[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"daily-2026-10-07":3},{"date":4,"title":5,"highlights":6,"content":13,"items":14},"2026-10-07","农业农村日报：AI与遥感驱动农业系统转型",[7,8,9,10,11,12],"中国农业保险改革研究揭示气候风险加剧下保险对粮食生产系统韧性的补偿效应，为农业风险管理政策提供实证依据。","多篇论文聚焦AI与大数据在食物系统转型、农学决策中的应用，同时指出数字平台整合面临微型企业行为意愿的机会鸿沟。","遥感技术进展显著：SAR与光学时序融合提升早期作物制图，无人机多光谱与纹理特征融合实现干旱区果树叶片氮含量精准估算。","卡霍夫卡大坝溃决案例提出半监督多传感器遥感管道，为冲突地区灌溉动态制图提供新方法。","植物基食品可持续治理研究揭示生态与超加工悖论，呼吁建立技术—营养—生态协同框架。","高通量表型成像新方法提升病害严重度估计精度，为抗性育种和精准农业提供可靠量化工具。","本期汇编12篇前沿研究，覆盖气候风险与农业保险、AI与大数据驱动食物系统转型、遥感与无人机精准监测、数字平台整合、土壤制图及植物病害表型等方向，兼顾冲突地区农业遥感与植物基食品可持续治理，呈现技术赋能农业系统韧性与可持续发展的多元路径。\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。*",[15,112,220,291,362,412,470,553,626,685,795,850,922,1014,1092],{"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":38,"primary_topic":44,"secondary_topics":50,"classification":57,"search_phrases":83,"slug":86,"view_count":87,"doi":88,"paper":89,"created_at":111},4289,"When climate risk intensifies, does insurance pay off? A community case study of China's agricultural insurance reform","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1954205","In the context of mounting global climate threats, fostering resilience in food production systems has become a critical imperative for upholding national food security. This paper exploits the staggered implementation, beginning in 2018, of China's agricultural insurance reforms covering full production costs and planting income as a quasi-natural experiment. Drawing on provincial panel data from 2013 to 2024, we first develop a multidimensional composite index to capture food production resilience. A staggered difference-in-differences specification is then adopted to systematically assess the causal effect of these reforms on such resilience and to explore the underlying transmission channels. Moreover, from a novel climate change perspective, the analysis examines the heterogeneous treatment effects across varying degrees of climate risk exposure. The empirical findings reveal that the policy-led agricultural insurance reform significantly and robustly enhances China's food production resilience. Mechanism tests indicate that advances in agricultural technology and the expansion of large-scale farming operations serve as important pathways through which the insurance policy takes effect. Further investigation shows that climate change risk positively moderates the policy impact: as climate risk intensifies, the marginal contribution of insurance to resilience becomes stronger. Heterogeneity analysis also demonstrates that the policy effect is more pronounced in western China and in localities with higher rates of disaster-induced losses. Taken together, these results offer solid empirical backing for broadening the pilot programs of full cost and planting income insurance. They also establish a theoretical basis for positioning publicly supported agricultural insurance as an effective instrument for climate change adaptation, providing valuable guidance on strengthening the climate adaptability and resilience of food production to ensure national food security.","在全球气候威胁日益加剧的背景下，增强粮食生产系统的韧性已成为维护国家粮食安全的关键任务。本文以2018年起分阶段实施的中国农业保险覆盖完全生产成本和种植收入的改革为准自然实验，基于2013—2024年省级面板数据，首先构建多维复合指数以刻画粮食生产韧性，继而采用交错双重差分模型系统评估该改革对粮食生产韧性的因果效应并探究其传导机制。此外，本文从气候变化这一新视角出发，考察了不同气候风险暴露程度下的异质性处理效应。实证结果表明，政策主导的农业保险改革显著且稳健地提升了中国粮食生产韧性。机制检验表明，农业技术进步与规模化经营扩张是保险政策发挥作用的重要路径。进一步研究发现，气候变化风险对政策效应具有正向调节作用：随着气候风险加剧，保险对韧性的边际贡献增强。异质性分析还表明，政策效应在中国西部地区以及灾害损失率较高的地区更为显著。综上，上述结果为扩大完全成本保险和种植收入保险试点提供了坚实的经验依据，也为将公共支持的农业保险定位为气候变化适应的有效工具奠定了理论基础，为增强粮食生产的气候适应性与韧性、保障国家粮食安全提供了有价值的政策启示。",null,"Frontiers in Sustainable Food Systems","2026-10-05T00:00:00Z","论文",10,false,88,{"impact":29,"substance":30,"depth":31,"authority":32,"freshness":33,"relevant":34,"comment":35},24,23,19,14,8,1,"基于2013-2024年省级面板数据的交错DID准自然实验，证实农业保险改革显著提升粮食生产韧性且气候风险具有正向调节作用，方法规范、结论可靠，对完善农业保险试点具有政策参考价值。",[37],{"name":22,"url":18},[39,40,41,42,43],"粮食安全","农业保险","农业政策","气候适应","生产韧性",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},"G3","rural-finance","农村金融与保险","\u002Ftopic\u002Frural-services\u002Frural-finance","G",[51],{"code":52,"slug":53,"name":54,"path":55,"parent_code":56},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":58,"locked":26,"version":59,"method":60,"evidence":61},"classified","2026-10-22.2","rules",{"candidates":62,"agricultural_evidence":65},[63,70,76],{"code":45,"score":64,"supported":65,"title":66,"abstract":68,"tags":69},15,true,[67],"agricultural insurance",[40,67],[40],{"code":52,"score":25,"supported":65,"title":71,"abstract":72,"tags":75},[],[73,42,74],"气候变化","climate change",[42],{"code":77,"score":78,"supported":65,"title":79,"abstract":80,"tags":82},"A8",7,[],[39,81],"food security",[39],[84,85],"农业保险改革 粮食生产韧性","完全成本保险 种植收入保险","农业保险改革粮食生产韧性-4289",3,"10.3389\u002Ffsufs.2026.1954205",{"doi":88,"openalex_id":90,"authors":91,"venue":22,"cited_by_count":103,"oa_url":18,"card":104,"direction":108,"ingested_from":110},"W7220367453",[92,95,97,99,101],{"name":93,"orcid":94},"Changzhe Deng","https:\u002F\u002Forcid.org\u002F0009-0006-0852-5997",{"name":96,"orcid":21},"Maimiao Sun",{"name":98,"orcid":21},"Xueyu Lin",{"name":100,"orcid":21},"Chencan Rao",{"name":102,"orcid":21},"Qiuping Guo",0,{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"基于2013-2024省级面板数据，评估中国农业保险改革对粮食生产韧性的因果影响。","多维度韧性指数+交错双重差分，利用2018年起保险改革试点作准自然实验。","保险改革显著提升粮食生产韧性，气候风险越高其边际贡献越强，西部和灾损高地区效果更明显。","农业绿色发展与碳","可探究保险改革与农业技术、规模化经营的协同机制，及气候风险下保险产品设计与精准赔付的优化路径。","openalex","2026-10-06T23:30:05.886883Z",{"id":113,"title":114,"url":115,"summary":116,"summary_zh":117,"content":21,"source_name":118,"source_url":115,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":119,"score_detail":120,"sources":125,"tags":127,"primary_topic":132,"secondary_topics":137,"classification":144,"search_phrases":174,"slug":177,"view_count":103,"doi":178,"paper":179,"created_at":219},4313,"A semi-supervised multi-sensor remote sensing pipeline for mapping irrigation dynamics in ground-truth deficient conflict zones: a case study of the Kakhovka Dam failure","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1920951","The ongoing war in Ukraine has drawn international attention to the impact of conflict on global agricultural production and food security. On 6 June 2023, the Kakhovka Dam was destroyed. The loss of this critical agricultural and energy infrastructure has left most farmers on the East bank of the Dnipro River without irrigation in Kherson and Zaporizhzhia oblasts. This study develops a multi-sensor Earth Observation framework combining high resolution satellite imagery (Sentinel-2, Landsat) with meteorological data (CHIRPS) and water productivity data (FAO WaPOR), using a semi-supervised machine learning pipeline. Using a rigorous stratified random-sampling approach with photointerpretation, we found pre-war irrigated areas between 2019 to 2021 to be on average 187.94 ± 14.43 kHa, approximately 4% of pre-war baseline cropland and 8% of summer season cropland in Kherson and Zaporizhzhia oblasts. In 2022, these numbers contracted to 140.04 ± 17.44 kHa with the expanded occupation of these territories by Russia, seeing an additional decline in 2023 to 74.97 ± 17.84 kHa. Fields in 2023 also exhibited variability in irrigation, ranging from interrupted irrigation owing to the destruction of the Kakhovka reservoir, to those that were sufficiently irrigated with water remaining in the channels. Irrigated areas diminished further in 2024 to 15.95 ± 9.97 kHa, a ∼91% decline from pre-war averages. Based on inspection, formerly irrigated fields before 2023 were either systematically abandoned or converted to winter cropland with lower input requirements by 2024–a pattern that continued into 2025 (total irrigated area 5.76 ± 0.87 kHa). This study demonstrates the power of advanced EO workflows to precisely quantify agricultural transformation and infrastructural failure in ground-truth deficient, high-risk environments.","乌克兰持续不断的战争使国际社会关注冲突对全球农业生产和粮食安全的影响。2023年6月6日，卡霍夫卡大坝被毁。这一关键农业和能源基础设施的丧失，使第聂伯河（Dnipro River）东岸赫尔松州和扎波罗热州的大多数农民失去了灌溉条件。本研究开发了一个多传感器地球观测（Earth Observation）框架，将高分辨率卫星影像（Sentinel-2、Landsat）与气象数据（CHIRPS）和水生产力数据（FAO WaPOR）相结合，采用半监督机器学习流程。通过严格的 stratified random-sampling 方法并结合照片判读，我们发现2019年至2021年战前灌溉面积平均为187.94 ± 14.43 kHa，约占赫尔松州和扎波罗热州战前基线耕地面积的4%，以及夏季作物耕地面积的8%。2022年，随着俄罗斯对这些领土占领的扩大，上述数字缩减至140.04 ± 17.44 kHa，2023年进一步下降至74.97 ± 17.84 kHa。2023年的田块在灌溉方面也表现出差异性，从因卡霍夫卡水库被毁而灌溉中断，到因渠道中仍有存水而得到充分灌溉的情况不等。2024年，灌溉面积进一步减少至15.95 ± 9.97 kHa，较战前平均值下降约91%。根据核查，2023年之前曾受灌溉的田块到2024年要么被系统性弃耕，要么转为投入需求较低的冬季作物用地——这一模式延续至2025年（总灌溉面积为5.76 ± 0.87 kHa）。本研究表明，先进的地球观测工作流程能够在缺乏地面真值、高风险的环境中精确量化农业转型和基础设施失效。","Frontiers in Remote Sensing",87,{"impact":121,"substance":29,"depth":31,"authority":122,"freshness":123,"relevant":34,"comment":124},22,13,9,"用半监督多源遥感量化战区灌溉萎缩，方法新颖、数据扎实，对农业遥感与粮食安全研究有参考价值。",[126],{"name":118,"url":115},[39,128,129,130,131],"遥感监测","冲突农业","多源遥感","灌溉",{"code":133,"slug":134,"name":135,"path":136,"parent_code":56},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",[138],{"code":139,"slug":140,"name":141,"path":142,"parent_code":143},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":58,"locked":26,"version":59,"method":60,"evidence":145},{"candidates":146,"agricultural_evidence":65},[147,151,156,160,168],{"code":133,"score":32,"supported":65,"title":148,"abstract":149,"tags":150},[134],[131,134],[],{"code":139,"score":25,"supported":65,"title":152,"abstract":154,"tags":155},[153],"remote sensing",[],[130,128],{"code":77,"score":78,"supported":65,"title":157,"abstract":158,"tags":159},[],[39,81],[39],{"code":161,"score":162,"supported":65,"title":163,"abstract":164,"tags":167},"I2",6,[],[165,166],"机器学习","machine learning",[],{"code":169,"score":87,"supported":65,"title":170,"abstract":171,"tags":173},"J3",[],[172],"全球农业",[],[175,176],"冲突农业 多源遥感 粮食安全 遥感监测","冲突农业 多源遥感","冲突农业多源遥感粮食安全遥感监测-4313","10.3389\u002Ffrsen.2026.1920951",{"doi":178,"openalex_id":180,"authors":181,"venue":118,"cited_by_count":103,"oa_url":212,"card":213,"direction":217,"ingested_from":110},"W7220438608",[182,185,188,191,194,197,200,202,204,206,209],{"name":183,"orcid":184},"Sheila Baber","https:\u002F\u002Forcid.org\u002F0000-0002-5596-8970",{"name":186,"orcid":187},"Sergii V. Skakun","https:\u002F\u002Forcid.org\u002F0000-0002-9039-0174",{"name":189,"orcid":190},"Yuval Sadeh","https:\u002F\u002Forcid.org\u002F0000-0002-4346-0432",{"name":192,"orcid":193},"Леонід Леонідович Шуміло","https:\u002F\u002Forcid.org\u002F0000-0002-7395-7933",{"name":195,"orcid":196},"Oleksandra Oliinyk","https:\u002F\u002Forcid.org\u002F0000-0002-2392-3938",{"name":198,"orcid":199},"Mehdi Hosseini","https:\u002F\u002Forcid.org\u002F0000-0003-3242-613X",{"name":201,"orcid":21},"Josef Wagner",{"name":203,"orcid":21},"Abdul Qadir Khan",{"name":205,"orcid":21},"Shabarinath Nair",{"name":207,"orcid":208},"Abhishek Kotcharlakota","https:\u002F\u002Forcid.org\u002F0009-0001-1832-4631",{"name":210,"orcid":211},"Inbal Becker‐Reshef","https:\u002F\u002Forcid.org\u002F0000-0002-2160-5151","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1920951\u002Fpdf",{"tldr":214,"method":215,"finding":216,"direction":217,"opportunity":218},"用半监督多源遥感监测卡霍夫卡大坝被毁后灌溉面积从战前18.8万公顷降至2025年0.58万公顷。","Sentinel-2、Landsat、CHIRPS与FAO WaPOR数据结合半","灌溉面积由2019-2021年均187.94 kHa降至2024年15.95 kHa，降幅约91%，","农业遥感与作物表型","可将该半监督多源框架迁移至其他缺地面真值冲突区，并耦合作物产量与粮食安全评估。","2026-10-06T23:30:20.495894Z",{"id":221,"title":222,"url":223,"summary":224,"summary_zh":225,"content":21,"source_name":22,"source_url":223,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":226,"score_detail":227,"sources":230,"tags":232,"primary_topic":238,"secondary_topics":242,"classification":243,"search_phrases":271,"slug":274,"view_count":103,"doi":275,"paper":276,"created_at":290},4291,"The role of artificial intelligence in food systems transformation: a review of opportunities, challenges, and future directions","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1892956","Global food systems face increasing pressure from climate change, resource scarcity, and supply-chain disruptions, creating a need for more integrated and resilient responses. This study critically examines the role of artificial intelligence (AI) in food-systems transformation through a systematic literature review of publications from 2020 to 2026. Guided by the PRISMA 2020 guidelines, the review searched multiple academic databases and applied predefined and subsequently refined eligibility criteria to identify and synthesize evidence from 40 publications addressing AI applications, implementation challenges, governance, sustainability, socio-technical conditions, and adoption patterns across food-system domains. The findings indicate that AI can support improvements in productivity, quality control, supply-chain traceability, resilience, and decision-making. However, these benefits are not automatic and depend on socio-technical readiness, governance, digital infrastructure, data systems, and organizational capability. Building on these findings, the review develops an integrated dynamic socio-technical AI food systems transformation framework by integrating socio-technical systems theory and diffusion of innovation theory. The framework conceptualizes AI-enabled food-systems transformation as a dynamic and conditional process and provides a basis for future research, policy development, and responsible AI implementation.","全球粮食系统正面临气候变化、资源稀缺和供应链中断日益增大的压力，因此需要更具整合性和韧性的应对措施。本研究通过对2020年至2026年发表的文献进行系统性综述，批判性地考察了人工智能（AI）在粮食系统转型中的作用。该综述以PRISMA 2020指南为指导，检索了多个学术数据库，并应用预设且随后完善的纳入标准，识别并综合了40篇文献中的证据，这些文献涉及AI应用、实施挑战、治理、可持续性、社会技术条件以及粮食系统各领域的采用模式。研究结果表明，AI能够支持生产力、质量控制、供应链可追溯性、韧性和决策方面的改进。然而，这些效益并非自动实现，而是取决于社会技术准备度、治理、数字基础设施、数据系统和组织能力。基于这些发现，本综述通过整合社会技术系统理论和创新扩散理论，构建了一个整合动态社会技术AI粮食系统转型框架。该框架将AI赋能的粮食系统转型概念化为一个动态且有条件的过程，并为未来研究、政策制定和负责任AI实施提供了基础。",85,{"impact":121,"substance":121,"depth":228,"authority":32,"freshness":123,"relevant":34,"comment":229},18,"基于PRISMA 2020的40篇文献系统综述，提出AI赋能粮食系统转型的社会技术动态框架，对智慧农业政策与研究有较高参考价值。",[231],{"name":22,"url":223},[233,234,235,236,237],"数字基础设施","智慧农业","农业人工智能","供应链溯源","粮食系统",{"code":161,"slug":239,"name":240,"path":241,"parent_code":143},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":58,"locked":26,"version":59,"method":60,"evidence":244},{"candidates":245,"agricultural_evidence":65},[246,252,256,261,266],{"code":161,"score":247,"supported":65,"title":248,"abstract":250,"tags":251},12,[249],"artificial intelligence",[249],[235],{"code":52,"score":162,"supported":65,"title":253,"abstract":254,"tags":255},[],[73,74],[],{"code":257,"score":34,"supported":26,"title":258,"abstract":259,"tags":260},"E4",[],[],[236],{"code":262,"score":34,"supported":26,"title":263,"abstract":264,"tags":265},"I1",[],[],[234],{"code":267,"score":34,"supported":26,"title":268,"abstract":269,"tags":270},"I6",[],[],[233],[272,273],"人工智能 粮食系统 转型","AI 食品系统 PRISMA","人工智能粮食系统转型-4291","10.3389\u002Ffsufs.2026.1892956",{"doi":275,"openalex_id":277,"authors":278,"venue":22,"cited_by_count":103,"oa_url":223,"card":284,"direction":288,"ingested_from":110},"W7220407651",[279,281],{"name":280,"orcid":21},"Neo Mokone",{"name":282,"orcid":283},"Emmanuel Ndhlovu","https:\u002F\u002Forcid.org\u002F0000-0002-2339-3068",{"tldr":285,"method":286,"finding":287,"direction":288,"opportunity":289},"系统综述2020-2026年AI在食品系统转型中的作用，提出社会技术整合框架。","PRISMA 2020系统文献综述，分析40篇出版物。","AI可提升生产力、质量、追溯与决策，但效益依赖社会技术准备与治理。","农业人工智能与决策模型","可实证检验该动态框架，研究不同区域社会技术条件对AI采纳与成效的调节机制。","2026-10-06T23:30:06.025498Z",{"id":292,"title":293,"url":294,"summary":295,"summary_zh":296,"content":21,"source_name":297,"source_url":294,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":298,"score_detail":299,"sources":301,"tags":303,"primary_topic":309,"secondary_topics":314,"classification":315,"search_phrases":339,"slug":342,"view_count":343,"doi":344,"paper":345,"created_at":361},4319,"Closing the opportunity gap: Exploring micro-enterprises' behavioral intention to integrate with digital platforms for a broader agri-food system","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.techfore.2026.124906","Digital agriculture platforms offer marginalized micro-enterprises a vital pathway to bridge the opportunity gap and overcome structural dependencies on focal companies. However, mainstream literature's focal-firm bias leaves the adoption logic of these grassroots operators underexplored. Addressing this gap, we operationalize an integrated Technology Acceptance Model (TAM) and Theory of Planned Behavior (TPB) framework. Using PLS-SEM on data from 167 micro-enterprises, this study investigates their platform integration behaviors. Results reveal distinct adoption pathways: a platform's operational simplicity cannot trigger adoption without first cultivating a favorable organizational mindset (full mediation). Conversely, its tangible strategic benefits—unexpectedly anchored in macro-systemic food safety guarantees and ecological conservation rather than mere short-term profits—motivate integration both directly and indirectly (partial mediation). Socio-psychologically, although micro-enterprises clearly perceive external pressures like government mandates and peer emulation, these fail to translate into adoption intent—a recognition-action gap that leaves adoption strongly conditioned by financial affordability and technical readiness instead. Ultimately, these dynamics reframe the presumed myopic rationality of micro-enterprises: viewed through the lens of push-pull theory, the strategic draw of sustainable platform value is offset by baseline capability constraints, such that this value becomes actionable only when matched by sufficient capability. Theoretically, this demonstrates that cultivating truly inclusive digital ecosystems necessitates shifting the analytical focus from top-down focal designs to bottom-up grassroots decision-making. Practically, it advises policymakers and platform sponsors to move beyond normative persuasion toward tangible capability empowerment and value-driven platform architectures.","数字农业平台为边缘化微型企业提供了弥合机会差距、克服对焦点企业结构性依赖的重要路径。然而，主流文献的焦点企业偏误使得这些草根运营者的采纳逻辑未得到充分探讨。为填补这一空白，我们操作化了一个整合技术接受模型（TAM）与计划行为理论（TPB）的框架。基于167家微型企业的数据，运用偏最小二乘结构方程模型（PLS-SEM），本研究考察了其平台整合行为。结果揭示了不同的采纳路径：平台的操作简便性若未首先培育有利的组织心态，则无法触发采纳（完全中介）。相反，其切实的战略收益——出乎意料地锚定于宏观系统性的食品安全保障与生态保护，而非单纯的短期利润——直接和间接地激励了整合（部分中介）。在社会心理层面，尽管微型企业清晰感知到政府指令和同行模仿等外部压力，但这些压力未能转化为采纳意愿——这一认知-行动差距使得采纳强烈受制于财务可负担性和技术准备度。最终，这些动态重新框定了微型企业被预设的短视理性：从推拉理论视角看，可持续平台价值的战略吸引力被基线能力约束所抵消，使得该价值只有在能力匹配时才可付诸行动。在理论上，这表明培育真正包容的数字生态系统需要将分析焦点从自上而下的焦点设计转向自下而上的草根决策。在实践上，它建议政策制定者和平台发起者超越规范性说服，转向切实的能力赋权和价值驱动的平台架构。","Technological Forecasting and Social Change",81,{"impact":228,"substance":121,"depth":228,"authority":32,"freshness":123,"relevant":34,"comment":300},"基于TAM-TPB整合框架与167家微型企业PLS-SEM实证，揭示数字农业平台采纳的“认知-行动鸿沟”与能力约束，对包容性数字生态政策有参考价值。",[302],{"name":297,"url":294},[304,305,306,307,308],"数字乡村","小农户","农业数字化转型","数字农业平台","平台采纳",{"code":257,"slug":310,"name":311,"path":312,"parent_code":313},"food-safety","质量安全与溯源","\u002Ftopic\u002Ffood-supply\u002Ffood-safety","E",[],{"status":58,"locked":26,"version":59,"method":60,"evidence":316},{"candidates":317,"agricultural_evidence":65},[318,324,330,335],{"code":262,"score":78,"supported":65,"title":319,"abstract":320,"tags":323},[],[321,322],"数字农业","digital agriculture",[306],{"code":257,"score":162,"supported":65,"title":325,"abstract":326,"tags":329},[],[327,328],"食品安全","food safety",[],{"code":331,"score":34,"supported":26,"title":332,"abstract":333,"tags":334},"G2",[],[],[305],{"code":267,"score":34,"supported":26,"title":336,"abstract":337,"tags":338},[],[],[304],[340,341],"农业数字平台 微型企业 采纳行为","TAM TPB 农业平台 整合","农业数字平台微型企业采纳行为-4319",5,"10.1016\u002Fj.techfore.2026.124906",{"doi":344,"openalex_id":346,"authors":347,"venue":297,"cited_by_count":103,"oa_url":294,"card":355,"direction":359,"ingested_from":110},"W7220358562",[348,350,353],{"name":349,"orcid":21},"Dong Xuemei",{"name":351,"orcid":352},"Guoqun Ma","https:\u002F\u002Forcid.org\u002F0000-0002-9619-8423",{"name":354,"orcid":21},"Feiyu Chen",{"tldr":356,"method":357,"finding":358,"direction":359,"opportunity":360},"基于TAM-TPB模型调查167家农业微型企业，揭示其融入数字平台的决策逻辑。","整合TAM与TPB框架，对167家微型企业问卷做PLS-SEM分析。","外部压力不转化为采纳意愿，平台价值需匹配财务与技术能力才起作用。","数字乡村与农业信息化","可研究能力赋能型平台设计如何弥合微型企业数字采纳的知行差距。","2026-10-06T23:30:25.320336Z",{"id":363,"title":364,"url":365,"summary":366,"summary_zh":367,"content":21,"source_name":22,"source_url":365,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":298,"score_detail":368,"sources":370,"tags":372,"primary_topic":21,"secondary_topics":378,"classification":379,"search_phrases":389,"slug":392,"view_count":103,"doi":393,"paper":394,"created_at":411},4290,"The eco–ultraprocessing paradox as evidence for a Tech–Nutri–Eco coherence framework in plant-based food sustainability governance","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1943562","Plant-based foods are widely promoted as sustainable, yet a large share are ultra-processed — a tension that current assessment instruments cannot detect. NOVA, Nutri-score, and eco-score each evaluate a single dimension in isolation and share no criterion for reconciling them, so a product may score favourably on one while remaining unreconciled across the others. The absence of such a criterion is directly consequential for EU directive 2024\u002F825, which requires environmental claims to be verifiable but sets no requirement of coherence across dimensions. The sustainability of a processed food product cannot be read from strong performance on any single dimension: coherence among the technological, nutritional, and environmental dimensions is a separate property, and one that current instruments do not assess. A synthesis of 2015–2025 literature yields 10 recurrent incoherence patterns in four structural families — metric reductionism, fragmented communication, scale and category errors, and pseudo-integration — from which we propose the Tech–Nutri–Eco framework and its operational measure, the integrated COherence iNdex (ICON), as a non-normative diagnostic. Applied to 49 plant-based products, ICON locates what we term the eco–ultraprocessing paradox — ultra-processed products with favourable nutritional or environmental scores — in 57% of the set, most often in plant-based drinks and in dairy and meat alternatives. NOVA 4 products showed markedly lower coherence than the rest (mean ICON 0.19 vs. 0.55; U = 43.0, p \u003C 0.001), a separation that follows from the construction of the index. Coherence assessment offers regulators a means of exposing selective sustainability claims that single-dimension labelling leaves intact.","植物基食品被广泛宣传为可持续的，但其中很大一部分属于超加工食品——当前评估工具无法检测到这一矛盾。NOVA、Nutri-score和eco-score各自孤立地评估单一维度，且彼此之间没有用于协调的标准，因此一个产品可能在某一方面得分良好，而在其他方面却无法协调一致。这种标准的缺失对欧盟第2024\u002F825号指令具有直接影响，该指令要求环境声明可验证，但未规定跨维度一致性的要求。加工食品的可持续性无法从任何单一维度的优异表现中读出：技术、营养和环境维度之间的一致性是一种独立属性，而当前工具并未对此进行评估。对2015—2025年文献的综合分析得出四大结构类别中的10种反复出现的不一致模式——指标还原论、碎片化传播、尺度与类别错误以及伪整合——据此我们提出技术—营养—环境（Tech–Nutri–Eco）框架及其操作化测量工具——综合一致性指数（integrated COherence iNdex, ICON），作为一种非规范性的诊断工具。将该工具应用于49种植物基产品后，ICON在57%的样本中定位到我们所称的“生态—超加工悖论”——即营养或环境评分良好的超加工产品——最常见于植物基饮品以及乳制品和肉类替代品中。NOVA 4类产品的一致性显著低于其余产品（ICON均值0.19 vs. 0.55；U = 43.0，p \u003C 0.001），这一分离源于该指数的构建方式。一致性评估为监管者提供了一种手段，用以揭露单维度标签所无法触及的选择性可持续性声明。",{"impact":228,"substance":30,"depth":228,"authority":122,"freshness":123,"relevant":34,"comment":369},"提出Tech–Nutri–Eco框架与ICON指数，揭示植物基食品“生态-超加工悖论”，对欧盟2024\u002F825指令下的可持续性声明治理有直接参考价值，方法新颖、数据扎实，值得进入每日精选。",[371],{"name":22,"url":365},[373,374,375,376,377],"可持续农业","植物基食品","食品标签","超加工食品","欧盟绿色声明",[],{"status":380,"locked":26,"version":59,"method":60,"evidence":381},"needs_review",{"candidates":382,"agricultural_evidence":26,"reason":388},[383],{"code":384,"score":34,"supported":26,"title":385,"abstract":386,"tags":387},"H8",[],[],[373],"农业相关性需要复核",[390,391],"植物基食品 可持续性 评估","NOVA Nutri-score eco-score 一致性","植物基食品可持续性评估-4290","10.3389\u002Ffsufs.2026.1943562",{"doi":393,"openalex_id":395,"authors":396,"venue":22,"cited_by_count":103,"oa_url":365,"card":406,"direction":108,"ingested_from":110},"W7220371439",[397,400,403],{"name":398,"orcid":399},"Rodica Siminiuc","https:\u002F\u002Forcid.org\u002F0000-0003-4257-1840",{"name":401,"orcid":402},"Dinu Țurcanu","https:\u002F\u002Forcid.org\u002F0000-0001-5540-4246",{"name":404,"orcid":405},"Sergiu Siminiuc","https:\u002F\u002Forcid.org\u002F0000-0002-1531-1560",{"tldr":407,"method":408,"finding":409,"direction":108,"opportunity":410},"提出Tech-Nutri-Eco框架与ICON指数，揭示植物基食品中生态与超加工的矛盾。","综合2015-2025文献，构建ICON指数，评估49种植物基产品的多维一致性。","57%产品存在生态-超加工悖论，NOVA 4产品一致性显著更低（0.19 vs 0.55）。","可将ICON指数扩展至更多食品类别，并研究其与欧盟环境声明验证政策的衔接。","2026-10-06T23:30:05.955445Z",{"id":413,"title":414,"url":415,"summary":416,"summary_zh":21,"content":21,"source_name":417,"source_url":415,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":418,"score_detail":419,"sources":423,"tags":425,"primary_topic":430,"secondary_topics":431,"classification":432,"search_phrases":446,"slug":449,"view_count":34,"doi":450,"paper":451,"created_at":469},4288,"Estimation of leaf nitrogen content of typical fruit trees in arid regions based on fusion of UAV multispectral information and texture features","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10465-z","Estimation of leaf nitrogen content of typical fruit trees in arid regions based on fusion of UAV multispectral information and texture features。Precision Agriculture","Precision Agriculture",78,{"impact":420,"substance":421,"depth":228,"authority":32,"freshness":123,"relevant":34,"comment":422},16,21,"核心期刊论文，将无人机多光谱与纹理特征融合用于干旱区果树叶片氮素估测，方法有创新、结论可靠，对果园精准施肥有参考价值，但属细分领域技术进展，影响范围有限。",[424],{"name":417,"url":415},[234,426,427,428,429],"农业遥感","无人机遥感","果树种植","氮素营养诊断",{"code":139,"slug":140,"name":141,"path":142,"parent_code":143},[],{"status":58,"locked":26,"version":59,"method":60,"evidence":433},{"candidates":434,"agricultural_evidence":65},[435,440],{"code":139,"score":122,"supported":65,"title":436,"abstract":438,"tags":439},[437],"multispectral",[437],[426,427],{"code":262,"score":441,"supported":65,"title":442,"abstract":443,"tags":445},4,[],[444],"precision agriculture",[234],[447,448],"无人机 多光谱 果树 氮含量","干旱区 果树 遥感 估测","无人机多光谱果树氮含量-4288","10.1007\u002Fs11119-026-10465-z",{"doi":450,"openalex_id":452,"authors":453,"venue":417,"cited_by_count":103,"oa_url":21,"card":21,"direction":21,"ingested_from":110},"W7220458084",[454,456,459,461,463,465,467],{"name":455,"orcid":21},"Ran Pang",{"name":457,"orcid":458},"Mamat Sawut","https:\u002F\u002Forcid.org\u002F0009-0004-9961-7381",{"name":460,"orcid":21},"Eniwar Sidik",{"name":462,"orcid":21},"Shanshan Liu",{"name":464,"orcid":21},"Weichen Tian",{"name":466,"orcid":21},"Reheman Rouzi",{"name":468,"orcid":21},"Xiaolong Zhang","2026-10-06T23:30:02.240820Z",{"id":471,"title":472,"url":473,"summary":474,"summary_zh":475,"content":21,"source_name":476,"source_url":473,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":477,"score_detail":478,"sources":480,"tags":482,"primary_topic":485,"secondary_topics":486,"classification":487,"search_phrases":526,"slug":529,"view_count":87,"doi":530,"paper":531,"created_at":552},4321,"Improving early season crop type mapping using machine learning algorithms with combined SAR and optical time series","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04839-6","Timely and reliable crop type mapping is essential for sustainable agricultural management and food security. This study investigates the potential of integrating multi-temporal Synthetic Aperture Radar (SAR) data from Sentinel-1 and optical imagery from Sentinel-2 for early-season crop classification in Udham Singh Nagar district, Uttarakhand, India. Leveraging the Google Earth Engine (GEE) cloud platform, two ensemble machine learning algorithms, Random Forest (RF) and Gradient Boosted Trees (GBT), were implemented and evaluated for their ability to classify major land cover and crop types using combined SAR-optical datasets acquired during November–December 2022. A total of 1141 ground truth samples were collected through field surveys. The integration of structural (SAR) and spectral (optical) information substantially enhanced classification performance compared with single-sensor approaches. Among the models, GBT achieved the highest accuracy, with an overall accuracy of 93% and a Kappa coefficient of 0.90. Wheat, forest, and water bodies were mapped with high precision (F1 ≥ 0.90), whereas mustard and sugarcane showed lower accuracy due to spectral similarity and limited training data. Feature importance analysis identified late-season SAR (VV, VH) and optical (red-edge and SWIR) bands as the most influential variables. The results demonstrate that the synergy between SAR and optical time-series data, coupled with ensemble machine learning, provides a robust and scalable framework for near real-time crop monitoring. This approach offers valuable insights for precision agriculture and supports data-driven policy planning in India’s agricultural sector.","及时可靠的作物类型制图对可持续农业管理和粮食安全至关重要。本研究探讨了整合Sentinel-1多时相合成孔径雷达（SAR）数据与Sentinel-2光学影像在印度北阿坎德邦乌达姆辛格纳加尔地区进行早季作物分类的潜力。依托Google Earth Engine（GEE）云平台，研究采用随机森林（RF）和梯度提升树（GBT）两种集成机器学习算法，利用2022年11月至12月获取的SAR-光学联合数据集，对主要土地覆盖和作物类型进行分类，并评估其分类能力。通过实地调查共采集1141个地面真实样本。与单一传感器方法相比，结构信息（SAR）与光谱信息（光学）的融合显著提升了分类性能。在各模型中，GBT取得了最高精度，总体精度达93%，Kappa系数为0.90。小麦、森林和水体的制图精度较高（F1 ≥ 0.90），而芥菜和甘蔗因光谱相似及训练数据有限，精度较低。特征重要性分析表明，晚季SAR（VV、VH）和光学（红边和短波红外）波段是最具影响力的变量。结果表明，SAR与光学时间序列数据的协同结合集成机器学习，为近实时作物监测提供了稳健且可扩展的框架。该方法为精准农业提供了有价值的见解，并支持印度农业领域的数据驱动政策规划。","Discover Sustainability",77,{"impact":420,"substance":421,"depth":228,"authority":122,"freshness":123,"relevant":34,"comment":479},"该研究将SAR与光学时序数据结合集成机器学习，实现93%早期作物分类精度，方法可扩展、结论可靠，对农业遥感监测有实质参考价值。",[481],{"name":476,"url":473},[234,235,39,483,484],"遥感","作物分类",{"code":161,"slug":239,"name":240,"path":241,"parent_code":143},[],{"status":58,"locked":26,"version":59,"method":60,"evidence":488},{"candidates":489,"agricultural_evidence":65},[490,494,498,503,510,517,521],{"code":161,"score":64,"supported":65,"title":491,"abstract":492,"tags":493},[166],[165,166],[235],{"code":77,"score":78,"supported":65,"title":495,"abstract":496,"tags":497},[],[39,81],[39],{"code":262,"score":78,"supported":65,"title":499,"abstract":500,"tags":502},[],[501,444],"精准农业",[234],{"code":504,"score":162,"supported":65,"title":505,"abstract":506,"tags":509},"A2",[],[507,508],"小麦","wheat",[],{"code":511,"score":162,"supported":65,"title":512,"abstract":513,"tags":516},"A6",[],[514,515],"甘蔗","sugarcane",[],{"code":384,"score":87,"supported":65,"title":518,"abstract":519,"tags":520},[],[373],[],{"code":139,"score":522,"supported":26,"title":523,"abstract":524,"tags":525},2,[],[],[484,483],[527,528],"Sentinel-1 Sentinel-2 作物分类","Google Earth Engine 机器学习 作物制图","Sentinel-1Sentinel-2作物分类-4321","10.1007\u002Fs43621-026-04839-6",{"doi":530,"openalex_id":532,"authors":533,"venue":476,"cited_by_count":103,"oa_url":473,"card":547,"direction":288,"ingested_from":110},"W7219792303",[534,537,540,542,545],{"name":535,"orcid":536},"Rajeev Ranjan Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-2670-6189",{"name":538,"orcid":539},"Jayanta Das","https:\u002F\u002Forcid.org\u002F0000-0003-0995-9114",{"name":541,"orcid":21},"Jadhav Rajaram Anna",{"name":543,"orcid":544},"Abhishek Danodia","https:\u002F\u002Forcid.org\u002F0000-0002-5724-8790",{"name":546,"orcid":21},"Dipanwita Haldar",{"tldr":548,"method":549,"finding":550,"direction":217,"opportunity":551},"融合Sentinel-1 SAR与Sentinel-2光学时序，用集成机器学习实现印度早季作物类型高","GEE平台，RF与GBT集成学习，1141个地面样本，SAR-光学多时相数据。","GBT精度最高（总体93%，Kappa 0.90），SAR与光学结合显著优于单传感器。","可探索更早物候期、小样本作物（如芥菜、甘蔗）的SAR-光学特征优化与迁移学习。","2026-10-06T23:30:38.288174Z",{"id":554,"title":555,"url":556,"summary":557,"summary_zh":558,"content":21,"source_name":559,"source_url":556,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":477,"score_detail":560,"sources":562,"tags":564,"primary_topic":21,"secondary_topics":566,"classification":567,"search_phrases":599,"slug":602,"view_count":103,"doi":603,"paper":604,"created_at":625},4311,"Cross-Regional Digital Soil Mapping of OpenLandMap-Derived USDA Soil Texture Classes Using Remote Sensing and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16192147","Soil is a fundamental environmental resource that supports food production and sustainable agricultural systems. Soil’s texture is a key soil property that affects its capacity to hold water, infiltration rate, fertility, erosion risk, and crop productivity. Traditionally, it is determined using hydrometer or pipette analysis. These laboratory procedures are costly and time-consuming, typically requiring approximately two working days, which limits their practicality for large-scale assessments. This paper proposes a cross-regional digital soil texture classification system based on remote sensing data and machine learning in Malaysia and Pakistan. The two countries were chosen because they represent contrasting environmental conditions: Malaysia has humid tropical conditions, and Pakistan has arid and semi-arid conditions. The OpenLandMap United States Department of Agriculture (USDA) soil texture classes served as the reference labels, and the spectral bands from Landsat, together with spectral indices and Shuttle Radar Topography Mission (SRTM) elevation, were used as predictor variables. The three ensemble models, including Random Forest (RF), XGBoost, and CatBoost, were evaluated for multi-class classification of USDA soil texture. The main Landsat-based Malaysia–Pakistan dataset produced the best results, with RF achieving the highest accuracy of 71.45%, XGBoost 71.31%, and CatBoost 67.33%. Additional experiments using 2025 Landsat 8\u002F9 and Sentinel-2 imagery achieved lower accuracies of 63.00% and 56.10%, respectively, while five-fold spatial block cross-validation produced a mean accuracy of 59.27 ± 1.84%. To strengthen dataset reliability, representative OpenLandMap-derived soil texture classes were externally validated using PCRWR sand–silt–clay fractions plotted on the USDA soil texture triangle and independent Malaysian soil resource references. The results of the feature importance analysis showed that elevation, Bare Soil Index (BSI), Normalized Difference Water Index (NDWI), and Normalized Difference Vegetation Index (NDVI) were important predictors for classifying OpenLandMap-derived USDA soil texture classes. These show that the Landsat-based spectral and terrain features, when used in conjunction with ensemble learning, could assist cross-regional soil texture classification for the USDA. However, class imbalance, spectral overlap between soil texture classes, temporal variability, and resolution mismatch between satellite predictors and soil labels remain important challenges. The findings of this study provide a useful foundation for large-scale soil texture mapping and future spatial validation across different environmental regions.","土壤是支撑粮食生产和可持续农业系统的基础环境资源。土壤质地是影响土壤持水能力、入渗速率、肥力、侵蚀风险和作物生产力的关键土壤属性。传统上，土壤质地采用比重计法或吸管法测定。这些实验室方法成本高、耗时长，通常需要约两个工作日，限制了其在大规模评估中的实用性。本文提出了一种基于遥感数据和机器学习的跨区域数字土壤质地分类系统，研究区域为马来西亚和巴基斯坦。选择这两个国家是因为它们代表了截然不同的环境条件：马来西亚属于湿润热带条件，巴基斯坦属于干旱和半干旱条件。以OpenLandMap提供的美国农业部（USDA）土壤质地类别作为参考标签，以Landsat光谱波段、光谱指数和航天飞机雷达地形测绘任务（SRTM）高程数据作为预测变量。评估了三种集成模型，包括随机森林（RF）、XGBoost和CatBoost，用于USDA土壤质地的多类分类。基于Landsat的马来西亚—巴基斯坦主数据集取得了最佳结果，RF达到最高精度71.45%，XGBoost为71.31%，CatBoost为67.33%。使用2025年Landsat 8\u002F9和Sentinel-2影像的额外实验分别取得了较低的精度，为63.00%和56.10%，而五折空间块交叉验证产生的平均精度为59.27 ± 1.84%。为增强数据集可靠性，使用PCRWR砂—粉—黏粒比例绘制在USDA土壤质地三角图上，并结合独立的马来西亚土壤资源参考资料，对具有代表性的OpenLandMap衍生土壤质地类别进行了外部验证。特征重要性分析结果表明，高程、裸土指数（BSI）、归一化差异水体指数（NDWI）和归一化差异植被指数（NDVI）是分类OpenLandMap衍生USDA土壤质地类别的重要预测因子。这些结果表明，基于Landsat的光谱和地形特征与集成学习结合使用时，可辅助USDA的跨区域土壤质地分类。然而，类别不平衡、土壤质地类别之间的光谱重叠、时间变异性以及卫星预测因子与s之间的分辨率不匹配","Agriculture",{"impact":420,"substance":421,"depth":228,"authority":122,"freshness":123,"relevant":34,"comment":561},"跨区域遥感与集成学习土壤质地分类研究，方法扎实、结论有参考价值，但精度有限，属细分领域进展。",[563],{"name":559,"url":556},[321,234,165,483,565],"土壤制图",[],{"status":380,"locked":26,"version":59,"method":60,"evidence":568},{"candidates":569,"agricultural_evidence":65,"reason":598},[570,577,581,585,590,594],{"code":571,"score":64,"supported":65,"title":572,"abstract":574,"tags":576},"H2",[573],"soil",[575,573],"土壤",[565],{"code":161,"score":64,"supported":65,"title":578,"abstract":579,"tags":580},[166],[165,166],[165],{"code":139,"score":64,"supported":65,"title":582,"abstract":583,"tags":584},[153],[483,153],[483],{"code":52,"score":87,"supported":65,"title":586,"abstract":587,"tags":589},[],[588],"干旱",[],{"code":384,"score":87,"supported":65,"title":591,"abstract":592,"tags":593},[],[373],[],{"code":262,"score":522,"supported":26,"title":595,"abstract":596,"tags":597},[],[],[321,234],"多个产业证据相当，需要确认主归属",[600,601],"OpenLandMap USDA 土壤质地","Landsat 土壤质地 机器学习","OpenLandMapUSDA土壤质地-4311","10.3390\u002Fagriculture16192147",{"doi":603,"openalex_id":605,"authors":606,"venue":559,"cited_by_count":103,"oa_url":556,"card":620,"direction":217,"ingested_from":110},"W7220411242",[607,609,611,614,617],{"name":608,"orcid":21},"Umair Maqsood",{"name":610,"orcid":21},"Fatima Iftikhar",{"name":612,"orcid":613},"Kashif Sattar","https:\u002F\u002Forcid.org\u002F0000-0001-8620-9419",{"name":615,"orcid":616},"Iftikhar A. Ahmad","https:\u002F\u002Forcid.org\u002F0000-0003-3719-2387",{"name":618,"orcid":619},"Madini Obad Alassafi","https:\u002F\u002Forcid.org\u002F0000-0001-9919-8368",{"tldr":621,"method":622,"finding":623,"direction":217,"opportunity":624},"用Landsat光谱与地形特征结合集成学习，实现马来西亚与巴基斯坦跨区域USDA土壤质地分类。","Landsat光谱波段、光谱指数与SRTM高程，RF\u002FXGBoost\u002FCatBo","RF精度最高71.45%，高程、BSI、NDWI、NDVI为关键预测因子，跨区域可行但精度受限。","可探索多源遥感融合与类别不平衡校正，提升跨气候区土壤质地制图精度与迁移能力。","2026-10-06T23:30:20.282911Z",{"id":627,"title":628,"url":629,"summary":630,"summary_zh":631,"content":21,"source_name":632,"source_url":629,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":477,"score_detail":633,"sources":635,"tags":637,"primary_topic":642,"secondary_topics":645,"classification":646,"search_phrases":662,"slug":665,"view_count":34,"doi":666,"paper":667,"created_at":684},4304,"A novel phenotyping approach for reconciling precision and variance in disease severity estimates from high-resolution imaging","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs13007-026-01593-8","Abstract Accurate quantification of plant disease is essential for resistance breeding, variety testing, and precision agriculture, yet visual ratings are limited by subjectivity, low precision, and restricted throughput. Image-based phenotyping can address these limitations, but field applications are challenging due to spatial heterogeneity and miniature diagnostic features. High-resolution imagery with a limited field of view and a shallow depth of field is therefore needed, restricting the analyzed leaf area. This introduces a fundamental trade-off: high-resolution images provide precise local measurements of disease, but spot-level estimates can be highly variable within experimental units. A key challenge is therefore to understand this variability and to develop sampling strategies that translate precise local observations into reliable plot-level measurements. Here, we analyzed spot-level estimates of septoria tritici blotch and brown rust severity derived from 16,650 images acquired in 15 experimental plots over two consecutive days to quantify the statistical distribution and spatial dependence of local estimates of disease. High-resolution macro-scale images were obtained at multiple positions around a plot and at multiple heights. Focus bracketing was evaluated as a practical strategy to increase the sampled leaf area without additional operator effort. Autocorrelation in severity estimates within focal image stacks and across positions within a plot was comparable, with 10 focal stack images or 10 positions per plot contributing approximately 2.5 independent observations each. Modeling plot-level severity as a latent Beta-distributed variable provided robust estimates of mean disease severity and its associated uncertainty, highlighting the importance of dense spatial sampling, particularly at advanced stages of disease development. Obtaining a precise understanding of the correlation structure and an accurate quantification of achievable precision gains from repeated measures will depend on larger experiments. Nevertheless, our results indicate that combining dense spatial sampling with focus bracketing and appropriate hierarchical statistical models can substantially improve the precision of plot-level disease estimates without sacrificing throughput.","摘要 植物病害的准确定量对于抗性育种、品种测试和精准农业至关重要，然而视觉评级受主观性、低精度和通量受限的制约。基于图像的表型分析可以解决这些局限，但田间应用因空间异质性和微小诊断特征而面临挑战。因此需要具有有限视场和浅景深的高分辨率图像，这限制了可分析的叶面积。这引入了一个根本性的权衡：高分辨率图像可提供病害的精确局部测量，但样点水平的估计值在试验单元内可能高度变异。因此，一个关键挑战是理解这种变异性，并开发采样策略，将精确的局部观测转化为可靠的小区水平测量。本研究分析了由连续两天在15个试验小区获取的16，650张图像得出的小麦叶枯病（septoria tritici blotch）和褐锈病（brown rust）严重度的样点水平估计值，以量化病害局部估计值的统计分布和空间依赖性。在小区周围的多个位置和多个高度获取高分辨率宏观尺度图像。评估了焦点堆叠（focus bracketing）作为一种实用策略，以在不增加操作者负担的情况下增加采样叶面积。焦点图像堆栈内以及小区内不同位置之间严重度估计值的自相关性相当，每个小区10张焦点堆栈图像或10个位置各贡献约2.5个独立观测值。将小区水平严重度建模为潜在的Beta分布变量，提供了病害平均严重度及其相关不确定性的稳健估计，凸显了密集空间采样的重要性，尤其是在病害发展的后期阶段。要精确理解相关结构并准确量化重复测量可实现的精度提升，将依赖于更大规模的试验。尽管如此，我们的结果表明，将密集空间采样与焦点堆叠及适当的层次统计模型相结合，可以在不牺牲通量的情况下大幅提高小区水平病害估计的精度。","Plant Methods",{"impact":420,"substance":121,"depth":228,"authority":122,"freshness":33,"relevant":34,"comment":634},"基于16650张高分辨率图像量化病害严重度分布与空间相关性，提出密集采样结合焦点包围曝光与分层统计模型提升小区级病害估计精度，方法新颖、数据规模可观，对作物抗病育种与精准农业有参考价值。",[636],{"name":632,"url":629},[234,638,639,640,641],"抗病育种","病害检测","植物表型","高分辨率成像",{"code":504,"slug":508,"name":507,"path":643,"parent_code":644},"\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":58,"locked":26,"version":59,"method":60,"evidence":647},{"candidates":648,"agricultural_evidence":65},[649,653,657],{"code":262,"score":78,"supported":65,"title":650,"abstract":651,"tags":652},[],[501,444],[234],{"code":504,"score":87,"supported":65,"title":654,"abstract":655,"tags":656},[],[507],[],{"code":658,"score":34,"supported":26,"title":659,"abstract":660,"tags":661},"F2",[],[],[638],[663,664],"小麦 叶斑病 表型分析","高分辨率成像 病害严重度","小麦叶斑病表型分析-4304","10.1186\u002Fs13007-026-01593-8",{"doi":666,"openalex_id":668,"authors":669,"venue":632,"cited_by_count":103,"oa_url":629,"card":679,"direction":217,"ingested_from":110},"W7220426885",[670,673,676],{"name":671,"orcid":672},"Radek Zenkl","https:\u002F\u002Forcid.org\u002F0009-0000-4099-1361",{"name":674,"orcid":675},"Bruce Alan McDonald","https:\u002F\u002Forcid.org\u002F0000-0002-5332-2172",{"name":677,"orcid":678},"Jonas Anderegg","https:\u002F\u002Forcid.org\u002F0000-0002-3345-4696",{"tldr":680,"method":681,"finding":682,"direction":217,"opportunity":683},"通过高分辨率成像与焦点包围曝光，结合分层统计模型，提升小区级病害严重度估计精度。","16,650张高分辨率图像，焦点包围曝光，空间自相关与Beta分层模型。","密集空间采样与焦点包围曝光可显著提高小区级病害估计精度且不牺牲通量。","可探索自适应采样策略与多尺度模型，平衡精度与通量并推广至其他病害。","2026-10-06T23:30:17.356095Z",{"id":686,"title":687,"url":688,"summary":689,"summary_zh":690,"content":21,"source_name":691,"source_url":688,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":692,"score_detail":693,"sources":697,"tags":699,"primary_topic":701,"secondary_topics":702,"classification":713,"search_phrases":770,"slug":773,"view_count":103,"doi":774,"paper":775,"created_at":794},4302,"BIG DATA IN AGRONOMY: TECHNOLOGIES, APPLICATIONS, BENEFITS AND CHALLENGES","https:\u002F\u002Fdoi.org\u002F10.4238\u002Fk6hcgw77","Big Data is becoming an important component of modern agronomy by enabling the integration, processing and analysis of large, diverse and continuously generated datasets for improved agricultural decision-making. Agricultural Big Data is generated from multiple sources, including remote sensing satellites, Unmanned Aerial Vehicles (UAVs), Internet of Things (IoT) sensors, weather stations, farm machinery, field observations and historical databases. The integration of these data sources with Geographic Information Systems (GIS), cloud computing, Artificial Intelligence (AI) and Machine Learning (ML) enables the identification of spatial and temporal patterns that are difficult to detect using conventional approaches. Big Data applications in agronomy include climate and weather prediction, pest and disease management, soil health and nutrient management, irrigation scheduling, crop yield prediction, precision agriculture, crop insurance and weed management. Examples from India and other regions demonstrate the application of satellite imagery, UAV-based sensing, IoT systems, crop-growth models and machine-learning algorithms for field-scale and regional agricultural decision making. Big Data analytics can improve resource-use efficiency, support predictive and real-time monitoring, strengthen agricultural risk assessment and facilitate site-specific management. However, effective implementation is constrained by challenges such as high infrastructure and operational costs, data quality and interoperability issues, data privacy and ownership concerns, limited rural digital infrastructure, inadequate technical skills and increasing requirements for data storage and computing. Therefore, the effective integration of Big Data with agronomic knowledge and decision-support systems can contribute to more precise, efficient and sustainable agricultural production while addressing emerging challenges related to climate variability, resource scarcity and food security.","大数据正成为现代农学的重要组成部分，它能够整合、处理和分析大规模、多样化且持续生成的数据集，从而改进农业决策。农业大数据来源于多种渠道，包括遥感卫星、无人机（UAV）、物联网（IoT）传感器、气象站、农业机械、田间观测和历史数据库。将这些数据源与地理信息系统（GIS）、云计算、人工智能（AI）和机器学习（ML）相结合，能够识别传统方法难以发现的空间和时间模式。大数据在农学中的应用包括气候与天气预测、病虫害管理、土壤健康与养分管理、灌溉调度、作物产量预测、精准农业、作物保险和杂草管理。来自印度及其他地区的案例展示了卫星影像、基于无人机的遥感、物联网系统、作物生长模型和机器学习算法在田块尺度和区域农业决策中的应用。大数据分析可以提高资源利用效率，支持预测性和实时监测，加强农业风险评估，并促进因地制宜的管理。然而，有效实施受到诸多挑战的制约，如高昂的基础设施和运营成本、数据质量和互操作性问题、数据隐私和所有权担忧、农村数字基础设施有限、技术技能不足以及数据存储和计算需求不断增加。因此，将大数据与农学知识和决策支持系统有效整合，有助于实现更精准、高效和可持续的农业生产，同时应对气候变异性、资源稀缺和粮食安全等方面的新兴挑战。","Genetics and Molecular Research",76,{"impact":228,"substance":694,"depth":695,"authority":122,"freshness":33,"relevant":34,"comment":696},20,17,"系统综述农业大数据技术、应用与挑战，信息密度高，对智慧农业决策有参考价值，但属综述性论文，非突破性成果。",[698],{"name":691,"url":688},[234,235,700,501,128],"农业大数据",{"code":161,"slug":239,"name":240,"path":241,"parent_code":143},[703,708],{"code":704,"slug":705,"name":706,"path":707,"parent_code":143},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"code":709,"slug":710,"name":711,"path":712,"parent_code":143},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":58,"locked":26,"version":59,"method":60,"evidence":714},{"candidates":715,"agricultural_evidence":65},[716,720,727,734,738,742,746,750,754,758,764],{"code":161,"score":25,"supported":65,"title":717,"abstract":718,"tags":719},[],[165,166,249],[235],{"code":704,"score":123,"supported":65,"title":721,"abstract":722,"tags":726},[],[723,724,725],"地理信息","GIS","geographic information",[],{"code":709,"score":123,"supported":65,"title":728,"abstract":729,"tags":733},[],[730,731,732],"物联网","internet of things","IoT",[],{"code":262,"score":33,"supported":65,"title":735,"abstract":736,"tags":737},[],[501,444],[234,501],{"code":139,"score":78,"supported":65,"title":739,"abstract":740,"tags":741},[],[483,153],[128],{"code":77,"score":162,"supported":65,"title":743,"abstract":744,"tags":745},[],[39,81],[],{"code":571,"score":162,"supported":65,"title":747,"abstract":748,"tags":749},[],[575,573],[],{"code":133,"score":162,"supported":65,"title":751,"abstract":752,"tags":753},[],[131,134],[],{"code":267,"score":441,"supported":65,"title":755,"abstract":756,"tags":757},[],[700],[700],{"code":759,"score":87,"supported":65,"title":760,"abstract":761,"tags":763},"F3",[],[762],"养分管理",[],{"code":765,"score":87,"supported":65,"title":766,"abstract":767,"tags":769},"F5",[],[768],"农业机械",[],[771,772],"农业大数据 遥感 物联网","机器学习 作物产量预测","农业大数据遥感物联网-4302","10.4238\u002Fk6hcgw77",{"doi":774,"openalex_id":776,"authors":777,"venue":691,"cited_by_count":103,"oa_url":688,"card":788,"direction":793,"ingested_from":110},"W7220374836",[778,780,782,784,786],{"name":779,"orcid":21},"Kodavali Aswini",{"name":781,"orcid":21},"Raju Marimuthu",{"name":783,"orcid":21},"Guru Gurusamy",{"name":785,"orcid":21},"Kannan Pandian",{"name":787,"orcid":21},"Anandham Rangasamy",{"tldr":789,"method":790,"finding":791,"direction":288,"opportunity":792},"综述农学大数据的技术、应用、效益与挑战，强调多源数据融合支撑精准农业决策。","整合遥感、无人机、物联网、GIS、云计算与AI\u002FML的多源农业数据分析。","大数据可提升资源效率与实时监测，但受成本、数据质量、隐私和农村数字基建制约。","可研究低成本边缘计算与数据互操作标准，破解小农户场景下大数据落地瓶颈。","智慧农业 \u002F 农业物联网","2026-10-06T23:30:11.880721Z",{"id":796,"title":797,"url":798,"summary":799,"summary_zh":800,"content":21,"source_name":417,"source_url":798,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":801,"score_detail":802,"sources":804,"tags":806,"primary_topic":21,"secondary_topics":809,"classification":810,"search_phrases":830,"slug":833,"view_count":522,"doi":834,"paper":835,"created_at":849},4287,"The effect of train-test data splitting ratio on yield prediction from multispectral UAV imagery: effective reduction of training ratio with algorithm selection for single- and multi-date models","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10464-0","Abstract Context Optimizing the ratio of data required for training spectral grain yield (GY) prediction models is critical for efficient sampling of reference data, but has been rarely addressed so far. Given the high costs for collecting ground truth data, standard data splitting ratios which use the majority of the data for training and the rest for testing the models should be minimized, but in turn may affect prediction accuracy. Methods Therefore, this study evaluated 11 different train-test data splitting ratios (TSR), ranging from using 5% to 95% of the data for training, and the remaining portion as test sets. Models with six different machine learning algorithms were compared in winter wheat breeding trials conducted with each several thousand plots in two locations in Germany over a period of four years. The input data consisted of the (unmanned aerial vehicle) UAV-based NDRE index data from individual measurements dates as well as multi-date combinations. Results The results indicate that GY prediction remained relatively stable when decreasing TSR to about 0.30. Conversely, multi-date models tended to benefit more from higher TSR than single-date models. Support vector machine and random forest algorithms demonstrated relative advantage both for higher TSR and multi-date models, whereas partial least squares and ridge regression were the best algorithms for lowest TSR-values. Furthermore, analysis via repeated data splitting revealed minimum R² variability at a TSR of 0.30, but substantially increased variance at higher TSR values. Conclusions It is concluded that decreasing TSR while considering algorithm selection can potentially reduce costs without compromising prediction accuracy, therefore making spectral phenotyping methods more accessible and ready-to-use, whereas the absolute number of data points requires additional examination.","摘要 背景 优化光谱谷物产量（grain yield, GY）预测模型所需数据的训练-测试比例对于高效采集参考数据至关重要，但迄今鲜有研究涉及。鉴于获取地面真实数据的高昂成本，应尽量减少使用大部分数据进行模型训练、其余部分用于测试的标准数据划分比例，但这反过来可能影响预测精度。方法 因此，本研究评估了11种不同的训练-测试数据划分比例（train-test data splitting ratio, TSR），训练数据占比从5%到95%不等，剩余部分作为测试集。在德国两个地点、为期四年、每个试验包含数千个小区的冬小麦育种试验中，比较了采用六种不同机器学习算法的模型。输入数据包括来自单次测量日期的基于无人机（unmanned aerial vehicle, UAV）的NDRE指数数据以及多日期组合数据。结果 结果表明，当TSR降低至约0.30时，GY预测仍保持相对稳定。相反，多日期模型比单日期模型更倾向于从较高的TSR中获益。支持向量机（support vector machine）和随机森林（random forest）算法在较高TSR和多日期模型中均表现出相对优势，而偏最小二乘回归（partial least squares）和岭回归（ridge regression）在最低TSR值下表现最佳。此外，通过重复数据划分分析发现，TSR为0.30时R²变异性最小，但在较高TSR值下方差显著增大。结论 研究表明，在考虑算法选择的前提下降低TSR有可能在不影响预测精度的情况下减少成本，从而使光谱表型分析方法更加易于获取和实用，但数据点的绝对数量仍需进一步研究。",75,{"impact":247,"substance":121,"depth":228,"authority":32,"freshness":123,"relevant":34,"comment":803},"基于四年多点小麦育种试验系统评估训练集比例与算法选择对无人机多光谱产量预测的影响，方法扎实、结论实用，对降低表型数据采集成本有直接参考价值。",[805],{"name":417,"url":798},[234,807,165,808,483],"产量预测","小麦育种",[],{"status":380,"locked":26,"version":59,"method":60,"evidence":811},{"candidates":812,"agricultural_evidence":65,"reason":598},[813,818,822,826],{"code":504,"score":25,"supported":65,"title":814,"abstract":815,"tags":817},[],[507,816,508],"winter wheat",[808],{"code":139,"score":25,"supported":65,"title":819,"abstract":820,"tags":821},[437],[],[807,483],{"code":161,"score":78,"supported":65,"title":823,"abstract":824,"tags":825},[],[165,166],[165],{"code":262,"score":34,"supported":26,"title":827,"abstract":828,"tags":829},[],[],[234],[831,832],"无人机 多光谱 小麦 产量预测","冬小麦 育种 遥感 机器学习","无人机多光谱小麦产量预测-4287","10.1007\u002Fs11119-026-10464-0",{"doi":834,"openalex_id":836,"authors":837,"venue":417,"cited_by_count":103,"oa_url":798,"card":844,"direction":217,"ingested_from":110},"W7220450104",[838,841],{"name":839,"orcid":840},"Lukas Prey","https:\u002F\u002Forcid.org\u002F0000-0001-6287-4596",{"name":842,"orcid":843},"Patrick Noack","https:\u002F\u002Forcid.org\u002F0000-0002-0226-6609",{"tldr":845,"method":846,"finding":847,"direction":217,"opportunity":848},"研究不同训练-测试数据划分比例对无人机多光谱小麦产量预测的影响，发现可降低训练比例。","基于德国四年两地点冬小麦育种试验，用UAV NDRE指数和六种机器学习算法比较1","训练比例降至约0.30时预测精度稳定，多时相模型更受益于高比例，SVM和随机森林较优。","可探索在更低训练比例下结合主动学习或迁移学习，进一步降低地面采样成本并验证跨地点泛化性。","2026-10-06T23:30:02.110164Z",{"id":851,"title":852,"url":853,"summary":854,"summary_zh":855,"content":21,"source_name":856,"source_url":853,"published_at":23,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":857,"score_detail":858,"sources":860,"tags":862,"primary_topic":868,"secondary_topics":872,"classification":873,"search_phrases":905,"slug":908,"view_count":103,"doi":909,"paper":910,"created_at":921},4324,"Holistic Modeling Approaches for Supporting Sustainability Transitions","https:\u002F\u002Fdoi.org\u002F10.48565\u002Fbonndoc-1000","Agricultural and environmental decisions in agroecological systems are made under profound uncertainty, with complex trade-offs between productivity, ecological integrity and human well-being. This cumulative habilitation thesis brings together 32 peer-reviewed studies that develop and apply holistic modeling approaches to support such decisions and, more broadly, sustainability transitions. The first part advances decision analytical methods in agroecology. Structured decision models, Bayesian networks and Monte Carlo simulations, informed by expert-elicited probabilities, are used to evaluate interventions under incomplete information. Applications span agroforestry adoption and carbon offset schemes, horticultural management strategies, water resource management, flood-based farming systems, agricultural policy and household nutrition, and climate change adaptation and mitigation, with case studies in Africa, Asia, Latin America and Europe. These models identify key trade-offs, risks and leverage points, and value-of-information analyses show where further measurements would most improve decisions. The second part advances methods in transdisciplinary research. It integrates participatory approaches, stakeholder engagement, local and Indigenous knowledge, and holistic sustainability assessment frameworks to co-create context-specific solutions and to bridge science, policy and practice. Together, the studies show that combining probabilistic modeling with participatory processes produces decision support that is both scientifically rigorous and practically relevant. The thesis concludes with implications for policy and with future research directions, including hybrid models that combine expert knowledge with emerging data, multi-criteria trade-off assessment, and the scaling of agroecological practices.","农业生态系统中的农业与环境决策是在深刻的不确定性下作出的， productivity）、生态完整性与人类福祉之间存在复杂的权衡。这本累积性资格论文汇集了32项同行评审研究，这些研究开发并应用整体性建模方法来支持此类决策，并在更广泛意义上支持可持续性转型。第一部分推进了农业生态学中的决策分析方法。结构化决策模型、贝叶斯网络和蒙特卡洛模拟，结合专家引出的概率信息，被用于在不完全信息下评估干预措施。应用范围涵盖农林复合经营采纳与碳补偿方案、园艺管理策略、水资源管理、洪水-based耕作系统、农业政策与家庭营养，以及气候变化适应与减缓，案例研究遍及非洲、亚洲、拉丁美洲和欧洲。这些模型识别了关键权衡、风险和杠杆点，信息价值分析则揭示了进一步的测量在哪些方面最能改善决策。第二部分推进了跨学科研究的方法。它整合了参与式方法、利益相关者参与、地方与原住民知识，以及整体可持续性评估框架，以共同创造情境特定的解决方案，并弥合科学、政策与实践之间的鸿沟。总体而言，这些研究表明，将概率建模与参与式过程相结合，能够产生既科学严谨又具有实际相关性的决策支持。论文最后提出了政策启示和未来研究方向，包括将专家知识与新兴数据相结合的混合模型、多标准权衡评估，以及农业生态实践的规模化推广。","bonndoc (University of Bonn)",74,{"impact":247,"substance":121,"depth":228,"authority":32,"freshness":33,"relevant":34,"comment":859},"波恩大学系统综述32项同行评审研究，方法学扎实但偏理论，对国内农业信息化实践的直接指导有限。",[861],{"name":856,"url":853},[863,864,865,866,867],"决策支持","农业生态","气候变化适应","贝叶斯网络","跨学科研究",{"code":56,"slug":869,"name":870,"path":871,"parent_code":21},"environment","资源环境与气候变化","\u002Ftopic\u002Fenvironment",[],{"status":874,"locked":26,"version":59,"method":60,"evidence":875},"partial",{"candidates":876,"agricultural_evidence":65,"reason":904},[877,883,887,893,899],{"code":878,"score":78,"supported":65,"title":879,"abstract":880,"tags":882},"H6",[],[864,881],"agroecology",[864],{"code":52,"score":78,"supported":65,"title":884,"abstract":885,"tags":886},[],[73,74],[865],{"code":133,"score":162,"supported":65,"title":888,"abstract":889,"tags":892},[],[890,891],"水资源","water resource",[],{"code":894,"score":162,"supported":65,"title":895,"abstract":896,"tags":898},"J1",[],[41,897],"agricultural policy",[],{"code":161,"score":441,"supported":65,"title":900,"abstract":901,"tags":903},[],[902],"decision support",[863],"一级领域明确，二级方向需要细分",[906,907],"波恩大学 农业生态 建模","参与式研究 可持续转型","波恩大学农业生态建模-4324","10.48565\u002Fbonndoc-1000",{"doi":909,"openalex_id":911,"authors":912,"venue":856,"cited_by_count":103,"oa_url":853,"card":916,"direction":288,"ingested_from":110},"W7220376706",[913],{"name":914,"orcid":915},"Cory Whitney","https:\u002F\u002Forcid.org\u002F0000-0003-4988-4583",{"tldr":917,"method":918,"finding":919,"direction":288,"opportunity":920},"综合32项研究，用整体建模方法支持农业生态系统的可持续转型决策。","贝叶斯网络、蒙特卡洛模拟、结构化决策模型与参与式方法结合。","概率建模与参与式过程结合可产出科学严谨且实用的决策支持。","可探索专家知识与新兴数据融合的混合模型，及多准则权衡评估的规模化应用。","2026-10-06T23:30:43.643777Z",{"id":923,"title":924,"url":925,"summary":926,"summary_zh":927,"content":21,"source_name":928,"source_url":925,"published_at":929,"category":24,"cover_url":21,"hotness":25,"is_selected":26,"score":857,"score_detail":930,"sources":932,"tags":934,"primary_topic":938,"secondary_topics":939,"classification":940,"search_phrases":988,"slug":991,"view_count":103,"doi":992,"paper":993,"created_at":1013},4318,"Soil Health Under Climate Change: A Review of Climate Impacts, Sustainable Management Strategies, and Future Directions","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu181910109","Soil health is fundamental to sustainable agriculture, crop productivity, and vital ecosystem services. However, climate change increasingly threatens the functional integrity of soil due to rising temperatures, altered precipitation patterns, elevated atmospheric carbon dioxide levels, and extreme weather events. These factors accelerate soil degradation and disrupt the physical, chemical, and biological processes essential for maintaining soil health. This review synthesizes recent evidence regarding the impacts of climate change on soil health and crop production, while also evaluating sustainable management strategies designed to enhance agricultural resilience. Techniques such as conservation agriculture, organic matter management, diversified cropping systems, and integrated nutrient management can improve soil structure, nutrient cycling, water retention, carbon sequestration, and overall crop productivity. Furthermore, emerging technologies offer new opportunities for real-time, site-specific, and data-driven soil management. These technologies include remote sensing, geographic information systems, artificial intelligence, digital agriculture, and advanced soil monitoring tools. Additionally, policy and socioeconomic factors—particularly financial incentives, extension services, and institutional support—are critical in encouraging farmers to adopt these practices. Despite recent advancements, challenges such as economic barriers, technological limitations, regional variability, and a lack of long-term evidence hinder the widespread implementation of sustainable soil health practices. This review provides an integrated perspective that links climate-driven changes in soil’s physical, chemical, and biological properties with sustainable management practices, emerging technologies, and policy support. It highlights the interactions and trade-offs among these components to promote climate-resilient and sustainable agricultural systems.","土壤健康是可持续农业、作物生产力及关键生态系统服务的基础。然而，气候变化正日益威胁土壤的功能完整性，其原因包括气温升高、降水模式改变、大气二氧化碳浓度上升以及极端天气事件。这些因素加速了土壤退化，并破坏了维持土壤健康所必需的物理、化学和生物过程。本文综述了关于气候变化对土壤健康和作物生产影响的最新证据，同时评估了旨在增强农业韧性的可持续管理策略。保护性农业、有机质管理、多样化种植制度及综合养分管理等措施能够改善土壤结构、养分循环、水分保持、碳固存及整体作物生产力。此外，新兴技术为实时、因地制宜和数据驱动的土壤管理提供了新机遇。这些技术包括遥感、地理信息系统、人工智能、数字农业及先进土壤监测工具。同时，政策和社会经济因素——尤其是财政激励、推广服务和制度支持——对于鼓励农民采用这些做法至关重要。尽管近期取得了进展，但经济障碍、技术限制、区域差异性及长期证据缺乏等挑战仍阻碍着可持续土壤健康实践的广泛实施。本文提供了一个综合视角，将气候驱动的土壤物理、化学和生物性质变化与可持续管理实践、新兴技术及政策支持相联系，着重阐述了这些组成部分之间的相互作用与权衡关系，以促进气候韧性及可持续农业系统的发展。","Sustainability","2026-10-03T00:00:00Z",{"impact":228,"substance":694,"depth":695,"authority":122,"freshness":162,"relevant":34,"comment":931},"综述系统整合气候变化对土壤健康的影响与保护性农业、数字农业等应对策略，具行业参考价值，但属综述类论文、时效一般，适合主题聚合而非头条精选。",[933],{"name":928,"url":925},[321,426,935,73,936,937],"保护性农业","土壤健康","土壤监测",{"code":56,"slug":869,"name":870,"path":871,"parent_code":21},[],{"status":874,"locked":26,"version":59,"method":60,"evidence":941},{"candidates":942,"agricultural_evidence":65,"reason":904},[943,947,951,957,961,965,969,973,979,984],{"code":571,"score":64,"supported":65,"title":944,"abstract":945,"tags":946},[573],[575,573],[936],{"code":52,"score":64,"supported":65,"title":948,"abstract":949,"tags":950},[74],[73,74],[73],{"code":384,"score":25,"supported":65,"title":952,"abstract":953,"tags":956},[],[373,954,955],"sustainable agriculture","conservation agriculture",[935],{"code":262,"score":78,"supported":65,"title":958,"abstract":959,"tags":960},[],[321,322],[321],{"code":139,"score":78,"supported":65,"title":962,"abstract":963,"tags":964},[],[483,153],[426],{"code":704,"score":162,"supported":65,"title":966,"abstract":967,"tags":968},[],[723,725],[],{"code":759,"score":87,"supported":65,"title":970,"abstract":971,"tags":972},[],[762],[],{"code":974,"score":87,"supported":65,"title":975,"abstract":976,"tags":978},"H4",[],[977],"carbon sequestration",[],{"code":878,"score":87,"supported":65,"title":980,"abstract":981,"tags":983},[],[982],"生态系统服务",[],{"code":161,"score":87,"supported":65,"title":985,"abstract":986,"tags":987},[],[249],[],[989,990],"土壤健康 气候变化 可持续管理","保护性农业 农业遥感 土壤健康 土壤监测","土壤健康气候变化可持续管理-4318","10.3390\u002Fsu181910109",{"doi":992,"openalex_id":994,"authors":995,"venue":928,"cited_by_count":103,"oa_url":925,"card":1008,"direction":217,"ingested_from":110},"W7220388580",[996,999,1002,1005],{"name":997,"orcid":998},"Muhammad Irfan","https:\u002F\u002Forcid.org\u002F0000-0002-7685-3689",{"name":1000,"orcid":1001},"Gamal El Afandi","https:\u002F\u002Forcid.org\u002F0000-0002-5235-026X",{"name":1003,"orcid":1004},"Santosh Sapkota","https:\u002F\u002Forcid.org\u002F0009-0007-2794-182X",{"name":1006,"orcid":1007},"Md Rafique Ahasan Chawdhery","https:\u002F\u002Forcid.org\u002F0000-0002-2010-3555",{"tldr":1009,"method":1010,"finding":1011,"direction":108,"opportunity":1012},"综述气候变化对土壤健康的影响，并评估可持续管理、新兴技术与政策支持。","文献综述，整合遥感、GIS、AI、数字农业等土壤监测技术。","保护性农业、有机质管理和多样化种植可提升土壤健康与气候韧性。","可量化不同区域气候情景下数字技术对土壤碳固持与作物产量的协同增效机制。","2026-10-06T23:30:23.095864Z",{"id":1015,"title":1016,"url":1017,"summary":1018,"summary_zh":1019,"content":21,"source_name":1020,"source_url":1017,"published_at":23,"category":24,"cover_url":21,"hotness":1021,"is_selected":26,"score":1022,"score_detail":1023,"sources":1025,"tags":1029,"primary_topic":1031,"secondary_topics":1035,"classification":1038,"search_phrases":1076,"slug":1079,"view_count":103,"doi":1080,"paper":1081,"created_at":1091},4310,"Comprehensive remote sensing and machine learning framework for multi-regional rice yield forecasting under hydroclimatic variability in Sahelian Niger","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149579","It is crucial to forecast rice yields effectively in order to improve agricultural planning and resilience to climate change in the Sahel, where production is greatly affected by hydroclimatic variability. This research has developed an integrated framework combining remote sensing analysis and machine learning to assess the variability in rice production in Niamey, Dosso, Tillaberi and Diffa, in Niger, over the period 2010–2025. They combined Landsat-derived NDVI and EVI with parameters such as evapotranspiration, precipitation, temperature, humidity, solar radiation, soil moisture, cultivated area, year and season. We processed and harmonised the datasets using Google Earth Engine and Python. We then evaluated four regression algorithms separately, Random Forest (RF), k-nearest neighbours (KNN), support vector regression (SVR) and XGBoost (XGB), for each region. The correlation analysis revealed modest positive links between rice yield and the NDVI (r = 0.27) and the EVI (r = 0.14), while a strong correlation was observed between the NDVI and the EVI (r = 0.80). The vegetation indices showed marked seasonal and interannual variability, generally exhibiting higher values during the wet season. Model performance varied considerably from one region to another","在萨赫勒地区，有效预测水稻产量对于改善农业规划和增强气候变化适应能力至关重要，因为该地区的生产在很大程度上受到水文气候变率的制约。本研究开发了一个集成框架，将遥感分析与机器学习相结合，以评估尼日尔尼亚美、多索、蒂拉贝里和迪法在2010—2025年期间水稻产量的变异性。研究将基于Landsat的归一化植被指数（NDVI）和增强型植被指数（EVI）与蒸散发、降水、温度、湿度、太阳辐射、土壤水分、耕地面积、年份和季节等参数相结合。利用Google Earth Engine和Python对数据集进行了处理和协调。随后，针对每个地区分别评估了四种回归算法：随机森林（RF）、k近邻（KNN）、支持向量回归（SVR）和XGBoost（XGB）。相关分析显示，水稻产量与NDVI（r = 0.27）和EVI（r = 0.14）之间存在弱正相关，而NDVI与EVI之间则观察到强相关（r = 0.80）。植被指数表现出明显的季节性和年际变异性，通常在湿季呈现较高值。模型性能在不同地区之间差异显著。","Zenodo (CERN European Organization for Nuclear Research)",25,72,{"impact":247,"substance":421,"depth":695,"authority":122,"freshness":123,"relevant":34,"comment":1024},"基于Landsat植被指数与四种机器学习模型的多区域水稻产量预测研究，方法扎实、数据跨度长，但属区域性学术成果，对国内农业信息化有方法借鉴价值。",[1026,1027],{"name":1020,"url":1017},{"name":1020,"url":1028},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[234,235,1030,807,483],"水稻",{"code":1032,"slug":1033,"name":1030,"path":1034,"parent_code":644},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice",[1036,1037],{"code":161,"slug":239,"name":240,"path":241,"parent_code":143},{"code":139,"slug":140,"name":141,"path":142,"parent_code":143},{"status":58,"locked":26,"version":59,"method":60,"evidence":1039},{"candidates":1040,"agricultural_evidence":65},[1041,1045,1049,1053,1057,1063,1067,1072],{"code":139,"score":420,"supported":65,"title":1042,"abstract":1043,"tags":1044},[153],[483,153],[807,483],{"code":1032,"score":64,"supported":65,"title":1046,"abstract":1047,"tags":1048},[1033],[1030,1033],[1030],{"code":161,"score":64,"supported":65,"title":1050,"abstract":1051,"tags":1052},[166],[165,166],[235],{"code":571,"score":162,"supported":65,"title":1054,"abstract":1055,"tags":1056},[],[575,573],[],{"code":133,"score":162,"supported":65,"title":1058,"abstract":1059,"tags":1062},[],[1060,1061],"蒸散发","evapotranspiration",[],{"code":52,"score":162,"supported":65,"title":1064,"abstract":1065,"tags":1066},[],[73,74],[],{"code":894,"score":87,"supported":65,"title":1068,"abstract":1069,"tags":1071},[],[1070],"农业规划",[],{"code":262,"score":34,"supported":26,"title":1073,"abstract":1074,"tags":1075},[],[],[234],[1077,1078],"尼日尔 水稻 遥感 产量预测","Landsat NDVI 水稻 机器学习","尼日尔水稻遥感产量预测-4310","10.5281\u002Fzenodo.23149579",{"doi":1080,"openalex_id":1082,"authors":1083,"venue":1020,"cited_by_count":103,"oa_url":1017,"card":1086,"direction":217,"ingested_from":110},"W7220391503",[1084],{"name":1085,"orcid":21},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":1087,"method":1088,"finding":1089,"direction":217,"opportunity":1090},"结合遥感植被指数与机器学习，预测尼日尔萨赫勒四地区2010–2025年水稻产量。","Landsat NDVI\u002FEVI 加气象土壤变量，GEE与Python处理，比较","NDVI\u002FEVI与产量仅弱相关，模型精度区域差异大，植被指数呈明显季节与年际波动。","可引入时序深度学习与迁移学习，解决跨区域泛化差及植被指数解释力弱的问题。","2026-10-06T23:30:20.077977Z",{"id":1093,"title":1094,"url":1095,"summary":1096,"summary_zh":1097,"content":21,"source_name":1020,"source_url":1095,"published_at":23,"category":24,"cover_url":21,"hotness":1021,"is_selected":26,"score":1022,"score_detail":1098,"sources":1100,"tags":1104,"primary_topic":1108,"secondary_topics":1109,"classification":1116,"search_phrases":1146,"slug":1149,"view_count":103,"doi":1150,"paper":1151,"created_at":1170},4294,"GIS- and Remote Sensing-Based Identification of Suitable Agricultural Waste Landfill Sites for Climate-Smart Agriculture in Ilorin, Nigeria","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23168428","Abstract Lack of a designated landfill for agricultural waste management (AWM) in Ilorin municipalities led to indiscriminate disposal of agricultural waste within the city and the only existing Sokoto-Ayekale general solid waste dumpsite, posing environmental and public health risks while undermining climate-smart agriculture (CSA). The study identifies suitable landfill sites for AWM by integrating Geographic Information System (GIS), Remote Sensing (RS), and Multi-Criteria Decision Analysis (MCDA) to locate environmentally and climate-resilient sites. Spatial data employed for the study include Shuttle Radar Topography Mission (SRTM), Landsat 9 imagery, Digital Elevation Model (DEM), road networks, waterbodies, built-up areas, soil quality, slope, and geology, which were processed in ArcGIS 10.3 to develop constraint thematic suitability maps. The Analytical Hierarchy Process (AHP) was employed to derive criterion weights, and the Weighted Linear Combination (WLC) was used to generate the map. AHP consistency ratio (CR) was used to validate the model’s consistency (CR=0.016), which falls within the acceptable CR \u003C0.1. The AHP weighted results were 0.41, 0.2, 0.14, 0.10, 0.08, and 0.07 for waterbodies, built-up area, slope, soil quality, geology, and road network, respectively. Maps were created for each criterion, reclassified, and integrated using the weighted linear combination method to generate an overall AWM suitability map. The study identified four potential locations for AWM. Approximately 507.23 km² are unsuitable, 1204.21 km² are marginally suitable, 4899.28 km² are moderately suitable, and 2021.7 km² are highly suitable for AWM landfill development. The findings present a scientifically based decision-support framework to guide policymakers, environmental agencies, and urban planners in developing sustainable AWM strategies that minimize environmental risk while advancing climate-smart agriculture. Keywords: Agricultural waste, Climate-smart agriculture, Landfill, Suitability, Sustainability","摘要 伊洛林各市镇缺乏用于农业废弃物管理（AWM）的指定填埋场，导致农业废弃物在城市内部及唯一现有的索科托-阿耶卡莱一般固体废弃物倾倒场被随意处置，既构成环境和公共健康风险，也削弱了气候智慧型农业（CSA）。本研究通过整合地理信息系统（GIS）、遥感（RS）和多准则决策分析（MCDA），识别适用于AWM的填埋场选址，以确定具有环境韧性和气候韧性的场址。研究采用的空间数据包括航天飞机雷达地形测绘任务（SRTM）数据、Landsat 9影像、数字高程模型（DEM）、道路网络、水体、建成区、土壤质量、坡度和地质，并在ArcGIS 10.3中进行处理以生成约束性专题适宜性图。采用层次分析法（AHP）推导准则权重，并运用加权线性组合（WLC）生成地图。使用AHP一致性比率（CR）验证模型的一致性（CR=0.016），该值处于可接受的CR\u003C0.1范围内。AHP加权结果分别为：水体0.41、建成区0.2、坡度0.14、土壤质量0.10、地质0.08、道路网络0.07。针对每个准则生成地图，经重分类后采用加权线性组合方法进行整合，生成总体AWM适宜性图。研究确定了四个潜在的AWM选址。约507.23 km²不适宜，1204.21 km²勉强适宜，4899.28 km²中等适宜，2021.7 km²高度适宜建设AWM填埋场。研究结果为政策制定者、环境机构和城市规划者提供了基于科学的决策支持框架，以指导制定可持续的AWM策略，在降低环境风险的同时推进气候智慧型农业。关键词：农业废弃物，气候智慧型农业，填埋场，适宜性，可持续性",{"impact":247,"substance":421,"depth":695,"authority":122,"freshness":123,"relevant":34,"comment":1099},"GIS与遥感结合MCDA为农业废弃物填埋选址提供决策框架，方法规范、数据翔实，但属区域性案例研究，公共影响有限。",[1101,1102],{"name":1020,"url":1095},{"name":1020,"url":1103},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23168429",[483,1105,1106,724,1107],"农业废弃物","气候智慧农业","选址评估",{"code":704,"slug":705,"name":706,"path":707,"parent_code":143},[1110,1115],{"code":1111,"slug":1112,"name":1113,"path":1114,"parent_code":56},"H5","waste","面源污染与废弃物利用","\u002Ftopic\u002Fenvironment\u002Fwaste",{"code":139,"slug":140,"name":141,"path":142,"parent_code":143},{"status":58,"locked":26,"version":59,"method":60,"evidence":1117},{"candidates":1118,"agricultural_evidence":65},[1119,1123,1128,1132,1138,1142],{"code":704,"score":228,"supported":65,"title":1120,"abstract":1121,"tags":1122},[724],[723,724,725],[724],{"code":1111,"score":64,"supported":65,"title":1124,"abstract":1126,"tags":1127},[1125],"agricultural waste",[1105,1125],[1105],{"code":139,"score":64,"supported":65,"title":1129,"abstract":1130,"tags":1131},[153],[483,153],[483],{"code":262,"score":1133,"supported":65,"title":1134,"abstract":1136,"tags":1137},11,[1135],"smart agriculture",[1135],[],{"code":571,"score":162,"supported":65,"title":1139,"abstract":1140,"tags":1141},[],[575,573],[],{"code":52,"score":34,"supported":26,"title":1143,"abstract":1144,"tags":1145},[],[],[1106],[1147,1148],"Ilorin 农业废弃物 填埋场 选址","GIS 遥感 农业废弃物 填埋场","Ilorin农业废弃物填埋场选址-4294","10.5281\u002Fzenodo.23168428",{"doi":1150,"openalex_id":1152,"authors":1153,"venue":1020,"cited_by_count":103,"oa_url":1095,"card":1165,"direction":793,"ingested_from":110},"W7220389353",[1154,1156,1158,1160,1163],{"name":1155,"orcid":21},"Saheed Mohammed Ishaq",{"name":1157,"orcid":21},"Alamin Adedeji Adenekan",{"name":1159,"orcid":21},"Ibrahim Dauda",{"name":1161,"orcid":1162},"Afeez Oladeji Amoo","https:\u002F\u002Forcid.org\u002F0000-0002-0412-9333",{"name":1164,"orcid":21},"Nureni Babatunde Amoo",{"tldr":1166,"method":1167,"finding":1168,"direction":108,"opportunity":1169},"用GIS、遥感和多准则决策为尼日利亚Ilorin筛选农业废弃物填埋场适宜选址。","GIS\u002FRS结合AHP与加权线性组合，基于DEM、Landsat 9等空间数据。","识别出4处潜在选址，约2021.7 km²高度适宜，模型一致性良好。","可将该选址框架与温室气体排放、运输成本及气候情景耦合，拓展到其他区域。","2026-10-06T23:30:07.715522Z"]