[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3119":3,"related-3119":85},{"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":69,"slug":72,"view_count":73,"doi":8,"paper":74,"created_at":84},3119,"CropRowSeg: A Lightweight Model for Seedling Crop Row Image Segmentation Combining Multi-scale CNN and Transformer（融合多尺度 CNN 与 Transformer 的苗期作物行图像轻量化分割模型）","https:\u002F\u002Fnews.cau.edu.cn\u002Fkxyj\u002F9f1540e749e745f29f11355eac1c9444.htm","中国农业大学农机装备智能化设计与制造高水平创新团队翟志强副教授在国际学术期刊《Agriculture Communications》发表研究论文。中国农业大学为唯一署名单位，硕士研究生田永浩为论文第一作者、翟志强为通讯作者。研究面向农机对行作业和作物表型观测对作物行视觉感知的实际需求，提出从图像高效标注、模型架构设计到模型训练的系统解决方案：从数据标注、模型架构、损失函数三个维度构建完整的作物行图像分割技术体系；提出基于中心线引导的条带标注方法仅需人工标注冠层中心线两个端点即可自动生成分割掩码；CropRowSeg 模型采用编码器—解码器架构（编码器 CNN+ViT 双分支结构+通道-空间混合注意力机制，解码器残差连接与坐标注意力结合的渐进式解码架构）。研究可为大田作物感知提供视觉基础模型，为研发农业人工智能专用模型提供借鉴思路。",null,"中国农业大学","2026-09-18T12:39:00Z","论文",10,false,78,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},18,21,17,14,8,1,"中国农业大学团队提出轻量化作物行分割模型CropRowSeg，方法体系完整、创新点明确，对农机对行作业与作物表型感知有实用价值，值得进入每日精选。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","农机导航","作物行识别","图像分割",{"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},[44,50,57,64],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},5,true,[],[27],[27,30],{"code":51,"score":52,"supported":46,"title":53,"abstract":54,"tags":56},"F5",4,[],[55],"农机",[28],{"code":58,"score":59,"supported":46,"title":60,"abstract":61,"tags":63},"I3",3,[],[62],"作物表型",[],{"code":65,"score":21,"supported":13,"title":66,"abstract":67,"tags":68},"I1",[],[],[26],[70,71],"中国农业大学 翟志强 作物行分割","CropRowSeg 苗期作物行","中国农业大学翟志强作物行分割-3119",2,{"doi":8,"openalex_id":8,"authors":75,"venue":8,"cited_by_count":76,"oa_url":8,"card":77,"direction":81,"ingested_from":83},[],0,{"tldr":78,"method":79,"finding":80,"direction":81,"opportunity":82},"提出轻量级作物行分割模型CropRowSeg，并设计中心线引导的条带标注方法。","多尺度CNN与ViT双分支编码器、混合注意力、渐进式解码器，中心线引导标注。","模型实现高效作物行图像分割，降低标注成本，为农机对行作业提供视觉基础。","农业遥感与作物表型","可探索该轻量模型在边缘设备上的实时部署及多作物、多生长阶段的泛化能力。","agent","2026-09-22T00:05:37.930057Z",{"total":86,"page":21,"page_size":86,"items":87},6,[88,165,254,309,370,433],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":8,"source_name":94,"source_url":91,"published_at":95,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":96,"score_detail":97,"sources":102,"tags":104,"primary_topic":107,"secondary_topics":108,"classification":109,"search_phrases":126,"slug":129,"view_count":21,"doi":130,"paper":131,"created_at":164},5147,"FDUNet-LRSA: efficient frequency-adaptive segmentation for automated crop disease inspection","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1963106","The transition toward industrialized and automated agriculture requires reliable machine vision for high-throughput crop health monitoring and field decision support. Automated sweetpotato disease inspection, however, remains challenging because field images exhibit substantial variations in leaf scale, appearance, illumination, occlusion, and background complexity. Conventional U-shaped networks rely primarily on fixed convolutional kernels and local feature aggregation, whereas Transformer-based alternatives often introduce considerable computational overhead. This article proposes FDUNet-LRSA, a frequency-adaptive segmentation network that integrates frequency-domain dynamic convolution, low-resolution self-attention, and boundary-aware refinement. Frequency-domain dynamic convolution reconstructs input-dependent spatial kernels to improve feature adaptation under changing imaging conditions. Low-resolution self-attention captures long-range contextual dependencies in a fixed compact feature space, while boundary-aware refinement preserves irregular leaf contours during mask reconstruction. Under the reported evaluation protocol, FDUNet-LRSA achieved a mean test foreground IoU of 0.94 and a Dice coefficient of 0.97, with 3.72 GFLOPs. Additional experiments indicate that task-oriented moderate augmentation improves generalization compared with stronger augmentation. The proposed network provides an efficient visual perception approach for automated crop inspection systems.","向工业化与自动化农业转型，需要可靠的机器视觉技术，以支持高通量作物健康监测与田间决策。然而，甘薯病害自动检测仍具挑战性，因为田间图像在叶片尺度、外观、光照、遮挡和背景复杂度方面存在显著变化。传统U形网络主要依赖固定卷积核和局部特征聚合，而基于Transformer的替代方案往往带来较大的计算开销。本文提出FDUNet-LRSA，一种频率自适应分割网络，融合了频域动态卷积、低分辨率自注意力与边界感知细化。频域动态卷积重建依赖输入的空间卷积核，以提升成像条件变化下的特征适应性。低分辨率自注意力在固定的紧凑特征空间中捕获长程上下文依赖，而边界感知细化在掩码重建过程中保留不规则叶片轮廓。在所报告的评估协议下，FDUNet-LRSA取得了0.94的平均测试前景IoU和0.97的Dice系数，计算量为3.72 GFLOPs。额外实验表明，与更强的增强相比，面向任务的中等增强可提升泛化能力。所提出的网络为自动化作物检测系统提供了一种高效的视觉感知方法。","Frontiers in Plant Science","2026-10-16T00:00:00Z",76,{"impact":98,"substance":17,"depth":18,"authority":99,"freshness":100,"relevant":21,"comment":101},16,13,9,"提出频域自适应分割网络，在甘薯病害检测上取得高精度且计算量低，方法有新意、结论可靠，属细分领域实质进展，值得进入每日精选。",[103],{"name":94,"url":91},[26,27,105,106,30],"作物病害","甘薯",{"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},[112,117,122],{"code":32,"score":45,"supported":46,"title":113,"abstract":114,"tags":116},[],[115],"decision support",[27,30],{"code":118,"score":52,"supported":46,"title":119,"abstract":120,"tags":121},"A5",[],[106],[106],{"code":65,"score":21,"supported":13,"title":123,"abstract":124,"tags":125},[],[],[26],[127,128],"FDUNet-LRSA 甘薯病害","甘薯病害 图像分割","FDUNet-LRSA甘薯病害-5147","10.3389\u002Ffpls.2026.1963106",{"doi":130,"openalex_id":132,"authors":133,"venue":94,"cited_by_count":76,"oa_url":156,"card":157,"direction":162,"ingested_from":163},"W7222502318",[134,137,140,143,145,148,150,152,154],{"name":135,"orcid":136},"Ru Han","https:\u002F\u002Forcid.org\u002F0009-0000-5128-1314",{"name":138,"orcid":139},"Lei Shu","https:\u002F\u002Forcid.org\u002F0000-0002-6700-9347",{"name":141,"orcid":142},"Grzegorz Cielniak","https:\u002F\u002Forcid.org\u002F0000-0002-6299-8465",{"name":144,"orcid":8},"Yan Zhu",{"name":146,"orcid":147},"Jucheng Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5046-2663",{"name":149,"orcid":8},"Fan Yang",{"name":151,"orcid":8},"Weihan Song",{"name":153,"orcid":8},"Qian Zhang",{"name":155,"orcid":8},"Kai Huang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1963106\u002Fpdf",{"tldr":158,"method":159,"finding":160,"direction":81,"opportunity":161},"提出频域自适应分割网络FDUNet-LRSA，用于甘薯病害自动巡检。","频域动态卷积、低分辨率自注意力与边界感知细化，结合适度数据增强。","测试前景IoU达0.94、Dice达0.97，仅3.72 GFLOPs，轻量高效。","可探索频域动态卷积在多种作物病害与复杂田间光照下的跨域泛化与边缘部署。","智慧农业 \u002F 农业物联网","openalex","2026-10-17T23:30:08.487857Z",{"id":166,"title":167,"url":168,"summary":169,"summary_zh":170,"content":8,"source_name":171,"source_url":168,"published_at":172,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":173,"score_detail":174,"sources":177,"tags":179,"primary_topic":182,"secondary_topics":183,"classification":184,"search_phrases":213,"slug":216,"view_count":52,"doi":217,"paper":218,"created_at":253},4010,"Intelligent Automated Crop Monitoring System Based on Unmanned Aerial Vehicles and Deep Learning for Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fapp16199747","The rapid development of precision agriculture technologies requires intelligent systems capable of automatically analyzing unmanned aerial vehicle (UAV) imagery and transforming image-processing results into structured information for crop-monitoring decision support. This study develops and computationally validates an integrated framework combining deep learning-based semantic segmentation, RGB-based spatial interpretation, image-space vectorization of candidate RGB heterogeneity zones, and monitoring-priority assessment. Experimental validation was performed using the open-access dataset “High-Resolution RGB Images and Corresponding Masks of Agricultural Fields”, comprising mixed agricultural vegetation scenes. Following data-integrity verification, 326 valid RGB image–reference mask pairs were retained and divided into 21,324 non-overlapping 512 × 512-pixel patches. U-Net-ResNet50, DeepLabV3-ResNet50, and FCN-ResNet50 were evaluated in three repeated source-image-grouped holdout experiments using the full dataset. U-Net-ResNet50 achieved the highest held-out performance, with mean Precision = 0.9946 ± 0.0008, Recall = 0.9931 ± 0.0021, vegetation IoU = 0.9877 ± 0.0020, and Dice = 0.9938 ± 0.0010, and was therefore selected for subsequent spatial analysis. Its segmentation outputs were combined with VARI, ExG, and GLI indices to identify candidate RGB heterogeneity zones, which were converted into image-space vector objects in source-image pixel coordinates. The revised full-data analysis generated 58,206 candidate RGB heterogeneity zones. These regions represent visible canopy heterogeneity rather than physiologically confirmed crop stress and are intended to support targeted field verification and monitoring prioritization. The results demonstrate the feasibility of an end-to-end UAV RGB processing workflow that transforms pixel-level segmentation outputs into structured spatial information for precision-agriculture monitoring and decision support.","精准农业技术的快速发展需要智能系统能够自动分析无人机（UAV）影像，并将图像处理结果转化为结构化信息，以支持作物监测决策。本研究开发并通过计算验证了一个集成框架，该框架结合了基于深度学习的语义分割、基于RGB的空间解译、候选RGB异质性区域的图像空间矢量化以及监测优先级评估。实验验证使用开放获取数据集“High-Resolution RGB Images and Corresponding Masks of Agricultural Fields”进行，该数据集包含混合农业植被场景。经数据完整性验证后，保留了326对有效RGB图像-参考掩膜对，并划分为21,324个不重叠的512 × 512像素图像块。使用完整数据集，在三次重复的以源图像分组的留出实验中评估了U-Net-ResNet50、DeepLabV3-ResNet50和FCN-ResNet50。U-Net-ResNet50取得了最高的留出性能，平均精确率 = 0.9946 ± 0.0008，召回率 = 0.9931 ± 0.0021，植被IoU = 0.9877 ± 0.0020，Dice = 0.9938 ± 0.0010，因此被选用于后续空间分析。其分割输出与VARI、ExG和GLI指数相结合，用于识别候选RGB异质性区域，并将其转换为源图像像素坐标下的图像空间矢量对象。修订后的全数据分析生成了58,206个候选RGB异质性区域。这些区域代表可见的冠层异质性，而非经生理学确认的作物胁迫，旨在支持有针对性的田间验证和监测优先级排序。结果表明，端到端无人机RGB处理工作流程具有可行性，该流程可将像素级分割输出转化为结构化空间信息，用于精准农业监测与决策支持。","Applied Sciences","2026-10-01T00:00:00Z",80,{"impact":16,"substance":175,"depth":16,"authority":99,"freshness":100,"relevant":21,"comment":176},22,"基于无人机RGB影像与深度学习语义分割的端到端作物监测框架，数据规模大、指标可靠，对精准农业决策支持有实质参考价值。",[178],{"name":171,"url":168},[26,27,180,181,30],"无人机遥感","作物监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":185},{"candidates":186,"agricultural_evidence":46},[187,194,202,209],{"code":32,"score":188,"supported":46,"title":189,"abstract":191,"tags":193},19,[190],"deep learning",[192,190,115],"深度学习",[27,30],{"code":65,"score":195,"supported":46,"title":196,"abstract":198,"tags":201},15,[197],"smart agriculture",[199,200],"精准农业","precision agriculture",[26],{"code":203,"score":86,"supported":46,"title":204,"abstract":205,"tags":208},"I4",[],[206,207],"空间分析","spatial analysis",[],{"code":58,"score":73,"supported":13,"title":210,"abstract":211,"tags":212},[],[],[181,180],[214,215],"UAV 作物监测 深度学习","U-Net 植被分割 无人机","UAV作物监测深度学习-4010","10.3390\u002Fapp16199747",{"doi":217,"openalex_id":219,"authors":220,"venue":171,"cited_by_count":76,"oa_url":168,"card":248,"direction":162,"ingested_from":163},"W7215074401",[221,224,227,230,232,234,237,239,242,245],{"name":222,"orcid":223},"Аnatoliy M. Тryhuba","https:\u002F\u002Forcid.org\u002F0000-0001-8014-5661",{"name":225,"orcid":226},"Paweł Kiełbasa","https:\u002F\u002Forcid.org\u002F0000-0003-0249-8626",{"name":228,"orcid":229},"Nazarii Ya. Koval","https:\u002F\u002Forcid.org\u002F0000-0001-7846-2924",{"name":231,"orcid":8},"Inna Tryhuba",{"name":233,"orcid":8},"Oleh Andrushkiv",{"name":235,"orcid":236},"Vitalij Grabovets","https:\u002F\u002Forcid.org\u002F0000-0002-0340-185X",{"name":238,"orcid":8},"Nataliia Kozak",{"name":240,"orcid":241},"Akinniyi Akinsunmade","https:\u002F\u002Forcid.org\u002F0000-0002-1602-1741",{"name":243,"orcid":244},"Anna Miernik","https:\u002F\u002Forcid.org\u002F0000-0003-0394-9185",{"name":246,"orcid":247},"Paweł Pysz","https:\u002F\u002Forcid.org\u002F0000-0001-7083-1078",{"tldr":249,"method":250,"finding":251,"direction":81,"opportunity":252},"构建无人机RGB影像深度学习分割与空间矢量化框架，实现作物监测优先级评估。","U-Net-ResNet50等模型在326张影像21,324个512×512块上","U-Net-ResNet50分割最优（IoU 0.9877），生成58,206个候选异质区用于田间验","可延伸研究：将RGB异质区与多光谱\u002F热红外数据融合，验证生理胁迫并构建实时决策模型。","2026-10-02T23:30:11.747839Z",{"id":255,"title":256,"url":257,"summary":258,"summary_zh":259,"content":8,"source_name":260,"source_url":257,"published_at":261,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":262,"score_detail":263,"sources":266,"tags":268,"primary_topic":271,"secondary_topics":272,"classification":273,"search_phrases":289,"slug":292,"view_count":73,"doi":293,"paper":294,"created_at":308},3195,"Segmentation of Cactus Diseases Using Machine and Deep Learning)","https:\u002F\u002Fdoi.org\u002F10.37394\u002F232018.2026.14.50","Artificial intelligence and machine learning play a critical role in plant disease detection and management. This study proposes an approach for diagnosing and segmenting cactus diseases using Random Forest (RF) and compares its performance with SVM, ANN, KNN, CNN, and U-Net models. A dataset of 20 cactus images (10 cochineal and 10 black bacterial soft rot), resized to 720×720 pixels, was used. Experimental results show that U-Net achieved the highest accuracy, reaching 98% for cochineal and 94% for black bacterial soft rot. RF also demonstrated strong performance, achieving 92% and 91%, respectively, outperforming several traditional machine learning models. These results confirm the effectiveness of U-Net for accurate segmentation and the suitability of RF for reliable disease detection with limited datasets, supporting their application in precision agriculture.","人工智能与机器学习在植物病害检测与管理中发挥着关键作用。本研究提出了一种利用随机森林（Random Forest, RF）诊断和分割仙人掌病害的方法，并将其性能与SVM、ANN、KNN、CNN和U-Net模型进行了比较。研究使用了20张仙人掌图像数据集（10张胭脂虫病害和10张黑细菌性软腐病），图像尺寸调整为720×720像素。实验结果表明，U-Net取得了最高准确率，胭脂虫病害达到98%，黑细菌性软腐病达到94%。随机森林同样表现出强劲性能，分别达到92%和91%，优于多种传统机器学习模型。这些结果证实了U-Net在精确分割方面的有效性，以及随机森林在有限数据集下进行可靠病害检测的适用性，支持其在精准农业中的应用。","WSEAS TRANSACTIONS ON COMPUTER RESEARCH","2026-09-21T00:00:00Z",62,{"impact":20,"substance":16,"depth":19,"authority":264,"freshness":12,"relevant":21,"comment":265},12,"方法对比扎实但数据集仅20张图像，属细分作物病害识别的技术验证，产业影响有限。",[267],{"name":260,"url":257},[26,27,269,30,270],"植物病害识别","仙人掌",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":274},{"candidates":275,"agricultural_evidence":46},[276,284],{"code":32,"score":277,"supported":46,"title":278,"abstract":279,"tags":283},20,[190],[280,281,282],"机器学习","machine learning","artificial intelligence",[27,30,269],{"code":65,"score":285,"supported":46,"title":286,"abstract":287,"tags":288},7,[],[199,200],[26],[290,291],"仙人掌 病害 图像分割","U-Net 胭脂虫 黑腐病","仙人掌病害图像分割-3195","10.37394\u002F232018.2026.14.50",{"doi":293,"openalex_id":295,"authors":296,"venue":260,"cited_by_count":76,"oa_url":257,"card":302,"direction":306,"ingested_from":163},"W7213945610",[297,299],{"name":298,"orcid":8},"Aissam El Ibrahimi",{"name":300,"orcid":301},"Nabil El Akchioui","https:\u002F\u002Forcid.org\u002F0000-0001-9808-932X",{"tldr":303,"method":304,"finding":305,"direction":306,"opportunity":307},"该研究用随机森林和多种深度学习模型对仙人掌病害进行分割诊断，并比较性能。","使用20张仙人掌图像，对比RF、SVM、ANN、KNN、CNN和U-Net模型。","U-Net分割准确率最高（胭脂虫98%，黑细菌软腐病94%），RF在有限数据下表现良好。","农业人工智能与决策模型","可探索小样本条件下传统机器学习与深度学习融合的病害分割方法，并扩展至更多作物和病害类型。","2026-09-22T23:30:39.786818Z",{"id":310,"title":311,"url":312,"summary":313,"summary_zh":314,"content":8,"source_name":315,"source_url":312,"published_at":316,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":317,"score_detail":318,"sources":320,"tags":322,"primary_topic":325,"secondary_topics":331,"classification":333,"search_phrases":350,"slug":353,"view_count":76,"doi":354,"paper":355,"created_at":369},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":20,"substance":17,"depth":16,"authority":264,"freshness":12,"relevant":21,"comment":319},"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。",[321],{"name":315,"url":312},[26,27,323,269,324],"小农户","可解释性",{"code":326,"slug":327,"name":328,"path":329,"parent_code":330},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[332],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":334},{"candidates":335,"agricultural_evidence":46},[336,341,346],{"code":326,"score":264,"supported":46,"title":337,"abstract":339,"tags":340},[338],"smallholder",[338],[323],{"code":32,"score":12,"supported":46,"title":342,"abstract":344,"tags":345},[343],"computer vision",[],[27,269],{"code":65,"score":21,"supported":13,"title":347,"abstract":348,"tags":349},[],[],[26],[351,352],"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":354,"openalex_id":356,"authors":357,"venue":315,"cited_by_count":76,"oa_url":312,"card":364,"direction":306,"ingested_from":163},"W7223137323",[358,360,362],{"name":359,"orcid":8},"Akshay Ramgoolam",{"name":361,"orcid":8},"Priya Bundhoo Appadoo",{"name":363,"orcid":8},"Jean-Noël LEspérance",{"tldr":365,"method":366,"finding":367,"direction":306,"opportunity":368},"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":371,"title":372,"url":373,"summary":374,"summary_zh":375,"content":8,"source_name":315,"source_url":373,"published_at":316,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":317,"score_detail":376,"sources":378,"tags":380,"primary_topic":384,"secondary_topics":390,"classification":392,"search_phrases":415,"slug":418,"view_count":76,"doi":419,"paper":420,"created_at":432},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":20,"substance":175,"depth":16,"authority":264,"freshness":100,"relevant":21,"comment":377},"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。",[379],{"name":315,"url":373},[26,27,381,382,383],"灌溉决策","安全保证","试验设计",{"code":385,"slug":386,"name":387,"path":388,"parent_code":389},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[391],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":393},{"candidates":394,"agricultural_evidence":46},[395,400,404,411],{"code":385,"score":195,"supported":46,"title":396,"abstract":397,"tags":399},[386],[398,386],"灌溉",[381],{"code":32,"score":264,"supported":46,"title":401,"abstract":402,"tags":403},[282],[115],[27],{"code":405,"score":86,"supported":46,"title":406,"abstract":407,"tags":410},"H2",[],[408,409],"土壤","soil",[],{"code":65,"score":21,"supported":13,"title":412,"abstract":413,"tags":414},[],[],[26],[416,417],"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":419,"openalex_id":421,"authors":422,"venue":315,"cited_by_count":76,"oa_url":373,"card":427,"direction":306,"ingested_from":163},"W7223131205",[423,425],{"name":424,"orcid":8},"Nassima Benkhelifa",{"name":426,"orcid":8},"Yacine Aït Ahmed",{"tldr":428,"method":429,"finding":430,"direction":306,"opportunity":431},"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":434,"title":435,"url":436,"summary":437,"summary_zh":438,"content":8,"source_name":315,"source_url":436,"published_at":316,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":439,"score_detail":440,"sources":442,"tags":444,"primary_topic":447,"secondary_topics":448,"classification":450,"search_phrases":465,"slug":468,"view_count":76,"doi":469,"paper":470,"created_at":484},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":20,"substance":175,"depth":16,"authority":264,"freshness":12,"relevant":21,"comment":441},"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。",[443],{"name":315,"url":436},[26,27,323,445,446],"作物病害识别","模型审计",{"code":326,"slug":327,"name":328,"path":329,"parent_code":330},[449],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":451},{"candidates":452,"agricultural_evidence":46},[453,457,461],{"code":326,"score":195,"supported":46,"title":454,"abstract":455,"tags":456},[338],[323,338],[323],{"code":32,"score":12,"supported":46,"title":458,"abstract":459,"tags":460},[343],[],[445,27],{"code":65,"score":21,"supported":13,"title":462,"abstract":463,"tags":464},[],[],[26],[466,467],"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":469,"openalex_id":471,"authors":472,"venue":315,"cited_by_count":76,"oa_url":436,"card":479,"direction":306,"ingested_from":163},"W7223088030",[473,475,477],{"name":474,"orcid":8},"Abdi-Basid Idriss Farah",{"name":476,"orcid":8},"Amina Abdillahi Guedi",{"name":478,"orcid":8},"Moussa Omar Youssouf",{"tldr":480,"method":481,"finding":482,"direction":306,"opportunity":483},"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"]