IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"An OSCAT Simultaneous Wind/Rain Geophysical Model Function","authors":"Benjamin J. Fogg;David G. Long","doi":"10.1109/JSTARS.2025.3585769","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585769","url":null,"abstract":"Conventional near-surface vector wind (VW) estimates from microwave scatterometers degrade in quality in the presence of rain because the standard wind-only (WO) geophysical model function (GMF) does not model rain effects. The WO GMF maps the noise-free normalized radar cross-section (<inline-formula><tex-math>$sigma ^circ$</tex-math></inline-formula>) to the near-surface VW but omits other geophysical phenomena, such as rain rate (<inline-formula><tex-math>$R$</tex-math></inline-formula>). Previous studies have developed simultaneous wind/rain (SWR) GMFs that map <inline-formula><tex-math>$sigma ^circ$</tex-math></inline-formula> to the near-surface VW and <inline-formula><tex-math>$R$</tex-math></inline-formula> to account for rain effects [1]. This article develops an SWR GMF for the Ku-band OceanSat-2 Scatterometer (OSCAT) using a <inline-formula><tex-math>$sigma ^circ$</tex-math></inline-formula>, VW, and <inline-formula><tex-math>$R$</tex-math></inline-formula> triple collocated database. OSCAT <inline-formula><tex-math>$sigma ^circ$</tex-math></inline-formula> measurements are collocated with Tropical Rain Measuring Mission (TRMM) near-surface <inline-formula><tex-math>$R$</tex-math></inline-formula>, and European Centre for Medium-Range Weather Forecasts (ECMWFs) numerical weather prediction near-surface VW product creating the OSCAT, TRMM, and ECMWF Database (OTED). Four novel approaches for creating an SWR GMF are discussed and the most accurate GMF is found to be the path integrated attenuation method. The estimate accuracy is analyzed using the OTED, which reveals that the SWR wind speed estimate accuracy is between 0.25 and 0.7 m/s more accurate (depending on the rain rate) on average compared to WO speed estimates. However, wind direction estimates are not improved by SWR with WO outperforming the SWR estimates by between 1<inline-formula><tex-math>$^circ$</tex-math></inline-formula> and 10<inline-formula><tex-math>$^circ$</tex-math></inline-formula> (depending on the <inline-formula><tex-math>$sigma ^circ$</tex-math></inline-formula> spatial resolution).","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"17852-17864"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11068141","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CerraData-4 MM: A Multimodal Benchmark Dataset on Cerrado for Land Use and Land Cover Classification","authors":"Mateus de Souza Miranda;Ronny Hänsch;Valdivino Alexandre de Santiago Júnior;Thales Sehn Körting;Erison Carlos dos Santos Monteiro","doi":"10.1109/JSTARS.2025.3585805","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585805","url":null,"abstract":"The <italic>Cerrado</i> faces increasing environmental pressures, necessitating accurate land use and land cover mapping despite challenges, such as class imbalance and visually similar categories. To address this, we present CerraData-4 MM, a multimodal dataset combining Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral imagery with 10 m spatial resolution. The dataset includes two hierarchical classification levels with seven and 14 classes, respectively, focusing on the diverse <italic>Bico do Papagaio</i> ecoregion. We benchmark two models trained on CerraData-4 MM, employing a visual transformer-based architecture and a convolutional-based architecture. The ViT achieves superior performance in multimodal scenarios, with the highest macro F1-score of 57.60% and a mean Intersection over Union of 49.05% at the first hierarchical level. Both models struggle with minority classes, particularly at the second hierarchical level, where U-Net’s performance drops to an F1-score of 18.16%. Weighted loss improves representation for underrepresented classes but reduces overall accuracy, underscoring the trade-off in weighted training. CerraData-4 MM offers a challenging benchmark for advancing deep learning models to handle class imbalance and multimodal data fusion.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"18031-18041"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11068119","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144716341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DAM-Net: Domain Adaptation Network With Microlabeled Fine-Tuning for Change Detection","authors":"Hongjia Chen;Xin Xu;Fangling Pu","doi":"10.1109/JSTARS.2025.3585529","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585529","url":null,"abstract":"Change detection (CD) in remote sensing imagery plays a crucial role in various applications, such as urban planning, damage assessment, and resource management. While deep learning approaches have significantly advanced CD performance, current methods suffer from poor domain adaptability, requiring extensive labeled data for retraining when applied to new scenarios. This limitation severely restricts their practical applications across different datasets. In this work, we propose DAM-Net, a domain adaptation network with microlabeled fine-tuning for CD. Our network introduces adversarial domain adaptation to CD for utilizing a specially designed segmentation-discriminator and alternating training strategy to enable effective transfer between domains. In addition, we propose a novel microlabeled fine-tuning approach that strategically selects and labels a minimal amount of samples (less than 1%) to enhance domain adaptation. The network incorporates a multitemporal transformer for feature fusion and optimized backbone structure based on previous research. Experiments conducted on the LEVIR-CD and WHU-CD datasets demonstrate that DAM-Net significantly outperforms the existing domain adaptation methods, achieving comparable performance to semisupervised approaches that require 10% labeled data while using only 0.3% labeled samples. Our approach significantly advances cross-dataset CD applications and provides a new paradigm for efficient domain adaptation in remote sensing.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"18042-18054"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11066298","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144716342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatial–Temporal Semantic and Geographic Correlation Network for SAR Image Change Detection With Limited Training Data","authors":"Haolin Li;Bin Zou;Lamei Zhang;Jiang Qin","doi":"10.1109/JSTARS.2025.3585568","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585568","url":null,"abstract":"Existing supervised and semisupervised methods for synthetic aperture radar (SAR) image change detection are limited by the scarcity of labeled data and the challenges of modeling spatial–temporal correlations. To address these issues, we propose STSGNet, a graph contrastive learning-based framework that captures spatial–temporal correlations from large amounts of unlabeled data and leverages limited labeled data for fine-tuning, thereby enhancing the model’s change detection performance. STSGNet consists of three primary modules: the spatial–temporal semantic (STS) module, the spatial–temporal geographic (STG) module, and the dynamic weighted fusion (DWF) module. The STS module integrates a bitemporal semantic enhancement module to capture cross-temporal semantic similarities and differences, while the STG module applies a geographic correlation data augmentation strategy and incorporates geographic transformer blocks to integrate geographic information, enhancing spatial representation and contextual reasoning. The DWF module effectively integrates the semantic and geographic features, producing comprehensive spatial–temporal feature representations. By extending the model to the complex-valued domain, STSGNet incorporates both amplitude and phase information, enabling a more detailed perception of potential changes. STSGNet comprehends complex interdependencies across time and space, enabling accurate predictions of change areas even with limited labeled data. Experiments on five diverse SAR image scenes confirm that STSGNet surpasses baseline methods under both unsupervised and limited supervised conditions, validating its effectiveness.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"17119-17138"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11066238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FVPNet: A Fuzzy Visual Positioning Perception Network for Small Object Segmentation in Remote Sensing Images","authors":"Yu Yan;Jindong Xu;Qianpeng Chong;Guangyi Wei;Zhixiang Wang","doi":"10.1109/JSTARS.2025.3585184","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585184","url":null,"abstract":"The increasing availability of high-resolution remote sensing images (RSIs), driven by advancements in satellite and optical imaging technologies, presents both new opportunities and challenges for small object segmentation (SOS) tasks. A primary challenge in SOS tasks is the substantial sample imbalance between foreground and background, resulting in the underrepresentation or even loss of features for small foreground targets. Furthermore, grayscale variability intensifies boundary uncertainty, complicating accurate segmentation. To address these issues, we propose a fuzzy visual perception network, which incorporates a feature inheritance downsampling (FID) module, a fuzzy refinement subnet, and a small target perception (STP) subnet, along with a hierarchical balance loss that prioritizes small foreground objects to effectively reduce foreground bias in regression. The FID module integrates diverse feature map extraction techniques to construct a more robust feature map through various subsampling methods, mitigating feature loss in foreground targets. The FR subnet employs high-order fuzzy modeling with adaptive membership functions and a constrained-space boundary adaptation strategy to address boundary uncertainty in RSIs. Meanwhile, the STP subnet adopts a “coarse-to-fine” paradigm, utilizing a pyramidal structure alongside an auxiliary semantic decoder to enhance the network’s capacity for accurate small target localization. We conduct extensive experiments and ablation studies on three benchmark datasets, iSAID, Vaihingen, and Potsdam datasets. Across the three datasets, our method achieved mean Intersection over Union scores of 73.08%, 87.37%, and 81.54%, respectively. Both quantitative and qualitative evaluations clearly demonstrate that the proposed approach significantly outperforms existing state-of-the-art methods, achieving a superior balance between segmentation accuracy and computational efficiency.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"17805-17819"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11066261","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EDG-Net: Edge-Enhanced Dynamic Graph Convolutional Network for Remote Sensing Scene Classification of Mining-Disturbed Land","authors":"Xianju Li;Pan Kong;Weitao Chen;Wenxi He;Jian Feng;Jiangyuan Wang","doi":"10.1109/JSTARS.2025.3585311","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585311","url":null,"abstract":"Scene classification and mapping of surface mining-disturbed land can attain semantic-level information that is useful for monitoring mine geo-environment. Mining land’s complex characteristics makes it difficult to extract key features, restricting the accuracy improvements. This study first constructed a 5-class dataset based on multispectral, synthetic aperture radar, and topographic images. Subsequently, a novel model of edge-enhanced dynamic graph convolutional network (GCN) (EDG-Net) was proposed to learn the discriminative features for classification of mining land with irregular edges, different sizes, a relatively small proportion, and sparse spatial distribution. (1) Edge-enhanced multiscale attention module: it is designed to capture key multiscale features and edge details using parallel dilated convolutions with attention fusion and edge enhancement, which facilitates the identification of objects with irregular edges and different sizes. (2) Downsampling fusion module: it integrates the features obtained through spatially split learning and max-pooling to overcome the information loss issue of small objects. (3) Patch-based dynamic GCN: the input images were split into several patches as nodes, and a graph was constructed and dynamically updated by connecting the nearest neighbors. It is beneficial to progressively explore the inherent attributes within node feature maps and fully utilize long-range information, which helps address the sparse distribution issue of mines. Finally, the convolutional and graph features are fused using a residual structure to obtain richer feature representations. The proposed EDG-Net achieved an overall accuracy of 78.08% ± 0.22% and acceptable regional-scale mapping performance, indicating that the proposed dataset and model were beneficial for classification and mapping of mining land.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"17622-17637"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11063351","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Fusion Mamba Network for Joint Land Cover Classification Using Hyperspectral and LiDAR Data","authors":"Haizhu Pan;Ruixiang Zhao;Haimiao Ge;Moqi Liu;Quanxiu Zhang","doi":"10.1109/JSTARS.2025.3585640","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585640","url":null,"abstract":"With the rapid advancement of deep learning technologies, the use of computers for processing and analyzing multimodal remote sensing data has attracted significant attention. Joint land cover classification (LCC) using hyperspectral image (HSI) and light detection and ranging (LiDAR) data is one such key area of research. Recently, the emerging deep learning framework Mamba has shown superior performance over traditional architectures, including transformers and convolutional neural networks. However, its application to LCC faces challenges. First, existing methods typically use a unified feature extraction approach for heterogeneous data, which fails to capture the distinct characteristics of each data modality. Moreover, effectively integrating these heterogeneous features remains a significant difficulty. To address these issues, we propose the multimodal fusion Mamba network (M2FMNet), which consists of three key components: the spatial–spectral adaptive Mamba, the elevation-enhanced Mamba, and an enhanced fusion module. The spatial–spectral adaptive Mamba combines two distinct scanning methods to efficiently extract spatial and spectral features from HSI data. The elevation-enhanced Mamba, designed for LiDAR data, utilizes a specialized scanning method to extract elevation features. Finally, the enhanced fusion module integrates intra- and intermodal relationships of these features at the pixel level. Experimental results on three real-world datasets show that the M2FMNet outperforms state-of-the-art methods in both qualitative and quantitative metrics.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"17328-17345"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11066256","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Removal of LiDAR Negative Outliers Based on Retroreflective Surface","authors":"Haolong Gao;Shaobo Li;Zhouyi Kang;Fan Zhang;Yi Zhang;Yunlong Wu","doi":"10.1109/JSTARS.2025.3585534","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585534","url":null,"abstract":"LiDAR is an essential tool for terrain data acquisition; however, its application in coastal environments is often limited by negative outliers caused by multipath reflections. The negative outliers can result in deviations of several meters, significantly complicating subsequent data processing and analysis. This article investigates the retroreflective characteristics of negative outliers in terms of spatial structure and intensity and presents a negative outlier removal algorithm based on these features. First, the LiDAR surveying equation is introduced to establish the intensity relationship between negative outliers and their corresponding preliminary reflection points. Second, by analyzing the spatial distribution of point clouds, a covariance matrix is generated, and eigenvalue decomposition is performed to extract structural descriptors for identifying outliers. Third, a terrain mesh model is constructed to approximate the retroreflective surface, enabling a feature-based comparison between negative outliers and their preliminary reflection points. Finally, points below the terrain mesh and their corresponding reflection points are extracted. By comparing their structural similarity and intensity relationships, negative outliers are accurately identified and removed. Experimental results validate the effectiveness of the proposed algorithm, achieving a precision of 88.97% and a recall of 91.94%, ensuring robust outlier removal while preserving terrain details.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"16831-16843"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11066278","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A One-Stage HMDV Algorithm Applied in Multitarget Detection in SAR Images","authors":"Lei Pang;Weihe Huang;Fengli Zhang;Yinhong Song","doi":"10.1109/JSTARS.2025.3585103","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3585103","url":null,"abstract":"Synthetic aperture radar (SAR) image target detection is a key method in image interpretation. Currently, most radar target detection methods are primarily designed for single category, without adequately addressing the challenges of multitarget detection accuracy and lightweight deployment in coastal areas. To tackle these issues, this article proposes a single-stage multi-target detection network called HMDV. First, a hybrid feature extraction module is designed to address the computational complexity caused by increased width and depth in convolutional neural networks. Second, to overcome the challenges posed by the diversity of target sizes in multi-target detection, the loss of dense target feature information, and background clutter, a mult-idimensional perceptual feature aggregation and dispersion module is developed. This module effectively improves the detection accuracy for aircraft and oil tank targets in SAR images. Finally, to resolve the issue of low detection performance due to the small proportion of small targets in the prediction boxes, a new width and height vector loss function is proposed. This function simultaneously constrains the width, height, and proportion of bounding boxes, enhancing the network’s convergence speed and reducing misdetections of small-sized ships. Experimental results demonstrate that the proposed model improves mean average precision accuracy by 2.4% and reduces the number of parameters to 13% of the original, confirming the model’s effectiveness and robustness.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"16488-16496"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11062704","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving InSAR Tropospheric Delay Correction in Deep Canyon Regions With a DEM Watershed-Based Segmented Linear Model","authors":"Menghua Li;Dongxu Huang;Mengshi Yang;Weitao Tian;Cheng Huang;Bo-Hui Tang","doi":"10.1109/JSTARS.2025.3584821","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3584821","url":null,"abstract":"Accurate atmospheric correction is critical for improving the reliability of InSAR deformation monitoring in mountainous area, such as southeastern edge of the Tibetan Plateau, where rugged topography and complex atmospheric conditions introduce significant tropospheric delays. Traditional correction methods, including global linear models (LMs), regular-window segmented linear model (RSLMs), and numerical weather models such as ERA-5 and Generic Atmospheric Correction Online Service (GACOS), often fail to address the spatial heterogeneity of atmospheric signals in such terrains, leaving residual artifacts that obscure surface deformation measurements. To overcome these limitations, this study proposes a watershed-segmented linear model (WSLM) that incorporates vertical atmospheric stratification and lateral watershed boundaries to effectively capture localized atmospheric variability. The performance of WSLM was evaluated using both simulated datasets and real Sentinel-1 data from the Deqin section of the Lancang River and compared with corrections provided by LM, RSLM, GACOS, and ERA-5 corrections. The results show that WSLM effectively reduces atmospheric artifacts, mitigates vertical stratification delays, and improves the recovery of realistic deformation signals. Compared to existing methods, it achieves lower residual phase standard deviations—reducing them by up to 75.78% —weakens phase-elevation correlations, and enhances time-series displacement accuracy. While uncertainties remain in determining the optimal weighting factors and segmentation thresholds, WSLM effectively reduces atmospheric errors and provides valuable insights for deformation monitoring in complex mountainous environments.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"16868-16878"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11062326","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}