[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4197":3,"related-4197":91},{"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":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":75,"slug":78,"view_count":79,"doi":8,"paper":80,"created_at":90},4197,"智慧农业(中英文)2026年多篇论文集中上线","https:\u002F\u002Fwww.ncpssd.cn\u002Fjournal\u002Fsecure\u002Fdetails?params=Q0Z3MVcrNHQxM3JCazJqWnVka3BVYXFWdUtYZS9xSit2elNpRXp6NThqRWt2dUZ1dTFtTFJ4Rk0wTHNYQ1hyUQ","智慧农业(中英文)2026年网络首发多篇：(1)杨积忠等《基于特征优选与优化算法的干热河谷区柑橘蒸腾模拟》；(2)吴明清等《多尺度异构特征协同的棉花叶片病害检测模型》；(3)沈学利等《LiteFocus-Net：面向玉米叶片病虫害小目标检测的三点式轻量化增强框架》；(4)杨玉等《农业产业链可信数据空间：理论框架、运行机制与实施路径》；(5)张新等《数字技术赋能下生态农产品产业链脆弱性的基模分析与韧性治理》；(6)王翠霞等《数字技术赋能下生态农产品产业链脆弱性的基模分析与韧性治理》。",null,"智慧农业(中英文)·2026年","2026-10-01T00:00:00Z","论文",10,false,80,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,14,8,1,"核心期刊多篇论文集中网络首发，涵盖病害检测、蒸腾模拟与产业链数据空间等前沿方向，专业增量充足，值得精选。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","产业链韧性","农业数据空间","病虫害检测",{"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",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":46},[43,50,56,63,69],{"code":44,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},"I1",12,true,[25],[25],[25],{"code":31,"score":51,"supported":46,"title":52,"abstract":53,"tags":55},5,[],[54],"目标检测",[26,29],{"code":57,"score":58,"supported":46,"title":59,"abstract":60,"tags":62},"A3",3,[],[61],"玉米",[],{"code":64,"score":58,"supported":46,"title":65,"abstract":66,"tags":68},"A6",[],[67],"棉花",[],{"code":70,"score":58,"supported":46,"title":71,"abstract":72,"tags":74},"B2",[],[73],"柑橘",[],[76,77],"智慧农业 中英文 网络首发","棉花叶片病害 玉米病虫害 检测模型","智慧农业中英文网络首发-4197",6,{"doi":8,"openalex_id":8,"authors":81,"venue":8,"cited_by_count":82,"oa_url":8,"card":83,"direction":87,"ingested_from":89},[],0,{"tldr":84,"method":85,"finding":86,"direction":87,"opportunity":88},"汇总《智慧农业》2026年多篇论文，涵盖蒸腾模拟、病害检测与产业链数字化。","特征优选与优化算法、多尺度异构特征、轻量化检测框架、可信数据空间。","研究聚焦作物表型智能检测与农业产业链数字治理两大方向。","农业人工智能与决策模型","可探索轻量化病害检测模型在边缘设备部署与产业链数据可信共享的交叉研究。","agent","2026-10-05T00:04:56.092764Z",{"total":79,"page":20,"page_size":79,"items":92},[93,155,234,296,357,409],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":8,"source_name":99,"source_url":96,"published_at":100,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":101,"score_detail":102,"sources":106,"tags":108,"primary_topic":111,"secondary_topics":112,"classification":113,"search_phrases":132,"slug":135,"view_count":82,"doi":136,"paper":137,"created_at":154},4875,"YOLO-Based Leaf Disease Detection in Smart Agriculture: Evolution, Task Adaptation, and Deployment Challenges","https:\u002F\u002Fdoi.org\u002F10.3390\u002Felectronics15204699","Computer vision-based leaf disease detection has become an important technical approach in smart agriculture and agricultural inspection services. Recent advances in artificial intelligence (AI) and deep learning have provided effective solutions for automated leaf disease monitoring, and You Only Look Once (YOLO)-based detectors have attracted increasing attention for balancing detection accuracy and inference speed. However, leaf disease detection remains challenging because lesions often occupy small regions, exhibit subtle visual features, have blurred boundaries, and appear against complex backgrounds, with considerable variation under field conditions. To address these challenges, numerous studies have improved lightweight backbones, feature fusion mechanisms, attention modules, detection heads, loss functions, and training strategies. This critical narrative review examines YOLO-based leaf disease detection, organizing reported adaptations by task characteristics and interpreting their outcomes in relation to datasets, annotations, and evaluation conditions. Representative studies report gains in detection performance, model compactness, or measured inference speed, together with trade-offs that depend on the task and configuration. Nevertheless, several challenges remain, including limited dataset diversity, insufficient cross-crop and cross-environment generalization, inadequate consideration of annotation uncertainty, biased evaluation of lightweight models based only on parameter reduction, and the gap between benchmark performance and real-world deployment. Future research should focus on task-oriented optimization, robust visual perception, improved model generalization, and efficient deployment toward intelligent agricultural monitoring systems.","基于计算机视觉的叶片病害检测已成为智慧农业和农业巡检服务中的一项重要技术途径。近年来，人工智能（AI）与深度学习的进展为自动化叶片病害监测提供了有效解决方案，其中基于You Only Look Once（YOLO）的检测器因在检测精度与推理速度之间取得平衡而受到越来越多的关注。然而，叶片病害检测仍面临诸多挑战，因为病斑通常占据较小区域、具有细微的视觉特征、边界模糊，并且出现在复杂背景中，在田间条件下还存在相当大的变化。为应对这些挑战，大量研究对轻量级骨干网络、特征融合机制、注意力模块、检测头、损失函数和训练策略进行了改进。本批判性叙述综述考察了基于YOLO的叶片病害检测，按任务特征对已报道的改进进行组织，并结合数据集、标注和评估条件解释其结果。代表性研究报告了检测性能、模型紧凑性或实测推理速度方面的提升，同时也揭示了取决于任务和配置的权衡。尽管如此，仍存在若干挑战，包括数据集多样性有限、跨作物和跨环境泛化能力不足、对标注不确定性考虑不充分、仅基于参数减少对轻量级模型进行有偏评估，以及基准性能与实际部署之间的差距。未来研究应聚焦于面向任务的优化、鲁棒的视觉感知、改进的模型泛化能力以及面向智能农业监测系统的高效部署。","Electronics","2026-10-13T00:00:00Z",67,{"impact":45,"substance":16,"depth":103,"authority":104,"freshness":19,"relevant":20,"comment":105},16,13,"系统梳理YOLO在叶片病害检测中的任务适配与落地瓶颈，对农业AI研发有参考价值，但属综述类论文，产业影响有限。",[107],{"name":99,"url":96},[25,26,109,29,110],"计算机视觉","模型轻量化",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":114},{"candidates":115,"agricultural_evidence":46},[116,126],{"code":31,"score":117,"supported":46,"title":118,"abstract":120,"tags":125},20,[119],"YOLO",[121,109,122,123,124,119],"深度学习","deep learning","artificial intelligence","computer vision",[26,110,29,109],{"code":44,"score":127,"supported":46,"title":128,"abstract":130,"tags":131},15,[129],"smart agriculture",[25,129],[25],[133,134],"YOLO 叶片病害检测","智慧农业 病害识别 模型部署","YOLO叶片病害检测-4875","10.3390\u002Felectronics15204699",{"doi":136,"openalex_id":138,"authors":139,"venue":99,"cited_by_count":82,"oa_url":96,"card":147,"direction":152,"ingested_from":153},"W7221646013",[140,143,145],{"name":141,"orcid":142},"Xinyi Sun","https:\u002F\u002Forcid.org\u002F0009-0007-5992-1516",{"name":144,"orcid":8},"Liyang Liu",{"name":146,"orcid":8},"Baoquan Yin",{"tldr":148,"method":149,"finding":150,"direction":87,"opportunity":151},"综述了基于YOLO的叶片病害检测的演进、任务适配与部署挑战。","关键方法：轻量骨干、特征融合、注意力、检测头、损失函数与训练策略改进。","YOLO检测性能提升但存在数据集单一、泛化不足、标注不确定与部署差距。","可研究跨作物跨环境泛化、标注不确定性建模及面向真实部署的轻量模型评估。","智慧农业 \u002F 农业物联网","openalex","2026-10-14T23:30:08.538550Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":160,"content":8,"source_name":161,"source_url":158,"published_at":162,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":163,"sources":166,"tags":168,"primary_topic":170,"secondary_topics":171,"classification":172,"search_phrases":204,"slug":207,"view_count":82,"doi":208,"paper":209,"created_at":233},4811,"Explainable deep learning framework for real-time insect pest detection in smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02109-y","Abstract Global losses of crop production due to insect pest infestations are estimated to be around 20–40% annually, which represents one of the highest threats to agricultural productivity, farmer livelihoods and food security. Current manual scouting is labor intensive, subjective and non-scalable, and many automated scouting methods suffer when they come to deal with different field conditions and offer little insight into decision making. To tackle these challenges, this study proposes Crop Protection in Smart Agriculture—Real-time Insect Pest Detection using Continual Spatio-Temporal Graph Convolutional Network (CPSA-RIPD-CSTGCN), a unified and interpretable deep learning framework that combines the four synergistic components: (i) the Ensemble Transform Schmidt–Kalman Filter (ETSKF) for image preprocessing, including resizing, normalization, and noise suppression; (ii) data augmentation using rotation, flipping, scaling, shearing, and contrast adjustment, which enhances generalization and reduces overfitting; (iii) the Continual Spatio-Temporal Graph Convolutional Network (CSTGCN) that jointly models the spatial dependency across crop regions and temporal evolution of pest dynamics to achieve robust feature extraction and classification; and (iv) the Revolution Optimization Algorithm (ROA) for hyperparameter optimization of CSTGCN weights to adaptively adjust the network. Further, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization is introduced to give post-hoc explainability as it shows regions that are relevant to the biological process and areas that are affected by pests. This framework was tested on IP102 benchmark dataset with 60%-40%-split train-test with 10 economically important classes of pests with 97% accuracy, 98% precision, 98% recall and 98% F1 score, mean ± 0.32% accuracy, across 5-fold cross validation. Among other baseline models, these results consistently outperform VGG16 (82%), InceptionV3 (85%), MobileNetV2 (87%), DenseNet121 (88%), EfficientNetB0 (89%) and task-specific models like EDCP-DIA-RNN(Early Disease and Crop Pest—Diagnosis\u002FDetection using Image Analysis RNN) (94%), EPCY-TPA-ANN (Efficient Prediction of Crop Yield—Through Parameter Analysis ANN) (91%) and ICPM-ESA-CNN (Interactive Crop and Pest Management Enhanced Soil Analysis CNN) (90%). The results of ablation studies showed the solitary effects of each module of the Ensemble Transform Schmidt–Kalman Filter pre-processing and Revolution Optimization Algorithm optimization, and the confusion matrix analysis demonstrated high per-class reliability and only a small amount of misclassification, implying that the proposed method could be applied to real-time, large-scale smart agriculture deployments.","摘要 由于害虫侵扰导致的全球作物产量损失估计每年约为20–40%，这是对农业生产力、农民生计和粮食安全的最大威胁之一。当前的人工田间巡查劳动强度大、主观性强且难以规模化，而许多自动化巡查方法在面对不同田间条件时表现不佳，且对决策制定提供的洞见有限。为应对这些挑战，本研究提出了智慧农业中的作物保护——基于持续时空图卷积网络的实时害虫检测（CPSA-RIPD-CSTGCN），这是一个统一且可解释的深度学习框架，融合了四个协同组件：（i）集成变换施密特-卡尔曼滤波器（ETSKF），用于图像预处理，包括调整尺寸、归一化和噪声抑制；（ii）使用旋转、翻转、缩放、剪切和对比度调整进行数据增强，以增强泛化能力并减少过拟合；（iii）持续时空图卷积网络（CSTGCN），联合建模作物区域间的空间依赖性和害虫动态的时间演化，以实现鲁棒的特征提取和分类；（iv）革命优化算法（ROA），用于CSTGCN权重的超参数优化，以自适应调整网络。此外，引入梯度加权类激活映射（Grad-CAM）可视化以提供事后可解释性，因为它显示了与生物过程相关的区域以及受害虫影响的区域。该框架在IP102基准数据集上进行了测试，采用60%-40%的训练-测试划分，涵盖10个具有经济重要性的害虫类别，在5折交叉验证中达到了97%的准确率、98%的精确率、98%的召回率和98%的F1分数，准确率均值±0.32%。在其他基线模型中，这些结果持续优于VGG16（82%）、InceptionV3（85%）、MobileNetV2（87%）、DenseNet121（88%）、EfficientNetB0（89%）以及特定任务模型，如EDCP-DIA-RNN（基于图像分析的早期病害和作物害虫诊断\u002F检测RNN）（94%）、EPCY-TPA-ANN（通过参数分析人工神经网络高效预测作物产量）（91%）和ICPM-ESA-CNN（交互式作物和害虫管理增强土壤分析CNN）（90%）。消融研究的结果显示了集成变换施密特-卡尔曼滤波器预处理和革命优化算法各模块的单独效果。","Discover Artificial Intelligence","2026-10-12T00:00:00Z",{"impact":16,"substance":17,"depth":16,"authority":104,"freshness":164,"relevant":20,"comment":165},9,"提出可解释时空图卷积虫害实时检测框架，在IP102基准上达97%准确率并优于多种主流模型，方法新颖、数据扎实，对智慧农业植保具有参考价值。",[167],{"name":161,"url":158},[25,26,169,121,29],"可解释AI",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":173},{"candidates":174,"agricultural_evidence":46},[175,180,184,191,198],{"code":31,"score":176,"supported":46,"title":177,"abstract":178,"tags":179},17,[122],[121,122],[26,169,121,29],{"code":44,"score":127,"supported":46,"title":181,"abstract":182,"tags":183},[129],[25,129],[25],{"code":185,"score":79,"supported":46,"title":186,"abstract":187,"tags":190},"A8",[],[188,189],"粮食安全","food security",[],{"code":192,"score":79,"supported":46,"title":193,"abstract":194,"tags":197},"H2",[],[195,196],"土壤","soil",[],{"code":199,"score":58,"supported":46,"title":200,"abstract":201,"tags":203},"F4",[],[202],"crop protection",[],[205,206],"IP102 害虫检测","CSTGCN 虫害识别","IP102害虫检测-4811","10.1007\u002Fs44163-026-02109-y",{"doi":208,"openalex_id":210,"authors":211,"venue":161,"cited_by_count":82,"oa_url":158,"card":228,"direction":152,"ingested_from":153},"W7221565168",[212,215,218,221,224,226],{"name":213,"orcid":214},"J. Briskilal","https:\u002F\u002Forcid.org\u002F0000-0003-4849-3249",{"name":216,"orcid":217},"M. K. Vidhyalakshmi","https:\u002F\u002Forcid.org\u002F0000-0002-6879-9897",{"name":219,"orcid":220},"Aswathy K Cherian","https:\u002F\u002Forcid.org\u002F0009-0002-3679-2583",{"name":222,"orcid":223},"S. Neduncheliyan","https:\u002F\u002Forcid.org\u002F0009-0002-0904-8695",{"name":225,"orcid":8},"Ajay Kumar",{"name":227,"orcid":8},"Rakesh Kumar",{"tldr":229,"method":230,"finding":231,"direction":87,"opportunity":232},"提出可解释深度学习框架CPSA-RIPD-CSTGCN，实现智慧农业中害虫实时检测。","用CSTGCN时空图卷积、ROA超参优化、ETSKF预处理与Grad-CAM，在","10类害虫检测准确率97%，优于VGG16、EfficientNetB0及多种任务专用模型。","可探索轻量化模型在边缘设备部署，并融合多模态田间数据提升跨域泛化能力。","2026-10-13T23:30:10.529316Z",{"id":235,"title":236,"url":237,"summary":238,"summary_zh":239,"content":8,"source_name":240,"source_url":237,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":242,"score_detail":243,"sources":246,"tags":248,"primary_topic":252,"secondary_topics":258,"classification":260,"search_phrases":276,"slug":279,"view_count":82,"doi":280,"paper":281,"created_at":295},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":19,"substance":244,"depth":16,"authority":45,"freshness":12,"relevant":20,"comment":245},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。",[247],{"name":240,"url":237},[25,26,249,250,251],"小农户","植物病害识别","可解释性",{"code":253,"slug":254,"name":255,"path":256,"parent_code":257},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[259],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":261},{"candidates":262,"agricultural_evidence":46},[263,268,272],{"code":253,"score":45,"supported":46,"title":264,"abstract":266,"tags":267},[265],"smallholder",[265],[249],{"code":31,"score":12,"supported":46,"title":269,"abstract":270,"tags":271},[124],[],[26,250],{"code":44,"score":20,"supported":13,"title":273,"abstract":274,"tags":275},[],[],[25],[277,278],"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":280,"openalex_id":282,"authors":283,"venue":240,"cited_by_count":82,"oa_url":237,"card":290,"direction":87,"ingested_from":153},"W7223137323",[284,286,288],{"name":285,"orcid":8},"Akshay Ramgoolam",{"name":287,"orcid":8},"Priya Bundhoo Appadoo",{"name":289,"orcid":8},"Jean-Noël LEspérance",{"tldr":291,"method":292,"finding":293,"direction":87,"opportunity":294},"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":297,"title":298,"url":299,"summary":300,"summary_zh":301,"content":8,"source_name":240,"source_url":299,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":242,"score_detail":302,"sources":304,"tags":306,"primary_topic":310,"secondary_topics":316,"classification":318,"search_phrases":339,"slug":342,"view_count":82,"doi":343,"paper":344,"created_at":356},5591,"Hierarchical Conformal Risk Control for Artificial Intelligence Agriculture Irrigation Scheduling Under Unmodeled Infiltration: A Computer Safety-Guarantee Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543665","Irrigation scheduling algorithms that rely on soil-moisture forecasts are vulnerable to unmodeled infiltration, the process by which water bypasses the root zone through preferential pathways that resistance-based soil models cannot represent. The framework is evaluated through a replication-based design study that characterises the operating characteristics of the before-after-control-impact estimator used to audit scheduler performance, under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 54 clusters are required to detect a 5-percentage-point effect at 80% power, and that the minimum detectable effect declines steeply as cluster count rises from 8 to 32. The contribution is a formal safety guarantee for irrigation decision support that remains valid when the infiltration model is wrong, together with an audit design that makes the guarantee empirically checkable.","依赖土壤湿度预报的灌溉调度算法容易受到未建模入渗的影响，即水分通过优先路径绕过根区的过程，而基于阻力的土壤模型无法表征这一过程。该框架通过一项基于重复的设计研究进行评估，该研究刻画了用于审计调度器性能的前后对照影响估计量的运行特性，其所依据的声明方差结构为：组间标准差6.0、残差标准差4.5、组内相关系数0.64。功效估计覆盖2000个设计单元，涵盖聚类数8、16、24和32以及效应量3、5和8个百分点。分析表明，在80%功效下检测5个百分点效应需要54个聚类，且最小可检测效应随聚类数从8增至32而急剧下降。本文的贡献在于为灌溉决策支持提供了一种正式的安全保证，该保证在入渗模型错误时仍然有效，同时提出了一种使该保证可经实证检验的审计设计。",{"impact":19,"substance":17,"depth":16,"authority":45,"freshness":164,"relevant":20,"comment":303},"该研究提出在入渗模型失配条件下仍有效的灌溉决策安全保证框架，并给出可审计的试验设计，方法新颖、结论可靠，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[305],{"name":240,"url":299},[25,26,307,308,309],"灌溉决策","安全保证","试验设计",{"code":311,"slug":312,"name":313,"path":314,"parent_code":315},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[317],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":319},{"candidates":320,"agricultural_evidence":46},[321,326,331,335],{"code":311,"score":127,"supported":46,"title":322,"abstract":323,"tags":325},[312],[324,312],"灌溉",[307],{"code":31,"score":45,"supported":46,"title":327,"abstract":328,"tags":330},[123],[329],"decision support",[26],{"code":192,"score":79,"supported":46,"title":332,"abstract":333,"tags":334},[],[195,196],[],{"code":44,"score":20,"supported":13,"title":336,"abstract":337,"tags":338},[],[],[25],[340,341],"灌溉调度 安全保证","农业人工智能 安全保证 智慧农业 灌溉决策","灌溉调度安全保证-5591","10.5281\u002Fzenodo.23543665",{"doi":343,"openalex_id":345,"authors":346,"venue":240,"cited_by_count":82,"oa_url":299,"card":351,"direction":87,"ingested_from":153},"W7223131205",[347,349],{"name":348,"orcid":8},"Nassima Benkhelifa",{"name":350,"orcid":8},"Yacine Aït Ahmed",{"tldr":352,"method":353,"finding":354,"direction":87,"opportunity":355},"提出分层保形风险控制，为未建模入渗下的灌溉调度提供安全保证。","分层保形风险控制与基于重复设计的BACI审计，2000个设计单元功效分析。","检测5个百分点效应需54个集群，最小可检测效应随集群数增加陡降。","可将保形风险控制扩展到其他未建模扰动下的农业决策安全保证与审计设计。","2026-10-22T11:21:10.283561Z",{"id":358,"title":359,"url":360,"summary":361,"summary_zh":362,"content":8,"source_name":240,"source_url":360,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":363,"score_detail":364,"sources":366,"tags":368,"primary_topic":371,"secondary_topics":372,"classification":374,"search_phrases":389,"slug":392,"view_count":82,"doi":393,"paper":394,"created_at":408},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":19,"substance":17,"depth":16,"authority":45,"freshness":12,"relevant":20,"comment":365},"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。",[367],{"name":240,"url":360},[25,26,249,369,370],"作物病害识别","模型审计",{"code":253,"slug":254,"name":255,"path":256,"parent_code":257},[373],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":375},{"candidates":376,"agricultural_evidence":46},[377,381,385],{"code":253,"score":127,"supported":46,"title":378,"abstract":379,"tags":380},[265],[249,265],[249],{"code":31,"score":12,"supported":46,"title":382,"abstract":383,"tags":384},[124],[],[369,26],{"code":44,"score":20,"supported":13,"title":386,"abstract":387,"tags":388},[],[],[25],[390,391],"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":393,"openalex_id":395,"authors":396,"venue":240,"cited_by_count":82,"oa_url":360,"card":403,"direction":87,"ingested_from":153},"W7223088030",[397,399,401],{"name":398,"orcid":8},"Abdi-Basid Idriss Farah",{"name":400,"orcid":8},"Amina Abdillahi Guedi",{"name":402,"orcid":8},"Moussa Omar Youssouf",{"tldr":404,"method":405,"finding":406,"direction":87,"opportunity":407},"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":410,"title":411,"url":412,"summary":413,"summary_zh":414,"content":8,"source_name":240,"source_url":412,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":415,"score_detail":416,"sources":418,"tags":420,"primary_topic":423,"secondary_topics":424,"classification":425,"search_phrases":443,"slug":446,"view_count":82,"doi":447,"paper":448,"created_at":458},5589,"Conformal-Risk Evaluation for Artificial Intelligence Agriculture Spray-Nozzle Fault Detection Under Label-Delay Feedback: A Computer Coverage Audit","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544107","Spray-nozzle fault detection in precision agriculture is a classification problem in which the label that confirms a fault arrives after the spray pass, so the detector must act on unlabelled evidence and its error rate must be certified before the label exists. Conformal prediction offers distribution-free coverage guarantees, but the guarantee is stated for exchangeable calibration and test data, an assumption that label-delayed feedback violates because the calibration set is always older than the deployment set. the present analysis formalises label-delay feedback as a distribution shift in the conformity score and derives a coverage bound for split-conformal fault detectors under that shift. The bound separates the nominal miscoverage rate into an exchangeable component and a delay-induced component that scales with the total variation distance between the calibration and deployment score distributions. A replication-based evaluation of the ['Intercept', 'exposure', 'group', 'severity'] estimator was conducted: 600 data sets of N = 500 were drawn from a declared data-generating process (intercept 12.0, exposure 0.42, group -3.1, severity 1.35, error SD 4.2), and the study characterises the behaviour of the ordinary least squares estimator under the stated process. The estimator recovered the declared coefficients with estimated bias 0.01122 for the intercept and -0.0002 for exposure, root mean squared error 0.9217 and 0.01614 respectively, and empirical coverage of the nominal 95% intervals of 1.0 for both parameters across 600 replications. The coverage audit shows that the delay-induced term, not the exchangeable term, dominates the risk of a conformal spray-nozzle detector, and that the audit procedure can certify a detector before field labels return.","在精准农业中，喷雾喷嘴故障检测是一个分类问题，其中确认故障的标签在喷雾作业结束后才到达，因此检测器必须基于未标记的证据采取行动，并且其错误率必须在标签存在之前得到认证。保形预测（conformal prediction）提供了无分布覆盖保证，但该保证是针对可交换的校准数据和测试数据而言的，而标签延迟反馈违反了这一假设，因为校准集总是比部署集更旧。本分析将标签延迟反馈形式化为一致性分数中的分布偏移，并推导了在该偏移下分裂保形故障检测器的覆盖界。该界将名义错误覆盖 rate 分解为可交换分量和延迟诱导分量，后者随校准与部署分数分布之间的全变差距离而缩放。对 ['Intercept', 'exposure', 'group', 'severity'] 估计器进行了基于重复的评估：从声明的数据生成过程（截距 12.0，暴露 0.42，分组 -3.1，严重程度 1.35，误差标准差 4.2）中抽取了 600 个 N = 500 的数据集，研究刻画了普通最小二乘估计器在所述过程下的行为。该估计器恢复了声明的系数，截距的估计偏差为 0.01122，暴露为 -0.0002，均方根误差分别为 0.9217 和 0.01614，两个参数在 600 次重复中名义 95% 区间的经验覆盖率为 1.0。覆盖审计表明，延迟诱导项而非可交换项主导了保形喷雾喷嘴检测器的风险，并且该审计程序可以在田间标签返回之前对检测器进行认证。",62,{"impact":19,"substance":16,"depth":176,"authority":164,"freshness":12,"relevant":20,"comment":417},"论文提出标签延迟下共形预测覆盖界，方法有新意但属预印本、应用面窄，可作为专业补充而非每日精选头条。",[419],{"name":240,"url":412},[25,26,421,422],"精准施药","病虫害监测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":426},{"candidates":427,"agricultural_evidence":46},[428,432,439],{"code":31,"score":164,"supported":46,"title":429,"abstract":430,"tags":431},[123],[],[26],{"code":44,"score":433,"supported":46,"title":434,"abstract":435,"tags":438},7,[],[436,437],"精准农业","precision agriculture",[25],{"code":199,"score":20,"supported":13,"title":440,"abstract":441,"tags":442},[],[],[421],[444,445],"农业人工智能 病虫害监测 智慧农业 精准施药","农业人工智能 病虫害监测","农业人工智能病虫害监测智慧农业精准施药-5589","10.5281\u002Fzenodo.23544107",{"doi":447,"openalex_id":449,"authors":450,"venue":240,"cited_by_count":82,"oa_url":412,"card":453,"direction":87,"ingested_from":153},"W7223116087",[451],{"name":452,"orcid":8},"Achieng' Atim Okello",{"tldr":454,"method":455,"finding":456,"direction":87,"opportunity":457},"将标签延迟反馈建模为共形分数分布偏移，推导覆盖率界并审计喷雾喷嘴故障检测器。","分裂共形预测、总变差距离、600次重复模拟（N=500）评估OLS估计。","延迟诱导项而非可交换项主导检测器风险，审计可在田间标签返回前认证检测器。","可将该覆盖率审计框架扩展到其他标签延迟的农业传感器故障检测，并研究延迟分布估计误差对认证的影响。","2026-10-22T11:21:02.845718Z"]