[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"daily-2026-09-26":3},{"date":4,"title":5,"highlights":6,"content":13,"items":14},"2026-09-26","农业农村日报：AI赋能气候智慧农业与数字乡村",[7,8,9,10,11,12],"多篇论文聚焦AI在气候智慧农业中的落地，探讨AI建议作为强化层如何弥合农户意愿与实际行动的差距，并关注数据匮乏地区的气候适应决策支持。","数字乡村建设被证实影响农村人口迁移决策，同时社会服务可及性与绿色农业发展强度被揭示为提升农村老年福祉的关键路径。","面向小农户的AI农业咨询与诊断系统研究升温，涵盖技术架构、证据与部署优先级，并系统梳理农户对AI的认知、接受度与采纳障碍。","遥感与智能监测技术持续突破：OCO-3与ECOSTRESS联合观测生态系统水分利用效率，双物候加权法校正大豆物候估算时间偏差。","区块链与联邦学习融合框架被提出用于协作式智慧农场异常检测，数字全息与AI结合助力葡萄病害精准防控。","计算机视觉加速入侵性水生有害生物监测，加州蟹类毒素健康风险管理研究揭示生态保护与渔业经济的平衡难题。","本期汇编12篇前沿研究，覆盖AI农业咨询、气候适应决策、数字乡村与人口迁移、农村老年福祉、遥感物候监测、联邦学习与区块链安全、计算机视觉病虫害识别及渔业健康风险等方向，集中呈现智能技术驱动农业绿色转型与乡村治理的最新进展。\n\n---\n*本日报内容整理自公开来源，学术论文元数据来自 OpenAlex 等开放接口；外文资料已译为中文，翻译与摘要仅供参考；引用与决策请以官方原文与正式出版物为准。*",[15,77,119,155,191,257,296,331,380,412,456,516,551,584,630],{"id":16,"title":17,"url":18,"summary":19,"summary_zh":20,"content":21,"source_name":22,"source_url":18,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":27,"score_detail":28,"sources":36,"tags":41,"search_phrases":47,"slug":50,"view_count":51,"doi":52,"paper":53,"created_at":76},3470,"AI-generated advice as a reinforcement layer in climate-smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.landusepol.2026.108336","Climate-smart agricultural (CSA) practices are central to food-system decarbonisation, yet adoption often falls short of farmers’ stated intentions, weakening the impact of incentives and extension under capacity constraints. We test whether spatially targeted, AI-generated advice can narrow this intention-action gap in a randomised field experiment with 1529 row crop farmers in Iowa, Illinois and Indiana during the cover crop decision window. Farmers assigned to receive four AI-generated emails were 4.45 %age points more likely to plant cover crops than controls (z = 2.81, p = 0.005), despite high baseline intentions in both groups. Effects operated on the extensive margin: there was no detectable change in the share of land planted among adopters. Survey responses indicate high engagement and a shift from untested optimism to more calibrated trust after exposure. Supervised AI advice can provide a low-cost, scalable complement to existing extension, improving follow-through and modestly expanding uptake without displacing human expertise.","气候智慧型农业（CSA）实践是食品系统脱碳的核心，然而在能力受限的情况下，农户的实际采用往往低于其声称的意愿，削弱了激励措施和推广服务的效果。我们在爱荷华州、伊利诺伊州和印第安纳州开展了一项随机田间试验，覆盖1529名大田作物种植户，在覆盖作物决策窗口期测试了空间靶向的AI生成建议能否缩小这一意愿—行动差距。被分配接收四封AI生成电子邮件的农户种植覆盖作物的概率比对照组高4.45个百分点（z = 2.81，p = 0.005），尽管两组基线意愿均较高。效应体现在广延边际上：采用者中种植土地比例未检测到显著变化。调查回复表明参与度较高，且在接触建议后，农户从未经检验的乐观转向更为校准的信任。有监督的AI建议可作为现有推广服务的低成本、可扩展补充，改善后续落实并适度扩大采用，而不会取代人类专业知识。",null,"Land Use Policy","2026-09-24T00:00:00Z","论文",25,false,87,{"impact":29,"substance":30,"depth":31,"authority":32,"freshness":33,"relevant":34,"comment":35},22,23,19,14,9,1,"随机对照试验证实AI生成建议可低成本缩小农户意愿与行动差距，对智慧农业推广具参考价值。",[37,38],{"name":22,"url":18},{"name":39,"url":40},"Apollo","https:\u002F\u002Fdoi.org\u002F10.17863\u002Fcam.134741",[42,43,44,45,46],"智慧农业","农业人工智能","农业技术推广","覆盖作物","气候智慧农业",[48,49],"AI生成建议 覆盖作物","爱荷华 伊利诺伊 印第安纳 覆盖作物","AI生成建议覆盖作物-3470",0,"10.1016\u002Fj.landusepol.2026.108336",{"doi":52,"openalex_id":54,"authors":55,"venue":22,"cited_by_count":51,"oa_url":18,"card":68,"direction":74,"ingested_from":75},"W7214223143",[56,59,61,63,66],{"name":57,"orcid":58},"Callum Alexander","https:\u002F\u002Forcid.org\u002F0009-0007-5275-4583",{"name":60,"orcid":21},"Aiora Zabala",{"name":62,"orcid":21},"Andreas Kontoleon",{"name":64,"orcid":65},"Shalamar Armstrong","https:\u002F\u002Forcid.org\u002F0000-0002-1326-9936",{"name":67,"orcid":21},"Anuoluwa Sangotayo",{"tldr":69,"method":70,"finding":71,"direction":72,"opportunity":73},"随机试验检验AI生成建议能否缩小农户覆盖作物种植的意图-行动差距。","1529户美国中西部农户随机对照试验，四次AI生成邮件干预。","AI建议使覆盖作物种植率提高4.45个百分点，效果体现在是否采纳而非种植面积。","农业人工智能与决策模型","可探索AI建议与人工推广协同、长期持续效果及不同作物区域的异质性影响。","智慧农业 \u002F 农业物联网","openalex","2026-09-25T23:30:09.887867Z",{"id":78,"title":79,"url":80,"summary":81,"summary_zh":82,"content":21,"source_name":83,"source_url":80,"published_at":84,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":86,"score_detail":87,"sources":92,"tags":94,"search_phrases":98,"slug":101,"view_count":51,"doi":102,"paper":103,"created_at":118},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",10,86,{"impact":29,"substance":88,"depth":31,"authority":89,"freshness":90,"relevant":34,"comment":91},24,13,8,"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。",[93],{"name":83,"url":80},[42,43,95,96,97],"气候适应","遥感监测","早期预警",[99,100],"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":102,"openalex_id":104,"authors":105,"venue":21,"cited_by_count":51,"oa_url":111,"card":112,"direction":117,"ingested_from":75},"W7214097088",[106,108],{"name":107,"orcid":21},"H Heuristics",{"name":109,"orcid":110},"Hunter Hughes","https:\u002F\u002Forcid.org\u002F0009-0002-6161-9387","https:\u002F\u002Fessopenarchive.org\u002Fdoi\u002Fpdf\u002F10.22541\u002Fessoar.15009304\u002Fv1",{"tldr":113,"method":114,"finding":115,"direction":72,"opportunity":116},"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",{"id":120,"title":121,"url":122,"summary":123,"summary_zh":124,"content":21,"source_name":125,"source_url":122,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":86,"score_detail":126,"sources":129,"tags":131,"search_phrases":137,"slug":140,"view_count":51,"doi":141,"paper":142,"created_at":154},3457,"Social service accessibility and Green Agricultural Development Intensity as pathways to Rural Elderly Welfare: panel evidence from China’s underserved regions","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1863204","Background The elderly population in the rural areas of China, defined as 60 years or older, is over 121 million, representing 23.8% of the total rural population. The elderly population is growing rapidly and is characterized by the triple burden of poor access to healthcare, reduced agricultural income, and being digitally excluded. Although numerous national programs to expand social services and promote green agricultural transformation have been developed, the overall impact of these two policy streams on elderly wellbeing remains an untested area. This study aims to examine the independent and combined effects of social service accessibility (SSA) and Green Agricultural Development Intensity (GADI) on Rural Elderly Welfare (REW), while considering livelihood resilience (LR) as the mediating variable and the digital divide index (DDI) as the moderating condition. Both SSA and GADI are operationalized as province-level composite indices of service provision and agricultural development intensity, respectively, rather than as direct measures of individual elderly residents’ service use or farming behavior; this measurement level is made explicit throughout. Methods A panel data set was created, with the data collected at the provincial level and covering 30 provinces in China from 2013 to 2022 ( N = 268). Three province-year cells are missing because Tibet and Hainan entered the relevant statistical series after 2013, and a further 29 cells were dropped through listwise deletion of province-years with incomplete sub-indicators. The data was collected from the China Statistical Yearbooks, CNNIC internet reports, and the China Health and Retirement Longitudinal Study. The estimation results were based on two-way fixed-effects regression with interaction terms, and a bootstrap mediation analysis with 5,000 replications. The results were also checked for robustness through IV-2SLS estimation, winsorization, alternative specification for the dependent variable, excluding municipalities, and dynamic panel (system-GMM) estimation. Results SSA exerted a significant positive effect on REW ( β = 0.27, p \u003C 0.05), as did GADI ( β = 0.18, p \u003C 0.10). The SSA × GADI interaction was significant and positive ( β = 0.14, p \u003C 0.05), implying that the combined effect exceeds the additive effect of individual components. Livelihood resilience partially mediated both the SSA–REW pathway (indirect effect = 0.09, 95% CI [0.03, 0.16]) and the GADI–REW pathway (indirect effect = 0.06, 95% CI [0.01, 0.12]). Contrary to expectations, DDI failed to significantly moderate the relationship between GADI and REW ( β = −0.023, p = 0.412). Conclusion Coordinating social services with green agriculture was associated with wellbeing gains modestly but significantly greater than the sum of the two policy streams implemented in isolation. The synergy premium was estimated at 6% over the additive prediction (approximately 1–11% based on the 95% CI of the interaction coefficient), a pattern consistent with partial transmission through livelihood resilience. Interventions in the underserved rural areas should focus on integrated packages consisting of improved access to healthcare services and subsidies in green agriculture, rather than the two policy streams in isolation.","背景 中国农村60岁及以上老年人口超过1.21亿，占农村总人口的23.8%。老年人口增长迅速，且呈现出三重负担特征：医疗服务可及性差、农业收入减少以及被数字排斥。尽管国家已制定多项扩大社会服务和推动绿色农业转型的计划，但这两类政策对老年人福祉的总体影响仍是一个未经检验的领域。本研究旨在考察社会服务可及性（SSA）与绿色农业发展强度（GADI）对农村老年人福祉（REW）的独立效应和联合效应，同时将生计韧性（LR）作为中介变量、数字鸿沟指数（DDI）作为调节条件纳入考量。SSA和GADI分别被操作化为省级层面的服务供给和农业发展强度综合指数，而非个体老年居民服务使用或耕作行为的直接测量指标；这一测量层次在全文中有明确说明。方法 本研究构建了一个面板数据集，数据在省级层面收集，覆盖中国30个省份2013年至2022年（N = 268）。由于西藏和海南在2013年之后才进入相关统计序列，有3个省份-年份单元缺失；另有29个单元因省份-年份子指标不完整而通过列表删除法被剔除。数据来源于《中国统计年鉴》、CNNIC互联网报告和中国健康与养老追踪调查。估计结果基于带交互项的双向固定效应回归，以及重复5,000次的Bootstrap中介分析。研究还通过IV-2SLS估计、缩尾处理、因变量替代设定、剔除直辖市以及动态面板（系统GMM）估计对结果进行了稳健性检验。结果 SSA对REW具有显著正向效应（β = 0.27，p \u003C 0.05），GADI亦然（β = 0.18，p \u003C 0.10）。SSA × GADI交互项显著且为正（β = 0.14，p \u003C 0.05），表明联合效应超过各组成部分的加性效应。生计韧性部分中介了SSA–REW路径（间接效应 = 0.09，95% CI [0.03, 0.16]）和GADI–REW路径（间接效应 =","Frontiers in Sustainable Food Systems",{"impact":29,"substance":30,"depth":127,"authority":32,"freshness":33,"relevant":34,"comment":128},18,"基于30省十年面板数据，首次量化社会服务可及性与绿色农业发展强度对农村老年福祉的协同效应，方法扎实、结论有政策参考价值，值得进入每日精选。",[130],{"name":125,"url":122},[132,133,134,135,136],"数字乡村","绿色农业","数字鸿沟","农业社会化服务","农村养老",[138,139],"农村老年福祉 绿色农业 社会服务","中国农村 数字鸿沟 面板数据","农村老年福祉绿色农业社会服务-3457","10.3389\u002Ffsufs.2026.1863204",{"doi":141,"openalex_id":143,"authors":144,"venue":125,"cited_by_count":51,"oa_url":122,"card":149,"direction":117,"ingested_from":75},"W7214194964",[145,147],{"name":146,"orcid":21},"Linxin Wang",{"name":148,"orcid":21},"Fengyi Wang",{"tldr":150,"method":151,"finding":152,"direction":117,"opportunity":153},"用中国30省面板数据检验社会服务可及性与绿色农业发展强度对农村老年人福利的影响。","2013-2022年省级面板数据，双向固定效应、交互项与bootstrap中介检","两者均显著提升农村老年福利，且存在正向交互，生计韧性起部分中介作用。","可下沉到个体或村级数据，检验数字鸿沟调节下服务与绿色农业协同的微观福利机制。","2026-09-25T23:30:06.791118Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":160,"content":21,"source_name":125,"source_url":158,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":161,"score_detail":162,"sources":164,"tags":166,"search_phrases":171,"slug":174,"view_count":51,"doi":175,"paper":176,"created_at":190},3453,"The impact of digital village construction on rural population migration decisions","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1875724","Introduction With the widespread application of digital technologies such as big data and cloud computing in agriculture and rural areas, digital village construction has become a key initiative for promoting agricultural modernization and rural revitalization. Understanding how this process reshapes rural population mobility is therefore essential. This paper examines the impact of digital rural construction on rural residents’ migration decisions and identifies the underlying mechanisms. Methods We match household-level data from the 2020 China Rural Revitalization Survey (CRRS) with the county-level Digital Rural Index developed by Peking University, and estimate Logit models of the out-migration decision. A comprehensive battery of robustness checks is conducted, including alternative estimation models, sample restriction, exclusion of policy confounding, replacement of the core explanatory and dependent variables, omitted variable tests, and instrumental variable approaches. Mechanism and heterogeneity analyses are then performed. Results Digital rural construction significantly inhibits rural population out-migration, and this finding remains robust across all checks. The inhibitory effect is transmitted primarily through two mechanisms: encouraging non-agricultural business participation and expanding the scale of rural industries. The substitution effect arising from improved land resource allocation efficiency is weaker than the labor release effect of land transfer. The effect is more pronounced in eastern and western regions, among part-time farming and non-agricultural households, in non-mountainous areas, and among labor force groups aged 40 and above with junior secondary education or below. Digital rural construction also increases both the non-agricultural business income and the wage income of rural households. Discussion By uncovering the specific pathways and group-level heterogeneity through which digital village construction shapes migration decisions at the micro level, this study provides empirical evidence and policy implications for leveraging digitalization to promote local rural employment and advance urban–rural integrated development.","引言 随着大数据、云计算等数字技术在农业农村领域的广泛应用，数字乡村建设已成为推进农业现代化和乡村振兴的重要举措。理解这一过程如何重塑农村人口流动，因而至关重要。本文考察数字乡村建设对农村居民迁移决策的影响，并识别其内在机制。方法 本文将2020年中国乡村振兴调查（CRRS）的农户层面数据与北京大学发布的县域数字乡村指数进行匹配，估计农村人口外流决策的Logit模型。研究进行了一系列全面的稳健性检验，包括替代估计模型、样本限制、排除政策混杂因素、替换核心解释变量和被解释变量、遗漏变量检验以及工具变量方法。随后进行机制分析和异质性分析。结果 数字乡村建设显著抑制了农村人口外流，且这一发现在所有检验中均保持稳健。这种抑制效应主要通过两条机制传导：促进非农创业参与和扩大乡村产业规模。土地资源配置效率提升所带来的替代效应弱于土地流转的劳动力释放效应。该效应在东部和西部地区、兼业农户和非农户、非山区，以及40岁及以上、初中及以下学历的劳动力群体中更为明显。数字乡村建设还提高了农村家庭的非农经营收入和工资性收入。讨论 通过揭示数字乡村建设在微观层面影响迁移决策的具体路径和群体异质性，本研究为利用数字化促进农村本地就业、推进城乡融合发展提供了经验证据和政策启示。",84,{"impact":29,"substance":30,"depth":127,"authority":89,"freshness":90,"relevant":34,"comment":163},"基于CRRS与北大数字乡村指数的微观实证研究，机制与异质性分析扎实，对数字乡村就业政策有参考价值。",[165],{"name":125,"url":158},[167,132,168,169,170],"数字农业","乡村振兴","城乡融合","农村人口流动",[172,173],"中国乡村振兴调查 数字乡村指数","数字乡村建设 农村劳动力迁移","中国乡村振兴调查数字乡村指数-3453","10.3389\u002Ffsufs.2026.1875724",{"doi":175,"openalex_id":177,"authors":178,"venue":125,"cited_by_count":51,"oa_url":158,"card":185,"direction":117,"ingested_from":75},"W7214148499",[179,181,183],{"name":180,"orcid":21},"Deshan Li",{"name":182,"orcid":21},"Shuangqiang Li",{"name":184,"orcid":21},"Fengming Li",{"tldr":186,"method":187,"finding":188,"direction":117,"opportunity":189},"数字乡村建设显著抑制农村人口外流，并揭示其作用机制与群体异质性。","匹配2020年CRRS农户数据与北大县域数字乡村指数，构建Logit模型。","数字乡村建设通过促进非农创业和扩大乡村产业规模抑制外迁，且效应存在区域与群体差异。","可探究数字乡村抑制外迁的长期动态效应及对城乡收入差距的反馈机制。","2026-09-25T23:30:06.381563Z",{"id":192,"title":193,"url":194,"summary":195,"summary_zh":196,"content":21,"source_name":197,"source_url":194,"published_at":198,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":199,"score_detail":200,"sources":203,"tags":205,"search_phrases":211,"slug":214,"view_count":51,"doi":215,"paper":216,"created_at":256},3507,"OCO‐3 Meets ECOSTRESS: Insights Into Ecosystem Diurnal Water‐Use Efficiency From Co‐Located Solar‐Induced Fluorescence and Thermal Observations","https:\u002F\u002Fdoi.org\u002F10.1029\u002F2026gl124105","Abstract Terrestrial ecosystem regulation of carbon and water fluxes is critical for constraining climate–biosphere feedbacks but remains poorly quantified across space and time. Here, we evaluate whether co‐located observations from NASA's Orbiting Carbon Observatory‐3 (OCO‐3) and the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) can reproduce ecosystem water use efficiency (WUE) dynamics observed at FLUXNET sites across temporal scales, vegetation types, climates, and drought conditions. We created the ECOCO3 data set, which harmonizes OCO‐3 and ECOSTRESS observations in space and time. ECOCO3 captures broad seasonal and diurnal carbon and water flux patterns including midday drought responses. Sampling sensitivity analysis shows that ECOCO3 is primarily limited by available sample size for distinguishing vegetation and climate driven differences in WUE. Our findings highlight both the promise and limitations of remote sensing for resolving sub‐daily carbon–water coupling.","陆地生态系统对碳通量和水通量的调节对于约束气候–生物圈反馈至关重要，但在空间和时间尺度上仍缺乏充分的量化。在此，我们评估了来自NASA轨道碳观测站-3（OCO-3）和空间站生态系统星载热辐射计实验（ECOSTRESS）的同位观测能否在时间尺度、植被类型、气候条件和干旱状况下重现FLUXNET站点观测到的生态系统水分利用效率（WUE）动态。我们创建了ECOCO3数据集，该数据集在空间和时间上协调了OCO-3和ECOSTRESS的观测。ECOCO3能够捕捉广泛的季节性和日间碳通量与水通量模式，包括正午干旱响应。采样敏感性分析表明，ECOCO3主要受限于可用样本量，难以区分植被和气候驱动的WUE差异。我们的研究结果既凸显了遥感在解析亚日尺度碳–水耦合方面的前景，也揭示了其局限性。","Geophysical Research Letters","2026-09-23T00:00:00Z",81,{"impact":127,"substance":29,"depth":127,"authority":201,"freshness":90,"relevant":34,"comment":202},15,"NASA两颗卫星协同观测提升生态系统碳水耦合监测能力，方法新颖、数据可靠，对农业遥感与水资源管理有参考价值。",[204],{"name":197,"url":194},[206,207,208,209,210],"农业遥感","遥感","水资源利用","生态监测","碳汇",[212,213],"OCO-3 ECOSTRESS 水分利用效率","ECOCO3 数据集 碳水通量","OCO-3ECOSTRESS水分利用效率-3507","10.1029\u002F2026gl124105",{"doi":215,"openalex_id":217,"authors":218,"venue":197,"cited_by_count":51,"oa_url":249,"card":250,"direction":254,"ingested_from":75},"W7214122316",[219,222,225,228,231,234,237,240,243,246],{"name":220,"orcid":221},"Zoe Pierrat","https:\u002F\u002Forcid.org\u002F0000-0002-6726-2406",{"name":223,"orcid":224},"Thomas P. Kurosu","https:\u002F\u002Forcid.org\u002F0000-0003-2555-7780",{"name":226,"orcid":227},"Abhishek Chatterjee","https:\u002F\u002Forcid.org\u002F0000-0002-3680-0160",{"name":229,"orcid":230},"Joshua B. Fisher","https:\u002F\u002Forcid.org\u002F0000-0003-4734-9085",{"name":232,"orcid":233},"Margaret C. Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1481-9706",{"name":235,"orcid":236},"Le Kuai","https:\u002F\u002Forcid.org\u002F0000-0001-6406-1150",{"name":238,"orcid":239},"Kaniska Mallick","https:\u002F\u002Forcid.org\u002F0000-0002-2735-930X",{"name":241,"orcid":242},"Nicholas Cody Parazoo","https:\u002F\u002Forcid.org\u002F0000-0002-4424-7780",{"name":244,"orcid":245},"Benjamin C. Wiebe","https:\u002F\u002Forcid.org\u002F0000-0002-9325-1540",{"name":247,"orcid":248},"Kerry A. Cawse-Nicholson","https:\u002F\u002Forcid.org\u002F0000-0002-0510-4066","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1029\u002F2026GL124105",{"tldr":251,"method":252,"finding":253,"direction":254,"opportunity":255},"融合OCO-3与ECOSTRESS观测评估生态系统日间水分利用效率动态。","构建ECOCO3数据集，结合FLUXNET站点验证与采样敏感性分析。","ECOCO3能捕捉季节与日间碳-水通量模式，但样本量限制其区分植被与气候差异。","农业遥感与作物表型","可探索多源遥感融合提升亚日尺度碳水耦合估算精度，并扩展至农田生态系统。","2026-09-25T23:30:33.881463Z",{"id":258,"title":259,"url":260,"summary":261,"summary_zh":262,"content":21,"source_name":263,"source_url":260,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":199,"score_detail":264,"sources":266,"tags":268,"search_phrases":272,"slug":275,"view_count":51,"doi":276,"paper":277,"created_at":295},3501,"A Dual-Phenological-Characteristic Weighting Method to Reconcile Time Discrepancies in Soybean Phenology Estimation from MODIS NDVI Time Series","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193300","Accurate large-scale monitoring of crop phenology is essential for optimizing agricultural management. Remote sensing has been widely used for estimating crop phenological stages, yet time discrepancies often exist between remotely sensed phenological metrics and ground-observed growth stages. Moreover, phenological parameters derived from different characterization models exhibit varying degrees of deviation from field observations. The primary goal of this study was to develop a novel method that fully exploits the deviation patterns of diverse phenological parameters to enhance the accuracy of soybean phenology retrieval. To this end, we extracted 11 phenological parameters for six key growth stages—emerged, blooming, pod-setting, turning yellow, dropping leaf, and harvest—of soybean across 16 U.S. states using MODIS NDVI (normalized difference vegetation index) time-series data from 2000 to 2020, employing GU-, curvature-, and derivative-based phenological modeling methods. The study design centered on proposing a dual-phenological-characteristic weighting (DPCW) method that leverages the deviation features of different phenological parameters relative to ground-observed growth stages, generating composite phenological characteristics by pairing two distinct parameters. The key innovation of this paper is the use of dual-feature weighting to improve the correspondence between satellite-derived phenometrics and field observations, offering an alternative to conventional phenological estimation. The results demonstrated that the optimal DPCW-based combinations for the six growth stages were SOS (start of season) and GREEN, SOS and POS (peak of season), MATURITY and POS, EOS (end of season) and SENES (senescence), RD (recession date) and DD (downturn date), and EOS and DORM (dormancy), respectively. The coefficient of determination (R2) between the retrieved transition dates and ground observations exceeded 0.65 for most stages, with the emerged stage improving to 0.47 from 0.052 and 0.357 of the unadjusted and offset-adjusted benchmarks. The average root mean square error (RMSE) was less than 5 days in most cases, representing a reduction of over 40%, with the most substantial improvement at the turning yellow stage, where RMSE dropped from 12.8 days to 2.8 days. A strength of this study lies in its multi-state, multi-decade validation, demonstrating the robustness and temporal consistency of the DPCW method within the major U.S. soybean-growing region. However, a limitation is that the method’s performance may vary with different satellite sensors or crop types, warranting further investigation. The proposed approach is expected to enhance the accuracy of remote sensing-based crop phenology monitoring and offers an effective alternative for calibrating remotely sensed phenological parameters.","准确的大尺度作物物候监测对于优化农业管理至关重要。遥感已被广泛用于估算作物物候阶段，但遥感物候指标与地面观测生育阶段之间常存在时间差异。此外，不同特征化模型衍生的物候参数与田间观测之间存在不同程度的偏差。本研究的主要目标是开发一种新方法，充分利用多种物候参数的偏差模式，以提高大豆物候反演精度。为此，我们利用2000—2020年MODIS NDVI（归一化差异植被指数）时间序列数据，采用基于GU、曲率和导数的方法提取了美国16个州大豆六个关键生育阶段——出苗、开花、结荚、黄化、落叶和收获——的11个物候参数。研究设计的核心是提出一种双物候特征加权（dual-phenological-characteristic weighting，DPCW）方法，该方法利用不同物候参数相对于地面观测生育阶段的偏差特征，通过配对两个不同参数生成复合物候特征。本文的关键创新在于利用双特征加权提高卫星衍生物候指标与田间观测之间的对应关系，为传统物候估算提供了一种替代方案。结果表明，六个生育阶段基于DPCW的最优组合分别为SOS（生长季开始）与GREEN、SOS与POS（生长季峰值）、MATURITY与POS、EOS（生长季结束）与SENES（衰老）、RD（衰退日期）与DD（下降日期）以及EOS与DORM（休眠）。反演得到的转换日期与地面观测之间的决定系数（R²）在大多数阶段超过0.65，其中出苗阶段从基准的0.052和偏移调整后的0.357提高至0.47。大多数情况下平均均方根误差（RMSE）小于5天，降幅超过40%，其中黄化阶段改善最为显著，RMSE从12.8天降至2.8天。本研究的一个优势在于其多州、多年代际验证，证明了DPCW方法在美国主要大豆种植区内的稳健性和时间一致性。","Remote Sensing",{"impact":127,"substance":29,"depth":127,"authority":32,"freshness":33,"relevant":34,"comment":265},"提出双物候特征加权方法，用MODIS NDVI长时序数据校正大豆物候遥感估算偏差，方法新颖、验证扎实，对农情遥感监测有参考价值。",[267],{"name":263,"url":260},[42,269,270,207,271],"大豆","农情监测","作物表型",[273,274],"MODIS NDVI 大豆 物候","美国大豆 遥感 物候监测","MODISNDVI大豆物候-3501","10.3390\u002Frs18193300",{"doi":276,"openalex_id":278,"authors":279,"venue":263,"cited_by_count":51,"oa_url":260,"card":290,"direction":254,"ingested_from":75},"W7214203102",[280,282,285,288],{"name":281,"orcid":21},"Qiuxiang Yi",{"name":283,"orcid":284},"Siting Chen","https:\u002F\u002Forcid.org\u002F0000-0003-3468-9320",{"name":286,"orcid":287},"Fumin Wang","https:\u002F\u002Forcid.org\u002F0000-0002-5078-358X",{"name":289,"orcid":21},"Qinyan Zhu",{"tldr":291,"method":292,"finding":293,"direction":254,"opportunity":294},"提出双物候特征加权法，校正MODIS NDVI大豆物候估计与地面观测的时间偏差。","用MODIS NDVI 2000-2020数据，结合GU、曲率、导数三类物候模型","多数生育期R²超0.65，RMSE多小于5天，降幅超40%，转黄期RMSE从12.8天降至2.8天。","可将该加权校正思路迁移到其他作物与多源遥感数据，并探索自适应权重与深度学习融合的物候反演。","2026-09-25T23:30:31.075499Z",{"id":297,"title":298,"url":299,"summary":300,"summary_zh":301,"content":21,"source_name":302,"source_url":299,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":199,"score_detail":303,"sources":305,"tags":307,"search_phrases":311,"slug":314,"view_count":51,"doi":315,"paper":316,"created_at":330},3471,"A secure federated learning framework with blockchain-based authentication for anomaly detection in cooperative smart farming","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.engappai.2026.116072","Agriculture is still a crucial global pillar of the world economy, ensuring food security and livelihood. But changing climate conditions and increasing reliance on the Internet of Things (IoT) based precision agriculture have brought new challenges, mainly cybersecurity. Cooperative Smart Farming (CSF) schemes promote resource pooling among small farmers and thus, the adoption of cutting-edge technologies. Although democratizing precision farming also makes it more accessible to cyber threats. To sort out all these problems, the proposed method introduces a secure federated learning framework along with blockchain-based authentication for anomaly detection in CSFs. The proposed method employs a federated transfer learning-based shadow attention mechanism, in conjunction with the Zeiler and Fergus network, to amplify the performance of the anomaly detection technique. This allows farms to detect threats in premises while protecting data privacy, as only model updates that are encrypted are transmitted. A blockchain-backed decentralized authentication scheme based on the proof of authentication consensus protocol is built to provide trust and resistance to tampering. Moreover, the random k-sparsification technique with changing rank adjustment has a positive impact on communication efficiency, which results in the same level of accuracy but with less communication overhead. The proposed method is executed on four datasets, CSE-CIS-IDS2018, MQTTset, ToN-IoT, and Edge IoT, achieving classification accuracies of 99.99%,99.93%,99.94%, and 99.91%, respectively, and it performs better than the current techniques. This comprehensive framework provides a scalable and trusted method for anomaly detection in CSFs, enabling resilient, privacy-preserving, and intelligent smart farming ecosystems.","农业仍然是全球经济的重要支柱，保障着粮食安全和生计。然而，不断变化的气候条件以及日益依赖基于物联网（IoT）的精准农业，带来了新的挑战，主要是网络安全问题。合作智慧农业（Cooperative Smart Farming, CSF）方案促进了小农户之间的资源共享，从而推动了前沿技术的采用。尽管精准农业的民主化使其更加普及，但也使其更容易受到网络威胁。为解决上述问题，所提出的方法引入了一种安全的联邦学习框架，并结合基于区块链的身份验证，用于CSF中的异常检测。所提出的方法采用基于联邦迁移学习的阴影注意力机制，结合Zeiler和Fergus网络，以提升异常检测技术的性能。这使得农场能够在本地检测威胁，同时保护数据隐私，因为仅传输加密的模型更新。构建了一种基于认证证明共识协议的区块链支持的去中心化身份验证方案，以提供信任和防篡改能力。此外，具有变化秩调整的随机k稀疏化技术对通信效率产生了积极影响，在保持相同精度的同时减少了通信开销。所提出的方法在四个数据集CSE-CIS-IDS2018、MQTTset、ToN-IoT和Edge IoT上执行，分别达到了99.99%、99.93%、99.94%和99.91%的分类准确率，且性能优于当前技术。该综合框架为CSF中的异常检测提供了一种可扩展且可信的方法，实现了具有韧性、隐私保护和智能化的智慧农业生态系统。","Engineering Applications of Artificial Intelligence",{"impact":127,"substance":29,"depth":127,"authority":32,"freshness":33,"relevant":34,"comment":304},"提出联邦学习与区块链认证结合的农业异常检测框架，在四个数据集上验证高精度，方法新颖且具产业应用潜力，值得入选每日精选。",[306],{"name":302,"url":299},[42,43,308,309,310],"联邦学习","区块链","物联网安全",[312,313],"联邦学习 区块链 异常检测","协同智慧农业 物联网安全","联邦学习区块链异常检测-3471","10.1016\u002Fj.engappai.2026.116072",{"doi":315,"openalex_id":317,"authors":318,"venue":302,"cited_by_count":51,"oa_url":299,"card":325,"direction":74,"ingested_from":75},"W7214230618",[319,321,323],{"name":320,"orcid":21},"Ramesh Pandharinath Daund",{"name":322,"orcid":21},"Mohammad Junedul Haque",{"name":324,"orcid":21},"Prof. Umesh B. Pawar",{"tldr":326,"method":327,"finding":328,"direction":74,"opportunity":329},"提出融合联邦迁移学习与区块链认证的异常检测框架，保障协作智慧农业数据隐私与安全。","联邦迁移学习、影子注意力机制、Zeiler-Fergus网络、区块链认证、随机k","在四个IoT数据集上分类准确率均超99.9%，且通信开销更低，优于现有方法。","可探索轻量级区块链共识与联邦学习在资源受限农业边缘设备上的能效与实时性优化。","2026-09-25T23:30:09.960528Z",{"id":332,"title":333,"url":334,"summary":335,"summary_zh":336,"content":21,"source_name":337,"source_url":334,"published_at":198,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":339,"sources":341,"tags":343,"search_phrases":347,"slug":350,"view_count":51,"doi":351,"paper":352,"created_at":379},3513,"Accelerated development and deployment of computer vision models for invasive aquatic pests","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72212-8","Abstract Aquatic non-indigenous species (NIS) incur significant cultural, environmental and economic costs worldwide, and human surveillance is expensive and impractical at large scales. Computer vision models (CVMs) deployed on remote and autonomous vehicles can reduce the burden on trained human observers, but aquatic environments present unique challenges and lack frameworks for biosecurity-focused development and deployment. We present a practical framework for developing and deploying new species-specific CVMs for real-time use across surface vessel and remote vehicle platforms. We demonstrate the utility of our framework through its application to several taxonomically and ecologically diverse NIS in New Zealand: Mediterranean fanworm Sabella spallanzanii , South African oxygen weed Lagarosiphon major, and exotic Caulerpa ( Caulerpa brachypus and C. parvifolia ). For S. spallanzanii , we demonstrate efficient training from small datasets and deployment for real-time detection. Using exotic Caulerpa , we show how CVMs can be rapidly improved during an early incursion response. For L. major , standardised field validation methods enable the comparison of CVM and human detection rates across diverse locations and operating conditions. Collectively, these case studies demonstrate that our framework enables accurate detection and the robust assessment of model effectiveness under realistic field conditions and can be effectively applied to imagery from multiple platforms.","摘要 水生外来非本土物种（NIS）在全球范围内造成显著的文化、环境和经济损失，而人工监测成本高昂且难以大规模实施。部署在远程和自主载具上的计算机视觉模型（CVM）可减轻对训练有素的人类观察者的依赖，但水生环境面临独特挑战，且缺乏以生物安全为重点的开发和部署框架。我们提出了一个实用框架，用于开发和部署新的物种特异性CVM，以在水面船只和远程载具平台上实时使用。我们通过将该框架应用于新西兰多个在分类学和生态学上具有多样性的NIS来展示其效用：地中海缨鳃虫 Sabella spallanzanii、南非氧草 Lagarosiphon major 以及外来Caulerpa（Caulerpa brachypus 和 C. parvifolia）。对于 S. spallanzanii，我们展示了从小型数据集进行高效训练并部署用于实时检测。利用外来Caulerpa，我们展示了CVM如何在入侵早期响应期间快速改进。对于 L. major，标准化野外验证方法使得能够在不同地点和操作条件下比较CVM与人类检测率。总体而言，这些案例研究表明，我们的框架能够在现实野外条件下实现准确检测和对模型有效性的稳健评估，并可有效应用于来自多个平台的图像。","Scientific Reports",80,{"impact":127,"substance":29,"depth":127,"authority":32,"freshness":90,"relevant":34,"comment":340},"提出面向水生入侵物种的计算机视觉模型开发与部署框架，含多物种实地验证，方法新颖且具生物安全应用价值，但属新西兰案例，对国内农业信息化影响有限。",[342],{"name":337,"url":334},[42,43,344,345,346],"计算机视觉","入侵物种监测","水生生物安全",[348,349],"新西兰 入侵水生物种 计算机视觉","Caulerpa 实时检测 模型","新西兰入侵水生物种计算机视觉-3513","10.1038\u002Fs41598-026-72212-8",{"doi":351,"openalex_id":353,"authors":354,"venue":337,"cited_by_count":51,"oa_url":373,"card":374,"direction":117,"ingested_from":75},"W7214089404",[355,358,360,362,364,367,370],{"name":356,"orcid":357},"Rose A. Pearson","https:\u002F\u002Forcid.org\u002F0000-0002-4700-2113",{"name":359,"orcid":21},"Gareth Preston",{"name":361,"orcid":21},"Jeremy Bulleid",{"name":363,"orcid":21},"Svenja David",{"name":365,"orcid":366},"Felix Vaux","https:\u002F\u002Forcid.org\u002F0000-0002-2882-7996",{"name":368,"orcid":369},"Daniel Clements","https:\u002F\u002Forcid.org\u002F0000-0001-9319-5588",{"name":371,"orcid":372},"Leigh W. Tait","https:\u002F\u002Forcid.org\u002F0000-0001-9153-139X","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72212-8_reference.pdf",{"tldr":375,"method":376,"finding":377,"direction":72,"opportunity":378},"提出一套开发与部署水生入侵物种计算机视觉模型的实用框架，并在新西兰三种入侵物种上验证。","基于水面船与遥控平台图像，小数据集训练、实时检测与标准化野外验证。","框架能实现实时准确检测，并在真实野外条件下稳健评估模型效果。","可迁移至农业入侵生物监测，探索小样本跨平台模型与野外标准化评估体系。","2026-09-25T23:30:42.003495Z",{"id":381,"title":382,"url":383,"summary":384,"summary_zh":385,"content":21,"source_name":386,"source_url":383,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":387,"sources":389,"tags":391,"search_phrases":393,"slug":396,"view_count":51,"doi":397,"paper":398,"created_at":411},3512,"AI-Driven Agricultural Advisory and Diagnostic Systems for Smallholder Farming: Technical Architectures, Evidence and Deployment Priorities for North-East India","https:\u002F\u002Fdoi.org\u002F10.9734\u002Farja\u002F2026\u002Fv19i4919","Artificial intelligence (AI) is being introduced into agricultural advisory services through machine learning, computer vision, conversational large language models, retrieval-augmented generation and multimodal interfaces. For smallholder farming, the central question is not whether these technologies can produce technically plausible outputs, but whether they can provide locally correct, actionable and safe recommendations under heterogeneous agronomic, linguistic and connectivity conditions. This critical narrative review integrates evidence on digital extension, AI-enabled agricultural advice, image-based diagnosis and responsible digital agriculture, with particular reference to North-East India. Literature published from 1 January 2010 to 17 July 2026 was considered, with emphasis on peer-reviewed field evaluations, technical validation studies, reviews and regionally relevant research. Evidence from digital extension provides the strongest causal baseline: mobile and personalised advisory services frequently improve information recall, agronomic knowledge and adoption of recommended practices, yet effects on yield, profit and welfare are inconsistent. Recent generative-AI studies show that large language models can produce useful agricultural responses, but site-specific rates, timing and local practice remain recurrent failure points. Retrieval grounding and expert feedback improve local relevance, although multi-season farm-level effectiveness evidence remains scarce. Image-based plant-disease systems achieve high accuracy in curated datasets, but performance can deteriorate sharply under field domain shift, class novelty and variable image quality. North-East Indian studies of mobile advisory systems in Meghalaya, Nagaland and Tripura demonstrate a valuable institutional foundation based on interactive voice response, local expert networks and user-centred service design; they do not, however, establish the effectiveness of autonomous AI. The most defensible deployment model is therefore an offline-tolerant, multilingual, multimodal and human-supervised architecture that grounds recommendations in curated regional knowledge, represents uncertainty, preserves provenance and escalates high-risk or out-of-distribution cases. Future research should prioritise prospective district- and season-spanning evaluations that connect model quality to farmer decisions, agronomic outcomes, equity, safety and cost-effectiveness.","人工智能（AI）正通过机器学习、计算机视觉、对话式大语言模型、检索增强生成和多模态界面被引入农业咨询服务。对于小农户而言，核心问题不在于这些技术能否产生技术上看似合理的输出，而在于它们能否在异质的农艺、语言和网络连接条件下提供本地正确、可操作且安全的建议。本批判性叙事综述整合了数字推广、AI赋能的农业建议、基于图像的诊断和负责任数字农业方面的证据，并特别关注印度东北部。本文考察了2010年1月1日至2026年7月17日期间发表的文献，重点关注同行评议的田间评估、技术验证研究、综述及区域相关研究。来自数字推广的证据提供了最强的因果基线：移动化和个性化咨询服务经常改善信息记忆、农艺知识和对推荐措施的采纳，但对产量、利润和福利的影响并不一致。近期生成式AI研究表明，大语言模型能够产生有用的农业回答，但针对具体地点的用量、时机和本地实践仍是反复出现的失败点。检索 grounding 和专家反馈可提高本地相关性，但多季农场层面的有效性证据仍然稀缺。基于图像的植物病害系统在精选数据集上达到高准确率，但在田间域偏移、类别新颖性和图像质量多变的情况下，性能可能急剧下降。印度东北部在梅加拉亚邦、那加兰邦和特里普拉邦开展的移动咨询系统研究展示了基于交互式语音应答、本地专家网络和以用户为中心的服务设计的宝贵制度基础；然而，这些研究并未确立自主AI的有效性。因此，最可辩护的部署模式是一种容忍离线、多语言、多模态且有人工监督的架构，该架构将建议建立在精选的区域知识之上，表征不确定性，保留来源信息，并对高风险或分布外案例进行升级处理。未来研究应优先开展前瞻性的跨区县和跨季节评估，将模型质量与农户决策、农艺结果、公平性、安全性和成本效益联系起来。","Asian Research Journal of Agriculture",{"impact":127,"substance":29,"depth":127,"authority":89,"freshness":33,"relevant":34,"comment":388},"系统综述AI农业咨询与诊断系统在印度东北小农场景的技术架构与落地证据，指出人机协同、离线多语言与检索增强是可行路径，对智慧农业落地有参考价值。",[390],{"name":386,"url":383},[132,42,43,44,392],"小农户",[394,395],"印度东北部 农业AI 小农户","农业智能诊断 多语言 离线","印度东北部农业AI小农户-3512","10.9734\u002Farja\u002F2026\u002Fv19i4919",{"doi":397,"openalex_id":399,"authors":400,"venue":386,"cited_by_count":51,"oa_url":383,"card":406,"direction":117,"ingested_from":75},"W7214205238",[401,403],{"name":402,"orcid":21},"Pravangkar Boruah",{"name":404,"orcid":405},"Rubul Kumar Bania","https:\u002F\u002Forcid.org\u002F0000-0001-6294-0231",{"tldr":407,"method":408,"finding":409,"direction":72,"opportunity":410},"综述AI农业咨询与诊断系统，聚焦印度东北小农，提出人监督多模态部署架构。","批判性叙述综述，整合2010-2026年数字推广、生成式AI与图像诊断证据。","AI输出技术可行但本地化、安全与田间效果证据不足，需人监督与检索增强。","可开展跨区跨季前瞻评估，连接模型质量与农户决策、产量、公平及成本效益。","2026-09-25T23:30:39.745514Z",{"id":413,"title":414,"url":415,"summary":416,"summary_zh":417,"content":21,"source_name":418,"source_url":415,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":419,"sources":421,"tags":423,"search_phrases":426,"slug":429,"view_count":51,"doi":430,"paper":431,"created_at":455},3469,"ARTIFICIAL INTELLIGENCE FOR AGRICULTURE: A SYSTEMATIC REVIEW OF FARMERS' PERCEPTIONS, ACCEPTANCE, ADOPTION AND BARRIERS","https:\u002F\u002Fdoi.org\u002F10.64013\u002Fbbasrjlifess.v2026i1.70","Artificial intelligence (AI) is rapidly reshaping agriculture, enabling the application of data for efficient decision-making, precision farming, crop monitoring, pest management, disease detection, smart irrigation, yield prediction, and various aspects of farm automation. Yet, to successfully gain a foothold in farms, factors like farmers' perceptions, their acceptance, desire, and readiness to adopt, as well as the capability to surmount socioeconomic, technological, and institutional challenges, must also make a difference. This article systematically collates the available information on farmers' perspectives on, acceptance of, readiness to adopt, and the obstacles related to AI in the agricultural context. The PRISMA 2020 guideline has been followed to select studies that are related, evaluated for inclusion, and finally, per the criteria, combined into a systematic synthesis. The review mainly discusses the aspects that influence the use of AI, like perceived usefulness, ease of use, trust, digital literacy, affordability, farm size, socioeconomic characteristics, availability of digital infrastructure, and access to agricultural technical advisory services. Main challenges identified involve the high cost of implementing AI, poor connectivity, weak rural infrastructure, low levels of technological knowledge, unavailability of support services, concerns about data privacy, distrust of algorithmic bias, language barriers, and inequalities impacting smallholder farmers. Besides barriers, the review indicates the potential of leveraging AI through extension services, agricultural mobile apps, precision farming, climate-smart agriculture, early-warning systems, and tailored farm advisories. By drawing out technical, behavioral, socioeconomic, and institutional perspectives, the review pinpoints important research questions and presents a farmholder-oriented setup to explain the process of taking up AI in farming. The outcomes can be used by scientific experts, policymakers, extension personnel, and software developers to create low-cost, reliable, and accessible AI systems aimed at promoting sustainable agricultural development.","人工智能（AI）正迅速重塑农业，使数据得以应用于高效决策、精准农业、作物监测、病虫害管理、病害检测、智能灌溉、产量预测以及农场自动化的各个方面。然而，要在农场中成功立足，农民的认知、接受度、采用意愿和准备程度，以及克服社会经济、技术和制度挑战的能力，同样至关重要。本文系统梳理了现有关于农民对农业领域人工智能的看法、接受度、采用准备程度及相关障碍的信息。研究遵循PRISMA 2020指南，筛选相关研究，评估其纳入资格，并最终依据标准进行系统性综合。综述主要探讨了影响人工智能使用的因素，包括感知有用性、易用性、信任、数字素养、可负担性、农场规模、社会经济特征、数字基础设施的可用性以及农业技术咨询服务的获取。识别出的主要挑战包括人工智能实施成本高昂、网络连接不佳、农村基础设施薄弱、技术水平低下、支持服务缺乏、数据隐私担忧、对算法偏见的疑虑、语言障碍以及影响小农户的不平等问题。除障碍外，综述还指出了通过推广服务、农业移动应用、精准农业、气候智慧型农业、预警系统和定制化农场咨询来利用人工智能的潜力。通过梳理技术、行为、社会经济和制度层面的视角，本综述指出了重要的研究问题，并提出了一个以农场主为导向的框架，以解释在农业中采用人工智能的过程。研究结果可供科学专家、政策制定者、推广人员和软件开发者用于创建低成本、可靠且可及的人工智能系统，以促进可持续农业发展。","Journal of Life and Social Sciences",{"impact":127,"substance":29,"depth":127,"authority":89,"freshness":33,"relevant":34,"comment":420},"基于PRISMA的系统综述，系统梳理农户对AI的认知、接受度与采纳障碍，对智慧农业推广与政策设计有实质参考价值。",[422],{"name":418,"url":415},[42,43,424,425,392],"数字素养","农户采纳",[427,428],"农民 AI 采纳 障碍","农业人工智能 系统综述","农民AI采纳障碍-3469","10.64013\u002Fbbasrjlifess.v2026i1.70",{"doi":430,"openalex_id":432,"authors":433,"venue":418,"cited_by_count":51,"oa_url":415,"card":450,"direction":74,"ingested_from":75},"W7214189410",[434,436,438,440,442,444,446,448],{"name":435,"orcid":21},"MM JAMEEL",{"name":437,"orcid":21},"M SAEED",{"name":439,"orcid":21},"SA SHER",{"name":441,"orcid":21},"Z ALI",{"name":443,"orcid":21},"Q HAYYAT",{"name":445,"orcid":21},"S KIRBAG",{"name":447,"orcid":21},"S KHAN",{"name":449,"orcid":21},"HN AHMAD",{"tldr":451,"method":452,"finding":453,"direction":117,"opportunity":454},"系统综述农民对农业AI的感知、接受度、采纳意愿及障碍。","遵循PRISMA 2020指南，系统筛选并综合相关文献。","成本、基础设施、数字素养与信任是主要障碍，小农户受影响最大。","可研究低成本、本地化AI采纳模型及小农户数字包容机制。","2026-09-25T23:30:09.670568Z",{"id":457,"title":458,"url":459,"summary":460,"summary_zh":461,"content":21,"source_name":462,"source_url":459,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":463,"sources":465,"tags":467,"search_phrases":471,"slug":474,"view_count":51,"doi":475,"paper":476,"created_at":515},3467,"Smart agriculture using digital holography and artificial intelligence","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1871510","In viticulture, direct protection against downy and powdery mildews relies on the preventive application of fungicides, requiring growers to anticipate infection events. Decision-making is mainly supported by forecasting models driven by weather predictions. However, these decisions are inherently uncertain, as some treatments ultimately prove unnecessary, although this information only becomes available retrospectively from observed conditions. This study explores the integration of an advanced spore detection device to better target fungicide applications in vineyards, aiming to reduce the use of phytosanitary products while maintaining high grape quality. The stand-alone device uses digital holography combined with artificial intelligence (AI) for detecting and classifying airborne spores of both downy and powdery mildew. It enables the tracking of disease dynamics as well as the assessment of environmental conditions and treatment effects on spore counts. Two case studies with real-time data access in Changins, Switzerland and Château le Puy, France, are presented and revealed promising strategies for substantial reductions in fungicide use while maintaining effective disease control.","在葡萄栽培中，对霜霉病和白粉病的直接防护依赖于杀菌剂的预防性施用，这要求种植者预判侵染事件的发生。决策主要依靠由天气预报驱动的预测模型来支持。然而，这些决策本质上具有不确定性，因为有些处理最终被证明是不必要的，尽管这一信息只能通过观测条件回顾性地获得。本研究探索了集成先进孢子检测装置以更精准地指导葡萄园杀菌剂施用的方法，旨在减少植物检疫产品的使用，同时保持葡萄的高品质。该独立装置利用数字全息术结合人工智能（AI）来检测和分类空气中的霜霉病和白粉病孢子。它能够追踪病害动态，并评估环境条件和处理措施对孢子数量的影响。本文介绍了在瑞士Changins和法国Château le Puy进行的两个可实时获取数据的案例研究，并揭示了在保持有效病害控制的同时大幅减少杀菌剂用量的有前景的策略。","Frontiers in Plant Science",{"impact":127,"substance":29,"depth":127,"authority":32,"freshness":90,"relevant":34,"comment":464},"数字全息结合AI检测葡萄病害孢子，为减少杀菌剂施用提供实证案例，方法新颖且具推广价值。",[466],{"name":462,"url":459},[42,43,468,469,470],"精准施药","葡萄种植","病害预警",[472,473],"数字全息 孢子检测 葡萄","霜霉病 白粉病 人工智能","数字全息孢子检测葡萄-3467","10.3389\u002Ffpls.2026.1871510",{"doi":475,"openalex_id":477,"authors":478,"venue":462,"cited_by_count":51,"oa_url":459,"card":510,"direction":74,"ingested_from":75},"W7214152870",[479,481,483,486,489,492,495,497,499,502,505,508],{"name":480,"orcid":21},"Tessa Chiara Basso",{"name":482,"orcid":21},"Sara Leoni",{"name":484,"orcid":485},"Denis Ullmann","https:\u002F\u002Forcid.org\u002F0000-0002-7179-005X",{"name":487,"orcid":488},"Adimulya Kartiyasa","https:\u002F\u002Forcid.org\u002F0009-0003-3142-1174",{"name":490,"orcid":491},"Livio Ruzzante","https:\u002F\u002Forcid.org\u002F0000-0002-8693-8678",{"name":493,"orcid":494},"Sylvain Schnée","https:\u002F\u002Forcid.org\u002F0000-0002-1014-1961",{"name":496,"orcid":21},"Anne‐Lise Fabre",{"name":498,"orcid":21},"Steven Hewison",{"name":500,"orcid":501},"Jérôme Kasparian","https:\u002F\u002Forcid.org\u002F0000-0003-2398-3882",{"name":503,"orcid":504},"Nicolas Berti","https:\u002F\u002Forcid.org\u002F0000-0003-3769-3966",{"name":506,"orcid":507},"Pierre‐Henri Dubuis","https:\u002F\u002Forcid.org\u002F0000-0002-9624-3925",{"name":509,"orcid":21},"Jean-Pierre Wolf",{"tldr":511,"method":512,"finding":513,"direction":74,"opportunity":514},"利用数字全息与AI检测葡萄园空气中霜霉和白粉病菌孢子，优化杀菌剂施用。","数字全息成像结合AI分类孢子，在瑞士和法国葡萄园实时监测。","孢子检测可追踪病害动态，在保持防效下大幅减少杀菌剂使用。","可探索孢子自动监测与气象预报融合的精准施药决策模型，并验证多作物适用性。","2026-09-25T23:30:09.459179Z",{"id":517,"title":518,"url":519,"summary":520,"summary_zh":521,"content":21,"source_name":125,"source_url":519,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":522,"sources":524,"tags":526,"search_phrases":532,"slug":535,"view_count":51,"doi":536,"paper":537,"created_at":550},3459,"A blooming dilemma: maintaining access to California crab while managing biotoxin health risks","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1881090","The widespread and persistent 2015–16 domoic acid- (DA) producing algal bloom along the US West Coast led to fishery closures, resulting not only in significant economic losses to California’s commercial Dungeness and rock crab fisheries, but also substantial social impacts and disruption throughout the seafood system. The closures highlighted the need to identify and evaluate strategies for managing and building resilience to future blooms to minimize losses of access and impacts to the seafood system while protecting public health. Using a mixed methods approach, we integrated semi-structured interviews with insights from participant observation, commercial fisheries data, and other archival materials, to begin to address this need. We evaluated the impacts and implications of recent and potential DA management measures for access to crab by fishermen, seafood handlers, retailers and food service providers, and consumers, and explored strategies to mitigate them. Each of the measures considered—area closures, evisceration orders, depuration requirements, and educational campaigns—was found to have particular and potentially profound impacts and implications for the seafood system and its participants. The latter three measures, which are intended to mitigate the risk of consumer exposure to DA while still providing some access to the fishery and seafood products, differ in who can participate in the fishery, how and by whom the catch can be handled, and the product forms that may be sold. All were considered problematic, with evisceration and depuration expected to affect access by re-distributing opportunities, costs and benefits among fishery participants and communities. Various mitigation strategies may lessen the adverse impacts of these measures, including “normalizing” evisceration and directing resources toward training, product development, and marketing to enable broader fishery and market participation, among others. Further, our findings support a fundamental paradigm shift for addressing this issue from one of fishery resource management to one of food system management, utilizing existing frameworks and systems and making it consistent with how other food contaminant concerns are managed. Ultimately, such a paradigm shift could help mitigate impacts throughout the seafood system while offering a more cost-effective, efficient and balanced means for managing fisheries and DA events.","2015–16年，美国西海岸持续爆发范围广泛的产软骨藻酸（domoic acid, DA）藻华，导致渔业关闭，不仅给加利福尼亚州商业珍宝蟹和岩蟹渔业造成重大经济损失，也对整个海产品系统产生了显著的社会影响和扰动。这些关闭事件凸显出，有必要识别和评估相关策略，以管理和增强对未来藻华的韧性，从而在保护公众健康的同时，最大限度减少准入损失和对海产品系统的影响。我们采用混合方法，将半结构化访谈与参与式观察的洞见、商业渔业数据及其他档案材料相结合，初步回应这一需求。我们评估了近期及潜在的DA管理措施对渔民、海产品加工者、零售商和餐饮服务提供者以及消费者获取蟹类的影响和意义，并探讨了缓解这些影响的策略。所考虑的每一项措施——区域关闭、去内脏令、净化要求和教育活动——都被发现对海产品系统及其参与者具有特定的、可能深远的影响和意义。后三项措施旨在降低消费者接触DA的风险，同时仍提供一定的渔业和海产品准入机会，但它们在谁可以参与渔业、渔获可以如何处理及由谁处理，以及可以销售的产品形态方面各不相同。所有这些措施都被认为存在问题，其中去内脏和净化预计会通过重新分配渔业参与者和社区之间的机会、成本和收益来影响准入。多种缓解策略可以减轻这些措施的不利影响，包括使去内脏“常态化”，以及将资源导向培训、产品开发和营销，以促进更广泛的渔业和市场参与等。此外，我们的发现支持一种根本性的范式转变，即从渔业资源管理转向食品系统管理来处理这一问题，利用现有框架和系统，并使其与其他食品污染物关切的管理方式保持一致。最终，这种范式转变有助于减轻整个海产品系统的影响，同时为管理渔业和DA事件提供更具成本效益、更高效且更平衡的方式。",{"impact":127,"substance":29,"depth":127,"authority":32,"freshness":90,"relevant":34,"comment":523},"以混合方法评估软骨藻酸藻华下加州蟹类渔业管理措施对海产品体系的影响，提出从资源管理转向食物系统管理的范式转变，结论扎实但属美国区域案例，对国内渔业与食品安全管理有借鉴意义。",[525],{"name":125,"url":519},[527,528,529,530,531],"食品安全","渔业管理","赤潮藻华","海产品供应链","渔业政策",[533,534],"加州 珍宝蟹 软骨藻酸","domoic acid 蟹类 渔业关闭","加州珍宝蟹软骨藻酸-3459","10.3389\u002Ffsufs.2026.1881090",{"doi":536,"openalex_id":538,"authors":539,"venue":125,"cited_by_count":51,"oa_url":519,"card":544,"direction":548,"ingested_from":75},"W7214236994",[540,542],{"name":541,"orcid":21},"Carrie Pomeroy",{"name":543,"orcid":21},"Carolynn Culver",{"tldr":545,"method":546,"finding":547,"direction":548,"opportunity":549},"研究加州蟹类渔业在软骨藻酸风险下的管理措施及其对海鲜系统的影响。","混合方法：半结构化访谈、参与观察、渔业数据与档案分析。","各管理措施均影响海鲜系统，需从渔业资源管理转向食品系统管理。","其他","可探索将食品安全框架融入渔业管理，评估不同措施的成本效益与公平性。","2026-09-25T23:30:06.914404Z",{"id":552,"title":553,"url":554,"summary":555,"summary_zh":556,"content":21,"source_name":125,"source_url":554,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":338,"score_detail":557,"sources":559,"tags":561,"search_phrases":567,"slug":570,"view_count":51,"doi":571,"paper":572,"created_at":583},3456,"Food insecurity severity, household food acquisition patterns, and food basket contraction in Peru: a national analysis of ENAHO 2025","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1966104","Background Food insecurity may affect both access to food and the quantities acquired by households. However, evidence on its relationship with the acquisition of specific food groups in Peru remains limited. Objective To evaluate the association between food insecurity severity and the probability and quantity of food acquisition among Peruvian households. Methods A cross-sectional study was conducted using data from 32,053 households participating in the 2025 National Household Survey (ENAHO). Food insecurity was assessed using the Food Insecurity Experience Scale (FIES; 0–8 points). Per capita acquisition of fruits, vegetables, legumes, cereals, pseudocereals and cereal-based foods, fish and seafood, processed meats, and sugar-sweetened beverages was estimated. Modified Poisson regression models were used to estimate adjusted prevalence ratios (aPRs), and Gamma regression models with a log link were used to estimate adjusted mean ratios (aMRs), accounting for the complex survey design. Results Each 1-point increase in FIES was associated with 2.6% lower fruit acquisition (aMR = 0.974; 95% CI: 0.968–0.980) and 1.3% lower vegetable acquisition (aMR = 0.987; 95% CI: 0.982–0.992). Higher FIES severity was also associated with lower probabilities of acquiring fish and seafood, processed meats, and carbonated soft drinks. Cereals, pseudocereals, and cereal-based foods showed only minimal positive associations in continuous models, while categorical analyses showed no monotonic gradient across severity bands. Conclusion Greater food insecurity severity was associated with selective contraction of household food acquisition, particularly for fruits and vegetables, rather than a uniform shift across all food groups.","背景 粮食不安全可能同时影响家庭的食物获取途径和获取数量。然而，在秘鲁，其与特定食物类别获取之间关系的证据仍然有限。目的 评估秘鲁家庭粮食不安全严重程度与食物获取概率及数量之间的关联。方法 采用横断面研究，使用2025年全国家庭调查（ENAHO）中32,053户家庭的数据。粮食不安全采用粮食不安全体验量表（FIES；0–8分）进行评估。估算了水果、蔬菜、豆类、谷物、伪谷物及谷物制品、鱼类和海鲜、加工肉类以及含糖饮料的人均获取量。使用修正泊松回归模型估计调整后患病率比（aPRs），并使用对数链接的Gamma回归模型估计调整后均值比（aMRs），同时考虑复杂抽样设计。结果 FIES每增加1分，水果获取量降低2.6%（aMR = 0.974；95% CI：0.968–0.980），蔬菜获取量降低1.3%（aMR = 0.987；95% CI：0.982–0.992）。FIES严重程度越高，获取鱼类和海鲜、加工肉类以及碳酸软饮料的概率也越低。谷物、伪谷物及谷物制品在连续模型中仅显示极小的正相关，而分类分析未显示严重程度分级之间存在单调梯度。结论 粮食不安全严重程度越高与家庭食物获取的选择性收缩相关，尤其是水果和蔬菜，而非所有食物类别的普遍变化。",{"impact":127,"substance":29,"depth":127,"authority":89,"freshness":33,"relevant":34,"comment":558},"基于秘鲁3.2万户全国调查数据，揭示食物不安全严重程度与果蔬等食物获取收缩的关联，方法规范、数据规模大，对粮食安全与营养监测有参考价值，但属他国研究，国内落地性有限。",[560],{"name":125,"url":554},[562,563,564,565,566],"粮食安全","膳食营养","秘鲁农业","食物不安全","家庭食物消费",[568,569],"ENAHO 2025 秘鲁 食物不安全","FIES 食物获取 秘鲁","ENAHO2025秘鲁食物不安全-3456","10.3389\u002Ffsufs.2026.1966104",{"doi":571,"openalex_id":573,"authors":574,"venue":125,"cited_by_count":51,"oa_url":554,"card":578,"direction":117,"ingested_from":75},"W7214178487",[575],{"name":576,"orcid":577},"Jacksaint Saintila","https:\u002F\u002Forcid.org\u002F0000-0002-7340-7974",{"tldr":579,"method":580,"finding":581,"direction":117,"opportunity":582},"基于秘鲁2025年ENAHO全国调查，分析粮食不安全严重程度与家庭食物获取模式的关系。","使用FIES量表、修正泊松回归和Gamma回归分析32053户家庭食物获取数据。","粮食不安全每增加1分，水果获取降2.6%、蔬菜降1.3%，呈选择性收缩而非全面减少。","可结合农业信息化手段监测粮食不安全家庭的食物获取变化，为精准干预提供数据支撑。","2026-09-25T23:30:06.728569Z",{"id":585,"title":586,"url":587,"summary":588,"summary_zh":589,"content":21,"source_name":590,"source_url":587,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":591,"score_detail":592,"sources":594,"tags":596,"search_phrases":601,"slug":604,"view_count":51,"doi":605,"paper":606,"created_at":629},3516,"Approaches to forecast soil nutrient dynamics for precision agriculture and sustainable fertiliser management: A review","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.16160","Predictive modelling of soil nutrient dynamics is an essential tool for promoting sustainable agricultural practices and environmentally responsible farming methods. The statistical and machine learning techniques used to forecast the availability and dynamics of soil nutrients are summarised in this review. The core frameworks for measuring spatio-temporal nutritional variability are established by traditional statistical approaches such as time-series models autoregressive integrated moving average (ARIMA), seasonal autoregressive integrated moving average (SARIMA), multivariate techniques (Principal component analysis (PCA) and factor analysis) and geostatistical tools (kriging). By capturing intricate nonlinear interactions within heterogeneous agroecosystems, machine learning techniques like random forest, support vector machines and ensemble approaches (XGBoost, LightGBM and AdaBoost) provide higher prediction accuracy. Forecasting capabilities are further enhanced by hybrid frameworks [Autoregressive integrated moving average with exogenous variables–artificial neural network. (ARIMAX-ANN)] and deep learning architectures (Convolutional neural network (CNN), long short-term memory (LSTM), ANN). With R2 values above 0.93 and notable decreases in prediction errors, ensemble approaches routinely perform better than traditional linear models. Nevertheless, persistent challenges include data quality limitations, spatial sampling constraints, insufficient environmental covariates and reduced model transferability across diverse pedoclimatic regions. Integrating high-resolution soil properties, climatic variables, terrain attributes and spectral information with advanced modelling architectures remains crucial for enhancing predictive reliability, ultimately supporting precision nutrient management, improved fertiliser efficiency and environmentally responsible agricultural systems.","土壤养分动态的预测建模是推动可持续农业实践和环境友好型耕作方法的重要工具。本综述总结了用于预测土壤养分有效性及其动态变化的统计与机器学习技术。传统统计方法，如时间序列模型自回归积分滑动平均模型（ARIMA）、季节性自回归积分滑动平均模型（SARIMA）、多变量技术（主成分分析（PCA）和因子分析）以及地统计工具（克里金法），为量化养分的时空变异性奠定了核心框架。通过捕捉异质性农业生态系统中复杂的非线性相互作用，随机森林、支持向量机和集成方法（XGBoost、LightGBM和AdaBoost）等机器学习技术可实现更高的预测精度。混合框架[含外生变量的自回归积分滑动平均模型–人工神经网络（ARIMAX-ANN）]和深度学习架构（卷积神经网络（CNN）、长短期记忆网络（LSTM）、人工神经网络（ANN））进一步增强了预测能力。集成方法的R²值超过0.93，且预测误差显著降低，其表现通常优于传统线性模型。然而，持续存在的挑战包括数据质量限制、空间采样约束、环境协变量不足以及模型在不同土壤气候区域间可迁移性降低等问题。将高分辨率土壤属性、气候变量、地形属性和光谱信息与先进建模架构相结合，对于提高预测可靠性仍然至关重要，最终可为精准养分管理、提高肥料利用效率以及环境友好型农业系统提供支撑。","Plant Science Today",79,{"impact":127,"substance":29,"depth":127,"authority":89,"freshness":90,"relevant":34,"comment":593},"系统综述土壤养分动态预测的统计与机器学习方法，方法体系完整、结论有量化支撑，对精准施肥与农业信息化有参考价值，但属综述类论文，产业级影响有限。",[595],{"name":590,"url":587},[42,597,598,599,600],"变量施肥","机器学习","精准农业","土壤养分",[602,603],"土壤养分 预测模型 精准农业","机器学习 施肥管理 可持续农业","土壤养分预测模型精准农业-3516","10.14719\u002Fpst.16160",{"doi":605,"openalex_id":607,"authors":608,"venue":590,"cited_by_count":51,"oa_url":587,"card":624,"direction":72,"ingested_from":75},"W7214167059",[609,612,615,618,621],{"name":610,"orcid":611},"R Rathna","https:\u002F\u002Forcid.org\u002F0009-0004-7797-2673",{"name":613,"orcid":614},"B Sivasankari","https:\u002F\u002Forcid.org\u002F0000-0001-9921-8170",{"name":616,"orcid":617},"R. Gangai Selvi","https:\u002F\u002Forcid.org\u002F0000-0002-4475-2293",{"name":619,"orcid":620},"J Prabhakaran","https:\u002F\u002Forcid.org\u002F0000-0001-7339-175X",{"name":622,"orcid":623},"K. G. Sabarinathan","https:\u002F\u002Forcid.org\u002F0000-0002-8659-6479",{"tldr":625,"method":626,"finding":627,"direction":72,"opportunity":628},"综述土壤养分动态预测的统计与机器学习方法，比较精度与局限。","综述ARIMA、地统计、随机森林、XGBoost、CNN\u002FLSTM及混合模型。","集成与深度学习模型精度更高（R²>0.93），但数据质量与跨区迁移性仍是瓶颈。","可研究多源遥感与气候数据融合的迁移学习模型，提升跨区域养分预测泛化能力。","2026-09-25T23:30:54.950445Z",{"id":631,"title":632,"url":633,"summary":634,"summary_zh":635,"content":21,"source_name":263,"source_url":633,"published_at":23,"category":24,"cover_url":21,"hotness":85,"is_selected":26,"score":591,"score_detail":636,"sources":639,"tags":641,"search_phrases":644,"slug":647,"view_count":51,"doi":648,"paper":649,"created_at":677},3494,"Rice Cropping Pattern Mapping Using GEE-Based Sentinel-1\u002F2 Time-Series Imagery and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193302","Accurate mapping of rice cropping patterns is fundamental to sustainable agricultural management and regional food security assessment. In this study, we developed a high-precision mapping framework for major rice cropping patterns in the Yangtze River Delta region, China, using the Google Earth Engine (GEE) cloud platform. A multi-temporal and multi-source feature set was constructed by integrating Sentinel-1 radar backscatter (VV\u002FVH polarization), Sentinel-2 optical indices, including the normalized difference vegetation index (NDVI) and land surface water index (LSWI), and topographic factors (DEM and slope), to classify three predominant cropping systems, namely, wheat–rice rotation, double rice, and rapeseed–rice rotation. A total of 548 field-surveyed sample points collected during the 2024–2025 growing season were used for model training and validation. Three classical classifiers—Random Forest (RF), A Gradient Boosting Tree (GBTREE), and a Support Vector Machine (SVM)—were systematically compared. The ablation experiment demonstrated that the fusion of Sentinel-1 and Sentinel-2 outperformed both the Sentinel-1-only and Sentinel-2-only configurations across all three classifiers. Among them, the GBTREE achieved the highest overall accuracy (93.8%), Kappa coefficient (0.87), and macro-average F1 score (88.3%) in this specific experiment. Notably, it also performed best on the more challenging double-rice class. The SHapley Additive exPlanations (SHAP)-based feature importance analysis revealed that multi-temporal NDVI phenological features were the primary drivers of classification accuracy, while radar backscatter and water indices provided essential complementary information, and topographic factors served as spatial constraints at the regional scale. The spatial distribution derived from the GBTREE classification exhibited clear patterns: wheat–rice rotation dominated the northern plains (northern Jiangsu, northern Anhui, and the Hangjiahu Plain); double rice was concentrated in the southern Zhejiang hills and scattered valley plains; and rapeseed–rice rotation showed a scattered, mosaic distribution. Overall, this study demonstrates that integrating multi-source remote sensing data on the GEE platform with the GBTREE classifier enables effective and scalable high-precision mapping of rice cropping patterns in complex agricultural landscapes. This approach provides a reliable technical foundation for regional agricultural structure analysis, crop rotation assessment, and sustainable agricultural monitoring.","准确绘制水稻种植模式图是实现可持续农业管理和区域粮食安全评估的基础。本研究基于Google Earth Engine（GEE）云平台，构建了长江三角洲地区主要水稻种植模式的高精度制图框架。通过整合Sentinel-1雷达后向散射（VV\u002FVH极化）、Sentinel-2光学指数（包括归一化差异植被指数NDVI和地表水体指数LSWI）以及地形因子（DEM和坡度），构建了多时相、多源特征集，用于分类三种主要种植制度，即麦–稻轮作、双季稻和油–稻轮作。利用2024—2025年生长季采集的548个实地调查样点进行模型训练与验证。系统比较了三种经典分类器——随机森林（RF）、梯度提升树（GBTREE）和支持向量机（SVM）。消融实验表明，Sentinel-1与Sentinel-2的融合在三种分类器中均优于仅使用Sentinel-1或仅使用Sentinel-2的配置。其中，GBTREE在本实验中取得了最高的总体精度（93.8%）、Kappa系数（0.87）和宏平均F1分数（88.3%）。值得注意的是，其在更具挑战性的双季稻类别上同样表现最佳。基于SHapley加法解释（SHAP）的特征重要性分析表明，多时相NDVI物候特征是分类精度的主要驱动因素，雷达后向散射和水体指数提供了必要的补充信息，而地形因子则在区域尺度上起到空间约束作用。基于GBTREE分类得到的空间分布呈现出清晰的格局：麦–稻轮作主导北部平原（苏北、皖北和杭嘉湖平原）；双季稻集中于浙南丘陵和零散的河谷平原；油–稻轮作则呈零散镶嵌状分布。总体而言，本研究表明，在GEE平台上整合多源遥感数据与GBTREE分类器，能够对复杂农业景观中的水稻种植模式进行有效且可扩展的高精度制图。该方法为区域农业结构分析和作物",{"impact":637,"substance":29,"depth":127,"authority":32,"freshness":33,"relevant":34,"comment":638},16,"基于GEE与Sentinel-1\u002F2时序影像结合机器学习实现长三角水稻种植模式高精度制图，方法扎实、结论可靠，对农业遥感监测有参考价值。",[640],{"name":263,"url":633},[42,642,598,207,643],"水稻","作物分类",[645,646],"长三角 水稻 种植模式 遥感","Sentinel-1 Sentinel-2 水稻制图","长三角水稻种植模式遥感-3494","10.3390\u002Frs18193302",{"doi":648,"openalex_id":650,"authors":651,"venue":263,"cited_by_count":51,"oa_url":633,"card":672,"direction":254,"ingested_from":75},"W7214147197",[652,655,658,661,663,666,669],{"name":653,"orcid":654},"Xuan Li","https:\u002F\u002Forcid.org\u002F0000-0001-5509-2385",{"name":656,"orcid":657},"Lintao Chen","https:\u002F\u002Forcid.org\u002F0009-0000-6558-1289",{"name":659,"orcid":660},"Lin Chen","https:\u002F\u002Forcid.org\u002F0000-0002-9270-1626",{"name":662,"orcid":21},"Chao Su",{"name":664,"orcid":665},"Hoi Leong Lee","https:\u002F\u002Forcid.org\u002F0000-0002-4984-2183",{"name":667,"orcid":668},"Ruci Wang","https:\u002F\u002Forcid.org\u002F0000-0001-7049-7006",{"name":670,"orcid":671},"Xuguang Tang","https:\u002F\u002Forcid.org\u002F0009-0008-3494-8867",{"tldr":673,"method":674,"finding":675,"direction":254,"opportunity":676},"基于GEE融合Sentinel-1\u002F2时序与地形特征，用机器学习高精度制图长三角水稻种植模式。","GEE平台、Sentinel-1\u002F2时序特征、DEM、548个实地样本、RF\u002FG","GBTREE精度最高（总体93.8%、Kappa 0.87），双季稻识别最好；NDVI物候特征贡献最","可探索样本稀缺区迁移学习与多作物轮作模式泛化制图，并耦合产量与碳核算。","2026-09-25T23:30:30.511522Z"]