[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1727":3,"related-1727":73},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":29,"secondary_topics":35,"classification":36,"search_phrases":54,"slug":57,"view_count":58,"doi":59,"paper":60,"created_at":72},1727,"Deep Learning-Based Crop Disease Detection Using EfficientNet-B3 for Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10104203\u002Fv1","Deep Learning-Based Crop Disease Detection Using EfficientNet-B3 for Smart Agriculture。Research Square",null,"Research Square","2026-09-04T00:00:00Z","论文",10,false,56,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},12,15,14,8,7,1,"基于EfficientNet-B3的深度学习作物病害检测研究，方法有一定新颖性，但缺乏具体数据规模与结论细节，权威性一般。",[24],{"name":9,"url":6},[26,27,28],"智慧农业","农业人工智能","作物病害",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":37,"locked":13,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44},[42,49],{"code":43,"score":16,"supported":44,"title":45,"abstract":47,"tags":48},"I1",true,[46],"smart agriculture",[46],[26],{"code":30,"score":16,"supported":44,"title":50,"abstract":52,"tags":53},[51],"deep learning",[51],[27],[55,56],"农业人工智能 作物病害 智慧农业","农业人工智能 作物病害","农业人工智能作物病害智慧农业-1727",4,"10.21203\u002Frs.3.rs-10104203\u002Fv1",{"doi":59,"openalex_id":61,"authors":62,"venue":9,"cited_by_count":69,"oa_url":6,"card":8,"direction":70,"ingested_from":71},"W7208777285",[63,65,67],{"name":64,"orcid":8},"Gajanan Ankatwar",{"name":66,"orcid":8},"Chitra Dhawale",{"name":68,"orcid":8},"Supriya Narad",0,"智慧农业 \u002F 农业物联网","openalex","2026-09-05T23:30:09.738110Z",{"total":74,"page":21,"page_size":74,"items":75},6,[76,137,215,269,328,391],{"id":77,"title":78,"url":79,"summary":80,"summary_zh":81,"content":8,"source_name":82,"source_url":79,"published_at":83,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":84,"score_detail":85,"sources":90,"tags":92,"primary_topic":95,"secondary_topics":96,"classification":97,"search_phrases":116,"slug":119,"view_count":69,"doi":120,"paper":121,"created_at":136},5584,"Distributionally-Robust Evaluation of Computer Vision Agriculture Disease Classifiers Under Climate-Driven Pathogen Range Shifts: An Artificial Intelligence Worst-Case Generalization Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544150","Computer vision classifiers for crop disease are evaluated almost exclusively on held-out samples drawn from the same distribution as their training data, yet climate-driven pathogen range shifts mean that deployment environments are systematically out of distribution. The framework treats the deployment distribution as an adversarial perturbation of the training distribution within a Wasserstein ball whose radius is calibrated to observed climate displacement. Using NASA POWER monthly reanalysis for Harare, Zimbabwe (2000-2023, 312 monthly observations), the analysis estimates a mean air temperature of 18.914 C, a standard deviation of 3.107 C, and a warming trend of 0.2001 C per decade. These estimates anchor the radius of the ambiguity set and the resulting bound. The bound decomposes worst-case risk into an empirical risk term, a Wasserstein radius term scaled by the Lipschitz constant of the classifier, and a concentration term. Under plausible Lipschitz constants for convolutional backbones, the radius term dominates the empirical risk term once the climate displacement exceeds a threshold that the Harare record already approaches. The contribution is a formal evaluation criterion that replaces the i. i. d. assumption with a climate-calibrated ambiguity set, together with the analytical machinery needed to compute it.","作物病害的计算机视觉分类器几乎完全在与训练数据同分布的留出样本上进行评估，然而气候驱动的病原体分布范围变化意味着部署环境系统性地处于分布之外。该框架将部署分布视为训练分布在Wasserstein球内的对抗性扰动，球的半径根据观测到的气候位移进行校准。利用NASA POWER对津巴布韦哈拉雷的月度再分析数据（2000—2023年，312个月度观测值），分析估计平均气温为18.914°C，标准差为3.107°C，每十年升温趋势为0.2001°C。这些估计值锚定了模糊集的半径及由此得到的界。该界将最坏情况风险分解为经验风险项、由分类器Lipschitz常数缩放后的Wasserstein半径项以及集中项。在卷积骨干网络合理的Lipschitz常数下，一旦气候位移超过哈拉雷记录已接近的阈值，半径项便主导经验风险项。本文的贡献在于提出了一种形式化评估准则，以气候校准的模糊集替代独立同分布（i.i.d.）假设，并提供了计算该准则所需的分析工具。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",75,{"impact":16,"substance":86,"depth":87,"authority":88,"freshness":12,"relevant":21,"comment":89},22,18,13,"方法新颖、数据具体，但属方法论预印论文，产业影响有限，适合作为专业精选而非头条。",[91],{"name":82,"url":79},[26,27,93,28,94],"计算机视觉","气候变化",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":98},{"candidates":99,"agricultural_evidence":44},[100,107,112],{"code":30,"score":101,"supported":44,"title":102,"abstract":105,"tags":106},24,[103,104],"artificial intelligence","computer vision",[93,104],[27,93],{"code":108,"score":21,"supported":13,"title":109,"abstract":110,"tags":111},"H7",[],[],[94],{"code":43,"score":21,"supported":13,"title":113,"abstract":114,"tags":115},[],[],[26],[117,118],"NASA POWER 哈拉雷 气温","Wasserstein 分布鲁棒 病害分类","NASAPOWER哈拉雷气温-5584","10.5281\u002Fzenodo.23544150",{"doi":120,"openalex_id":122,"authors":123,"venue":82,"cited_by_count":69,"oa_url":79,"card":130,"direction":134,"ingested_from":71},"W7223087892",[124,126,128],{"name":125,"orcid":8},"Kossi Afeli",{"name":127,"orcid":8},"Akouvi Amegashie",{"name":129,"orcid":8},"Komlan Sélom Dossou",{"tldr":131,"method":132,"finding":133,"direction":134,"opportunity":135},"提出气候校准的分布鲁棒评估准则，替代i.i.d.假设评价作物病害视觉分类器。","用Wasserstein球建模部署分布偏移，以NASA POWER哈拉雷气温数据","气候位移超阈值后，半径项主导经验风险，现有评估会高估模型泛化能力。","农业人工智能与决策模型","可将气候校准的鲁棒评估扩展到多作物多区域，并研究适应分布偏移的鲁棒训练方法。","2026-10-22T11:21:00.036937Z",{"id":138,"title":139,"url":140,"summary":141,"summary_zh":142,"content":8,"source_name":143,"source_url":140,"published_at":144,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":145,"score_detail":146,"sources":152,"tags":154,"primary_topic":157,"secondary_topics":158,"classification":159,"search_phrases":177,"slug":180,"view_count":21,"doi":181,"paper":182,"created_at":214},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":147,"substance":148,"depth":149,"authority":88,"freshness":150,"relevant":21,"comment":151},16,21,17,9,"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。",[153],{"name":143,"url":140},[26,27,28,155,156],"甘薯","图像分割",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":160},{"candidates":161,"agricultural_evidence":44},[162,168,173],{"code":30,"score":163,"supported":44,"title":164,"abstract":165,"tags":167},5,[],[166],"decision support",[27,156],{"code":169,"score":58,"supported":44,"title":170,"abstract":171,"tags":172},"A5",[],[155],[155],{"code":43,"score":21,"supported":13,"title":174,"abstract":175,"tags":176},[],[],[26],[178,179],"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":181,"openalex_id":183,"authors":184,"venue":143,"cited_by_count":69,"oa_url":207,"card":208,"direction":70,"ingested_from":71},"W7222502318",[185,188,191,194,196,199,201,203,205],{"name":186,"orcid":187},"Ru Han","https:\u002F\u002Forcid.org\u002F0009-0000-5128-1314",{"name":189,"orcid":190},"Lei Shu","https:\u002F\u002Forcid.org\u002F0000-0002-6700-9347",{"name":192,"orcid":193},"Grzegorz Cielniak","https:\u002F\u002Forcid.org\u002F0000-0002-6299-8465",{"name":195,"orcid":8},"Yan Zhu",{"name":197,"orcid":198},"Jucheng Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5046-2663",{"name":200,"orcid":8},"Fan Yang",{"name":202,"orcid":8},"Weihan Song",{"name":204,"orcid":8},"Qian Zhang",{"name":206,"orcid":8},"Kai Huang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1963106\u002Fpdf",{"tldr":209,"method":210,"finding":211,"direction":212,"opportunity":213},"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。","农业遥感与作物表型","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。","2026-10-17T23:30:08.487857Z",{"id":216,"title":217,"url":218,"summary":219,"summary_zh":8,"content":8,"source_name":9,"source_url":218,"published_at":220,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":221,"score_detail":222,"sources":224,"tags":226,"primary_topic":228,"secondary_topics":233,"classification":235,"search_phrases":251,"slug":253,"view_count":58,"doi":254,"paper":255,"created_at":268},1404,"Explainable Deep Learning-Based Potato Leaf Disease Detection and Severity Assessment for Smart Agriculture in Bangladesh","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10879535\u002Fv1","Explainable Deep Learning-Based Potato Leaf Disease Detection and Severity Assessment for Smart Agriculture in Bangladesh。Research Square","2026-09-01T00:00:00Z",53,{"impact":19,"substance":17,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":223},"针对孟加拉国马铃薯病害的可解释深度学习检测研究，方法新颖但地域性强，影响有限。",[225],{"name":9,"url":218},[26,27,227,28],"马铃薯",{"code":169,"slug":229,"name":230,"path":231,"parent_code":232},"tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[234],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":236},{"candidates":237,"agricultural_evidence":44},[238,243,247],{"code":169,"score":16,"supported":44,"title":239,"abstract":241,"tags":242},[240],"potato",[240],[227],{"code":43,"score":16,"supported":44,"title":244,"abstract":245,"tags":246},[46],[46],[26],{"code":30,"score":16,"supported":44,"title":248,"abstract":249,"tags":250},[51],[51],[27],[252,56],"农业人工智能 作物病害 智慧农业 马铃薯","农业人工智能作物病害智慧农业马铃薯-1404","10.21203\u002Frs.3.rs-10879535\u002Fv1",{"doi":254,"openalex_id":256,"authors":257,"venue":9,"cited_by_count":69,"oa_url":267,"card":8,"direction":70,"ingested_from":71},"W7204884709",[258,261,264],{"name":259,"orcid":260},"Kazi Abdul Mannan","https:\u002F\u002Forcid.org\u002F0000-0002-7123-132X",{"name":262,"orcid":263},"Sinha Nafiz Hasan","https:\u002F\u002Forcid.org\u002F0009-0007-8906-4586",{"name":265,"orcid":266},"Ahmed Shafin","https:\u002F\u002Forcid.org\u002F0009-0000-4162-6913","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10879535\u002Flatest.pdf","2026-09-02T23:30:10.900822Z",{"id":270,"title":271,"url":272,"summary":273,"summary_zh":274,"content":8,"source_name":82,"source_url":272,"published_at":83,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":275,"score_detail":276,"sources":278,"tags":280,"primary_topic":284,"secondary_topics":290,"classification":292,"search_phrases":308,"slug":311,"view_count":69,"doi":312,"paper":313,"created_at":327},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。",69,{"impact":19,"substance":148,"depth":87,"authority":16,"freshness":12,"relevant":21,"comment":277},"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。",[279],{"name":82,"url":272},[26,27,281,282,283],"小农户","植物病害识别","可解释性",{"code":285,"slug":286,"name":287,"path":288,"parent_code":289},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[291],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":293},{"candidates":294,"agricultural_evidence":44},[295,300,304],{"code":285,"score":16,"supported":44,"title":296,"abstract":298,"tags":299},[297],"smallholder",[297],[281],{"code":30,"score":12,"supported":44,"title":301,"abstract":302,"tags":303},[104],[],[27,282],{"code":43,"score":21,"supported":13,"title":305,"abstract":306,"tags":307},[],[],[26],[309,310],"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":312,"openalex_id":314,"authors":315,"venue":82,"cited_by_count":69,"oa_url":272,"card":322,"direction":134,"ingested_from":71},"W7223137323",[316,318,320],{"name":317,"orcid":8},"Akshay Ramgoolam",{"name":319,"orcid":8},"Priya Bundhoo Appadoo",{"name":321,"orcid":8},"Jean-Noël LEspérance",{"tldr":323,"method":324,"finding":325,"direction":134,"opportunity":326},"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":329,"title":330,"url":331,"summary":332,"summary_zh":333,"content":8,"source_name":82,"source_url":331,"published_at":83,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":275,"score_detail":334,"sources":336,"tags":338,"primary_topic":342,"secondary_topics":348,"classification":350,"search_phrases":373,"slug":376,"view_count":69,"doi":377,"paper":378,"created_at":390},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":86,"depth":87,"authority":16,"freshness":150,"relevant":21,"comment":335},"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。",[337],{"name":82,"url":331},[26,27,339,340,341],"灌溉决策","安全保证","试验设计",{"code":343,"slug":344,"name":345,"path":346,"parent_code":347},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[349],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":351},{"candidates":352,"agricultural_evidence":44},[353,358,362,369],{"code":343,"score":17,"supported":44,"title":354,"abstract":355,"tags":357},[344],[356,344],"灌溉",[339],{"code":30,"score":16,"supported":44,"title":359,"abstract":360,"tags":361},[103],[166],[27],{"code":363,"score":74,"supported":44,"title":364,"abstract":365,"tags":368},"H2",[],[366,367],"土壤","soil",[],{"code":43,"score":21,"supported":13,"title":370,"abstract":371,"tags":372},[],[],[26],[374,375],"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":377,"openalex_id":379,"authors":380,"venue":82,"cited_by_count":69,"oa_url":331,"card":385,"direction":134,"ingested_from":71},"W7223131205",[381,383],{"name":382,"orcid":8},"Nassima Benkhelifa",{"name":384,"orcid":8},"Yacine Aït Ahmed",{"tldr":386,"method":387,"finding":388,"direction":134,"opportunity":389},"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":392,"title":393,"url":394,"summary":395,"summary_zh":396,"content":8,"source_name":82,"source_url":394,"published_at":83,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":397,"score_detail":398,"sources":400,"tags":402,"primary_topic":405,"secondary_topics":406,"classification":408,"search_phrases":423,"slug":426,"view_count":69,"doi":427,"paper":428,"created_at":442},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":86,"depth":87,"authority":16,"freshness":12,"relevant":21,"comment":399},"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。",[401],{"name":82,"url":394},[26,27,281,403,404],"作物病害识别","模型审计",{"code":285,"slug":286,"name":287,"path":288,"parent_code":289},[407],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":409},{"candidates":410,"agricultural_evidence":44},[411,415,419],{"code":285,"score":17,"supported":44,"title":412,"abstract":413,"tags":414},[297],[281,297],[281],{"code":30,"score":12,"supported":44,"title":416,"abstract":417,"tags":418},[104],[],[403,27],{"code":43,"score":21,"supported":13,"title":420,"abstract":421,"tags":422},[],[],[26],[424,425],"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":427,"openalex_id":429,"authors":430,"venue":82,"cited_by_count":69,"oa_url":394,"card":437,"direction":134,"ingested_from":71},"W7223088030",[431,433,435],{"name":432,"orcid":8},"Abdi-Basid Idriss Farah",{"name":434,"orcid":8},"Amina Abdillahi Guedi",{"name":436,"orcid":8},"Moussa Omar Youssouf",{"tldr":438,"method":439,"finding":440,"direction":134,"opportunity":441},"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"]