[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1413":3,"related-1413":113},{"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":9,"secondary_topics":30,"classification":31,"search_phrases":61,"slug":64,"view_count":55,"doi":65,"paper":66,"created_at":112},1413,"Oil Palm Detection from High Resolution Remote Sensing Imagery with Improved YOLO Deep Learning Frameworks","https:\u002F\u002Fdoi.org\u002F10.4038\u002Fjas.v21i3.11793","Purpose: Most existing oil palm detection studies rely on standard You Only Look Once (YOLO) models without architectural modifications, limiting their detection performance. This study aims to improve the YOLO11 model for oil palm detection by integrating various attention mechanisms.Research Method: A total of 53,113 annotations of WorldView-2 and UAV datasets were used for training (80%), validation (10%), and testing (10%). An external validation dataset was included to evaluate model generalizability to different tree crown sizes and spatial characteristics (young oil palm, mature oil palm, mixed land cover). To improve the YOLO11 model, attention modules such as Coordinate Attention (CA), Efficient Channel Attention (ECA), and Convolutional Block Attention Module (CBAM) were integrated into the neck component. Model evaluation was conducted in terms of accuracy assessment and processing times.Findings and Values: For the primary dataset, YOLO11-CBAM achieved the highest mAP50-95 for validation (0.605) and testing (0.611). For the external validation dataset, YOLO11-CBAM also achieved the highest Recall and F1-score for both the young oil palm region (Recall: 0.988, F1-score: 0.992) and the mixed land cover region (Recall: 0.924, F1-score: 0.953). However, YOLO11-ECA achieved the highest accuracy across all metrics for the mature oil palm region. This study demonstrates that adding attention modules to the YOLO11 architecture improves detection accuracy and generalization despite the slightly increased inference time. The attention-enhanced models outperformed the baseline model and benchmark detectors (Faster R-CNN, RetinaNet) in oil palm detection across different environmental conditions.","目的：现有大多数油棕检测研究依赖于标准YOLO（You Only Look Once）模型，未进行架构修改，限制了其检测性能。本研究旨在通过集成多种注意力机制改进YOLO11模型，以提升油棕检测效果。研究方法：共使用53，113个WorldView-2和无人机数据集的标注，分别用于训练（80%）、验证（10%）和测试（10%）。另纳入外部验证数据集，以评估模型对不同树冠大小和空间特征（幼龄油棕、成熟油棕、混合土地覆盖）的泛化能力。为改进YOLO11模型，在颈部组件中集成了坐标注意力（Coordinate Attention，CA）、高效通道注意力（Efficient Channel Attention，ECA）和卷积块注意力模块（Convolutional Block Attention Module，CBAM）等注意力模块。模型评估涵盖精度评估和处理时间两方面。研究发现与价值：对于主要数据集，YOLO11-CBAM在验证集（0.605）和测试集（0.611）上取得了最高的mAP50-95值。对于外部验证数据集，YOLO11-CBAM在幼龄油棕区域（召回率：0.988，F1分数：0.992）和混合土地覆盖区域（召回率：0.924，F1分数：0.953）均取得了最高的召回率和F1分数。然而，YOLO11-ECA在成熟油棕区域的所有指标上均取得了最高精度。本研究表明，尽管推理时间略有增加，但在YOLO11架构中添加注意力模块可提高检测精度和泛化能力。在不同环境条件下，注意力增强模型在油棕检测中的表现均优于基线模型和基准检测器（Faster R-CNN、RetinaNet）。",null,"Journal of Agricultural Sciences – Sri Lanka","2026-09-01T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,12,7,1,"改进YOLO模型用于油棕检测，方法新颖且数据量大，对精准农业有参考价值。",[24],{"name":10,"url":6},[26,27,28,29],"农业人工智能","目标检测","遥感","油棕",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":35},"needs_review","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":14,"reason":60},[37,46,53],{"code":38,"score":39,"supported":40,"title":41,"abstract":44,"tags":45},"I2",21,true,[42,43],"deep learning","YOLO",[43],[26,27],{"code":47,"score":48,"supported":40,"title":49,"abstract":51,"tags":52},"I3",9,[50],"remote sensing",[],[28],{"code":54,"score":55,"supported":40,"title":56,"abstract":57,"tags":59},"I7",3,[],[58],"研究方法",[],"农业相关性需要复核",[62,63],"农业人工智能 目标检测 油棕 遥感","农业人工智能 目标检测","农业人工智能目标检测油棕遥感-1413","10.4038\u002Fjas.v21i3.11793",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":102,"oa_url":103,"card":104,"direction":110,"ingested_from":111},"W7204970559",[69,72,75,78,81,84,87,90,93,96,99],{"name":70,"orcid":71},"F. A. A. Marzuki","https:\u002F\u002Forcid.org\u002F0009-0006-3157-9248",{"name":73,"orcid":74},"Helmi Zulhaidi Mohd Shafri","https:\u002F\u002Forcid.org\u002F0000-0002-8669-874X",{"name":76,"orcid":77},"Siti Nur Aliaa Roslan","https:\u002F\u002Forcid.org\u002F0000-0002-9725-4378",{"name":79,"orcid":80},"M M A Al-Habshi","https:\u002F\u002Forcid.org\u002F0000-0002-1214-0858",{"name":82,"orcid":83},"N. S. N. Shaharum","https:\u002F\u002Forcid.org\u002F0000-0001-6769-6100",{"name":85,"orcid":86},"Yuhao Ang","https:\u002F\u002Forcid.org\u002F0000-0002-3014-3024",{"name":88,"orcid":89},"Yang Ping Lee","https:\u002F\u002Forcid.org\u002F0000-0002-2750-6701",{"name":91,"orcid":92},"Shahrul Azman Bakar","https:\u002F\u002Forcid.org\u002F0000-0002-2800-7779",{"name":94,"orcid":95},"Haryati Abidin","https:\u002F\u002Forcid.org\u002F0000-0002-9909-9746",{"name":97,"orcid":98},"H. S. Lim","https:\u002F\u002Forcid.org\u002F0000-0002-4835-8015",{"name":100,"orcid":101},"Rosni Abdullah","https:\u002F\u002Forcid.org\u002F0000-0002-3061-5837",0,"https:\u002F\u002Fjas.sljol.info\u002Farticles\u002F11793\u002Ffiles\u002F6a96555668f6e.pdf",{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"改进YOLO11模型，集成注意力机制提升油棕树遥感检测精度与泛化能力。","在YOLO11颈部集成CA、ECA、CBAM注意力模块，使用WorldView-","YOLO11-CBAM在多数数据集上精度最高，YOLO11-ECA在成熟油棕区最优，均优于基线。","农业遥感与作物表型","可探索注意力机制在轻量化模型中的部署，或针对不同树龄\u002F混合地类优化注意力模块选择。","智慧农业 \u002F 农业物联网","openalex","2026-09-02T23:30:13.762911Z",{"total":114,"page":21,"page_size":114,"items":115},6,[116,190,252,310,370,417],{"id":117,"title":118,"url":119,"summary":120,"summary_zh":121,"content":9,"source_name":122,"source_url":119,"published_at":123,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":124,"score_detail":125,"sources":129,"tags":131,"primary_topic":133,"secondary_topics":138,"classification":139,"search_phrases":160,"slug":163,"view_count":102,"doi":164,"paper":165,"created_at":189},5393,"IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr251214006i","CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.","卷积神经网络（CNNs）已发展成为现代计算机视觉系统的核心骨干，在多个应用领域中展现出卓越的目标检测与分类性能。然而，人工设计合适的CNN架构并相应地选择最优超参数集仍然是繁琐且耗时的过程。本综述旨在全面回顾遗传算法、粒子群优化及其他群体智能方法等元启发式优化算法如何嵌入基于CNN的流程中以获得更优的检测与分类结果。我们汇集了自动化架构搜索、超参数调优、模型压缩和集成学习方面的最新进展。通过系统梳理在医学影像、农业、车辆识别和遥感领域的应用，我们揭示了混合优化方法如何以计算效率持续实现更优的精度。优化后的CNN模型在多数情况下远超其基线版本，尤其在健康诊断领域，若干精细调优的架构达到了超过99%的准确率。本综述为将在基于深度学习的计算机视觉系统中应用元启发式优化的从业者和研究者，提供了关于方法学进展、实施实践和新兴研究方向的结构化且更新的概述。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",61,{"impact":126,"substance":17,"depth":127,"authority":19,"freshness":126,"relevant":21,"comment":128},8,15,"综述系统梳理元启发式优化在CNN视觉任务中的嵌入方法，含农业应用，但属通用方法综述，非农业专属突破。",[130],{"name":122,"url":119},[132,26,27,28],"智慧农业",{"code":38,"slug":134,"name":135,"path":136,"parent_code":137},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":140,"locked":14,"version":33,"method":34,"evidence":141},"classified",{"candidates":142,"agricultural_evidence":40},[143,151,155],{"code":38,"score":144,"supported":40,"title":145,"abstract":146,"tags":150},11,[],[27,147,148,42,149],"深度学习","计算机视觉","computer vision",[26,27],{"code":47,"score":20,"supported":40,"title":152,"abstract":153,"tags":154},[],[28,50],[28],{"code":156,"score":21,"supported":14,"title":157,"abstract":158,"tags":159},"I1",[],[],[132],[161,162],"元启发式优化 卷积神经网络","CNN 目标检测","元启发式优化卷积神经网络-5393","10.22190\u002Ffuacr251214006i",{"doi":164,"openalex_id":166,"authors":167,"venue":122,"cited_by_count":102,"oa_url":119,"card":183,"direction":108,"ingested_from":111},"W7222920697",[168,171,174,177,180],{"name":169,"orcid":170},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":172,"orcid":173},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":175,"orcid":176},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":178,"orcid":179},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":181,"orcid":182},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":184,"method":185,"finding":186,"direction":187,"opportunity":188},"综述元启发式算法嵌入CNN流程以优化目标检测与分类的研究进展。","系统综述遗传算法、粒子群等群智能方法用于CNN架构搜索与超参调优。","混合优化方法在医学影像、农业等领域兼顾精度与效率，部分模型准确率超99%。","农业人工智能与决策模型","农业场景下元启发式优化CNN的架构搜索与轻量化部署仍缺乏系统基准与田间验证。","2026-10-20T23:30:19.233167Z",{"id":191,"title":192,"url":193,"summary":194,"summary_zh":195,"content":9,"source_name":196,"source_url":193,"published_at":197,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":102,"score_detail":198,"sources":200,"tags":202,"primary_topic":9,"secondary_topics":204,"classification":205,"search_phrases":227,"slug":230,"view_count":102,"doi":9,"paper":231,"created_at":251},4220,"Системи на основі YOLO для виявлення вибухонебезпечних залишків війни: огляд для гуманітарного розмінування","https:\u002F\u002Fais.khpi.edu.ua\u002Farticle\u002Fview\u002F372728","Relevance. Humanitarian demining remains a critical safety challenge because explosive remnants of war, landmines, and unexploded ordnance continue to endanger civilians and hinder post-conflict recovery. In this context, artificial intelligence and computer vision are increasingly used to support hazardous-object detection in UAVs-based survey operations. The purpose of this paper is to synthesize contemporary approaches to the detection of landmines, unexploded ordnance, and other explosive remnants of war, and to define the role of YOLO models in an integrated technological pipeline for surveying hazardous areas. The object of the review is technological solutions for detecting hazardous objects using UAVs, sensor systems, geoinformation technologies, and YOLO-family models. The subject of the paper is the application of YOLO-based systems in integrated pipelines for localizing potential explosive objects from visual and spectral data. Research results. The review shows that modern approaches combine ground-penetrating radar, magnetometry, thermal sensing, multispectral imaging, hyperspectral imaging, UAV-based inspection, GIS platforms, and edge\u002Fcloud architectures. YOLO demonstrates strong potential for rapid localization of visually or spectrally expressed indicators of hazardous objects, especially when combined with other sensing modalities. Conclusions. At the same time, YOLO cannot serve as the sole basis for declaring an area safe. Its use is constrained by small target size, camouflage, domain shift, limited annotated datasets, and the high cost of false negatives. Therefore, YOLO-based detection should be treated as one component of a multisensor, human-supervised decision-support system.","相关性。人道主义排雷仍然是一项关键的安全挑战，因为战争遗留爆炸物、地雷和未爆弹药继续危及平民并阻碍冲突后恢复。在此背景下，人工智能和计算机视觉越来越多地被用于支持基于无人机（UAV）的勘察作业中的危险物体检测。本文旨在综合当前对地雷、未爆弹药和其他战争遗留爆炸物的检测方法，并明确YOLO模型在危险区域勘察集成技术流程中的作用。综述的对象是利用无人机、传感器系统、地理信息技术和YOLO系列模型检测危险物体的技术解决方案。论文的主题是基于YOLO的系统在集成流程中的应用，用于从视觉和光谱数据中定位潜在爆炸物体。研究结果。综述表明，现代方法结合了探地雷达、磁力测量、热传感、多光谱成像、高光谱成像、基于无人机的检查、GIS平台以及边缘\u002F云架构。YOLO在快速定位视觉或光谱上可表现出的危险物体指标方面展现出强大潜力，尤其是与其他传感模态结合使用时。结论。与此同时，YOLO不能作为宣布某一区域安全的唯一依据。其使用受到小目标尺寸、伪装、域偏移、标注数据集有限以及假阴性高成本的制约。因此，基于YOLO的检测应被视为多传感器、人工监督决策支持系统的一个组成部分。","The Scientific Issues of Ternopil Volodymyr Hnatiuk National Pedagogical University Series pedagogy","2026-10-02T00:00:00Z",{"impact":102,"substance":102,"depth":102,"authority":102,"freshness":102,"relevant":102,"comment":199},"主题为人道主义排雷中的YOLO目标检测综述，属军事\u002F人道安全领域，与三农及农业信息化无直接关联，不予入选。",[201],{"name":196,"url":193},[203,26,27,28],"无人机",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":206},{"candidates":207,"agricultural_evidence":14,"reason":60},[208,214,220],{"code":38,"score":209,"supported":40,"title":210,"abstract":211,"tags":213},19,[43],[148,212,149,43],"artificial intelligence",[26,27],{"code":47,"score":20,"supported":40,"title":215,"abstract":216,"tags":219},[],[217,218],"multispectral","hyperspectral",[28],{"code":221,"score":114,"supported":40,"title":222,"abstract":223,"tags":226},"I4",[],[224,225],"地理信息","GIS",[],[228,229],"YOLO 排雷 无人机","人道主义排雷 遥感","YOLO排雷无人机-4220",{"doi":9,"openalex_id":232,"authors":233,"venue":196,"cited_by_count":102,"oa_url":193,"card":246,"direction":110,"ingested_from":111},"W7218146160",[234,236,239,241,244],{"name":235,"orcid":9},"Andrii Podorozhniak",{"name":237,"orcid":238},"Денис Левченко","https:\u002F\u002Forcid.org\u002F0009-0005-4102-6236",{"name":240,"orcid":9},"Nataliia Liubchenko",{"name":242,"orcid":243},"Іслам Ісламов","https:\u002F\u002Forcid.org\u002F0000-0001-8645-0640",{"name":245,"orcid":9},"Oleksandr Skorlupin",{"tldr":247,"method":248,"finding":249,"direction":108,"opportunity":250},"综述YOLO模型在无人机人道排雷中检测战争爆炸残留物的应用与局限。","综述探地雷达、磁力、热成像、多\u002F高光谱、无人机、GIS与YOLO集成方案。","YOLO可快速定位危险目标，但受小目标、伪装、域偏移、数据少和高漏检代价限制，不能单独判定区域安全。","可探索多源遥感与YOLO融合的轻量边缘检测，并构建农业场景下小目标、域偏移的鲁棒性评估基准。","2026-10-05T23:30:12.187482Z",{"id":253,"title":254,"url":255,"summary":256,"summary_zh":257,"content":9,"source_name":258,"source_url":255,"published_at":259,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":260,"score_detail":261,"sources":266,"tags":268,"primary_topic":270,"secondary_topics":274,"classification":275,"search_phrases":287,"slug":290,"view_count":48,"doi":291,"paper":292,"created_at":309},3503,"Adversarial Patch and Camouflage Attacks on Aerial Object Detection: A Geometry-Aware Review","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26196057","Uncrewed aerial vehicles increasingly rely on on-board deep object detectors for applications such as surveillance, delivery, agriculture, and traffic monitoring. The vulnerability of these detectors to adversarial patches has therefore become a practical safety concern. Research on adversarial patch and camouflage attacks against aerial object detection has expanded rapidly, yet existing reviews consider aerial systems only as one application domain among many and do not examine the unique geometric conditions of aerial imagery. This review surveys adversarial patch and camouflage attacks, together with the corresponding defense mechanisms, for aerial, UAV, and remote sensing object detection. The literature is organized using a taxonomy based on two dimensions: the physical medium of the perturbation and the application domain it targets. Existing methods are then compared with respect to physical robustness, evaluation datasets and detectors, threat models, and their treatment of viewpoint variation. A recurring observation across the literature is that viewpoint variation is represented primarily through object scale, while explicit modeling of viewing geometry remains limited. This trend is closely linked to the characteristics of the aerial datasets used for evaluation, which typically provide realistic imagery but limited geometric information. Consequently, questions concerning viewpoint-dependent placement, degradation, and naturalness remain only partially explored. The review concludes by identifying the major research gaps, future directions, and deployment challenges that are likely to shape the next generation of aerial adversarial attack and defense research.","无人驾驶飞行器（UAV）在监视、配送、农业和交通监测等应用中日益依赖机载深度目标检测器。因此，这些检测器对对抗性补丁的脆弱性已成为一个实际的安全问题。针对空中目标检测的对抗性补丁与伪装攻击研究迅速扩展，然而现有综述仅将空中系统视为众多应用领域之一，并未考察航空影像独特的几何条件。本综述考察了针对空中、无人机及遥感目标检测的对抗性补丁与伪装攻击以及相应的防御机制。文献按照基于两个维度的分类体系进行组织：扰动的物理介质及其所针对的应用领域。随后，现有方法在物理鲁棒性、评估数据集与检测器、威胁模型以及其对视角变化的处理方面进行了比较。文献中反复出现的一个观察是，视角变化主要通过目标尺度来表示，而对观察几何的显式建模仍然有限。这一趋势与用于评估的航空数据集的特征密切相关，这些数据集通常提供真实影像但几何信息有限。因此，关于视角依赖的放置、退化及自然性的问题仅得到部分探讨。本综述最后指出了可能塑造下一代空中对抗攻击与防御研究的主要研究空白、未来方向及部署挑战。","Sensors","2026-09-24T00:00:00Z",67,{"impact":126,"substance":262,"depth":263,"authority":264,"freshness":48,"relevant":21,"comment":265},20,17,13,"系统梳理航空与无人机目标检测的对抗补丁与伪装攻击及防御，指出视角几何建模不足的研究空白，对农业遥感与无人机应用安全有参考价值。",[267],{"name":258,"url":255},[203,26,27,28,269],"对抗攻击",{"code":47,"slug":271,"name":272,"path":273,"parent_code":137},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[],{"status":140,"locked":14,"version":33,"method":34,"evidence":276},{"candidates":277,"agricultural_evidence":40},[278,282],{"code":47,"score":20,"supported":40,"title":279,"abstract":280,"tags":281},[],[28,50],[28],{"code":38,"score":283,"supported":40,"title":284,"abstract":285,"tags":286},5,[],[27],[26,27],[288,289],"无人机 对抗补丁 目标检测","航空图像 对抗攻击","无人机对抗补丁目标检测-3503","10.3390\u002Fs26196057",{"doi":291,"openalex_id":293,"authors":294,"venue":258,"cited_by_count":102,"oa_url":255,"card":304,"direction":108,"ingested_from":111},"W7214217753",[295,298,301],{"name":296,"orcid":297},"Sandesh Shrestha","https:\u002F\u002Forcid.org\u002F0000-0001-5298-4468",{"name":299,"orcid":300},"K. T. Y. Mahima","https:\u002F\u002Forcid.org\u002F0000-0003-4975-9408",{"name":302,"orcid":303},"Asanka G. Perera","https:\u002F\u002Forcid.org\u002F0000-0003-4021-3943",{"tldr":305,"method":306,"finding":307,"direction":108,"opportunity":308},"综述无人机与遥感目标检测中的对抗补丁与伪装攻击及防御，并提出几何感知分类体系。","基于扰动介质与应用领域的分类法，比较物理鲁棒性、数据集、威胁模型与视角处理。","现有研究多以目标尺度代替视角变化，缺乏显式视角几何建模，因数据集几何信息有限。","可构建含视角几何标注的农业航拍数据集，研究视角依赖的对抗补丁放置与自然性防御。","2026-09-25T23:30:31.219576Z",{"id":311,"title":312,"url":313,"summary":314,"summary_zh":315,"content":9,"source_name":316,"source_url":313,"published_at":317,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":318,"score_detail":319,"sources":321,"tags":323,"primary_topic":326,"secondary_topics":327,"classification":328,"search_phrases":354,"slug":357,"view_count":102,"doi":358,"paper":359,"created_at":369},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。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",74,{"impact":19,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":21,"comment":320},"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。",[322],{"name":316,"url":313},[132,26,324,28,325],"粮食安全","气候分析",{"code":38,"slug":134,"name":135,"path":136,"parent_code":137},[],{"status":140,"locked":14,"version":33,"method":34,"evidence":329},{"candidates":330,"agricultural_evidence":40},[331,335,341,346,350],{"code":38,"score":48,"supported":40,"title":332,"abstract":333,"tags":334},[212],[],[26],{"code":336,"score":55,"supported":40,"title":337,"abstract":338,"tags":340},"I5",[],[339],"农业传感",[],{"code":342,"score":21,"supported":14,"title":343,"abstract":344,"tags":345},"A8",[],[],[324],{"code":156,"score":21,"supported":14,"title":347,"abstract":348,"tags":349},[],[],[132],{"code":47,"score":21,"supported":14,"title":351,"abstract":352,"tags":353},[],[],[28],[355,356],"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":358,"openalex_id":360,"authors":361,"venue":316,"cited_by_count":102,"oa_url":313,"card":364,"direction":187,"ingested_from":111},"W7223111766",[362],{"name":363,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":365,"method":366,"finding":367,"direction":108,"opportunity":368},"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。","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",{"id":371,"title":372,"url":373,"summary":374,"summary_zh":375,"content":9,"source_name":316,"source_url":373,"published_at":317,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":260,"score_detail":376,"sources":378,"tags":380,"primary_topic":383,"secondary_topics":384,"classification":386,"search_phrases":401,"slug":404,"view_count":102,"doi":405,"paper":406,"created_at":416},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。",{"impact":126,"substance":262,"depth":263,"authority":19,"freshness":13,"relevant":21,"comment":377},"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[379],{"name":316,"url":373},[132,26,381,28,382],"产量预测","可解释性",{"code":38,"slug":134,"name":135,"path":136,"parent_code":137},[385],{"code":47,"slug":271,"name":272,"path":273,"parent_code":137},{"status":140,"locked":14,"version":33,"method":34,"evidence":387},{"candidates":388,"agricultural_evidence":40},[389,393,397],{"code":38,"score":19,"supported":40,"title":390,"abstract":391,"tags":392},[149],[148],[26],{"code":47,"score":126,"supported":40,"title":394,"abstract":395,"tags":396},[],[28,50],[381,28],{"code":156,"score":21,"supported":14,"title":398,"abstract":399,"tags":400},[],[],[132],[402,403],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":405,"openalex_id":407,"authors":408,"venue":316,"cited_by_count":102,"oa_url":373,"card":411,"direction":108,"ingested_from":111},"W7223114002",[409],{"name":410,"orcid":9},"Kadiatou Barry",{"tldr":412,"method":413,"finding":414,"direction":108,"opportunity":415},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":418,"title":419,"url":420,"summary":421,"summary_zh":422,"content":9,"source_name":423,"source_url":420,"published_at":317,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":424,"score_detail":425,"sources":427,"tags":429,"primary_topic":432,"secondary_topics":438,"classification":444,"search_phrases":502,"slug":505,"view_count":102,"doi":506,"paper":507,"created_at":530},5564,"Dynamic thermal imaging for crop water stress detection across phenological stages: Enhancing irrigation scheduling precision","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.17728","Thermal remote sensing and derived indices such as the crop water stress index (CWSI) can assess crop water status and support precision irrigation. However, most operational and artificial intelligence (AI)-based approaches rely on fixed, season-long thresholds to interpret canopy–air temperature differences and often overlook the influence of crop phenology. This review synthesises evidence from grapevine, wheat, maize, potato and several other crops on how developmental stage affects the non-water-stressed baseline (NWSB), CWSI thresholds and irrigation-scheduling algorithms. It covers CWSI theory and estimation practices; crop-specific, phenology-dependent behaviour of baselines and thresholds; a comparison of threshold-based, machine learning, Internet of Things (IoT), digital twin and Food and Agriculture Organization (FAO)-56 approaches with respect to crop phenology; and a conceptual framework for phenology-aware scheduling. Across the reviewed crops, baseline behaviour generally varied systematically across the growing season, the relationship between CWSI and crop water status generally strengthened after canopy closure and CWSI measured during reproductive stages was generally most closely related to yield. A quantitative audit of 56 AI-, thermal-imaging-, or CWSI-based studies found that 78.6 % either did not explicitly incorporate crop phenology or relied on day of year as a temporal proxy, whereas only 5.4 % explicitly encoded phenological stage. The proposed framework considers phenology explicitly in baseline estimation, threshold setting and data fusion or machine learning for irrigation scheduling; the framework will require multi-year, multi-site field validation before operational use. Future research should prioritise standardised phenology definitions and long-term, multi-location studies to establish and validate stage-specific parameters.","热红外遥感及其衍生的作物水分胁迫指数（crop water stress index, CWSI）等指标可评估作物水分状况并支持精准灌溉。然而，大多数业务化方法和基于人工智能（artificial intelligence, AI）的方法依赖固定的全生育期阈值来解释冠层—空气温差，且往往忽视作物物候的影响。本文综述了葡萄、小麦、玉米、马铃薯及其他若干作物在发育阶段如何影响非水分胁迫基线（non-water-stressed baseline, NWSB）、CWSI阈值和灌溉调度算法的相关证据。综述内容涵盖CWSI理论与估算实践；基线和阈值的作物特异性、物候依赖性行为；基于阈值、机器学习、物联网（Internet of Things, IoT）、数字孪生及联合国粮农组织（Food and Agriculture Organization, FAO）-56等方法在作物物候方面的比较；以及物候感知调度的概念框架。在所综述的作物中，基线行为在整个生长季通常呈系统性变化，CWSI与作物水分状况之间的关系在冠层封垄后总体增强，且在生殖阶段测得的CWSI与产量的关系总体最为密切。对56项基于AI、热成像或CWSI的研究进行的定量审查发现，78.6%的研究要么未明确纳入作物物候，要么依赖年积日作为时间代理变量，而仅5.4%的研究明确编码了物候阶段。所提出的框架在基线估算、阈值设定以及用于灌溉调度的数据融合或机器学习中明确考虑物候；该框架在投入业务应用前尚需多年、多站点的田间验证。未来研究应优先建立标准化的物候定义，并开展长期、多地点研究以建立和验证阶段特异性参数。","Plant Science Today",79,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":48,"relevant":21,"comment":426},"系统综述热成像与CWSI在物候期感知灌溉中的应用，含56项研究量化审计，方法学价值突出，但属综述类论文，影响偏学术层面。",[428],{"name":423,"url":420},[132,26,28,430,431],"作物水分胁迫","精准灌溉",{"code":433,"slug":434,"name":435,"path":436,"parent_code":437},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[439,440],{"code":38,"slug":134,"name":135,"path":136,"parent_code":137},{"code":336,"slug":441,"name":442,"path":443,"parent_code":137},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":140,"locked":14,"version":33,"method":34,"evidence":445},{"candidates":446,"agricultural_evidence":40},[447,452,458,465,471,475,482,489,496],{"code":433,"score":127,"supported":40,"title":448,"abstract":449,"tags":451},[434],[450,434],"灌溉",[431],{"code":38,"score":13,"supported":40,"title":453,"abstract":454,"tags":457},[],[455,456,212],"机器学习","machine learning",[26],{"code":336,"score":48,"supported":40,"title":459,"abstract":460,"tags":464},[],[461,462,463],"物联网","internet of things","IoT",[],{"code":156,"score":20,"supported":40,"title":466,"abstract":467,"tags":470},[],[468,469],"数字孪生","digital twin",[132],{"code":47,"score":20,"supported":40,"title":472,"abstract":473,"tags":474},[],[28,50],[28],{"code":476,"score":114,"supported":40,"title":477,"abstract":478,"tags":481},"A2",[],[479,480],"小麦","wheat",[],{"code":483,"score":114,"supported":40,"title":484,"abstract":485,"tags":488},"A3",[],[486,487],"玉米","maize",[],{"code":490,"score":114,"supported":40,"title":491,"abstract":492,"tags":495},"A5",[],[493,494],"马铃薯","potato",[],{"code":497,"score":55,"supported":40,"title":498,"abstract":499,"tags":501},"B2",[],[500],"葡萄",[],[503,504],"热成像 作物水分胁迫","CWSI 灌溉调度","热成像作物水分胁迫-5564","10.14719\u002Fpst.17728",{"doi":506,"openalex_id":508,"authors":509,"venue":423,"cited_by_count":102,"oa_url":420,"card":525,"direction":110,"ingested_from":111},"W7223088921",[510,513,516,519,522],{"name":511,"orcid":512},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":514,"orcid":515},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":517,"orcid":518},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":520,"orcid":521},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":523,"orcid":524},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":526,"method":527,"finding":528,"direction":108,"opportunity":529},"综述物候期对热成像CWSI阈值的影响，提出物候感知灌溉调度框架。","综述葡萄、小麦、玉米等作物的热遥感CWSI研究，并审计56项AI\u002F热成像研究。","78.6%研究未显式纳入物候，仅5.4%编码物候期；CWSI与产量在生殖期关联最强。","可开展多站点多年物候期特异性CWSI阈值标定与标准化物候定义研究。","2026-10-22T11:20:24.526683Z"]