[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4013":3,"related-4013":61},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":24,"classification":25,"search_phrases":41,"slug":44,"view_count":45,"doi":46,"paper":47,"created_at":60},4013,"GRID PATROL COPILOT: An AI-Powered Patrol Intelligence Framework for Transmission Line Fault Localization and Field Response Optimization","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.84991","Rapid fault identification and effective field patrolling are essential for minimizing outage duration and restoring transmission system availability following line faults. In conventional practice, patrol planning requires engineers to manually collect and correlate information from multiple sources, including relay fault records, transmission line profiles, tower databases, terrain information, and historical maintenance records. This process is often time-consuming and heavily dependent on individual experience, resulting in delays in patrol deployment and fault restoration. This paper presents GRID PATROL COPILOT, an Artificial Intelligence (AI)-powered patrol intelligence framework developed to transform fault-related information into actionable field recommendations through a conversational interface. The proposed framework integrates fault location analysis, transmission line databases, tower intelligence, terrain information, and patrol planning logic using Microsoft Copilot Studio, Power Automate, SharePoint, and Generative AI technologies. Upon receiving fault details, the system automatically identifies the probable fault span, determines vulnerable towers, evaluates access conditions, and generates optimized patrol deployment recommendations. A practical implementation on extra-high-voltage transmission lines is presented to demonstrate the framework's capability in supporting fault localization and patrol decision-making. The results indicate significant reduction in manual analysis effort, improved standardization of patrol planning, faster field deployment, and enhanced restoration readiness. The proposed framework demonstrates a practical and scalable approach for integrating AIdriven decision support into transmission line operation and maintenance activities","快速故障识别和有效的现场巡视对于在线路故障后最大限度缩短停电时间和恢复输电系统可用性至关重要。在传统实践中，巡视规划需要工程师手动收集并关联来自多个来源的信息，包括继电保护故障记录、输电线路参数、杆塔数据库、地形信息以及历史检修记录。这一过程往往耗时且高度依赖个人经验，导致巡视部署和故障恢复延迟。本文提出了GRID PATROL COPILOT，这是一种由人工智能（AI）驱动的巡视智能框架，旨在通过对话式界面将故障相关信息转化为可执行的现场建议。所提出的框架利用Microsoft Copilot Studio、Power Automate、SharePoint和生成式AI技术，集成了故障定位分析、输电线路数据库、杆塔智能信息、地形信息以及巡视规划逻辑。在接收到故障详情后，系统会自动识别可能的故障档距，确定易受损杆塔，评估可达条件，并生成优化的巡视部署建议。本文展示了在特高压输电线路上的实际应用，以证明该框架在支持故障定位和巡视决策方面的能力。结果表明，该框架显著减少了人工分析工作量，提高了巡视规划的标准化程度，加快了现场部署速度，并增强了恢复准备能力。所提出的框架展示了一种实用且可扩展的方法，可将AI驱动的决策支持集成到输电线路运维活动中。",null,"International Journal for Research in Applied Science and Engineering Technology","2026-09-30T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该论文聚焦输电线路AI巡检与故障定位，属电力系统运维领域，与三农、农业信息化、智慧农业无关，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23],"人工智能","电力巡检","输电线路",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":40},[31],{"code":32,"score":33,"supported":34,"title":35,"abstract":36,"tags":39},"I2",7,true,[],[37,38],"artificial intelligence","decision support",[21],"农业相关性需要复核",[42,43],"输电线路 故障定位 AI","人工智能 电力巡检 输电线路","输电线路故障定位AI-4013",1,"10.22214\u002Fijraset.2026.84991",{"doi":46,"openalex_id":48,"authors":49,"venue":10,"cited_by_count":15,"oa_url":6,"card":52,"direction":58,"ingested_from":59},"W7215125947",[50],{"name":51,"orcid":9},"Chaganti Chandra Mouli",{"tldr":53,"method":54,"finding":55,"direction":56,"opportunity":57},"提出AI巡检智能框架，将故障信息转为可执行的现场巡检建议。","用Copilot Studio、Power Automate、SharePoin","在特高压线路上实现故障定位与巡检决策，显著减少人工分析、加快现场部署。","农业人工智能与决策模型","可将该对话式AI决策框架迁移至农村配电网或农业设施供电故障巡检场景。","智慧农业 \u002F 农业物联网","openalex","2026-10-02T23:30:13.643585Z",{"total":62,"page":45,"page_size":62,"items":63},6,[64,126,171,213,298,359],{"id":65,"title":66,"url":67,"summary":68,"summary_zh":69,"content":9,"source_name":70,"source_url":67,"published_at":71,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":72,"sources":74,"tags":76,"primary_topic":9,"secondary_topics":79,"classification":80,"search_phrases":104,"slug":107,"view_count":15,"doi":108,"paper":109,"created_at":125},5191,"Artificial intelligence in immovable cultural heritage research: a bibliometric and knowledge mapping review","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs43238-026-00324-1","Abstract In recent years, the application of artificial intelligence (AI) in immovable cultural heritage research has expanded rapidly, supporting new approaches to heritage documentation, condition assessment, conservation, management, and public communication. In this study, immovable cultural heritage primarily refers to historic buildings, archaeological sites, monuments, cultural landscapes, and other heritage places with fixed spatial locations. Movable cultural objects, museum collections, and intangible cultural heritage are not systematically examined unless the relevant studies directly address the documentation, monitoring, restoration, conservation, or management of immovable heritage. Despite the growing volume of research, existing studies have largely focused on individual technical applications, while comprehensive bibliometric analyses and knowledge-structure mapping from a global perspective remain limited. To address this gap, this study retrieved 382 English-language publications from the Web of Science Core Collection covering the period from 1 January 2015 to 1 October 2025. Using bibliometric methods and analytical tools including VOSviewer, CiteSpace, and ArcGIS, the study examines publication trends, geographical distribution, disciplinary categories, major authors, institutional affiliations, collaboration networks, thematic evolution, and emerging research topics. The results show that publication output increased substantially after 2020. China, Italy, and Spain were among the most productive countries and occupied important positions in the international collaboration network. Major research themes included digital heritage, structural health monitoring, virtual reconstruction, deep learning, remote sensing, and sustainability-related applications. These findings indicate that AI-related research on immovable cultural heritage is strongly represented in engineering, conservation science, computer science, remote sensing, and related technical fields. However, this pattern should not be interpreted as evidence of a general disciplinary shift across cultural heritage studies as a whole. Rather, it reflects the technological orientation of the literature captured by the present search strategy, which was limited to English-language publications indexed in the Web of Science Core Collection. This study maps the development and knowledge structure of AI applications in immovable cultural heritage research and provides quantitative evidence for identifying major research areas, collaboration patterns, methodological tendencies, and future research needs.","摘要 近年来，人工智能（AI）在不可移动文物保护研究中的应用迅速扩展，为遗产记录、状况评估、保护、管理和公众传播提供了新的方法路径。本研究中的不可移动文物主要指历史建筑、考古遗址、纪念物、文化景观及其他具有固定空间位置的遗产场所。可移动文物、博物馆藏品和非物质文化遗产不在系统考察范围内，除非相关研究直接涉及不可移动遗产的记录、监测、修复、保护或管理。尽管研究数量不断增长，现有研究大多聚焦于单项技术应用，而从全球视角开展的综合文献计量分析和知识结构图谱仍较为有限。为弥补这一空白，本研究从Web of Science核心合集检索了2015年1月1日至2025年10月1日期间的382篇英文文献，运用文献计量方法及VOSviewer、CiteSpace和ArcGIS等分析工具，考察了发文趋势、地理分布、学科类别、主要作者、机构隶属、合作网络、主题演化及新兴研究议题。结果表明，2020年后发文量显著增长。中国、意大利和西班牙是发文量最高的国家之一，并在国际合作网络中占据重要位置。主要研究主题包括数字遗产、结构健康监测、虚拟重建、深度学习、遥感及可持续性相关应用。这些发现表明，AI相关的不可移动文物研究在工程学、保护科学、计算机科学、遥感及相关技术领域具有较强的代表性。然而，这一格局不应被解释为整个文化遗产研究领域普遍发生学科转向的证据，而是反映了本研究所采用的检索策略所捕获文献的技术导向，该策略仅限于Web of Science核心合集收录的英文文献。本研究梳理了AI在不可移动文物保护研究中的应用发展与知识结构，并提供了定量证据","Built Heritage","2026-10-15T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":73},"该文研究不可移动文化遗产领域的AI文献计量，与三农、农业信息化、智慧农业、数字乡村无关，相关性门槛未通过。",[75],{"name":70,"url":67},[21,77,78],"文献计量","文化遗产",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":81},{"candidates":82,"agricultural_evidence":14,"reason":40},[83,90,97],{"code":32,"score":84,"supported":34,"title":85,"abstract":86,"tags":89},18,[37],[87,88,37],"深度学习","deep learning",[21],{"code":91,"score":92,"supported":34,"title":93,"abstract":95,"tags":96},"I7",15,[94],"bibliometric",[77,94],[77],{"code":98,"score":62,"supported":34,"title":99,"abstract":100,"tags":103},"I3",[],[101,102],"遥感","remote sensing",[],[105,106],"不可移动文物 人工智能","人工智能 文化遗产 文献计量","不可移动文物人工智能-5191","10.1186\u002Fs43238-026-00324-1",{"doi":108,"openalex_id":110,"authors":111,"venue":70,"cited_by_count":15,"oa_url":117,"card":118,"direction":124,"ingested_from":59},"W7222247878",[112,115],{"name":113,"orcid":114},"Yating Wen","https:\u002F\u002Forcid.org\u002F0009-0003-0289-3199",{"name":116,"orcid":9},"Marzudi Md Yunus","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1186\u002Fs43238-026-00324-1.pdf",{"tldr":119,"method":120,"finding":121,"direction":122,"opportunity":123},"用文献计量与知识图谱方法梳理2015-2025年AI在不可移动文化遗产研究中的应用格局。","Web of Science核心合集382篇英文文献，用VOSviewer、Ci","2020年后发文量激增，中意西三国领先，主题集中于数字遗产、结构健康监测、虚拟重建、深度学习与遥感。","其他","可借鉴其遥感与深度学习主题，探索AI在农业文化遗产、传统村落等不可移动农业遗产监测保护中的空白。","数字乡村与农业信息化","2026-10-17T23:30:41.024676Z",{"id":127,"title":128,"url":129,"summary":130,"summary_zh":131,"content":9,"source_name":132,"source_url":129,"published_at":133,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":134,"sources":136,"tags":138,"primary_topic":9,"secondary_topics":142,"classification":143,"search_phrases":152,"slug":155,"view_count":15,"doi":156,"paper":157,"created_at":170},4817,"Use of artificial intelligence and other data-driven technologies for coastal management","https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835","Biogeochemical cycles occur naturally in coastal regions. Estuaries, wetlands, and tidal creeks assist these cycles. Since increased anthropogenic activities and naturally occurring events act as stressors, they impact physical, chemical, and biological processes in maritime spaces and hence these cycles. This makes existing ecosystems susceptible to trophic imbalance. Resultantly, researchers began monitoring and mapping coastal environments to understand how different stressors impact these biogeochemical processes using numerical and empirical models. With advances in computation infrastructure, use of data-driven techniques such as Artificial Intelligence, Machine Learning, and Deep Learning in different hydrological systems have become commonplace. This has invigorated the use of predictive and decision-making frameworks in coastal management, making habitat conservation more scientific. Such frameworks balance ecological health and human activities through hard and soft engineering, nature-based solutions, and managed retreat. Though substantial literature on the use of Artificial Intelligence and Machine Learning in the coastal environment exists, they focus on independent domains, with limited discussion of their combined impact on coastal management. Accordingly, this desk-based qualitative review discusses recent developments in Artificial Intelligence, Machine Learning, Deep Learning, and other data-driven techniques used for coastal management. In addition, it will identify future directions for such studies, especially with combined stressors. ------------------------------------------------------------------------------Cite this article: APA Style:Agarwala, N. (2027). Use of artificial intelligence and other data-driven technologies for coastal management. Maritime Technology and Research, 9(1), 289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 MDPI Style:Agarwala, N. Use of artificial intelligence and other data-driven technologies for coastal management. Marit. Technol. Res. 2027, 9, 289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 Vancouver Style:Agarwala N. (2027). Use of artificial intelligence and other data-driven technologies for coastal management. Marit. Technol. Res. 9(1):289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 ------------------------------------------------------------------------------ Highlights Provides an overview tying disparate AI\u002FML to cohesive coastal management frameworks Shows how coastal modeling has transitioned from traditional linear systems to modern multi-physics data-driven frameworks Shows how PINNs addresses AI limitations like hallucinations and physical anomalies Shows how AI optimizes hard gray infrastructure while scaling up soft green solutions Showcases how Decision Support Systems use spatial-temporal algorithms to balance ecosystem preservation with economic priorities","生物地球化学循环在沿海地区自然发生。河口、湿地和潮汐溪流对这些循环起到辅助作用。由于人类活动增加和自然发生的事件作为压力源，它们影响海洋空间中的物理、化学和生物过程，进而影响这些循环。这使得现有生态系统易受营养失衡的影响。因此，研究人员开始监测和绘制沿海环境，以了解不同压力源如何利用数值模型和经验模型影响这些生物地球化学过程。随着计算基础设施的进步，人工智能、机器学习和深度学习等数据驱动技术在不同水文系统中的应用已变得普遍。这推动了预测和决策框架在海岸管理中的应用，使栖息地保护更加科学。此类框架通过硬工程和软工程、基于自然的解决方案以及有管理的后退，平衡生态健康与人类活动。尽管关于人工智能和机器学习在沿海环境中应用的文献已相当丰富，但它们聚焦于独立领域，对其在海岸管理中的综合影响讨论有限。因此，本项基于案头的定性综述讨论了人工智能、机器学习、深度学习及其他用于海岸管理的数据驱动技术的最新进展。此外，它将确定此类研究的未来方向，尤其是在复合压力源方面。 ------------------------------------------------------------------------------ 引用本文： APA格式：Agarwala, N. (2027). Use of artificial intelligence and other data-driven technologies for coastal management. Maritime Technology and Research, 9(1), 289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 MDPI格式：Agarwala, N. Use of artificial intelligence and other data-driven technologies for coastal management. Marit. Technol. Res. 2027, 9, 289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 Vancouver格式：Agarwala N. (2027). Use of artificial intelligence and other data-driven technologies for coastal management. Marit. Technol. Res. 9(1):289835. https:\u002F\u002Fdoi.org\u002F10.33175\u002Fmtr.2027.289835 ------------------------------------------------------------------------------ 亮点 提供概述，将分散的人工智能\u002F机器学习与连贯的海岸管理框架联系起来 展示海岸建模如何转变","Maritime Technology and Research","2026-10-11T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":135},"该论文聚焦海岸带管理与海洋生态，属海洋与海事领域，与三农、农业信息化、智慧农业、数字乡村无直接关联，相关性门槛未通过。",[137],{"name":132,"url":129},[139,21,140,141],"机器学习","数据驱动","海岸带管理",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":144},{"candidates":145,"agricultural_evidence":14,"reason":40},[146],{"code":32,"score":147,"supported":34,"title":148,"abstract":149,"tags":151},19,[37],[87,139,150,88,37,38],"machine learning",[21,139],[153,154],"海岸带管理 人工智能 数据驱动 机器学习","海岸带管理 人工智能","海岸带管理人工智能数据驱动机器学习-4817","10.33175\u002Fmtr.2027.289835",{"doi":156,"openalex_id":158,"authors":159,"venue":132,"cited_by_count":15,"oa_url":163,"card":164,"direction":58,"ingested_from":59},"W7221479771",[160],{"name":161,"orcid":162},"Nitin Agarwala","https:\u002F\u002Forcid.org\u002F0000-0003-0916-3044","https:\u002F\u002Fso04.tci-thaijo.org\u002Findex.php\u002FMTR\u002Farticle\u002Fdownload\u002F289835\u002F193722",{"tldr":165,"method":166,"finding":167,"direction":168,"opportunity":169},"综述人工智能与数据驱动技术在海岸带管理中的应用，并指出未来方向。","基于文献的定性综述，梳理AI、机器学习与深度学习在海岸环境建模中的应用。","现有研究多局限于独立领域，缺乏对多重压力下综合管理框架的整合讨论。","农业遥感与作物表型","可探索多压力源耦合下AI决策框架，并迁移至农业面源污染与滨海湿地协同治理。","2026-10-13T23:30:14.084085Z",{"id":172,"title":173,"url":174,"summary":175,"summary_zh":176,"content":9,"source_name":177,"source_url":174,"published_at":178,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":179,"sources":181,"tags":183,"primary_topic":9,"secondary_topics":186,"classification":187,"search_phrases":196,"slug":199,"view_count":45,"doi":200,"paper":201,"created_at":212},4496,"Artificial Intelligence and Cultural Heritage: A Review of Opportunities, Risks, and Ethical Challenges","https:\u002F\u002Fdoi.org\u002F10.61424\u002Fijcgrs.v3i1.1060","Artificial intelligence (AI) is increasingly transforming the documentation, preservation, interpretation, and public engagement of cultural heritage. This review examines the opportunities, risks, and ethical challenges associated with the application of AI in cultural heritage management and research. Drawing on interdisciplinary literature spanning heritage studies, computer science, digital humanities, museum studies, and information ethics, the review synthesizes evidence on the use of machine learning, computer vision, natural language processing, generative AI, and three-dimensional technologies in heritage contexts. The findings indicate that AI can enhance the digitization and classification of cultural collections, reconstruct damaged or lost heritage assets, support archaeological analysis, improve multilingual access to heritage resources, and create more interactive experiences for museums and heritage sites. AI also offers opportunities for predictive conservation through automated monitoring of environmental conditions, material deterioration, and structural changes. However, these benefits are accompanied by significant risks, including algorithmic bias, inaccurate reconstruction, cultural misrepresentation, intellectual-property disputes, data privacy concerns, technological dependency, and the marginalization of communities whose cultural knowledge is incorporated into AI systems without meaningful participation or consent. Generative AI presents additional challenges because synthetic representations may blur distinctions between historically documented evidence and machine-generated interpretations. The review therefore emphasizes the importance of human oversight, transparent documentation of AI-generated outputs, culturally sensitive data governance, community participation, provenance tracking, and equitable access to digital heritage technologies. Overall, AI should be understood not simply as a technological tool but as a socio-cultural intervention whose deployment requires collaboration among technologists, heritage professionals, researchers, governments, and source communities. Responsible and inclusive AI governance can enable technological innovation while protecting the authenticity, diversity, ownership, and cultural significance of heritage resources.","人工智能（AI）正日益改变文化遗产的记录、保存、阐释与公众参与方式。本文综述了AI在文化遗产管理与研究中应用所带来的机遇、风险与伦理挑战。通过整合涵盖遗产研究、计算机科学、数字人文、博物馆学与信息伦理学的跨学科文献，本文综合了机器学习、计算机视觉、自然语言处理、生成式AI及三维技术在遗产领域应用的证据。研究结果表明，AI能够促进文化藏品的数字化与分类，重建受损或遗失的遗产资产，支持考古分析，改善遗产资源的多语言获取，并为博物馆与遗产地创造更具互动性的体验。AI还通过自动监测环境条件、材料劣化与结构变化，为预测性保护提供了机遇。然而，这些益处伴随着显著风险，包括算法偏见、重建不准确、文化误现、知识产权争议、数据隐私问题、技术依赖，以及那些其文化知识在缺乏实质性参与或同意的情况下被纳入AI系统的社区所面临的边缘化。生成式AI带来了额外挑战，因为合成表征可能模糊历史文献证据与机器生成阐释之间的界限。因此，本文强调人工监督、AI生成产出的透明记录、文化敏感的数据治理、社区参与、来源追踪以及数字遗产技术公平获取的重要性。总体而言，AI不应仅被理解为一种技术工具，而应被视为一种社会文化干预，其部署需要技术人员、遗产专业人员、研究者、政府与来源社区之间的协作。负责任且包容的AI治理能够在保护遗产资源真实性、多样性、所有权与文化意义的同时，推动技术创新。","OpenAlex","2026-10-07T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":180},"主题为AI在文化遗产领域的综述，与三农、农业信息化、智慧农业无直接关联，不进入每日精选。",[182],{"name":177,"url":174},[21,78,184,185],"数字人文","伦理治理",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":188},{"candidates":189,"agricultural_evidence":14,"reason":40},[190],{"code":32,"score":84,"supported":34,"title":191,"abstract":192,"tags":195},[37],[139,193,150,37,194],"计算机视觉","computer vision",[21],[197,198],"人工智能 伦理治理 数字人文 文化遗产","人工智能 伦理治理","人工智能伦理治理数字人文文化遗产-4496","10.61424\u002Fijcgrs.v3i1.1060",{"doi":200,"openalex_id":202,"authors":203,"venue":9,"cited_by_count":15,"oa_url":206,"card":207,"direction":58,"ingested_from":59},"W7220858187",[204],{"name":205,"orcid":9},"Morgan Roberts","https:\u002F\u002Fbluemarkpublishers.com\u002Findex.php\u002FIJCGRS\u002Farticle\u002Fdownload\u002F1060\u002F916",{"tldr":208,"method":209,"finding":210,"direction":122,"opportunity":211},"综述AI在文化遗产管理中的机遇、风险与伦理挑战，强调负责任治理。","跨学科文献综述，涵盖机器学习、计算机视觉、生成式AI与3D技术。","AI可助力遗产数字化与预测性保护，但存在偏见、误重建与社区边缘化风险。","可探索文化遗产AI的社区参与式数据治理与生成内容溯源机制，平衡创新与真实性。","2026-10-09T23:30:11.121326Z",{"id":214,"title":215,"url":216,"summary":217,"summary_zh":218,"content":9,"source_name":219,"source_url":216,"published_at":178,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":220,"score_detail":221,"sources":225,"tags":227,"primary_topic":9,"secondary_topics":233,"classification":234,"search_phrases":277,"slug":280,"view_count":45,"doi":281,"paper":282,"created_at":297},4495,"A review of forest innovation: Technologies and sustainable practices for environmental conservation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.nxsust.2026.100546","Forests play a crucial role in climate regulation, biodiversity conservation, ecosystem service provision, and sustainable socio-economic development. However, increasing deforestation, climate change, habitat fragmentation, and unsustainable resource exploitation continue to threaten forest ecosystems worldwide. The objective of this review is to determine the ecological, economic, and governance conditions under which specific forest innovations translate into measurable sustainability outcomes, and to synthesize these conditions into coherent, evidence-based pathways applicable across different regional contexts. Framed through a social-ecological systems (SES) and resilience lens, this review critically examines recent advances in forest innovation by integrating sustainable forest management practices with emerging technological developments, including precision forestry, remote sensing, geographic information systems (GIS), LiDAR, unmanned aerial vehicles (UAVs), biotechnology, artificial intelligence (AI), digital forestry, biomass utilization, and forest-based bioeconomy approaches. Unlike conventional narrative reviews, this study applies a common five criterion evaluation framework comprising ecological effectiveness, technological maturity, economic feasibility, governance requirements, and regional applicability to comparatively evaluates the strengths, limitations, implementation challenges of these innovations across diverse ecological and socio-economic contexts, thereby moving beyond the largely descriptive, single-domain coverage of prior forest technology and forest governance reviews to an explicitly cross-domain, comparative synthesis. The review further explores the contributions of community-based forest management, climate-smart forestry, carbon management strategies, ecosystem services, green infrastructure, and innovative forest-derived products toward achieving long-term environmental sustainability. The analysis demonstrates that technological innovations alone cannot ensure sustainable forest management unless supported by effective governance, equitable community participation, adequate financial investment, and adaptive policy frameworks. The review identifies critical knowledge gaps related to technology adoption, institutional capacity, climate resilience, and long-term monitoring, and derives four specific, evidence-anchored integrated pathways that combine ecological, technological, economic, and governance innovations. This review provides a comprehensive, deliberately broad-scope synthesis of contemporary forest innovation and offers practical recommendations for researchers, policymakers, and forest managers working toward resilient forest ecosystems and the achievement of the United Nations Sustainable Development Goals, particularly SDG 15 (Life on Land).","森林在气候调节、生物多样性保护、生态系统服务供给以及可持续社会经济发展中发挥着至关重要的作用。然而，日益加剧的森林砍伐、气候变化、栖息地破碎化以及不可持续的资源开发持续威胁着全球森林生态系统。本综述旨在明确特定森林创新在何种生态、经济与治理条件下能够转化为可衡量的可持续性成果，并将这些条件综合为适用于不同区域背景的连贯且基于证据的路径。本综述以社会-生态系统（SES）和韧性为理论框架，通过将可持续森林管理实践与新兴技术发展相结合，批判性地审视了森林创新的最新进展，这些技术包括精准林业、遥感、地理信息系统（GIS）、激光雷达（LiDAR）、无人机（UAV）、生物技术、人工智能（AI）、数字林业、生物质利用以及基于森林的生物经济方法。与传统叙述性综述不同，本研究采用统一的五标准评价框架，包括生态有效性、技术成熟度、经济可行性、治理要求和区域适用性，对上述创新在不同生态和社会经济背景下的优势、局限及实施挑战进行比较评估，从而超越以往森林技术和森林治理综述 largely 描述性、单一领域的覆盖范围，实现明确的跨领域比较综合。本综述进一步探讨了社区森林管理、气候智慧型林业、碳管理策略、生态系统服务、绿色基础设施以及创新性林产品对实现长期环境可持续性的贡献。分析表明，除非得到有效治理、公平的社区参与、充足的财政投资和适应性政策框架的支持，否则仅靠技术创新无法确保可持续森林管理。本综述识别了与技术采用、机构能力、气候韧性和长期监测相关的关键知识空白，并推导出四条具体的、以证据为锚点的综合路径，这些路径融合了生态、技术、经济和治理创新。Th","Next Sustainability",77,{"impact":84,"substance":222,"depth":84,"authority":223,"freshness":33,"relevant":45,"comment":224},21,13,"该综述系统整合精准林业、遥感、AI等技术与治理条件，提出四条证据支撑路径，对智慧林业与数字乡村建设有较高参考价值，但属综述类论文、时效性一般，适合进入主题聚合而非头条精选。",[226],{"name":219,"url":216},[21,228,229,230,231,232],"智慧林业","遥感监测","森林碳汇","数字林业","可持续经营",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":235},{"candidates":236,"agricultural_evidence":14,"reason":40},[237,247,255,263,267,272],{"code":238,"score":239,"supported":34,"title":240,"abstract":241,"tags":246},"H6",9,[],[242,243,244,245],"生物多样性","生态系统服务","biodiversity","ecosystem service",[],{"code":248,"score":239,"supported":34,"title":249,"abstract":250,"tags":254},"H7",[],[251,252,253],"气候变化","climate change","climate resilience",[],{"code":256,"score":239,"supported":34,"title":257,"abstract":258,"tags":262},"I4",[],[259,260,261],"地理信息","GIS","geographic information",[],{"code":98,"score":33,"supported":34,"title":264,"abstract":265,"tags":266},[],[101,102],[229],{"code":32,"score":268,"supported":34,"title":269,"abstract":270,"tags":271},4,[],[37],[21],{"code":273,"score":45,"supported":14,"title":274,"abstract":275,"tags":276},"H4",[],[],[230],[278,279],"森林创新 遥感 LiDAR 无人机","数字林业 森林碳汇 可持续经营","森林创新遥感LiDAR无人机-4495","10.1016\u002Fj.nxsust.2026.100546",{"doi":281,"openalex_id":283,"authors":284,"venue":219,"cited_by_count":15,"oa_url":291,"card":292,"direction":58,"ingested_from":59},"W7220854619",[285,288],{"name":286,"orcid":287},"Shivani Garg","https:\u002F\u002Forcid.org\u002F0000-0001-7879-7177",{"name":289,"orcid":290},"Pooja Arora","https:\u002F\u002Forcid.org\u002F0000-0002-4860-4714","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2949823626003016\u002Fpdf",{"tldr":293,"method":294,"finding":295,"direction":168,"opportunity":296},"综述森林创新技术，用五标准框架比较其可持续性成效与实施条件。","社会生态系统与韧性视角，五标准评估框架，综合遥感、AI、数字林业等。","技术创新需治理、社区参与、投资和适应性政策配合才能实现可持续森林管理。","可研究遥感\u002FAI在森林碳汇监测中的技术采纳障碍与制度适配路径。","2026-10-09T23:30:10.090218Z",{"id":299,"title":300,"url":301,"summary":302,"summary_zh":303,"content":9,"source_name":304,"source_url":301,"published_at":305,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":306,"sources":308,"tags":310,"primary_topic":9,"secondary_topics":313,"classification":314,"search_phrases":332,"slug":335,"view_count":336,"doi":337,"paper":338,"created_at":358},4218,"YOLO-BASED SYSTEMS FOR DETECTING EXPLOSIVE REMNANTS OF WAR: A REVIEW FOR HUMANITARIAN DEMINING","https:\u002F\u002Fdoi.org\u002F10.20998\u002F2522-9052.2026.4.10","Relevance. Humanitarian demining remains a critical safety challenge because explosive remnants of war, landmines, and unexploded ordnance continue to endanger civilians and hinder post-conflict recovery. In this context, artificial intelligence and computer vision are increasingly used to support hazardous-object detection in UAVs-based survey operations. The purpose of this paper is to synthesize contemporary approaches to the detection of landmines, unexploded ordnance, and other explosive remnants of war, and to define the role of YOLO models in an integrated technological pipeline for surveying hazardous areas. The object of the review is technological solutions for detecting hazardous objects using UAVs, sensor systems, geoinformation technologies, and YOLO-family models. The subject of the paper is the application of YOLO-based systems in integrated pipelines for localizing potential explosive objects from visual and spectral data. Research results. The review shows that modern approaches combine ground-penetrating radar, magnetometry, thermal sensing, multispectral imaging, hyperspectral imaging, UAV-based inspection, GIS platforms, and edge\u002Fcloud architectures. YOLO demonstrates strong potential for rapid localization of visually or spectrally expressed indicators of hazardous objects, especially when combined with other sensing modalities. Conclusions. At the same time, YOLO cannot serve as the sole basis for declaring an area safe. Its use is constrained by small target size, camouflage, domain shift, limited annotated datasets, and the high cost of false negatives. Therefore, YOLO-based detection should be treated as one component of a multisensor, human-supervised decision-support system.","相关性。人道主义排雷仍然是一项关键的安全挑战，因为战争遗留爆炸物、地雷和未爆弹药继续危及平民并阻碍冲突后恢复。在此背景下，人工智能和计算机视觉越来越多地被用于支持基于无人机（UAV）的勘察作业中的危险物体检测。本文旨在综合当前对地雷、未爆弹药和其他战争遗留爆炸物的检测方法，并明确YOLO模型在危险区域勘察集成技术流程中的作用。综述的对象是利用无人机、传感器系统、地理信息技术和YOLO系列模型检测危险物体的技术解决方案。论文的主题是基于YOLO的系统在集成流程中从视觉和光谱数据定位潜在爆炸物体的应用。研究结果。综述表明，现代方法结合了探地雷达、磁力测量、热传感、多光谱成像、高光谱成像、基于无人机的检查、GIS平台以及边缘\u002F云架构。YOLO在快速定位视觉或光谱上可表现出的危险物体指标方面展现出强大潜力，尤其是与其他传感模态结合使用时。结论。与此同时，YOLO不能作为宣布某一区域安全的唯一依据。其应用受到目标尺寸小、伪装、域偏移、标注数据集有限以及假阴性成本高的制约。因此，基于YOLO的检测应被视为多传感器、人工监督的决策支持系统中的一个组成部分。","Advanced Information Systems","2026-10-02T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":307},"主题为人道主义排雷中的YOLO目标检测综述，属军事安全与遥感交叉领域，与三农、农业信息化无直接关联，不建议进入每日精选。",[309],{"name":304,"url":301},[311,21,312,101],"无人机","目标检测",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":315},{"candidates":316,"agricultural_evidence":14,"reason":40},[317,322,328],{"code":32,"score":147,"supported":34,"title":318,"abstract":320,"tags":321},[319],"YOLO",[193,37,194,319],[21,312],{"code":98,"score":33,"supported":34,"title":323,"abstract":324,"tags":327},[],[325,326],"multispectral","hyperspectral",[101],{"code":256,"score":62,"supported":34,"title":329,"abstract":330,"tags":331},[],[259,260],[],[333,334],"YOLO 排雷 无人机","未爆弹药 遥感 检测","YOLO排雷无人机-4218",2,"10.20998\u002F2522-9052.2026.4.10",{"doi":337,"openalex_id":339,"authors":340,"venue":304,"cited_by_count":15,"oa_url":352,"card":353,"direction":58,"ingested_from":59},"W7216173401",[341,343,345,347,350],{"name":342,"orcid":9},"Andrii Podorozhniak",{"name":344,"orcid":9},"Denys Levchenko",{"name":346,"orcid":9},"Nataliia Liubchenko",{"name":348,"orcid":349},"Іслам Ісламов","https:\u002F\u002Forcid.org\u002F0000-0001-8645-0640",{"name":351,"orcid":9},"Oleksandr Skorlupin","https:\u002F\u002Fais.khpi.edu.ua\u002Farticle\u002Fdownload\u002F372728\u002F356290",{"tldr":354,"method":355,"finding":356,"direction":168,"opportunity":357},"综述YOLO模型在无人机人道排雷中检测地雷与未爆弹药的技术管线。","综述探地雷达、磁力、热成像、多\u002F高光谱、无人机与GIS结合YOLO的方法。","YOLO可快速定位危险目标，但受小目标、伪装、域偏移等限制，不能单独判定区域安全。","可将多传感器+YOLO的排雷管线迁移到农田未爆物检测与农业遥感安全评估中。","2026-10-05T23:30:11.995589Z",{"id":360,"title":361,"url":362,"summary":363,"summary_zh":9,"content":364,"source_name":365,"source_url":9,"published_at":366,"category":367,"cover_url":9,"hotness":13,"is_selected":34,"score":368,"score_detail":369,"sources":375,"tags":377,"primary_topic":382,"secondary_topics":387,"classification":388,"search_phrases":412,"slug":415,"view_count":416,"doi":9,"paper":9,"created_at":417},1913,"农业农村部发布《全国渔业发展\"十五五\"规划》 提出推进\"人工智能+\"渔业发展新模式","https:\u002F\u002Fwww.ce.cn\u002Fcysc\u002Fnewmain\u002Fyc\u002Fjsxw\u002F202609\u002Ft20260909_3201368.shtml","农业农村部9月8日发布《全国渔业发展\"十五五\"规划》，明确到2030年设施渔业现代化水平稳步提高，大数据、人工智能应用更加广泛，构建\"陆海空天\"一体化数据采集网络，推进智慧养殖、智慧捕捞、智慧流通、智慧销售，打造智慧决策管理平台。规划围绕五方面展开：发展高质量水产养殖业、安全规范可持续捕捞业、系统性推进水生生物资源养护、履行负责任渔业大国责任、发展渔业新质生产力。","## 积极推动“人工智能+”渔业发展新模式\n\n2026年09月09日 07:14 来源：证券日报 刘萌\n\n9月8日，农业农村部对外发布《全国渔业发展“十五五”规划》（以下简称《规划》）。\n\n《规划》提出，到2030年，渔业水域面积保持稳定，经营主体活力不断增强，渔业产业结构持续优化，优质水产品供给量明显增加，实现质的有效提升和量的合理增长。设施渔业现代化水平稳步提高，核心技术装备加速攻关，大数据、人工智能应用更加广泛。长江水生生物完整性指数持续提升，海洋渔业资源衰退趋缓，珍稀物种种群稳中有增。渔业治理能力显著增强，海洋渔船安全生产形势稳定。\n\n从内容上看，《规划》围绕五方面展开：一是发展高质量水产养殖业，守牢质量安全底线和提高品质并重；二是打造安全规范可持续捕捞业，守牢生产安全底线和优化产业结构并重；三是系统性推进水生生物资源养护，守牢资源安全底线和持续利用并重；四是履行负责任渔业大国责任，守牢涉外安全底线和稳定发展空间并重；五是发展渔业新质生产力，推动科技创新与产业创新深度融合。\n\n其中，在发展渔业新质生产力，推动科技创新与产业创新深度融合方面，《规划》提出振兴水产种业。聚焦20个核心种类，组织科研企业力量，强化种业创新，开展全基因组选择、分子设计育种等关键技术联合攻关，突破人工繁育瓶颈，提升规模化自繁能力，摆脱国外引种和野生捕捞依赖，实现种源自主可控。实施“蓝色种业”创新行动，选育适配深远海养殖、盐碱水养殖、海水工厂化循环水养殖等场景的突破性优良品种。改革新品种审定制度，优化审定流程。加强苗种进出口管理，推广抗病抗逆等优良复合性状新品种。\n\n同时，《规划》提出，推进渔业设施装备升级和人工智能应用。深化现代信息技术与渔业全链条、全场景融合，积极推动“人工智能+”渔业发展新模式。构建“陆海空天”一体化数据采集网络，推进智慧养殖、智慧捕捞、智慧流通、智慧销售，打造智慧决策管理平台。\n\n围绕全产业链提质增效，《规划》明确培育壮大龙头企业、家庭农场、农民合作社，打造特色区域公用品牌，培育一批全产业链产值百亿、千亿级优势特色养殖产业，带动广大渔民共同发展。出台休闲渔船管理办法，改造渔村、渔港、养殖区环境，完善休闲设施，推进“渔业+”产业融合。\n\n此外，《规划》要求统筹安排渔业发展补助资金等财政资金，切实保障规划实施财力需求。加强前瞻布局，强化用地、用海、用水等要素保障，健全政策资金引导、金融信贷跟进、社会资本参与的多元投入格局，支持渔业重点项目。\n\n(责任编辑：黄春棉)","中国经济网 2026-09-09","2026-09-09T00:00:00Z","政策",91,{"impact":370,"substance":371,"depth":372,"authority":373,"freshness":13,"relevant":45,"comment":374},28,22,17,14,"全国性渔业规划发布，明确推进AI+渔业，政策层级高、信息量大，时效性强。",[376],{"name":365,"url":362},[378,379,21,380,381],"新质生产力","种业振兴","智慧养殖","渔业规划",{"code":383,"slug":384,"name":385,"path":386,"parent_code":9},"D","aquaculture","渔业水产","\u002Ftopic\u002Faquaculture",[],{"status":389,"locked":14,"version":27,"method":28,"evidence":390},"partial",{"candidates":391,"agricultural_evidence":34},[392,398,403,407],{"code":383,"score":373,"supported":34,"title":393,"abstract":395,"tags":397},[394],"渔业",[396,394],"水产",[],{"code":399,"score":45,"supported":14,"title":400,"abstract":401,"tags":402},"F1",[],[],[379],{"code":32,"score":45,"supported":14,"title":404,"abstract":405,"tags":406},[],[],[21],{"code":408,"score":45,"supported":14,"title":409,"abstract":410,"tags":411},"J2",[],[],[378],[413,414],"新质生产力 人工智能 智慧养殖 渔业规划","新质生产力 人工智能","新质生产力人工智能智慧养殖渔业规划-1913",5,"2026-09-09T00:03:51.790198Z"]