2026· IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing· Vol 19, pp. 25248-25265· 0 citations· 77 references
Abstract
Monitoring glacier surface wetness and near-surface facies evolution with high spatiotemporal resolution is important for characterizing seasonal melt conditions and supporting downstream glaciological modeling. However, current remote sensing methods are hindered by cloud contamination in optical data and ambiguities in SAR backscatter interpretation. In this study, a novel framework for automated glacier surface-state mapping is proposed by integrating Sentinel-1 SAR and Sentinel-2 optical imagery. Pixel-wise wet snow probability maps are generated using a convolutional neural network trained on multitemporal optical data, which then guides an adaptive thresholding scheme for SAR-based wet snow detection. Finally, the wet snow maps are refined through a postprocessing scheme that leverages temporal consistency and spatial segmentation, and classification stability is significantly enhanced. The proposed algorithm is evaluated over three glaciers on the Tibetan Plateau using carefully constructed remote-sensing reference labels. The results show agreement with the reference labels, with mean F1-scores of 0.849 for Shenshe Glacier, 0.811 for Laohugou Glacier No.12, and 0.858 for Bayi Glacier, with peak values exceeding 0.93 during mid-season observations. The results also indicate relatively stable agreement under varying signal conditions. This study provides a flexible and transferable strategy for mapping wet-snow extent, wet-snow timing, and glacier surface facies evolution, which can provide useful constraints for subsequent mass-balance and runoff modelling in complex mountainous terrain.
Abstract. Accurate and timely land cover mapping in heterogeneous metropolitan environments remains a fundamental challenge in Earth observation, particularly under conditions where optical imagery is compromised by cloud cover or seasonal atmospheric interference. This study presents a systematic evaluation of four state-of-the-art machine learning algorithms Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and a shallow Artificial Neural Network (ANN) for pixel-based land cover classification over the Istanbul metropolitan region using single-date ALOS-2 PALSAR-2 L-band Synthetic Aperture Radar (SAR) imagery. The methodological framework integrates dual-polarimetric backscatter coefficients (HH and HV) with Grey-Level Co-occurrence Matrix (GLCM) texture features, Land Parcel Identification System (LPIS) boundaries for reference data delineation, Bayesian hyperparameter optimization, and LightGBM-guided Recursive Feature Elimination (RFE) to establish a reproducible and computationally efficient classification pipeline. Among all tested configurations, LightGBM achieved the highest overall accuracy (OA = 85.1%, κ = 0.81) with a 10-feature subset identified through RFE, while XGBoost demonstrated the strongest performance for urban class discrimination. Bayesian optimization yielded statistically meaningful improvements over default configurations for all gradient-boosting models. The optimal feature count was found to be ten, with HV-derived texture features particularly Entropy and Contrast identified as the most discriminative predictors. These results confirm that systematic feature engineering and algorithm tuning are as critical as classifier selection in SAR-based land cover mapping and lay the foundation for scalable operational workflows applicable to rapidly urbanizing regions.
Melih Altay, B. Tavus, Fatih Fehmi Şi̇mşek et al.· The International Archives o...· 0 citations
Optical vegetation and soil indices are widely used in Earth observation, although their estimation is strongly affected by cloud coverage and illumination variability. Synthetic-aperture radar (SAR) has therefore attracted increasing interest as an alternative source for spectral index prediction. Most existing studies focus on directly estimating a single index from SAR observations. In this work, we investigate a more flexible formulation in which Sentinel-2 multispectral bands are first reconstructed from Sentinel-1 SAR data and subsequently used to derive multiple spectral indices. Experiments are conducted on the SEN12TP dataset, exploiting near-synchronous paired Sentinel-1 and Sentinel-2 acquisitions together with auxiliary elevation and land-cover information. Three SAR-to-multispectral reconstruction strategies are compared, namely, Efficient-UNet, Pix2Pix, and a conditional flow matching model. The resulting indices are then evaluated against those obtained through dedicated index-specific reconstruction models. The results show that Efficient-UNet achieves the best overall multispectral reconstruction performance among the evaluated architectures. Moreover, indices derived from reconstructed multispectral bands achieve performance comparable to dedicated index-specific models while offering substantially greater flexibility, as multiple indices can be computed within a single framework without retraining task-specific models. At the same time, the experiments highlight important intrinsic limitations of SAR-based spectral reconstruction. Although the reconstructed products preserve the large-scale spatial organization of the scenes, they do not fully recover fine spectral and vegetation-sensitive details. Consequently, SAR-derived spectral indices should be regarded as approximate proxies of optical observations rather than direct substitutes, particularly in applications requiring accurate biophysical interpretation.
Mirko Paolo Barbato, Roberto Cilli, Paolo Napoletano et al.· Remote Sensing· 0 citations
Microwave scatterometers are capable of acquiring land surface backscattering coefficients day and night under all-weather conditions, offering advantages for snow cover monitoring. However, the relatively low spatial resolution of traditional scatterometer data limits their application in the fine-scale monitoring of snow cover distribution. To improve the spatial representation of snow cover and mitigate mixed-pixel effects in complex spring snowmelt scenarios, this study proposes an adaptive bilateral filtering scatterometer image reconstruction (SIR-ABF) algorithm based on the rotating fan-beam scanning characteristics of the FengYun-3E Wind Radar (FY-3E WindRAD). The Ku-band data of FY-3E WindRAD were reconstructed from the original 10 km resolution to an enhanced resolution of 3.125 km. Furthermore, by integrating the reconstructed scatterometer backscatter with multi-source auxiliary data, an optimal feature subset was determined through a feature selection strategy that considers both feature-label correlation and inter-feature multicollinearity. Finally, the best feature subset was combined with four machine learning (ML) models for snow cover classification. The results indicate that the Support Vector Machine (SVM) achieved the best performance, yielding an Overall Accuracy (OA), Macro-F1, and Kappa coefficient (Kc) of 91.64%, 86.47%, and 0.730, respectively. Compared with the snow cover classification results derived from the original 10 km Ku-band data, the 3.125 km reconstructed data provided more detailed spatial information and better characterized fragmented snow patches and snow transition boundaries. Further comparison with existing snow cover products demonstrated the spatial consistency and continuity of the proposed classification results, highlighting the potential of high-resolution scatterometer data for fine-scale snow cover monitoring during the spring snowmelt period in Northeast China.
Reliable monitoring of lake turbidity is often constrained by the trade-off between the spatial coverage of passive optical imagery and the vertical profiling capability of active LiDAR observations. This study proposes a multi-source retrieval framework integrating ICESat-2 ATL03 photon data with Sentinel-2 multispectral imagery for large-scale turbidity mapping in Lake Erie. An adaptive quadtree pruning strategy combined with Otsu thresholding was applied to isolate high-confidence surface water photons. Vertical distribution descriptors, including penetration depth and attenuation-related photon metrics, were quantified along 500-m segments. A Random Forest inversion model was established using these LiDAR-derived features, achieving an RMSE of 2.67 NTU. To overcome the spatial discontinuity of ICESat-2 tracks, the LiDAR-derived turbidity estimates were incorporated as virtual buoy constraints to calibrate temporally matched Sentinel-2 reflectance products. A Bayesian-optimized fusion framework was subsequently developed to generate spatially continuous turbidity fields. Validation results indicate that the synergistic model achieved an RMSE of 2.95 NTU, representing a 39% improvement over conventional optical-only retrieval methods. The proposed framework demonstrates the potential of cross-modal remote sensing synergy for large-scale inland water quality monitoring.
Rong He, Heng Chen, Guang-Hui Zhu· GEOINFORMATICS· 0 citations
Abstract. Timely and accurate detection of deforestation is essential for managing tropical forests, yet individual Earth observation sensors have inherent limitations. Multispectral imagery offers detailed spectral information on vegetation properties but is frequently hindered by cloud cover, while Synthetic Aperture Radar (SAR) imagery provides insights on vegetation structure independent of weather conditions but is sensitive to moisture variability and residual vegetation post-clearing. The complementary nature of these data has motivated multi-source fusion approaches, though most existing methods rely on offline processing or decision-level integration, limiting their real-time applicability. This study generalizes a Bayesian Online Changepoint Detection (BOCD) framework based on the recursive estimation of the number of acquisitions since the last change to asynchronous, irregularly sampled Sentinel-1 SAR and Sentinel-2 multispectral time series. A dynamically weighted fusion mechanism is implemented, in which each sensor’s relevance reduces with increasing time since its last observation, according to a physical decay model. The resulting method, named ms-BOCD, enables interpretable, and Near Real-Time (NRT) detection of forest loss. The ms-BOCD method is validated using MapBiomas Alerta reference data spanning deforestation polygons ranging from 0.1 to 50 hectares in the Brazilian Amazon. Compared to V H-BOCD (BOCD using Sentinel-1 cross-polarization only) and the operational RADD and TropiSCO systems, ms-BOCD achieves a ∼ 25% improvement in detection performance and maintains 13% fewer false alarms than Global Forest Watch (GFW), a platform that aggregates multiple independent deforestation alert products. Overall, these results demonstrate the strong potential of multi-source Bayesian fusion for operational tropical forest monitoring.
Marta Bottani, L. Ferro-Famil· ISPRS Annals of the Photogra...· 0 citations
Accurate characterization of flood dynamics in large river–lake systems remains challenging due to the difficulty of simultaneously capturing inundation extent and water surface elevation (WSE) variations under rapidly changing hydrological conditions. This study develops an integrated Synthetic Aperture Radar (SAR) and wide-swath interferometric altimetry framework to reconstruct the spatiotemporal evolution and storage dynamics of the 2024 flood event in the East Dongting Lake system, China. Sentinel-1 SAR imagery is utilized to derive high-resolution inundation extent, while the Surface Water and Ocean Topography (SWOT) mission, equipped with the Ka-band Radar Interferometer (KaRIn), provides two-dimensional WSE observations. To improve SAR-based flood extraction in heterogeneous floodplain environments, an Adaptive Spatially-Constrained Fuzzy C-Means (AS-FCM) algorithm is proposed by incorporating adaptive spatial regularization and structure-aware neighborhood weighting. Quantitative evaluation demonstrates that the proposed method achieves the highest performance among the evaluated conventional approaches, with an Overall Accuracy of 93.6%, an Intersection over Union of 0.89, and a Kappa coefficient of 0.87. The multi-temporal inundation sequence reveals a distinct flood evolution pattern characterized by rapid expansion during the rising stage and gradual recession during the post-peak period. SWOT-derived WSE observations exhibit strong agreement with synchronous in situ measurements after bias adjustment, with a correlation coefficient of 0.988. By integrating SAR-derived inundation extent with temporally matched water-level observations constrained by bias-adjusted SWOT and in situ gauge data, an empirical WSE–area relationship (R2=0.937) is established to reconstruct daily flood dynamics and estimate cumulative water storage variation. The results indicate that the East Dongting Lake floodplain played an important buffering role during the 2024 flood event, with cumulative storage variation reaching approximately 10.7km3 during the peak stage. Overall, the proposed framework demonstrates strong potential for flood monitoring and hydrological storage assessment in complex river–lake systems.
Yixuan Li, Yunhua Zhang, Dong Li et al.· Remote Sensing· 0 citations