Remote Sensing of Environment最新文献

{"title":"Assessment and intercomparison of 23 global satellite and model-based soil moisture products using cosmic ray neutron sensing observations over Europe","authors":"Pariha Helili ,&nbsp;Xiaojun Li ,&nbsp;Jean-Pierre Wigneron ,&nbsp;Gabrielle De Lannoy ,&nbsp;Jian Peng ,&nbsp;Frédéric Frappart ,&nbsp;Jiangyuan Zeng ,&nbsp;Yao Xiao ,&nbsp;L. Karthikeyan ,&nbsp;Patricia de Rosnay ,&nbsp;Zanpin Xing ,&nbsp;Ardeshir Ebtehaj ,&nbsp;Andreas Colliander ,&nbsp;Preethi Konkathi ,&nbsp;Ke Zhang ,&nbsp;Lei Fan","doi":"10.1016/j.rse.2025.115207","DOIUrl":"10.1016/j.rse.2025.115207","url":null,"abstract":"<div><div>Comprehensive evaluation of satellite and model-based soil moisture (SM) products is essential for their further development and application. With the advent of Cosmic Ray Neutron Sensing (CRNS), which has an observation radius of 130–240 m, the spatial representativeness mismatch between these grid-based SM products and ground single-point observations during the evaluation process can be feasibly relieved. In this study, we systematically evaluated 23 gridded SM products, including single-sensor satellite, multi-sensor merged, and model-based products, using 68 CRNS measurement sites across the Europe. Our evaluation revealed that the SMAP-INRAE-BORDEAUX (SMAP-IB) SM retrievals showed the superior consistency with CRNS measurements among all analyzed products, demonstrating both high correlation (<em>R</em> = 0.80) and low unbiased root mean square error (ubRMSE = 0.050 m³/m³). The CCI/C3S combined active-passive SM products ranked second in performance (<em>R</em> &gt; 0.75, ubRMSE &lt;0.060 m³/m³). In the bias analysis, 17 products had negative bias (−0.003 m³/m³ to −0.190 m³/m³) against CRNS measurements, while AMSR2-LPRM at C1 and C2 bands and CCI/C3S at active and passive products had positive bias (0.011 m³/m³ to 0.161 m³/m³). It was also found that the capabilities of all SM products retrievals degraded in terms of R and ubRMSE with increasing vegetation density, topographic complexity and soil wetness. Most products showed the lowest ubRMSE and highest R values in cropland compared to other land cover types. Our study emphasizes the substantial potential of cosmic field-scale SM observations for the validation of satellite- and model-based SM products, and our findings have the potential to advance algorithm refinement, product improvement, and hydrometeorological applications.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115207"},"PeriodicalIF":11.4,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated scan simultaneous trajectory enhancement and mapping (IS2-TEAM) for fine resolution forest inventory using backpack LiDAR","authors":"Chunxi Zhao ,&nbsp;Songlin Fei ,&nbsp;Ayman Habib","doi":"10.1016/j.rse.2025.115212","DOIUrl":"10.1016/j.rse.2025.115212","url":null,"abstract":"<div><div>Advancements in close-range remote sensing offer promises in automated forest inventory, facilitating sustainable forest management. Backpack LiDAR is a mobile mapping system that can be deployed for different applications, including forest inventory. However, under-canopy trajectories derived from backpacks equipped with GNSS units are often unreliable due to signal outages, resulting in degraded mapping results. To overcome this challenge, an Integrated Scan Simultaneous Trajectory Enhancement and Mapping (IS^{<strong>2</strong>}-TEAM) framework is proposed for fine-resolution forest inventory. For multi-beam spinning LiDAR, a single scan refers to points from a full revolution of the laser beam assembly, while an integrated scan combines multiple successive single scans. The framework introduces feature extraction strategies for defining reliable semantic features (tree trunk and ground) from integrated scans to enhance trajectory and mapping results. If available, the framework can incorporate a Digital Terrain Model (DTM) extracted from existing geospatial data to enhance georeferencing accuracy of backpack LiDAR. Finally, extracted features together with enhanced point cloud undergo a machine-learning post-processing strategy to evaluate the IS^{<strong>2</strong>}-TEAM's performance in tree detection and provide tree classification results based on maturity. The proposed approach has been thoroughly evaluated across multiple study sites with different forest types and terrain conditions. Through the experimental results, it has been shown that the IS^{<strong>2</strong>}-TEAM extracts reliable ground and tree trunk features and generates point clouds with alignment quality range of 2–4 cm. Furthermore, DTM-assisted IS²-TEAM significantly improves the georeferencing accuracy of the derived point cloud in forests with varying terrain conditions, achieving an average vertical accuracy improvement of 1 m across all test datasets. Finally, the proposed self-evaluation strategy successfully identifies all mature trees and achieves over 90 % accuracy in tree classification.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115212"},"PeriodicalIF":11.4,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leaf fall witnessed by night-time light: A first attempt to detect urban leaf fall dates using satellite nighttime light data","authors":"Liming Wang ,&nbsp;Yang Hu ,&nbsp;Xiaoyue Tan ,&nbsp;Zixuan Pei ,&nbsp;Xiaolin Zhu ,&nbsp;Jin Chen","doi":"10.1016/j.rse.2025.115211","DOIUrl":"10.1016/j.rse.2025.115211","url":null,"abstract":"<div><div>Autumn leaf fall is a critical phenological event in temperate deciduous forests, with important ecological and socioeconomic implications. Traditional estimates based on daytime vegetation indices primarily capture foliage color changes rather than the actual timing of leaf fall, and are often affected by mixed-pixel effects that reduce the accuracy. This study proposes a novel workflow for detecting the autumn leaf fall date (LFD) using nighttime light (NTL) data in urban areas, validated through in-situ observations from phenological cameras and city-scale assessments. Results showed that NTL-derived LFDs closely matched in-situ observations across three cities (New York City, Boston, and Beijing), with an RMSE of around 5 days and a bias of 0.77 days. In Beijing, both interannual (2012–2024) and spatial variations (2024) in LFD were delayed by higher preseason temperature and precipitation but advanced by greater strong-wind frequency, consistent with known autumn phenological controls and supporting the reliability of the NTL-based approach. These results demonstrate that NTL data can provide more accurate and interpretable LFD estimates than traditional daytime remote sensing, enabling detailed city-scale mapping. The use of NTL-derived LFD dynamics facilitates a more comprehensive understanding of their spatiotemporal patterns in urban environments and their linkages to climate change and human activities.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115211"},"PeriodicalIF":11.4,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gap-free GNSS-R wind field reconstruction: A neural mapping scheme and initial validation","authors":"Hao Du ,&nbsp;Ronan Fablet ,&nbsp;Thi Thuy Nga Nguyen ,&nbsp;Weiqiang Li ,&nbsp;Estel Cardellach ,&nbsp;Bertrand Chapron","doi":"10.1016/j.rse.2025.115218","DOIUrl":"10.1016/j.rse.2025.115218","url":null,"abstract":"<div><div>Spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) has been widely demonstrated as an effective method for ocean wind speed retrieval. This study explores the feasibility of using track-wise GNSS-R wind products to generate gap-free wind fields. A physics-informed neural mapping scheme, 4DVarNet, is adapted to reconstruct wind fields. Results indicate that the root mean square errors (RMSEs) of the 1-hour, 3-hour, and 6-hour 4DVarNet winds are 1.13 m/s, 1.16 m/s, and 1.24 m/s compared to European Center for Medium-Range Weather Forecast (ECMWF) ERA5 wind products, while 1.40 m/s, 1.41 m/s, and 1.48 m/s are referred to Advanced Microwave Scanning Radiometer-2 (AMSR2) all-weather winds. Spatial and temporal error analyses further confirm the robustness of 4DVarNet-derived winds, with daily RMSEs remaining below 1.6 m/s. Error decomposition reveals discrepancies between ECMWF and GNSS-R winds, which may support future recalibration of GNSS-R wind products or enhancements to ECMWF forecasts. A case study of Super Typhoon Surigae proves that 4DVarNet winds closely align with the International Best Track Archive for Climate Stewardship (IBTrACS) track data. The reconstructed winds detect the peak intensity temporally consistent with IBTrACS data, whereas ECMWF forecasts exhibit a two-day lag. Moreover, asymmetries in Tropical Storm Kompasu are observed, with the radius of maximum wind (<span><math><msub><mi>R</mi><mtext>max</mtext></msub></math></span>) over the Northeast quadrant 38% larger than that over the Northwest quadrant. Despite the absence of background wind field inputs, 4DVarNet effectively learns wind patterns from ECMWF data and integrates GNSS-R observations to generate gap-free wind mappings, exhibiting strong agreement with ECMWF wind fields. The reconstruction performance is degraded at high winds due to the underestimation of referenced ECMWF ERA5 winds and the small quantity of observations. This limitation could be alleviated through denser GNSS-R observations from multiple missions such as Fengyun-3, Tianmu-1, recently launched HydroGNSS, etc., and other training references with more high winds for improving the representation of 4DVarNet at high winds.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115218"},"PeriodicalIF":11.4,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 global intercomparison of SWOT and traditional nadir radar altimetry for monitoring river water surface elevation","authors":"Yue Xu ,&nbsp;Frédéric Frappart ,&nbsp;Guoqiang Tang ,&nbsp;Guoqing Zhang ,&nbsp;Peirong Lin ,&nbsp;Liguang Jiang ,&nbsp;Simon Papalexiou ,&nbsp;Fangfang Yao ,&nbsp;Xiaoran Han ,&nbsp;Jun Xia","doi":"10.1016/j.rse.2025.115219","DOIUrl":"10.1016/j.rse.2025.115219","url":null,"abstract":"<div><div>The water surface elevation (WSE) of rivers serves as fundamental data for various hydrological research and applications. The recently launched Surface Water and Ocean Topography (SWOT) satellite offers a revolutionary altimetry approach by providing wide-swath elevation mapping using a SAR Interferometer (InSAR) operating at Ka-band. While SWOT provides unprecedented spatio-temporal coverage of WSE, it has not been systematically compared with reference water stage databases. Currently, due to difficulties in accessing recent and globally homogenous gauge station records, established WSE derived from radar altimetry (RA) missions is the most suitable dataset to perform global validation of WSE. This study presents the first global-scale intercomparison of the two altimetry systems, the wide-swath InSAR technique used for the first time by SWOT and the classical along-track RA using the SAR technique, and identifies several representative factors influencing their consistency. SWOT WSE are compared with virtual stations derived from Sentinel-3 and Sentinel-6 missions, across five different node quality categories (“good”, “suspect”, “degraded”, “bad” and a combined “all” group without “bad” data). The analysis further examines the potential influences from river width, river ice, backscattering coefficients (sigma0), and dark water fraction in modulating data consistency. The root mean square error (and correlation coefficient) between WSE from SWOT and RA in “good” and “suspect” data are 0.80 m (0.85) and 1.62 m (0.78), respectively, while those for “degraded” and “bad” data rise significantly to 8.80 m (0.60) and 16.91 m (0.50). The combined “all” category yields an overall <em>RMSE</em> (<em>CC</em>) of 5.15 m (0.65). For rivers wider than 160 m, SWOT measurements with “good” and “suspect” quality demonstrate notably improved consistency with RA compared to narrower rivers. Under frozen conditions, the reduced consistency between SWOT and RA is most evident in the “degraded” and “bad” quality data, with average reductions in <em>CC</em> of 0.17 and 0.21, respectively. In addition, radar backscatter strongly impacts the quality of SWOT-based WSE, as both extremely low values (dark water) and very high values (specular ringing) can lead to unrealistic estimates. Overall, this study offers important insights into the global performance of SWOT-based WSE estimation and informs the future refinement and application of SWOT data in hydrological research.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115219"},"PeriodicalIF":11.4,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating classifier transfer and sample transfer strategies for in-season crop mapping based on sample weighting technique","authors":"Yunze Zang ,&nbsp;Junxiong Zhou ,&nbsp;Xuehong Chen ,&nbsp;Tianyu Liu ,&nbsp;Miaogen Shen ,&nbsp;Wei Yang ,&nbsp;Xiufang Zhu ,&nbsp;Fei Zhang ,&nbsp;Jin Chen","doi":"10.1016/j.rse.2025.115208","DOIUrl":"10.1016/j.rse.2025.115208","url":null,"abstract":"<div><div>Timely crop mapping is crucial for field management, policy formulation, phenological monitoring, and yield forecasting. However, acquiring sufficient labeled samples in the current year presents a formidable challenge for in-season mapping. Previously proposed solutions mainly include classifier transfer and sample transfer strategies. The classifier transfer strategy trains classifiers with historical samples associated with historical-year features and then transfers the trained historical sample classifiers (HSC) to classify remote sensing data in the current year; the sample transfer strategy generates trusted samples associated with current-year remote sensing features by predicting labels of the current-year sample based on some prior knowledge (e.g., crop rotation pattern) and then trains trusted sample classifiers (TSC) for current-year classification. However, the performance of the classifier-transfer strategy may degrade when there is large interannual feature variation, while the performance of the sample-transfer strategy depends on the reliability of the generated trusted samples. This study proposes a novel approach that integrates the above two strategies for in-season mapping through a sample weighting technique. Firstly, two sample sets, trusted samples and classified samples associated with current-year features, are generated by crop rotation prediction and HSC, respectively. Subsequently, based on an independent assumption between the rotational prediction errors and the current-year remote sensing features, the optimal weights of these two sample sets are derived based on the Bayesian principle. Finally, an optimal weighted sample classifier (OWSC) is trained using the weighted samples for in-season classification. To illustrate the robustness of the proposed OWSC, we compared it with different methods combined with various classification models across four regions with different interannual feature variation and crop rotation stability. Results demonstrated that OWSC maintained its advantages across various regions and different available lengths of historical crop-type sequences. Owing to its independence from specific classifiers, the proposed sample weighting method can be seamlessly applied to any classification model and thus continues to benefit from advances in classification algorithms. Additionally, sensitivity experiments regarding the uncertainty in trusted samples and historical crop-type sequences showed that OWSC performed stably across different scenarios. Therefore, OWSC provides a promising solution for in-season crop mapping without current-year samples.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115208"},"PeriodicalIF":11.4,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Delta-X: An airborne remote sensing framework to calibrate hydrodynamic and ecogeomorphic processes responsible for land building in coastal deltas","authors":"Marc Simard ,&nbsp;Cathleen E. Jones ,&nbsp;Robert R. Twilley ,&nbsp;Edward Castañeda-Moya ,&nbsp;Sergio Fagherazzi ,&nbsp;Cédric G. Fichot ,&nbsp;Michael P. Lamb ,&nbsp;Paola Passalacqua ,&nbsp;Tamlin M. Pavelsky ,&nbsp;David R. Thompson ,&nbsp;Saoussen Belhadj-aissa ,&nbsp;Pradipta Biswas ,&nbsp;Alexandra Christensen ,&nbsp;Luca Cortese ,&nbsp;Michael Denbina ,&nbsp;Carmine Donatelli ,&nbsp;Sarah Flores ,&nbsp;Andy Fontenot ,&nbsp;Joshua P. Harringmeyer ,&nbsp;Daniel Jensen ,&nbsp;Yang Zheng","doi":"10.1016/j.rse.2025.115201","DOIUrl":"10.1016/j.rse.2025.115201","url":null,"abstract":"<div><div>Coastal river deltas are highly dynamic regions with hydrological processes that vary on hourly, daily, and seasonal timescales. Soil formation in deltas relies on the balance between mineral sediment deposition, erosion, and organic matter production, which are intricately controlled by vegetation and hydrodynamic conditions. The spatial complexity and rapid variations in flow, particularly due to tides, present a major challenge to spaceborne remote sensing achieving the required spatial resolution and temporal sampling. Here, we present an airborne remote sensing and in situ framework that measures parameters that are critical to calibrate and validate hydrodynamic, sediment transport, morphodynamic, and ecogeomorphic models. We discuss the measurements and models within the context of the NASA Earth Venture-Suborbital Delta-X mission, which implemented the framework in two deltaic regions of the Mississippi River Delta with contrasting hydrological regimes, namely the Atchafalaya (i.e., active, river-dominated) and Terrebonne (inactive, river-abandoned) basins that are undergoing land gain and land loss, respectively. The Delta-X framework uses two airborne radar instruments to monitor hydrodynamic processes, measuring water surface level and slope within channels, and tide-induced water level change within wetlands. In addition, an airborne imaging spectrometer provides estimates of suspended sediment concentrations in open water as well as vegetation type and aboveground biomass. We also discuss how the data are used to calibrate and validate the models that estimate sediment deposition and organic soil production, which build land to offset subsidence and sea level rise.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115201"},"PeriodicalIF":11.4,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emulation-based self-supervised SIF retrieval in the O2-A absorption band with HyPlant","authors":"Jim Buffat ,&nbsp;Miguel Pato ,&nbsp;Kevin Alonso ,&nbsp;Stefan Auer ,&nbsp;Emiliano Carmona ,&nbsp;Stefan Maier ,&nbsp;Rupert Müller ,&nbsp;Patrick Rademske ,&nbsp;Uwe Rascher ,&nbsp;Hanno Scharr","doi":"10.1016/j.rse.2025.115203","DOIUrl":"10.1016/j.rse.2025.115203","url":null,"abstract":"<div><div>The retrieval of sun-induced fluorescence (SIF) from hyperspectral imagery requires accurate atmospheric compensation to correctly disentangle its small contribution to the at-sensor radiance from other confounding factors. In spectral fitting SIF retrieval approaches this compensation is estimated in a joint optimization of free variables when fitting the measured at-sensor signal. Due to the computational complexity of Radiative Transfer Models (RTMs) that satisfy the level of precision required for accurate SIF retrieval, fully joint estimations are practically unachievable with exact physical simulation. We present in this contribution an emulator-based spectral fitting method neural network (EmSFMNN) approach integrating RTM emulation and self-supervised training for computationally efficient and accurate SIF retrieval in the O₂-A absorption band of HyPlant imagery. In a validation study with in-situ top-of-canopy SIF measurements we find improved performance over traditional retrieval methods. Furthermore, we show that the model predicts plausible SIF emission in topographically variable terrain without scene-specific adaptations. Since EmSFMNN can be adapted to hyperspectral imaging sensors in a straightforward fashion, it may prove to be an interesting SIF retrieval method for other sensors on airborne and spaceborne platforms.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115203"},"PeriodicalIF":11.4,"publicationDate":"2025-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised representation learning for cloud detection using Sentinel-2 images","authors":"Yawogan Jean Eudes Gbodjo ,&nbsp;Lloyd Haydn Hughes ,&nbsp;Matthieu Molinier ,&nbsp;Devis Tuia ,&nbsp;Jun Li","doi":"10.1016/j.rse.2025.115205","DOIUrl":"10.1016/j.rse.2025.115205","url":null,"abstract":"<div><div>The unavoidable presence of clouds and their shadows in optical satellite imagery hinders the true spectral response of the Earth’s underlying surface. Accurate cloud and cloud shadow detection is therefore a crucial preprocessing step for optical satellite images and any downstream analysis. Various methods have been developed to address this critical task and can be broadly categorized into physical rule-based methods and learning based methods. In recent years, machine learning based methods, particularly deep learning frameworks, have proven to outperform physical rule-based models. However, these approaches are mostly fully supervised and require a large amount of pixel-level annotations whose acquisition is costly and time consuming. In this work, we propose to address cloud and cloud shadow detection in optical satellite images using self-supervised representation learning, a machine learning paradigm that focuses on extracting relevant representations from unlabeled data, which can then be used as an effective starting point to fine-tune models with few labeled data in a supervised fashion. These approaches have been shown to perform competitively with fully supervised methods without the requirement of large annotation datasets. Specifically, we assessed two self-supervised representation learning methods that use different philosophies about self-supervision: Momentum Contrast (MoCo), based on contrastive learning and DeepCluster, based on clustering. Using two publicly available Sentinel-2 cloud datasets, namely WHUS2–CD+ and CloudSEN12, we show that MoCo and DeepCluster, trained with only 25 % of the annotated data, can perform better than physical rule-based methods such as FMask and Sen2Cor, weakly supervised methods and even several fully supervised methods. These results highlight the strong applicability of self-supervised representation learning methods to the task of cloud and cloud shadow detection with self-supervised pretraining leading to fine-tuned models that outperform industry standards and achieve near state-of-the-art performance with a fraction of the data.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115205"},"PeriodicalIF":11.4,"publicationDate":"2025-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An integrated atmospheric-topographic correction framework for land surface reflectance estimation using a spatial-spectral Attention U-Net model","authors":"Yichuan Ma ,&nbsp;Shunlin Liang ,&nbsp;Han Ma ,&nbsp;Tao He ,&nbsp;Xiran Shi ,&nbsp;Wenyuan Li ,&nbsp;Dejun Cai ,&nbsp;Xiongxin Xiao ,&nbsp;Shikang Guan ,&nbsp;Weiwei Liu ,&nbsp;Jianglei Xu ,&nbsp;Yongzhe Chen ,&nbsp;Yuxiang Zhang","doi":"10.1016/j.rse.2025.115188","DOIUrl":"10.1016/j.rse.2025.115188","url":null,"abstract":"<div><div>Surface reflectance, a fundamental parameter for deriving high-level satellite products, is typically obtained through atmospheric correction. However, in rugged terrains, topographic effects substantially distort surface reflectance estimates. Many post-topographic correction methods for surface reflectance were proposed and applied to mitigate topographic effects. However, the coupled atmospheric and topographic influences in radiative transfer processes cause significant errors when these corrections are performed separately. For example, we observed over 50 % of pixels in the official Landsat 8 surface reflectance data across a complex terrain exhibited physically implausible negative values, predominantly in shadowed areas. Moreover, traditional pixel-by-pixel methods failed to leverage valuable spatial information for estimation. To address these limitations, we developed an integrated atmospheric and topographic correction framework, Unet-TopoFlat, leveraging a spatial-spectral Attention U-Net algorithm and a novel pseudo-topographic synthetic strategy. The pseudo-topographic synthetic strategy generated sufficient and robust topographically incorporated TOA radiance samples across different terrains, surfaces, and atmospheric conditions, using surface reflectance over flat terrains based on radiative transfer models, atmospheric parameters, random forest regression, and a mountainous radiative transfer parameterization scheme. Using Landsat 8 data as a proxy for evaluation, the Unet-TopoFlat was trained on 47,398 samples (256 × 256 pixels), leveraging multiple datasets. The Unet-TopoFlat model effectively captured the spatial and spectral relationships between TOA radiance and surface reflectance, achieving a relative root mean square error (rRMSE) of 4.5 %–6.2 % across 20,314 samples spanning different terrain, temporal, and spectral bands. Compared to the baseline Unet-FLAT model, which lacked topographic consideration and exhibited substantial uncertainties, Unet-TopoFlat effectively reduced topographic effects, lowering negative reflectance ratios from 55.5 % to 2.8 % while accurately recovering surface information and preserving spectral information. Moreover, the leaf area index (LAI) and snow cover mapping using our estimated surface reflectance were superior to those using official products, and deviations reached up to 2.4 for LAI and 8 % for snow cover mapping at the regional scale. Our proposed framework is not sensor-specific and can be potentially applied to multiple optical remotely sensed data.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"334 ","pages":"Article 115188"},"PeriodicalIF":11.4,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}