Science of Remote Sensing最新文献

{"title":"Assessing the combination of passive and active microwave satellite observations (1.4 to 36 GHz) to estimate above ground biomass (AGB) globally","authors":"Catherine Prigent ,&nbsp;Carlos Jimenez ,&nbsp;Maurizio Santoro ,&nbsp;Oliver Cartus ,&nbsp;Samuel Favrichon","doi":"10.1016/j.srs.2026.100386","DOIUrl":"10.1016/j.srs.2026.100386","url":null,"abstract":"<div><div>A Neural Network inversion method has been developed to estimate Above Ground Biomass (AGB) on a global scale using multiple microwave satellite observations from both passive and active instruments. The reference dataset is the AGB from the European Agency (ESA) Climate Climatology Initiative (CCI). The study evaluates the potential of each observation type individually and in combination, from current Advanced Microwave Scanning Radiometer 2 (AMSR2), Soil Moisture Active Passive (SMAP), and Advanced SCATterometer (ASCAT) satellite instruments. Additionally, auxiliary data from Normalized Difference Vegetation Index (NDVI from MODIS), land surface temperature (LST from ERA5), and soil moisture (SM from ERA5) are incorporated and evaluated into the retrieval process alongside microwave observations.</div><div>Findings confirm that passive 1.4 GHz observations exhibit the highest sensitivity to AGB compared to other passive measurements up to 36 GHz. In contrast, active observations at 6 GHz demonstrate limited potential for AGB estimation when used in isolation, at least within the framework of this study. However, combining microwave observations between 1.4 and 36 GHz yields strong results compared to the CCI AGB dataset. The inclusion of NDVI, LST, and SM further enhances performance, achieving an R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.88 globally and an RMSE of 30 Mg/ha, as compared to the CCI AGB.</div><div>The combination of passive microwave observations at 18 and 36 GHz, supplemented with auxiliary data, shows promise for assessing global AGB. With these passive microwave data available since the 1990s, long-term AGB dynamics could be estimated.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100386"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146187983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Major improvements in spaceborne early fire detection and small-fire FRP retrieval with the meteosat third generation flexible combined imager","authors":"Weidong Xu ,&nbsp;Martin J. Wooster ,&nbsp;Jiangping He ,&nbsp;Andrea Meraner ,&nbsp;Jose Gomez-Dans ,&nbsp;Zixia Liu ,&nbsp;Isabel F. Trigo ,&nbsp;Emanuel Dutra","doi":"10.1016/j.srs.2026.100366","DOIUrl":"10.1016/j.srs.2026.100366","url":null,"abstract":"<div><div>Geostationary Earth Observation satellites, originally developed for weather forecasting, offer unique high temporal resolution imaging capabilities increasingly suited for detecting the fast-changing dynamics of landscape fires. The newly operational Meteosat Third Generation (MTG) satellite carries a Flexible Combined Imager (FCI) that greatly improves on the spatial, temporal and radiometric characteristics of the predecessor Meteosat Second Generation (MSG) Spinning Enhanced Visible and Infrared Imager (SEVIRI) system. Here we describe for the first time the application of an active fire (AF) detection algorithm to FCI data, and the retrieval of fire radiative power (FRP) estimates from the detected AF pixels. The algorithm used is the Fire Thermal Anomaly (FTA) approach, currently used to generate the operational SEVIRI AF data products at the EUMETSAT Land Surface Analysis Satellite Application Facility (LSA SAF). A comparative analysis between the FCI-derived outputs and those obtained from the existing SEVIRI system is undertaken in order to evaluate the benefits provided by FCI. We also include in this comparison data products from the polar-orbiting Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) systems. Our intercomparisons made in detail over specific Portuguese and Greek wildfires, and systematically across Africa and Europe, reveals four key findings: (1) FCI detects fire onset up to 4 h earlier than SEVIRI for the specific fires examined, and 2 h before MODIS and 4 h before VIIRS; (2) FCI generated 5 × more AF pixel detections than SEVIRI, due to a much reduced minimum FRP detection threshold (∼10 MW versus ∼40 MW) enabling the detection of the many AF pixels missed by SEVIRI; (3) FCI AF detection errors of omission were 38 % compared to MODIS centre-of-scan data, and 68 % compared to VIIRS, substantially improving on SEVIRI's 83 % and 89 % respectively; while commission errors compared to these two remained low at 12 % and 10 % respectively; (4) FCI FRP retrievals showed very strong agreement with the matching ones provided by MODIS (r² = 0.97, slope = 0.93). FCI offers detections every 10 min over the full disk, and 2.5 min over Europe when rapid-scan commences after launch of the second MTG Imagery platform. The results shown here suggest that the operational active fire data products based on FCI and planned to be issued from the EUMETSAT LSA SAF using the FTA algorithm should deliver a substantial improvement in satellite-based fire monitoring across Europe and Africa compared to the already successful products currently generated from MSG.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100366"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A spatio-temporal machine learning method for estimating high-resolution XCO2 in China","authors":"Fengxue Ruan ,&nbsp;Fen Qin ,&nbsp;Jie Li ,&nbsp;Weichen Mu","doi":"10.1016/j.srs.2025.100359","DOIUrl":"10.1016/j.srs.2025.100359","url":null,"abstract":"<div><div>Column-averaged dry air mole fraction of carbon dioxide (XCO₂) data is of great significance for addressing global climate change, monitoring carbon emissions. Currently, satellite XCO₂ exhibit significant spatial discontinuity, which makes it difficult to meet the needs of research at small spatial scales. Although machine learning methods have been widely used to fill the gaps in satellite XCO₂ data, mainstream methods are mostly data-driven mode, which, to some extent, limits the accuracy and generalization ability of the models. Given the limitations of existing studies in mining the spatiotemporal characteristics of XCO₂, this study innovatively proposes a new spatiotemporal XGBoost model (XGBKT) to generate high-resolution XCO₂ dataset covering the entire territory of China. This model focuses on the three major spatiotemporal characteristics of XCO₂, namely spatial correlation, temporal heterogeneity, and temporal periodicity. Through the spatiotemporal encoding strategy, these characteristics are skillfully transformed into features that the XGBoost model can efficiently utilize, thereby enabling the model to explore the spatiotemporal distribution pattern of XCO₂ and significantly improve its estimation accuracy and reliability. The research results indicate that: The XGBKT model significantly enhances the estimation performance and generalization ability of machine learning models, demonstrating clear advantages compared to mainstream machine learning methods; The XGBKT model validates the effectiveness of spatiotemporal characteristics, thereby further strengthening the interpretability of machine learning models. Overall, XGBKT is an effective method for accurately estimating XCO₂, providing a reliable data foundation for the fine-scale quantification of regional carbon cycling.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100359"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A frequency-based approach to improve the geometric accuracy of FY4B/AGRI geostationary satellite observations","authors":"Zhenduo Deng ,&nbsp;Xuanlong Ma","doi":"10.1016/j.srs.2025.100348","DOIUrl":"10.1016/j.srs.2025.100348","url":null,"abstract":"<div><div>The Advanced Geostationary Radiation Imager (AGRI) onboard the FengYun-4B (FY4B) satellite—a new-generation geostationary (GEO) platform—offers spatial and radiometric resolutions comparable to those of polar-orbiting satellites such as EOS-MODIS, but with substantially higher temporal resolution. This enhanced temporal capability expands the potential of GEO observations beyond meteorology into terrestrial sciences. Precise geometric accuracy is essential for quantitative remote sensing, as the reliability of any downstream retrieval algorithm depends on accurate geolocation. Operational correction of geometric errors is challenging due to the scarcity of ground control points and large data volumes. Here, we evaluated the geolocation accuracy of FY4B/AGRI imagery using a full year of data and developed an integrated geometric correction workflow combining the Phase-Only Correlation method based on Fast Fourier Transform (FFT-POC) with a ray-tracing orthorectification process. In the original imagery, significant geometric instabilities were observed: east-west offsets (COFF) frequently fluctuated between ±5 and ± 10 pixels (reaching ±15 pixels) due to diurnal thermal deformation and operational maneuvers, whereas north-south offsets (LOFF) remained comparatively stable within ±5 pixels. These systematic errors were fully corrected by the FFT-POC step, while the subsequent orthorectification effectively eliminated terrain-induced parallax distortions exceeding 3 pixels in high-altitude regions. The corrected FY4B/AGRI data offers accurate geolocation to support operational hyper-temporal applications such as disaster monitoring and carbon cycle sciences.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100348"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145750391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Satellite remote sensing for estimating reservoir physical characteristics: A global review of existing methodologies for operational monitoring","authors":"Audrey Kantz Dossou Codjia ,&nbsp;Komlavi Akpoti ,&nbsp;Moctar Dembélé ,&nbsp;Roland Yonaba ,&nbsp;Tazen Fowe ,&nbsp;Triumph Prosper Orowale ,&nbsp;Modeste G. Déo-Gratias Koissi ,&nbsp;Soumahila Sankande ,&nbsp;Sander J. Zwart","doi":"10.1016/j.srs.2026.100383","DOIUrl":"10.1016/j.srs.2026.100383","url":null,"abstract":"<div><div>Accurate and timely estimates of reservoir surface area, water level, and volume are essential for water resource management. Yet no recent synthesis compares the remote sensing methods used to obtain these physical characteristics. This study evaluates peer-reviewed studies from 2000 to 2025 that derived any of the three characteristics from satellite data to identify reliable techniques and operational gaps. A total of 169 cases of surface area mapping (88), water level retrieval (49), and volume estimation (32) were analyzed from 106 articles across more than 60 countries. Each case was classified according to its physical characteristics, approach, sensor, and validation method. Surface area is typically mapped using optical imagery (76 %). Threshold indices dominate at 63 %. Meanwhile, machine and deep learning methods are being used more frequently to provide more accurate classifications. Water levels are usually obtained from radar altimetry (67 %) followed by area-elevation models (30 %). Volume is most often computed using combined area-elevation approaches (60 %), followed by water level-volume regressions (25 %) and area-volume curves (15 %), with average errors of up to 10 %. Three critical gaps emerge: only 11 % of studies address reservoirs smaller than 1 km², turbid or vegetated waters incur estimation errors, and only a few studies use sensors with a revisit time of three days or less, which limits real-time management. Although fusion of several sensor data is demonstrably more accurate, it remains rare. These insights guide managers and future research directions to enable automated, high-resolution monitoring of both large and small reservoirs.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100383"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146187385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond spectral signals: Geographic features drive bathymetric accuracy in the turbid Sancha Lake using machine learning","authors":"Xiaojuan Li ,&nbsp;Wei Zhang ,&nbsp;Hongrui Zheng ,&nbsp;Zhongqiang Wu ,&nbsp;Hongliang Lu","doi":"10.1016/j.srs.2025.100355","DOIUrl":"10.1016/j.srs.2025.100355","url":null,"abstract":"<div><div>Accurate bathymetric mapping in inland water bodies presents significant challenges for conventional optical remote sensing due to complex water quality conditions and variable bottom types. This study introduces a novel Spectral-Geospatial XGBoost Regression (SG-XGBoost) model that revolutionizes depth estimation by integrating comprehensive spectral transformations with explicit geographic coordinates through gradient boosting methodology. Applied to Sancha Lake, a morphologically complex reservoir in China's Upper Yangtze watershed, the model achieved exceptional performance with R² = 0.91 and RMSE = 1.66m, representing 70 % improvement over traditional empirical methods (Stumpf, Log-Linear) and 21 % advancement beyond Random Forest. The iterative error correction and sophisticated regularization of the gradient boosting methodology not only enable the effective exploitation of spatial-spectral interactions but also ensure better accuracy is maintained across all depth ranges (2–31m). The feature importance analysis revealed an unexpected finding, the geographic coordinates dominated predictive power (85 % contribution), while spectral features contributed minimally, challenging fundamental assumptions about optical bathymetry. The iterative error correction and sophisticated regularization of the gradient boosting methodology not only enable the effective exploitation of spatial-spectral interactions but also ensure better accuracy is maintained across all depth ranges (2–31m). Bathymetric maps generated by SG-XGBoost successfully captured fine-scale morphological features invisible to conventional approaches, including channels &lt;30m wide and subtle depth variations of 1–2m. Despite limitations in extreme turbidity and site-specificity requiring readjustment for new water bodies, this research establishes gradient boosting with spatial-spectral integration as a transformative approach for inland water bathymetry, with broader implications for aquatic remote sensing applications including water quality monitoring and habitat mapping.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100355"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Four decades of remote sensing for monitoring terrestrial ecosystems: a global review and future challenges","authors":"Jose Manuel Álvarez-Martínez ,&nbsp;Tijana Nikolić Lugonja ,&nbsp;Alicia Valdés ,&nbsp;Jorge González Le Barbier ,&nbsp;Marta Pérez Suárez ,&nbsp;Gonzalo Hernández Romero ,&nbsp;Mirjana Radulović ,&nbsp;Maja Knežević ,&nbsp;Sonja Tarčak ,&nbsp;Branko Brkljač ,&nbsp;Bojana Bokić ,&nbsp;Boris Radak ,&nbsp;Andrijana Andrić ,&nbsp;Miljana Marković ,&nbsp;Sanja Brdar ,&nbsp;Predrag Lugonja ,&nbsp;Isidora Simović ,&nbsp;Lori Giagnacovo ,&nbsp;Borja Jiménez-Alfaro","doi":"10.1016/j.srs.2025.100341","DOIUrl":"10.1016/j.srs.2025.100341","url":null,"abstract":"<div><div>Remote sensing (RS) has evolved from occasional mapping to continuous, indicator-based monitoring of terrestrial ecosystems. This review synthesizes four decades of global progress in RS to characterize natural and semi-natural ecosystems, examining how study purposes, sensor types and analytical methods have diversified from 1985 to 2025. A systematic literature review of 6856 publications (1567 selected) documents the transition from expert-based visual interpretation using aerial photography and early Landsat missions, to harmonized, AI-driven workflows that enable scalable and replicable ecosystem assessments. Advances in cloud computing, data cubes and open-access archives now allow wall-to-wall time series of analyses across regions and biomes. Yet, important challenges persist, including the underrepresentation of biodiversity-rich areas, limited in-situ calibration data and uncertainties related to phenological variability, image correction or temporal mosaicking pipelines. Building on case studies from a global perspective, we outline design principles for policy-ready ecosystem indicators traceable to raw observations, comparable through time and space, and aligned with biodiversity policy frameworks. Integrating multi-sensor data (optical, radar, LiDAR, thermal), standardized in-situ observations and artificial intelligence/machine learning algorithms, RS provides a robust pathway towards operational ecosystem accounting and large-scale functional mapping and monitoring, strengthening conservation planning and ecosystem management worldwide.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100341"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145748183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Crop classification mapping in multi-cloud Regions: An integrated approach using GF-SG time series reconstruction and 3D deep convolutional networks","authors":"Sihan Xue ,&nbsp;Haibin Shi ,&nbsp;Xianyue Li ,&nbsp;Jianwen Yan ,&nbsp;Weigang Wang ,&nbsp;Qingfeng Miao ,&nbsp;Yan Yan ,&nbsp;Cong Hou ,&nbsp;Yi Zhao ,&nbsp;Xinlu Li","doi":"10.1016/j.srs.2025.100361","DOIUrl":"10.1016/j.srs.2025.100361","url":null,"abstract":"<div><div>Persistent cloud contamination severely affects optical satellite-based crop classification, creating critical gaps in phenological monitoring essential for food security. This study presents GS-3D FCN, a novel framework integrating Gap Filling-Savitzky-Golay (GF-SG) time series reconstruction with 3D Fully Convolutional Networks (3D FCN) for robust crop mapping under extreme cloud conditions. The method reconstructs cloud-contaminated pixels using GF-SG algorithm and leverages MODIS-Landsat fusion to generate continuous NDVI time series. These reconstructed layers are integrated as spectral-temporal dimensions into the 3D FCN architecture, enabling hierarchical extraction of crop phenological patterns. An enhanced Automatic Cloud Cover Assessment algorithm adaptively adjusts decision criteria to maximize valid pixel retention. To address severe class imbalance from cloud occlusion, we apply Synthetic Minority Over-sampling Technique with Gaussian Noise (SMOGN) combined with Cross-entropy loss Middle Supervision (CE-MidS) and Supervised Contrastive loss Middle Supervision (SupCon-MidS) intermediate supervision strategies, facilitating discriminative feature learning. Applied to the cloud-prone South Bank Yellow River irrigation area in Inner Mongolia, GS-3D FCN achieves 93.80 % overall accuracy across four sites. The framework demonstrates exceptional stability, maintaining 85.2 % accuracy at 80 % cloud coverage compared to 33.6–37.2 % accuracy degradation in traditional methods. The GF-SG component achieves RMSE of 0.0853 with edge preservation index of 0.0085. Analysis reveals the critical role of dataset balance in crop mapping under cloud interference. The proposed GS-3D FCN framework provides a simple and effective solution for crop mapping in cloud-prone areas. By integrating near-real-time NDVI data sources, the framework provides a feasible path for accurate crop monitoring in global continuous cloudy areas, and provides a new perspective for future research on the interaction between extreme climate and crop mapping.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100361"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel two-stage adversarial joint learning model for reconstructing InSAR phase in decorrelated areas","authors":"Mahmoud Abdallah ,&nbsp;Songbo Wu ,&nbsp;Xiaoli Ding","doi":"10.1016/j.srs.2026.100373","DOIUrl":"10.1016/j.srs.2026.100373","url":null,"abstract":"<div><div>Interferograms are basic observables of any Interferometric Synthetic Aperture Radar (InSAR) measurements. Interferometric decorrelation, however, often reduces the quality of interferograms, sometimes to an extent where no interferometric measurements can be properly carried out. Techniques such as applying a filter can help in reducing the impact of noise in interferograms but often cannot overcome the problem of decorrelation satisfactorily. This paper presents an approach based on a novel two-stage generative adversarial network (GAN) tailored for reconstructing interferometric phase values in decorrelated areas. The approach comprises an edge mapping stage (EMS) and a phase predicting stage (PPS). During the edge mapping stage, a pre-trained convolutional neural network (CNN) identifies fringe lines, while a GAN reconnects the discontinuous fringes. In the phase predicting stage, a second GAN uses the reconnected fringes as a guide to reconstruct the phase information. The model was trained on simulated datasets, achieving an overall accuracy (OA) of 84 % in fringe reconnection and a structural similarity index (SSIM) of 96 %. We validated the proposed model with real-world case studies, successfully reconstructing the phases of co-seismic deformation interferograms for the Tonopah, Nevada earthquake (M 6.5, May 15, 2020) and the Western Xizang earthquake (M 6.3, July 22, 2020). We also evaluated the adaptability of the proposed model using topographic mapping datasets. The experimental results achieved a cross-correlation range of 0.72–0.87 when reconstructing phase information over the Greater Bay Area (GBA) with fine-tuning, indicating potential applicability of the approach to a broader range of InSAR applications.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100373"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HCV-CVAE: A hierarchical convolutional variational transformer for thin cloud removal in remote sensing imagery","authors":"Yan Zhang ,&nbsp;Feng Han ,&nbsp;Juwei Xiang ,&nbsp;Jiwu Guan ,&nbsp;Song Wang","doi":"10.1016/j.srs.2026.100380","DOIUrl":"10.1016/j.srs.2026.100380","url":null,"abstract":"<div><div>To address the challenge faced by existing thin-cloud removal methods in balancing global structure reconstruction and local texture restoration under complex cloud conditions, this paper proposes a remote sensing image de-clouding approach based on a Hierarchical Convolutional Variational Vision Transformer (HCV-CVAE). Built upon the conventional CVAE framework, the proposed model introduces an HCV-ViT encoder that integrates the strengths of convolutional networks and Transformers to enhance local texture representation while capturing global semantic dependencies. Furthermore, strategies such as KL-divergence annealing, cross-dimensional weighted mutual information loss, and test-time augmentation are incorporated to improve the stability of the latent space and the robustness of the generation process. The proposed approach exhibits superior performance over existing algorithms on the RICE2 and T-Cloud datasets, with the highest PSNR and SSIM reaching 40.93 dB and 0.9872, respectively. The HCV-CVAE effectively restores fine details and spectral characteristics beneath clouds while maintaining global structural consistency, exhibiting significant advantages in both visual quality and quantitative metrics. All implementation code and pretrained models are publicly available at: <span><span>https://github.com/Kyperio/HCV-CVAE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"13 ","pages":"Article 100380"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}