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

{"title":"A New Phase Unwrapping Method for Disconnected Regions Inspired by Continental Drift Theory","authors":"Pengfei Li;Zhiwei Li;Mi Jiang;Lei Guo;Minzheng Mu;Xin He;Jiachen Li;Yan Zhu;Yukun Yang","doi":"10.1109/JSTARS.2025.3581025","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3581025","url":null,"abstract":"Phase unwrapping (PU) is a crucial step in interferometric synthetic aperture radar, as it directly influences the accuracy of surface deformation monitoring and topographic mapping. However, PU in disconnected regions due to surrounding low-coherence pixels and irregular terrain like islands remains challenging. To address this issue, we propose an advanced PU method that enhances network construction for disconnected regions by leveraging continental drift concept and visual contour features. The method adaptively connects disconnected regions and reconstructs a spatial network, significantly increasing the number of network connections between these regions compared to the original network. Consequently, our method can optimize the unwrapping paths, enhance antinoise performance, and improve PU accuracy. The effectiveness of the proposed method is validated through both simulated and real datasets. The results demonstrate that our proposed method outperforms the classical minimum cost flow method, achieving a 37.29% reduction in phase standard deviation, and improving the accuracy of subsequent parameter estimation.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15616-15628"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045082","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536378","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":"Enhancing Water Bodies Detection in the Highland and Coastal Zones Through Multisensor Spectral Data Fusion and Deep Learning","authors":"Xiaofei Han;Nazih Y. Rebouh;Yasmeen Ahmed;Muhammad Nasar Ahmad;Zainab Tahir;Yahia Said;Ishfaq Gujree","doi":"10.1109/JSTARS.2025.3580595","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580595","url":null,"abstract":"Accurate mapping of inland and coastal water bodies is crucial for monitoring environmental changes, managing hydrological resources, and assessing the impacts of climatic variability. This study presents a deep-learning-based semantic segmentation framework that leverages multiband Sentinel-2 imagery for delineating glaciers and coastal lakes. The dataset comprises 400 × 400-pixel image patches, constructed using false-color composites of Sentinel-2 bands 8 (NIR), 4 (red), and 3 (green), which enhance the spectral separation between water and nonwater surfaces. These bands were strategically selected to improve water body contrast and boundary definition through multisensor data fusion, enabling more precise lake border extraction. Each image patch is paired with hand-labeled binary lake masks to serve as ground truth. We developed and trained a simple U-Net in PyTorch and a shallow convolutional neural network in TensorFlow to evaluate model performance and architectural efficiency using the same dataset. Both models were assessed using standard performance metrics, including precision, recall, <italic>F</i>1-score, and intersection over union (IoU). Results show high segmentation accuracy across both platforms (<italic>F</i>1 > 0.92 and IoU > 0.86). The TensorFlow-based model exhibited faster training and inference, while the PyTorch U-Net provided more consistent and accurate border delineation. This work demonstrates the synergistic power of multiband spectral fusion and deep learning for environmental feature extraction in remote sensing. The proposed models and methods are scalable and adaptable for broader applications in coastal monitoring, inland water mapping, and climate-related hydrological assessments, offering a valuable contribution to automated Earth observation workflows under changing climatic conditions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15629-15642"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045151","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557789","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":"Noncloud Contaminants in Agricultural Soil Monitoring: Quantifying Spectral Distortions From Plastic Covers, Pylons, and Aircraft Overpasses","authors":"Elsy Ibrahim;Anne Gobin","doi":"10.1109/JSTARS.2025.3581045","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3581045","url":null,"abstract":"The detection and exclusion of clouds and their shadows have been the primary focus of pixel contamination in spaceborne agricultural soil monitoring. However, contaminants affecting specific parts of agricultural fields, such as stationary features (large pylons and artificial soil cover) and dynamic sources (pylon shadows and passing aircraft with contrails), have been overlooked despite their importance in precision agriculture. This study investigates these underexplored sources of pixel contamination and their implications for agricultural soil monitoring. Using bare soil data from 2017 to 2023 and focusing on the field preparation period from mid-April to late May, we analyzed the effects of artificial soil cover, transmission tower shadows, and aircraft overflights on bare soil reflectance. These pixel contaminants significantly altered surface reflectance compared to clear bare soil pixels, with P <inline-formula><tex-math>$leq$</tex-math></inline-formula> 0.0001 for artificially covered, P <inline-formula><tex-math>$leq$</tex-math></inline-formula> 0.01 for aircraft-impacted and P <inline-formula><tex-math>$leq$</tex-math></inline-formula> 0.05 for tower shadowed pixels. Artificial cover increased the surface reflectance of bare soil by 10% to 50% in the visible and near-infrared bands, with a smaller increase of 5% in the shortwave infrared bands; pylon shadows reduced the surface reflectance by up to 5% within a 10 m buffer around the shadow. Aircraft footprints caused a sixfold increase in reflectance, with contrails affecting large areas and increasing reflectance by up to 30%. Important spectral indices for bare soil analyses were significantly affected by artificial cover, but not always by shadows or aircraft impact. The analysis provides insights into the spectral anomalies caused by pixel contaminants and highlights the need to account for such influences to improve the accuracy of spaceborne agricultural soil monitoring, particularly in small parcels or field zones.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15876-15886"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11044435","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557954","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":"Enhancing Hyperspectral Images Compressive Sensing Reconstruction With Smooth Low-Rankness Joint Gradient Sparsity","authors":"Yanyan Lv;Dan Li;Fanqiang Kong;Xinwei Wan;Qiang Wang","doi":"10.1109/JSTARS.2025.3580668","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580668","url":null,"abstract":"The application of compressive sensing (CS) theory in hyperspectral images (HSI) reconstruction has been validated. The key to model-based reconstruction methods lies in effectively integrating prior knowledge of HSI. However, capturing multiple prior knowledge means that multiple regularization terms need to be set, which not only increases the complexity of the model, but also reduces its stability. In this article, a model based on smooth low-rank joint gradient sparsity is proposed to enhance the capability of HSI compressed sensing reconstruction. First, we propose a new model called the smooth spatial-spectral low-rank model (SSLR). Unlike most current models that treat the low-rankness and local smoothness of HSI as two separate regularization terms, SSLR uses only one regularization term. In addition, the use of 2-D gradient images introduces spatial–spectral correlation, while the constraint of Tucker rank allows for a more comprehensive capture of low-rank information across spatial and spectral dimensions. At the same time, to address the shortcomings of SSLR in capturing spatial features and sparsity, we design the multidimensional coupled gradient sparsity model to extract these features. The combination of 1-D spatial gradient images with a 2-D spatial-spectral gradient image fully captures the gradient sparsity across multiple dimensions. In addition, it obtains the rich spatial structure information of HSI. The superiority of the proposed model is demonstrated through comparative experiments conducted on three datasets.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15659-15674"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11042909","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557809","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":"An Improved Processing Method for Low-Frequency Spaceborne Full-Polarimetric SAR Data Affected by Ionospheric Faraday Rotation","authors":"Xun Wang;Yunhua Zhang;Dong Li","doi":"10.1109/JSTARS.2025.3581144","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3581144","url":null,"abstract":"Spaceborne full-polarimetric (FP) synthetic aperture radar (SAR) system operating at low frequency (such as L- or P-band) is a powerful microwave sensor used to capture the Earth’s surface information. However, the application effectiveness of the data acquired by such a sensor depends on the processing for the effects of ionospheric Faraday rotation (FR) and possibly-existing certain system errors. This article develops an improved processing method for low-frequency spaceborne FP SAR data affected by FR in the presence of additive noise to generate the 3 × 3 coherency matrix (CM) used for polarimetric analysis. The key to this method is an improved dichotomy of the FR corrected 4 × 4 CM obtained by directly correcting the measured 4 × 4 CM with the estimated FR. The dichotomy is obtained by solving an optimal dichotomy of the FR corrected 4 × 4 CM based on the Schur complement of a 4 × 4 matrix under two constraints with clear physical significance. Specifically, the two decomposed components are Hermitian and positive semidefinite, while the component related to additive noise possesses the smallest trace. From the perspective of polarimetric scattering entropy and the trace of the second component, the effectiveness and robustness of the improved processing method featuring the proposed dichotomy is tested on diverse L-band ALOS PALSAR and ALOS-2 PALSAR-2 FP acquisitions by comparing it with the processing method holding the same basic steps but applying the commonly used direct dichotomy. Experimental results indicate that the improved processing method can effectively alleviate the influence of additive noise on the generated 3 × 3 CM.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15774-15788"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557788","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":"Monitoring Snowmelt in Mountainous Areas by Considering SAR Geometric Distortion From Ascending and Descending Orbits","authors":"Yanli Zhang;Yalong Ma;Kairui Lei;Gang Chen","doi":"10.1109/JSTARS.2025.3580604","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580604","url":null,"abstract":"Synthetic aperture radar (SAR) multitemporal and multipolarization change detection method has been widely utilized for wet snow extraction. Although SAR terrain correction can alleviate the geometric distortion caused by foreshortening and layover, it fails to fully eliminate terrain shadows and great layover effects on steep slopes, presenting significant challenges for high-precision monitoring of snowmelt. This study proposes a method for identifying snowmelt in mountainous areas by combining Sentinel-1 ascending and descending orbits data, taking advantage of the significant differences in geometric distortion areas between two types of orbits that transit on the same day. First, geometric distortion areas and reliable areas are identified on the Sentinel-1 ascending orbit images (evening) and descending orbit images (morning) using radar and local incidence angles, respectively. Wet snow is extracted from each reliable area using SAR multitemporal and multipolarization change detection algorithm. Then, the Sentinel-1 images of the two orbits are combined to obtain the reliable areas with minimal geometric distortion, and wet snow information is obtained through wet snow priority method and reliable areas priority method. Using the Babao River Basin in the Qilian Mountains as the study area, the data were accessed through the Google Earth Engine (GEE) and analysis was run on GEE. At the same time, in order to accurately extract the snow cover range, the spatiotemporal data fusion model was employed to simulate Sentinel-2 images that transit on the same day as Sentinel-1. Finally, the extracted dry/wet snow was corrected using a digital elevation model to determine the distribution of dry/wet snow in the Babao River Basin for a hydrological year from September 2021 to August 2022. Using 71 field measurements of snow water content for accuracy verification, the results indicated that the overall accuracy of using combined ascending and descending orbits data increased from 71.2% for descending orbit alone and 72.4% for ascending orbit alone to 81.7%.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15587-15600"},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045183","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557831","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":"SEMSF-Net: Explainable Squeeze–Excitation Multiscale Fusion Network for Aerial Scene and Coastal Area Recognition Using Remote Sensing Images","authors":"Muhammad John Abbas;Muhammad Attique Khan;Ameer Hamza;Shrooq Alsenan;Areej Alasiry;Mehrez Marzougui;Yang Li;Yunyoung Nam","doi":"10.1109/JSTARS.2025.3580801","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580801","url":null,"abstract":"Land use and land cover (LULC) classification has played a key role over the last decade for managing the decay of resources and mitigating the impact of population growth. It is used in several places, such as rapid urbanization, agriculture, climate change, coastal areas, and disaster recovery. The traditional remote sensing (RS) techniques encounter limitations in accurately classifying dynamic and complex ariel scenes, such as coastal areas and LULC. This article proposed a novel squeeze–excitation multiscale fusion network (SEMSF-Net) to classify LULC and the coastal regions using RS images. The proposed model is based on the squeeze-and-excitation block initially embedded with inception and dense blocks separately. These blocks are designed based on the multiscale to generate more important feature information that can later perform accurate classification. In the next phase, these blocks are fused at the network level, where bottleneck and inverted residual blocks are connected to reduce the learnable parameters and improve feature strength. The hyperparameters of this network are selected based on the several experiments utilized in the training of the proposed model. The trained SEMSF-Net architecture is further employed in the testing phase, and classification is performed. The GradCAM is also used to interpret the trained model’s visual prediction. Three datasets are utilized for the experimental process: the Coastal dataset, MLRSNet, and NWPU. We obtained an improved accuracy of 94.94%, 93.7%, and 95.70% on these datasets, respectively. In addition, the macro recall rates are 79.0%, 93.0%, and 96%, respectively. Comparison with several recent techniques shows that the proposed model outperforms the selected datasets.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15755-15773"},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039102","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557953","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":"Semantic–Spatial Feature Fusion With Dynamic Graph Refinement for Remote Sensing Image Captioning","authors":"Maofu Liu;Jiahui Liu;Xiaokang Zhang","doi":"10.1109/JSTARS.2025.3580686","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580686","url":null,"abstract":"Remote sensing image captioning aims to generate semantically accurate descriptions that are closely linked to the visual features of remote sensing images. Existing approaches typically emphasize fine-grained extraction of visual features and capturing global information. However, they often overlook the complementary role of textual information in enhancing visual semantics and face challenges in precisely locating objects that are most relevant to the image context. To address these challenges, this article presents a semantic–spatial feature fusion with dynamic graph refinement (SFDR) method, which integrates the semantic–spatial feature fusion (SSFF) and dynamic graph feature refinement (DGFR) modules. The SSFF module utilizes a multilevel feature representation strategy by leveraging pretrained CLIP features, grid features, and ROI features to integrate rich semantic and spatial information. In the DGFR module, a graph attention network captures the relationships between feature nodes, while a dynamic weighting mechanism prioritizes objects that are most relevant to the current scene and suppresses less significant ones. Therefore, the proposed SFDR method significantly enhances the quality of the generated descriptions. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15442-15455"},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536380","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":"Rainfall Rate Measurement for Advanced Meteorological Imager of the GEO-KOMPSAT-2A Satellite","authors":"Dong-Bin Shin;Dong-Cheol Kim;Damwon So","doi":"10.1109/JSTARS.2025.3580888","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580888","url":null,"abstract":"An operational rainfall rate (RR) algorithm for the advanced meteorological imager (AMI) on the GEO-KOMPSAT-2A (GK2A) satellite has been developed. This algorithm exploits <italic>a priori</i> information, including rainfall data from the global precipitation measurement (GPM) dual-frequency precipitation radar (DPR) and infrared (IR) brightness temperature (TB) from GK2A. The performance of the RR algorithm is enhanced by incorporating <italic>a priori</i> information that encompasses a wide range of precipitation systems. Additionally, retrieval accuracy can be improved by distinguishing between physically different precipitation systems during the retrieval process. To classify precipitating clouds, the RR algorithm uses brightness temperature differences between IR channels, accounting for the diverse radiative characteristics resulting from various hydrometeor and cloud thickness distributions. Consequently, the RR algorithm categorizes five types of precipitating clouds (one shallow and four nonshallow) and separates the databases into four latitudinal bands to capture regional variations. A Bayesian approach was applied to invert TB values from five IR channels to RR, based on <italic>a priori</i> databases constructed using one year of collocated DPR and AMI data. The RR algorithm’s estimates were compared with those from DPR and GPM microwave imager over two months and twelve typhoon cases. The results indicate that the RR algorithm meets the operational accuracy requirement, with a bias of 9 mm/h at 10 mm/h. Additional validation with the ground radar observations over the Korean Peninsula confirmed that the retrieval biases were within the accuracy requirement.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15725-15739"},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039691","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557955","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":"Cloud Removal Advances: A Comprehensive Review and Analysis for Optical Remote Sensing Images","authors":"Jin Ning;Lianbin Xie;Jie Yin;Yiguang Liu","doi":"10.1109/JSTARS.2025.3580718","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3580718","url":null,"abstract":"Cloud cover significantly decreases the quality of optical remote sensing (ORS) images, adversely impacting its effectiveness in geographic monitoring, disaster prevention, and advanced visual applications. This phenomenon has made cloud removal a critical preprocessing step in ORS image processing. This article comprehensively reviews cloud removal techniques and classifies them based on the type of auxiliary data used: single-image, multimodal, and multitemporal. The discussed methods include physical modeling, deep learning, multispectral analysis, and synthetic aperture radar (SAR) fusion strategies. This article analyzes the core concepts and fundamental processes of these techniques and addresses the challenges encountered in actual scenarios. The article also includes future research directions. Moreover, the article outlines the benchmark datasets and evaluation metrics commonly used in cloud removal, thereby establishing a standardized reference for algorithm development and performance evaluation. A thorough comparative analysis was performed to assess their performance variations using visualization outcomes from the most recent and representative methodologies.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"15914-15930"},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039671","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557952","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}