[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1747":3,"related-1747":101},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":30,"secondary_topics":36,"classification":48,"search_phrases":75,"slug":78,"view_count":79,"doi":80,"paper":81,"created_at":100},1747,"Artificial Intelligence and Large Language Models in Agricultural Extension: Critical Synthesis of Adoption, Efficacy, and Equity in Smallholder Advisory Systems","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fair\u002F2026\u002Fv27i51723","Agricultural extension and advisory services are undergoing a rapid digital transformation driven by artificial intelligence (AI), machine learning, natural language processing, and, more recently, generative artificial intelligence and large language models (LLMs). These technologies have the potential to address persistent constraints in conventional agricultural extension, including limited adviser-to-farmer ratios, geographical isolation, inadequate localisation of information, and delays in the dissemination of climate, market, and agronomic information. LLM-based advisory systems are particularly significant because they can transform complex agricultural knowledge into conversational, multilingual, and potentially personalised guidance. However, their technical capability does not automatically translate into effective or equitable agricultural outcomes. This review synthesises emerging evidence on the adoption, efficacy, scalability, and equity implications of AI and LLM-based agricultural advisory systems, with particular emphasis on smallholder farmers in low- and middle-income countries. The literature indicates that AI-enabled advisory systems can improve access to timely information, facilitate question-answering, support crop and pest management, and extend the reach of human extension personnel. Emerging platforms such as Farmer.Chat demonstrate the feasibility of large-scale generative AI-enabled advisory delivery, while recent experiments with retrieval-augmented generation indicate promising pathways for improving factual grounding and contextual relevance. Nevertheless, evidence of direct impacts on farm productivity, profitability, resilience, and sustained behavioural change remains considerably weaker than evidence of technological feasibility and user engagement. Major limitations include hallucination, outdated or geographically inappropriate information, language and dialect constraints, weak interoperability with local agricultural databases, limited transparency, data governance concerns, and overreliance on automated recommendations. Equity is an equally important concern because digital access, literacy, gender, income, connectivity, and social norms influence who can benefit from AI-enabled services. The review argues that LLMs should therefore be positioned as augmentation technologies within pluralistic extension systems rather than as substitutes for human advisers. Future agricultural AI systems should combine retrieval from authoritative local knowledge bases, multimodal and multilingual interfaces, human oversight, participatory design, continuous evaluation, responsible data governance, and explicit equity metrics. The future value of AI in agricultural extension will ultimately depend not on model sophistication alone but on the quality of the socio-technical systems in which these technologies are embedded.","农业推广与咨询服务正在经历一场由人工智能（AI）、机器学习、自然语言处理以及近年来兴起的生成式人工智能和大语言模型（LLMs）驱动的快速数字化转型。这些技术有望解决传统农业推广中长期存在的制约因素，包括推广人员与农民比例有限、地理隔离、信息本地化不足，以及气候、市场和农艺信息传播的延迟。基于大语言模型的咨询系统尤为重要，因为它们能够将复杂的农业知识转化为对话式、多语言且可能实现个性化的指导。然而，其技术能力并不会自动转化为有效或公平的农业成果。本综述综合了关于基于AI和大语言模型的农业咨询系统在采用、有效性、可扩展性和公平性影响方面的新兴证据，特别关注低收入和中等收入国家的小农户。文献表明，AI赋能的咨询系统能够改善及时信息的获取，促进问答交互，支持作物与病虫害管理，并扩展人工推广人员的服务范围。诸如Farmer.Chat等新兴平台展示了大规模生成式AI赋能咨询服务的可行性，而近期关于检索增强生成的实验则表明，在改善事实依据和情境相关性方面存在有前景的路径。尽管如此，关于对农业生产率、盈利能力、韧性及持续性行为改变产生直接影响的证据，仍明显弱于关于技术可行性和用户参与度的证据。主要局限包括幻觉现象、信息过时或地理上不适用、语言和方言限制、与当地农业数据库的互操作性薄弱、透明度有限、数据治理问题，以及对自动化建议的过度依赖。公平性同样是一个重要关切，因为数字接入、素养、性别、收入、连通性和社会规范都会影响谁能够从AI赋能的服务中受益。本综述认为，大语言模型应被定位为多元推广体系中的增强技术，而非人类推广人员的替代品。未来的农业AI系统应将检索增强生成与结构化农业知识图谱、",null,"Advances in Research","2026-09-04T00:00:00Z","论文",10,false,82,{"impact":17,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},22,20,13,5,1,"系统综述AI与LLM在农技推广中的应用、效能与公平性，对智慧农业实践有重要参考价值。",[24],{"name":10,"url":6},[26,27,28,29],"农业人工智能","大语言模型","小农户","农技推广",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[37,43],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"G1","extension-transfer","农技推广与成果转化","\u002Ftopic\u002Frural-services\u002Fextension-transfer","G",{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services",{"status":49,"locked":14,"version":50,"method":51,"evidence":52},"classified","2026-10-22.2","rules",{"candidates":53,"agricultural_evidence":56},[54,63,70],{"code":31,"score":55,"supported":56,"title":57,"abstract":59,"tags":62},19,true,[58],"artificial intelligence",[60,61,58],"机器学习","machine learning",[26,27],{"code":38,"score":64,"supported":56,"title":65,"abstract":67,"tags":69},15,[66],"agricultural extension",[68,66],"农业推广",[29],{"code":44,"score":64,"supported":56,"title":71,"abstract":73,"tags":74},[72],"smallholder",[28,72],[28],[76,77],"农业人工智能 大语言模型 农技推广 小农户","农业人工智能 大语言模型","农业人工智能大语言模型农技推广小农户-1747",2,"10.9734\u002Fair\u002F2026\u002Fv27i51723",{"doi":80,"openalex_id":82,"authors":83,"venue":10,"cited_by_count":91,"oa_url":6,"card":92,"direction":98,"ingested_from":99},"W7208785535",[84,87,89],{"name":85,"orcid":86},"Swati Sucharita","https:\u002F\u002Forcid.org\u002F0000-0003-3409-3295",{"name":88,"orcid":9},"Pratima Sachan",{"name":90,"orcid":9},"T. Sravan Kumar",0,{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"综述AI与LLM在农业推广中的应用，评估其采纳、效果与公平性，尤其关注小农户。","系统综述新兴证据，分析AI\u002FLLM咨询系统的采用、效能、可扩展性及公平性。","AI可提升信息获取，但生产力影响证据弱，存在幻觉、公平性等问题，应作为增强而非替代。","农业人工智能与决策模型","研究空白：LLM在农业推广中的实际生产力影响与公平性机制，以及如何结合本地数据与人类顾问实现增强。","数字乡村与农业信息化","openalex","2026-09-05T23:30:36.654266Z",{"total":102,"page":21,"page_size":102,"items":103},6,[104,165,217,284,367,418],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":109,"content":9,"source_name":110,"source_url":107,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":113,"sources":119,"tags":121,"primary_topic":125,"secondary_topics":126,"classification":128,"search_phrases":145,"slug":148,"view_count":91,"doi":149,"paper":150,"created_at":164},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":114,"substance":115,"depth":116,"authority":117,"freshness":13,"relevant":21,"comment":118},8,21,18,12,"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。",[120],{"name":110,"url":107},[122,26,28,123,124],"智慧农业","植物病害识别","可解释性",{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},[127],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":49,"locked":14,"version":50,"method":51,"evidence":129},{"candidates":130,"agricultural_evidence":56},[131,135,140],{"code":44,"score":117,"supported":56,"title":132,"abstract":133,"tags":134},[72],[72],[28],{"code":31,"score":13,"supported":56,"title":136,"abstract":138,"tags":139},[137],"computer vision",[],[26,123],{"code":141,"score":21,"supported":14,"title":142,"abstract":143,"tags":144},"I1",[],[],[122],[146,147],"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":149,"openalex_id":151,"authors":152,"venue":110,"cited_by_count":91,"oa_url":107,"card":159,"direction":96,"ingested_from":99},"W7223137323",[153,155,157],{"name":154,"orcid":9},"Akshay Ramgoolam",{"name":156,"orcid":9},"Priya Bundhoo Appadoo",{"name":158,"orcid":9},"Jean-Noël LEspérance",{"tldr":160,"method":161,"finding":162,"direction":96,"opportunity":163},"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",{"id":166,"title":167,"url":168,"summary":169,"summary_zh":170,"content":9,"source_name":110,"source_url":168,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":171,"score_detail":172,"sources":174,"tags":176,"primary_topic":179,"secondary_topics":180,"classification":182,"search_phrases":197,"slug":200,"view_count":91,"doi":201,"paper":202,"created_at":216},5590,"Evaluation of Concept-Probe Temporal-Stability Audits for Computer Vision Agriculture Disease Classifiers Under Seasonal Phenology Drift: An Interpretability Decay Bound for Smallholder Fungicide Timing","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545234","Concept-probe audits are increasingly used to certify that a crop-disease classifier's internal representations track the pathological concepts a smallholder would act on, but a probe certified at one point in the season may silently decouple from those concepts as phenology shifts the visual statistics of the field. the present analysis treats that decoupling as a formal object. It defines a temporal-stability audit as a sequence of concept-probe accuracies measured across defined phenological windows, and it derives an interpretability decay bound: the rate at which probe accuracy can fall before the fungicide-timing decision it is meant to support becomes unreliable. The bound is expressed as a function of the probe's initial margin, the drift in concept prevalence between windows, and the classifier's sensitivity to the drifted features, and it yields a certified audit interval rather than a single-point certificate. The paper then characterises the operating characteristics of the audit design under a declared variance structure, using a replication-based evaluation of the before-after-control-impact estimator with between-cluster SD = 6.0, residual SD = 4.5 and intraclass correlation = 0.64. Power was estimated across 2000 design cells over cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 54 clusters were required for 5 percentage points at 80% power. The contribution is a decision-theoretic account of when a concept-probe certificate expires, and a design rule for scheduling re-audits across the season.","概念探针审计（concept-probe audit）日益被用于验证作物病害分类器的内部表征是否追踪小农户会据以采取行动的病理学概念，但在生长季某一时点获得认证的探针，可能随着物候变化改变田间的视觉统计特征而悄然与这些概念脱钩。本分析将这种脱钩视为一个形式化对象。它将时间稳定性审计（temporal-stability audit）定义为在既定物候窗口内测量的一系列概念探针准确率，并推导出一个可解释性衰减界限（interpretability decay bound）：即探针准确率在其所支持的杀菌剂施用时机决策变得不可靠之前所能下降的速率。该界限表示为探针初始裕度、窗口间概念流行率漂移以及分类器对漂移特征敏感度的函数，并给出一个经认证的审计区间而非单点认证。随后，本文在声明的方差结构下刻画该审计设计的运行特征，采用基于重复的前后对照影响估计量评估，其中组间标准差 = 6.0、残差标准差 = 4.5、组内相关系数 = 0.64。功效在 2000 个设计单元上估计，聚类数取 8、16、24 和 32，效应量取 3、5 和 8 个百分点；在 80% 功效下达到 5 个百分点需要 54 个聚类。本文的贡献在于从决策论角度阐明概念探针认证何时失效，并给出在整个生长季内安排重新审计的设计规则。",70,{"impact":114,"substance":17,"depth":116,"authority":117,"freshness":13,"relevant":21,"comment":173},"该论文提出概念探针审计的时序稳定性框架与可解释性衰减界，方法新颖、统计设计扎实，但属小众方法论研究，产业影响有限，适合作为专业精选而非头条。",[175],{"name":110,"url":168},[122,26,28,177,178],"作物病害识别","模型审计",{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},[181],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":49,"locked":14,"version":50,"method":51,"evidence":183},{"candidates":184,"agricultural_evidence":56},[185,189,193],{"code":44,"score":64,"supported":56,"title":186,"abstract":187,"tags":188},[72],[28,72],[28],{"code":31,"score":13,"supported":56,"title":190,"abstract":191,"tags":192},[137],[],[177,26],{"code":141,"score":21,"supported":14,"title":194,"abstract":195,"tags":196},[],[],[122],[198,199],"概念探针 时序稳定性 作物病害分类器","杀菌剂 施药时机 可解释性衰减","概念探针时序稳定性作物病害分类器-5590","10.5281\u002Fzenodo.23545234",{"doi":201,"openalex_id":203,"authors":204,"venue":110,"cited_by_count":91,"oa_url":168,"card":211,"direction":96,"ingested_from":99},"W7223088030",[205,207,209],{"name":206,"orcid":9},"Abdi-Basid Idriss Farah",{"name":208,"orcid":9},"Amina Abdillahi Guedi",{"name":210,"orcid":9},"Moussa Omar Youssouf",{"tldr":212,"method":213,"finding":214,"direction":96,"opportunity":215},"提出概念探针时间稳定性审计与可解释性衰减界，判断何时需重新审计。","定义跨物候窗口探针精度序列，推导衰减界，用BACI复制评估统计功效。","5个百分点效应需54个聚类达80%功效，审计证书会随物候漂移过期。","可将衰减界与再审计调度规则嵌入小农户杀菌剂时机决策支持系统，并验证跨作物泛化。","2026-10-22T11:21:08.978348Z",{"id":218,"title":219,"url":220,"summary":221,"summary_zh":222,"content":9,"source_name":223,"source_url":220,"published_at":224,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":225,"score_detail":226,"sources":229,"tags":231,"primary_topic":234,"secondary_topics":235,"classification":237,"search_phrases":265,"slug":268,"view_count":102,"doi":269,"paper":270,"created_at":283},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":116,"substance":17,"depth":116,"authority":19,"freshness":227,"relevant":21,"comment":228},9,"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。",[230],{"name":223,"url":220},[232,122,26,233,28],"数字乡村","农业技术推广",{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},[236],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":49,"locked":14,"version":50,"method":51,"evidence":238},{"candidates":239,"agricultural_evidence":56},[240,244,249,256,260],{"code":44,"score":64,"supported":56,"title":241,"abstract":242,"tags":243},[72],[28,72],[28],{"code":31,"score":13,"supported":56,"title":245,"abstract":246,"tags":248},[],[60,247,61,58,137],"计算机视觉",[26],{"code":141,"score":250,"supported":56,"title":251,"abstract":252,"tags":255},7,[],[253,254],"数字农业","digital agriculture",[122],{"code":38,"score":21,"supported":14,"title":257,"abstract":258,"tags":259},[],[],[233],{"code":261,"score":21,"supported":14,"title":262,"abstract":263,"tags":264},"I6",[],[],[232],[266,267],"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":269,"openalex_id":271,"authors":272,"venue":223,"cited_by_count":91,"oa_url":220,"card":278,"direction":98,"ingested_from":99},"W7214205238",[273,275],{"name":274,"orcid":9},"Pravangkar Boruah",{"name":276,"orcid":277},"Rubul Kumar Bania","https:\u002F\u002Forcid.org\u002F0000-0001-6294-0231",{"tldr":279,"method":280,"finding":281,"direction":96,"opportunity":282},"综述AI农业咨询与诊断系统，聚焦印度东北小农，提出人监督多模态部署架构。","批判性叙述综述，整合2010-2026年数字推广、生成式AI与图像诊断证据。","AI输出技术可行但本地化、安全与田间效果证据不足，需人监督与检索增强。","可开展跨区跨季前瞻评估，连接模型质量与农户决策、产量、公平及成本效益。","2026-09-25T23:30:39.745514Z",{"id":285,"title":286,"url":287,"summary":288,"summary_zh":289,"content":9,"source_name":290,"source_url":287,"published_at":224,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":225,"score_detail":291,"sources":293,"tags":295,"primary_topic":298,"secondary_topics":299,"classification":301,"search_phrases":336,"slug":339,"view_count":20,"doi":340,"paper":341,"created_at":366},3469,"ARTIFICIAL INTELLIGENCE FOR AGRICULTURE: A SYSTEMATIC REVIEW OF FARMERS' PERCEPTIONS, ACCEPTANCE, ADOPTION AND BARRIERS","https:\u002F\u002Fdoi.org\u002F10.64013\u002Fbbasrjlifess.v2026i1.70","Artificial intelligence (AI) is rapidly reshaping agriculture, enabling the application of data for efficient decision-making, precision farming, crop monitoring, pest management, disease detection, smart irrigation, yield prediction, and various aspects of farm automation. Yet, to successfully gain a foothold in farms, factors like farmers' perceptions, their acceptance, desire, and readiness to adopt, as well as the capability to surmount socioeconomic, technological, and institutional challenges, must also make a difference. This article systematically collates the available information on farmers' perspectives on, acceptance of, readiness to adopt, and the obstacles related to AI in the agricultural context. The PRISMA 2020 guideline has been followed to select studies that are related, evaluated for inclusion, and finally, per the criteria, combined into a systematic synthesis. The review mainly discusses the aspects that influence the use of AI, like perceived usefulness, ease of use, trust, digital literacy, affordability, farm size, socioeconomic characteristics, availability of digital infrastructure, and access to agricultural technical advisory services. Main challenges identified involve the high cost of implementing AI, poor connectivity, weak rural infrastructure, low levels of technological knowledge, unavailability of support services, concerns about data privacy, distrust of algorithmic bias, language barriers, and inequalities impacting smallholder farmers. Besides barriers, the review indicates the potential of leveraging AI through extension services, agricultural mobile apps, precision farming, climate-smart agriculture, early-warning systems, and tailored farm advisories. By drawing out technical, behavioral, socioeconomic, and institutional perspectives, the review pinpoints important research questions and presents a farmholder-oriented setup to explain the process of taking up AI in farming. The outcomes can be used by scientific experts, policymakers, extension personnel, and software developers to create low-cost, reliable, and accessible AI systems aimed at promoting sustainable agricultural development.","人工智能（AI）正迅速重塑农业，使数据得以应用于高效决策、精准农业、作物监测、病虫害管理、病害检测、智能灌溉、产量预测以及农场自动化的各个方面。然而，要在农场中成功立足，农民的认知、接受度、采用意愿和准备程度，以及克服社会经济、技术和制度挑战的能力，同样至关重要。本文系统梳理了现有关于农民对农业领域人工智能的看法、接受度、采用准备程度及相关障碍的信息。研究遵循PRISMA 2020指南，筛选相关研究，评估其纳入资格，并最终依据标准进行系统性综合。综述主要探讨了影响人工智能使用的因素，包括感知有用性、易用性、信任、数字素养、可负担性、农场规模、社会经济特征、数字基础设施的可用性以及农业技术咨询服务的获取。识别出的主要挑战包括人工智能实施成本高昂、网络连接不佳、农村基础设施薄弱、技术水平低下、支持服务缺乏、数据隐私担忧、对算法偏见的疑虑、语言障碍以及影响小农户的不平等问题。除障碍外，综述还指出了通过推广服务、农业移动应用、精准农业、气候智慧型农业、预警系统和定制化农场咨询来利用人工智能的潜力。通过梳理技术、行为、社会经济和制度层面的视角，本综述指出了重要的研究问题，并提出了一个以农场主为导向的框架，以解释在农业中采用人工智能的过程。研究结果可供科学专家、政策制定者、推广人员和软件开发者用于创建低成本、可靠且可及的人工智能系统，以促进可持续农业发展。","Journal of Life and Social Sciences",{"impact":116,"substance":17,"depth":116,"authority":19,"freshness":227,"relevant":21,"comment":292},"基于PRISMA的系统综述，系统梳理农户对AI的认知、接受度与采纳障碍，对智慧农业推广与政策设计有实质参考价值。",[294],{"name":290,"url":287},[122,26,296,297,28],"数字素养","农户采纳",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[300],{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":302},{"candidates":303,"agricultural_evidence":56},[304,308,312,318,325,332],{"code":31,"score":117,"supported":56,"title":305,"abstract":306,"tags":307},[58],[58],[26],{"code":44,"score":114,"supported":56,"title":309,"abstract":310,"tags":311},[],[28,72],[297,28],{"code":141,"score":250,"supported":56,"title":313,"abstract":314,"tags":317},[],[315,316],"精准农业","smart agriculture",[122],{"code":319,"score":102,"supported":56,"title":320,"abstract":321,"tags":324},"H3",[],[322,323],"灌溉","irrigation",[],{"code":326,"score":327,"supported":56,"title":328,"abstract":329,"tags":331},"H8",3,[],[330],"可持续农业",[],{"code":261,"score":21,"supported":14,"title":333,"abstract":334,"tags":335},[],[],[296],[337,338],"农民 AI 采纳 障碍","农业人工智能 系统综述","农民AI采纳障碍-3469","10.64013\u002Fbbasrjlifess.v2026i1.70",{"doi":340,"openalex_id":342,"authors":343,"venue":290,"cited_by_count":91,"oa_url":287,"card":360,"direction":365,"ingested_from":99},"W7214189410",[344,346,348,350,352,354,356,358],{"name":345,"orcid":9},"MM JAMEEL",{"name":347,"orcid":9},"M SAEED",{"name":349,"orcid":9},"SA SHER",{"name":351,"orcid":9},"Z ALI",{"name":353,"orcid":9},"Q HAYYAT",{"name":355,"orcid":9},"S KIRBAG",{"name":357,"orcid":9},"S KHAN",{"name":359,"orcid":9},"HN AHMAD",{"tldr":361,"method":362,"finding":363,"direction":98,"opportunity":364},"系统综述农民对农业AI的感知、接受度、采纳意愿及障碍。","遵循PRISMA 2020指南，系统筛选并综合相关文献。","成本、基础设施、数字素养与信任是主要障碍，小农户受影响最大。","可研究低成本、本地化AI采纳模型及小农户数字包容机制。","智慧农业 \u002F 农业物联网","2026-09-25T23:30:09.670568Z",{"id":368,"title":369,"url":370,"summary":371,"summary_zh":372,"content":9,"source_name":373,"source_url":370,"published_at":374,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":375,"score_detail":376,"sources":378,"tags":380,"primary_topic":383,"secondary_topics":384,"classification":386,"search_phrases":401,"slug":404,"view_count":91,"doi":405,"paper":406,"created_at":417},5078,"The Importance of Electronic Communication in the Use of Artificial Intelligence Programs and Applications in the Field of Smart Agriculture from the Point of View of Agricultural Extension Workers in Nineveh Governorate, Iraq","https:\u002F\u002Fdoi.org\u002F10.25125\u002Fijoear-oct-2026-3","The study aimed to identify the level of importance of electronic communication among agricultural extension workers in using artificial intelligence (AI) programs and applications in the field of smart agriculture. It also aimed to identify the most frequently used electronic communication means by extension workers in employing AI programs and applications and rank them according to their relative importance; measure the contribution of electronic communication to improving extension workers' efficiency in using AI programs and applications in smart agriculture; identify individual differences in the importance of electronic communication and the use of AI applications according to selected independent variables, namely gender, educational qualification, years of service, training courses, level of Internet use, and willingness to use social networking sites concerning smart-agriculture technologies; and identify the obstacles facing extension workers in using AI applications in smart agriculture. To obtain the study data, a questionnaire consisting of five parts was used. The first part concerned the respondents' personal and occupational information. The second part included a scale measuring the importance of electronic communication among extension workers in using AI programs and applications in smart agriculture. The third part measured the electronic communication means most frequently used by extension workers in employing AI programs and applications. The fourth part measured the contribution of electronic communication to improving extension workers' efficiency in using AI programs and applications in smart agriculture. The fifth part contained 15 items measuring the major obstacles facing extension workers in using AI applications in smart agriculture. After establishing the face validity of the questionnaire, reliability was assessed using Cronbach's alpha, which reached 0.95. The study population consisted of extension workers in the Nineveh Directorate of Agriculture and its 32 agricultural divisions, totaling 256 extension workers. A simple random sample of 128 extension workers, representing approximately 50% of the population, was selected. The data were coded, tabulated, and analyzed using SPSS. The results showed that the level of importance of electronic communication among extension workers in using AI programs and applications in smart agriculture was moderate and tended toward high, with a percentage of 48%. The item \"Using electronic platforms belonging to agricultural institutions to obtain information related to AI programs and applications\" ranked first, with a mean of 4.34. The contribution of electronic communication to improving extension workers' efficiency in using AI programs and applications in smart agriculture was high, with a percentage of 46%. No significant differences were found in the importance of electronic communication according to gender or training courses, whereas significant differences were reported according to educational qualification, years of occupational service, level of Internet use, and willingness to use social networking sites concerning smart-agriculture technologies. The item \"Poor compatibility of some AI applications with the nature and needs of agricultural extension work in Nineveh Governorate\" was identified as the most important obstacle. The major recommendation was for the Ministry of Agriculture to establish or develop official agricultural electronic platforms affiliated with agricultural and extension institutions and containing updated information on AI applications and their use in different agricultural fields. The main proposed future study was to investigate the obstacles to using AI applications in agricultural extension work in Nineveh Governorate from the perspective of extension workers.","本研究旨在确定农业推广人员在智慧农业领域使用人工智能（AI）程序和应用时电子沟通的重要程度，同时旨在确定推广人员在运用AI程序和应用时最常使用的电子沟通手段，并按其相对重要性进行排序；衡量电子沟通对提高推广人员在智慧农业中使用AI程序和应用效率的贡献；根据选定的自变量，即性别、学历、工龄、培训课程、互联网使用水平以及使用社交网站了解智慧农业技术的意愿，确定电子沟通重要性和AI应用使用方面的个体差异；并确定推广人员在智慧农业中使用AI应用所面临的障碍。为获取研究数据，使用了由五个部分组成的问卷。第一部分涉及受访者的个人和职业信息。第二部分包括一个测量推广人员在智慧农业中使用AI程序和应用时电子沟通重要性的量表。第三部分测量了推广人员在运用AI程序和应用时最常使用的电子沟通手段。第四部分测量了电子沟通对提高推广人员在智慧农业中使用AI程序和应用效率的贡献。第五部分包含15个题项，测量推广人员在智慧农业中使用AI应用面临的主要障碍。在确定问卷的表面效度后，使用克隆巴赫Alpha系数评估信度，达到0.95。研究总体为尼尼微农业局及其32个农业部门的推广人员，共计256名推广人员。采用简单随机抽样选取了128名推广人员，约占总体的50%。数据经编码、制表后使用SPSS进行分析。结果表明，推广人员在智慧农业中使用AI程序和应用时电子沟通的重要程度为中等且倾向于高，占比为48%。题项“使用电子","International Journal of Environmental and Agriculture Research","2026-10-15T00:00:00Z",62,{"impact":114,"substance":116,"depth":64,"authority":117,"freshness":227,"relevant":21,"comment":377},"伊拉克尼尼微省农业推广人员使用AI与电子通信的实证问卷研究，样本128人、信度0.95，结论与障碍分析具体，但属区域性研究，公共影响有限。",[379],{"name":373,"url":370},[122,26,68,381,382],"伊拉克农业","电子通信",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[385],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":49,"locked":14,"version":50,"method":51,"evidence":387},{"candidates":388,"agricultural_evidence":56},[389,393,397],{"code":38,"score":64,"supported":56,"title":390,"abstract":391,"tags":392},[66],[68,66],[68],{"code":141,"score":64,"supported":56,"title":394,"abstract":395,"tags":396},[316],[122,316],[122],{"code":31,"score":117,"supported":56,"title":398,"abstract":399,"tags":400},[58],[58],[26],[402,403],"尼尼微省 农业推广 人工智能","伊拉克 智慧农业 电子平台","尼尼微省农业推广人工智能-5078","10.25125\u002Fijoear-oct-2026-3",{"doi":405,"openalex_id":407,"authors":408,"venue":373,"cited_by_count":91,"oa_url":411,"card":412,"direction":365,"ingested_from":99},"W7222298248",[409],{"name":410,"orcid":9},"Luma Monther Adress","https:\u002F\u002Fijoear.com\u002Fassets\u002Farticles_menuscripts\u002Ffile\u002FIJOEAR-OCT-2026-3.pdf",{"tldr":413,"method":414,"finding":415,"direction":98,"opportunity":416},"调查伊拉克尼尼微省农业推广人员对电子通信在智慧农业AI应用中重要性的认知及障碍。","问卷量表+SPSS分析，128名推广人员样本，Cronbach's α=0.95","电子通信重要性处于中等偏高水平（48%），并识别出使用AI应用的主要障碍。","可延伸至发展中国家推广人员AI采纳行为与电子通信渠道的实证比较研究。","2026-10-16T23:30:08.170356Z",{"id":419,"title":420,"url":421,"summary":422,"summary_zh":423,"content":9,"source_name":424,"source_url":421,"published_at":425,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":426,"score_detail":427,"sources":429,"tags":431,"primary_topic":434,"secondary_topics":435,"classification":437,"search_phrases":463,"slug":466,"view_count":327,"doi":467,"paper":468,"created_at":486},3154,"The Role of Agricultural Extension Services in Promoting Climate-Smart Agriculture Adoption among Smallholder Farmers in Mwingi West sub-county Kitui County, Kenya","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fajaees\u002F2026\u002Fv44i103022","Agricultural extension services provide smallholder farmers with knowledge, technical guidance, and advisory support that can facilitate the adoption of climate-smart agricultural (CSA) practices. This study examined the role of agricultural extension services in promoting CSA adoption among smallholder farmers in Mwingi West Sub-County, Kitui County, Kenya. A cross-sectional mixed-methods design was used. Quantitative data were collected from 200 randomly selected farmers through structured questionnaires, while qualitative evidence was obtained from 10 agricultural extension officers and 10 focus group discussions with farmer groups. Quantitative data were analysed using descriptive statistics and the chi-square test of independence. Significant associations were reported between CSA adoption and access to agricultural extension services, the source of extension information, type of extension support received, frequency of extension contact, perceived usefulness of extension services, CSA practices promoted through extension, and farmers’ perceived influence of extension services on adoption. Most respondents (82.0%) had access to extension services. Extension agents were the main information source (46.0%), and technical training was the most frequently reported support (38.0%). Conservation agriculture (30.0%), agroforestry (22.0%), and water harvesting (19.0%) were the leading practices promoted through extension activities. Nearly half of respondents (48.0%) reported that extension services had increased CSA adoption to a great extent. The findings indicate that accessible, practical, and regular extension support is closely associated with CSA adoption in the study area.","农业推广服务为小农户提供知识、技术指导和咨询服务，有助于促进气候智能型农业（CSA）实践的采纳。本研究考察了农业推广服务在促进肯尼亚基图伊县姆温吉西分区小农户采纳气候智能型农业实践中的作用。研究采用横断面混合方法设计。定量数据通过结构化问卷从200名随机抽取的农户中收集，定性证据则来自10名农业推广官员以及10次农户小组焦点小组讨论。定量数据采用描述性统计和卡方独立性检验进行分析。结果显示，气候智能型农业实践的采纳与以下因素存在显著关联：能否获得农业推广服务、推广信息来源、所获推广支持类型、推广接触频率、推广服务的感知有用性、通过推广所宣传的气候智能型农业实践，以及农户对推广服务在采纳过程中影响力的感知。大多数受访者（82.0%）能够获得推广服务。推广人员是主要的信息来源（46.0%），技术培训是最常报告的支持类型（38.0%）。通过推广活动宣传的主要实践包括保护性农业（30.0%）、农林业（22.0%）和雨水收集（19.0%）。近半数受访者（48.0%）表示推广服务在很大程度上提高了气候智能型农业实践的采纳率。研究结果表明，在研究区域内，可及、实用且定期的推广支持与气候智能型农业实践的采纳密切相关。","Asian Journal of Agricultural Extension Economics & Sociology","2026-09-22T00:00:00Z",65,{"impact":114,"substance":18,"depth":64,"authority":117,"freshness":13,"relevant":21,"comment":428},"基于肯尼亚小农户的实证研究，数据翔实但地域性强，对国内三农信息化参考价值有限，可作国际经验收录。",[430],{"name":424,"url":421},[432,28,433,68],"肯尼亚","气候智慧农业",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[436],{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":438},{"candidates":439,"agricultural_evidence":56},[440,445,449,453,458],{"code":38,"score":116,"supported":56,"title":441,"abstract":442,"tags":444},[66],[68,443,66],"技术培训",[68],{"code":44,"score":64,"supported":56,"title":446,"abstract":447,"tags":448},[72],[28,72],[28],{"code":141,"score":114,"supported":56,"title":450,"abstract":451,"tags":452},[316],[],[],{"code":326,"score":327,"supported":56,"title":454,"abstract":455,"tags":457},[],[456],"conservation agriculture",[],{"code":459,"score":21,"supported":14,"title":460,"abstract":461,"tags":462},"H7",[],[],[433],[464,465],"气候智慧农业 农业推广 小农户 肯尼亚","气候智慧农业 农业推广","气候智慧农业农业推广小农户肯尼亚-3154","10.9734\u002Fajaees\u002F2026\u002Fv44i103022",{"doi":467,"openalex_id":469,"authors":470,"venue":424,"cited_by_count":91,"oa_url":421,"card":481,"direction":365,"ingested_from":99},"W7213979623",[471,473,475,477,479],{"name":472,"orcid":9},"Simon Mbala",{"name":474,"orcid":9},"David Kawioo Mwanzia",{"name":476,"orcid":9},"Thomas Ekamais Akuja",{"name":478,"orcid":9},"Felix Ngunzo Kioli",{"name":480,"orcid":9},"Harrison Musyoka Maithya",{"tldr":482,"method":483,"finding":484,"direction":98,"opportunity":485},"研究肯尼亚小农户中农业推广服务对气候智慧型农业采纳的促进作用。","混合方法，200份农户问卷、10名推广员访谈和10组焦点小组，卡方检验。","推广服务可及性、信息源、支持类型和接触频率与CSA采纳显著相关，82%农户有推广服务。","可探索数字推广渠道（如手机短信、APP）如何替代或补充传统推广员，提升小农户CSA采纳率。","2026-09-22T23:30:10.323072Z"]