[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2939":3,"related-2939":53},{"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":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":52},2939,"Climate Change and Food Security in Africa: Harnessing Responsible AI for Sustainable Agricultural Transformation","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijaes.vol.11.no9.2025.pg79.102","Africa stands at the crossroads of two defining 21st-century challenges: climate change and food insecurity. The continents agricultural systems are increasingly disrupted by rising temperatures, erratic rainfall, and extreme weather events, exacerbating hunger, poverty, and rural vulnerability. At the same time, Artificial Intelligence (AI) presents transformative potential to support climate adaptation, improve agricultural resilience, and enhance food systems governance across Africa. This study undertakes a qualitative content analysis and critical synthesis of 25 peer-reviewed articles, institutional reports, and working papers to examine how AI is currently applied and could be more effectively leveraged for climate-resilient agriculture and food security on the continent. Findings reveal a growing body of innovations, from AIdriven weather forecasting and early warning systems to precision agriculture and supply chain optimization. Yet the study identifies persistent structural limitations, including unreliable data infrastructure, low digital capacity in rural areas, and governance gaps around ethical deployment, data ownership, and equitable access. Through African case studies, the paper explores how localized AI solutions when supported by inclusive policies, multi-stakeholder collaboration, and responsible innovation frameworks can mitigate climate-induced food shocks and drive sustainable development. The paper argues for a strategic alignment between AI deployment and national adaptation plans, emphasizing the need for stronger public-private partnerships, investments in AI-ready infrastructure, and the development of ethical and contextsensitive governance mechanisms. In doing so, it offers a roadmap for policymakers, development agencies, and researchers seeking to harness AI not just as a technological tool, but as a catalyst for systemic transformation in African food systems in the era of climate change.","非洲正处在21世纪两大决定性挑战的交汇点：气候变化与粮食不安全。随着气温上升、降雨异常和极端天气事件频发，非洲大陆的农业系统日益受到扰乱，饥饿、贫困和农村脆弱性问题不断加剧。与此同时，人工智能（AI）展现出变革性潜力，可支持非洲的气候适应、提升农业韧性并改善粮食系统治理。本研究对25篇同行评审论文、机构报告和工作论文进行了定性内容分析与批判性综合，考察AI当前在非洲大陆的应用方式，以及如何更有效地将其用于气候韧性农业和粮食安全。研究发现，相关创新不断涌现，涵盖AI驱动的天气预报和预警系统、精准农业以及供应链优化等领域。然而，研究也识别出持续存在的结构性制约，包括数据基础设施不可靠、农村地区数字能力薄弱，以及围绕伦理部署、数据所有权和公平获取的治理缺口。通过非洲案例研究，本文探讨了在包容性政策、多利益相关方协作和负责任创新框架支持下，本地化的AI解决方案如何能够缓解气候引发的粮食冲击并推动可持续发展。本文主张将AI部署与国家适应计划进行战略对接，强调需要加强公私伙伴关系、投资于AI就绪型基础设施，并建立合乎伦理且情境敏感的治理机制。由此，本文为政策制定者、发展机构和研究人员提供了一份路线图，旨在气候变化时代将AI不仅作为技术工具，更作为非洲粮食系统系统性转型的催化剂加以利用。",null,"INTERNATIONAL JOURNAL OF AGRICULTURE AND EARTH SCIENCE","2026-09-16T00:00:00Z","论文",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,20,17,13,8,1,"系统综述25篇文献，梳理AI在非洲气候韧性农业中的应用与治理缺口，对农业信息化有参考价值，但属境外区域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","粮食安全","非洲农业","气候适应",[33,34],"非洲 农业人工智能 粮食安全","AI 气候韧性农业 非洲","非洲农业人工智能粮食安全-2939",0,"10.56201\u002Fijaes.vol.11.no9.2025.pg79.102",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":43,"card":44,"direction":50,"ingested_from":51},"W7213462904",[41],{"name":42,"orcid":9},"Izuchukwu Adamaagashi","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJAES\u002FVOL. 11 NO. 9 2025\u002FClimate Change and Food Security 79-102.pdf",{"tldr":45,"method":46,"finding":47,"direction":48,"opportunity":49},"通过定性分析25篇文献，探讨如何负责任地利用AI推动非洲气候适应型农业与粮食安全。","对25篇同行评议论文、机构报告和工作论文进行定性内容分析与批判性综合。","AI在天气预报、精准农业等方面有创新，但面临数据基础设施差、农村数字能力低和治理缺口等结构性限制。","农业人工智能与决策模型","可研究非洲本地化AI解决方案的伦理治理框架与公私合作模式，填补数据所有权和公平获取的研究空白。","智慧农业 \u002F 农业物联网","openalex","2026-09-19T23:30:19.482449Z",{"total":54,"page":22,"page_size":54,"items":55},6,[56,87,114,169,226,255],{"id":57,"title":58,"url":59,"summary":60,"summary_zh":9,"content":9,"source_name":61,"source_url":9,"published_at":62,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":63,"score_detail":64,"sources":68,"tags":70,"search_phrases":73,"slug":76,"view_count":36,"doi":77,"paper":78,"created_at":86},2859,"县域大豆产量预测的深度学习方法:利用大规模环境数据——Frontiers in Artificial Intelligence","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1914697\u002Ffull","论文提出了基于深度学习的大规模环境数据县域大豆产量预测方法。利用县级大豆产量数据和环境变量构建预测模型,评估多种深度学习架构(卷积神经网络、循环神经网络、Transformer等)在大豆产量预测中的表现,并与传统统计回归模型进行比较。结果显示,深度学习方法在预测精度和稳定性方面优于传统模型,能够更好地捕捉环境因素与产量之间的非线性关系,为农业政策制定和粮食安全评估提供数据支持。","Frontiers in Artificial Intelligence","2026-09-17T00:00:00Z",77,{"impact":65,"substance":66,"depth":19,"authority":20,"freshness":13,"relevant":22,"comment":67},16,21,"论文以县级大规模环境数据对比多种深度学习架构与传统回归模型，方法新颖、结论可靠，对农业政策与粮食安全评估有参考价值，值得进入每日精选。",[69],{"name":61,"url":59},[27,28,29,71,72],"大豆产量预测","环境数据",[74,75],"农业人工智能 大豆产量预测 智慧农业 环境数据","农业人工智能 大豆产量预测","农业人工智能大豆产量预测智慧农业环境数据-2859","10.3389\u002Ffrai.2026.1914697\u002Ffull",{"doi":77,"openalex_id":9,"authors":79,"venue":9,"cited_by_count":36,"oa_url":9,"card":80,"direction":48,"ingested_from":85},[],{"tldr":81,"method":82,"finding":83,"direction":48,"opportunity":84},"用深度学习结合大规模环境数据预测县域大豆产量，并对比多种网络架构与传统模型。","县级大豆产量与环境变量数据，采用CNN、RNN、Transformer等深度学习","深度学习在预测精度和稳定性上优于传统统计回归，能更好捕捉非线性关系。","可探索多模态环境数据融合与可解释性，提升跨区域迁移和极端气候下的预测鲁棒性。","agent","2026-09-18T00:03:31.241582Z",{"id":88,"title":89,"url":90,"summary":91,"summary_zh":9,"content":92,"source_name":93,"source_url":9,"published_at":62,"category":94,"cover_url":9,"hotness":13,"is_selected":95,"score":96,"score_detail":97,"sources":103,"tags":105,"search_phrases":109,"slug":112,"view_count":36,"doi":9,"paper":9,"created_at":113},2816,"中央网信办专家解读:乘\"数\"而上 向\"智\"而行——大力发展智慧农业加快建设数字乡村","https:\u002F\u002Fwww.cac.gov.cn\u002F2026-09\u002F17\u002Fc_1789925195600209.htm","专家解读指出,\"十五五\"时期数字乡村将加快迈向数智乡村,智慧农业建设将进入创新发展、落地见效的关键阶段。《加快农业农村现代化\"十五五\"规划》明确\"推进人工智能运用和智慧农业发展\"。人工智能等数智技术正加速演进,数据产业加快培育、应用场景全链拓展、新兴产业加快培育,为智慧农业发展带来前所未有的新机遇:数据从辅助性工具发展为新型生产要素,农业大模型与智能装备在生物育种、农情监测、生产管理、动植物疫病识别与防控、产量预测等场景加速落地。","习近平总书记高度重视数字乡村建设和智慧农业发展，作出重要指示强调，“瞄准农业现代化主攻方向，提高农业生产智能化、经营网络化水平，帮助广大农民增加收入”“要用好现代信息技术，创新乡村治理方式，提高乡村善治水平”。2019年，中共中央办公厅、国务院办公厅印发了《数字乡村发展战略纲要》。此后，中央一号文件连续八年对推进数字乡村和智慧农业作出重要部署。各地区各有关部门持续推进数字技术与农业生产、乡村生活日益融合，数字乡村建设和智慧农业发展取得重要阶段性成效。近日，国家互联网信息办公室、农业农村部联合发布《中国数字乡村发展报告（2019—2025年）》（以下简称《报告》），系统总结了七年来我国数字乡村发展的成就和经验。《报告》立足新形势新要求，展示了以信息基础设施为底座、数据资源体系为核心、智慧农业与乡村数字经济为重点、数字文化与数字治理为支撑、信息服务与智慧美丽乡村为拓展、政策机制与人才队伍为保障的体系化发展路径。该《报告》不仅为全面了解发展成效、科学谋划“十五五”数字乡村发展蓝图提供了重要参考，也积极回应各方关切，向国际社会展示了我国借助数字技术推动农业与乡村治理数智化转型的经验。回顾七年历程，智慧农业作为数字乡村建设的重要内容，已由试点探索转向快速起步、由点状突破迈向系统推进，正乘“数”而上，向“智”而行，为推进农业农村现代化提供有力支撑。\n\n**一、智慧农业正从“盆景”走向“风景”**\n\n数字乡村涵盖乡村经济、治理、文化、服务等多个维度，内涵丰富。《报告》提出，智慧农业是“农业新质生产力的重要内容，是乡村产业数字化的关键着力点”。智慧农业为数字乡村高质量发展提供了坚实的产业支撑，成为推动数字乡村发展的关键动能。《报告》显示，七年的探索推进和快速发展，推动智慧农业实现了“四个跨越”。\n\n**第一，智慧农业基础设施实现从“基础覆盖”到“深化赋能”的跨越。**完善的网络基础设施为智慧农业在田间地头、池塘圈舍的落地拓展提供了基础支撑。截至2025年底，农村地区互联网普及率达69.5%，较2018年底提升31.1个百分点。传统基础设施数字化为智慧农业提供了更加坚实的硬件底座和场景支撑，农村水利、农田、电网、公路及寄递物流等持续升级完善。农业数据资源日益丰富，为智慧农业落地应用提供了基础资源和创新引擎，“天空地一体化”监测网络等新型基础设施加快建设，全国农产品批发市场价格信息等涉农数据开发利用不断深入。\n\n**第二，关键技术装备实现从“基础”到“核心”的跨越。**智能农机装备研发应用取得重要进展，新一代信息技术与农业装备深度融合，正推动农业生产方式从“靠天吃饭”向“知天而作”加速转变。产学研用相衔接的智慧农业创新体系加快形成，支撑取得一批关键智慧农业技术装备创新成果。《报告》显示，截至2025年底，累计建设智慧农业创新中心、分中心34个，智慧农业创新应用项目116个，104项关键智慧农业技术和62项整机智能装备研发取得突破。智慧农业技术装备质量管控更加严格、应用推广不断拓展，布局建设国家农机装备产业计量测试中心，强化农机装备产业计算测试技术研究与应用。\n\n**第三，主要产业数字化实现从“单点试验”到“面上推广”的跨越。**大田种植领域，天空地一体化农情感知与数据驱动模式初步构建，实现水稻、小麦、玉米苗情长势动态监测。截至2025年底，累计推广应用各类农机北斗终端超350万台套，农用无人机保有量超过30万架、年作业面积突破4.6亿亩。智能农机共享租赁加速普及。畜禽养殖领域，精准饲喂、环境控制、行为分析等智能技术广泛应用于生猪养殖和家禽立体高效养殖中。全国659个动物防疫通道纳入信息化管理，动物检疫监督更加智能化、便捷化和高效化。渔业领域，数字技术持续赋能多元化养殖模式，智能化网箱设备、投料机器人等智能装备加速迭代，海洋养殖智能化水平不断提升。\n\n**第四，粮食安全保障实现从“人工管控”到“数智赋能”的跨越。**粮食安全是“国之大者”，数智技术正在为其构筑起坚实保障。在耕地保护方面，“三区三线”等“一张图”相关基础数据库进一步完善，让“藏粮于地”有了更坚实的数据底座，助力守牢18亿亩耕地红线。在种业振兴方面，中国种业大数据平台建成运行，全国农作物种质资源信息平台已上线58.8万份国家级库圃种质资源信息，为育种创新提供了坚实的资源基础。在防灾减损领域，气象预警信息全面接入全国123万个应急广播终端并在16个省份386个市县试行开展“闪信”技术应用，以气象预警为先导的应急响应联动机制更加健全。在仓储方面，借助数字化仓储技术，粮库储粮周期内综合损耗率控制在1%以内，支撑节粮减损效果明显。从种到收、从田间到粮仓，数智技术正在全链条赋能国家粮食安全保障体系。\n\n**二、智慧农业发展需要坚定走好符合国情农情的路子**\n\n七年来，在信息革命加速农业深刻变革的进程中，智慧农业加快发展、数字乡村建设深入推进，推动农业成为更有奔头的产业、农村成为更加宜居宜业的家园，为网络强国、农业强国建设贡献了重要力量。回顾七年实践，我们进一步深化了对智慧农业发展的规律性认识。\n\n**一是政府引导与市场机制协同发力。**党中央、国务院印发的《加快建设农业强国规划（2024—2035年）》、农业农村部印发的《关于大力发展智慧农业的指导意见》《全国智慧农业行动计划（2024—2028年）》等文件构建了智慧农业“四梁八柱”。七年来，从智慧农业创新中心布局到创新应用项目建设实施，从主推技术遴选、典型案例推介到智慧农业创新大赛，政府的“有形之手”在搭建平台、降低门槛、推动产业化等方面发挥了重要作用。同时，平台经济等推动拓展创业空间，返乡青年、家庭农场、农民合作社和农村个体商户以平台化方式进入市场、链接消费和重构经营模式，农村电商、数字服务等新业态加速发展，市场的“无形之手”进一步增强了智慧农业发展的动力活力。\n\n**二是技术创新与农情农艺深度结合。**农业不同于工业、农村不同于城市，发展智慧农业、建设数字乡村必须坚持问题导向、应用导向，走适宜化、低成本、易操作的技术路线。近年来，农机北斗终端实现快速规模化推广，在于其有效契合了播种、收获等关键环节的实际生产需求，让农民“用得上、用得起、用得好”。\n\n**三是智慧农业与小农户有机衔接。**“大国小农”的基本国情农情决定了智慧农业要实现大规模落地应用，必须坚持让小农户共享数字红利的现实路径。各类农业社会化服务组织加速布点，通过集采智能装备、统一调度作业、提供“菜单式”服务，将智能农机、无人机植保、精准施肥等先进技术和装备转化为小农户“点单即享”的标准化服务，有效破解小农户“买不起、用不好”的难题。以社会化服务为纽带，智慧农业正成为促进小农户与现代农业发展有机衔接的重要手段。\n\n**三、奋力推进“十五五”时期智慧农业建设**\n\n“十五五”时期是基本实现农业农村现代化的关键时期。展望未来五年，数字乡村将加快迈向数智乡村，智慧农业建设将进入创新发展、落地见效的关键阶段。《加快农业农村现代化“十五五”规划》明确，要“推进人工智能运用和智慧农业发展”。这要求我们既要总结运用好实践中积累形成的宝贵经验，又要准确把握未来数智技术和农业发展新趋势。\n\n当前，人工智能等数智技术加速演进，深刻重塑农业发展的底层逻辑，为智慧农业发展带来了前所未有的新机遇。**一是数据产业加快培育，释放要素价值潜能。**数据从支撑农业农村发展的辅助性工具，逐步发展为具有独立价值、可市场化运营的新型生产要素，其基础资源和创新引擎作用日渐显现，数智技术加速内化成为农业农村领域的发展动能，要抓实数据这个根本，进一步加快“统筹部署农业农村数据基础设施”“发展农业农村领域数据产业”。**二是应用场景全链拓展，场景驱动成为重要引擎。**农业大模型、智能装备加速在生物育种、农情监测、生产管理、动植物疫病识别与防控、产量预测等场景落地，场景驱动技术迭代的效能日益凸显，要打造丰富多样的应用场景，“加快农业人工智能应用场景拓展”**。三是新兴产业加快培育，拓展农业发展新空间。**智能设计育种、新能源农机、农业低空经济等先导性产业规模化发展，开辟智慧农业高质量发展全新赛道，要从智能育种等产业急需领域做起，加快“培育发展乡村新产业新业态”。\n\n《报告》的发布既是阶段性总结，更是新征程的动员。面向“十五五”，我们要坚决贯彻党中央、国务院关于大力推进“人工智能+”农业的部署要求，在基础设施上强基固本，在关键技术装备上聚力攻坚，在产业数智化上扩面提效，在粮食安全保障上筑牢数字防线，加快推动智慧农业从“点上突破”迈向“面上成势”，从“量的积累”转向“质的跃升”。以智慧农业的创新发展，推动数字乡村高质量发展，为加快农业农村现代化、扎实推进乡村全面振兴注入更加澎湃的数智动能。（作者：李韶民 农业农村部信息中心副主任）","中央网信办 \u002F 网信中国","政策",true,94,{"impact":98,"substance":99,"depth":17,"authority":100,"freshness":101,"relevant":22,"comment":102},28,24,15,9,"中央网信办与农业农村部联合发布七年数字乡村发展报告，含大量权威数据与十五五部署方向，政策层级高、信息增量足，值得进入每日精选。",[104],{"name":93,"url":90},[106,107,27,28,29,108],"十五五","数字乡村","农业数据要素",[110,111],"农业人工智能 农业数据要素 数字乡村 智慧农业","农业人工智能 农业数据要素","农业人工智能农业数据要素数字乡村智慧农业-2816","2026-09-18T00:03:24.723951Z",{"id":115,"title":116,"url":117,"summary":118,"summary_zh":119,"content":9,"source_name":120,"source_url":117,"published_at":121,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":122,"score_detail":123,"sources":127,"tags":129,"search_phrases":132,"slug":135,"view_count":36,"doi":136,"paper":137,"created_at":168},2670,"A knowledge-guided machine learning framework for cross-scale wheat harvest monitoring via sample augmentation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115671","Accurate monitoring of wheat harvest is crucial for precision agriculture and ensuring food security. However, rapid changes in land surface composition during the harvest period in intensive agricultural regions make it difficult to obtain sufficiently high-confidence ground samples, limiting the performance and generalization of data-driven remote sensing methods. Therefore, this study proposes a Knowledge-Guided Machine Learning (KGML) framework that integrates multi-satellite Earth observation data (PlanetScope, Sentinel-2, and MODIS) to monitor harvest from the field to regional scales. Ground data were collected using vehicle-mounted cameras and smartphones during the 2023 and 2024 wheat harvest periods. The results showed that combining spectral knowledge rules with a Random Forest model (regional accuracy >0.80) generated numerous high-confidence augmented samples from PlanetScope imagery. The augmented dataset was used to train a Hybrid CNN-Transformer-LSTM (HCTL) model with two pathways: Sentinel-2 classification for field-level harvest mapping (overall accuracy = 0.93) and MODIS regression for sub-pixel harvest fraction estimation, which showed high agreement with PlanetScope-derived harvest fractions (R 2 = 0.97, RMSE = 0.07, rRMSE = 0.15). The harvest dates derived from the MODIS harvest fraction time series showed high consistency with field observations (R 2 = 0.82, RMSE = 1.30 days). This framework provides an effective solution for wheat harvest monitoring by bridging the gap between limited ground-truth data and multi-scale satellite observations, thereby supporting food security assessments and informed agricultural management decisions.","准确监测小麦收获对精准农业和保障粮食安全至关重要。然而，在集约化农业区域，收获期地表组成的快速变化使得获取足够高置信度的地面样本变得困难，限制了数据驱动遥感方法的性能和泛化能力。因此，本研究提出了一种知识引导机器学习（KGML）框架，集成多卫星地球观测数据（PlanetScope、Sentinel-2和MODIS），实现从田块到区域尺度的收获监测。地面数据通过车载摄像头和智能手机在2023年和2024年小麦收获期采集。结果表明，将光谱知识规则与随机森林模型相结合（区域精度>0.80），可从PlanetScope影像中生成大量高置信度增强样本。利用该增强数据集训练了混合CNN-Transformer-LSTM（HCTL）模型，该模型包含两条路径：Sentinel-2分类用于田块尺度收获制图（总体精度=0.93），MODIS回归用于亚像元收获比例估算，其结果与PlanetScope-derived收获比例高度一致（R²=0.97，RMSE=0.07，rRMSE=0.15）。由MODIS收获比例时间序列提取的收获日期与田间观测结果高度一致（R²=0.82，RMSE=1.30天）。该框架通过弥合有限地面真值数据与多尺度卫星观测之间的差距，为小麦收获监测提供了有效解决方案，从而支持粮食安全评估和农业管理决策。","Remote Sensing of Environment","2026-09-15T00:00:00Z",87,{"impact":124,"substance":125,"depth":17,"authority":100,"freshness":101,"relevant":22,"comment":126},22,23,"提出知识引导机器学习框架，融合多源卫星数据实现田块到区域尺度的跨尺度小麦收获监测，方法新颖、精度可靠，对精准农业与粮食安全评估有实质参考价值。",[128],{"name":120,"url":117},[27,28,29,130,131],"遥感监测","小麦收获",[133,134],"农业人工智能 小麦收获 智慧农业 粮食安全","农业人工智能 小麦收获","农业人工智能小麦收获智慧农业粮食安全-2670","10.1016\u002Fj.rse.2026.115671",{"doi":136,"openalex_id":138,"authors":139,"venue":120,"cited_by_count":36,"oa_url":117,"card":162,"direction":166,"ingested_from":51},"W7213296259",[140,143,145,147,149,151,153,155,158,160],{"name":141,"orcid":142},"Mingchao Shao","https:\u002F\u002Forcid.org\u002F0000-0003-2619-4272",{"name":144,"orcid":9},"Chongya Jiang",{"name":146,"orcid":9},"Jingwei An",{"name":148,"orcid":9},"Haokai Zhu",{"name":150,"orcid":9},"Yue Li",{"name":152,"orcid":9},"Xia Yao",{"name":154,"orcid":9},"Tao Cheng",{"name":156,"orcid":157},"Hengbiao Zheng","https:\u002F\u002Forcid.org\u002F0009-0008-4778-0450",{"name":159,"orcid":9},"Weixing Cao",{"name":161,"orcid":9},"Yan Zhu",{"tldr":163,"method":164,"finding":165,"direction":166,"opportunity":167},"提出知识引导机器学习框架，用样本增强实现田块到区域尺度的冬小麦收获监测。","融合PlanetScope、Sentinel-2、MODIS与车载相机地面数据，","增强样本训练的HCTL模型田块分类精度0.93，区域收获比例R²=0.97，收获日期误差约1.3天。","农业遥感与作物表型","可迁移至其他作物收获监测，并探索知识规则自动化构建与跨区域泛化能力。","2026-09-16T23:30:30.474537Z",{"id":170,"title":171,"url":172,"summary":173,"summary_zh":174,"content":9,"source_name":175,"source_url":172,"published_at":176,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":177,"score_detail":178,"sources":180,"tags":182,"search_phrases":185,"slug":188,"view_count":36,"doi":189,"paper":190,"created_at":225},2653,"Artificial intelligence and food insecurity: opportunities, risks, and equity pathways for the Global South","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23311932.2026.2730680","Food insecurity affects 691–783 million people globally, with disproportionate impacts on low-income and middle-income countries, marginalized groups, and conflict-affected populations. Artificial intelligence (AI) presents unprecedented opportunities to address food security challenges through precision agriculture, supply chain optimization, and early warning systems, achieving up to 91% accuracy in crop yield prediction and reducing food waste by 22%. Its deployment risks perpetuating existing inequities. Drawing on a systematic literature search of 64 peer-reviewed studies across Scopus, Web of Science, PubMed, AGRIS, and IEEE Xplore (2015–2025), this review examines AI’s double-edged role in food systems through a comprehensive framework encompassing inclusive data practices, equitable governance, participatory design, and local capacity building. Key risks include data colonialism, algorithmic bias favoring industrial agriculture, the digital exclusion of vulnerable communities, and technological dependency that threatens food sovereignty. However, evidence from successful implementations in sub-Saharan Africa demonstrates that inclusive approaches can enhance productivity while promoting gender equality and environmental sustainability. The study concludes that AI’s impact of AI fundamentally depends on the design principles and governance frameworks that prioritize equity. Without inclusive implementation strategies, AI may reinforce hunger gaps; conversely, equity-centered approaches can contribute to resilient, just, and food-secure systems for all populations.","粮食不安全影响着全球6.91亿至7.83亿人，对低收入和中等收入国家、边缘化群体以及受冲突影响人口的影响尤为严重。人工智能（AI）通过精准农业、供应链优化和早期预警系统，为解决粮食安全挑战提供了前所未有的机遇，在作物产量预测中实现了高达91%的准确率，并将粮食浪费减少了22%。然而，其部署也可能固化现有的不平等。本文基于对Scopus、Web of Science、PubMed、AGRIS和IEEE Xplore数据库中64项同行评审研究（2015—2025年）的系统性文献检索，通过一个涵盖包容性数据实践、公平治理、参与式设计和本地能力建设的综合框架，审视了AI在粮食系统中的双刃剑作用。主要风险包括数据殖民主义、偏向工业化农业的算法偏见、对脆弱社区的数字排斥，以及威胁粮食主权的技术依赖。然而，来自撒哈拉以南非洲成功实施的证据表明，包容性方法可以在提高生产力的同时促进性别平等和环境可持续性。研究得出结论，AI的影响从根本上取决于优先考虑公平的设计原则和治理框架。缺乏包容性实施策略，AI可能加剧饥饿差距；反之，以公平为中心的方法可以为所有人群构建具有韧性、公正且粮食安全的体系。","Cogent Food & Agriculture","2026-09-14T00:00:00Z",83,{"impact":124,"substance":124,"depth":17,"authority":20,"freshness":21,"relevant":22,"comment":179},"基于64篇文献的系统综述，系统梳理AI在粮食安全中的双刃剑效应与公平治理路径，数据与框架均有实质增量，对农业信息化政策设计具参考价值。",[181],{"name":175,"url":172},[27,28,29,183,184],"数字鸿沟","全球南方",[186,187],"农业人工智能 全球南方 数字鸿沟 智慧农业","农业人工智能 全球南方","农业人工智能全球南方数字鸿沟智慧农业-2653","10.1080\u002F23311932.2026.2730680",{"doi":189,"openalex_id":191,"authors":192,"venue":175,"cited_by_count":36,"oa_url":218,"card":219,"direction":50,"ingested_from":51},"W7213346271",[193,196,199,202,205,208,211,214,216],{"name":194,"orcid":195},"Ahmed Abdiaziz Alasow","https:\u002F\u002Forcid.org\u002F0000-0002-9888-6131",{"name":197,"orcid":198},"Yusuf Hared Abdi","https:\u002F\u002Forcid.org\u002F0009-0002-7224-2247",{"name":200,"orcid":201},"Abdimalik Ali Warsame","https:\u002F\u002Forcid.org\u002F0000-0001-6130-5607",{"name":203,"orcid":204},"Yakub Burhan Abdullahi","https:\u002F\u002Forcid.org\u002F0009-0001-8535-198X",{"name":206,"orcid":207},"Mohamed Sharif Abdi","https:\u002F\u002Forcid.org\u002F0009-0007-0220-4014",{"name":209,"orcid":210},"Shazia Bashir","https:\u002F\u002Forcid.org\u002F0009-0007-6900-9870",{"name":212,"orcid":213},"Nova Ahmed","https:\u002F\u002Forcid.org\u002F0009-0009-9058-4807",{"name":215,"orcid":9},"Shuaibus Saidu Musa",{"name":217,"orcid":9},"Don Eliseo Lucero-Prisno","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F23311932.2026.2730680?needAccess=true",{"tldr":220,"method":221,"finding":222,"direction":223,"opportunity":224},"系统综述64项研究，分析AI在全球南方粮食安全中的机遇、风险与公平路径。","系统文献综述，检索Scopus、WoS、PubMed、AGRIS、IEEE Xp","AI可提升产量预测与减少浪费，但数据殖民、算法偏见等风险可能加剧不平等。","数字乡村与农业信息化","可实证检验公平导向的AI治理框架在低收入国家小农户中的落地效果与机制。","2026-09-16T23:30:17.199269Z",{"id":227,"title":228,"url":229,"summary":230,"summary_zh":9,"content":9,"source_name":231,"source_url":229,"published_at":232,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":233,"score_detail":234,"sources":237,"tags":239,"search_phrases":242,"slug":245,"view_count":36,"doi":246,"paper":247,"created_at":254},2054,"Quantifying Thermoregulation in Niche Construction of Apis mellifera as an Extended Phenotype to Map the Selection Pressure of Volatile Climate Using Hybrid CNN Bi-LSTM Architecture and Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10938207\u002Fv1","Quantifying Thermoregulation in Niche Construction of Apis mellifera as an Extended Phenotype to Map the Selection Pressure of Volatile Climate Using Hybrid CNN Bi-LSTM Architecture and Remote Sensing。Research Square","Research Square","2026-09-08T00:00:00Z",52,{"impact":21,"substance":235,"depth":100,"authority":54,"freshness":101,"relevant":22,"comment":236},14,"以混合CNN-BiLSTM与遥感量化蜜蜂巢域构建的热调节，方法新颖但属预印本、应用面窄，适合主题聚合而非每日精选。",[238],{"name":231,"url":229},[27,28,240,241,31],"遥感","蜜蜂",[243,244],"农业人工智能 智慧农业 气候适应 蜜蜂","农业人工智能 智慧农业","农业人工智能智慧农业气候适应蜜蜂-2054","10.21203\u002Frs.3.rs-10938207\u002Fv1",{"doi":246,"openalex_id":248,"authors":249,"venue":231,"cited_by_count":36,"oa_url":253,"card":9,"direction":166,"ingested_from":51},"W7211926390",[250],{"name":251,"orcid":252},"M. R. K. Pathan","https:\u002F\u002Forcid.org\u002F0009-0002-1943-7942","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10938207\u002Flatest.pdf","2026-09-10T23:30:24.223473Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":260,"content":9,"source_name":261,"source_url":258,"published_at":262,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":263,"sources":266,"tags":268,"search_phrases":271,"slug":274,"view_count":36,"doi":275,"paper":276,"created_at":287},2040,"Climate Change and Agricultural Insect Pests: Ecological Mechanisms, Crop Productivity Impacts and Climate Adaptation Strategies","https:\u002F\u002Fdoi.org\u002F10.47495\u002Fokufbed.2000761","Climate change has emerged as one of the most significant challenges affecting agricultural production systems worldwide. Rising temperatures, altered precipitation patterns, increasing atmospheric carbon dioxide concentrations, and the growing frequency of extreme weather events are substantially influencing the biology, ecology, distribution, and population dynamics of agricultural pests. These changes contribute to increased pest abundance, expanded geographical ranges, higher overwintering success, accelerated development rates, and greater numbers of generations per year. Consequently, pest-induced crop losses are expected to increase, posing serious threats to crop productivity, agricultural sustainability, and global food security. In addition to direct effects on pest populations, climate change disrupts plant–pest–natural enemy interactions and weakens biological control mechanisms, further increasing pest pressure within agricultural ecosystems. This review examines the effects of climate change on agricultural insect pest populations and evaluates their implications for crop productivity. Particular attention is given to temperature increases, changes in precipitation and humidity regimes, geographical distribution shifts, invasive species expansion, and phenological mismatches. Furthermore, innovative adaptation strategies including integrated pest management, artificial intelligence-based forecasting systems, precision agriculture technologies, climate-smart agriculture approaches, and remote sensing applications are discussed as potential tools for enhancing agricultural resilience under changing climatic conditions. The findings indicate that sustainable management of climate-related pest risks requires multidisciplinary approaches integrating climate information, pest monitoring, ecological processes, and advanced decision-support technologies. Developing climate-resilient, technology-supported and ecologically based pest management strategies will be essential for safeguarding agricultural productivity and long-term global food security.","气候变化已成为影响全球农业生产系统的最重大挑战之一。气温上升、降水模式改变、大气二氧化碳浓度增加以及极端天气事件日益频繁，正在显著影响农业害虫的生物学、生态学、分布和种群动态。这些变化导致害虫丰度增加、地理分布范围扩大、越冬成功率提高、发育速率加快以及每年世代数增多。因此，害虫引起的作物损失预计将增加，对作物生产力、农业可持续性和全球粮食安全构成严重威胁。除对害虫种群的直接影响外，气候变化还扰乱了植物—害虫—天敌之间的相互作用，削弱了生物防治机制，进一步加剧了农业生态系统内的害虫压力。本文综述了气候变化对农业害虫种群的影响，并评估了其对作物生产力的意义。特别关注了温度升高、降水和湿度状况变化、地理分布转移、入侵物种扩散以及物候错配等方面。此外，还讨论了创新性适应策略，包括有害生物综合治理、基于人工智能的预测系统、精准农业技术、气候智慧型农业方法以及遥感应用，作为在气候变化条件下增强农业韧性的潜在工具。研究结果表明，气候相关害虫风险的可持续管理需要多学科方法，整合气候信息、害虫监测、生态过程和先进决策支持技术。开发气候韧性、技术支撑和基于生态的害虫管理策略，对于保障农业生产力和长期全球粮食安全至关重要。","Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi","2026-09-09T00:00:00Z",{"impact":17,"substance":18,"depth":19,"authority":264,"freshness":101,"relevant":22,"comment":265},12,"系统综述气候变化对农业害虫生态机制与作物生产力的影响，并整合IPM、AI预测、精准农业与遥感等适应策略，对智慧植保与气候韧性农业有参考价值。",[267],{"name":261,"url":258},[27,28,29,269,270,130],"病虫害防控","气候变化",[272,273],"农业人工智能 病虫害防控 智慧农业 气候变化","农业人工智能 病虫害防控","农业人工智能病虫害防控智慧农业气候变化-2040","10.47495\u002Fokufbed.2000761",{"doi":275,"openalex_id":277,"authors":278,"venue":261,"cited_by_count":36,"oa_url":258,"card":282,"direction":50,"ingested_from":51},"W7212022123",[279],{"name":280,"orcid":281},"Ekrem ASLAN","https:\u002F\u002Forcid.org\u002F0000-0001-8829-7301",{"tldr":283,"method":284,"finding":285,"direction":48,"opportunity":286},"综述气候变化对农业害虫生态机制、作物生产力影响及气候适应策略。","文献综述，整合气候数据、害虫监测与AI预测、遥感等技术。","气候变暖扩大害虫分布、增加世代与危害，削弱生物防治，威胁粮食安全。","可构建融合气候、遥感与AI的害虫风险预警决策模型，填补多尺度动态预测空白。","2026-09-10T23:30:09.295781Z"]