GIScience & Remote Sensing最新文献

{"title":"High-resolution land cover mapping from coarse labels via a noisy label learning-guided cross-scale framework","authors":"Xiangyu Nie,Cong Lin,Wei Zhang,Hong Fang,Zhen Dong,Sicong Liu,Zhaohui Xue","doi":"10.1080/15481603.2026.2726002","DOIUrl":"https://doi.org/10.1080/15481603.2026.2726002","url":null,"abstract":"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.","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"13 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Audio-visual fusion for near-surface wind speed estimation using surveillance cameras","authors":"Xing Wang,Cuiyan Zhang,Heyueyang Li,Maosu Wang","doi":"10.1080/15481603.2026.2731700","DOIUrl":"https://doi.org/10.1080/15481603.2026.2731700","url":null,"abstract":"Surveillance camera-based wind speed (WS) estimation provides a promising and cost-effective solution for near-surface wind sensing; however, its performance remains limited in complex urban environments due to the instability and insufficient accuracy of single-modality observations. This study proposes a surveillance audio-visual fusion framework for WS estimation, termed VA-WindNet. VA-WindNet jointly exploits wind-induced visual motion features and acoustic spectral signatures by integrating convolutional neural networks (CNNs) for spatial feature extraction with temporal neural networks for sequential modeling, together with a sequential bidirectional cross-modal interaction mechanism that progressively refines the visual and acoustic temporal representations before feature aggregation. A multi-scene audio-visual wind dataset of approximately 64 hours was constructed, and 48 VA-WindNet variants were developed by combining multiple CNN backbones with different temporal modeling modules for systematic training and evaluation. Results from real-world experiments show that the VA-WindNet model configured with DenseNet169 and a recurrent neural network achieved the best performance with an RMSE of 1.42 m/s. This corresponds to RMSE reductions of approximately 12.9% and 27.2% compared with the best video-only and audio-only configurations, respectively, and approximately 19% compared with two advanced vision-based wind speed estimation models. Under audio- and video-interference conditions, the median RMSEs of VA-WindNet variants were 1.68 m/s and 2.11 m/s, representing reductions of 33.3% and 19.5% relative to the audio-only and video-only baselines, respectively. These results highlight the potential of surveillance camera networks as a low-cost and infrastructure-efficient solution for high-resolution near-surface wind sensing in urban environments, supporting sustainable urban environmental monitoring, fine-scale wind field analysis, and smart-city-oriented observation enhancement as a complement to existing networks.","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"2 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Shifting pathways of post-earthquake vegetation structural and functional recovery under varying earthquake disturbance intensities","authors":"Dandan Yao,Huaan Jin,Wei Zhao,Gaofei Yin,Li Peng,Xinyao Xie,Xiao Ma,Wenjuan Wang","doi":"10.1080/15481603.2026.2728759","DOIUrl":"https://doi.org/10.1080/15481603.2026.2728759","url":null,"abstract":"Extreme disturbances (e.g. earthquakes) alter ecosystem structure and function, and shape the patterns of ecosystem resilience and carbon sink recovery. Spatial heterogeneities in varying seismic intensities may drive divergent structural and functional recovery trajectories, yet the synchrony between the two recoveries remains unclear. Moreover, the inadequate evaluation of satellite-derived biophysical products, along with the effects of climate change and human activities, may bias the interpretation of earthquake-induced vegetation recovery trajectories. Taking the 2017 Jiuzhaigou earthquake as a case study, we developed the dual-dimensional recovery assessment framework that integrated the leaf area index (LAI, proxy of structure) and gross primary productivity (GPP, proxy of function). The multiple GPP and LAI products were separately evaluated using eddy covariance observations and high-resolution reference data to select the representative vegetation structure and function proxies. The vegetation damaged areas (VDA) were then extracted using joint GPP–LAI thresholds. Subsequently, the residual analysis was served isolate the effects of climate change and human activities, as well as to quantify the impacts of earthquake disturbances on vegetation recovery during 2018–2023. The results indicated that PML-V2 GPP and MODIS LAI exhibited relatively high stability, and 56.52% of the area experienced concurrent structural and functional damage, with the earthquake disturbance contributing approximately 75% to the VDA. Early post-earthquake structural and functional recovery showed pronounced asynchrony but gradually became coordinated over time. Distinct recovery pathways of vegetation structure and function were observed across disturbance intensity zones. Specifically, in severely disturbed zones, the GPP recovered faster than LAI, which implied that functional recovery outpaced structural recovery (i.e. the function-leading recovery pathway). In contrast, the opposite pattern was observed in the moderately and weakly disturbed zones, where structural recovery preceded functional recovery (i.e. the structure-dominated pathway). The variation in leaf photosynthetic efficiency partly explained the divergent recovery dynamics between LAI and GPP under different earthquake disturbance intensities. By 2023, more than half of the area remained degraded or in ongoing recovery, which highlighted the long-term and spatially heterogeneous nature of ecosystem recovery. Our study reveals distinct post-earthquake vegetation recovery pathways from an integrated structure–function perspective. These findings provide important insights into the spatiotemporal dynamics of vegetation recovery and its implications for regional carbon cycling.","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"81 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MambaMPD: a mamba-driven segmentation framework for marine pollution detection from remote sensing imagery","authors":"Shuaiyu Chen,Wei Han,Peng Ren,Chunbo Luo,Zeyu Fu","doi":"10.1080/15481603.2026.2730893","DOIUrl":"https://doi.org/10.1080/15481603.2026.2730893","url":null,"abstract":"Accurate detection of marine pollution is essential for protecting coastal ecosystems and marine biodiversity. Recently, vision Mamba-based approaches have shown promise in remote sensing semantic segmentation due to their ability to efficiently capture long-range dependencies and global context. However, their potential remains largely unexplored in the context of marine pollution detection (MPD), with distinct challenges, including low signal-to-noise ratios, spatial fragmentation of pollution patterns, and indistinct boundaries caused by strong visual similarity between pollutants and the surrounding marine environment. To address these challenges, we propose MambaMPD, an enhanced Mamba-based framework tailored for marine pollution detection. MambaMPD incorporates two targeted modules that enhance the Mamba encoder with complementary structural priors: the frequency-aware augmentation (FAA) module and the multi-scale edge-guided attention (EGA) module. The FAA module strengthens the encoding process by integrating Wavelet Transforms, which decompose features into multi-scale frequency subbands. This enables the model to efficiently capture both low-frequency contextual semantics and high-frequency structural details, essential for identifying small, low-contrast, and irregular pollution patterns. Meanwhile, the EGA module adaptively integrates hierarchical Laplacian-derived multi-scale boundary cues into deep semantic representations, guiding the refinement of encoder features before decoding, thereby sharpening boundary delineation and alleviating ambiguity in visually confusing and spatially fragmented marine scenes. Additionally, a U-Net-style decoder equipped with squeeze-and-excitation attention and deep supervision is employed to progressively recover and refine semantic and spatial features across multiple scales. Extensive experiments on two benchmark marine pollution detection datasets demonstrate that the proposed method outperforms the compared methods in mIoU while maintaining significantly lower computational cost than foundation-model-based approaches. On MADOS, it surpasses OSDMamba by 3.6% in F1, and on M4D it improves Oil Spill IoU by 6.82% over TransOilSeg. The source code of our approach will be available at https://github.com/Multimodal-Intelligence-Lab-MIL/MambaMPD.","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"7 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nonlinear responses of net ecosystem productivity to heatwaves over the Qinghai–Tibetan Plateau: insights from climate and vegetation","authors":"Hongzhe Li,Yi He,Qing Zhu,Lifeng Zhang,Li Quan","doi":"10.1080/15481603.2026.2728311","DOIUrl":"https://doi.org/10.1080/15481603.2026.2728311","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"10 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Aboveground woody biomass regression and uncertainty estimation from spaceborne lidar and optical datasets","authors":"Hailey S. Melzow,Javier Osorio Leyton,Sorin C. Popescu,Horia G. Olariu,X. Ben Wu","doi":"10.1080/15481603.2026.2707801","DOIUrl":"https://doi.org/10.1080/15481603.2026.2707801","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"40 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing local and transferable spectral endmembers for disturbance detection in\u0000 Pinus\u0000 sylvestris\u0000 L. forests across Spain","authors":"Saioa Munuera,Cristina Gómez,Beatriz Águeda,Francisco Rodríguez-Puerta","doi":"10.1080/15481603.2026.2728760","DOIUrl":"https://doi.org/10.1080/15481603.2026.2728760","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"60 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Balancing solution quality and runtime in modular mobile hospital location: a hybrid approach of deep reinforcement learning and integer programming","authors":"Suyeon Hwang,Hanseong Chae,Seohyeon Baek,Jinmu Choi","doi":"10.1080/15481603.2026.2730795","DOIUrl":"https://doi.org/10.1080/15481603.2026.2730795","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"267 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-scale voxel-based framework for robust multisource forest LiDAR registration","authors":"Wenrui Song,Xin Zong,Wenlong Song,Nianpeng He,Jianping Huang,Yanqiu Xing,Weigang Li,Marco Heurich","doi":"10.1080/15481603.2026.2724603","DOIUrl":"https://doi.org/10.1080/15481603.2026.2724603","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"37 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A soil-thickness-constrained geospatial framework for reconstructing monthly shallow soil water storage across the Tibetan Plateau","authors":"Xin Zhang,Jianrong Fan","doi":"10.1080/15481603.2026.2728825","DOIUrl":"https://doi.org/10.1080/15481603.2026.2728825","url":null,"abstract":"","PeriodicalId":55091,"journal":{"name":"GIScience & Remote Sensing","volume":"11 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}