[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1602":3,"related-1602":71},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":8,"secondary_topics":29,"classification":30,"search_phrases":48,"slug":51,"view_count":21,"doi":52,"paper":53,"created_at":70},1602,"Agricultural workers as key practitioners for agricultural technology adoption in California's Central Valley","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104899","Agricultural workers as key practitioners for agricultural technology adoption in California's Central Valley。Agricultural Systems",null,"Agricultural Systems","2026-09-03T00:00:00Z","论文",10,false,71,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},18,20,16,14,3,1,"聚焦加州农业工人技术采纳，对国内农业技术推广有借鉴意义，但地域性强，时效性一般。",[24],{"name":9,"url":6},[26,27,28],"智慧农业","农业技术推广","劳动力",[],{"status":31,"locked":13,"version":32,"method":33,"evidence":34},"unclassified","2026-10-22.2","rules",{"candidates":35,"agricultural_evidence":46,"reason":47},[36,41],{"code":37,"score":21,"supported":13,"title":38,"abstract":39,"tags":40},"G1",[],[],[27],{"code":42,"score":21,"supported":13,"title":43,"abstract":44,"tags":45},"I1",[],[],[26],true,"缺少足够的主题证据",[49,50],"农业技术推广 智慧农业 劳动力","农业技术推广 智慧农业","农业技术推广智慧农业劳动力-1602","10.1016\u002Fj.agsy.2026.104899",{"doi":52,"openalex_id":54,"authors":55,"venue":9,"cited_by_count":68,"oa_url":8,"card":8,"direction":8,"ingested_from":69},"W7207544986",[56,58,61,63,65],{"name":57,"orcid":8},"Kimberly J. Gibson",{"name":59,"orcid":60},"Leigh Bernacchi","https:\u002F\u002Forcid.org\u002F0000-0002-1447-0447",{"name":62,"orcid":8},"Karen Aceves",{"name":64,"orcid":8},"Shobha Khanna",{"name":66,"orcid":67},"Joshua H. Viers","https:\u002F\u002Forcid.org\u002F0000-0001-7957-7942",0,"openalex","2026-09-04T23:30:05.540505Z",{"total":72,"page":21,"page_size":72,"items":73},6,[74,125,211,290,343,424],{"id":75,"title":76,"url":77,"summary":78,"summary_zh":8,"content":8,"source_name":79,"source_url":77,"published_at":80,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":81,"score_detail":82,"sources":86,"tags":88,"primary_topic":8,"secondary_topics":92,"classification":93,"search_phrases":105,"slug":108,"view_count":20,"doi":109,"paper":110,"created_at":124},3563,"Can information increase farmers’ willingness to pay for digital agricultural technologies? A survey experiment on agricultural drones in rural China","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jrurstud.2026.104423","Can information increase farmers’ willingness to pay for digital agricultural technologies? A survey experiment on agricultural drones in rural China。Journal of Rural Studies","Journal of Rural Studies","2026-09-25T00:00:00Z",78,{"impact":18,"substance":83,"depth":16,"authority":19,"freshness":84,"relevant":21,"comment":85},21,9,"基于中国农村调查实验，实证信息干预对农户数字农业技术支付意愿的影响，方法规范、结论有政策参考价值，值得进入每日精选。",[87],{"name":79,"url":77},[89,26,27,90,91],"数字农业","农业无人机","农户支付意愿",[],{"status":31,"locked":13,"version":32,"method":33,"evidence":94},{"candidates":95,"agricultural_evidence":46,"reason":47},[96,101],{"code":42,"score":97,"supported":13,"title":98,"abstract":99,"tags":100},2,[],[],[89,26],{"code":37,"score":21,"supported":13,"title":102,"abstract":103,"tags":104},[],[],[27],[106,107],"农业无人机 农户 支付意愿","信息干预 调查实验","农业无人机农户支付意愿-3563","10.1016\u002Fj.jrurstud.2026.104423",{"doi":109,"openalex_id":111,"authors":112,"venue":79,"cited_by_count":68,"oa_url":77,"card":8,"direction":123,"ingested_from":69},"W7214363671",[113,115,118,121],{"name":114,"orcid":8},"Zhixian Lu",{"name":116,"orcid":117},"Huang Chen","https:\u002F\u002Forcid.org\u002F0000-0002-2284-8083",{"name":119,"orcid":120},"Yi-Xiang Wang","https:\u002F\u002Forcid.org\u002F0000-0001-5697-0717",{"name":122,"orcid":8},"Kaixing Huang","数字乡村与农业信息化","2026-09-26T23:30:38.738490Z",{"id":126,"title":127,"url":128,"summary":129,"summary_zh":130,"content":8,"source_name":131,"source_url":128,"published_at":132,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":133,"score_detail":134,"sources":138,"tags":140,"primary_topic":144,"secondary_topics":150,"classification":157,"search_phrases":191,"slug":194,"view_count":72,"doi":195,"paper":196,"created_at":210},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","2026-09-24T00:00:00Z",80,{"impact":16,"substance":135,"depth":16,"authority":136,"freshness":84,"relevant":21,"comment":137},22,13,"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。",[139],{"name":131,"url":128},[141,26,142,27,143],"数字乡村","农业人工智能","小农户",{"code":145,"slug":146,"name":147,"path":148,"parent_code":149},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[151],{"code":152,"slug":153,"name":154,"path":155,"parent_code":156},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":158,"locked":13,"version":32,"method":33,"evidence":159},"classified",{"candidates":160,"agricultural_evidence":46},[161,167,176,182,186],{"code":145,"score":162,"supported":46,"title":163,"abstract":165,"tags":166},15,[164],"smallholder",[143,164],[143],{"code":152,"score":12,"supported":46,"title":168,"abstract":169,"tags":175},[],[170,171,172,173,174],"机器学习","计算机视觉","machine learning","artificial intelligence","computer vision",[142],{"code":42,"score":177,"supported":46,"title":178,"abstract":179,"tags":181},7,[],[89,180],"digital agriculture",[26],{"code":37,"score":21,"supported":13,"title":183,"abstract":184,"tags":185},[],[],[27],{"code":187,"score":21,"supported":13,"title":188,"abstract":189,"tags":190},"I6",[],[],[141],[192,193],"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":195,"openalex_id":197,"authors":198,"venue":131,"cited_by_count":68,"oa_url":128,"card":204,"direction":123,"ingested_from":69},"W7214205238",[199,201],{"name":200,"orcid":8},"Pravangkar Boruah",{"name":202,"orcid":203},"Rubul Kumar Bania","https:\u002F\u002Forcid.org\u002F0000-0001-6294-0231",{"tldr":205,"method":206,"finding":207,"direction":208,"opportunity":209},"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。","农业人工智能与决策模型","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":212,"title":213,"url":214,"summary":215,"summary_zh":216,"content":8,"source_name":217,"source_url":214,"published_at":132,"category":11,"cover_url":8,"hotness":218,"is_selected":13,"score":219,"score_detail":220,"sources":224,"tags":229,"primary_topic":232,"secondary_topics":236,"classification":237,"search_phrases":263,"slug":266,"view_count":177,"doi":267,"paper":268,"created_at":289},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。","Land Use Policy",25,87,{"impact":135,"substance":221,"depth":222,"authority":19,"freshness":84,"relevant":21,"comment":223},23,19,"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。",[225,226],{"name":217,"url":214},{"name":227,"url":228},"Apollo","https:\u002F\u002Fdoi.org\u002F10.17863\u002Fcam.134741",[26,142,27,230,231],"覆盖作物","气候智慧农业",{"code":42,"slug":233,"name":234,"path":235,"parent_code":156},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":158,"locked":13,"version":32,"method":33,"evidence":238},{"candidates":239,"agricultural_evidence":46},[240,245,250,254,259],{"code":42,"score":84,"supported":46,"title":241,"abstract":243,"tags":244},[242],"smart agriculture",[],[26],{"code":246,"score":21,"supported":13,"title":247,"abstract":248,"tags":249},"A7",[],[],[230],{"code":37,"score":21,"supported":13,"title":251,"abstract":252,"tags":253},[],[],[27],{"code":255,"score":21,"supported":13,"title":256,"abstract":257,"tags":258},"H7",[],[],[231],{"code":152,"score":21,"supported":13,"title":260,"abstract":261,"tags":262},[],[],[142],[264,265],"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","10.1016\u002Fj.landusepol.2026.108336",{"doi":267,"openalex_id":269,"authors":270,"venue":217,"cited_by_count":68,"oa_url":214,"card":283,"direction":288,"ingested_from":69},"W7214223143",[271,274,276,278,281],{"name":272,"orcid":273},"Callum Alexander","https:\u002F\u002Forcid.org\u002F0009-0007-5275-4583",{"name":275,"orcid":8},"Aiora Zabala",{"name":277,"orcid":8},"Andreas Kontoleon",{"name":279,"orcid":280},"Shalamar Armstrong","https:\u002F\u002Forcid.org\u002F0000-0002-1326-9936",{"name":282,"orcid":8},"Anuoluwa Sangotayo",{"tldr":284,"method":285,"finding":286,"direction":208,"opportunity":287},"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。","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","2026-09-25T23:30:09.887867Z",{"id":291,"title":292,"url":293,"summary":294,"summary_zh":295,"content":8,"source_name":296,"source_url":293,"published_at":297,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":298,"score_detail":299,"sources":303,"tags":305,"primary_topic":308,"secondary_topics":309,"classification":310,"search_phrases":325,"slug":328,"view_count":20,"doi":329,"paper":330,"created_at":342},3273,"Determinants of the Use and Extent of Digital Agriculture Among Moroccan Farmers","https:\u002F\u002Fdoi.org\u002F10.22004\u002Fag.econ.412776","Digital agriculture, driven by advancements in financial engineering, holds significant potential to enhance productivity and sustainability in agricultural production. However, the adoption and extent of these technologies fundamentally depend on farmers’ willingness to accept and use them. While recent studies have identified key factors influencing the adoption of digital agriculture, to the best of our knowledge, no academic study has specifically examined the determinants of both the use and the extent of adoption, particularly within the Moroccan context. This study investigates both the adoption and intensity of digital agriculture among a sample of 250 Moroccan farmers, utilizing a paper-based survey and two econometric approaches: a multinomial logit model and the Heckman model. The findings reveal that farmer age has a negative and significant impact on digital agriculture adoption. At the same time, crop type and risk aversion emerge as significant positive determinants of both the adoption and the extent of smart farming use. Specifically, technology adoption is mainly influenced by age, crop type, and risk aversion, whereas the extent of use is primarily driven by risk aversion and the type of crops cultivated. These results highlight the importance of implementing targeted policies and training programs to promote broader and more intensive use of digital agriculture technologies. Additionally, these findings open up avenues for further research aimed at better understanding the underlying factors that shape Moroccan farmers' behavior toward digital agriculture adoption.","由金融工程进步所驱动的数字农业，在提升农业生产率与可持续性方面具有巨大潜力。然而，这些技术的采用及其程度从根本上取决于农民接受和使用它们的意愿。尽管近期研究已识别出影响数字农业采用的关键因素，但据我们所知，尚无学术研究专门考察使用与采用程度的决定因素，尤其是在摩洛哥背景下。本研究基于250名摩洛哥农民的样本，采用纸质问卷调查和两种计量经济学方法——多项Logit模型与Heckman模型——考察了数字农业的采用情况及使用强度。研究发现，农民年龄对数字农业采用具有显著负向影响。与此同时，作物类型与风险规避对智慧农业的采用及使用程度均呈现显著正向决定作用。具体而言，技术采用主要受年龄、作物类型和风险规避影响，而使用程度则主要由风险规避和所种植作物类型驱动。这些结果凸显了实施有针对性的政策与培训项目以促进数字农业技术更广泛、更深入应用的重要性。此外，这些发现为后续研究开辟了方向，有助于更深入理解塑造摩洛哥农民数字农业采用行为的潜在因素。","AgEcon Search (University of Minnesota, USA)","2026-09-21T00:00:00Z",72,{"impact":300,"substance":83,"depth":301,"authority":136,"freshness":84,"relevant":21,"comment":302},12,17,"基于250户摩洛哥农户调查，用多项Logit与Heckman模型揭示年龄、作物类型与风险规避对数字农业采纳及使用强度的差异化影响，方法规范、结论有新意，对发展中国家数字农业推广有借鉴价值。",[304],{"name":296,"url":293},[89,26,27,306,307],"农户采纳","摩洛哥农业",{"code":42,"slug":233,"name":234,"path":235,"parent_code":156},[],{"status":158,"locked":13,"version":32,"method":33,"evidence":311},{"candidates":312,"agricultural_evidence":46},[313,317,321],{"code":42,"score":222,"supported":46,"title":314,"abstract":315,"tags":316},[180],[26,89,180],[89,26],{"code":37,"score":21,"supported":13,"title":318,"abstract":319,"tags":320},[],[],[27],{"code":145,"score":21,"supported":13,"title":322,"abstract":323,"tags":324},[],[],[306],[326,327],"摩洛哥 农户 数字农业","Heckman 模型 智慧农业 采纳","摩洛哥农户数字农业-3273","10.22004\u002Fag.econ.412776",{"doi":329,"openalex_id":331,"authors":332,"venue":296,"cited_by_count":68,"oa_url":293,"card":337,"direction":288,"ingested_from":69},"W7213999238",[333,335],{"name":334,"orcid":8},"Adil Jouamaa Mohammed",{"name":336,"orcid":8},"I. Mubarak Abdulilah",{"tldr":338,"method":339,"finding":340,"direction":123,"opportunity":341},"研究摩洛哥250位农民采用数字农业及其使用程度的决定因素。","纸质问卷，多项Logit模型与Heckman模型。","年龄负向影响采用，作物类型和风险规避正向影响采用与使用程度。","可针对不同作物和风险偏好农民设计差异化推广策略，并开展跨区域比较研究。","2026-09-23T23:30:11.088448Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":349,"source_url":346,"published_at":350,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":351,"score_detail":352,"sources":354,"tags":356,"primary_topic":359,"secondary_topics":364,"classification":365,"search_phrases":401,"slug":404,"view_count":21,"doi":405,"paper":406,"created_at":423},1526,"Resource constraint effects on water smart agricultural practice retention in Guatemala’s Dry Corridor","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44279-026-00752-8","Water smart agriculture (WSA)—improved crop, soil, and water retention practices that support climate adaptation—is increasingly promoted in dryland countries such as Guatemala, where Catholic Relief Services (CRS) has used farmer field schools (FFS) to disseminate WSA knowledge. However, resource constraints can limit how much knowledge participants retain. We examine how perceived resource constraint affects retention of four WSA practices (permanent mulching, responsible nutrient management, integrated armyworm management, and visual soil evaluation) six months to a year after FFS participation, drawing on cognitive load theory to explain why some practices are harder to acquire than others. Using multivariate probit regression on survey data from 507 beneficiaries who attended CRS farmer field schools in Guatemala’s Dry Corridor between 2020 and 2021, we find that retention declines as both the cognitive load of a practice and participants’ perceived resource constraints increase, though education levels partially offset the former’s effect. Retention is strongest for practices like permanent mulching that build on locally established methods, and weakest for more cognitively intensive practices targeting long-term soil quality, though land tenure improves retention of the latter. These findings carry practical implications for future programming, which should offset resource constraints long enough for WSA practices to take hold and align guidance with existing agricultural practices and measurement methods, while attending to the pedagogical role of women as household-level trainers.","水资源智慧农业（WSA）——通过改良作物、土壤及保水措施以支持气候适应——正日益在危地马拉等干旱国家推广，天主教救济服务处（CRS）已采用农民田间学校（FFS）传播WSA知识。然而，资源限制可能制约参与者所保留的知识量。本研究探讨感知资源约束如何影响参与FFS后六个月至一年内对四种WSA实践（永久覆盖、负责任养分管理、综合草地贪夜蛾管理及视觉土壤评估）的保留情况，并借鉴认知负荷理论解释为何某些实践较难掌握。基于对2020至2021年间参与CRS在危地马拉干旱走廊举办的农民田间学校的507名受益者的调查数据，采用多元概率比回归分析，我们发现：随着实践的认知负荷及参与者感知资源约束的增加，知识保留率下降，尽管教育水平在一定程度上抵消了前者的影响。对于建立在当地既有方法之上的实践（如永久覆盖），保留效果最强；而对于针对长期土壤质量、认知要求较高的实践，保留效果最弱，但土地权属改善可提升后者的保留率。这些发现对未来项目规划具有实际意义：应提供足够长的资源支持以促使WSA实践扎根，将指导与现有农业实践及测量方法相结合，同时关注女性作为家庭层面培训者的教育作用。","Discover Agriculture","2026-09-02T00:00:00Z",63,{"impact":300,"substance":17,"depth":16,"authority":12,"freshness":20,"relevant":21,"comment":353},"研究农民田间学校知识保留的影响因素，对农业技术推广有参考价值，但地域性强，时效性低。",[355],{"name":349,"url":346},[26,27,357,358],"气候变化适应","农民培训",{"code":255,"slug":360,"name":361,"path":362,"parent_code":363},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",[],{"status":158,"locked":13,"version":32,"method":33,"evidence":366},{"candidates":367,"agricultural_evidence":46},[368,374,378,385,391,397],{"code":255,"score":177,"supported":46,"title":369,"abstract":370,"tags":373},[],[371,372],"气候适应","干旱",[357],{"code":42,"score":177,"supported":46,"title":375,"abstract":376,"tags":377},[],[26,242],[26],{"code":379,"score":72,"supported":46,"title":380,"abstract":381,"tags":384},"H2",[],[382,383],"土壤","soil",[],{"code":386,"score":20,"supported":46,"title":387,"abstract":388,"tags":390},"F3",[],[389],"养分管理",[],{"code":392,"score":20,"supported":46,"title":393,"abstract":394,"tags":396},"H3",[],[395],"水资源",[],{"code":37,"score":21,"supported":13,"title":398,"abstract":399,"tags":400},[],[],[27],[402,403],"农业技术推广 气候变化适应 农民培训 智慧农业","农业技术推广 气候变化适应","农业技术推广气候变化适应农民培训智慧农业-1526","10.1007\u002Fs44279-026-00752-8",{"doi":405,"openalex_id":407,"authors":408,"venue":349,"cited_by_count":68,"oa_url":346,"card":418,"direction":288,"ingested_from":69},"W7205012096",[409,411,413,416],{"name":410,"orcid":8},"Aidé Cuenca Narváez",{"name":412,"orcid":8},"Alixandra Underwood",{"name":414,"orcid":415},"Festus O. Amadu","https:\u002F\u002Forcid.org\u002F0000-0002-9973-7541",{"name":417,"orcid":8},"Tracy Kijewski-Correa",{"tldr":419,"method":420,"finding":421,"direction":123,"opportunity":422},"研究资源约束如何影响危地马拉旱走廊农民对节水农业实践的保留率。","基于认知负荷理论，对507名农民调查数据用多元概率比回归分析。","认知负荷和资源约束增加会降低实践保留，教育可部分抵消，土地权属有助于长期实践保留。","可探索如何通过降低认知负荷和资源约束（如提供长期支持）提高农业技术采纳与保留，尤其关注女性培训者角色。","2026-09-03T23:30:09.613860Z",{"id":425,"title":426,"url":427,"summary":428,"summary_zh":429,"content":8,"source_name":430,"source_url":427,"published_at":431,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":432,"score_detail":433,"sources":436,"tags":438,"primary_topic":441,"secondary_topics":442,"classification":444,"search_phrases":459,"slug":462,"view_count":68,"doi":463,"paper":464,"created_at":478},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",69,{"impact":434,"substance":83,"depth":16,"authority":300,"freshness":12,"relevant":21,"comment":435},8,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[437],{"name":430,"url":427},[26,142,143,439,440],"植物病害识别","可解释性",{"code":145,"slug":146,"name":147,"path":148,"parent_code":149},[443],{"code":152,"slug":153,"name":154,"path":155,"parent_code":156},{"status":158,"locked":13,"version":32,"method":33,"evidence":445},{"candidates":446,"agricultural_evidence":46},[447,451,455],{"code":145,"score":300,"supported":46,"title":448,"abstract":449,"tags":450},[164],[164],[143],{"code":152,"score":12,"supported":46,"title":452,"abstract":453,"tags":454},[174],[],[142,439],{"code":42,"score":21,"supported":13,"title":456,"abstract":457,"tags":458},[],[],[26],[460,461],"农业人工智能 植物病害识别 可解释性 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":463,"openalex_id":465,"authors":466,"venue":430,"cited_by_count":68,"oa_url":427,"card":473,"direction":208,"ingested_from":69},"W7223137323",[467,469,471],{"name":468,"orcid":8},"Akshay Ramgoolam",{"name":470,"orcid":8},"Priya Bundhoo Appadoo",{"name":472,"orcid":8},"Jean-Noël LEspérance",{"tldr":474,"method":475,"finding":476,"direction":208,"opportunity":477},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z"]