[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2907":3,"related-2907":81},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":56,"slug":59,"view_count":21,"doi":60,"paper":61,"created_at":80},2907,"MMTA-ACDD: Multi-teacher online adaptive learning and multimodal augmentation synergy for robust crop disease detection","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112429","The diagnosis and control of crop diseases are crucial for ensuring agricultural productivity. Single-stage real-time efficient detection models have been widely applied to crop disease detection tasks, but typically perform well only when the training and test sets have consistent distributions. However, in practical crop cultivation environments, real-time detection models not only need to perform excellently on source domain data but also must adapt to target domain data with different distributions. To address this challenge, this paper proposes a primary–auxiliary teacher collaborative enhanced supervision test-time adaptation framework to improve the robustness of real-time detection models in dynamic crop cultivation environments. Specifically, first, we propose a primary teacher supervision and auxiliary teacher guidance strategy, which combines weak augmentation and multimodal background strong augmentation techniques, respectively, to generate higher-quality pseudo-labels for the student model, thereby alleviating the problem of error accumulation in adaptive training. Second, we propose a maximum gradient dynamic adaptive recovery strategy(MGDA), which retains more effective knowledge from the source model by setting a maximum recovery trigger threshold and dynamic adaptive mechanism, preventing the student model from forgetting original knowledge when adapting to new domains. Finally, to enhance the robustness of the multi-teacher architecture under target distribution shift, we introduce a target class-aware contrastive learning strategy(OACL) to more effectively utilize pseudo-labels for feature learning in crop disease target detection tasks. Experimental results demonstrate that our proposed framework significantly improves the performance of real-time detection models in dynamic environments, providing an effective solution for crop disease detection.","作物病害的诊断与控制对保障农业生产力至关重要。单阶段实时高效检测模型已广泛应用于作物病害检测任务，但通常仅在训练集与测试集分布一致时表现良好。然而，在实际作物种植环境中，实时检测模型不仅需要在源域数据上表现优异，还必须适应具有不同分布的目标域数据。为解决这一挑战，本文提出了一种主辅教师协同增强监督的测试时自适应框架，以提升实时检测模型在动态作物种植环境中的鲁棒性。具体而言，首先，我们提出了主教师监督与辅助教师引导策略，分别结合弱增强和多模态背景强增强技术，为学生模型生成更高质量的伪标签，从而缓解自适应训练中的误差累积问题。其次，我们提出了最大梯度动态自适应恢复策略（MGDA），通过设置最大恢复触发阈值和动态自适应机制，保留源模型中更有效的知识，防止学生模型在适应新域时遗忘原有知识。最后，为增强多教师架构在目标分布偏移下的鲁棒性，我们引入了目标类别感知对比学习策略（OACL），以更有效地利用伪标签进行作物病害目标检测任务中的特征学习。实验结果表明，本文提出的框架显著提升了实时检测模型在动态环境中的性能，为作物病害检测提供了有效的解决方案。",null,"Computers and Electronics in Agriculture","2026-09-18T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"提出主辅教师协同与多模态增强的测试时自适应框架，显著提升动态农田环境下实时病害检测鲁棒性，方法新颖且实验充分，值得精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","作物病害检测","域自适应","多模态增强",{"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":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":50},4,true,[],[49],"目标检测",[27],{"code":52,"score":21,"supported":14,"title":53,"abstract":54,"tags":55},"I1",[],[],[26],[57,58],"作物病害检测 域自适应 多教师","作物病害检测 农业人工智能 多模态增强 域自适应","作物病害检测域自适应多教师-2907","10.1016\u002Fj.compag.2026.112429",{"doi":60,"openalex_id":62,"authors":63,"venue":10,"cited_by_count":72,"oa_url":6,"card":73,"direction":77,"ingested_from":79},"W7213546000",[64,66,68,70],{"name":65,"orcid":9},"Hao Sun",{"name":67,"orcid":9},"Shiyu Wang",{"name":69,"orcid":9},"Zhenqi Cheng",{"name":71,"orcid":9},"Rui Fu",0,{"tldr":74,"method":75,"finding":76,"direction":77,"opportunity":78},"提出多教师在线自适应与多模态增强框架，提升作物病害实时检测模型在动态环境下的鲁棒性。","主辅教师协同监督测试时自适应，弱增强与多模态背景强增强生成伪标签，MGDA与OA","框架显著提升实时检测模型在分布偏移下的性能，缓解伪标签误差累积与源知识遗忘。","农业人工智能与决策模型","可探索多模态增强与测试时自适应在田间边缘设备上的轻量化部署及跨作物泛化。","openalex","2026-09-19T23:30:01.851144Z",{"total":82,"page":21,"page_size":82,"items":83},6,[84,142,202,267,319,369],{"id":85,"title":86,"url":87,"summary":88,"summary_zh":89,"content":9,"source_name":90,"source_url":87,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":92,"score_detail":93,"sources":99,"tags":101,"primary_topic":104,"secondary_topics":105,"classification":106,"search_phrases":123,"slug":126,"view_count":72,"doi":127,"paper":128,"created_at":141},5580,"Backdoor-Trigger Evaluation for Computer Agriculture Disease-Detection Models Under Third-Party Pretrained Checkpoints: An Artificial Intelligence Poisoning-Rate Audit","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544382","Third-party pretrained checkpoints are now the default starting point for computer-vision disease detectors in digital agriculture, yet the poisoning rate at which a backdoor trigger survives fine-tuning on clean crop imagery has not been characterised as a design quantity. the present analysis treats the backdoor trigger as a property of the checkpoint supply chain rather than of the attacker, and asks what poisoning rate a defender must assume when the provenance of the pretrained weights is unknown. A formal model of trigger persistence is developed in which the backdoor is represented as a parameter-space displacement whose survival under gradient fine-tuning depends on the ratio of trigger-aligned to task-aligned curvature. From this model a persistence bound is derived, and the bound is then embedded in a before-after-control-impact design that treats the poisoned checkpoint as the intervention and the clean checkpoint as the control. Operating characteristics were evaluated across 2000 replications per design cell for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points, under a declared variance structure with between-cluster SD of 6.0, residual SD of 4.5 and intraclass correlation of 0.64. The design required 54 clusters to detect a 5 percentage-point difference at 80% power.","第三方预训练检查点现已成为数字农业中计算机视觉病害检测器的默认起点，然而，后门触发器在干净作物图像上经过微调后仍能存活的投毒率，尚未被作为一个设计量加以刻画。本分析将后门触发器视为检查点供应链的一种属性，而非攻击者的属性，并追问：当预训练权重的来源未知时，防御者必须假定怎样的投毒率。本文建立了一个触发器持续性的形式化模型，其中后门被表示为参数空间中的位移，其在梯度微调下的存活取决于触发器对齐曲率与任务对齐曲率之比。由该模型推导出一个持续性界，并将该界嵌入前后对照干预设计，将受投毒检查点作为干预、干净检查点作为对照。在每设计单元2000次重复下评估运行特性，聚类数为8、16、24和32，效应量为3、5和8个百分点，在声明的方差结构下，组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64。该设计需要54个聚类才能在80%功效下检测到5个百分点的差异。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",67,{"impact":94,"substance":95,"depth":96,"authority":97,"freshness":13,"relevant":21,"comment":98},8,21,17,11,"该研究把后门投毒率作为预训练权重供应链的设计量来量化，方法新颖、统计设计严谨，但属于细分安全审计方向，产业影响有限，适合作为专业精选而非头条。",[100],{"name":90,"url":87},[26,27,28,102,103],"模型后门","预训练模型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":107},{"candidates":108,"agricultural_evidence":46},[109,116],{"code":32,"score":110,"supported":46,"title":111,"abstract":113,"tags":115},12,[112],"artificial intelligence",[114],"计算机视觉",[27],{"code":52,"score":117,"supported":46,"title":118,"abstract":119,"tags":122},7,[],[120,121],"数字农业","digital agriculture",[26],[124,125],"农业病害检测 后门触发 投毒率","第三方预训练权重 后门","农业病害检测后门触发投毒率-5580","10.5281\u002Fzenodo.23544382",{"doi":127,"openalex_id":129,"authors":130,"venue":90,"cited_by_count":72,"oa_url":87,"card":135,"direction":140,"ingested_from":79},"W7223102358",[131,133],{"name":132,"orcid":9},"Teresa Kambanda Neto",{"name":134,"orcid":9},"Mateus Chilombo Kiala",{"tldr":136,"method":137,"finding":138,"direction":77,"opportunity":139},"将后门触发器视为预训练检查点供应链属性，量化微调后后门存活的投毒率。","建立触发器持久性形式化模型，推导持久性界，嵌入前后对照设计，2000次重复模拟。","检测5个百分点差异需54个聚类，给出防御者应假设的投毒率设计量。","可研究不同作物病害检测架构与微调策略下后门持久性界的实证验证与防御阈值。","数字乡村与农业信息化","2026-10-22T11:20:47.572271Z",{"id":143,"title":144,"url":145,"summary":146,"summary_zh":147,"content":9,"source_name":90,"source_url":145,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":148,"score_detail":149,"sources":151,"tags":153,"primary_topic":157,"secondary_topics":163,"classification":165,"search_phrases":182,"slug":185,"view_count":72,"doi":186,"paper":187,"created_at":201},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":94,"substance":95,"depth":17,"authority":110,"freshness":13,"relevant":21,"comment":150},"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。",[152],{"name":90,"url":145},[26,27,154,155,156],"小农户","植物病害识别","可解释性",{"code":158,"slug":159,"name":160,"path":161,"parent_code":162},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[164],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":166},{"candidates":167,"agricultural_evidence":46},[168,173,178],{"code":158,"score":110,"supported":46,"title":169,"abstract":171,"tags":172},[170],"smallholder",[170],[154],{"code":32,"score":13,"supported":46,"title":174,"abstract":176,"tags":177},[175],"computer vision",[],[27,155],{"code":52,"score":21,"supported":14,"title":179,"abstract":180,"tags":181},[],[],[26],[183,184],"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":186,"openalex_id":188,"authors":189,"venue":90,"cited_by_count":72,"oa_url":145,"card":196,"direction":77,"ingested_from":79},"W7223137323",[190,192,194],{"name":191,"orcid":9},"Akshay Ramgoolam",{"name":193,"orcid":9},"Priya Bundhoo Appadoo",{"name":195,"orcid":9},"Jean-Noël LEspérance",{"tldr":197,"method":198,"finding":199,"direction":77,"opportunity":200},"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":203,"title":204,"url":205,"summary":206,"summary_zh":207,"content":9,"source_name":90,"source_url":205,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":148,"score_detail":208,"sources":210,"tags":212,"primary_topic":216,"secondary_topics":222,"classification":224,"search_phrases":249,"slug":252,"view_count":72,"doi":253,"paper":254,"created_at":266},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":94,"substance":18,"depth":17,"authority":110,"freshness":20,"relevant":21,"comment":209},"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。",[211],{"name":90,"url":205},[26,27,213,214,215],"灌溉决策","安全保证","试验设计",{"code":217,"slug":218,"name":219,"path":220,"parent_code":221},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[223],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":225},{"candidates":226,"agricultural_evidence":46},[227,233,238,245],{"code":217,"score":228,"supported":46,"title":229,"abstract":230,"tags":232},15,[218],[231,218],"灌溉",[213],{"code":32,"score":110,"supported":46,"title":234,"abstract":235,"tags":237},[112],[236],"decision support",[27],{"code":239,"score":82,"supported":46,"title":240,"abstract":241,"tags":244},"H2",[],[242,243],"土壤","soil",[],{"code":52,"score":21,"supported":14,"title":246,"abstract":247,"tags":248},[],[],[26],[250,251],"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":253,"openalex_id":255,"authors":256,"venue":90,"cited_by_count":72,"oa_url":205,"card":261,"direction":77,"ingested_from":79},"W7223131205",[257,259],{"name":258,"orcid":9},"Nassima Benkhelifa",{"name":260,"orcid":9},"Yacine Aït Ahmed",{"tldr":262,"method":263,"finding":264,"direction":77,"opportunity":265},"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":268,"title":269,"url":270,"summary":271,"summary_zh":272,"content":9,"source_name":90,"source_url":270,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":273,"score_detail":274,"sources":276,"tags":278,"primary_topic":281,"secondary_topics":282,"classification":284,"search_phrases":299,"slug":302,"view_count":72,"doi":303,"paper":304,"created_at":318},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":94,"substance":18,"depth":17,"authority":110,"freshness":13,"relevant":21,"comment":275},"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。",[277],{"name":90,"url":270},[26,27,154,279,280],"作物病害识别","模型审计",{"code":158,"slug":159,"name":160,"path":161,"parent_code":162},[283],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":285},{"candidates":286,"agricultural_evidence":46},[287,291,295],{"code":158,"score":228,"supported":46,"title":288,"abstract":289,"tags":290},[170],[154,170],[154],{"code":32,"score":13,"supported":46,"title":292,"abstract":293,"tags":294},[175],[],[279,27],{"code":52,"score":21,"supported":14,"title":296,"abstract":297,"tags":298},[],[],[26],[300,301],"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":303,"openalex_id":305,"authors":306,"venue":90,"cited_by_count":72,"oa_url":270,"card":313,"direction":77,"ingested_from":79},"W7223088030",[307,309,311],{"name":308,"orcid":9},"Abdi-Basid Idriss Farah",{"name":310,"orcid":9},"Amina Abdillahi Guedi",{"name":312,"orcid":9},"Moussa Omar Youssouf",{"tldr":314,"method":315,"finding":316,"direction":77,"opportunity":317},"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":320,"title":321,"url":322,"summary":323,"summary_zh":324,"content":9,"source_name":90,"source_url":322,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":325,"score_detail":326,"sources":328,"tags":330,"primary_topic":333,"secondary_topics":334,"classification":335,"search_phrases":353,"slug":356,"view_count":72,"doi":357,"paper":358,"created_at":368},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":94,"substance":17,"depth":96,"authority":20,"freshness":13,"relevant":21,"comment":327},"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。",[329],{"name":90,"url":322},[26,27,331,332],"精准施药","病虫害监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":336},{"candidates":337,"agricultural_evidence":46},[338,342,348],{"code":32,"score":20,"supported":46,"title":339,"abstract":340,"tags":341},[112],[],[27],{"code":52,"score":117,"supported":46,"title":343,"abstract":344,"tags":347},[],[345,346],"精准农业","precision agriculture",[26],{"code":349,"score":21,"supported":14,"title":350,"abstract":351,"tags":352},"F4",[],[],[331],[354,355],"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":357,"openalex_id":359,"authors":360,"venue":90,"cited_by_count":72,"oa_url":322,"card":363,"direction":77,"ingested_from":79},"W7223116087",[361],{"name":362,"orcid":9},"Achieng' Atim Okello",{"tldr":364,"method":365,"finding":366,"direction":77,"opportunity":367},"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",{"id":370,"title":371,"url":372,"summary":373,"summary_zh":374,"content":9,"source_name":90,"source_url":372,"published_at":91,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":375,"score_detail":376,"sources":378,"tags":380,"primary_topic":384,"secondary_topics":385,"classification":386,"search_phrases":414,"slug":417,"view_count":72,"doi":418,"paper":419,"created_at":430},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。",74,{"impact":110,"substance":18,"depth":17,"authority":110,"freshness":13,"relevant":21,"comment":377},"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[379],{"name":90,"url":372},[26,27,381,382,383],"粮食安全","遥感","气候分析",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":387},{"candidates":388,"agricultural_evidence":46},[389,393,400,405,409],{"code":32,"score":20,"supported":46,"title":390,"abstract":391,"tags":392},[112],[],[27],{"code":394,"score":395,"supported":46,"title":396,"abstract":397,"tags":399},"I5",3,[],[398],"农业传感",[],{"code":401,"score":21,"supported":14,"title":402,"abstract":403,"tags":404},"A8",[],[],[381],{"code":52,"score":21,"supported":14,"title":406,"abstract":407,"tags":408},[],[],[26],{"code":410,"score":21,"supported":14,"title":411,"abstract":412,"tags":413},"I3",[],[],[382],[415,416],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":418,"openalex_id":420,"authors":421,"venue":90,"cited_by_count":72,"oa_url":372,"card":424,"direction":77,"ingested_from":79},"W7223111766",[422],{"name":423,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":425,"method":426,"finding":427,"direction":428,"opportunity":429},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","农业遥感与作物表型","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","2026-10-22T11:21:02.682497Z"]