[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3861":3,"related-3861":108},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":82,"slug":85,"view_count":86,"doi":87,"paper":88,"created_at":107},3861,"TOE Drivers and Farm Performance: The Mediating Role of AI Adoption in Omani Hydroponics—An Exploratory Sequential Mixed-Methods Study","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu18199941","Artificial intelligence (AI) provides significant benefits for hydroponic systems by enabling precise nutrient management, efficient water recycling, and predictive decision support. However, adoption of AI in Omani hydroponic operations remains inconsistent, and the mechanisms linking contextual factors to farm-level performance are not well understood. This study investigates how technological, organizational, and environmental conditions relate to AI adoption, the association between adoption and perceived performance, and the mediating role of adoption in this relationship. An exploratory sequential mixed-methods approach, based on the Technology–Organization–Environment (TOE) framework, was employed. Data from nineteen interviews produced 563 coded references, and that material then shaped the item wording of a structured survey we administered to seventy-nine respondents. Reliability analysis using Cronbach’s alpha demonstrated acceptable to excellent internal consistency (α = 0.71–0.92). All three TOE dimensions were significant predictors of AI adoption (β = 0.29–0.33; R2 = 0.58). AI adoption emerged as the sole significant direct predictor of perceived performance (β = 0.70; R2 = 0.67), with none of the TOE dimensions retaining a significant direct association. Bootstrap analysis with five thousand resamples confirmed significant indirect effects for the Technological and Environmental dimensions, while the indirect effect for the Organizational dimension was inconclusive: its confidence interval crossing zero—a pattern we read as jointly reflecting heterogeneous organizational capacity across farms and the limited statistical power of a study this size for smaller effects. This study advances the TOE framework within Gulf-region hydroponic agriculture, identifies AI adoption as a key mediating mechanism, and provides evidence-based recommendations for policymakers, agricultural institutions, and technology providers. Since we define performance here in terms of water recycling, resource use and yield stability, the observed associations speak directly to sustainable production in arid settings.","人工智能（AI）为水培系统带来了显著效益，能够实现精准养分管理、高效水循环利用和预测性决策支持。然而，阿曼水培运营中AI的采用仍不均衡，情境因素与农场层面绩效之间的关联机制尚不明确。本研究探讨技术、组织与环境条件如何与AI采用相关，采用与感知绩效之间的关联，以及采用在这一关系中的中介作用。研究采用基于技术—组织—环境（TOE）框架的探索性序贯混合方法。来自十九次访谈的数据产生了563条编码引用，这些材料随后塑造了我们向七十九名受访者发放的结构化问卷的题项措辞。使用克隆巴赫α进行的信度分析显示内部一致性处于可接受至优秀水平（α = 0.71–0.92）。TOE三个维度均为AI采用的显著预测因素（β = 0.29–0.33；R² = 0.58）。AI采用成为感知绩效唯一显著的直接预测因素（β = 0.70；R² = 0.67），而TOE各维度均未保留显著的直接关联。基于五千次重抽样的Bootstrap分析确认了技术维度与环境维度的显著间接效应，而组织维度的间接效应尚无定论：其置信区间跨越零——我们将这一模式解读为既反映了各农场组织能力的异质性，也反映了本研究在检测较小效应方面统计功效有限。本研究推进了TOE框架在海湾地区水培农业中的应用，确认AI采用为关键中介机制，并为政策制定者、农业机构和技术提供者提供了循证建议。由于我们将绩效界定为水循环利用、资源使用和产量稳定性，所观察到的关联直接关系到干旱环境下的可持续生产。",null,"Sustainability","2026-09-29T00:00:00Z","论文",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,21,17,13,9,1,"以TOE框架结合混合方法实证AI采纳对阿曼水培农场绩效的中介作用，方法规范、数据扎实，但样本量小且地域性强，属细分领域学术进展。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","节水农业","水培农业","TOE框架",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,53,60,66,72,77],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":52},7,true,[],[50,51],"artificial intelligence","decision support",[28],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":59},"B7",3,[],[58],"hydroponic",[],{"code":61,"score":55,"supported":47,"title":62,"abstract":63,"tags":65},"F3",[],[64],"养分管理",[],{"code":67,"score":55,"supported":47,"title":68,"abstract":69,"tags":71},"H7",[],[70],"干旱",[],{"code":73,"score":22,"supported":14,"title":74,"abstract":75,"tags":76},"H3",[],[],[29],{"code":78,"score":22,"supported":14,"title":79,"abstract":80,"tags":81},"I1",[],[],[27],[83,84],"阿曼 水培 AI 采纳","TOE框架 水培农场绩效","阿曼水培AI采纳-3861",0,"10.3390\u002Fsu18199941",{"doi":87,"openalex_id":89,"authors":90,"venue":10,"cited_by_count":86,"oa_url":6,"card":99,"direction":105,"ingested_from":106},"W7214748616",[91,93,96],{"name":92,"orcid":9},"Duaa Al Ghafri",{"name":94,"orcid":95},"Abdulaziz Aborujilah","https:\u002F\u002Forcid.org\u002F0000-0002-7497-4321",{"name":97,"orcid":98},"Samir Hammami","https:\u002F\u002Forcid.org\u002F0000-0002-4003-5705",{"tldr":100,"method":101,"finding":102,"direction":103,"opportunity":104},"基于TOE框架，用混合方法研究阿曼水培农场AI采纳的驱动因素及对绩效的中介作用。","探索性序列混合方法：19次访谈编码加79份问卷，TOE框架与Bootstrap中","AI采纳是绩效唯一显著直接预测因子，技术、环境维度通过采纳产生显著间接效应。","智慧农业 \u002F 农业物联网","可扩大样本并引入客观绩效指标，检验组织维度中介效应及干旱区水培AI采纳的跨区域普适性。","农业人工智能与决策模型","openalex","2026-09-30T23:30:50.324727Z",{"total":109,"page":22,"page_size":109,"items":110},6,[111,198,274,336,391,443],{"id":112,"title":113,"url":114,"summary":115,"summary_zh":116,"content":9,"source_name":117,"source_url":114,"published_at":118,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":120,"sources":126,"tags":128,"primary_topic":131,"secondary_topics":136,"classification":138,"search_phrases":175,"slug":178,"view_count":109,"doi":179,"paper":180,"created_at":197},4567,"An embedded deep learning–fuzzy logic framework for intelligent and automated irrigation in smart farming","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72706-5","Water scarcity and the need to improve resource efficiency have made intelligent and automated irrigation management an important research challenge in smart farming. This study proposes IrrigaDL-FL, a low-cost automated smart irrigation framework based on the internet of things, integrating intelligent data routing with adaptive irrigation decision-making. The proposed framework consists of two complementary components. First, a Deep Learning–Fuzzy Logic (DL-FL) framework is integrated with the Open Shortest Path First (OSPF) protocol to enhance data routing efficiency in the network. The DL-FL framework combines these heterogeneous characteristics to identify suitable next-hop nodes and establish energy-efficient routing paths. Second, irrigation decision-making is performed using a lightweight Convolutional Neural Network–Fuzzy Logic Controller (CNN-FLC). The CNN-FLC processes sensor-derived and crop-related information, including air temperature, relative humidity, soil moisture, evapotranspiration rate, crop growth coefficient, crop water requirement, planting date, cumulative rainfall, recent rainfall, irrigation history, crop growth stage, and the difference between actual and target soil moisture. These inputs are used to characterize crop hydration stress and dynamically determine the appropriate irrigation program and sprinkler activation duration. The proposed IrrigaDL-FL framework is evaluated through simulations with different numbers of sensor nodes over predefined routing rounds and is compared with several existing approaches. The results demonstrate that IrrigaDL-FL achieves superior performance in terms of network lifetime, residual energy, energy variance, number of transmitted packets, and average path length.","水资源短缺与提高资源效率的需求，使智能化和自动化灌溉管理成为智慧农业中的重要研究挑战。本研究提出IrrigaDL-FL，一种基于物联网的低成本自动化智能灌溉框架，将智能数据路由与自适应灌溉决策相结合。该框架由两个互补部分组成。首先，将深度学习-模糊逻辑（DL-FL）框架与开放最短路径优先（OSPF）协议集成，以提高网络中的数据路由效率。DL-FL框架结合这些异构特征来识别合适的下一跳节点并建立节能路由路径。其次，灌溉决策通过轻量级卷积神经网络-模糊逻辑控制器（CNN-FLC）执行。CNN-FLC处理来自传感器的信息和作物相关信息，包括空气温度、相对湿度、土壤湿度、蒸散速率、作物生长系数、作物需水量、种植日期、累计降雨量、近期降雨量、灌溉历史、作物生长阶段以及实际土壤湿度与目标土壤湿度之间的差值。这些输入用于表征作物水分胁迫，并动态确定合适的灌溉方案和喷灌器启动时长。所提出的IrrigaDL-FL框架通过在预定义路由轮次下对不同数量传感器节点进行仿真评估，并与若干现有方法进行比较。结果表明，IrrigaDL-FL在网络寿命、剩余能量、能量方差、传输数据包数量和平均路径长度方面均取得了更优性能。","Scientific Reports","2026-10-08T00:00:00Z",77,{"impact":121,"substance":18,"depth":122,"authority":123,"freshness":124,"relevant":22,"comment":125},16,18,14,8,"提出低成本物联网智能灌溉框架，融合深度学习与模糊逻辑优化路由与灌溉决策，方法新颖、仿真验证充分，对智慧农业节水研究有参考价值。",[127],{"name":117,"url":114},[27,28,129,130,29],"农业物联网","智能灌溉",{"code":73,"slug":132,"name":133,"path":134,"parent_code":135},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[137],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":139},{"candidates":140,"agricultural_evidence":47},[141,149,156,163,170],{"code":73,"score":142,"supported":47,"title":143,"abstract":144,"tags":148},19,[132],[145,146,132,147],"灌溉","水资源","evapotranspiration",[130,29],{"code":33,"score":150,"supported":47,"title":151,"abstract":153,"tags":155},15,[152],"deep learning",[154,152],"深度学习",[28],{"code":157,"score":46,"supported":47,"title":158,"abstract":159,"tags":162},"I5",[],[160,161],"物联网","internet of things",[129],{"code":164,"score":109,"supported":47,"title":165,"abstract":166,"tags":169},"H2",[],[167,168],"土壤","soil",[],{"code":78,"score":171,"supported":47,"title":172,"abstract":173,"tags":174},4,[],[27],[27],[176,177],"IrrigaDL-FL 智能灌溉","CNN-FLC 灌溉决策","IrrigaDL-FL智能灌溉-4567","10.1038\u002Fs41598-026-72706-5",{"doi":179,"openalex_id":181,"authors":182,"venue":117,"cited_by_count":86,"oa_url":191,"card":192,"direction":103,"ingested_from":106},"W7221040139",[183,185,187,189],{"name":184,"orcid":9},"Ze Luo",{"name":186,"orcid":9},"Zhuo Yang",{"name":188,"orcid":9},"Yi Hu",{"name":190,"orcid":9},"Jun Wang","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72706-5_reference.pdf",{"tldr":193,"method":194,"finding":195,"direction":103,"opportunity":196},"提出IrrigaDL-FL低成本物联网智能灌溉框架，融合深度学习与模糊逻辑优化路由和灌溉决策。","用CNN-模糊逻辑控制器处理多源传感器与作物数据，结合OSPF协议做节能路由。","在仿真中网络寿命、剩余能量、能耗方差、传输包数和平均路径长度均优于现有方法。","可探索真实农田部署下多作物、多气候场景的泛化能力与边缘计算资源约束优化。","2026-10-10T23:30:11.306685Z",{"id":199,"title":200,"url":201,"summary":202,"summary_zh":203,"content":9,"source_name":204,"source_url":201,"published_at":205,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":206,"sources":209,"tags":211,"primary_topic":213,"secondary_topics":214,"classification":221,"search_phrases":248,"slug":251,"view_count":124,"doi":252,"paper":253,"created_at":273},3355,"AI and Sustainable Agriculture Through Cost–Benefit Analysis of Smart Irrigation Systems","https:\u002F\u002Fdoi.org\u002F10.22004\u002Fag.econ.412813","The advancing role of Artificial Intelligence (AI) and its application in agriculture have disrupted traditional agricultural practices, with smart irrigation systems representing one of the leading technologies enabling sustainable agriculture. Smart irrigation systems utilize real–time data, machine learning algorithms, and predictive analytics to better optimize irrigation water use, limit wasted resources, and improve the yields of crop products. The proposed research will assess the economic and environmental impacts of AI smart irrigation systems with a full costs–benefits analysis. The proposed research considers both the capital cost and operating cost of smart irrigation systems and compares these traditional irrigation practices while also examining the long–term benefits of potential water savings from Smart Irrigation Systems, expanded agricultural production, and reduced human labour. This will give context for measuring the impacts of Smart Irrigation Systems on farm businesses, including both opportunities and barriers to adoption. Additionally, using a formal literature review to lock down existing research and surveys of irrigation farmers to collect a field data set will provide the proposed researchers a collective sample to measure the efficacy of AI smart irrigation systems, identify barriers, compare opportunities, and measure performance under differing climate and soil properties. The research will find high and substantial respective levels of benefits from the implementation of AI–based smart systems, particularly in water–stressed systems with positive impacts on farm profitability, private, and environmental conservation. This research is essential for informing stakeholders of actions and the delivery of AI–enabled solutions in support of more sustainable agricultural practices.","人工智能（Artificial Intelligence, AI）的不断发展及其在农业中的应用已经颠覆了传统的农业实践，其中智能灌溉系统是实现可持续农业的领先技术之一。智能灌溉系统利用实时数据、机器学习算法和预测分析，更好地优化灌溉用水、减少资源浪费并提高作物产量。拟议研究将通过全面的成本效益分析，评估AI智能灌溉系统的经济和环境影响。该研究将综合考虑智能灌溉系统的资本成本和运营成本，并将其与传统灌溉实践进行比较，同时考察智能灌溉系统在潜在节水、扩大农业生产和减少人力劳动方面的长期效益。这将为衡量智能灌溉系统对农场经营的影响提供背景，包括采用的机会和障碍。此外，通过正式文献综述锁定现有研究成果，并对灌溉农户进行调查以收集实地数据集，将为拟议研究者提供一个集体样本，用以衡量AI智能灌溉系统的效能、识别障碍、比较机会，并评估在不同气候和土壤条件下的表现。研究发现，实施基于AI的智能系统可带来显著且可观的效益，尤其是在水资源紧张的地区，对农场盈利能力、私人利益和环境保护均有积极影响。这项研究对于向利益相关者通报行动方案以及推动AI赋能解决方案以支持更可持续的农业实践至关重要。","AgEcon Search (University of Minnesota, USA)","2026-09-23T00:00:00Z",{"impact":122,"substance":207,"depth":122,"authority":20,"freshness":124,"relevant":22,"comment":208},20,"该研究以成本效益分析评估AI智能灌溉的经济与环境效益，方法系统、结论具参考价值，但属学术论文而非政策或产业事件，适合作为智慧农业主题的深度补充。",[210],{"name":204,"url":201},[27,28,130,29,212],"成本效益分析",{"code":73,"slug":132,"name":133,"path":134,"parent_code":135},[215,220],{"code":216,"slug":217,"name":218,"path":219,"parent_code":135},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":222},{"candidates":223,"agricultural_evidence":47},[224,228,234,240,244],{"code":73,"score":142,"supported":47,"title":225,"abstract":226,"tags":227},[132],[145,146,132],[130,29],{"code":216,"score":123,"supported":47,"title":229,"abstract":231,"tags":233},[230],"sustainable agriculture",[232,230],"可持续农业",[],{"code":33,"score":13,"supported":47,"title":235,"abstract":236,"tags":239},[],[237,238,50],"机器学习","machine learning",[28],{"code":164,"score":109,"supported":47,"title":241,"abstract":242,"tags":243},[],[167,168],[],{"code":78,"score":22,"supported":14,"title":245,"abstract":246,"tags":247},[],[],[27],[249,250],"AI 智能灌溉 成本效益","AgEcon Search 智能灌溉","AI智能灌溉成本效益-3355","10.22004\u002Fag.econ.412813",{"doi":252,"openalex_id":254,"authors":255,"venue":204,"cited_by_count":86,"oa_url":201,"card":268,"direction":103,"ingested_from":106},"W7214115789",[256,258,260,262,264,266],{"name":257,"orcid":9},"Venkata Suman Jami",{"name":259,"orcid":9},"Purushotham Prasad Kalisetti",{"name":261,"orcid":9},"Sampath Dakshina Murthy A.",{"name":263,"orcid":9},"Gurunadha R.",{"name":265,"orcid":9},"Hema Mamidipaka",{"name":267,"orcid":9},"Gurrapu Omprakash",{"tldr":269,"method":270,"finding":271,"direction":103,"opportunity":272},"通过成本效益分析评估AI智能灌溉系统的经济与环境影响。","文献综述结合灌溉农户调查数据，进行成本效益分析。","AI智能灌溉在水资源紧张地区效益显著，提升利润并促进环保。","可针对不同气候土壤条件，量化AI灌溉的长期采纳障碍与推广机制。","2026-09-24T23:30:10.558578Z",{"id":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":9,"source_name":280,"source_url":277,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":283,"sources":285,"tags":287,"primary_topic":291,"secondary_topics":297,"classification":299,"search_phrases":316,"slug":319,"view_count":86,"doi":320,"paper":321,"created_at":335},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":124,"substance":18,"depth":122,"authority":17,"freshness":13,"relevant":22,"comment":284},"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。",[286],{"name":280,"url":277},[27,28,288,289,290],"小农户","植物病害识别","可解释性",{"code":292,"slug":293,"name":294,"path":295,"parent_code":296},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[298],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":300},{"candidates":301,"agricultural_evidence":47},[302,307,312],{"code":292,"score":17,"supported":47,"title":303,"abstract":305,"tags":306},[304],"smallholder",[304],[288],{"code":33,"score":13,"supported":47,"title":308,"abstract":310,"tags":311},[309],"computer vision",[],[28,289],{"code":78,"score":22,"supported":14,"title":313,"abstract":314,"tags":315},[],[],[27],[317,318],"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":320,"openalex_id":322,"authors":323,"venue":280,"cited_by_count":86,"oa_url":277,"card":330,"direction":105,"ingested_from":106},"W7223137323",[324,326,328],{"name":325,"orcid":9},"Akshay Ramgoolam",{"name":327,"orcid":9},"Priya Bundhoo Appadoo",{"name":329,"orcid":9},"Jean-Noël LEspérance",{"tldr":331,"method":332,"finding":333,"direction":105,"opportunity":334},"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":337,"title":338,"url":339,"summary":340,"summary_zh":341,"content":9,"source_name":280,"source_url":339,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":342,"sources":345,"tags":347,"primary_topic":351,"secondary_topics":352,"classification":354,"search_phrases":373,"slug":376,"view_count":86,"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":124,"substance":343,"depth":122,"authority":17,"freshness":21,"relevant":22,"comment":344},22,"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。",[346],{"name":280,"url":339},[27,28,348,349,350],"灌溉决策","安全保证","试验设计",{"code":73,"slug":132,"name":133,"path":134,"parent_code":135},[353],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":355},{"candidates":356,"agricultural_evidence":47},[357,361,365,369],{"code":73,"score":150,"supported":47,"title":358,"abstract":359,"tags":360},[132],[145,132],[348],{"code":33,"score":17,"supported":47,"title":362,"abstract":363,"tags":364},[50],[51],[28],{"code":164,"score":109,"supported":47,"title":366,"abstract":367,"tags":368},[],[167,168],[],{"code":78,"score":22,"supported":14,"title":370,"abstract":371,"tags":372},[],[],[27],[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":280,"cited_by_count":86,"oa_url":339,"card":385,"direction":105,"ingested_from":106},"W7223131205",[381,383],{"name":382,"orcid":9},"Nassima Benkhelifa",{"name":384,"orcid":9},"Yacine Aït Ahmed",{"tldr":386,"method":387,"finding":388,"direction":105,"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":9,"source_name":280,"source_url":394,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":397,"score_detail":398,"sources":400,"tags":402,"primary_topic":405,"secondary_topics":406,"classification":408,"search_phrases":423,"slug":426,"view_count":86,"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":124,"substance":343,"depth":122,"authority":17,"freshness":13,"relevant":22,"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":280,"url":394},[27,28,288,403,404],"作物病害识别","模型审计",{"code":292,"slug":293,"name":294,"path":295,"parent_code":296},[407],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":409},{"candidates":410,"agricultural_evidence":47},[411,415,419],{"code":292,"score":150,"supported":47,"title":412,"abstract":413,"tags":414},[304],[288,304],[288],{"code":33,"score":13,"supported":47,"title":416,"abstract":417,"tags":418},[309],[],[403,28],{"code":78,"score":22,"supported":14,"title":420,"abstract":421,"tags":422},[],[],[27],[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":280,"cited_by_count":86,"oa_url":394,"card":437,"direction":105,"ingested_from":106},"W7223088030",[431,433,435],{"name":432,"orcid":9},"Abdi-Basid Idriss Farah",{"name":434,"orcid":9},"Amina Abdillahi Guedi",{"name":436,"orcid":9},"Moussa Omar Youssouf",{"tldr":438,"method":439,"finding":440,"direction":105,"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",{"id":444,"title":445,"url":446,"summary":447,"summary_zh":448,"content":9,"source_name":280,"source_url":446,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":449,"score_detail":450,"sources":452,"tags":454,"primary_topic":457,"secondary_topics":458,"classification":459,"search_phrases":477,"slug":480,"view_count":86,"doi":481,"paper":482,"created_at":492},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":124,"substance":122,"depth":19,"authority":21,"freshness":13,"relevant":22,"comment":451},"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。",[453],{"name":280,"url":446},[27,28,455,456],"精准施药","病虫害监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":460},{"candidates":461,"agricultural_evidence":47},[462,466,472],{"code":33,"score":21,"supported":47,"title":463,"abstract":464,"tags":465},[50],[],[28],{"code":78,"score":46,"supported":47,"title":467,"abstract":468,"tags":471},[],[469,470],"精准农业","precision agriculture",[27],{"code":473,"score":22,"supported":14,"title":474,"abstract":475,"tags":476},"F4",[],[],[455],[478,479],"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":481,"openalex_id":483,"authors":484,"venue":280,"cited_by_count":86,"oa_url":446,"card":487,"direction":105,"ingested_from":106},"W7223116087",[485],{"name":486,"orcid":9},"Achieng' Atim Okello",{"tldr":488,"method":489,"finding":490,"direction":105,"opportunity":491},"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"]