25T23:30:12.980548Z",{"total":114,"page":21,"page_size":114,"items":115},6,[116,210,281,349,416,477],{"id":117,"title":118,"url":119,"summary":120,"summary_zh":121,"content":9,"source_name":122,"source_url":119,"published_at":123,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":124,"score_detail":125,"sources":129,"tags":131,"primary_topic":136,"secondary_topics":137,"classification":144,"search_phrases":188,"slug":191,"view_count":192,"doi":193,"paper":194,"created_at":209},3617,"Applications and challenges of geospatial technologies in veterinary medicine","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44338-026-00259-y","Geospatial technologies are increasingly recognized as critical assets in veterinary medicine, providing robust frameworks for disease surveillance, risk mapping, and informed decision‑making. The objective of this narrative review is to summarize the role of Geographic Information Systems, Global Positioning System, and Remote Sensing in advancing veterinary medicine by synthesizing current applications, identifying prevailing challenges, and exploring future prospects. Collectively, these tools enable monitoring of disease dynamics, identification of epidemiological hotspots, outbreak prediction, and integration of spatial and epidemiological datasets to guide targeted interventions. For instance, GIS‑based mapping of Rift Valley fever outbreaks in East Africa has enabled rapid identification of epidemiological hotspots and guided vaccination campaigns, while RS‑derived vegetation indices have successfully predicted tick distribution patterns in southern Africa, improving targeted control strategies. Their utility extends beyond livestock health, contributing significantly to wildlife disease monitoring, zoonotic risk assessment, food safety assurance, and broader veterinary decision processes. Despite such successes, adoption remains limited, hindered by technical\u002Finfrastructure barriers, poor data quality, and ethical and policy challenges. In Ethiopia, recent surveys indicate that fewer than 20% of veterinary institutions actively use GIS platforms for routine surveillance, and integration of RS into national veterinary services is still limited to pilot projects. This gap underscores the urgent need for national geospatial data repositories, standardized protocols, and capacity‑building initiatives to ensure equitable access and sustainable utilization. Future opportunities lie in harnessing advances in Artificial Intelligence, Machine Learning, and cloud‑based GIS platforms, alongside global collaboration and training programs, to strengthen veterinary epidemiology and surveillance systems. Addressing these challenges will be essential for the sustainable integration of geospatial technologies into veterinary practice, thereby enhancing disease control, safeguarding public health, and supporting livestock productivity.","地理空间技术在兽医学中日益被视为关键资产，为疾病监测、风险制图和知情决策提供了稳健框架。本叙述性综述旨在总结地理信息系统（Geographic Information Systems, GIS）、全球定位系统（Global Positioning System, GPS）和遥感（Remote Sensing, RS）在推动兽医学发展中的作用，通过综合当前应用、识别主要挑战并探讨未来前景。总体而言，这些工具有助于监测疾病动态、识别流行病学热点、预测疫情，并整合空间与流行病学数据集以指导针对性干预。例如，基于GIS的东非裂谷热疫情制图能够快速识别流行病学热点并指导疫苗接种活动，而遥感衍生的植被指数已成功预测南部非洲蜱虫分布模式，改善了针对性控制策略。其效用不仅限于家畜健康，还对野生动物疾病监测、人兽共患病风险评估、食品安全保障及更广泛的兽医决策过程作出重要贡献。尽管取得了这些成功，其应用仍然有限，受到技术\u002F基础设施障碍、数据质量不佳以及伦理和政策挑战的制约。在埃塞俄比亚，近期调查表明，不到20%的兽医机构在常规监测中积极使用GIS平台，而遥感纳入国家兽医服务仍局限于试点项目。这一差距凸显了建立国家地理空间数据存储库、标准化方案和能力建设举措的迫切需求，以确保公平获取和可持续利用。未来的机遇在于利用人工智能、机器学习和基于云的GIS平台的进步，以及全球合作和培训项目，来加强兽医流行病学和监测系统。应对这些挑战对于将地理空间技术可持续地整合到兽医实践中至关重要，从而增强疾病控制、保障公共卫生并支持家畜生产力。","Discover Animals","2026-09-24T00:00:00Z",75,{"impact":17,"substance":18,"depth":126,"authority":127,"freshness":20,"relevant":21,"comment":128},17,12,"综述系统梳理GIS、GPS与遥感在兽医领域的应用与瓶颈，含东非裂谷热、南部非洲蜱虫分布及埃塞俄比亚使用率不足20%等实证数据，对农业信息化与动物疫病防控有参考价值。",[130],{"name":122,"url":119},[28,132,133,134,135],"遥感监测","人兽共患病","兽医信息化","地理信息系统",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[138,143],{"code":139,"slug":140,"name":141,"path":142,"parent_code":36},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":45,"locked":14,"version":46,"method":47,"evidence":145},{"candidates":146,"agricultural_evidence":52},[147,154,161,168,176,183],{"code":39,"score":148,"supported":52,"title":149,"abstract":150,"tags":153},19,[69],[151,69,152],"人兽共患","zoonotic",[133,28],{"code":139,"score":13,"supported":52,"title":155,"abstract":156,"tags":160},[],[157,158,159],"地理信息","GIS","geographic information",[135],{"code":32,"score":162,"supported":52,"title":163,"abstract":164,"tags":167},9,[],[165,166,54],"机器学习","machine learning",[],{"code":169,"score":170,"supported":52,"title":171,"abstract":172,"tags":175},"I3",7,[],[173,174],"遥感","remote sensing",[132],{"code":177,"score":114,"supported":52,"title":178,"abstract":179,"tags":182},"E4",[],[180,181],"食品安全","food safety",[],{"code":43,"score":184,"supported":52,"title":185,"abstract":186,"tags":187},3,[],[61],[],[189,190],"GIS 兽医 疾病监测","遥感 蜱虫 分布 预测","GIS兽医疾病监测-3617",2,"10.1007\u002Fs44338-026-00259-y",{"doi":193,"openalex_id":195,"authors":196,"venue":122,"cited_by_count":102,"oa_url":202,"card":203,"direction":110,"ingested_from":111},"W7214225608",[197,200],{"name":198,"orcid":199},"Assaye Wollelie Fentie","https:\u002F\u002Forcid.org\u002F0009-0005-9099-9819",{"name":201,"orcid":9},"Daniel Haile Asefa","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44338-026-00259-y.pdf",{"tldr":204,"method":205,"finding":206,"direction":207,"opportunity":208},"综述地理空间技术在兽医领域的应用、挑战与前景，聚焦疾病监测与风险制图。","叙述性综述，整合GIS、GPS、遥感在兽医流行病学中的应用案例与调查数据。","GIS\u002FRS能有效预测疫情和病媒分布，但应用受限于基础设施、数据质量及政策，如埃塞俄比亚使用率不足2","农业遥感与作物表型","可探索AI\u002F机器学习与云GIS结合，构建兽医领域标准化地理空间数据平台与预警系统。","2026-09-27T23:30:26.015992Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":215,"content":9,"source_name":216,"source_url":213,"published_at":217,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":218,"score_detail":219,"sources":222,"tags":224,"primary_topic":227,"secondary_topics":228,"classification":234,"search_phrases":254,"slug":257,"view_count":21,"doi":258,"paper":259,"created_at":280},4975,"Detection of mounting behavior and mounted ewes in group-housed environments using HSM-YOLO algorithm","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102639","The detection of mounting behavior and the mounted ewe is critical for estrus monitoring in sheep. However, existing methods suffer from low detection efficiency and high false detection rates due to the similarity between non-sexual and sexual mounting behaviors and the complexity of group-housed environments. To address these challenges, this study introduced a fine-grained classification of mounting behaviors into sexual and non-sexual categories, and further proposed an improved detection algorithm named Hu Sheep Mounting-YOLO (HSM-YOLO) based on the YOLOv11n architecture for detecting sheep mounting behavior and the corresponding mounted ewes. The HSM-YOLO algorithm employed depthwise separable convolution (DWSConv) to reduce the model complexity. To improve behavioral feature extraction and pose discrimination capabilities, it further integrated the C3k2_RepViTBlock-RepBottleneck (C3k2_BiRep) module, an efficient multi-scale attention (EMA) module, and the Inner-SIoU loss function. To evaluate the performance of the proposed algorithm, comparative experiments were conducted on a multiple scenarios dataset. The experimental results showed that the HSM-YOLO model achieved an F1 score of 88.1%, a mean Average Precision (mAP) of 90.2%, with 2.2M parameters and 5.4G floating-point operations (FLOPs). Compared to the baseline YOLOv11n model, HSM-YOLO improved the F1 score by 5.8% and the mAP by 5.7%, while reducing both model parameters and computational complexity. When deployed and tested on an RTX 4090, the system delivered an average detection speed of 47.9 frames per second (FPS). Moreover, despite considerable variation in detection performance across the four different imaging scenarios, HSM-YOLO consistently demonstrated superior detection accuracy. These results confirm that the HSM-YOLO provides a robust and efficient solution for detecting sheep mounting behaviors and mounted ewes in complex and variable scenarios, paving the way for the development of automated estrus monitoring systems.","检测羊只的爬跨行为及被爬跨母羊对于绵羊发情监测至关重要。然而，由于非性爬跨行为与性爬跨行为之间的相似性以及群养环境的复杂性，现有方法存在检测效率低和误检率高的问题。为解决这些挑战，本研究将爬跨行为细粒度分类为性爬跨和非性爬跨两类，并进一步提出了一种基于YOLOv11n架构的改进检测算法——湖羊爬跨-YOLO（HSM-YOLO），用于检测绵羊爬跨行为及相应的被爬跨母羊。HSM-YOLO算法采用深度可分离卷积（DWSConv）以降低模型复杂度。为提高行为特征提取和姿态判别能力，该算法进一步集成了C3k2_RepViTBlock-RepBottleneck（C3k2_BiRep）模块、高效多尺度注意力（EMA）模块以及Inner-SIoU损失函数。为评估所提算法的性能，在多场景数据集上进行了对比实验。实验结果表明，HSM-YOLO模型的F1分数达到88.1%，平均精度均值（mAP）达到90.2%，参数量为2.2M，浮点运算量为5.4G。与基线YOLOv11n模型相比，HSM-YOLO的F1分数提高了5.8%，mAP提高了5.7%，同时降低了模型参数量和计算复杂度。在RTX 4090上部署测试时，系统平均检测速度达到47.9帧每秒（FPS）。此外，尽管在四种不同成像场景下检测性能存在较大差异，HSM-YOLO始终展现出优越的检测精度。这些结果证实，HSM-YOLO为复杂多变场景下检测绵羊爬跨行为和被爬跨母羊提供了一种鲁棒且高效的解决方案，为自动化发情监测系统的开发奠定了基础。","Smart Agricultural Technology","2026-10-12T00:00:00Z",81,{"impact":17,"substance":220,"depth":17,"authority":19,"freshness":162,"relevant":21,"comment":221},22,"提出HSM-YOLO算法实现羊只爬跨行为与受体母羊检测，为自动化发情监测提供高效方案，方法新颖、指标扎实，具行业参考价值。",[223],{"name":216,"url":213},[26,27,225,29,226],"目标检测","羊只发情监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[229],{"code":230,"slug":231,"name":232,"path":233,"parent_code":43},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants",{"status":45,"locked":14,"version":46,"method":47,"evidence":235},{"candidates":236,"agricultural_evidence":52},[237,243,250],{"code":32,"score":238,"supported":52,"title":239,"abstract":241,"tags":242},13,[240],"YOLO",[240],[27,225],{"code":230,"score":162,"supported":52,"title":244,"abstract":245,"tags":249},[],[246,247,248],"湖羊","绵羊","sheep",[],{"code":73,"score":21,"supported":14,"title":251,"abstract":252,"tags":253},[],[],[26],[255,256],"HSM-YOLO 羊只爬跨行为 检测","绵羊 发情监测 目标检测","HSM-YOLO羊只爬跨行为检测-4975","10.1016\u002Fj.atech.2026.102639",{"doi":258,"openalex_id":260,"authors":261,"venue":216,"cited_by_count":102,"oa_url":213,"card":275,"direction":108,"ingested_from":111},"W7221573347",[262,264,266,268,271,273],{"name":263,"orcid":9},"Yanchao Wang",{"name":265,"orcid":9},"Ming Gao",{"name":267,"orcid":9},"Zhixin Hua",{"name":269,"orcid":270},"Asim Shakeel","https:\u002F\u002Forcid.org\u002F0000-0003-2942-9081",{"name":272,"orcid":9},"Chengyu Ren",{"name":274,"orcid":9},"Kaiying Wang",{"tldr":276,"method":277,"finding":278,"direction":108,"opportunity":279},"提出HSM-YOLO算法，在群养环境下检测羊爬跨行为及被爬跨母羊，用于发情监测。","基于YOLOv11n改进，引入DWSConv、C3k2_BiRep、EMA和In","F1达88.1%、mAP达90.2%，参数量2.2M，较基线提升且更轻量，检测速度47.9 FPS。","可延伸至多物种发情行为细粒度识别与轻量化边缘部署，结合时序信息提升监测实时性。","2026-10-15T23:30:03.393878Z",{"id":282,"title":283,"url":284,"summary":285,"summary_zh":286,"content":9,"source_name":287,"source_url":284,"published_at":288,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":289,"sources":293,"tags":295,"primary_topic":298,"secondary_topics":299,"classification":300,"search_phrases":319,"slug":322,"view_count":114,"doi":323,"paper":324,"created_at":348},3970,"PhySinc-Net: A physics-informed interpretable deep learning architecture for non-contact respiratory rate monitoring in dairy goats","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112472","PhySinc-Net: A physics-informed interpretable deep learning architecture for non-contact respiratory rate monitoring in dairy goats。Computers and Electronics in Agriculture","PhySinc-Net：一种用于奶山羊非接触式呼吸频率监测的物理信息可解释深度学习架构。","Computers and Electronics in Agriculture","2026-10-01T00:00:00Z",{"impact":290,"substance":291,"depth":17,"authority":19,"freshness":162,"relevant":21,"comment":292},16,21,"物理信息驱动的可解释深度学习用于奶山羊非接触呼吸率监测，方法新颖、发表于农业信息领域核心期刊，对智慧畜牧有参考价值。",[294],{"name":287,"url":284},[26,27,29,296,297],"呼吸监测","非接触感知",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":301},{"candidates":302,"agricultural_evidence":52},[303,310,315],{"code":32,"score":304,"supported":52,"title":305,"abstract":307,"tags":309},15,[306],"deep learning",[308,306],"深度学习",[27],{"code":230,"score":184,"supported":52,"title":311,"abstract":312,"tags":314},[],[313],"山羊",[],{"code":73,"score":21,"supported":14,"title":316,"abstract":317,"tags":318},[],[],[26],[320,321],"PhySinc-Net 奶山羊 呼吸率","非接触呼吸监测 奶牛","PhySinc-Net奶山羊呼吸率-3970","10.1016\u002Fj.compag.2026.112472",{"doi":323,"openalex_id":325,"authors":326,"venue":287,"cited_by_count":102,"oa_url":9,"card":343,"direction":110,"ingested_from":111},"W7215068338",[327,329,332,334,336,338,340],{"name":328,"orcid":9},"Wenxuan Lu",{"name":330,"orcid":331},"Rui Mao","https:\u002F\u002Forcid.org\u002F0000-0001-5345-8128",{"name":333,"orcid":9},"Bohan Jiang",{"name":335,"orcid":9},"Jiayi Tian",{"name":337,"orcid":9},"Hanrui Li",{"name":339,"orcid":9},"Xianyao Zhu",{"name":341,"orcid":342},"Mei Li","https:\u002F\u002Forcid.org\u002F0000-0003-2962-8945",{"tldr":344,"method":345,"finding":346,"direction":110,"opportunity":347},"提出物理信息可解释深度学习架构PhySinc-Net，实现奶山羊非接触呼吸率监测。","融合物理先验与深度学习的可解释网络，用于奶山羊呼吸信号分析。","该架构可非接触准确监测奶山羊呼吸率，并具备物理可解释性。","可将物理信息可解释模型迁移至其他畜禽生理监测，解决数据稀缺与黑箱问题。","2026-10-02T23:30:02.169669Z",{"id":350,"title":351,"url":352,"summary":353,"summary_zh":354,"content":9,"source_name":355,"source_url":352,"published_at":356,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":357,"score_detail":358,"sources":360,"tags":362,"primary_topic":365,"secondary_topics":366,"classification":367,"search_phrases":392,"slug":395,"view_count":192,"doi":396,"paper":397,"created_at":415},3065,"A MULTIMODAL FRAMEWORK FOR LIVESTOCK DETECTION AND EPIZOOTIC MONITORING","https:\u002F\u002Fdoi.org\u002F10.67048\u002Fqxju2026ai128iss7m1055","This study proposes an automated computer vision framework to detect and monitor mixed herds of cattle and sheep. By integrating unmanned aerial vehicle (UAV) imagery with ground-level perspectives, a multimodal dataset was curated. Using this data, a lightweight, single-stage object detector (YOLOv8n), tailored for resource-constrained edge devices, was trained and optimised. The integration of computer vision and UAV technology offers agricultural agencies a scalable tool for proactive epizootic surveillance.","本研究提出了一种自动化计算机视觉框架，用于检测和监测牛与羊的混合畜群。通过将无人机（UAV）影像与地面视角相结合，构建了一个多模态数据集。利用该数据，训练并优化了一个轻量级单阶段目标检测器（YOLOv8n），专为资源受限的边缘设备而设计。计算机视觉与无人机技术的融合为农业机构提供了一种可扩展的工具，用于主动进行动物流行病监测。","Agro ilm","2026-09-18T00:00:00Z",71,{"impact":17,"substance":18,"depth":126,"authority":20,"freshness":20,"relevant":21,"comment":359},"多模态无人机视觉框架用于牛羊混群检测与疫病预警，方法具体、面向边缘设备，对智慧畜牧有实用参考价值。",[361],{"name":355,"url":352},[26,27,363,29,364],"无人机遥感","疫病监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":368},{"candidates":369,"agricultural_evidence":52},[370,375,379,384,388],{"code":32,"score":13,"supported":52,"title":371,"abstract":372,"tags":374},[],[225,57,373],"computer vision",[27],{"code":43,"score":20,"supported":52,"title":376,"abstract":377,"tags":378},[61],[],[],{"code":230,"score":114,"supported":52,"title":380,"abstract":381,"tags":383},[],[382,248],"cattle",[],{"code":73,"score":21,"supported":14,"title":385,"abstract":386,"tags":387},[],[],[26],{"code":169,"score":21,"supported":14,"title":389,"abstract":390,"tags":391},[],[],[363],[393,394],"YOLOv8n 牲畜检测","无人机 畜牧 疫病监测","YOLOv8n牲畜检测-3065","10.67048\u002Fqxju2026ai128iss7m1055",{"doi":396,"openalex_id":398,"authors":399,"venue":355,"cited_by_count":102,"oa_url":409,"card":410,"direction":110,"ingested_from":111},"W7213668410",[400,403,406],{"name":401,"orcid":402},"R. N. Khadzhaev","https:\u002F\u002Forcid.org\u002F0009-0001-8124-2399",{"name":404,"orcid":405},"Sa’dulla Avezbayev","https:\u002F\u002Forcid.org\u002F0009-0008-8896-7078",{"name":407,"orcid":408},"Sayfuddin Sharipov","https:\u002F\u002Forcid.org\u002F0000-0002-4232-1369","https:\u002F\u002Fqxjurnal.uz\u002Findex.php\u002Fai\u002Farticle\u002Fdownload\u002F1055\u002F936",{"tldr":411,"method":412,"finding":413,"direction":110,"opportunity":414},"提出多模态计算机视觉框架，用无人机和地面图像检测牛羊并监测疫情。","融合无人机与地面视角构建多模态数据集，训练轻量级YOLOv8n边缘检测器。","轻量级模型可在资源受限设备上实现混合畜群检测，支持主动疫情监测。","可探索多物种、复杂地形下的实时边缘检测与疫情早期预警模型优化。","2026-09-21T23:30:13.271856Z",{"id":417,"title":418,"url":419,"summary":420,"summary_zh":421,"content":9,"source_name":422,"source_url":419,"published_at":423,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":424,"score_detail":425,"sources":427,"tags":429,"primary_topic":433,"secondary_topics":439,"classification":441,"search_phrases":457,"slug":460,"view_count":102,"doi":461,"paper":462,"created_at":476},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":291,"depth":17,"authority":127,"freshness":13,"relevant":21,"comment":426},"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。",[428],{"name":422,"url":419},[26,27,430,431,432],"小农户","植物病害识别","可解释性",{"code":434,"slug":435,"name":436,"path":437,"parent_code":438},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[440],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":45,"locked":14,"version":46,"method":47,"evidence":442},{"candidates":443,"agricultural_evidence":52},[444,449,453],{"code":434,"score":127,"supported":52,"title":445,"abstract":447,"tags":448},[446],"smallholder",[446],[430],{"code":32,"score":13,"supported":52,"title":450,"abstract":451,"tags":452},[373],[],[27,431],{"code":73,"score":21,"supported":14,"title":454,"abstract":455,"tags":456},[],[],[26],[458,459],"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":461,"openalex_id":463,"authors":464,"venue":422,"cited_by_count":102,"oa_url":419,"card":471,"direction":108,"ingested_from":111},"W7223137323",[465,467,469],{"name":466,"orcid":9},"Akshay Ramgoolam",{"name":468,"orcid":9},"Priya Bundhoo Appadoo",{"name":470,"orcid":9},"Jean-Noël LEspérance",{"tldr":472,"method":473,"finding":474,"direction":108,"opportunity":475},"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":478,"title":479,"url":480,"summary":481,"summary_zh":482,"content":9,"source_name":422,"source_url":480,"published_at":423,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":424,"score_detail":483,"sources":485,"tags":487,"primary_topic":491,"secondary_topics":497,"classification":499,"search_phrases":522,"slug":525,"view_count":102,"doi":526,"paper":527,"created_at":539},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":220,"depth":17,"authority":127,"freshness":162,"relevant":21,"comment":484},"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。",[486],{"name":422,"url":480},[26,27,488,489,490],"灌溉决策","安全保证","试验设计",{"code":492,"slug":493,"name":494,"path":495,"parent_code":496},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[498],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":45,"locked":14,"version":46,"method":47,"evidence":500},{"candidates":501,"agricultural_evidence":52},[502,507,511,518],{"code":492,"score":304,"supported":52,"title":503,"abstract":504,"tags":506},[493],[505,493],"灌溉",[488],{"code":32,"score":127,"supported":52,"title":508,"abstract":509,"tags":510},[54],[55],[27],{"code":512,"score":114,"supported":52,"title":513,"abstract":514,"tags":517},"H2",[],[515,516],"土壤","soil",[],{"code":73,"score":21,"supported":14,"title":519,"abstract":520,"tags":521},[],[],[26],[523,524],"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":526,"openalex_id":528,"authors":529,"venue":422,"cited_by_count":102,"oa_url":480,"card":534,"direction":108,"ingested_from":111},"W7223131205",[530,532],{"name":531,"orcid":9},"Nassima Benkhelifa",{"name":533,"orcid":9},"Yacine Aït Ahmed",{"tldr":535,"method":536,"finding":537,"direction":108,"opportunity":538},"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"]