[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2790":3,"related-2790":99},{"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":63,"slug":66,"view_count":67,"doi":68,"paper":69,"created_at":98},2790,"High-resolution land cover mapping from coarse labels via a noisy label learning-guided cross-scale framework","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15481603.2026.2726002","High-resolution remote sensing images (HRSIs) provide essential data support for land cover mapping, where deep learning has shown great promise. However, deep learning-based methods rely on abundant high-quality annotations, while low-resolution coarse labels are difficult to use directly in HRSIs training. In this paper, a novel noisy label learning-guided cross-scale framework (NL-CSF) is proposed, which is designed to achieve high-resolution land cover mapping from coarse labels. First, a spectral-based label mask filtering strategy is developed to preliminarily optimize coarse labels. Then, an adaptive noise evaluation scheme is introduced that assigns loss weights based on the noise differences between image and label patches in the training set. Finally, we design a cross-scale transfer Transformer (CSTT) model based on the vision Transformer (ViT) architecture, and the training process is guided by a noise-weighted loss function. Two cross-scale datasets are utilized to evaluate the performance of NL-CSF in multiple spatial scale differences (10 m to 3 m, 3 m to 0.5 m, and 10 m to 0.5 m). Experimental results demonstrate that NL-CSF improves overall accuracy (OA) by at least 7%, 6%, and 4% across the three cross-scale tasks in the first dataset, and by at least 2%, 9%, and 4% in the second dataset, respectively, compared with existing methods. Furthermore, the proposed framework is applied to cross-scale mapping across Jianye District of Nanjing (urban), Sheyang County of Yancheng (agricultural), and the Yellow River Delta of Dongying (wetland), leveraging a low-resolution land cover product and high-resolution PlanetScope images to generate more precise land cover maps. These results demonstrate the effectiveness of the proposed framework in mitigating the impact of noisy coarse labels and generating reliable high-resolution land cover maps.","高分辨率遥感影像(high-resolution remote sensing images, HRSIs)为土地覆盖制图提供了重要的数据支撑，深度学习在此领域展现出巨大潜力。然而，基于深度学习的方法依赖于大量高质量标注，而低分辨率粗标签难以直接用于高分辨率遥感影像训练。本文提出了一种新的噪声标签学习引导的跨尺度框架(noisy label learning-guided cross-scale framework, NL-CSF)，旨在从粗标签实现高分辨率土地覆盖制图。首先，提出了一种基于光谱的标签掩膜过滤策略，对粗标签进行初步优化。然后，引入了一种自适应噪声评估方案，根据训练集中影像块与标签块之间的噪声差异分配损失权重。最后，基于视觉Transformer(vision Transformer, ViT)架构设计了跨尺度迁移Transformer(cross-scale transfer Transformer, CSTT)模型，并以噪声加权损失函数引导训练过程。利用两个跨尺度数据集评估NL-CSF在多种空间尺度差异(10 m至3 m、3 m至0.5 m、10 m至0.5 m)下的性能。实验结果表明，与现有方法相比，NL-CSF在第一个数据集的三个跨尺度任务中总体精度(overall accuracy, OA)分别至少提升7%、6%和4%，在第二个数据集中分别至少提升2%、9%和4%。此外，将所提框架应用于南京建邺区(城市)、盐城射阳县(农业)和东营黄河三角洲(湿地)的跨尺度制图，利用低分辨率土地覆盖产品和高分PlanetScope影像生成更精确的土地覆盖图。这些结果证明了所提框架在减轻噪声粗标签影响和生成可靠高分辨率土地覆盖图方面的有效性。",null,"GIScience & Remote Sensing","2026-09-16T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"提出噪声标签学习引导的跨尺度框架，用低分辨率粗标签生成高分辨率土地覆盖图，精度提升显著，对农业遥感监测有实用价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"农业人工智能","深度学习","遥感","土地覆盖","高分辨率制图",{"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},[44,51,58],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":50},8,true,[],[27,49],"deep learning",[26,27],{"code":52,"score":53,"supported":46,"title":54,"abstract":55,"tags":57},"I3",7,[],[28,56],"remote sensing",[28],{"code":59,"score":21,"supported":14,"title":60,"abstract":61,"tags":62},"H6",[],[],[29],[64,65],"农业人工智能 高分辨率制图 土地覆盖 深度学习","农业人工智能 高分辨率制图","农业人工智能高分辨率制图土地覆盖深度学习-2790",3,"10.1080\u002F15481603.2026.2726002",{"doi":68,"openalex_id":70,"authors":71,"venue":10,"cited_by_count":90,"oa_url":6,"card":91,"direction":95,"ingested_from":97},"W7213283296",[72,75,78,81,84,86,88],{"name":73,"orcid":74},"Xiangyu Nie","https:\u002F\u002Forcid.org\u002F0009-0001-5095-6401",{"name":76,"orcid":77},"Cong Lin","https:\u002F\u002Forcid.org\u002F0000-0001-5386-7343",{"name":79,"orcid":80},"Wei Zhang","https:\u002F\u002Forcid.org\u002F0000-0001-8162-9422",{"name":82,"orcid":83},"Hong Fang","https:\u002F\u002Forcid.org\u002F0000-0003-3707-0910",{"name":85,"orcid":9},"Zhen Dong",{"name":87,"orcid":9},"Sicong Liu",{"name":89,"orcid":9},"Zhaohui Xue",0,{"tldr":92,"method":93,"finding":94,"direction":95,"opportunity":96},"提出噪声标签学习引导的跨尺度框架，用低分辨率粗标签生成高分辨率土地覆盖图。","谱掩膜过滤粗标签、自适应噪声评估加权损失、基于ViT的跨尺度迁移Transfor","在多个跨尺度任务上总体精度提升2%-9%，并在城市、农业、湿地场景生成更精确土地覆盖图。","农业遥感与作物表型","可探索将粗标签跨尺度学习用于作物精细分类与长时序农情监测，降低高精度标注依赖。","openalex","2026-09-17T23:30:34.952106Z",{"total":100,"page":21,"page_size":100,"items":101},6,[102,165,236,290,347,406],{"id":103,"title":104,"url":105,"summary":106,"summary_zh":107,"content":9,"source_name":108,"source_url":105,"published_at":109,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":115,"tags":117,"primary_topic":120,"secondary_topics":124,"classification":126,"search_phrases":147,"slug":150,"view_count":45,"doi":151,"paper":152,"created_at":164},3618,"Multi-Target Remote Sensing Segmentation with Cross-Scale Attention for Urban-Ecological Intelligence","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijgem.vol.12.no1.2026.pg131.154","Remote sensing image segmentation is essential to extract valuable information from satellite and aerial images to achieve significant applications such as urban planning and ecological monitoring. Yet, it is hard to accurately segment diverse and complicated features because of the constraints of conventional approaches and the requirement to process variable object sizes and complicated boundaries. This research aims to address the above difficulties through the use and assessment of advanced deep learning models specifically UNet, SegNet, and TransU-Net in multi target semantic segmentation. These networks have been applied in single-object segmentation tasks with a focus on structures and roads, while the UNet architecture was additionally utilized for multi-object segmentation comprising buildings, woods, grasslands, water bodies, and cultivated land. Using appropriate remote sensing datasets, the accuracy of the models was thoroughly evaluated using common evaluation metrics, including pixel accuracy, Intersection over Union (IoU), and F1-score. The experimental outcomes illustrate the capabilities of these deep learning methods to provide accurate identification of essential features. Notably, the maximum attainable accuracy for single-object building segmentation was 96.85%, whereas the overall accuracy for multi-object segmentation with the UNet was 84.2%. The experimental results show these deep learning algorithms can effectively separate different targets from remote sensing imagery, thus making them fundamental tools for geospatial analysis and related fields.","遥感图像分割对于从卫星和航空图像中提取有价值信息，以实现城市规划和生态监测等重要应用至关重要。然而，由于传统方法的局限以及处理可变目标尺寸和复杂边界的需要，准确分割多样且复杂的地物十分困难。本研究旨在通过使用和评估先进的深度学习模型，特别是UNet、SegNet和TransU-Net在多目标语义分割中的应用，来解决上述难题。这些网络已被应用于单目标分割任务，重点关注建筑物和道路，而UNet架构还被额外用于多目标分割，包括建筑物、林地、草地、水体和耕地。利用适当的遥感数据集，通过常用评价指标对模型的精度进行了全面评估，包括像素精度、交并比（IoU）和F1分数。实验结果表明了这些深度学习方法在准确识别关键地物方面的能力。值得注意的是，单目标建筑物分割的最高可达精度为96.85%，而使用UNet进行多目标分割的总体精度为84.2%。实验结果表明，这些深度学习算法能够有效地从遥感图像中分离出不同目标，从而使其成为地理空间分析及相关领域的基础工具。","IIARD INTERNATIONAL JOURNAL OF GEOGRAPHY AND ENVIRONMENTAL MANAGEMENT","2026-09-25T00:00:00Z",63,{"impact":112,"substance":17,"depth":113,"authority":13,"freshness":45,"relevant":21,"comment":114},12,15,"将UNet、SegNet、TransU-Net用于多目标遥感语义分割，建筑单目标精度96.85%、多目标84.2%，方法常规但结论对农业与生态遥感监测有参考价值。",[116],{"name":108,"url":105},[26,27,118,28,119],"语义分割","生态监测",{"code":52,"slug":121,"name":122,"path":123,"parent_code":36},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[125],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":127},{"candidates":128,"agricultural_evidence":46},[129,133,137,143],{"code":52,"score":113,"supported":46,"title":130,"abstract":131,"tags":132},[56],[28,56],[28],{"code":32,"score":20,"supported":46,"title":134,"abstract":135,"tags":136},[],[27,49],[26,27,118],{"code":138,"score":67,"supported":46,"title":139,"abstract":140,"tags":142},"I4",[],[141],"空间分析",[],{"code":59,"score":21,"supported":14,"title":144,"abstract":145,"tags":146},[],[],[119],[148,149],"UNet 遥感 多目标分割","TransU-Net 城市生态 遥感","UNet遥感多目标分割-3618","10.56201\u002Fijgem.vol.12.no1.2026.pg131.154",{"doi":151,"openalex_id":153,"authors":154,"venue":108,"cited_by_count":90,"oa_url":157,"card":158,"direction":163,"ingested_from":97},"W7214298981",[155],{"name":156,"orcid":9},"Chibueze Favour Aririguzo","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJGEM\u002FVOL. 12 NO. 1 2026\u002FMulti-Target Remote Sensing Segmentation 131-154.pdf",{"tldr":159,"method":160,"finding":161,"direction":95,"opportunity":162},"评估UNet、SegNet和TransU-Net在多目标遥感语义分割中的性能，用于城市与生态监测。","使用UNet、SegNet、TransU-Net模型，在遥感数据集上以像素精度、","单目标建筑分割最高精度96.85%，UNet多目标分割总体精度84.2%。","可探索跨尺度注意力机制提升多目标分割精度，并迁移至耕地与作物精细分类。","智慧农业 \u002F 农业物联网","2026-09-27T23:30:28.366758Z",{"id":166,"title":167,"url":168,"summary":169,"summary_zh":170,"content":9,"source_name":171,"source_url":168,"published_at":172,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":173,"score_detail":174,"sources":177,"tags":179,"primary_topic":182,"secondary_topics":183,"classification":185,"search_phrases":210,"slug":213,"view_count":21,"doi":214,"paper":215,"created_at":235},2942,"Deep learning-driven multisource remote sensing image fusion: Advances, challenges, and future directions","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.engappai.2026.116319","Multisource remote sensing image fusion has become an important solution to a long-standing limitation in Earth observation: individual sensors rarely provide high spatial detail, rich spectral information, reliable structural sensitivity, and frequent temporal coverage at the same time. This review examines how deep learning and artificial intelligence are being used to integrate multispectral, hyperspectral, panchromatic, optical, and synthetic aperture radar imagery for more reliable interpretation of complex ground scenes. It provides a technical synthesis of convolutional neural networks, autoencoders, generative adversarial networks, transformer architectures, diffusion models, and hybrid model driven approaches, with attention to their fusion mechanisms, reconstruction behavior, computational demand, and suitability for operational use. Applications include land cover mapping, precision agriculture, environmental monitoring, urban analysis, disaster assessment, and defense related interpretation. Rather than treating each fusion task separately, this review connects sensor heterogeneity, spatial and spectral resolution trade offs, radiometric correction, geometric correction, registration, noise reduction, and fusion level design within a single framework. The analysis indicates that convolutional models remain effective for stable local detail recovery, adversarial learning can improve visual sharpness but may introduce spectral distortion, transformer models better capture long range spatial and spectral relationships, and diffusion models offer refined reconstruction at greater computational cost. The review further identifies open challenges involving misregistration, spectral bias, limited labeled data, weak generalization across sensors, high memory requirements, and limited interpretability. Future progress should prioritize sensor aware learning, self supervised training, uncertainty aware evaluation, lightweight deployment, and application oriented benchmarks to improve reliability in operational Earth observation.","多源遥感图像融合已成为解决地球观测领域一个长期局限的重要方案：单一传感器很少能够同时提供高空间细节、丰富光谱信息、可靠的结构敏感性以及频繁的时间覆盖。本文综述了如何利用深度学习和人工智能整合多光谱、高光谱、全色、光学和合成孔径雷达（synthetic aperture radar, SAR）影像，以更可靠地解译复杂地表场景。文章对卷积神经网络、自编码器、生成对抗网络、Transformer架构、扩散模型以及混合模型驱动方法进行了技术综合，重点关注其融合机制、重建行为、计算需求以及业务化适用性。应用领域包括土地覆盖制图、精准农业、环境监测、城市分析、灾害评估和国防相关解译。本文并非将每种融合任务分开处理，而是在一个统一框架内将传感器异质性、空间与光谱分辨率权衡、辐射校正、几何校正、配准、降噪和融合层级设计联系起来。分析表明，卷积模型在稳定的局部细节恢复方面仍然有效，对抗学习可以提升视觉锐度但可能引入光谱失真，Transformer模型能更好地捕捉长程空间与光谱关系，而扩散模型以更高的计算成本提供精细重建。本文进一步指出了涉及配准误差、光谱偏差、标注数据有限、跨传感器泛化能力弱、高内存需求以及可解释性有限等开放挑战。未来的进展应优先关注传感器感知学习、自监督训练、不确定性感知评估、轻量化部署以及面向应用的基准测试，以提高业务化地球观测的可靠性。","Engineering Applications of Artificial Intelligence","2026-09-18T00:00:00Z",82,{"impact":17,"substance":18,"depth":175,"authority":19,"freshness":20,"relevant":21,"comment":176},19,"发表于核心期刊的综述，系统梳理深度学习多源遥感融合的方法、应用与挑战，对农业遥感与精准农业有直接参考价值，时效性强，值得进入每日精选。",[178],{"name":171,"url":168},[26,27,180,28,181],"精准农业","多源数据融合",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[184],{"code":52,"slug":121,"name":122,"path":123,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":186},{"candidates":187,"agricultural_evidence":46},[188,193,199,205],{"code":32,"score":175,"supported":46,"title":189,"abstract":190,"tags":192},[49],[27,49,191],"artificial intelligence",[26,27],{"code":52,"score":17,"supported":46,"title":194,"abstract":195,"tags":198},[56],[28,56,196,197],"multispectral","hyperspectral",[28],{"code":200,"score":53,"supported":46,"title":201,"abstract":202,"tags":204},"I1",[],[180,203],"precision agriculture",[180],{"code":206,"score":21,"supported":14,"title":207,"abstract":208,"tags":209},"I5",[],[],[181],[211,212],"多源遥感 图像融合 深度学习","农业人工智能 多源数据融合 深度学习 精准农业","多源遥感图像融合深度学习-2942","10.1016\u002Fj.engappai.2026.116319",{"doi":214,"openalex_id":216,"authors":217,"venue":171,"cited_by_count":90,"oa_url":168,"card":230,"direction":95,"ingested_from":97},"W7213544281",[218,221,224,227],{"name":219,"orcid":220},"Shahid Karim","https:\u002F\u002Forcid.org\u002F0000-0001-9986-5052",{"name":222,"orcid":223},"Akeel Qadir","https:\u002F\u002Forcid.org\u002F0000-0003-0358-6505",{"name":225,"orcid":226},"Asif Ali Laghari","https:\u002F\u002Forcid.org\u002F0000-0001-5831-5943",{"name":228,"orcid":229},"Irfana Bibi","https:\u002F\u002Forcid.org\u002F0000-0003-2794-504X",{"tldr":231,"method":232,"finding":233,"direction":95,"opportunity":234},"综述深度学习多源遥感图像融合方法、挑战与未来方向。","综述CNN、GAN、Transformer、扩散模型等融合机制与重建行为。","CNN擅局部细节，GAN易谱失真，Transformer长程关系强，扩散模型精度高但算力大。","面向农业的轻量、自监督、不确定性感知融合与基准数据集构建。","2026-09-19T23:30:32.767384Z",{"id":237,"title":238,"url":239,"summary":240,"summary_zh":241,"content":9,"source_name":242,"source_url":239,"published_at":243,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":244,"score_detail":245,"sources":249,"tags":251,"primary_topic":253,"secondary_topics":254,"classification":256,"search_phrases":272,"slug":275,"view_count":247,"doi":276,"paper":277,"created_at":289},1769,"Land Cover Classification using Hyperspectral Imagery: A Deep Learning Approach","https:\u002F\u002Fdoi.org\u002F10.17485\u002Fijst\u002Fv19i31.487","Objectives: This research aimed to perform proper land cover classification of the Krishnagiri and Dharmapuri districts using hyperspectral imagery. This research also attempted to determine the usefulness of deep learning models in detecting large land cover classes, such as quarry, barren, forest, built-up, and agricultural land, using hyperspectral data. Method: The analysis of the land cover patterns in the study area used hyperspectral images (HSI) taken between 2015 and 2022, which had 230 spectral bands. A total of 3000 hyperspectral images were processed, 2000 of which were utilized for training and 1000 for testing. The images were then preprocessed, segmented into superpixels using superpixel segmentation, and classified. Three deep learning models, a Convolutional Neural Network (CNN), Residual Neural Network 18 (ResNet-18), and Visual Geometry Group-16 (VGG-16), were used as classification models. Standard measures of accuracy, precision, recall, and F-score were used to evaluate the performance and effectiveness of the models. Findings: The results indicate that ResNet-18 outperformed the other models in determining land cover classes using hyperspectral images. The model has shown high classification levels among various types of land, with built-up land having an accuracy level of approximately 95.09, indicating a better ability to extract and classify features than CNN and VGG-16. Novelty: The novelty of this study lies in the combination of hyperspectral image processing with deep learning frameworks to classify regions based on land cover. The relative analysis of CNN, ResNet-18, and VGG-16 demonstrated the usefulness of residual learning networks in enhancing the classification accuracy in hyperspectral remote sensing scenarios. Keywords: Hyperspectral Image (HSI), Land Cover Classification, Deep Learning, Convolutional Neural Network (CNN), ResNet-18, VGG-16, Remote Sensing, Spectral–Spatial Analysis","目标：本研究旨在利用高光谱影像对克里希纳吉里区和达尔马普里区进行准确的土地覆盖分类，并尝试确定深度学习模型在利用高光谱数据检测大型土地覆盖类别（如采石场、荒地、森林、建成区和农业用地）方面的有效性。方法：研究区域的土地覆盖模式分析使用了2015年至2022年间获取的高光谱图像（HSI），共包含230个光谱波段。共处理了3000幅高光谱图像，其中2000幅用于训练，1000幅用于测试。图像经过预处理后，采用超像素分割方法将其分割为超像素，并进行分类。使用三种深度学习模型作为分类模型，即卷积神经网络（CNN）、残差神经网络18（ResNet-18）和视觉几何组-16（VGG-16）。采用准确率、精确率、召回率和F值等标准指标来评估模型的性能和有效性。结果：结果表明，ResNet-18在利用高光谱图像确定土地覆盖类别方面优于其他模型。该模型在各种土地类型中表现出较高的分类水平，其中建成区的准确率约为95.09，表明其在特征提取和分类能力上优于CNN和VGG-16。新颖性：本研究的创新之处在于将高光谱图像处理与深度学习框架相结合，基于土地覆盖对区域进行分类。CNN、ResNet-18和VGG-16的相对分析证明了残差学习网络在提高高光谱遥感场景分类准确性方面的有效性。关键词：高光谱图像（HSI）、土地覆盖分类、深度学习、卷积神经网络（CNN）、ResNet-18、VGG-16、遥感、光谱-空间分析","Indian Journal of Science and Technology","2026-09-05T00:00:00Z",58,{"impact":112,"substance":17,"depth":246,"authority":13,"freshness":247,"relevant":21,"comment":248},16,2,"研究比较了三种深度学习模型在高光谱影像土地分类中的表现，方法有参考价值，但时效性差，影响范围有限。",[250],{"name":242,"url":239},[26,27,28,252],"土地分类",{"code":52,"slug":121,"name":122,"path":123,"parent_code":36},[255],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":257},{"candidates":258,"agricultural_evidence":46},[259,263,267],{"code":52,"score":17,"supported":46,"title":260,"abstract":261,"tags":262},[197],[28,56,197],[28],{"code":32,"score":246,"supported":46,"title":264,"abstract":265,"tags":266},[49],[27,49],[26,27],{"code":138,"score":100,"supported":46,"title":268,"abstract":269,"tags":271},[],[141,270],"spatial analysis",[],[273,274],"农业人工智能 土地分类 深度学习 遥感","农业人工智能 土地分类","农业人工智能土地分类深度学习遥感-1769","10.17485\u002Fijst\u002Fv19i31.487",{"doi":276,"openalex_id":278,"authors":279,"venue":242,"cited_by_count":90,"oa_url":239,"card":284,"direction":95,"ingested_from":97},"W7208825957",[280,282],{"name":281,"orcid":9},"P Nithya",{"name":283,"orcid":9},"P Sudhakar",{"tldr":285,"method":286,"finding":287,"direction":95,"opportunity":288},"利用高光谱影像和深度学习模型对印度两地区进行土地覆盖分类，比较CNN、ResNet-18和VGG-1","使用2015-2022年230波段高光谱影像，超像素分割后，用CNN、ResNe","ResNet-18表现最佳，建成区分类准确率约95.09%，优于CNN和VGG-16。","可探索将ResNet-18等深度学习模型应用于高光谱影像的作物精细分类，或结合多时相数据提升农业监测精度。","2026-09-06T23:30:27.341932Z",{"id":291,"title":292,"url":293,"summary":294,"summary_zh":295,"content":9,"source_name":296,"source_url":293,"published_at":297,"category":12,"cover_url":9,"hotness":298,"is_selected":14,"score":299,"score_detail":300,"sources":303,"tags":307,"primary_topic":310,"secondary_topics":311,"classification":312,"search_phrases":327,"slug":330,"view_count":67,"doi":331,"paper":332,"created_at":346},1534,"Deep Learning Based Semantic Segmentation of Satellite Imagery for Land Cover Classification","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22251467","Land cover classification from remote sensing imagery underpins agricultural monitoring, urban planning, disaster response, and environmental assessment, and deep learning has become the dominant paradigm for extracting land cover information from satellite scenes at pixel-level granularity. This survey reviews recent advances in deep learning-based land cover classification and semantic segmentation, organizing the literature into convolutional neural network (CNN)-based encoder–decoder architectures, attention and self-attention mechanisms, transformer and hybrid CNN–Transformer architectures, and optimization-augmented and foundation-model-adapted approaches. We summarize the datasets, evaluation metrics, and comparative performance reported across the reviewed studies, and use a representative hybrid EfficientNet–Vision Transformer framework as a case study to illustrate current design trends. Persistent challenges are identified, including class imbalance for narrow structures such as roads, the computational cost of hybrid transformer-based models, limited cross-dataset generalization, and the scarcity of densely annotated data. The survey concludes by outlining promising future directions, including lightweight hybrid architectures, self-supervised and weakly supervised learning, adaptation of large vision foundation models, multi-sensor data fusion, and explainable land cover mapping.","基于遥感影像的土地覆盖分类支撑着农业监测、城市规划、灾害响应和环境评估，而深度学习已成为从卫星场景中提取像素级土地覆盖信息的主导范式。本综述回顾了基于深度学习的土地覆盖分类与语义分割的最新进展，将相关文献组织为基于卷积神经网络（CNN）的编码器-解码器架构、注意力与自注意力机制、Transformer及CNN-Transformer混合架构，以及优化增强和基础模型适配方法等类别。我们总结了所评述研究中报告的数据集、评估指标和对比性能，并以一个具有代表性的混合EfficientNet-Vision Transformer框架作为案例研究，以说明当前的设计趋势。本文指出了持续存在的挑战，包括道路等狭窄结构的类别不平衡问题、基于混合Transformer模型的计算成本、跨数据集泛化能力有限，以及密集标注数据的稀缺性。综述最后概述了有前景的未来方向，包括轻量级混合架构、自监督和弱监督学习、大型视觉基础模型的适配、多传感器数据融合以及可解释的土地覆盖制图。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-02T00:00:00Z",25,67,{"impact":112,"substance":301,"depth":17,"authority":13,"freshness":53,"relevant":21,"comment":302},20,"综述深度学习用于卫星影像土地覆盖分类，对农业监测有参考价值，但偏学术，影响有限。",[304,305],{"name":296,"url":293},{"name":296,"url":306},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22251468",[308,26,27,28,309],"智慧农业","土地覆盖分类",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":313},{"candidates":314,"agricultural_evidence":46},[315,319,323],{"code":32,"score":246,"supported":46,"title":316,"abstract":317,"tags":318},[49],[27,49],[26,27],{"code":52,"score":53,"supported":46,"title":320,"abstract":321,"tags":322},[],[28,56],[28],{"code":200,"score":21,"supported":14,"title":324,"abstract":325,"tags":326},[],[],[308],[328,329],"农业人工智能 土地覆盖分类 智慧农业 深度学习","农业人工智能 土地覆盖分类","农业人工智能土地覆盖分类智慧农业深度学习-1534","10.5281\u002Fzenodo.22251467",{"doi":331,"openalex_id":333,"authors":334,"venue":296,"cited_by_count":90,"oa_url":293,"card":341,"direction":95,"ingested_from":97},"W7206172334",[335,337,339],{"name":336,"orcid":9},"Antony Daniel Rex. J",{"name":338,"orcid":9},"R. Vidya",{"name":340,"orcid":9},"A. Martin",{"tldr":342,"method":343,"finding":344,"direction":95,"opportunity":345},"综述深度学习用于卫星影像土地覆盖分类的语义分割方法，并分析挑战与未来方向。","综述CNN、Transformer及混合架构，案例为EfficientNet-V","混合架构性能优，但存在类别不平衡、计算成本高、泛化差等问题。","可探索轻量级混合架构或自监督学习，以提升农业土地覆盖分类的精度与泛化能力。","2026-09-03T23:30:30.230250Z",{"id":348,"title":349,"url":350,"summary":351,"summary_zh":352,"content":9,"source_name":296,"source_url":350,"published_at":353,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":354,"score_detail":355,"sources":357,"tags":359,"primary_topic":362,"secondary_topics":363,"classification":364,"search_phrases":389,"slug":392,"view_count":90,"doi":393,"paper":394,"created_at":405},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。","2026-10-21T00:00:00Z",74,{"impact":112,"substance":18,"depth":17,"authority":112,"freshness":13,"relevant":21,"comment":356},"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。",[358],{"name":296,"url":350},[308,26,360,28,361],"粮食安全","气候分析",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":365},{"candidates":366,"agricultural_evidence":46},[367,371,376,381,385],{"code":32,"score":20,"supported":46,"title":368,"abstract":369,"tags":370},[191],[],[26],{"code":206,"score":67,"supported":46,"title":372,"abstract":373,"tags":375},[],[374],"农业传感",[],{"code":377,"score":21,"supported":14,"title":378,"abstract":379,"tags":380},"A8",[],[],[360],{"code":200,"score":21,"supported":14,"title":382,"abstract":383,"tags":384},[],[],[308],{"code":52,"score":21,"supported":14,"title":386,"abstract":387,"tags":388},[],[],[28],[390,391],"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":393,"openalex_id":395,"authors":396,"venue":296,"cited_by_count":90,"oa_url":350,"card":399,"direction":404,"ingested_from":97},"W7223111766",[397],{"name":398,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":400,"method":401,"finding":402,"direction":95,"opportunity":403},"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。","农业人工智能与决策模型","2026-10-22T11:21:02.682497Z",{"id":407,"title":408,"url":409,"summary":410,"summary_zh":411,"content":9,"source_name":296,"source_url":409,"published_at":353,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":299,"score_detail":412,"sources":415,"tags":417,"primary_topic":420,"secondary_topics":421,"classification":423,"search_phrases":440,"slug":443,"view_count":90,"doi":444,"paper":445,"created_at":455},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":45,"substance":301,"depth":413,"authority":112,"freshness":13,"relevant":21,"comment":414},17,"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。",[416],{"name":296,"url":409},[308,26,418,28,419],"产量预测","可解释性",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[422],{"code":52,"slug":121,"name":122,"path":123,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":424},{"candidates":425,"agricultural_evidence":46},[426,432,436],{"code":32,"score":112,"supported":46,"title":427,"abstract":429,"tags":431},[428],"computer vision",[430],"计算机视觉",[26],{"code":52,"score":45,"supported":46,"title":433,"abstract":434,"tags":435},[],[28,56],[418,28],{"code":200,"score":21,"supported":14,"title":437,"abstract":438,"tags":439},[],[],[308],[441,442],"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":444,"openalex_id":446,"authors":447,"venue":296,"cited_by_count":90,"oa_url":409,"card":450,"direction":95,"ingested_from":97},"W7223114002",[448],{"name":449,"orcid":9},"Kadiatou Barry",{"tldr":451,"method":452,"finding":453,"direction":95,"opportunity":454},"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"]