[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4211":3,"related-4211":117},{"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":38,"search_phrases":86,"slug":89,"view_count":90,"doi":91,"paper":92,"created_at":116},4211,"An integrated scientometric and BERTopic-based analysis on examining the role of artificial intelligence in achieving Sustainable Development Goals (SDGs)","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04841-y","This study investigates the role of Artificial Intelligence (AI) in achieving the United Nations Sustainable Development Goals (SDGs) through a comprehensive scientometric analysis. It explores the evolution of scholarly research, identifies leading contributors, maps thematic trends, examines how AI technologies contribute to advancing sustainability across multiple domains, and identifies latent semantic themes. A total of 3262 unique scholarly records published between 1989 and 2025, after deduplication and screening, were finalized from the Scopus and Web of Science databases. The dataset was analysed using Biblioshiny (R-based Bibliometrix) and VOSviewer to examine publication trends, citation impact, collaborative networks, thematic evolution, and conceptual structures. Indicators such as Relative Growth Rate (RGR), Doubling Time (DT), h-index, g-index, and Lotka’s Law were applied to evaluate research productivity and scholarly influence. In addition, BERTopic-based abstract-level topic modelling was applied to identify latent semantic themes, SDG-linked thematic domains, temporal evolution and potential research gaps. Results reveal a significant growth in AI-SDG research, particularly after 2015, with an accelerated increase post-2020. India, USA, and China emerged as the most productive contributors, while countries like USA, India, United Kingdom and Australia lead in research impact and citation quality. Thematic evolution analysis reveals a transition from foundational themes such as AI, machine learning, climate change, and decision support systems toward more integrated and sustainability-oriented research themes, including sustainable development and SDGs. Thematic linkages further demonstrate the persistent foundational role of AI and machine learning, alongside the growing centrality of climate change and sustainable development, reflecting the increasing convergence of AI research with global sustainability priorities. BERTopic analysis further revealed eleven interpretable abstract-level thematic domains after excluding one heterogeneous outlier category. The dominant themes included digital transformation and green innovation, AI-enabled education, digital health, smart agriculture, renewable energy systems, clean water and sanitation, remote sensing, NLP-based decision support, sustainable construction, tourism, and sustainable chemistry\u002Fpharmaceutical applications. This study maps the AI–SDG research landscape by integrating bibliometric indicators with thematic evolution, conceptual analysis, and abstract-level semantic topic modelling. The findings provide insights into the development and thematic orientation of AI-related research in the context of sustainable development. The use of BERTopic complements conventional bibliometric approaches by examining semantic patterns within publication abstracts alongside keyword and citation-based analyses.","本研究通过一项全面的科学计量分析，探讨了人工智能（Artificial Intelligence, AI）在实现联合国可持续发展目标（Sustainable Development Goals, SDGs）中的作用。研究考察了学术研究的演进历程，识别了主要贡献者，绘制了主题趋势图谱，分析了AI技术如何在多个领域推动可持续发展，并识别了潜在语义主题。经去重和筛选后，最终从Scopus和Web of Science数据库中确定了1989年至2025年间发表的3262条独特学术记录。使用Biblioshiny（基于R的Bibliometrix）和VOSviewer对数据集进行分析，以考察出版趋势、引用影响、合作网络、主题演进和概念结构。采用相对增长率（Relative Growth Rate, RGR）、倍增时间（Doubling Time, DT）、h指数、g指数和洛特卡定律（Lotka's Law）等指标评估研究生产力和学术影响力。此外，应用基于BERTopic的摘要级主题建模，以识别潜在语义主题、与SDG相关的主题领域、时间演变和潜在研究空白。结果显示，AI-SDG研究显著增长，尤其在2015年之后，2020年后增长加速。印度、美国和中国是最多产的贡献者，而美国、印度、英国和澳大利亚等国家在研究影响力和引用质量方面领先。主题演进分析揭示了从AI、机器学习、气候变化和决策支持系统等基础主题向更综合、面向可持续发展的研究主题（包括可持续发展和SDGs）的转变。主题关联进一步表明AI和机器学习的持续基础性作用，同时气候变化和可持续发展的中心性日益增强，反映了AI研究与全球可持续发展优先事项日益融合。BERTopic分析在排除一个异质性离群类别后，进一步揭示了十一个可解释的摘要级主题领域。主导主题包括数字化转型与绿色创新、AI赋能教育、数字健康、智慧农业、可再生能源系统、清洁水和卫生设施、遥感、基于自然语言处理的决策支持、可持续建筑、旅游业以及可持续化学\u002F制药应用。本研究通过整合文献计量",null,"Discover Sustainability","2026-10-04T00:00:00Z","论文",10,false,80,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,9,1,"该研究以3262篇文献的计量与BERTopic主题建模系统梳理AI支撑SDGs的研究格局，其中智慧农业、遥感、数字健康等主题与农业信息化高度相关，方法新颖、数据规模大，值得进入每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"数字乡村","智慧农业","农业人工智能","可持续发展","遥感",{"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",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,53,60,66,74,81],{"code":32,"score":17,"supported":45,"title":46,"abstract":48,"tags":52},true,[47],"artificial intelligence",[49,50,47,51],"机器学习","machine learning","decision support",[28],{"code":54,"score":55,"supported":45,"title":56,"abstract":57,"tags":59},"I1",7,[],[27,58],"smart agriculture",[27],{"code":61,"score":55,"supported":45,"title":62,"abstract":63,"tags":65},"I3",[],[30,64],"remote sensing",[30],{"code":67,"score":68,"supported":45,"title":69,"abstract":70,"tags":73},"H7",6,[],[71,72],"气候变化","climate change",[],{"code":75,"score":68,"supported":45,"title":76,"abstract":77,"tags":80},"I7",[],[78,79],"文献计量","bibliometric",[],{"code":82,"score":21,"supported":14,"title":83,"abstract":84,"tags":85},"I6",[],[],[26],[87,88],"AI SDG 文献计量","BERTopic 可持续农业","AISDG文献计量-4211",2,"10.1007\u002Fs43621-026-04841-y",{"doi":91,"openalex_id":93,"authors":94,"venue":10,"cited_by_count":107,"oa_url":6,"card":108,"direction":114,"ingested_from":115},"W7219683711",[95,98,101,104],{"name":96,"orcid":97},"Reetu Verma","https:\u002F\u002Forcid.org\u002F0000-0002-0567-7219",{"name":99,"orcid":100},"Ashok Kumar","https:\u002F\u002Forcid.org\u002F0009-0005-3279-2895",{"name":102,"orcid":103},"Kavita Pabreja","https:\u002F\u002Forcid.org\u002F0000-0001-9856-0900",{"name":105,"orcid":106},"Saurabh Kumar","https:\u002F\u002Forcid.org\u002F0009-0000-5924-6425",0,{"tldr":109,"method":110,"finding":111,"direction":112,"opportunity":113},"用科学计量与BERTopic分析3262篇文献，揭示AI助力可持续发展目标的研究格局与主题演化。","Scopus\u002FWoS文献，Biblioshiny、VOSviewer计量分析加B","AI-SDG研究2015年后激增，主题从基础AI转向可持续发展，识别出智慧农业等11个主题域。","农业人工智能与决策模型","可聚焦智慧农业主题，探究AI在农业SDG中的具体贡献路径与区域差异，填补细粒度实证空白。","智慧农业 \u002F 农业物联网","openalex","2026-10-05T23:30:09.006483Z",{"total":68,"page":21,"page_size":68,"items":118},[119,187,258,317,370,480],{"id":120,"title":121,"url":122,"summary":123,"summary_zh":124,"content":9,"source_name":125,"source_url":122,"published_at":126,"category":12,"cover_url":9,"hotness":127,"is_selected":14,"score":128,"score_detail":129,"sources":133,"tags":137,"primary_topic":138,"secondary_topics":139,"classification":140,"search_phrases":169,"slug":172,"view_count":173,"doi":174,"paper":175,"created_at":186},3462,"AI For Sustainable Development Opportunities & Innovation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22933761","Abstract Artificial Intelligence is increasingly being explored as a tool for accelerating progress toward sustainable development. AI can analyse large datasets, identify patterns, forecast events, optimise systems and support decision-making across agriculture, energy, water, healthcare, education, cities, industry and environmental management. Recent research shows that AI-for-SDG research is expanding rapidly, while also revealing gaps in social inclusion, governance and assessment of AI’s own environmental footprint. This project examines the major opportunities for AI-enabled sustainable development, including smart agriculture, renewable-energy optimisation, climate and disaster forecasting, intelligent waste management, sustainable cities, healthcare and education. It also discusses innovation pathways such as machine learning, computer vision, remote sensing, generative AI, digital twins and edge AI. The study emphasises that technological capability alone is insufficient: responsible AI requires reliable data, transparency, privacy, human oversight, equitable access, energy-efficient computing and lifecycle environmental assessment.","摘要 人工智能正日益被视为加速可持续发展进程的工具。人工智能可以分析大型数据集、识别模式、预测事件、优化系统，并在农业、能源、水资源、医疗、教育、城市、工业与环境管理等领域支持决策。近期研究表明，人工智能促进可持续发展目标（SDG）的研究正在迅速扩展，同时也揭示了在社会包容、治理以及人工智能自身环境足迹评估方面的不足。本项目考察了人工智能赋能可持续发展的主要机遇，包括智慧农业、可再生能源优化、气候与灾害预测、智能废物管理、可持续城市、医疗和教育。项目还讨论了机器学习、计算机视觉、遥感、生成式人工智能、数字孪生和边缘人工智能等创新路径。研究强调，仅靠技术能力是不够的：负责任的人工智能需要可靠的数据、透明度、隐私保护、人类监督、公平获取、节能计算以及生命周期环境评估。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-30T00:00:00Z",25,68,{"impact":17,"substance":130,"depth":131,"authority":19,"freshness":68,"relevant":21,"comment":132},16,15,"系统梳理AI赋能农业等可持续发展领域的机遇与治理挑战，属综合性研究综述，对智慧农业方向有参考价值但非突破性成果。",[134,135],{"name":125,"url":122},{"name":125,"url":136},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22933762",[26,27,28,29,30],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":141},{"candidates":142,"agricultural_evidence":45},[143,148,154,158,165],{"code":54,"score":13,"supported":45,"title":144,"abstract":145,"tags":147},[],[27,146,58],"数字孪生",[27],{"code":32,"score":13,"supported":45,"title":149,"abstract":150,"tags":153},[],[49,151,50,47,152],"计算机视觉","computer vision",[28],{"code":61,"score":55,"supported":45,"title":155,"abstract":156,"tags":157},[],[30,64],[30],{"code":159,"score":160,"supported":45,"title":161,"abstract":162,"tags":164},"H3",3,[],[163],"水资源",[],{"code":82,"score":21,"supported":14,"title":166,"abstract":167,"tags":168},[],[],[26],[170,171],"AI 可持续发展 智慧农业","农业人工智能 可持续发展 数字乡村 智慧农业","AI可持续发展智慧农业-3462",4,"10.5281\u002Fzenodo.22933761",{"doi":174,"openalex_id":176,"authors":177,"venue":125,"cited_by_count":107,"oa_url":122,"card":180,"direction":114,"ingested_from":115},"W7214172367",[178],{"name":179,"orcid":9},"Saloni Ananda Patil",{"tldr":181,"method":182,"finding":183,"direction":184,"opportunity":185},"综述AI在可持续发展各领域的机会与创新路径，并强调负责任AI的治理要求。","文献综述，覆盖机器学习、计算机视觉、遥感、数字孪生与边缘AI等。","AI-for-SDG研究快速扩张，但社会包容、治理与AI自身环境足迹评估仍存缺口。","农业绿色发展与碳","可量化AI自身能耗与碳足迹，并评估其在农业减排中的净环境效益。","2026-09-25T23:30:08.894307Z",{"id":188,"title":189,"url":190,"summary":191,"summary_zh":192,"content":9,"source_name":125,"source_url":190,"published_at":126,"category":12,"cover_url":9,"hotness":127,"is_selected":14,"score":193,"score_detail":194,"sources":197,"tags":201,"primary_topic":203,"secondary_topics":204,"classification":210,"search_phrases":240,"slug":243,"view_count":173,"doi":244,"paper":245,"created_at":257},2333,"Empowering India's Digital Future through Artificial Intelligence in Geography","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22705830","The convergence of Geographic Information Systems (GIS), high-resolution Earth observation (EO) systems, and Artificial Intelligence (AI) has established a new paradigm: Geospatial Artificial Intelligence (GeoAI). In the context of India's rapid digital transformation, GeoAI serves as a core technology driving sustainable urbanization, precision agriculture, disaster risk reduction, and multi-modal logistics planning. Anchored by strategic national frameworks such as the National Geospatial Policy (NGP), PM Gati Shakti National Master Plan, and the SVAMITVA scheme, this paper examines how AI-integrated spatial analysis accelerates India's digital governance. Through technical methodologies, statistical hypothesis testing, applied case studies, and systemic evaluation, this study demonstrates the pivotal role of GeoAI in building resilient spatial data infrastructure and offers strategic policy recommendations for scalable national adoption.","地理信息系统（GIS）、高分辨率对地观测（EO）系统与人工智能（AI）的融合，已确立了一种新范式：地理空间人工智能（GeoAI）。在印度快速数字化转型的背景下，GeoAI成为推动可持续城市化、精准农业、灾害风险降低和多式联运物流规划的核心技术。本文以国家地理空间政策（NGP）、PM Gati Shakti国家总体规划以及SVAMITVA计划等战略性国家框架为依托，考察了AI集成的空间分析如何加速印度的数字治理。通过技术方法、统计假设检验、应用案例研究和系统性评估，本研究表明GeoAI在构建韧性空间数据基础设施中发挥关键作用，并为全国范围的可扩展应用提供了战略性政策建议。",72,{"impact":17,"substance":195,"depth":17,"authority":19,"freshness":160,"relevant":21,"comment":196},20,"论文系统阐述GeoAI在印度精准农业、数字治理中的应用与政策建议，方法扎实但发布日期在未来，时效性存疑。",[198,199],{"name":125,"url":190},{"name":125,"url":200},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22705829",[26,27,28,30,202],"地理信息",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[205],{"code":206,"slug":207,"name":208,"path":209,"parent_code":36},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"status":39,"locked":14,"version":40,"method":41,"evidence":211},{"candidates":212,"agricultural_evidence":45},[213,218,226,232,236],{"code":32,"score":214,"supported":45,"title":215,"abstract":216,"tags":217},12,[47],[47],[28],{"code":206,"score":20,"supported":45,"title":219,"abstract":220,"tags":225},[],[202,221,222,223,224],"空间分析","GIS","spatial analysis","geographic information",[],{"code":54,"score":55,"supported":45,"title":227,"abstract":228,"tags":231},[],[229,230],"精准农业","precision agriculture",[27],{"code":61,"score":21,"supported":14,"title":233,"abstract":234,"tags":235},[],[],[30],{"code":82,"score":21,"supported":14,"title":237,"abstract":238,"tags":239},[],[],[26],[241,242],"农业人工智能 地理信息 数字乡村 智慧农业","农业人工智能 地理信息","农业人工智能地理信息数字乡村智慧农业-2333","10.5281\u002Fzenodo.22705830",{"doi":244,"openalex_id":246,"authors":247,"venue":125,"cited_by_count":107,"oa_url":190,"card":250,"direction":256,"ingested_from":115},"W7212270621",[248],{"name":249,"orcid":9},"Lalitkumar G. Thakur",{"tldr":251,"method":252,"finding":253,"direction":254,"opportunity":255},"本文探讨地理空间人工智能（GeoAI）如何推动印度数字治理与可持续发展。","结合GIS、高分辨率对地观测与AI，采用案例研究、统计检验和政策评估。","GeoAI在精准农业、灾害减灾等领域关键，需国家政策框架支持规模化应用。","农业遥感与作物表型","可研究GeoAI在印度小农精准农业中的适配性、数据鸿沟与政策落地机制。","数字乡村与农业信息化","2026-09-13T23:30:29.245252Z",{"id":259,"title":260,"url":261,"summary":262,"summary_zh":263,"content":9,"source_name":125,"source_url":261,"published_at":264,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":265,"score_detail":266,"sources":268,"tags":270,"primary_topic":273,"secondary_topics":274,"classification":275,"search_phrases":301,"slug":304,"view_count":107,"doi":305,"paper":306,"created_at":316},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。","2026-10-21T00:00:00Z",74,{"impact":214,"substance":18,"depth":17,"authority":214,"freshness":13,"relevant":21,"comment":267},"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[269],{"name":125,"url":261},[27,28,271,30,272],"粮食安全","气候分析",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":276},{"candidates":277,"agricultural_evidence":45},[278,282,288,293,297],{"code":32,"score":20,"supported":45,"title":279,"abstract":280,"tags":281},[47],[],[28],{"code":283,"score":160,"supported":45,"title":284,"abstract":285,"tags":287},"I5",[],[286],"农业传感",[],{"code":289,"score":21,"supported":14,"title":290,"abstract":291,"tags":292},"A8",[],[],[271],{"code":54,"score":21,"supported":14,"title":294,"abstract":295,"tags":296},[],[],[27],{"code":61,"score":21,"supported":14,"title":298,"abstract":299,"tags":300},[],[],[30],[302,303],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":305,"openalex_id":307,"authors":308,"venue":125,"cited_by_count":107,"oa_url":261,"card":311,"direction":112,"ingested_from":115},"W7223111766",[309],{"name":310,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":312,"method":313,"finding":314,"direction":254,"opportunity":315},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","2026-10-22T11:21:02.682497Z",{"id":318,"title":319,"url":320,"summary":321,"summary_zh":322,"content":9,"source_name":125,"source_url":320,"published_at":264,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":323,"score_detail":324,"sources":328,"tags":330,"primary_topic":333,"secondary_topics":334,"classification":339,"search_phrases":354,"slug":357,"view_count":107,"doi":358,"paper":359,"created_at":369},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。",67,{"impact":325,"substance":195,"depth":326,"authority":214,"freshness":13,"relevant":21,"comment":327},8,17,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[329],{"name":125,"url":320},[27,28,331,30,332],"产量预测","可解释性",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[335],{"code":61,"slug":336,"name":337,"path":338,"parent_code":36},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":39,"locked":14,"version":40,"method":41,"evidence":340},{"candidates":341,"agricultural_evidence":45},[342,346,350],{"code":32,"score":214,"supported":45,"title":343,"abstract":344,"tags":345},[152],[151],[28],{"code":61,"score":325,"supported":45,"title":347,"abstract":348,"tags":349},[],[30,64],[331,30],{"code":54,"score":21,"supported":14,"title":351,"abstract":352,"tags":353},[],[],[27],[355,356],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":358,"openalex_id":360,"authors":361,"venue":125,"cited_by_count":107,"oa_url":320,"card":364,"direction":254,"ingested_from":115},"W7223114002",[362],{"name":363,"orcid":9},"Kadiatou Barry",{"tldr":365,"method":366,"finding":367,"direction":254,"opportunity":368},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":371,"title":372,"url":373,"summary":374,"summary_zh":375,"content":9,"source_name":376,"source_url":373,"published_at":264,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":377,"score_detail":378,"sources":380,"tags":382,"primary_topic":385,"secondary_topics":390,"classification":396,"search_phrases":451,"slug":454,"view_count":107,"doi":455,"paper":456,"created_at":479},5564,"Dynamic thermal imaging for crop water stress detection across phenological stages: Enhancing irrigation scheduling precision","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.17728","Thermal remote sensing and derived indices such as the crop water stress index (CWSI) can assess crop water status and support precision irrigation. However, most operational and artificial intelligence (AI)-based approaches rely on fixed, season-long thresholds to interpret canopy–air temperature differences and often overlook the influence of crop phenology. This review synthesises evidence from grapevine, wheat, maize, potato and several other crops on how developmental stage affects the non-water-stressed baseline (NWSB), CWSI thresholds and irrigation-scheduling algorithms. It covers CWSI theory and estimation practices; crop-specific, phenology-dependent behaviour of baselines and thresholds; a comparison of threshold-based, machine learning, Internet of Things (IoT), digital twin and Food and Agriculture Organization (FAO)-56 approaches with respect to crop phenology; and a conceptual framework for phenology-aware scheduling. Across the reviewed crops, baseline behaviour generally varied systematically across the growing season, the relationship between CWSI and crop water status generally strengthened after canopy closure and CWSI measured during reproductive stages was generally most closely related to yield. A quantitative audit of 56 AI-, thermal-imaging-, or CWSI-based studies found that 78.6 % either did not explicitly incorporate crop phenology or relied on day of year as a temporal proxy, whereas only 5.4 % explicitly encoded phenological stage. The proposed framework considers phenology explicitly in baseline estimation, threshold setting and data fusion or machine learning for irrigation scheduling; the framework will require multi-year, multi-site field validation before operational use. Future research should prioritise standardised phenology definitions and long-term, multi-location studies to establish and validate stage-specific parameters.","热红外遥感及其衍生的作物水分胁迫指数（crop water stress index, CWSI）等指标可评估作物水分状况并支持精准灌溉。然而，大多数业务化方法和基于人工智能（artificial intelligence, AI）的方法依赖固定的全生育期阈值来解释冠层—空气温差，且往往忽视作物物候的影响。本文综述了葡萄、小麦、玉米、马铃薯及其他若干作物在发育阶段如何影响非水分胁迫基线（non-water-stressed baseline, NWSB）、CWSI阈值和灌溉调度算法的相关证据。综述内容涵盖CWSI理论与估算实践；基线和阈值的作物特异性、物候依赖性行为；基于阈值、机器学习、物联网（Internet of Things, IoT）、数字孪生及联合国粮农组织（Food and Agriculture Organization, FAO）-56等方法在作物物候方面的比较；以及物候感知调度的概念框架。在所综述的作物中，基线行为在整个生长季通常呈系统性变化，CWSI与作物水分状况之间的关系在冠层封垄后总体增强，且在生殖阶段测得的CWSI与产量的关系总体最为密切。对56项基于AI、热成像或CWSI的研究进行的定量审查发现，78.6%的研究要么未明确纳入作物物候，要么依赖年积日作为时间代理变量，而仅5.4%的研究明确编码了物候阶段。所提出的框架在基线估算、阈值设定以及用于灌溉调度的数据融合或机器学习中明确考虑物候；该框架在投入业务应用前尚需多年、多站点的田间验证。未来研究应优先建立标准化的物候定义，并开展长期、多地点研究以建立和验证阶段特异性参数。","Plant Science Today",79,{"impact":17,"substance":18,"depth":17,"authority":214,"freshness":20,"relevant":21,"comment":379},"系统综述热成像与CWSI在物候期感知灌溉中的应用，含56项研究量化审计，方法学价值突出，但属综述类论文，影响偏学术层面。",[381],{"name":376,"url":373},[27,28,30,383,384],"作物水分胁迫","精准灌溉",{"code":159,"slug":386,"name":387,"path":388,"parent_code":389},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[391,392],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":283,"slug":393,"name":394,"path":395,"parent_code":36},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":39,"locked":14,"version":40,"method":41,"evidence":397},{"candidates":398,"agricultural_evidence":45},[399,404,408,415,420,424,431,438,445],{"code":159,"score":131,"supported":45,"title":400,"abstract":401,"tags":403},[386],[402,386],"灌溉",[384],{"code":32,"score":13,"supported":45,"title":405,"abstract":406,"tags":407},[],[49,50,47],[28],{"code":283,"score":20,"supported":45,"title":409,"abstract":410,"tags":414},[],[411,412,413],"物联网","internet of things","IoT",[],{"code":54,"score":55,"supported":45,"title":416,"abstract":417,"tags":419},[],[146,418],"digital twin",[27],{"code":61,"score":55,"supported":45,"title":421,"abstract":422,"tags":423},[],[30,64],[30],{"code":425,"score":68,"supported":45,"title":426,"abstract":427,"tags":430},"A2",[],[428,429],"小麦","wheat",[],{"code":432,"score":68,"supported":45,"title":433,"abstract":434,"tags":437},"A3",[],[435,436],"玉米","maize",[],{"code":439,"score":68,"supported":45,"title":440,"abstract":441,"tags":444},"A5",[],[442,443],"马铃薯","potato",[],{"code":446,"score":160,"supported":45,"title":447,"abstract":448,"tags":450},"B2",[],[449],"葡萄",[],[452,453],"热成像 作物水分胁迫","CWSI 灌溉调度","热成像作物水分胁迫-5564","10.14719\u002Fpst.17728",{"doi":455,"openalex_id":457,"authors":458,"venue":376,"cited_by_count":107,"oa_url":373,"card":474,"direction":114,"ingested_from":115},"W7223088921",[459,462,465,468,471],{"name":460,"orcid":461},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":463,"orcid":464},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":466,"orcid":467},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":469,"orcid":470},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":472,"orcid":473},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":475,"method":476,"finding":477,"direction":254,"opportunity":478},"综述物候期对热成像CWSI阈值的影响，提出物候感知灌溉调度框架。","综述葡萄、小麦、玉米等作物的热遥感CWSI研究，并审计56项AI\u002F热成像研究。","78.6%研究未显式纳入物候，仅5.4%编码物候期；CWSI与产量在生殖期关联最强。","可开展多站点多年物候期特异性CWSI阈值标定与标准化物候定义研究。","2026-10-22T11:20:24.526683Z",{"id":481,"title":482,"url":483,"summary":484,"summary_zh":485,"content":9,"source_name":486,"source_url":483,"published_at":487,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":488,"score_detail":489,"sources":491,"tags":493,"primary_topic":495,"secondary_topics":496,"classification":497,"search_phrases":515,"slug":518,"view_count":107,"doi":519,"paper":520,"created_at":543},5393,"IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr251214006i","CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.","卷积神经网络（CNNs）已发展成为现代计算机视觉系统的核心骨干，在多个应用领域中展现出卓越的目标检测与分类性能。然而，人工设计合适的CNN架构并相应地选择最优超参数集仍然是繁琐且耗时的过程。本综述旨在全面回顾遗传算法、粒子群优化及其他群体智能方法等元启发式优化算法如何嵌入基于CNN的流程中以获得更优的检测与分类结果。我们汇集了自动化架构搜索、超参数调优、模型压缩和集成学习方面的最新进展。通过系统梳理在医学影像、农业、车辆识别和遥感领域的应用，我们揭示了混合优化方法如何以计算效率持续实现更优的精度。优化后的CNN模型在多数情况下远超其基线版本，尤其在健康诊断领域，若干精细调优的架构达到了超过99%的准确率。本综述为将在基于深度学习的计算机视觉系统中应用元启发式优化的从业者和研究者，提供了关于方法学进展、实施实践和新兴研究方向的结构化且更新的概述。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",61,{"impact":325,"substance":17,"depth":131,"authority":214,"freshness":325,"relevant":21,"comment":490},"综述系统梳理元启发式优化在CNN视觉任务中的嵌入方法，含农业应用，但属通用方法综述，非农业专属突破。",[492],{"name":486,"url":483},[27,28,494,30],"目标检测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":498},{"candidates":499,"agricultural_evidence":45},[500,507,511],{"code":32,"score":501,"supported":45,"title":502,"abstract":503,"tags":506},11,[],[494,504,151,505,152],"深度学习","deep learning",[28,494],{"code":61,"score":55,"supported":45,"title":508,"abstract":509,"tags":510},[],[30,64],[30],{"code":54,"score":21,"supported":14,"title":512,"abstract":513,"tags":514},[],[],[27],[516,517],"元启发式优化 卷积神经网络","CNN 目标检测","元启发式优化卷积神经网络-5393","10.22190\u002Ffuacr251214006i",{"doi":519,"openalex_id":521,"authors":522,"venue":486,"cited_by_count":107,"oa_url":483,"card":538,"direction":254,"ingested_from":115},"W7222920697",[523,526,529,532,535],{"name":524,"orcid":525},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":527,"orcid":528},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":530,"orcid":531},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":533,"orcid":534},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":536,"orcid":537},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":539,"method":540,"finding":541,"direction":112,"opportunity":542},"综述元启发式算法嵌入CNN流程以优化目标检测与分类的研究进展。","系统综述遗传算法、粒子群等群智能方法用于CNN架构搜索与超参调优。","混合优化方法在医学影像、农业等领域兼顾精度与效率，部分模型准确率超99%。","农业场景下元启发式优化CNN的架构搜索与轻量化部署仍缺乏系统基准与田间验证。","2026-10-20T23:30:19.233167Z"]