Remote Sensing

25 pages, 2199 KB

Open AccessArticle

Comparative Assessment of Hyperspectral and Multispectral Vegetation Indices for Estimating Fire Severity in Mediterranean Ecosystems

by José Alberto Cipra-Rodriguez, José Manuel Fernández-Guisuraga and Carmen Quintano

Remote Sens. 2026, 18(2), 244; https://doi.org/10.3390/rs18020244 - 12 Jan 2026

Abstract

Assessing post-fire disturbance in Mediterranean ecosystems is essential for quantifying ecological impacts and guiding restoration strategies. This study evaluates fire severity following an extreme wildfire event (~28,000 ha) in northwestern Spain using vegetation indices (VIs) derived from PRISMA hyperspectral imagery, validated against field-based [...] Read more.

Assessing post-fire disturbance in Mediterranean ecosystems is essential for quantifying ecological impacts and guiding restoration strategies. This study evaluates fire severity following an extreme wildfire event (~28,000 ha) in northwestern Spain using vegetation indices (VIs) derived from PRISMA hyperspectral imagery, validated against field-based Composite Burn Index (CBI) measurements at the vegetation, soil, and site levels across three vegetation formations (coniferous forests, broadleaf forests, and shrublands). Hyperspectral VIs were benchmarked against multispectral VIs derived from Sentinel-2. Hyperspectral VIs yielded stronger correlations with CBI values than multispectral VIs. Vegetation-level CBI showed the highest correlations, reflecting the sensitivity of most VIs to canopy structural and compositional changes. Indices incorporating red-edge, near-infrared (NIR), and shortwave infrared (SWIR) bands demonstrated the greatest explanatory power. Among hyperspectral indices, DVIRED, EVI, and especially CAI performed best. For multispectral data, NDRE, CIREDGE, ENDVI, and GNDVI were the most effective. These findings highlight the strong potential of hyperspectral remote sensing for accurate, scalable post-fire severity assessment in heterogeneous Mediterranean ecosystems. Full article

(This article belongs to the Section Forest Remote Sensing)

54 pages, 2957 KB

Open AccessReview

Mamba for Remote Sensing: Architectures, Hybrid Paradigms, and Future Directions

by Zefeng Li, Long Zhao, Yihang Lu, Yue Ma and Guoqing Li

Remote Sens. 2026, 18(2), 243; https://doi.org/10.3390/rs18020243 - 12 Jan 2026

Abstract

Modern Earth observation combines high spatial resolution, wide swath, and dense temporal sampling, producing image grids and sequences far beyond the regime of standard vision benchmarks. Convolutional networks remain strong baselines but struggle to aggregate kilometre-scale context and long temporal dependencies without heavy [...] Read more.

Modern Earth observation combines high spatial resolution, wide swath, and dense temporal sampling, producing image grids and sequences far beyond the regime of standard vision benchmarks. Convolutional networks remain strong baselines but struggle to aggregate kilometre-scale context and long temporal dependencies without heavy tiling and downsampling, while Transformers incur quadratic costs in token count and often rely on aggressive patching or windowing. Recently proposed visual state-space models, typified by Mamba, offer linear-time sequence processing with selective recurrence and have therefore attracted rapid interest in remote sensing. This survey analyses how far that promise is realised in practice. We first review the theoretical substrates of state-space models and the role of scanning and serialization when mapping two- and three-dimensional EO data onto one-dimensional sequences. A taxonomy of scan paths and architectural hybrids is then developed, covering centre-focused and geometry-aware trajectories, CNN– and Transformer–Mamba backbones, and multimodal designs for hyperspectral, multisource fusion, segmentation, detection, restoration, and domain-specific scientific applications. Building on this evidence, we delineate the task regimes in which Mamba is empirically warranted—very long sequences, large tiles, or complex degradations—and those in which simpler operators or conventional attention remain competitive. Finally, we discuss green computing, numerical stability, and reproducibility, and outline directions for physics-informed state-space models and remote-sensing-specific foundation architectures. Overall, the survey argues that Mamba should be used as a targeted, scan-aware component in EO pipelines rather than a drop-in replacement for existing backbones, and aims to provide concrete design principles for future remote sensing research and operational practice. Full article

(This article belongs to the Section AI Remote Sensing)

29 pages, 2009 KB

Open AccessArticle

GCN-Embedding Swin–Unet for Forest Remote Sensing Image Semantic Segmentation

by Pingbo Liu, Gui Zhang and Jianzhong Li

Remote Sens. 2026, 18(2), 242; https://doi.org/10.3390/rs18020242 - 12 Jan 2026

Abstract

Forest resources are among the most important ecosystems on the earth. The semantic segmentation and accurate positioning of ground objects in forest remote sensing (RS) imagery are crucial to the emergency treatment of forest natural disasters, especially forest fires. Currently, most existing methods [...] Read more.

Forest resources are among the most important ecosystems on the earth. The semantic segmentation and accurate positioning of ground objects in forest remote sensing (RS) imagery are crucial to the emergency treatment of forest natural disasters, especially forest fires. Currently, most existing methods for image semantic segmentation are built upon convolutional neural networks (CNNs). Nevertheless, these techniques face difficulties in directly accessing global contextual information and accurately detecting geometric transformations within the image’s target regions. This limitation stems from the inherent locality of convolution operations, which are restricted to processing data structured in Euclidean space and confined to square-shaped regions. Inspired by the graph convolution network (GCN) with robust capabilities in processing irregular and complex targets, as well as Swin Transformers renowned for exceptional global context modeling, we present a hybrid semantic segmentation framework for forest RS imagery termed GSwin–Unet. This framework embeds the GCN model into Swin–Unet architecture to address the issue of low semantic segmentation accuracy of RS imagery in forest scenarios, which is caused by the complex texture features, diverse shapes, and unclear boundaries of land objects. GSwin–Unet features a parallel dual-encoder architecture of GCN and Swin Transformer. First, we integrate the Zero-DCE (Zero-Reference Deep Curve Estimation) algorithm into GSwin–Unet to enhance forest RS image feature representation. Second, a feature aggregation module (FAM) is proposed to bridge the dual encoders by fusing GCN-derived local aggregated features with Swin Transformer-extracted features. Our study demonstrates that, compared with the baseline models TransUnet, Swin–Unet, Unet, and DeepLab V3+, the GSwin–Unet achieves improvements of 7.07%, 5.12%, 8.94%, and 2.69% in the mean Intersection over Union (MIoU) and 3.19%, 1.72%, 4.3%, and 3.69% in the average F1 score (Ave.F1), respectively, on the RGB forest RS dataset. On the NIRGB forest RS dataset, the improvements in MIoU are 5.75%, 3.38%, 6.79%, and 2.44%, and the improvements in Ave.F1 are 4.02%, 2.38%, 4.72%, and 1.67%, respectively. Meanwhile, GSwin–Unet shows excellent adaptability on the selected GID dataset with high forest coverage, where the MIoU and Ave.F1 reach 72.92% and 84.3%, respectively. Full article

31 pages, 5199 KB

Open AccessArticle

A Comparison of Self-Supervised and Supervised Deep Learning Approaches in Floating Marine Litter and Other Types of Sea-Surface Anomalies Detection

by Olga Bilousova, Mikhail Krinitskiy, Maria Pogojeva, Viktoriia Spirina and Polina Krivoshlyk

Remote Sens. 2026, 18(2), 241; https://doi.org/10.3390/rs18020241 - 12 Jan 2026

Abstract

Monitoring marine litter in the Arctic is crucial for environmental assessment, yet automated methods are needed to process large volumes of visual data. This study develops and compares two distinct machine learning approaches to automatically detect floating marine litter, birds, and other anomalies [...] Read more.

Monitoring marine litter in the Arctic is crucial for environmental assessment, yet automated methods are needed to process large volumes of visual data. This study develops and compares two distinct machine learning approaches to automatically detect floating marine litter, birds, and other anomalies from ship-based optical imagery captured in the Barents and Kara seas. We evaluated a supervised Visual Object Detection (VOD) model (YOLOv11) against a self-supervised classification approach that combines a Momentum Contrast (MoCo) framework with a ResNet50 backbone and a CatBoost classifier. Both methods were trained and tested on a dataset of approximately 10,000 manually annotated sea surface images. Our findings reveal a significant performance trade-off between the two techniques. The YOLOv11 model excelled in detecting clearly visible objects like birds with an F1-score of 73%, compared to 67% for the classification method. However, for the primary and more challenging task of identifying marine litter, which demonstrates less clear visual representation in optical imagery, the self-supervised approach was substantially more effective, achieving a 40% F1-score, versus the 10% obtained for the VOD model. This study demonstrates that, while standard object detectors are effective for distinct objects, self-supervised learning strategies can offer a more robust solution for detecting less-defined targets like marine litter in complex sea-surface imagery. Full article

(This article belongs to the Section Ocean Remote Sensing)

30 pages, 10813 KB

Open AccessArticle

A Filter Method for Vehicle-Based Moving LiDAR Point Cloud Data for Removing IRI-Insensitive Components of Longitudinal Profile

by Guoqing Zhou, Hanwen Gao, Yufu Cai, Jiahao Guo and Xuesong Zhao

Remote Sens. 2026, 18(2), 240; https://doi.org/10.3390/rs18020240 - 12 Jan 2026

Abstract

The International Roughness Index (IRI) is calculated from elevation profiles acquired by high-speed profilers or laser scanners, but these raw data often contain measurement noise and extraneous wavelength components that can degrade the accuracy of IRI calculations. Existing filtering methods expose a limitation [...] Read more.

The International Roughness Index (IRI) is calculated from elevation profiles acquired by high-speed profilers or laser scanners, but these raw data often contain measurement noise and extraneous wavelength components that can degrade the accuracy of IRI calculations. Existing filtering methods expose a limitation in removing IRI-insensitive wavelength components. Thus, this paper proposes a Gaussian filtering algorithm based on the Nyquist sampling theorem to remove IRI-insensitive components of the longitudinal profile. The proposed approach first adaptively determines Gaussian template lengths according to sampling intervals, and then incorporates a boundary padding strategy to ensure processing stability. The proposed method enables precise wavelength selection within the IRI-sensitive band of 1.3–29.4 m while maintaining computational efficiency. The method was validated using the Paris–Lille dataset and the U.S. Long-Term Pavement Performance (LTPP) program dataset. The filtered profiles were evaluated by Power Spectral Density (PSD), and IRI values were calculated and compared with those obtained by conventional profile filtering methods. The results show that the proposed method is effective in removing the non-sensitive components of IRI and obtaining highly accurate IRI values. Compared with the standard IRI provided by the LTPP dataset, mean absolute error of the IRI values from the proposed method reaches 0.051 m/km, and mean relative error is less than 4%. These findings indicate that the proposed method improves the reliability of IRI calculation. Full article

(This article belongs to the Section Urban Remote Sensing)

► Show Figures

Figure 1

19 pages, 7475 KB

Open AccessArticle

Coseismic Slip and Early Postseismic Deformation Characteristics of the 2025 Mw 7.0 Dingri Earthquake

by Di Liang, Yi Xu, Qing Ding, Chuanzeng Shu, Xiaoping Zhang, Yun Qin, Weiqi Wu and Zhiguo Meng

Remote Sens. 2026, 18(2), 239; https://doi.org/10.3390/rs18020239 - 12 Jan 2026

Abstract

On 7 January 2025, an Mw 7.0 earthquake struck Dingri County, Shigatse, Tibet. This was the largest event in the region in recent years. Analysis of the Dingri earthquake is urgent for understanding the coseismic slip and early postseismic deformation characteristics. In this [...] Read more.

On 7 January 2025, an Mw 7.0 earthquake struck Dingri County, Shigatse, Tibet. This was the largest event in the region in recent years. Analysis of the Dingri earthquake is urgent for understanding the coseismic slip and early postseismic deformation characteristics. In this study, the coseismic characteristics were analyzed by using Lutan-1 and Sentinel-1 data with the Differential Interferometric Synthetic Aperture Radar method, and then the Okada elastic half-space dislocation model was used to invert the coseismic slip distribution of the seismogenic fault. The postseismic characteristics were analyzed by Sentinel-1 ascending and descending orbits, then time-series deformation results were obtained with the Small Baseline Subset InSAR method. The main results are as follows: (1) The maximum coseismic subsidence is −2.03 m and the maximum coseismic uplift is 0.68 m, the coseismic deformation is concentrated on the west side of the new rupture trace generated by the coseismic events; (2) the ruptured fault is dominated by normal faulting with a minor strike-slip component, and the slip is mainly distributed at depths of 0–15 km, with a maximum slip of about 3.97 m; (3) the deformation characteristics of the fault in the postseismic stage are basically consistent with those during the coseismic stage. The research results play an important role in understanding the earthquake fault tectonic activities. Full article

(This article belongs to the Special Issue Advances of Active and Passive Seismic and Remote Sensing for Subsurface Characterization)

► Show Figures

Figure 1

20 pages, 3463 KB

Open AccessArticle

Deep-Learning Spatial and Temporal Fusion Model for Land Surface Temperature Based on a Spatially Adaptive Feature and Temperature-Adaptive Correction Module

by Chenhao Jin, Jiasheng Li and Yao Shen

Remote Sens. 2026, 18(2), 238; https://doi.org/10.3390/rs18020238 - 12 Jan 2026

Abstract

Land surface temperature (LST) is essential for studying land–atmosphere energy exchange, the impact of climate change, and its influence on crop yields and hydrology. Although satellite remote sensing provides large-scale LST data, existing spatiotemporal fusion methods face challenges. Traditional algorithms have difficulty with [...] Read more.

Land surface temperature (LST) is essential for studying land–atmosphere energy exchange, the impact of climate change, and its influence on crop yields and hydrology. Although satellite remote sensing provides large-scale LST data, existing spatiotemporal fusion methods face challenges. Traditional algorithms have difficulty with heterogeneous surfaces, and deep-learning models often produce blurred details and inaccurate temperatures, which limits their use in high-precision applications. This study addresses these issues by developing a Deep-Learning Spatial and Temporal Fusion Model (DLSTFM) for Landsat-8 and MODIS LST imagery in Griffith, Australia. DLSTFM employs a dual-branch structure: one branch is dedicated to dual-temporal fusion, and the other branch is dedicated to multi-source feature fusion. Key innovations include the Spatial Adaptive Feature Modulation (SAFM) module, which performs adaptive multi-scale feature fusion, and the Temperature Adaptive Correction Module (TCM), which makes pixel-wise adjustments using reference data. Experiments demonstrate that DLSTFM significantly outperforms traditional methods and existing deep-learning fusion methods. DLSTFM achieves clearer surface features and a mean absolute temperature error of approximately 2.1 K. The model also demonstrated excellent generalization performance in another test area (Ardiethan) without retraining, showcasing its substantial practical value for high-accuracy LST fusion. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

28 pages, 89053 KB

Open AccessTechnical Note

Retrieval of Sea Ice Concentration and Thickness During the Arctic Freezing Period from Tianmu-1 Based on Machine Learning

by Xin Xu, Lijian Shi, Bin Zou, Peng Ren, Yingni Shi, Tao Zeng, Xiaoqing Lu, Qi Tang, Shuhan Hu, Shiyuan Qiu, Jiahua Li, Yilin Liu, Xin Liu and Zongqiang Liu

Remote Sens. 2026, 18(2), 237; https://doi.org/10.3390/rs18020237 - 11 Jan 2026

Abstract

Sea ice concentration (SIC) and thickness (SIT) are critical variables for polar research. In this study, the potential of Tianmu-1 GNSS-R observations for retrieving Arctic SIC and SIT is explored using machine learning algorithms. XGBoost demonstrated superior accuracy and efficiency in the comparison [...] Read more.

Sea ice concentration (SIC) and thickness (SIT) are critical variables for polar research. In this study, the potential of Tianmu-1 GNSS-R observations for retrieving Arctic SIC and SIT is explored using machine learning algorithms. XGBoost demonstrated superior accuracy and efficiency in the comparison of the three methods. For SIC retrieval, 14 parameters from Tianmu-1 were employed directly, whereas SIT retrieval incorporated additional auxiliary parameters, including SIC, sea ice salinity (S), and temperature (T). Among the different GNSS systems, GLO achieved the lowest RMSE for SIC, at 7.750%, whereas GAL performed comparatively poorly, with an RMSE of 10.475%. In SIT retrieval, the GPS and BDS yielded the smallest RMSE values of 0.276 m and 0.278 m, respectively, while GLO resulted in a slightly higher RMSE of 0.309 m. Daily retrievals of both the SIC and SIT were conducted from 18 October 2023 to 12 April 2024, with consistently stable evaluation metrics throughout the freezing season. In high-concentration regions, the retrieved SIC and SIT closely matched the reference data, whereas larger errors occurred in marginal ice zones and coastal areas. This study reveals the potential of Tianmu-1 to complement existing satellite missions in Arctic sea ice monitoring during the freezing period. Full article

(This article belongs to the Special Issue Tianmu-1 Constellation: Advancements in Atmospheric, Ionospheric and Surface Remote Sensing Using GNSS-RO and GNSS-R)

35 pages, 5524 KB

Open AccessArticle

Multi-Module Collaborative Optimization for SAR Image Aircraft Recognition: The SAR-YOLOv8l-ADE Network

by Xing Wang, Wen Hong, Qi Li, Yunqing Liu, Qiong Zhang and Ping Xin

Remote Sens. 2026, 18(2), 236; https://doi.org/10.3390/rs18020236 - 11 Jan 2026

Abstract

As a core node of the air transportation network, airports rely on aircraft model identification as a key link to support the development of smart aviation. Synthetic Aperture Radar (SAR), with its strong-penetration imaging capabilities, provides high-quality data support for this task. However, [...] Read more.

As a core node of the air transportation network, airports rely on aircraft model identification as a key link to support the development of smart aviation. Synthetic Aperture Radar (SAR), with its strong-penetration imaging capabilities, provides high-quality data support for this task. However, the field of SAR image interpretation faces numerous challenges. To address the core challenges in SAR image-based aircraft recognition, including insufficient dataset samples, single-dimensional target features, significant variations in target sizes, and high missed-detection rates for small targets, this study proposed an improved network architecture, SAR-YOLOv8l-ADE. Four modules achieve collaborative optimization: SAR-ACGAN integrates a self-attention mechanism to expand the dataset; SAR-DFE, a parameter-learnable dual-residual module, extracts multidimensional, detailed features; SAR-C2f, a residual module with multi-receptive field fusion, adapts to multi-scale targets; and 4SDC, a four-branch module with adaptive weights, enhances small-target recognition. Experimental results on the fused dataset SAR-Aircraft-EXT show that the mAP₅₀ of the SAR-YOLOv8l-ADE network is 6.1% higher than that of the baseline network YOLOv8l, reaching 96.5%. Notably, its recognition accuracy for small aircraft targets shows a greater improvement, reaching 95.2%. The proposed network outperforms existing methods in terms of recognition accuracy and generalization under complex scenarios, providing technical support for airport management and control, as well as for emergency rescue in smart aviation. Full article

26 pages, 6709 KB

Open AccessArticle

Spatial Heterogeneity and Land Use Modulation of Soil Moisture–Vapor Pressure Deficit–Solar-Induced Fluorescence Interactions in Henan, China: An Integrated Random Forest–GeoShapley Approach

by Xiaohu Luo, Linjie Bi, Xianwei Chang, Qiaoling Wang, Di Yang and Shuangcheng Li

Remote Sens. 2026, 18(2), 235; https://doi.org/10.3390/rs18020235 - 11 Jan 2026

Abstract

In the context of global climate change, solar-induced chlorophyll fluorescence (SIF), a robust proxy for gross primary productivity, is modulated by the coupled effects of soil moisture (SM) and vapor pressure deficit (VPD). However, fine-scale spatial heterogeneity in the SM–VPD–SIF interactions and their [...] Read more.

In the context of global climate change, solar-induced chlorophyll fluorescence (SIF), a robust proxy for gross primary productivity, is modulated by the coupled effects of soil moisture (SM) and vapor pressure deficit (VPD). However, fine-scale spatial heterogeneity in the SM–VPD–SIF interactions and their modulation by land use/cover change (LUCC) remain inadequately explored, particularly in transitional agricultural zones. This study utilized growing-season data (2001–2020) from Henan Province, China, and applied an integrated analytical framework combining Random Forest with GeoShapley analysis, alongside threshold detection and sensitivity modeling. The analysis was stratified by three dominant LUCC types: cropland, natural land, and built-up area. The key findings are as follows: (1) VPD and its geographic interaction terms (VPD × Longitude, VPD × Latitude) dominated the variability in SIF, exhibiting a combined contribution (Shapley value) over six times greater than that of SM and its geographic interactions. (2) LUCC-specific thresholds were identified: croplands exhibited the lowest SM threshold (approx. 0.231 m³/m³) and the highest sensitivity to VPD (−0.234 ± 0.018); natural lands displayed a shift from SM-dominated to VPD-dominated regulation at a VPD threshold of approximately 0.7 kPa; built-up areas showed weak environmental coupling. (3) The co-occurrence of high SM and high VPD induced significant SIF suppression in croplands, whereas natural lands demonstrated greater hydraulic resilience. This study provides a quantitative framework for understanding spatially explicit SM–VPD–SIF interactions and offers actionable thresholds (e.g., VPD of 0.7–0.8 kPa) to inform precision irrigation and drought risk management in transitional agricultural climates under future climate scenarios. Full article

► Show Figures

Figure 1

26 pages, 60469 KB

Open AccessArticle

Spatiotemporal Prediction of Ground Surface Deformation Using TPE-Optimized Deep Learning

by Maoqi Liu, Sichun Long, Tao Li, Wandi Wang and Jianan Li

Remote Sens. 2026, 18(2), 234; https://doi.org/10.3390/rs18020234 - 11 Jan 2026

Abstract

Surface deformation induced by the extraction of natural resources constitutes a non-stationary spatiotemporal process. Modeling surface deformation time series obtained through Interferometric Synthetic Aperture Radar (InSAR) technology using deep learning methods is crucial for disaster prevention and mitigation. However, the complexity of model [...] Read more.

Surface deformation induced by the extraction of natural resources constitutes a non-stationary spatiotemporal process. Modeling surface deformation time series obtained through Interferometric Synthetic Aperture Radar (InSAR) technology using deep learning methods is crucial for disaster prevention and mitigation. However, the complexity of model hyperparameter configuration and the lack of interpretability in the resulting predictions constrain its engineering applications. To enhance the reliability of model outputs and their decision-making value for engineering applications, this study presents a workflow that combines a Tree-structured Parzen Estimator (TPE)-based Bayesian optimization approach with ensemble inference. Using the Rhineland coalfield in Germany as a case study, we systematically evaluated six deep learning architectures in conjunction with various spatiotemporal coding strategies. Pairwise comparisons were conducted using a Welch t-test to evaluate the performance differences across each architecture under two parameter-tuning approaches. The Benjamini–Hochberg method was applied to control the false discovery rate (FDR) at 0.05 for multiple comparisons. The results indicate that TPE-optimized models demonstrate significantly improved performance compared to their manually tuned counterparts, with the ResNet+Transformer architecture yielding the most favorable outcomes. A comprehensive analysis of the spatial residuals further revealed that TPE optimization not only enhances average accuracy, but also mitigates the model’s prediction bias in fault zones and mineralize areas by improving the spatial distribution structure of errors. Based on this optimal architecture, we combined the ten highest-performing models from the optimization stage to generate a quantile-based susceptibility map, using the ensemble median as the central predictor. Uncertainty was quantified from three complementary perspectives: ensemble spread, class ambiguity, and classification confidence. Our analysis revealed spatial collinearity between physical uncertainty and absolute residuals. This suggests that uncertainty is more closely related to the physical complexity of geological discontinuities and human-disturbed zones, rather than statistical noise. In the analysis of super-threshold probability, the threshold sensitivity exhibited by the mining area reflects the widespread yet moderate impact of mining activities. By contrast, the fault zone continues to exhibit distinct high-probability zones, even under extreme thresholds. It suggests that fault-controlled deformation is more physically intense and poses a greater risk of disaster than mining activities. Finally, we propose an engineering decision strategy that combines uncertainty and residual spatial patterns. This approach transforms statistical diagnostics into actionable, tiered control measures, thereby increasing the practical value of susceptibility mapping in the planning of natural resource extraction. Full article

30 pages, 11402 KB

Open AccessArticle

Striping Noise Reduction: A Detector-Selection Approach in Multi-Column Scanning Radiometers

by Xiaowei Jia, Xiuju Li, Tao Wen and Changpei Han

Remote Sens. 2026, 18(2), 233; https://doi.org/10.3390/rs18020233 - 11 Jan 2026

Abstract

Striping noise is a common problem in multi-detector scanning radiometers on remote sensing satellites, typically caused by response inconsistency among detector elements. For payloads with a multi-column redundant architecture, this paper proposes a detector-selection framework that jointly considers sensitivity and uniformity from the [...] Read more.

Striping noise is a common problem in multi-detector scanning radiometers on remote sensing satellites, typically caused by response inconsistency among detector elements. For payloads with a multi-column redundant architecture, this paper proposes a detector-selection framework that jointly considers sensitivity and uniformity from the perspective of detector-element selection to mitigate striping noise. First, the degree of detector consistency is quantified using the Inter-Row Brightness Temperature Difference (IRBTD). Then, a dynamic programming approach based on the Viterbi algorithm is employed to select detector elements row by row with linear time complexity, optimizing the process through a weighted cost function that integrates sensitivity and consistency. Experiments on raw data from the FY-4B Geostationary High-speed Imager (GHI) show that the method reduces inconsistency by 10–40% while increasing the noise-equivalent temperature difference (NEdT) by only 1–4% (≤4 mK). The average IRBTD decreases by approximately 20–100 mK, and high-frequency striping energy is significantly suppressed (reduction of 50–90%). The algorithm exhibits linear time complexity and low computational overhead, making it suitable for real-time on-board processing. Its weighting parameter enables flexible trade-offs between sensitivity and uniformity. By suppressing striping noise directly during the detector-selection stage without introducing data distortion or requiring calibration adjustments, the proposed method can be widely applied to scanning radiometers that employ multi-column long-linear-arrays. Full article

(This article belongs to the Special Issue Remote Sensing Data Preprocessing and Calibration)

► Show Figures

Figure 1

23 pages, 1579 KB

Open AccessArticle

Exploring Difference Semantic Prior Guidance for Remote Sensing Image Change Captioning

by Yunpeng Li, Xiangrong Zhang, Guanchun Wang and Tianyang Zhang

Remote Sens. 2026, 18(2), 232; https://doi.org/10.3390/rs18020232 - 11 Jan 2026

Abstract

Understanding complex change scenes is a crucial challenge in remote sensing field. Remote sensing image change captioning (RSICC) task has emerged as a promising approach to translate appeared changes between bi-temporal remote sensing images into textual descriptions, enabling users to make accurate decisions. [...] Read more.

Understanding complex change scenes is a crucial challenge in remote sensing field. Remote sensing image change captioning (RSICC) task has emerged as a promising approach to translate appeared changes between bi-temporal remote sensing images into textual descriptions, enabling users to make accurate decisions. Current RSICC methods frequently encounter difficulties in consistency for contextual awareness and semantic prior guidance. Therefore, this study explores difference semantic prior guidance network to reason context-rich sentence for capturing appeared vision changes. Specifically, the context-aware difference module is introduced to guarantee the consistency of unchanged/changed context features, strengthening multi-level changed information to improve the ability of semantic change feature representation. Moreover, to effectively mine higher-level cognition ability to reason salient/weak changes, we employ difference comprehending with shallow change information to realize semantic change knowledge learning. In addition, the designed parallel cross refined attention in Transformer decoder can balance vision difference and semantic knowledge for implicit knowledge distilling, enabling fine-grained perception changes of semantic details and reducing pseudochanges. Compared with advanced algorithms on the LEVIR-CC and Dubai-CC datasets, experimental results validate the outstanding performance of the designed model in RSICC tasks. Notably, on the LEVIR-CC dataset, it reaches a CIDEr score of 143.34%, representing a 3.11% improvement over the most competitive SAT-cap. Full article

► Show Figures

Figure 1

21 pages, 4047 KB

Open AccessArticle

Sub-canopy Topography Inversion Using Multi-baseline Bistatic InSAR without External Vegetation-related Data

by Huiqiang Wang, Zhimin Feng, Ruiping Li and Yanan Yu

Remote Sens. 2026, 18(2), 231; https://doi.org/10.3390/rs18020231 - 11 Jan 2026

Abstract

Previous studies on single-polarized InSAR-based sub-canopy topography inversion have mainly relied on simplified or empirical models that only consider the volume scattering process. In a boreal forest area, the canopy layer is often discontinuous. In such a case, the radar backscattering echoes are [...] Read more.

Previous studies on single-polarized InSAR-based sub-canopy topography inversion have mainly relied on simplified or empirical models that only consider the volume scattering process. In a boreal forest area, the canopy layer is often discontinuous. In such a case, the radar backscattering echoes are mainly dominated by ground surface and volume scattering processes. However, interferometric scattering models like Random Volume over Ground (RVoG) have been little utilized in the case of single-polarized InSAR. In this study, we propose a novel method for retrieving sub-canopy topography by combining the RVoG model with multi-baseline InSAR data. Prior to the RVoG model inversion, a SAR-based dimidiate pixel model and a coherence-based penetration depth model are introduced to quantify the initial values of the unknown parameters, thereby minimizing the reliance on external vegetation datasets. Building on this, a nonlinear least-squares algorithm is employed. Then, we estimate the scattering phase center height and subsequently derive the sub-canopy topography. Two frames of multi-baseline TanDEM-X co-registered single-look slant-range complex (CoSSC) data (resampled to 10 m × 10 m) over the Krycklan catchment in northern Sweden are used for the inversion. Validation from airborne light detection and ranging (LiDAR) data shows that the root-mean-square error (RMSE) for the two test sites is 3.82 m and 3.47 m, respectively, demonstrating a significant improvement over the InSAR phase-measured digital elevation model (DEM). Furthermore, diverse interferometric baseline geometries and different initial values are identified as key factors influencing retrieval performance. In summary, our work effectively addresses the limitations of the traditional RVoG model and provides an advanced and practical tool for sub-canopy topography mapping in forested areas. Full article

21 pages, 12157 KB

Open AccessArticle

Background Error Covariance Matrix Structure and Impact in a Regional Tropical Cyclone Forecasting System

by Dongliang Wang, Hong Li, Hongjun Tian and Lin Deng

Remote Sens. 2026, 18(2), 230; https://doi.org/10.3390/rs18020230 - 11 Jan 2026

Abstract

The background error covariance matrix (BE) is a fundamental component of data assimilation (DA) systems. Its impact on both the DA process and subsequent forecast performance depends on model configuration and the types of observations assimilated. However, few studies have specifically examined BE [...] Read more.

The background error covariance matrix (BE) is a fundamental component of data assimilation (DA) systems. Its impact on both the DA process and subsequent forecast performance depends on model configuration and the types of observations assimilated. However, few studies have specifically examined BE behavior in the context of satellite DA for regional tropical cyclone (TC) prediction. In this study, we develop the BE and evaluate its structure for a TC forecasting system over the western North Pacific. A total of six BEs are modeled using three control variable (CV) schemes (aligned with the CV5, CV6, and CV7 options available in the Weather Research and Forecasting DA system (WRFDA)) with training data from two distinct periods: the TC season and the winter season. Results demonstrate that the BE structure is sensitive to the training data used. The performance of TC-season BEs derived from different CV schemes is assessed for TC track forecasting through the assimilation of microwave sounder satellite brightness temperature data. The evaluation is based on a set of 14 cases from 2018 that exhibited large official track forecast errors. The CV7 BE, which uses the x- and y-direction wind components as CVs, captures finer small-scale momentum error features and yields greater forecast improvement at shorter lead-times (24 h). In contrast, the CV6 BE, which employs stream function (ψ) and unbalanced velocity potential (χ_u) as CVs, incorporates more large-scale momentum error information. The inherent multivariate couplings among analysis variables in this scheme also allow for closer fits to satellite microwave brightness temperature data, which is particularly crucial for forecasting TCs that primarily develop over oceans where conventional observations are scarce. Consequently, it enhances the large-scale environmental field more effectively and delivers superior forecast skill at longer lead times (48 h and 72 h). Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

23 pages, 26429 KB

Open AccessArticle

Oil and Gas Facility Detection in High-Resolution Remote Sensing Images Based on Oriented R-CNN

by Yuwen Qian, Song Liu, Nannan Zhang, Yuhua Chen, Zhanpeng Chen and Mu Li

Remote Sens. 2026, 18(2), 229; https://doi.org/10.3390/rs18020229 - 10 Jan 2026

Abstract

Accurate detection of oil and gas (O&G) facilities in high-resolution remote sensing imagery is critical for infrastructure surveillance and sustainable resource management, yet conventional detectors struggle with severe class imbalance, extreme scale variation, and arbitrary orientation. In this work, we propose OGF Oriented [...] Read more.

Accurate detection of oil and gas (O&G) facilities in high-resolution remote sensing imagery is critical for infrastructure surveillance and sustainable resource management, yet conventional detectors struggle with severe class imbalance, extreme scale variation, and arbitrary orientation. In this work, we propose OGF Oriented R-CNN (Oil and Gas Facility Detection Oriented Region-based Convolutional Neural Network), an enhanced oriented detection model derived from Oriented R-CNN that integrates three improvements: (1) O&G Loss Function, (2) Class-Aware Hard Example Mining (CAHEM) module, and (3) Feature Pyramid Network with Feature Enhancement Attention (FPNFEA). Working in synergy, they resolve the coupled challenges more effectively than any standalone fix and do so without relying on rigid one-to-one matching between modules and individual issues. Evaluated on the O&G facility dataset comprising 3039 high-resolution images annotated with rotated bounding boxes across three classes (well sites: 3006, industrial and mining lands: 692, drilling: 244), OGF Oriented R-CNN achieves a mean average precision (mAP) of 82.9%, outperforming seven state-of-the-art (SOTA) models by margins of up to 27.6 percentage points (pp) and delivering a cumulative gain of +10.5 pp over Oriented R-CNN. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Methods for Remote Sensing Target and Object Detection (Third Edition))

21 pages, 5728 KB

Open AccessArticle

Multidimensional Validation of FVC Products over Qinghai–Tibetan Plateau Alpine Grasslands: Integrating Spatial Representativeness Metrics with Machine Learning Optimization

by Junji Li, Jianjun Chen, Xue Cheng, Jiayuan Yin, Qingmin Cheng, Haotian You, Xiaowen Han and Xinhong Li

Remote Sens. 2026, 18(2), 228; https://doi.org/10.3390/rs18020228 - 10 Jan 2026

Abstract

Fractional Vegetation Cover (FVC) dynamics on the Qinghai–Tibetan Plateau (QTP) are critical indicators for assessing ecosystem condition. However, uncertainties persist in the accuracy of existing FVC products over the QTP due to retrieval differences, scale effects, and limited validation data. This study utilized [...] Read more.

Fractional Vegetation Cover (FVC) dynamics on the Qinghai–Tibetan Plateau (QTP) are critical indicators for assessing ecosystem condition. However, uncertainties persist in the accuracy of existing FVC products over the QTP due to retrieval differences, scale effects, and limited validation data. This study utilized the Google Earth Engine platform to integrate unmanned aerial vehicle (UAV) observations, Sentinel-2, MODIS, climate, and topography datasets, and proposed a comprehensive framework incorporating dual-index screening, machine learning optimization, and multidimensional validation to systematically assess the accuracy of GEOV3, GLASS, and MuSyQ FVC products in the alpine grasslands. The dual-index screening reduced validation uncertainty by improving the spatial representativeness of ground data. To build a high-precision evaluation dataset with limited inter-class coverage, recursive feature elimination and grid search were applied to optimize five ML models, and CatBoost achieved the superior performance (R² = 0.880, RMSE = 0.122), followed by XGBoost, GBM, LightGBM, and RF models. Four validation scenarios were implemented, including direct validation using 250 m UAV plot FVC and multi-scale validation using a 10 m FVC reference aggregated to product grids. Results show that GEOV3 (R² = 0.909–0.925, RMSE = 0.082–0.103) outperformed GLASS (R² = 0.742–0.771, RMSE = 0.138–0.175) and MuSyQ (R² = 0.739–0.746, RMSE = 0.138–0.181), both of which exhibited systematic underestimation. This framework significantly enhances FVC product validation reliability, providing a robust solution for remote sensing product validation in alpine grassland ecosystems. Full article

(This article belongs to the Special Issue Integration of Remote Sensing and GIS to Forest and Grassland Ecosystem Monitoring (Second Edition))

30 pages, 28238 KB

Open AccessArticle

Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height

by Bryan Shaddy, Brianna Binder, Agnimitra Dasgupta, Haitong Qin, James Haley, Angel Farguell, Kyle Hilburn, Derek V. Mallia, Adam Kochanski, Jan Mandel and Assad A. Oberai

Remote Sens. 2026, 18(2), 227; https://doi.org/10.3390/rs18020227 - 10 Jan 2026

Abstract

Wildfire spread prediction models, including even the most sophisticated coupled atmosphere–wildfire models, diverge from observed wildfire progression during multi-day simulations, motivating the need for measurement-based assessments of wildfire state and improved data assimilation techniques. Data assimilation in the context of coupled atmosphere–wildfire models [...] Read more.

Wildfire spread prediction models, including even the most sophisticated coupled atmosphere–wildfire models, diverge from observed wildfire progression during multi-day simulations, motivating the need for measurement-based assessments of wildfire state and improved data assimilation techniques. Data assimilation in the context of coupled atmosphere–wildfire models entails estimating wildfire progression history from observations and using this to obtain initial conditions for subsequent simulations through a spin-up process. In this study, an approach is developed for estimating fire progression history from VIIRS active fire measurements, GOES-derived ignition times, and terrain height data. The approach utilizes a conditional Wasserstein Generative Adversarial Network trained on simulations of historic wildfires from the coupled atmosphere–wildfire model WRF-SFIRE, with corresponding measurements for training obtained through the application of an approximate observation operator. Once trained, the cWGAN leverages measurements of real fires and corresponding terrain data to probabilistically generate fire progression estimates that are consistent with the WRF-SFIRE solutions used for training. The approach is validated on five Pacific US wildfires, and results are compared against high-resolution perimeters measured via aircraft, finding an average Sørensen–Dice coefficient of 0.81. The influence of terrain data on fire progression estimates is also assessed, finding an increased contribution when measurements are uninformative. Full article

(This article belongs to the Special Issue Integrating Artificial Intelligence and Remote Sensing for Wildfire Detection, Monitoring and Management)

23 pages, 2960 KB

Open AccessArticle

Multi-Source Data-Driven CNN–Transformer Hybrid Modeling for Wind Energy Database Reconstruction in the Tropical Indian Ocean

by Jintao Xu, Yao Luo, Guanglin Wu, Weiqiang Wang, Zhenqiu Zhang and Arulananthan Kanapathipillai

Remote Sens. 2026, 18(2), 226; https://doi.org/10.3390/rs18020226 - 10 Jan 2026

Abstract

This study addresses the issues of sparse observations from buoys in the tropical Indian Ocean and systematic biases in reanalysis products by proposing a daily-mean wind speed reconstruction framework that integrates multi-source meteorological fields. This study also considers the impact of different source [...] Read more.

This study addresses the issues of sparse observations from buoys in the tropical Indian Ocean and systematic biases in reanalysis products by proposing a daily-mean wind speed reconstruction framework that integrates multi-source meteorological fields. This study also considers the impact of different source domains on model pre-training, with the goal of providing reliable data support for wind energy assessment. The model was pre-trained using data from the Americas and tropical Pacific buoys as the source domain and then fine-tuned on Indian Ocean buoys as the target domain. Using annual leave-one-out cross-validation, we evaluated the model’s performance against uncorrected ERA5 and CCMP data while comparing three deep reconstruction models. The results demonstrate that deep models significantly reduce reanalysis bias: the RMSE decreases from approximately 1.00 m/s to 0.88 m/s, while R² improves by approximately 8.9% and 7.1% compared to ERA5/CCMP, respectively. The Branch CNN–Transformer outperforms standalone LSTM or CNN models in overall accuracy and interpretability, with transfer learning yielding directional gains for specific wind conditions in complex topography and monsoon zones. The 20-year wind energy data reconstructed using this model indicates wind energy densities 60–150 W/m² higher than in the reanalysis data in open high-wind zones such as the southern Arabian Sea and the Somali coast. This study not only provides a pathway for constructing high-precision wind speed databases for tropical Indian Ocean wind resource assessment but also offers precise quantitative support for delineating priority development zones for offshore wind farms and mitigating near-shore engineering risks. Full article

(This article belongs to the Special Issue Advancing Ocean Observation, Analysis, and Forecasting Through AI-Powered Remote Sensing)

► Show Figures

Figure 1

Journal Description

Remote Sensing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI