[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3478":3,"related-3478":66},{"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":65},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",[32,33],"动物疫病 AI 预测","闭环智能体 畜牧","动物疫病AI预测-3478",0,"10.3389\u002Ffvets.2026.1968632",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":56,"card":57,"direction":63,"ingested_from":64},"W7214118204",[40,43,45,47,50,53],{"name":41,"orcid":42},"Yuzhi Wang","https:\u002F\u002Forcid.org\u002F0009-0001-8566-7810",{"name":44,"orcid":9},"Yingtong Zhou",{"name":46,"orcid":9},"Liyu Li",{"name":48,"orcid":49},"Huiling Xu","https:\u002F\u002Forcid.org\u002F0000-0001-8195-8648",{"name":51,"orcid":52},"Wangze Ni","https:\u002F\u002Forcid.org\u002F0000-0003-1438-1345",{"name":54,"orcid":55},"Xiaoliang Li","https:\u002F\u002Forcid.org\u002F0000-0002-2410-7545","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fveterinary-science\u002Farticles\u002F10.3389\u002Ffvets.2026.1968632\u002Fpdf",{"tldr":58,"method":59,"finding":60,"direction":61,"opportunity":62},"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":67,"page":21,"page_size":67,"items":68},6,[69,122,163,212,247,285],{"id":70,"title":71,"url":72,"summary":73,"summary_zh":74,"content":9,"source_name":75,"source_url":72,"published_at":76,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":77,"score_detail":78,"sources":81,"tags":83,"search_phrases":86,"slug":89,"view_count":35,"doi":90,"paper":91,"created_at":121},3347,"Integrating Material Flow Cost Accounting and IoT-Based Monitoring for Eco-Efficient Goat Farm Management","https:\u002F\u002Fdoi.org\u002F10.35145\u002F6e5wnv18","Goat farming plays an important role in supporting rural livelihoods, food production, and agricultural sustainability. However, conventional goat farm management often separates environmental monitoring, financial accounting, and livestock management, limiting the ability to identify resource inefficiencies and associated environmental impacts. This study aims to develop and implement GEMBALA (Green Eco-smart Management-Based Automation for Livestock and Accounting), an integrated digital platform that combines Internet of Things (IoT)-based environmental monitoring, Material Flow Cost Accounting (MFCA), emission analysis, artificial intelligence-based livestock management, and analytical reporting. The research employed a research and development approach in collaboration with CV Cahaya Firdaus (Fathur Farm). An IoT sensor prototype was developed, installed, and tested in a real goat farming environment to monitor temperature, humidity, Heat Index (THI), ammonia gas, and dust density. The platform also incorporates MFCA, emission, AI Estrus, AI Health, and analytical reporting modules. The results demonstrate progress toward integrating environmental, economic, and livestock management information within a unified digital platform. However, further validation is required to improve sensor data transmission, synchronization, emission calculations, MFCA data consistency, and AI performance evaluation. The study provides a foundation for eco-economic decision support, sustainable livestock management, and future commercialization of digital livestock technologies.","山羊养殖在支撑农村生计、粮食生产和农业可持续性方面发挥着重要作用。然而，传统的山羊养殖场管理往往将环境监测、财务核算和畜牧管理相互分离，限制了识别资源低效利用及相关环境影响的能力。本研究旨在开发并实施GEMBALA（基于绿色生态智能管理的畜牧与会计自动化平台），这是一个集成了基于物联网（IoT）的环境监测、物料流成本会计（MFCA）、排放分析、基于人工智能的畜牧管理以及分析报告的综合数字平台。研究采用研发方法，与CV Cahaya Firdaus（Fathur Farm）合作开展。研究开发了物联网传感器原型，并在真实山羊养殖环境中进行安装和测试，用于监测温度、湿度、热指数（THI）、氨气和粉尘密度。该平台还整合了MFCA、排放、AI发情检测、AI健康和分析报告模块。结果表明，在将环境、经济和畜牧管理信息整合到统一数字平台方面取得了进展。然而，仍需进一步验证，以改进传感器数据传输、同步、排放计算、MFCA数据一致性以及AI性能评估。本研究为生态经济决策支持、可持续畜牧管理以及数字畜牧技术的未来商业化提供了基础。","Journal of Applied Business and Technology","2026-09-24T00:00:00Z",62,{"impact":20,"substance":17,"depth":79,"authority":13,"freshness":13,"relevant":21,"comment":80},16,"论文提出融合物联网监测与物料流成本核算的山羊养殖数字平台，方法有创新但尚处原型验证阶段，产业影响有限。",[82],{"name":75,"url":72},[84,26,27,85,29],"数字农业","农业物联网",[87,88],"GEMBALA 山羊养殖 物联网","MFCA 畜牧 环境监测","GEMBALA山羊养殖物联网-3347","10.35145\u002F6e5wnv18",{"doi":90,"openalex_id":92,"authors":93,"venue":75,"cited_by_count":35,"oa_url":72,"card":116,"direction":63,"ingested_from":64},"W7214075234",[94,96,98,100,102,104,107,110,112,114],{"name":95,"orcid":9},"Nicholas Renaldo",{"name":97,"orcid":9},"Sulaiman Musa",{"name":99,"orcid":9},"Jaswar Koto",{"name":101,"orcid":9},"Kristy Veronica",{"name":103,"orcid":9},"Umar Faruq",{"name":105,"orcid":106},"Yulvia Nora Marlim","https:\u002F\u002Forcid.org\u002F0009-0007-8624-5023",{"name":108,"orcid":109},"Rangga Rahmadian Yuliendi","https:\u002F\u002Forcid.org\u002F0000-0003-2288-3580",{"name":111,"orcid":9},"Wilda Susanti",{"name":113,"orcid":9},"Achmad Tavip Junaedi",{"name":115,"orcid":9},"Nabila Wahid",{"tldr":117,"method":118,"finding":119,"direction":63,"opportunity":120},"开发集成物联网监测与物料流成本核算的山羊养殖数字平台GEMBALA。","研发方法，在真实羊场部署物联网传感器并集成MFCA、排放分析与AI模块。","平台初步实现环境、经济与养殖信息整合，但传感器传输与数据一致性仍需验证。","可延伸研究物联网数据与MFCA实时耦合的算法优化及AI模块的长期性能验证。","2026-09-24T23:30:09.863218Z",{"id":123,"title":124,"url":125,"summary":126,"summary_zh":127,"content":9,"source_name":128,"source_url":125,"published_at":129,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":130,"score_detail":131,"sources":134,"tags":136,"search_phrases":139,"slug":142,"view_count":35,"doi":143,"paper":144,"created_at":162},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":132,"authority":20,"freshness":20,"relevant":21,"comment":133},17,"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。",[135],{"name":128,"url":125},[26,27,137,29,138],"无人机遥感","疫病监测",[140,141],"YOLOv8n 牲畜检测","无人机 畜牧 疫病监测","YOLOv8n牲畜检测-3065","10.67048\u002Fqxju2026ai128iss7m1055",{"doi":143,"openalex_id":145,"authors":146,"venue":128,"cited_by_count":35,"oa_url":156,"card":157,"direction":63,"ingested_from":64},"W7213668410",[147,150,153],{"name":148,"orcid":149},"R. N. Khadzhaev","https:\u002F\u002Forcid.org\u002F0009-0001-8124-2399",{"name":151,"orcid":152},"Sa’dulla Avezbayev","https:\u002F\u002Forcid.org\u002F0009-0008-8896-7078",{"name":154,"orcid":155},"Sayfuddin Sharipov","https:\u002F\u002Forcid.org\u002F0000-0002-4232-1369","https:\u002F\u002Fqxjurnal.uz\u002Findex.php\u002Fai\u002Farticle\u002Fdownload\u002F1055\u002F936",{"tldr":158,"method":159,"finding":160,"direction":63,"opportunity":161},"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":164,"title":165,"url":166,"summary":167,"summary_zh":168,"content":9,"source_name":169,"source_url":166,"published_at":170,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":130,"score_detail":171,"sources":176,"tags":178,"search_phrases":181,"slug":184,"view_count":35,"doi":185,"paper":186,"created_at":211},2125,"Multi-frequency bioelectrical impedance and machine learning for non-invasive detection of Caseous Lymphadenitis in goats: a one health precision surveillance approach","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102548","Caseous lymphadenitis is a chronic infectious disease of sheep and goats caused by Corynebacterium pseudotuberculosis , with major implications for animal health, farm productivity, carcass value, and occupational exposure risk. Because infected animals may remain clinically inapparent or develop chronic lesions, practical field-based screening tools are needed to improve early detection and herd-level disease management. This study evaluated whether multi-frequency bioelectrical impedance analysis could differentiate healthy\u002Fcontrol goats from CL-positive goats using resistance, reactance, phase angle, and derived spectral features. Measurements were summarized across 50, 100, and 180 kHz, followed by multivariate visualization, Mahalanobis distance analysis, leave-one-subject-out validation, animal-level risk ranking, calibration assessment, and decision curve analysis. CL-positive goats showed distinct frequency-dependent impedance behavior, including altered resistance-reactance profiles and consistently higher phase angle responses across frequencies. Multivariate spectral distance from the healthy centroid was significantly greater in CL-positive animals, suggesting measurable bioelectrical deviation from the healthy impedance profile. A nonlinear model outperformed the linear model in leave-one-subject-out ROC analysis, with an AUC of 0.68 compared with 0.56, indicating moderate discrimination from raw impedance measurements. Animal-level risk ranking further showed enrichment of CL-positive goats among higher predicted-risk animals, while decision curve analysis suggested potential screening value at lower clinical threshold probabilities. These findings support the feasibility of BIA as a rapid, non-invasive adjunct screening tool for CL-associated risk classification in goats. From a One Health perspective, this approach may improve animal welfare, reduce disease persistence in small-ruminant systems, support producer decision-making, and decrease human exposure risk linked to infected animals and contaminated farm environments.","干酪性淋巴结炎是由假结核棒状杆菌（Corynebacterium pseudotuberculosis）引起的一种绵羊和山羊慢性传染病，对动物健康、农场生产力、胴体价值及职业暴露风险均有重大影响。由于感染动物可能保持临床不明显状态或发展为慢性病变，因此需要实用的现场筛查工具，以改善早期检测和群体水平的疾病管理。本研究评估了多频生物电阻抗分析（bioelectrical impedance analysis, BIA）能否利用电阻、电抗、相位角及衍生的频谱特征区分健康\u002F对照山羊与CL阳性山羊。测量结果在50、100和180 kHz频率下进行汇总，随后进行多变量可视化、马氏距离分析、留一受试者法验证、个体水平风险排序、校准评估和决策曲线分析。CL阳性山羊表现出明显的频率依赖性阻抗行为，包括电阻-电抗特征的改变以及各频率下相位角反应持续升高。CL阳性动物与健康质心的多变量频谱距离显著更大，提示其生物电特征偏离健康阻抗谱。在留一受试者法ROC分析中，非线性模型优于线性模型，AUC为0.68，而线性模型为0.56，表明原始阻抗测量具有中等区分能力。个体水平风险排序进一步显示，CL阳性山羊在预测风险较高的动物中富集，而决策曲线分析提示在较低临床阈值概率下具有潜在筛查价值。这些发现支持BIA作为山羊CL相关风险分类的快速、非侵入性辅助筛查工具的可行性。从“同一健康”视角来看，该方法可能改善动物福利，减少小反刍动物系统中疾病的持续存在，支持生产者决策，并降低与感染动物及受污染农场环境相关的人类暴露风险。","Smart Agricultural Technology","2026-09-08T00:00:00Z",{"impact":172,"substance":18,"depth":132,"authority":173,"freshness":174,"relevant":21,"comment":175},12,13,9,"多频生物阻抗结合机器学习实现山羊干酪性淋巴结炎无创筛查，方法新颖、数据扎实，属智慧畜牧与疫病精准监测的可行探索，但AUC仅0.68、样本有限，尚处早期验证阶段。",[177],{"name":169,"url":166},[26,27,28,179,180],"One Health","生物阻抗传感",[182,183],"农业人工智能 动物疫病防控 生物阻抗传感 智慧农业","农业人工智能 动物疫病防控","农业人工智能动物疫病防控生物阻抗传感智慧农业-2125","10.1016\u002Fj.atech.2026.102548",{"doi":185,"openalex_id":187,"authors":188,"venue":169,"cited_by_count":35,"oa_url":205,"card":206,"direction":63,"ingested_from":64},"W7211976751",[189,191,193,195,197,199,201,203],{"name":190,"orcid":9},"A. Siddique",{"name":192,"orcid":9},"A. Kingler",{"name":194,"orcid":9},"S. Neelagiri",{"name":196,"orcid":9},"R. Kota",{"name":198,"orcid":9},"D.I. Shapiro",{"name":200,"orcid":9},"C. Pisani",{"name":202,"orcid":9},"P. Batchu",{"name":204,"orcid":9},"T.H. Terrill","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526007732\u002Fpdf",{"tldr":207,"method":208,"finding":209,"direction":63,"opportunity":210},"用多频生物电阻抗结合机器学习，无创筛查山羊干酪性淋巴结炎。","50\u002F100\u002F180 kHz 生物电阻抗测量，非线性模型与留一受试者验证。","患病羊相位角更高、阻抗谱偏离健康中心，非线性模型 AUC 0.68。","可扩展多频阻抗传感与可穿戴设备，构建羊群疫病无创实时监测预警系统。","2026-09-11T23:30:04.019145Z",{"id":213,"title":214,"url":215,"summary":216,"summary_zh":217,"content":9,"source_name":218,"source_url":215,"published_at":76,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":219,"sources":222,"tags":224,"search_phrases":228,"slug":231,"view_count":35,"doi":232,"paper":233,"created_at":246},3517,"A Resource-Efficient Hybrid CNN-LSTM Network for Image-Based Bean Leaf Disease Classification","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fjimaging12100468","Accurate and resource-efficient automated diagnosis is a cornerstone of modern agricultural expert systems. While Convolutional Neural Networks (CNNs) have established benchmarks in plant pathology, their ability to capture long-range spatial dependencies is often limited by standard pooling layers, and their high memory footprint hinders deployment on portable devices. This paper proposes a lightweight hybrid CNN-LSTM system for bean leaf disease classification. By integrating an LSTM layer to model the spatial–sequential relationships within feature maps, our hybrid architecture achieves a 94.36% accuracy and 94.38% F1 score while maintaining an exceptionally small footprint of 1.86 MB, a 70% reduction in size compared to traditional CNN-based systems. Furthermore, we provide a systematic evaluation of image augmentation strategies, demonstrating that tailored transformations are superior to generic combinations for maintaining the integrity of diagnostic patterns. Results on the ibean dataset confirm that the proposed system achieves state-of-the-art F1 scores of 99.22% with EfficientNet-B7+LSTM, providing a potentially robust and scalable framework for real-time agricultural decision support in resource-constrained environments. The code and augmented datasets used in this study are publicly available on this GitHub repo.","准确且资源高效的自动化诊断是现代农业专家系统的基石。尽管卷积神经网络（CNN）在植物病理学领域已确立了基准，但其捕捉长程空间依赖关系的能力常受限于标准池化层，且高内存占用阻碍了其在便携设备上的部署。本文提出了一种用于豆叶病害分类的轻量级混合CNN-LSTM系统。通过集成LSTM层来建模特征图内的空间-序列关系，我们的混合架构达到了94.36%的准确率和94.38%的F1分数，同时保持了仅1.86 MB的极小占用，相较于传统基于CNN的系统体积减少了70%。此外，我们系统评估了图像增强策略，表明定制化变换在保持诊断模式完整性方面优于通用组合。在ibean数据集上的结果证实，所提出的系统结合EfficientNet-B7+LSTM达到了99.22%的最先进F1分数，为资源受限环境中的实时农业决策支持提供了一个潜在稳健且可扩展的框架。本研究使用的代码和增强数据集已在此GitHub仓库公开。","Journal of Imaging",{"impact":79,"substance":220,"depth":17,"authority":173,"freshness":174,"relevant":21,"comment":221},22,"轻量级CNN-LSTM豆叶病害识别研究，方法新颖、数据可靠且代码开源，对资源受限场景下的农业智能诊断有实用价值。",[223],{"name":218,"url":215},[26,27,225,226,227],"病害识别","轻量化模型","豆类作物",[229,230],"ibean dataset 豆叶病害","农业人工智能 轻量化模型 智慧农业 病害识别","ibeandataset豆叶病害-3517","10.3390\u002Fjimaging12100468",{"doi":232,"openalex_id":234,"authors":235,"venue":218,"cited_by_count":35,"oa_url":215,"card":241,"direction":61,"ingested_from":64},"W7154572440",[236,238],{"name":237,"orcid":9},"Hye Jin Rhee",{"name":239,"orcid":240},"Joseph Damilola Akinyemi","https:\u002F\u002Forcid.org\u002F0000-0003-3121-4231",{"tldr":242,"method":243,"finding":244,"direction":61,"opportunity":245},"提出轻量级CNN-LSTM混合网络，用于豆叶病害分类，兼顾高精度与低资源占用。","CNN提取特征后接LSTM建模空间序列关系，在ibean数据集上评估并系统比较图","模型准确率94.36%、F1 94.38%，仅1.86MB，比传统CNN缩小70%，Efficien","可探索面向移动端\u002F边缘设备的超轻量病害诊断模型，并研究增强策略与模型结构的自适应协同优化。","2026-09-25T23:30:59.276381Z",{"id":248,"title":249,"url":250,"summary":251,"summary_zh":252,"content":9,"source_name":253,"source_url":250,"published_at":76,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":77,"score_detail":254,"sources":257,"tags":259,"search_phrases":263,"slug":266,"view_count":35,"doi":267,"paper":268,"created_at":284},3515,"Soil mapping and fertilizer optimization for precision agriculture using artificial intelligence","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs13198-026-03435-1","Soil mapping and fertilizer optimization for precision agriculture using artificial intelligence。International Journal of Systems Assurance Engineering and Management","基于人工智能的精准农业土壤制图与肥料优化。《国际系统保障工程与管理杂志》","International Journal of Systems Assurance Engineering and Management",{"impact":172,"substance":19,"depth":255,"authority":173,"freshness":20,"relevant":21,"comment":256},15,"论文探讨AI用于土壤制图与施肥优化，属智慧农业细分方向，但摘要信息有限、影响面偏窄，暂不建议进入每日精选。",[258],{"name":253,"url":250},[26,27,260,261,262],"精准施肥","遥感","土壤制图",[264,265],"土壤制图 人工智能 精准施肥","精准农业 肥料优化 AI","土壤制图人工智能精准施肥-3515","10.1007\u002Fs13198-026-03435-1",{"doi":267,"openalex_id":269,"authors":270,"venue":253,"cited_by_count":35,"oa_url":9,"card":279,"direction":61,"ingested_from":64},"W7214144821",[271,274,276],{"name":272,"orcid":273},"Neetu Mittal","https:\u002F\u002Forcid.org\u002F0000-0002-2012-0523",{"name":272,"orcid":275},"https:\u002F\u002Forcid.org\u002F0000-0001-6923-0013",{"name":277,"orcid":278},"Pradeepta Kumar Sarangi","https:\u002F\u002Forcid.org\u002F0000-0003-3827-6208",{"tldr":280,"method":281,"finding":282,"direction":61,"opportunity":283},"利用人工智能进行土壤制图和肥料优化，以支持精准农业。","人工智能方法，用于土壤制图与肥料优化。","AI可提升土壤制图与肥料优化的精准性，促进精准农业。","可探索多源数据融合与实时决策模型，提升肥料推荐的自适应性和可解释性。","2026-09-25T23:30:49.869002Z",{"id":286,"title":287,"url":288,"summary":289,"summary_zh":290,"content":9,"source_name":291,"source_url":288,"published_at":292,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":293,"score_detail":294,"sources":298,"tags":300,"search_phrases":304,"slug":307,"view_count":35,"doi":308,"paper":309,"created_at":324},3514,"Artificial Intelligence for Climate Adaptation Decision Support in Data-Poor Developing Regions","https:\u002F\u002Fdoi.org\u002F10.22541\u002Fessoar.15009304\u002Fv1","Climate adaptation is a sequence of decisions taken under uncertainty, and the regions where climate risk is rising fastest are those with the least information to guide them. Only about 10 per cent of deaths are registered in the WHO African Region; nearly 90 per cent of required surface weather observations are missing across least developed countries and small island states; and only 40 per cent of African countries have multi-hazard early warning systems. This report examines whether artificial intelligence — machine learning, remote sensing and predictive analytics — can close these information gaps and improve adaptation decisions in data-poor developing regions. The report organises the problem as a decision chain with three information gaps — observation, prediction and decision — followed by an action gap that AI cannot close. It finds that AI has advanced fastest on prediction: AI weather models became operational at ECMWF in 2025, AI flood forecasts now cover 100 countries and about 700 million people, satellite nowcasts reach a continent with little radar, and AI monsoon-onset forecasts reached 38 million Indian farmers in 2025. On observation, satellite machine learning explains around 70 per cent of the variation in village wealth but only up to about half of the variation in changes over time. On decision, evidence from Togo, Bangladesh and Kenya shows that AI-assisted targeting, forecast-based triggers and satellite index insurance can deliver assistance faster and better, within clear limits. The report's central argument is the ground-truth paradox: AI stretches scarce observations further, but every AI product must be trained and verified against ground truth, so reliance on AI raises the value of each remaining station, survey and label. The 2025 interruption of FEWS NET and termination of the DHS Program show how fragile that foundation is. Because the value of information is the product of skill, lead time, reach, trust and the means to act, the highest returns usually lie not in more skilful models but in dissemination, institutions and prearranged finance. The report sets out a risk register, a six-principle policy framework, actions by actor and a roadmap to 2030.","气候适应是在不确定性下做出的一系列决策，而气候风险上升最快的地区恰恰是指导信息最匮乏的地区。世卫组织非洲区域仅登记了约10%的死亡病例；最不发达国家和小岛屿国家缺失了近90%所需的地面天气观测数据；仅有40%的非洲国家拥有多灾种早期预警系统。本报告考察人工智能——机器学习、遥感和预测分析——能否弥合这些信息缺口，改善数据匮乏的发展中地区的适应决策。报告将这一问题组织为一条决策链，包含三个信息缺口——观测、预测和决策——以及一个人工智能无法弥合的行动缺口。报告发现，人工智能在预测方面进展最快：人工智能天气模型于2025年在欧洲中期天气预报中心（ECMWF）投入业务运行，人工智能洪水预报现已覆盖100个国家和约7亿人口，卫星临近预报覆盖了一个几乎没有雷达的大陆，人工智能季风爆发预报于2025年惠及3800万印度农民。在观测方面，卫星机器学习可解释村庄财富约70%的变异，但对时间变化的解释力仅约一半。在决策方面，来自多哥、孟加拉国和肯尼亚的证据表明，人工智能辅助的目标定位、基于预报的触发机制和卫星指数保险能够在明确限度内更快、更好地提供援助。报告的核心论点是地面真值悖论：人工智能能够将稀缺的观测数据发挥更大效用，但每个人工智能产品都必须依据地面真值进行训练和验证，因此对人工智能的依赖提升了每一个剩余站点、调查和标注数据的价值。2025年FEWS NET的中断和DHS项目的终止表明这一基础何等脆弱。由于信息的价值是技能、提前期、覆盖面、信任和行动手段的乘积，最高回报通常不在于更精密的模型，而在于传播、制度和预先安排的融资。报告提出了风险登记册、六项原则的政策框架、各行为主体的行动以及到2030年的路线图。","OpenAlex","2026-09-22T00:00:00Z",86,{"impact":220,"substance":295,"depth":296,"authority":173,"freshness":20,"relevant":21,"comment":297},24,19,"系统梳理AI在数据匮乏地区气候适应决策中的观测、预测与决策三类信息缺口，提出“地面真值悖论”，数据与结论扎实，对农业信息化与智慧农业有较强参考价值。",[299],{"name":291,"url":288},[26,27,301,302,303],"气候适应","遥感监测","早期预警",[305,306],"AI 气候适应 决策支持","数据匮乏地区 农业预警","AI气候适应决策支持-3514","10.22541\u002Fessoar.15009304\u002Fv1",{"doi":308,"openalex_id":310,"authors":311,"venue":9,"cited_by_count":35,"oa_url":317,"card":318,"direction":323,"ingested_from":64},"W7214097088",[312,314],{"name":313,"orcid":9},"H Heuristics",{"name":315,"orcid":316},"Hunter Hughes","https:\u002F\u002Forcid.org\u002F0009-0002-6161-9387","https:\u002F\u002Fessopenarchive.org\u002Fdoi\u002Fpdf\u002F10.22541\u002Fessoar.15009304\u002Fv1",{"tldr":319,"method":320,"finding":321,"direction":61,"opportunity":322},"评估AI能否弥补数据匮乏地区气候适应决策的信息缺口，并提出地面真值悖论。","梳理观测、预测、决策三环节，结合AI天气模型、卫星ML与多国案例证据。","AI预测进展最快，但依赖地面真值；最高回报常在传播、制度与预置资金而非模型。","可研究AI辅助农业气候适应中地面真值稀缺下的验证与信任机制，及预置资金触发设计。","数字乡村与农业信息化","2026-09-25T23:30:46.008325Z"]