[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2400":3,"related-2400":77},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":62,"slug":65,"view_count":53,"doi":8,"paper":66,"created_at":76},2400,"Do Agricultural Subsidy Profiles Signal Bank-Authorized Lending? A Two-Stage Interpretable Machine Learning Analysis of Credit Access and Allocation","https:\u002F\u002Fwww.mdpi.com\u002F2071-1050\u002F18\u002F18\u002F9321","Sustainability 2026, 18(18):9321（2026-09-10）。北京市农林科学院数据科学与农业经济研究所胡延祥等基于北京2970家农业企业及合作社行政记录，分析多源补贴档案与银行授权信贷的关联。两阶段梯度提升树模型结合SHAP特征归因：在剩余实体类型中，组合模型预测精度ROC-AUC达0.97。原始行政特征对条件性授权信贷金额预测价值有限，纳入供应分数可显著提升。",null,"MDPI Sustainability | 2026-09-10","2026-09-10T00:00:00Z","论文",10,false,78,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,22,18,14,8,1,"基于2970家农业经营主体行政记录的两阶段可解释机器学习研究，方法新颖、数据扎实，对补贴档案与银行授权信贷的关联提供了实证证据，值得进入每日精选。",[24],{"name":9,"url":6},[26,27,28,29,30],"可解释机器学习","农村金融","农业补贴","农业数据","农业信贷",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":39,"locked":13,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51,57],{"code":32,"score":45,"supported":46,"title":47,"abstract":49,"tags":50},9,true,[48],"machine learning",[],[26],{"code":52,"score":53,"supported":13,"title":54,"abstract":55,"tags":56},"G3",3,[],[],[30,28,27],{"code":58,"score":21,"supported":13,"title":59,"abstract":60,"tags":61},"I6",[],[],[29],[63,64],"可解释机器学习 农业信贷 农业数据 农业补贴","可解释机器学习 农业信贷","可解释机器学习农业信贷农业数据农业补贴-2400",{"doi":8,"openalex_id":8,"authors":67,"venue":8,"cited_by_count":68,"oa_url":8,"card":69,"direction":73,"ingested_from":75},[],0,{"tldr":70,"method":71,"finding":72,"direction":73,"opportunity":74},"基于北京2970家农业主体行政记录，用两阶段可解释机器学习分析补贴档案与银行授权信贷的关联。","两阶段梯度提升树结合SHAP归因，使用北京农业企业及合作社行政记录数据。","组合模型预测授权信贷精度ROC-AUC达0.97，纳入供应分数可显著提升金额预测。","数字乡村与农业信息化","可探索补贴数据跨部门共享机制与可解释模型在涉农信贷风控中的落地路径。","agent","2026-09-14T00:06:33.352853Z",{"total":78,"page":21,"page_size":78,"items":79},6,[80,167,249,325,379,413],{"id":81,"title":82,"url":83,"summary":84,"summary_zh":85,"content":8,"source_name":86,"source_url":83,"published_at":87,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":88,"score_detail":89,"sources":94,"tags":96,"primary_topic":101,"secondary_topics":107,"classification":109,"search_phrases":136,"slug":139,"view_count":21,"doi":140,"paper":141,"created_at":166},5193,"Explainable machine learning with a graphical user interface for estimating compressive strength and life cycle assessment based embodied carbon of rice husk ash concrete","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs42452-026-09656-0","Meeting the growing demand for concrete while reducing its environmental impact remains a crucial challenge for the construction industry. Although rice husk ash (RHA) offers substantial potential as a supplementary cementitious material to lower cement-related emissions, its widespread adoption is constrained by uncertainty in achieving a performance-environmental efficiency trade-off between mechanical performance and embodied carbon reduction. This paper proposes an explainable machine learning (ML) framework for the evaluation of compressive strength of RHA-based concrete across various curing stages, complemented by life cycle assessment (LCA) based embodied carbon evaluation. A refined database compiled from existing studies was adopted to train and optimise eight different ML models. The models were optimised using Optuna and assessed using multiple performance metrics, while SHapley Additive exPlanation (SHAP) was adopted to quantify global and local feature contributions. To support practical deployment, the best performing models were incorporated within an interactive decision support interface facilitating real time, coding free compressive strength prediction together with LCA-based embodied carbon calculation; thereby supporting performance-based mix design and accelerating the sustainable use of agricultural waste derived cementitious materials.","在满足日益增长的混凝土需求的同时降低其环境影响，仍是建筑行业面临的关键挑战。尽管稻壳灰（rice husk ash, RHA）作为辅助胶凝材料在降低水泥相关排放方面具有巨大潜力，但其广泛应用受到力学性能与隐含碳减排之间性能-环境效率权衡不确定性的制约。本文提出了一种可解释机器学习（machine learning, ML）框架，用于评估稻壳灰基混凝土在不同养护阶段下的抗压强度，并辅以基于生命周期评价（life cycle assessment, LCA）的隐含碳评估。采用从现有研究中汇编的精细化数据库训练并优化了八种不同的机器学习模型。模型通过Optuna进行优化，并采用多项性能指标进行评估，同时采用SHapley加性解释（SHapley Additive exPlanation, SHAP）量化全局与局部特征贡献。为支持实际应用，将性能最优的模型集成于交互式决策支持界面中，实现实时、免编程的抗压强度预测及基于生命周期评价的隐含碳计算，从而支持基于性能的配合比设计，并加速农业废弃物衍生胶凝材料的可持续利用。","Discover Applied Sciences","2026-10-15T00:00:00Z",69,{"impact":90,"substance":91,"depth":92,"authority":90,"freshness":20,"relevant":21,"comment":93},12,20,17,"将稻壳灰混凝土的抗压强度预测与隐含碳评估整合为可解释机器学习框架，并配有图形界面，方法新颖、数据扎实，对农业废弃物高值化利用有参考价值，但属专业论文，公共影响范围有限。",[95],{"name":86,"url":83},[26,97,98,99,100],"生命周期评价","农业废弃物利用","稻壳灰混凝土","低碳建材",{"code":102,"slug":103,"name":104,"path":105,"parent_code":106},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[108],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":110},{"candidates":111,"agricultural_evidence":46},[112,118,123,131],{"code":32,"score":18,"supported":46,"title":113,"abstract":114,"tags":117},[48],[115,48,116],"机器学习","decision support",[26],{"code":102,"score":119,"supported":46,"title":120,"abstract":121,"tags":122},11,[103],[103],[],{"code":124,"score":125,"supported":46,"title":126,"abstract":127,"tags":130},"H5",7,[],[128,129],"农业废弃物","agricultural waste",[98],{"code":132,"score":21,"supported":13,"title":133,"abstract":134,"tags":135},"H4",[],[],[97],[137,138],"稻壳灰混凝土 抗压强度","稻壳灰 生命周期评价","稻壳灰混凝土抗压强度-5193","10.1007\u002Fs42452-026-09656-0",{"doi":140,"openalex_id":142,"authors":143,"venue":86,"cited_by_count":68,"oa_url":83,"card":158,"direction":164,"ingested_from":165},"W7222284745",[144,147,150,153,155],{"name":145,"orcid":146},"Stephen Adeyemi Alabi","https:\u002F\u002Forcid.org\u002F0000-0001-8731-6961",{"name":148,"orcid":149},"Ibrahim A. Tijani","https:\u002F\u002Forcid.org\u002F0000-0002-9423-1074",{"name":151,"orcid":152},"Alireza Moghayedi","https:\u002F\u002Forcid.org\u002F0000-0002-4165-0777",{"name":154,"orcid":8},"Jeffrey Mahachi",{"name":156,"orcid":157},"Samson Olalekan Odeyemi","https:\u002F\u002Forcid.org\u002F0000-0001-5217-3403",{"tldr":159,"method":160,"finding":161,"direction":162,"opportunity":163},"用可解释机器学习加图形界面预测稻壳灰混凝土抗压强度并评估隐含碳。","八种机器学习模型经Optuna优化，SHAP解释，结合生命周期评价与交互界面。","最优模型可实时无代码预测强度并算隐含碳，支撑性能导向配合比设计。","农业绿色发展与碳","可将稻壳灰混凝土的强度-碳权衡模型扩展到其他农业废弃物建材并接入乡村低碳建造决策。","农业人工智能与决策模型","openalex","2026-10-17T23:30:53.298664Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":172,"content":8,"source_name":173,"source_url":170,"published_at":174,"category":11,"cover_url":8,"hotness":175,"is_selected":13,"score":176,"score_detail":177,"sources":179,"tags":184,"primary_topic":189,"secondary_topics":190,"classification":191,"search_phrases":222,"slug":225,"view_count":21,"doi":226,"paper":227,"created_at":248},4526,"Explainable machine learning for spatial modelling of groundwater nitrate contamination: a multi-year analysis in the Duero basin","https:\u002F\u002Fdoi.org\u002F10.6084\u002Fm9.figshare.34244894.v1","Groundwater nitrate contamination is a major water-quality concern, with implications for drinking water supplies and groundwater-dependent ecosystems. This study assesses the Duero River basin (Spain), where groundwater nitrate concentrations have increased in recent decades due to intensive agriculture and livestock farming. The probability of elevated groundwater nitrate concentrations was predicted using machine learning, formulated as a binary classification problem with a threshold of 37.5 mg\u002FL. Monitoring data were combined with spatially derived environmental and anthropogenic predictors. Several tree-based algorithms were evaluated, with Random Forest selected for its consistent predictive performance. Model performance was assessed through repeated nested cross-validation and the use of metrics suitable for imbalanced datasets, achieving an AUC of 0.79-0.88 and an F1-score of 0.56-0.70 for the minority class across the three analysed hydrological years. SHAP analysis identified precipitation, diffuse agricultural pressures, distance to surface water bodies, NDVI, and soil properties as the main contributing predictors. Multi-year probability maps showed substantial spatial coherence with officially designated Nitrate Vulnerable Zones (46.9-64.9%), while identifying additional high-probability areas outside them (12.7-23.6%). The integration of explainable machine learning, multi-year spatial modelling, and regulatory comparison provides a framework to support groundwater monitoring, review vulnerable-zone delineation, and prioritise mitigation measures.","地下水硝酸盐污染是一个重要的水质问题，对饮用水供应和依赖地下水的生态系统具有影响。本研究评估了西班牙杜埃罗河流域（Duero River basin），近几十年来，由于集约化农业和畜牧业，该地区地下水硝酸盐浓度有所上升。本研究使用机器学习预测地下水硝酸盐浓度升高的概率，并将其表述为以37.5 mg\u002FL为阈值的二分类问题。监测数据与空间衍生的环境及人为预测因子相结合。研究评估了多种基于树的算法，并因随机森林（Random Forest）具有稳定的预测性能而选用该算法。模型性能通过重复嵌套交叉验证以及适用于不平衡数据集的指标进行评估，在三个分析水文年度中，少数类别的AUC达到0.79-0.88，F1分数达到0.56-0.70。SHAP分析确定降水、面源农业压力、距地表水体距离、NDVI和土壤属性为主要贡献预测因子。多年概率图显示出与官方指定硝酸盐脆弱区（Nitrate Vulnerable Zones）较高的空间一致性（46.9-64.9%），同时在这些区域之外识别出额外的高概率区域（12.7-23.6%）。可解释机器学习、多年空间建模和监管比较的整合提供了一个框架，可支持地下水监测、审查脆弱区划定并优先安排缓解措施。","Figshare","2026-10-08T00:00:00Z",25,79,{"impact":18,"substance":17,"depth":18,"authority":90,"freshness":45,"relevant":21,"comment":178},"可解释机器学习结合多年空间建模识别地下水硝酸盐污染高风险区，方法新颖、结论可靠，对农业面源污染监测与脆弱区划定有参考价值。",[180,181],{"name":173,"url":170},{"name":182,"url":183},"International Journal of River Basin Management","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15715124.2026.2742495",[26,185,186,187,188],"农业面源污染","遥感监测","地下水硝酸盐","硝酸盐脆弱区",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":192},{"candidates":193,"agricultural_evidence":46},[194,199,206,213,217],{"code":32,"score":195,"supported":46,"title":196,"abstract":197,"tags":198},15,[48],[115,48],[26],{"code":200,"score":78,"supported":46,"title":201,"abstract":202,"tags":205},"C",[],[203,204],"畜牧","livestock",[],{"code":207,"score":78,"supported":46,"title":208,"abstract":209,"tags":212},"H2",[],[210,211],"土壤","soil",[],{"code":124,"score":21,"supported":13,"title":214,"abstract":215,"tags":216},[],[],[185],{"code":218,"score":21,"supported":13,"title":219,"abstract":220,"tags":221},"I3",[],[],[186],[223,224],"SHAP 硝酸盐脆弱区","可解释机器学习 农业面源污染 地下水硝酸盐 硝酸盐脆弱区","SHAP硝酸盐脆弱区-4526","10.6084\u002Fm9.figshare.34244894.v1",{"doi":226,"openalex_id":228,"authors":229,"venue":173,"cited_by_count":68,"oa_url":170,"card":243,"direction":164,"ingested_from":165},"W7220971680",[230,233,235,237,240],{"name":231,"orcid":232},"Manuel Rodríguez del Rosario","https:\u002F\u002Forcid.org\u002F0000-0002-4202-6722",{"name":234,"orcid":8},"Victor Gómez-Escalonilla",{"name":236,"orcid":8},"Héctor Aguilera",{"name":238,"orcid":239},"Pedro Martínez‐Santos","https:\u002F\u002Forcid.org\u002F0000-0003-2014-4063",{"name":241,"orcid":242},"África de la Hera Portillo","https:\u002F\u002Forcid.org\u002F0000-0001-7821-1834",{"tldr":244,"method":245,"finding":246,"direction":162,"opportunity":247},"用可解释机器学习预测西班牙杜埃罗盆地地下水硝酸盐超标概率并绘制多年风险图。","随机森林二分类，结合监测数据与空间环境人为预测因子，SHAP解释。","模型AUC达0.79-0.88，识别出硝酸盐脆弱区外12.7-23.6%的高风险区。","可迁移至其他农业流域，结合时序遥感与政策情景模拟优化脆弱区动态划定。","2026-10-09T23:30:47.673746Z",{"id":250,"title":251,"url":252,"summary":253,"summary_zh":254,"content":8,"source_name":255,"source_url":252,"published_at":256,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":257,"score_detail":258,"sources":260,"tags":262,"primary_topic":267,"secondary_topics":268,"classification":274,"search_phrases":305,"slug":308,"view_count":309,"doi":310,"paper":311,"created_at":324},2746,"Fostering artificial intelligence in the livestock sector: Adoption factors and policy insights from the case of Spain","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104956","CONTEXT AND PURPOSE The integration of Artificial Intelligence (AI) and Precision Livestock Farming (PLF) offers significant opportunities to improve the productivity, animal welfare and sustainability of the livestock sector. However, the adoption of these technologies remains highly uneven. Moving beyond descriptive statistics, this study investigates the complex, interacting factors associated with AI adoption in the Spanish livestock sector. METHODOLOGY Utilising a survey-based sample of 666 Spanish livestock holdings, drawn from a national survey whose sampling was designed to be proportional to the 2020 Agricultural Census by subsector and region, a Partial Least Squares Structural Equation Modelling (PLS-SEM) approach was employed to evaluate a comprehensive adoption framework across different farming systems and operational scales. AI adoption was modelled as a formative composite of five self-reported AI system categories, and the framework was tested through mediation, moderation, subgroup and out-of-sample predictive analyses with a 10,000-resample bootstrap. MAIN FINDINGS The empirical results indicate that AI adoption is most strongly associated with a holding's baseline technological infrastructure (β = 0.6464, p \u003C 0.001); advanced predictive tools appear to presuppose a pre-existing ecosystem of digital farm books, automated feeding systems and interoperable sensors. A ‘perception-capability gap’ is formally supported: perceived benefits are associated with adoption only indirectly, through the infrastructure baseline (indirect-only mediation), and their association strengthens as infrastructure increases (positive interaction). Recognition of AI's theoretical benefits or awareness of public subsidies is thus not independently associated with adoption in the absence of foundational digital capability. Furthermore, the study identifies a stark structural divide: adoption reaches 56.3% in intensive and semi-intensive holdings but only 24.4% in extensive ones (χ2 = 57.61, p \u003C 0.001), as traditional extensive systems face severe physical and connectivity barriers that leave them systematically disadvantaged. Results are robust across reflective, count, reduced-indicator and logistic specifications, and the model shows substantial out-of-sample predictive power (Q 2 predict ≈ 0.53). CONCLUSIONS To facilitate a more inclusive digital transformation, the findings suggest that policymakers should adopt a ‘readiness-conditional’ model, ensuring farms meet baseline digital prerequisites and have access to robust extension services before subsidising advanced AI tools.","背景与目的 人工智能（Artificial Intelligence, AI）与精准畜牧业（Precision Livestock Farming, PLF）的融合为提升畜牧部门的生产力、动物福利和可持续性提供了重要机遇。然而，这些技术的采用仍然极不均衡。本研究超越描述性统计，探讨了西班牙畜牧部门中与AI采用相关的复杂交互因素。方法 基于一项全国性调查中抽取的666个西班牙畜牧养殖场的样本（该调查的抽样设计按2020年农业普查的子部门和地区比例进行），采用偏最小二乘结构方程模型（Partial Least Squares Structural Equation Modelling, PLS-SEM）方法，评估了一个跨不同养殖系统和经营规模的综合采用框架。AI采用被建模为五个自我报告的AI系统类别的形成性复合变量，并通过中介、调节、子组和样本外预测分析（10,000次重抽样自助法）对框架进行了检验。主要发现 实证结果表明，AI采用与养殖场的基线技术基础设施关联最为密切（β = 0.6464，p \u003C 0.001）；先进的预测工具似乎以已有的数字牧场记录、自动化饲喂系统和可互操作传感器生态系统为前提。“感知—能力差距”得到正式支持：感知收益仅通过基础设施基线间接与采用相关（仅间接中介），且其关联随基础设施的增加而增强（正向交互）。因此，在缺乏基础数字能力的情况下，对AI理论效益的认可或对公共补贴的知晓与采用并无独立关联。此外，研究识别出一条鲜明的结构性分界线：集约化和半集约化养殖场的采用率达到56.3%，而粗放型养殖场仅为24.4%（χ2 = 57.61，p \u003C 0.001），因为传统粗放型系统面临严重的物理和连接障碍，使其处于系统性劣势。结果在反映性、计数、简化指标和逻辑斯谛设定下均稳健，且模型显示出显著的样本外预测能力（Q 2 predict ≈ 0.53）。结论 为促进更具包容性的数字化转型，研究结果表明政策制定者应采取“就绪条件”模型，确保养殖场","Agricultural Systems","2026-09-16T00:00:00Z",81,{"impact":18,"substance":17,"depth":18,"authority":19,"freshness":45,"relevant":21,"comment":259},"基于666个西班牙牧场样本的实证研究，揭示AI采纳受数字基础设施制约的“感知—能力鸿沟”，并提出“就绪条件式”补贴政策思路，对智慧畜牧推广与数字乡村政策设计有参考价值。",[261],{"name":255,"url":252},[263,264,265,28,266],"智慧农业","农业人工智能","数字素养","精准畜牧",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[269],{"code":270,"slug":271,"name":272,"path":273,"parent_code":200},"C6","smart-livestock","养殖环境与智慧畜牧","\u002Ftopic\u002Flivestock\u002Fsmart-livestock",{"status":39,"locked":13,"version":40,"method":41,"evidence":275},{"candidates":276,"agricultural_evidence":46},[277,281,286,292,296,301],{"code":200,"score":19,"supported":46,"title":278,"abstract":279,"tags":280},[204],[203,204],[],{"code":32,"score":90,"supported":46,"title":282,"abstract":284,"tags":285},[283],"artificial intelligence",[283],[264],{"code":270,"score":12,"supported":46,"title":287,"abstract":288,"tags":291},[],[266,289,290],"动物福利","animal welfare",[266],{"code":52,"score":21,"supported":13,"title":293,"abstract":294,"tags":295},[],[],[28],{"code":297,"score":21,"supported":13,"title":298,"abstract":299,"tags":300},"I1",[],[],[263],{"code":58,"score":21,"supported":13,"title":302,"abstract":303,"tags":304},[],[],[265],[306,307],"农业人工智能 农业补贴 数字素养 智慧农业","农业人工智能 农业补贴","农业人工智能农业补贴数字素养智慧农业-2746",5,"10.1016\u002Fj.agsy.2026.104956",{"doi":310,"openalex_id":312,"authors":313,"venue":255,"cited_by_count":68,"oa_url":252,"card":319,"direction":73,"ingested_from":165},"W7213425399",[314,316],{"name":315,"orcid":8},"Carlos Parra-Lopez",{"name":317,"orcid":318},"Carmen Carmona‐Torres","https:\u002F\u002Forcid.org\u002F0000-0002-6982-1363",{"tldr":320,"method":321,"finding":322,"direction":73,"opportunity":323},"基于西班牙666家养殖场调查，用PLS-SEM分析AI采纳的影响因素与政策启示。","666份养殖场问卷，PLS-SEM建模，含中介、调节与分组分析。","AI采纳最依赖既有数字基础设施；感知收益仅间接起作用，集约场采纳率远高于粗放场。","可研究粗放养殖场数字基础设施与连接性短板，设计‘就绪度条件’式推广与补贴机制。","2026-09-17T23:30:04.844104Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":8,"source_name":331,"source_url":328,"published_at":332,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":333,"score_detail":334,"sources":337,"tags":339,"primary_topic":341,"secondary_topics":342,"classification":343,"search_phrases":359,"slug":362,"view_count":21,"doi":363,"paper":364,"created_at":378},1329,"Sistem Pendukung Keputusan Distribusi Bantuan Pertanian dengan Metode Simple Additive Weighting (SAW) Berbasis Web","https:\u002F\u002Fdoi.org\u002F10.55606\u002Fjubpi.v4i3.4520","This study aims to design and implement a web-based Decision Support System (DSS) for the distribution of agricultural aid using the Simple Additive Weighting (SAW) method. The background of this research is the frequent occurrence of inaccurate targeting and lack of transparency in the selection process of aid recipients, which is still conducted manually and tends to be subjective. As a result, deserving farmers often do not receive assistance, while less eligible ones may benefit from it. The research adopts a descriptive qualitative approach combined with software engineering using the waterfall development model. Data were collected through observation, interviews, documentation, and literature studies to understand the existing system and define system requirements. The developed system processes multiple criteria, including land ownership status, business scale, income level, group membership, and participation level in farmer groups. The SAW method is applied to normalize data, assign weights to each criterion, and generate a ranking of eligible recipients. The results show that the system improves efficiency by reducing processing time, enhances objectivity by minimizing human bias, and increases transparency by providing traceable decision-making processes. The implication of this research is that the developed system can be used as a practical tool for government agencies to support fair, efficient, and accountable distribution of agricultural aid.","本研究旨在设计并实现一个基于网络的决策支持系统（DSS），用于农业援助分配，采用简单加性加权法（SAW）。研究背景是援助对象选择过程中频繁出现目标不准确和缺乏透明度的问题，该过程目前仍以人工方式进行，且往往带有主观性。因此，应得援助的农民常常无法获得帮助，而资格较差的个体却可能从中受益。本研究采用描述性定性方法，结合瀑布开发模型的软件工程实践。通过观察、访谈、文献记录及文献研究收集数据，以了解现有系统并确定系统需求。所开发的系统处理多项标准，包括土地所有权状况、经营规模、收入水平、团体成员资格以及农民团体参与程度。应用SAW方法对数据进行归一化处理，为每项标准分配权重，并生成合格受助者的排名。结果表明，该系统通过缩短处理时间提高了效率，通过减少人为偏见增强了客观性，并通过提供可追溯的决策过程增加了透明度。本研究的启示在于，所开发的系统可作为政府机构支持公平、高效且负责任的农业援助分配的实际工具。","Jurnal Bintang Pendidikan Indonesia","2026-08-31T00:00:00Z",40,{"impact":20,"substance":90,"depth":90,"authority":78,"freshness":335,"relevant":21,"comment":336},2,"面向农业援助分配的Web决策支持系统，采用SAW方法提升精准性与透明度，但影响范围有限，时效性较低。",[338],{"name":331,"url":328},[263,340,28],"决策支持系统",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":344},{"candidates":345,"agricultural_evidence":46},[346,351,355],{"code":32,"score":347,"supported":46,"title":348,"abstract":349,"tags":350},4,[],[116],[340],{"code":52,"score":21,"supported":13,"title":352,"abstract":353,"tags":354},[],[],[28],{"code":297,"score":21,"supported":13,"title":356,"abstract":357,"tags":358},[],[],[263],[360,361],"决策支持系统 农业补贴 智慧农业","决策支持系统 农业补贴","决策支持系统农业补贴智慧农业-1329","10.55606\u002Fjubpi.v4i3.4520",{"doi":363,"openalex_id":365,"authors":366,"venue":331,"cited_by_count":68,"oa_url":328,"card":373,"direction":164,"ingested_from":165},"W7204770221",[367,369,371],{"name":368,"orcid":8},"Konradus Wolo Sukun",{"name":370,"orcid":8},"Bernadete Deta",{"name":372,"orcid":8},"Alfian Nara Weking",{"tldr":374,"method":375,"finding":376,"direction":164,"opportunity":377},"开发基于Web的农业援助分配决策支持系统，采用SAW方法提高精准性和透明度。","使用SAW方法，结合瀑布模型开发Web系统，多准则加权排序。","系统减少处理时间，提高客观性，增强决策透明度。","可扩展至其他农业资源分配，或引入模糊逻辑处理不确定信息，提升决策鲁棒性。","2026-09-01T23:30:41.287312Z",{"id":380,"title":381,"url":382,"summary":383,"summary_zh":8,"content":384,"source_name":385,"source_url":8,"published_at":386,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":387,"score_detail":388,"sources":390,"tags":392,"primary_topic":394,"secondary_topics":395,"classification":396,"search_phrases":407,"slug":410,"view_count":125,"doi":411,"paper":8,"created_at":412},186,"基于影像组学与可解释机器学习的香蕉病害快速识别","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1861135\u002Ffull","原文：Radiomics-driven and explainable machine learning for rapid characterization of Fusarium wilt and Black Sigatoka in banana crops。研究于2026年7月28日发表，聚焦利用影像组学和可解释机器学习快速表征香蕉枯萎病与黑斑病，属于作物病害智能识别方向。当前公开检索摘要未呈现完整实验细节，故不对模型精度作额外推断。","## Abstract\n\n**Introduction:**\n\nBanana production is increasingly threatened by fungal diseases such as Fusarium wilt and Black Sigatoka, posing severe risks to food security and agricultural economies. Recent image-based approaches using deep learning have shown high predictive capacity for plant disease recognition; however, their limited transparency, calibration uncertainty, and sensitivity to domain shifts can restrict their use in decision-support workflows that require auditability.\n\n**Methods:**\n\nThis study proposes an interpretable and calibrated Artificial Intelligence framework for multiclass banana disease-pattern characterization based on radiomic feature analysis of RGB leaf images. Radiomic features were extracted from HSV-segmented banana leaf regions, resulting in a dataset of 14,763 samples characterized by 103 quantitative descriptors and labeled as Healthy, Sigatoka, or Fusarium wilt race 1.\n\n**Results:**\n\nAmong the evaluated radiomics classifiers, the calibrated Random Forest achieved accuracy = 0.85, balanced accuracy = 0.84, macro-F1 = 0.84, and macro ROC-AUC OvR = 0.95 on the held-out test set. Bootstrap analysis yielded 95% confidence intervals of [0.8406, 0.8691] for accuracy and [0.8306, 0.8606] for balanced accuracy. Three deep learning baselines trained on the same partition achieved higher predictive performance: MobileNetV3 with accuracy = 0.96, macro-F1 = 0.95, and macro ROC-AUC OvR = 0.97; EfficientNet with accuracy = 0.96, macro-F1 = 0.97, and macro ROC-AUC OvR = 0.96; and ResNet-18 with accuracy = 0.96, macro-F1 = 0.96, and macro ROC-AUC OvR = 0.96.\n\n**Discussion:**\n\nThe CNNs produced strong classification performance on the evaluated repositories, and the radiomics approach demonstrated to be a complementary interpretable and explainable calibrated reference model. SHAP, LIME, permutation importance, accumulated local effects, calibration curves, and Brier score decomposition supported feature-level inspection of the final model.\n\n## 1 Introduction\n\nBanana (_Musa_ spp.) is one of the most important staple and export crops worldwide, playing a critical role in food security and socioeconomic stability across tropical and subtropical regions (). Ecuador is one of the world's leading exporters of bananas, and the crop represents a strategic pillar of its national agricultural economy (). However, banana production is increasingly threatened by fungal diseases that compromise yield, fruit quality, and plantation sustainability, most notably Fusarium wilt and Black Sigatoka (). The growing pressure exerted by these diseases has intensified the need for rapid, early, accurate, scalable, and interpretable diagnostic tools capable of supporting timely phytosanitary interventions.\n\nFusarium wilt of banana, caused by _Fusarium oxysporum_ f. sp. _cubense_, is considered one of the most destructive plant diseases globally because of its soilborne nature, long persistence, and the lack of effective chemical control (). Of particular concern is Tropical Race 4 (TR4), which has spread across Asia, Africa, and Latin America in recent years (). In Ecuador, recent phytosanitary alerts and institutional containment actions have reinforced the need for surveillance technologies that support risk prioritization, field inspection, and confirmatory laboratory workflows as stated by the Ecuadorian agricultural authority . Although these technologies are not intended to replace official diagnosis, they can help to enhance disease monitoring, the recognition of disease patterns, and prioritize suspect cases for expert inspection and laboratory testing (; ).\n\nBlack Sigatoka, caused by _Pseudocercospora fijiensis_, represents another major fungal threat, leading to leaf necrosis, reduced photosynthetic capacity, and yield losses if not properly managed (). Unlike Fusarium wilt, Sigatoka symptoms are primarily foliar and visually detectable; however, symptom progression varies with environmental conditions, disease stage, cultivar, and management practice, making manual recognition subjective and error prone. In addition, visual overlap among disease-related leaf alterations may lead to delayed response or incorrect operational actions (; ).\n\nTraditional disease identification in banana plantations relies heavily on expert visual inspection and laboratory-based confirmation. While effective, these approaches are time consuming, costly, and difficult to deploy continuously across large agricultural areas, particularly when diseases such as Foc TR4 require coordinated biosecurity, surveillance, and confirmatory response workflows (; ). Artificial Intelligence (AI) and Machine Learning (ML) have therefore emerged as tools for automated analysis of visual and spectral data in plant disease detection (; ). Deep learning (DL) architectures, including convolutional neural networks (CNNs), MobileNets, Vision Transformers, and emerging foundation or vision-language models, can achieve strong performance in plant disease recognition from RGB, UAV, multispectral, or hyperspectral imagery (; ; ). Nevertheless, high predictive accuracy alone is not sufficient for phytosanitary decision support: transparency, probability calibration, leakage-aware validation, interpretability, explainability and external testing are also required (; ; ).\n\nRadiomics is an approach for extracting quantitative descriptors that characterize intensity, shape, and texture patterns from images (). Originally developed in medical imaging, radiomics is conceptually aligned with image-based plant phenotyping because both aim to convert image patterns into quantitative, analyzable traits (). Texture descriptors derived from gray-level co-occurrence matrices (GLCM), gray-level run-length matrices (GLRLM), gray-level size-zone matrices (GLSZM), gray-level dependence matrices (GLDM), and neighboring gray-tone difference matrices (NGTDM) can capture lesion heterogeneity, tissue irregularity, and spatial organization; these feature families are widely used in standardized radiomics implementations such as PyRadiomics and follow IBSI-oriented definitions (; ). When combined with classical ML classifiers, radiomics enables models whose predictions can be inspected at the feature level using permutation importance, SHAP, LIME, and accumulated local effects (; ).\n\nThe methodological gap addressed in this study is not the absence of high-accuracy image classifiers. Rather, the gap lies in the limited availability of calibrated, leakage-aware, and feature-level interpretable baselines for multiclass banana disease-pattern characterization involving H ealthy, S igatoka, and F usarium wilt categories. This study evaluates a radiomics-based ML framework together with three CNN baselines (MobileNetV3, EfficientNet, and ResNet-18), to quantify the accuracy–interpretability trade-off under the same data partition. The radiomics model is positioned as a complementary, interpretable and auditable reference model, whereas the CNN baselines establish strong performance image-based benchmarks.\n\nThe remainder of this paper is organized as follows. Section 2 reviews recent AI-based approaches for plant disease characterization, including DL, interpretable models, calibration, and leakage-aware validation. Section 3 describes the data sources, leakage-aware partitioning, HSV-based segmentation, radiomic feature extraction, feature preprocessing, classical classifiers, CNN baselines, probability calibration, and statistical analyses. Section 4 presents the comparative results, bootstrap confidence intervals, McNemar testing, CNN baseline comparison, calibration assessment, and explainability analyses. Section 5 discusses the biological plausibility, operational implications, domain-shift limitations, and deployment constraints. Section 6 concludes with future directions for Ecuadorian field validation and hybrid interpretable DL systems.\n\n## 2 Related work\n\n### 2.1 AI-based approaches for plant disease characterization\n\nFusarium wilt, in particular TR4, has attracted increasing research attention because of its rapid spread and impact on banana production (). Existing characterization strategies focus primarily on molecular diagnostics, soil assays, and expert visual inspection (). While these methods are reliable, they are not easily scalable for continuous field monitoring. Recent work on Fusarium TR4 in Latin America and the Caribbean has emphasized that effective management requires surveillance, biosecurity, containment, resistant cultivars, and coordinated regional response strategies (). In addition, the socioeconomic effects of TR4 on banana producers in Latin America further reinforce the need for scalable monitoring and early-warning tools (). AI-driven approaches for Fusarium wilt characterization remain more limited than those for foliar diseases, and many image-based studies do not explicitly address differentiation between Fusarium wilt and other diseases with overlapping visual characteristics.\n\nBlack Sigatoka has been more extensively studied using image-based techniques, but many studies address binary classification or disease severity estimation rather than multiclass differentiation among healthy leaves and multiple disease types. Recent studies using UAV-based multispectral imagery and DL have demonstrated the feasibility of plantation-level monitoring; however, these approaches remain sensitive to dataset scale, geographic variability, acquisition devices, and environmental conditions (). These limitations are relevant for banana disease recognition because cultivar diversity, field management, illumination, canopy structure, and regional disease pressure can affect the visual appearance of symptoms and the generalization of image-based models.\n\nAI techniques have been explored for automating the recognition of disease patterns, mainly based on computer vision and using ML techniques. Early approaches focused on handcrafted features combined with classical classifiers, and recent reviews of plant disease detection emphasize that DL has become a dominant modeling paradigm because of its capacity to learn discriminative visual features directly from images (; ). Compact CNNs such as MobileNet variants are particularly relevant for agricultural applications because they reduce parameter count and computational requirements relative to larger architectures, whereas EfficientNet and ResNet families remain common image-classification benchmarks. At the same time, recent literature highlights continuing challenges in cross-domain generalization, benchmark design, data leakage, annotation quality, and interpretability (; ).\n\nCNN-based approaches have been applied to detect foliar diseases such as Black Sigatoka, using leaf images captured under natural illumination. Previous studies (; ) have reported high classification accuracy using architectures such as VGG, ResNet, MobileNet, and related CNN variants, showing the potential of DL for large-scale disease monitoring (; ). UAV-based and multispectral imaging combined with deep neural networks have further extended these capabilities to plantation-level analysis, including Black Sigatoka monitoring in banana crops (; ). However, these models often require sufficiently large and well-annotated datasets, and their performance may be sensitive to domain shifts caused by illumination, background variability, acquisition devices, geographic conditions, and canopy structure. In addition, many DL models operate through latent feature representations, which can limit direct feature-level interpretability and complicate adoption in decision-support or regulatory contexts (; ).\n\nParallel to DL developments, classical ML methods using handcrafted or radiomic descriptors remain relevant, particularly in scenarios where calibration, computational constraints, auditability, or explainability are important. Texture-based descriptors, including Haralick features derived from gray-level co-occurrence matrices (GLCM), have been widely used to characterize plant disease symptoms because they capture spatial heterogeneity and lesion structure (; ; ). These approaches are generally more transparent at the feature level than end-to-end DL models, although they may provide lower raw predictive accuracy. This motivates a direct comparison between calibrated radiomics models and CNN baselines under the same data partition, allowing the accuracy–interpretability trade-off to be quantified empirically.\n\n### 2.2 Radiomics, calibration, and explainability in agricultural AI\n\nRadiomics extends traditional texture analysis by extracting a large set of quantitative descriptors that characterize intensity distributions, shape, spatial heterogeneity, and multiscale texture (). Originally developed in medical imaging, radiomics has recently been adopted in agricultural and plant phenotyping contexts, where subtle morphological and textural changes may reflect disease progression, stress responses, or tissue degradation (; ). These descriptors provide an intermediate representation between raw image pixels and model predictions, enabling quantitative characterization of visual patterns that may otherwise be difficult to inspect directly.\n\nRecent research has demonstrated the utility of radiomic and texture-based features, such as first-order statistics, shape descriptors, GLCM, GLRLM, GLSZM, GLDM, NGTDM, and wavelet-derived descriptors, for characterizing heterogeneous image patterns associated with plant stress and disease. Foundational texture descriptors (; ), including Haralick features derived from gray-level co-occurrence matrices, remain relevant for methodological definitions because they capture spatial heterogeneity and local gray-level relationships. In plant pathology, these feature families are useful because fungal infections can induce lesion coalescence, tissue irregularity, necrotic patterns, and non-uniform spatial organization, all of which can be represented through quantitative shape and texture descriptors.\n\nBeyond predictive accuracy, recent research also emphasizes the importance of model calibration and interpretability for deploying AI systems in high-stakes or decision-support domains, including agriculture (; ). Poorly calibrated models may produce overconfident predictions, leading to inappropriate prioritization, inspection, or management decisions. Techniques such as Isotonic Regression () and Platt scaling () have been proposed to improve probability reliability when predicted probabilities are used for risk-aware decision support (; ). In phytosanitary workflows, calibration is relevant because model outputs may be used to define inspection thresholds, prioritize uncertain cases, or communicate confidence to agronomists and plant-health authorities.\n\nExplainable AI (XAI) methods, including Permutation Importance, SHAP, LIME, and Accumulated Local Effects (ALE), are increasingly used to interpret model behavior and identify features associated with model predictions (; ; ). Recent agricultural AI literature has further emphasized the role of XAI in improving transparency, interpretability, and trust in AI-driven decision-making systems (; ). These techniques are particularly valuable in radiomics-based models because explanations can be linked to explicit image descriptors such as perimeter, sphericity, intensity percentiles, and texture non-uniformity. This feature-level interpretation distinguishes radiomics from end-to-end CNN models, where explanations often require post-hoc saliency or attribution methods over latent representations.\n\nRecent work on data splitting in biological ML has also shown that random or naïve partitions may inflate performance when related biological entities, duplicated observations, or highly similar samples appear in both training and test sets. () introduced DataSAIL as a leakage-reduced splitting strategy intended to enable more realistic evaluation of ML models in biological data, particularly under out-of-distribution settings. This issue is relevant for agricultural image datasets because images may share acquisition conditions, plant identity, plot identity, or visually similar backgrounds. Therefore, leakage-aware validation is necessary to avoid overly optimistic performance estimates and to better approximate deployment conditions.\n\nWhile DL approaches dominate recent studies on plant disease recognition, there remains a need for calibrated, leakage-aware, and feature-level interpretable frameworks tailored to multiclass banana disease-pattern characterization. Radiomics-based ML approaches provide a complementary reference model for this purpose as an auditable framework that allows probability calibration and inspection of quantitative descriptors associated with disease-related image patterns. In this study a joint evaluation of a calibrated radiomics model and CNN baselines under the same data partition is proposed.\n\n## 3 Materials and methods\n\n### 3.1 Data sources and leakage-aware partitions\n\nTwo publicly available banana leaf image repositories were used to construct a three-class dataset comprising H ealthy, S igatoka, and F usarium wilt race 1 (F usarium1) samples. Images corresponding to Fusarium wilt and a subset of Healthy leaves were obtained from the Banana Leaves Imagery Dataset collected in Tanzania (; ). Additional Healthy samples and Sigatoka images were sourced from the Banana Leaf Disease Dataset Bangladesh (). All images were RGB and organized in class-specific directories prior to preprocessing ([Figure 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1861135\u002Ffull#F1)).\n\nFigure 1\n\nFollowing image segmentation and radiomic feature extraction, the resulting dataset consisted of _N_ = 14, 763 radiomic samples. The class distribution after radiomic extraction was 4,866 samples for the H ealthy class, 5,767 samples for the S igatoka class, and 4,130 samples for the F usarium1 class ([Figure 2](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1861135\u002Ffull#F2)). This distribution reflects moderate class imbalance, motivating the use of balanced accuracy and macro-averaged F1-score throughout the study.\n\nFigure 2\n\nTo reduce the risk of information leakage, the experimental protocol used a leakage-aware partitioning strategy based on original image identity. A group identifier was constructed from the original image path\u002Fstem, and samples derived from the same source image identity were assigned to only one of the training, validation, or test subsets. The dataset was partitioned into training, validation, and test subsets with proportions of 70%, 15%, and 15%, respectively. The test subset was held out and remained frozen during model selection, hyperparameter tuning, feature preprocessing, and probability calibration.\n\nThe public repositories used in this study do not provide verified plant-level, plot-level, or farm-level identifiers. Therefore, the present validation should not be interpreted as a plant-level or plot-level external validation. A stricter plant\u002Fplot-level or similarity-aware split, such as DataSAIL-like splitting (), would be preferable when the corresponding metadata or image-similarity matrices become available.\n\n#### 3.1.1 Definition of experimental unit and radiomic samples\n\nIn this study, the experimental unit was defined at the image level. Each RGB image obtained from the public banana leaf repositories was associated with one class label according to the original dataset annotation: H ealthy, S igatoka, or F usarium1. After HSV-based segmentation, a leaf-level region of interest (ROI) was extracted from each image and used for radiomic feature computation. Thus, each radiomic sample corresponds to one image-derived observation represented by a 103-dimensional radiomic feature vector.\n\nThe final dataset contained 14,763 radiomic samples, corresponding to","Frontiers in Artificial Intelligence","2026-07-28T00:00:00Z",60,{"impact":90,"substance":18,"depth":16,"authority":90,"freshness":335,"relevant":21,"comment":389},"论文提出可解释的香蕉病害识别方法，对农业信息化有参考价值，但时效性较低。",[391],{"name":385,"url":382},[263,393,26],"作物病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":397},{"candidates":398,"agricultural_evidence":46},[399,403],{"code":32,"score":195,"supported":46,"title":400,"abstract":401,"tags":402},[115],[115,48],[26],{"code":297,"score":21,"supported":13,"title":404,"abstract":405,"tags":406},[],[],[263],[408,409],"可解释机器学习 作物病害 智慧农业","可解释机器学习 作物病害","可解释机器学习作物病害智慧农业-186","10.3389\u002Ffrai.2026.1861135\u002Ffull","2026-08-02T23:54:41.266361Z",{"id":414,"title":415,"url":416,"summary":417,"summary_zh":418,"content":8,"source_name":419,"source_url":416,"published_at":420,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":88,"score_detail":421,"sources":424,"tags":426,"primary_topic":430,"secondary_topics":436,"classification":438,"search_phrases":455,"slug":458,"view_count":68,"doi":459,"paper":460,"created_at":474},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",{"impact":20,"substance":422,"depth":18,"authority":90,"freshness":12,"relevant":21,"comment":423},21,"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。",[425],{"name":419,"url":416},[263,264,427,428,429],"小农户","植物病害识别","可解释性",{"code":431,"slug":432,"name":433,"path":434,"parent_code":435},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[437],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":439},{"candidates":440,"agricultural_evidence":46},[441,446,451],{"code":431,"score":90,"supported":46,"title":442,"abstract":444,"tags":445},[443],"smallholder",[443],[427],{"code":32,"score":12,"supported":46,"title":447,"abstract":449,"tags":450},[448],"computer vision",[],[264,428],{"code":297,"score":21,"supported":13,"title":452,"abstract":453,"tags":454},[],[],[263],[456,457],"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":459,"openalex_id":461,"authors":462,"venue":419,"cited_by_count":68,"oa_url":416,"card":469,"direction":164,"ingested_from":165},"W7223137323",[463,465,467],{"name":464,"orcid":8},"Akshay Ramgoolam",{"name":466,"orcid":8},"Priya Bundhoo Appadoo",{"name":468,"orcid":8},"Jean-Noël LEspérance",{"tldr":470,"method":471,"finding":472,"direction":164,"opportunity":473},"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"]