Next Issue
Volume 17, December-2
Previous Issue
Volume 17, November-2
 
 
remotesensing-logo

Journal Browser

Journal Browser

Remote Sens., Volume 17, Issue 23 (December-1 2025) – 147 articles

Cover Story (view full-size image): This paper presents the third edition of the open-access benchmark Atmospheric Correction Inter-comparison eXercise (ACIX), providing a comprehensive assessment of atmospheric processors of space-borne hyperspectral missions over land surfaces. The exercise contains 90 scenes, covering stations for assessing aerosol optical depth and water vapour retrievals, as well as stationary networks and ad hoc campaigns for surface reflectance validation. This study shows a detailed analysis of similarities and differences of seven processors, offering critical insights for understanding the current capabilities and limitations of atmospheric correction algorithms for imaging spectroscopy. It offers a foundation for future improvements and a first practical guide to support users in selecting the most suitable processor for their application needs. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
20 pages, 17598 KB  
Article
Self-Supervised Learning for Soybean Disease Detection Using UAV Hyperspectral Imagery
by Mustafizur Rahaman, Vasit Sagan, Felipe A. Lopes, Haireti Alifu, Cagri Gul, Hadi Aliakbarpour and Kannappan Palaniappan
Remote Sens. 2025, 17(23), 3928; https://doi.org/10.3390/rs17233928 - 4 Dec 2025
Viewed by 1373
Abstract
The accuracy of machine learning models in plant disease detection significantly relies on large volumes of knowledge-based labeled data; the acquisition of annotation remains a significant bottleneck in domain-specific research such as plant disease detection. While unsupervised learning alleviates the need for labeled [...] Read more.
The accuracy of machine learning models in plant disease detection significantly relies on large volumes of knowledge-based labeled data; the acquisition of annotation remains a significant bottleneck in domain-specific research such as plant disease detection. While unsupervised learning alleviates the need for labeled data, its effectiveness is constrained by the intrinsic separability of feature clusters. These limitations underscore the need for approaches that enable supervised early disease detection without extensive annotation. To this end, we propose a self-supervised learning (SSL) framework for the early detection of soybean’s sudden death syndrome (SDS) using hyperspectral data acquired from an unmanned aerial vehicle (UAV). The methodology employs a novel distance-based spectral pairing technique that derives intermediate labels directly from the data. In addition, we introduce an adapted contrastive loss function designed to improve cluster separability and reinforce discriminative feature learning. The proposed approach yields an 11% accuracy gain over agglomerative hierarchical clustering and attains both classification accuracy and F1 score of 0.92, matching supervised baselines. Reflectance frequency analysis further demonstrates robustness to label noise, highlighting its suitability in label-scarce settings. Full article
(This article belongs to the Special Issue Advances in Deep Learning Approaches: UAV Data Analysis)
Show Figures

Figure 1

26 pages, 34171 KB  
Article
Assessing Surface Water Dynamics of Wetlands in Reclaimed Mining Areas in the Athabasca Oil Sands Region, Alberta, Canada, with Time-Varying Sentinel-1 SAR and Sentinel-2 Multi-Spectral Imagery
by Erik Biederstadt, Faramarz F. Samavati, Hannah Porter, Elizabeth Gillis and Jan J. H. Ciborowski
Remote Sens. 2025, 17(23), 3927; https://doi.org/10.3390/rs17233927 - 4 Dec 2025
Viewed by 697
Abstract
Wetlands provide critical ecological and socio-economic benefits, covering approximately 45% of the Athabasca Oil Sands Region in Alberta, Canada. However, open-pit oil sand mining has led to widespread wetland loss. While reclamation efforts are ongoing, the development of effective wetland monitoring methods remain [...] Read more.
Wetlands provide critical ecological and socio-economic benefits, covering approximately 45% of the Athabasca Oil Sands Region in Alberta, Canada. However, open-pit oil sand mining has led to widespread wetland loss. While reclamation efforts are ongoing, the development of effective wetland monitoring methods remain essential. This paper presents a novel approach to tracking wetland dynamics in reclaimed and reference landscapes using Sentinel-1 SAR and Sentinel-2 multispectral imagery. We assess surface water extent and emergent vegetation, validating our satellite-based measurements against high-resolution UAV-derived wetland area data (R2=0.902). Our results reveal minor differences in intra-annual variability in wetland area between wetlands in reclaimed versus those in reference landscapes. Wetlands exhibit a positive log-linear relationship between maximum depth and variability in open-water area, a pattern that was consistent between landscape types. Intra- and interannual variability in spatial extent were both positively associated with wetland area. This paper introduces the first ground-truthed automated wetland monitoring approach for the region. These findings document the similarities in range of variation between wetlands developing in reclaimed and reference landscapes and provide a simple tool to support long-term monitoring to document the persistence of wetlands forming in reclaimed landscapes. Full article
(This article belongs to the Section Ecological Remote Sensing)
Show Figures

Graphical abstract

25 pages, 7512 KB  
Article
Advancing Hyperspectral LWIR Imaging of Soils with a Controlled Laboratory Setup
by Helge L. C. Daempfling, Robert Milewski, Gila Notesco, Eyal Ben-Dor and Sabine Chabrillat
Remote Sens. 2025, 17(23), 3926; https://doi.org/10.3390/rs17233926 - 4 Dec 2025
Viewed by 610
Abstract
This study introduces a controlled laboratory setup for hyperspectral longwave infrared (LWIR) imaging of soils, designed to bridge the gap between laboratory measurements and remote sensing observations. A Fourier-transform hyperspectral LWIR imaging spectrometer (Telops Hyper-Cam LW) was employed, together with a specialized heating [...] Read more.
This study introduces a controlled laboratory setup for hyperspectral longwave infrared (LWIR) imaging of soils, designed to bridge the gap between laboratory measurements and remote sensing observations. A Fourier-transform hyperspectral LWIR imaging spectrometer (Telops Hyper-Cam LW) was employed, together with a specialized heating plate, rigorous calibration protocols, and a Spatial Averaging Before Blackbody Fitting (SABBF) method to enable accurate LWIR indoor measurements. Unlike established laboratory techniques that measure reflectance and calculate emissivity indirectly, this setup enables direct passive measurement of soil emissivity, replicating airborne and spaceborne LWIR measurements of the surface. The emissivity spectra of 12 variable soil samples obtained with the lab setup were compared and validated based on LWIR Hyper-Cam LW spectra acquired under outdoor conditions, then were subsequently analyzed to determine the mineral composition of each sample. Spectral features and indices were used to estimate the relative content of quartz, clay minerals, and carbonates, from the most to least abundant. The results demonstrate that the laboratory-based setup preserves spectral fidelity while offering improved repeatability, scheduling flexibility, and reduced dependence on weather. Beyond replicating outdoor measurements, this controlled setup is easy to install and provides a reproducible framework for LWIR soil spectroscopy that could be considered for standard laboratory protocols, enabling reliable mineral identification, calibration/validation of airborne and satellite LWIR data, and broader applications in soil monitoring and environmental remote sensing. Full article
Show Figures

Figure 1

23 pages, 11094 KB  
Article
RSDB-Net: A Novel Rotation-Sensitive Dual-Branch Network with Enhanced Local Features for Remote Sensing Ship Detection
by Danshu Zhou, Yushan Xiong, Shuangming Yu, Peng Feng, Jian Liu, Nanjian Wu, Runjiang Dou and Liyuan Liu
Remote Sens. 2025, 17(23), 3925; https://doi.org/10.3390/rs17233925 - 4 Dec 2025
Viewed by 574
Abstract
Ship detection in remote sensing imagery is hindered by cluttered backgrounds, large variations in scale, and random orientations, limiting the performance of detectors designed for natural images. We propose RSDB-Net, a Rotation-Sensitive Dual-Branch Detection Network that introduces innovations in feature extraction, fusion, and [...] Read more.
Ship detection in remote sensing imagery is hindered by cluttered backgrounds, large variations in scale, and random orientations, limiting the performance of detectors designed for natural images. We propose RSDB-Net, a Rotation-Sensitive Dual-Branch Detection Network that introduces innovations in feature extraction, fusion, and detection. The Swin Transformer–CNN Backbone (STCBackbone) combines a Swin Transformer for global semantics with a CNN branch for local spatial detail, while the Feature Conversion and Coupling Module (FCCM) aligns and fuses heterogeneous features to handle multi-scale objects, and a Rotation-sensitive Cross-branch Fusion Head (RCFHead) enables bidirectional interaction between classification and localization, improving detection of randomly oriented targets. Additionally, an enhanced Feature Pyramid Network (eFPN) with learnable transposed convolutions restores semantic information while maintaining spatial alignment. Experiments on DOTA-v1.0 and HRSC2016 show that RSDB-Net performs better than the state of the art (SOTA), with mAP-ship values of 89.13% and 90.10% (+5.54% and +44.40% over the baseline, respectively), and reaches 72 FPS on an RTX 3090. RSDB-Net also demonstrates strong generalization and scalability, providing an effective solution for rotation-aware ship detection. Full article
Show Figures

Figure 1

26 pages, 18827 KB  
Article
Physics-Driven Machine-Learning Retrieval and Uncertainty Quantification of Crop Leaf Area Index
by Wei Liu, Xiaohua Zhu, Suyi Yang and Zhihai Gao
Remote Sens. 2025, 17(23), 3924; https://doi.org/10.3390/rs17233924 - 4 Dec 2025
Viewed by 877
Abstract
Leaf Area Index (LAI) is a key biophysical descriptor of crop canopies and is essential for growth monitoring and yield estimation. We present a physics-driven machine-learning framework for operational LAI retrieval and end-to-end uncertainty quantification that couples the PROSAIL radiative transfer model with [...] Read more.
Leaf Area Index (LAI) is a key biophysical descriptor of crop canopies and is essential for growth monitoring and yield estimation. We present a physics-driven machine-learning framework for operational LAI retrieval and end-to-end uncertainty quantification that couples the PROSAIL radiative transfer model with a genetic-algorithm-optimised multilayer perceptron (NN–GA). PROSAIL is sampled across plausible parameter priors and spectra are convolved with Sentinel-2B spectral response functions to build a 30,000-sample training library; a GA is used to globally optimise network weights and biases. Total retrieval uncertainty is decomposed into a simulation component (PROSAIL parameter variability) and a training component (variability across repeated NN–GA trainings) and combined via the law of propagation of uncertainty. The model was developed in Minqin (modelling/testing area; entirely maize) and transferred to Zhangye (transfer/validation area; predominantly maize, with one sunflower plot). Sentinel-2B validation results were RMSE/R2 = 0.44/0.73 (Minqin) and 0.40/0.56 (Zhangye), indicating reasonable cross-site generalisation. The uncertainty split indicates physical-driven contributions of 11.42% and 11.48% and machine-learning contributions of 18.06% and 12.96%, respectively. The framework improves 10 m LAI retrieval accuracy and supplies a reproducible, per-pixel uncertainty budget to guide product use and refinement. Full article
Show Figures

Figure 1

24 pages, 6200 KB  
Article
An Efficient Biomass Estimation Model for Large-Scale Olea europaea L. by Integrating UAV-RGB and U2-Net with Allometric Equations
by Yungang He, Weili Kou, Ning Lu, Yi Yang, Lee Seng Hua, Chunqin Duan, Ziyi Yang, Yongjun Song, Jiayue Gao and Yue Chen
Remote Sens. 2025, 17(23), 3923; https://doi.org/10.3390/rs17233923 - 4 Dec 2025
Viewed by 749
Abstract
Olea europaea L. is an economically and ecologically significant species, for which accurate biomass estimation provides critical insights for artificial propagation, yield forecasting, and carbon sequestration assessments. Currently, research on biomass estimation for Olea europaea L. remains scarce, and there is a lack [...] Read more.
Olea europaea L. is an economically and ecologically significant species, for which accurate biomass estimation provides critical insights for artificial propagation, yield forecasting, and carbon sequestration assessments. Currently, research on biomass estimation for Olea europaea L. remains scarce, and there is a lack of efficient, accurate, and scalable technical solutions. To address this gap, this study achieved, for the first time, non-destructive estimation of Olea europaea L. biomass across individual tree to plot scales by integrating UAV-RGB (Unmanned Aerial Vehicle-Red-Green-Blue) imagery with the U2-Net model. This study initially developed allometric models for W-D-H, CA-D, and CA-H in Olea europaea L. (where W = biomass, D = ground diameter, H = tree height, and CA = canopy area). A single-parameter CA-based whole-plant biomass model was subsequently developed utilizing the optimal models. An innovative whole-plant biomass estimation model (UAV-RGB, U2-Net Total Biomass, UUTB) that combines UAV-RGB imagery with U2-Net at the sample-plot level was developed and assessed. The results revealed the following: (1) The model for Olea europaea L. aboveground biomass (AGB) was WA = 0.0025D1.943H0.690 (R2 = 0.912), the model for belowground biomass (BGB) was WB = 0.012D1.231H0.525 (R2 = 0.693), the model for CA-D was D = 4.31427C0.513 (R2 = 0.751), CA-H model was H = 226.51939C0.268 (R2 = 0.500). (2) The optimal AGB model for CA single-parameter was WA = 1.80901C1.181 (R2 = 0.845), and the model for BGB was WB = 1.25043C0.772 (R2 = 0.741). (3) The R2 of Olea europaea L. biomass, as estimated by CA derived from the U2-Net and UUTB models, was 0.855. This study presents the first integration of UAV-RGB imagery and the U2-Net model for biomass estimation in Olea europaea L., which not only addresses the research gap in species-specific allometric modeling but also overcomes the limitations of traditional manual measurement methods. The proposed approach provides a reliable technical foundation for accurate assessment of both economic yield and ecological carbon sequestration capacity. Full article
Show Figures

Figure 1

23 pages, 4742 KB  
Article
Marine Radar Oil Spill Monitoring Method Based on YOLOv11 and Improved NGO Algorithm
by Jin Xu, Yuanyuan Huang, Jin Yan, Zekun Guo, Bo Li, Haihui Dong and Peng Liu
Remote Sens. 2025, 17(23), 3922; https://doi.org/10.3390/rs17233922 - 3 Dec 2025
Cited by 2 | Viewed by 742
Abstract
To address the urgent need for rapid detection and precise segmentation of oil spill incidents, a cascaded processing framework integrating the YOLOv11 model with an enhanced Northern Goshawk Optimization (NGO) algorithm is proposed. This method effectively utilizes the advantages of deep learning and [...] Read more.
To address the urgent need for rapid detection and precise segmentation of oil spill incidents, a cascaded processing framework integrating the YOLOv11 model with an enhanced Northern Goshawk Optimization (NGO) algorithm is proposed. This method effectively utilizes the advantages of deep learning and metaheuristic algorithms. Firstly, the YOLOv11 model was used for preliminary localization and segmentation of oil spill target regions in marine radar images. Subsequently, an improved NGO algorithm based on adaptive weighting factors, Levy flight perturbation, and pinhole imaging perturbation was used to finely segment the region, balancing processing efficiency and accuracy requirements. The experimental results showed that the cascade architecture proposed effectively balances the problems of false detection and missed detection. Compared with other methods, the marine radar oil film detection method based on YOLOv11 combined with improved NGO exhibited strong adaptability in complex scenes. Multiple indicators, such as accuracy, precision, recall, specificity, and Dice similarity coefficient, indicate that this method has good performance in marine radar oil spill detection tasks. Full article
Show Figures

Figure 1

18 pages, 4825 KB  
Article
Dominant Role of Meteorology and Aerosols in Regulating the Seasonal Variation of Urban Thermal Environment in Beijing
by Shiyu Zhang, Yan Yang, Haitao Wang, Hao Fan, Jiayun Qi and Xiuting Lai
Remote Sens. 2025, 17(23), 3921; https://doi.org/10.3390/rs17233921 - 3 Dec 2025
Viewed by 584
Abstract
Land surface temperature (LST) is a key indicator of the urban heat island effect and is affected by multiple factors. However, existing research mainly focuses on the contributions of urban landscape and meteorology, and the impact of changes in atmospheric environment has not [...] Read more.
Land surface temperature (LST) is a key indicator of the urban heat island effect and is affected by multiple factors. However, existing research mainly focuses on the contributions of urban landscape and meteorology, and the impact of changes in atmospheric environment has not been fully considered. Based on multisource data and a random forest model, this study quantified the independent and interactive effects of aerosols, meteorological conditions, and urban features on LST in Beijing. The results revealed that the effects of the meteorological factors and aerosol optical depth (AOD) on LST were significantly greater than those of the urban landscape index. The response of LST to multiple factors is nonlinear, and the interactions of precipitation with wind speed and vegetation have the strongest cooling effects on LST. The aerosol impact shifts seasonally, with its direct radiative effect dominating in spring and inducing a cooling of up to about 2.0 °C. Notably, the land use type plays a background role in determining the LST, and the average LST decreases by approximately 1.5 °C for every 50% increase in tree coverage. As the building height increases by 10%, the summer LST increases by approximately 2 °C. In addition, the interactions of precipitation with wind speed and vegetation were identified as having the strongest cooling effects on LST. By elucidating the nonlinear interactions among aerosol, meteorological, and urban features, this work moves beyond isolated factor analysis and offers mechanism cognition for urban planning strategies. Full article
(This article belongs to the Special Issue Applications of Remote Sensing in Landscapes and Human Settlements)
Show Figures

Figure 1

33 pages, 12224 KB  
Article
Unsupervised Clustering of InSAR Time-Series Deformation in Mandalay Region from 2022 to 2025 Using Dynamic Time Warping and Longest Common Subsequence
by Jingyi Qin, Zhifang Zhao, Dingyi Zhou, Mengfan Yuan, Chaohai Liu, Xiaoyan Wei and Tin Aung Myint
Remote Sens. 2025, 17(23), 3920; https://doi.org/10.3390/rs17233920 - 3 Dec 2025
Cited by 1 | Viewed by 1073
Abstract
Urban land subsidence poses a significant threat in rapidly urbanizing regions, threatening infrastructure integrity and sustainable development. This study focuses on Mandalay, Myanmar, and presents a novel clustering framework—Dynamic Time Warping and Trend-based Longest Common Subsequence with Agglomerative Hierarchical Clustering (DTLCS-AHC)—to classify spatiotemporal [...] Read more.
Urban land subsidence poses a significant threat in rapidly urbanizing regions, threatening infrastructure integrity and sustainable development. This study focuses on Mandalay, Myanmar, and presents a novel clustering framework—Dynamic Time Warping and Trend-based Longest Common Subsequence with Agglomerative Hierarchical Clustering (DTLCS-AHC)—to classify spatiotemporal deformation patterns from Small Baseline Subset (SBAS) Interferometric Synthetic Aperture Radar (InSAR) time series derived from Sentinel-1A imagery covering January 2022 to March 2025. The method identifies four characteristic deformation regimes: stable uplift, stable subsidence, primary subsidence, and secondary subsidence. Time–frequency analysis employing Empirical Mode Decomposition (EMD) and Discrete Fourier Transform (DFT) reveals seasonal oscillations in stable areas. Notably, a transition from subsidence to uplift was detected in specific areas approximately seven months prior to the Mw 7.7 earthquake, but causal relationships require further validation. This study further establishes correlations between subsidence and both urban expansion and rainfall patterns. A physically informed conceptual model is developed through multi-source data integration, and cross-city validation in Yangon confirms the robustness and generalizability of the approach. This research provides a scalable technical framework for deformation monitoring and risk assessment in tropical, data-scarce urban environments. Full article
Show Figures

Graphical abstract

40 pages, 4023 KB  
Article
Benchmarking Elevation Plus Land Surface Parameters Finds FathomDEM and Copernicus DEM Win as Best Global DEMs
by Peter L. Guth, Sebastiano Trevisani, Carlos H. Grohmann, John B. Lindsay and Hannes I. Reuter
Remote Sens. 2025, 17(23), 3919; https://doi.org/10.3390/rs17233919 - 3 Dec 2025
Cited by 2 | Viewed by 2167
Abstract
We evaluated six global digital elevation DEMs at 1-arc-sec resolution: CopDEM and AW3D30, which are digital surface models (DSMs), and EDTM, GEDTM, FABDEM, and FathomDEM, which are digital terrain models (DTMs). We compared them to reference DTMs created by mean aggregation from 1–2 [...] Read more.
We evaluated six global digital elevation DEMs at 1-arc-sec resolution: CopDEM and AW3D30, which are digital surface models (DSMs), and EDTM, GEDTM, FABDEM, and FathomDEM, which are digital terrain models (DTMs). We compared them to reference DTMs created by mean aggregation from 1–2 m lidar-derived DTMs from national mapping agencies, using 1510 approximately 10 × 10 km test tiles from the United States and western Europe. Our criteria used the grids for elevation and derived land surface parameters (LSPs), including characteristics of the difference distributions and the fraction unexplained variance derived from grid correlations. The best DEM depends on the LSP used and the characteristics of the test tile, especially average slope, barrenness, and forest coverage. FathomDEM emerged as the best among the DEMs, with CopDEM the best overall for the DEMs with unrestricted licenses. GEDTM performed poorly. This is especially important for LSPs like curvature measures, which require higher-order partial derivatives for computation, and which should be used very cautiously. Full article
(This article belongs to the Section Environmental Remote Sensing)
Show Figures

Graphical abstract

21 pages, 2057 KB  
Article
Estimating Plant Physiological Parameters for Vitis vinifera L. Using In Situ Hyperspectral Measurements and Ensemble Machine Learning
by Marco Lutz, Emilie Lüdicke, Daniel Heßdörfer, Tobias Ullmann and Melanie Brandmeier
Remote Sens. 2025, 17(23), 3918; https://doi.org/10.3390/rs17233918 - 3 Dec 2025
Viewed by 666
Abstract
Accurate prediction of photosynthetic parameters is pivotal for precision viticulture, as it enables non-invasive monitoring of plant physiological status and informed management decisions. In this study, spectral reflectance data were used to predict key photosynthetic parameters such as assimilation rate (A), effective photosystem [...] Read more.
Accurate prediction of photosynthetic parameters is pivotal for precision viticulture, as it enables non-invasive monitoring of plant physiological status and informed management decisions. In this study, spectral reflectance data were used to predict key photosynthetic parameters such as assimilation rate (A), effective photosystem II (PSII) quantum yield (ΦPSII), and electron transport rate (ETR), as well as stem and leaf water potential (Ψstem and Ψleaf), in Vitis vinifera (cv. Müller-Thurgau) grown in an experimental vineyard in Lower Franconia (Germany). Measurements were obtained on 25 July, 7 August, and 12 August 2024 using a LI-COR LI-6800 system and a PSR+ hyperspectral spectroradiometer. Various machine learning models (SVR, Lasso, ElasticNet, Ridge, PLSR, a simple ANN, and Random Forest) were evaluated, both as standalone predictors and as base learners in a stacking ensemble regressor with a Random Forest meta-learner. First derivative reflectance (FDR) preprocessing enhanced predictive performance, particularly for ΦPSII and ETR, with the ensemble approach achieving R2 values up to 0.92 for ΦPSII and 0.85 for A at 1 nm resolution. At coarser spectral resolutions, predictive accuracy declined, though FDR preprocessing provided some mitigation of the performance loss. Diurnal patterns revealed that morning to mid-morning measurements, particularly between 9:00 and 11:00, captured peak photosynthetic activity, making them optimal for assessing vine vigor, while midday water potential declines indicated favorable timing for irrigation scheduling. These findings demonstrate the potential of integrating hyperspectral data with ensemble machine learning and FDR preprocessing for accurate, scalable, and high-throughput monitoring of grapevine physiology, supporting real-time vineyard management and the use of cost-effective sensors under diverse environmental conditions. Full article
Show Figures

Figure 1

33 pages, 10355 KB  
Article
S2GL-MambaResNet: A Spatial–Spectral Global–Local Mamba Residual Network for Hyperspectral Image Classification
by Tao Chen, Hongming Ye, Guojie Li, Yaohan Peng, Jianming Ding, Huayue Chen, Xiangbing Zhou and Wu Deng
Remote Sens. 2025, 17(23), 3917; https://doi.org/10.3390/rs17233917 - 3 Dec 2025
Viewed by 1029
Abstract
In hyperspectral image classification (HSIC), each pixel contains information across hundreds of contiguous spectral bands; therefore, the ability to perform long-distance modeling that stably captures and propagates these long-distance dependencies is critical. A selective structured state space model (SSM) named Mamba has shown [...] Read more.
In hyperspectral image classification (HSIC), each pixel contains information across hundreds of contiguous spectral bands; therefore, the ability to perform long-distance modeling that stably captures and propagates these long-distance dependencies is critical. A selective structured state space model (SSM) named Mamba has shown strong capabilities for capturing cross-band long-distance dependencies and exhibits advantages in long-distance modeling. However, the inherently high spectral dimensionality, information redundancy, and spatial heterogeneity of hyperspectral images (HSI) pose challenges for Mamba in fully extracting spatial–spectral features and in maintaining computational efficiency. To address these issues, we propose S2GL-MambaResNet, a lightweight HSI classification network that tightly couples Mamba with progressive residuals to enable richer global, local, and multi-scale spatial–spectral feature extraction, thereby mitigating the negative effects of high dimensionality, redundancy, and spatial heterogeneity on long-distance modeling. To avoid fragmentation of spatial–spectral information caused by serialization and to enhance local discriminability, we design a preprocessing method applied to the features before they are input to Mamba, termed the Spatial–Spectral Gated Attention Aggregator (SS-GAA). SS-GAA uses spatial–spectral adaptive gated fusion to preserve and strengthen the continuity of the central pixel’s neighborhood and its local spatial–spectral representation. To compensate for a single global sequence network’s tendency to overlook local structures, we introduce a novel Mamba variant called the Global_Local Spatial_Spectral Mamba Encoder (GLS2ME). GLS2ME comprises a pixel-level global branch and a non-overlapping sliding-window local branch for modeling long-distance dependencies and patch-level spatial–spectral relations, respectively, jointly improving generalization stability under limited sample regimes. To ensure that spatial details and boundary integrity are maintained while capturing spectral patterns at multiple scales, we propose a multi-scale Mamba encoding scheme, the Hierarchical Spectral Mamba Encoder (HSME). HSME first extracts spectral responses via multi-scale 1D spectral convolutions, then groups spectral bands and feeds these groups into Mamba encoders to capture spectral pattern information at different scales. Finally, we design a Progressive Residual Fusion Block (PRFB) that integrates 3D residual recalibration units with Efficient Channel Attention (ECA) to fuse multi-kernel outputs within a global context. This enables ordered fusion of local multi-scale features under a global semantic context, improving information utilization efficiency while keeping computational overhead under control. Comparative experiments on four publicly available HSI datasets demonstrate that S2GL-MambaResNet achieves superior classification accuracy compared with several state-of-the-art methods, with particularly pronounced advantages under few-shot and class-imbalanced conditions. Full article
Show Figures

Figure 1

23 pages, 25814 KB  
Article
Remote Sensing Standardized Soil Moisture Index for Drought Monitoring: A Case Study in the Ebro Basin
by Guillem Sánchez Alcalde and Maria José Escorihuela
Remote Sens. 2025, 17(23), 3916; https://doi.org/10.3390/rs17233916 - 3 Dec 2025
Cited by 1 | Viewed by 1310
Abstract
The occurrence and duration of droughts have increased in recent years, reinforcing their role as a major climate risk. This study evaluates a remote sensing soil moisture-based drought index, the Standardized Soil Moisture Index (SSI), as a tool to monitor different types of [...] Read more.
The occurrence and duration of droughts have increased in recent years, reinforcing their role as a major climate risk. This study evaluates a remote sensing soil moisture-based drought index, the Standardized Soil Moisture Index (SSI), as a tool to monitor different types of drought, from meteorological, agricultural to hydrological. The satellite-derived SSI at different integration times (from SSI-1 up to SSI-24) was compared with the Standardized Precipitation Index (SPI), calculated using precipitation data from 239 meteorological stations in the Ebro Basin. A good correlation (R>0.6) was found between the indices at all integration times. Our results suggest that, independently of the time scale, SSI tends to relate better to the SPI with an additional month for its integration time, reflecting soil moisture’s inertia. Comparison with a gridded SPI product further confirmed that SSI captures basin-wide drought variability, also suggesting that it can observe hydrological processes such as snowmelt and irrigation. These findings demonstrate that remote-sensed SSI is a robust and versatile drought index, capable of monitoring multiple drought types without relying on in situ measurements. Provided the existence of quality soil moisture data, satellite-derived SSI stands as a drought indicator with high coverage and enhanced spatial detail. Hence, this methodology paves the way for accurate drought monitoring in data-scarce regions. Full article
Show Figures

Graphical abstract

34 pages, 2582 KB  
Article
Integrating UAV Multi-Temporal Imagery and Machine Learning to Assess Biophysical Parameters of Douro Grapevines
by Pedro Marques, Leilson Ferreira, Telmo Adão, Joaquim J. Sousa, Raul Morais, Emanuel Peres and Luís Pádua
Remote Sens. 2025, 17(23), 3915; https://doi.org/10.3390/rs17233915 - 3 Dec 2025
Cited by 2 | Viewed by 833
Abstract
The accurate estimation of grapevine biophysical parameters is important for decision support in precision viticulture. This study addresses the use of unmanned aerial vehicle (UAV) multispectral data and machine learning (ML) techniques to estimate leaf area index (LAI), pruning wood biomass, and yield, [...] Read more.
The accurate estimation of grapevine biophysical parameters is important for decision support in precision viticulture. This study addresses the use of unmanned aerial vehicle (UAV) multispectral data and machine learning (ML) techniques to estimate leaf area index (LAI), pruning wood biomass, and yield, across mixed-variety vineyards in the Douro Region of Portugal. Data were collected at three phenological stages, from veraison to maturation and two modeling approaches were tested: one using only spectral features, and another combining spectral and geometric features derived from photogrammetric elevation data. Multiple linear regression (MLR) and five ML algorithms were applied, with feature selection performed using both forward and backward selection procedures. Logarithmic transformations were used to mitigate data skewness. Overall, ML algorithms provided better predictive performance than MLR, particularly when geometric features were included. At harvest-ready, Random Forest achieved the highest accuracy for LAI (R2 = 0.83) and yield (R2 = 0.75), while MLR produced the most accurate estimates for pruning wood biomass (R2 = 0.83). Among geometric variables, canopy area was the most informative. For spectral data, the Modified Soil-Adjusted Vegetation Index (MSAVI) and the Soil-Adjusted Vegetation Index (SAVI) were the most relevant. The models performed well across grapevine varieties, indicating that UAV-based monitoring can serve as a practical, non-invasive, and scalable approach for vineyard management in heterogeneous vineyards. Full article
(This article belongs to the Special Issue Retrieving Leaf Area Index Using Remote Sensing)
Show Figures

Figure 1

24 pages, 5841 KB  
Article
Probing Early and Long-Term Drought Responses in Kauri Using Canopy Hyperspectral Imaging
by Mark Jayson B. Felix, Russell Main, Michael S. Watt and Taoho Patuawa
Remote Sens. 2025, 17(23), 3914; https://doi.org/10.3390/rs17233914 - 3 Dec 2025
Viewed by 955
Abstract
Global increases in drought frequency and severity pose growing risks to forest resilience, particularly for long-lived endemic tree species such as kauri (Agathis australis). Building on prior leaf-level work, this study assessed the utility of multitemporal canopy-scale hyperspectral imaging to characterise [...] Read more.
Global increases in drought frequency and severity pose growing risks to forest resilience, particularly for long-lived endemic tree species such as kauri (Agathis australis). Building on prior leaf-level work, this study assessed the utility of multitemporal canopy-scale hyperspectral imaging to characterise water stress in both controlled nursery and field conditions. Two complementary experiments were undertaken: (i) a 10-week controlled-environment experiment comparing drought and control groups, and (ii) a field-based assessment of juvenile kauri trees across multiple time points with contrasting soil volumetric water content. In the controlled-environment experiment, drought-treated seedlings exhibited delayed physiological responses, with reductions in stomatal conductance and assimilation emerging only after three weeks. In contrast, time-series analysis of narrow band hyperspectral indices (NBHIs) revealed detectable stress signatures within one week after drought initiation, with early sensitivity driven by structural and pigment-related indices. As stress progressed, pigment-specific indices became the dominant predictors. These findings were consistent with the field-based experiment. Variation in leaf equivalent water thickness (EWT) was strongly explained by pigment-sensitive indices, including Pigment Specific Simple Ratio Carotenoid (PSSRc) and Carotenoid Reflectance indices (CRI700 and CRI550), which together accounted for ca. 87% of the variance. Structural indices such as the Normalised Difference Vegetation Index (NDVI) also ranked among the top 20 predictors, but had comparatively lower explanatory power (<75%). Overall, the two experiments show that canopy-based hyperspectral imaging provides early, sensitive, and consistent detection of water stress in kauri. The findings highlight a scalable approach for monitoring drought impacts on kauri and offer a foundation for developing operational forest health tools under increasing climate pressure. Full article
(This article belongs to the Collection Feature Papers for Section Environmental Remote Sensing)
Show Figures

Figure 1

36 pages, 22245 KB  
Article
CMSNet: A SAM-Enhanced CNN–Mamba Framework for Damaged Building Change Detection in Remote Sensing Imagery
by Jianli Zhang, Liwei Tao, Wenbo Wei, Pengfei Ma and Mengdi Shi
Remote Sens. 2025, 17(23), 3913; https://doi.org/10.3390/rs17233913 - 3 Dec 2025
Viewed by 1204
Abstract
In war and explosion scenarios, buildings often suffer varying degrees of damage characterized by complex, irregular, and fragmented spatial patterns, posing significant challenges for remote sensing–based change detection. Additionally, the scarcity of high-quality datasets limits the development and generalization of deep learning approaches. [...] Read more.
In war and explosion scenarios, buildings often suffer varying degrees of damage characterized by complex, irregular, and fragmented spatial patterns, posing significant challenges for remote sensing–based change detection. Additionally, the scarcity of high-quality datasets limits the development and generalization of deep learning approaches. To overcome these issues, we propose CMSNet, an end-to-end framework that integrates the structural priors of the Segment Anything Model (SAM) with the efficient temporal modeling and fine-grained representation capabilities of CNN–Mamba. Specifically, CMSNet adopts CNN–Mamba as the backbone to extract multi-scale semantic features from bi-temporal images, while SAM-derived visual priors guide the network to focus on building boundaries and structural variations. A Pre-trained Visual Prior-Guided Feature Fusion Module (PVPF-FM) is introduced to align and fuse these priors with change features, enhancing robustness against local damage, non-rigid deformations, and complex background interference. Furthermore, we construct a new RWSBD (Real-world War Scene Building Damage) dataset based on Gaza war scenes, comprising 42,732 annotated building damage instances across diverse scales, offering a strong benchmark for real-world scenarios. Extensive experiments on RWSBD and three public datasets (CWBD, WHU-CD, and LEVIR-CD+) demonstrate that CMSNet consistently outperforms eight state-of-the-art methods in both quantitative metrics (F1, IoU, Precision, Recall) and qualitative evaluations, especially in fine-grained boundary preservation, small-scale change detection, and complex scene adaptability. Overall, this work introduces a novel detection framework that combines foundation model priors with efficient change modeling, along with a new large-scale war damage dataset, contributing valuable advances to both research and practical applications in remote sensing change detection. Additionally, the strong generalization ability and efficient architecture of CMSNet highlight its potential for scalable deployment and practical use in large-area post-disaster assessment. Full article
Show Figures

Figure 1

25 pages, 9230 KB  
Article
Analysis of the Statistical Relationship Between Vertical Ground Displacements and Selected Explanatory Factors: A Case Study of the Underground Gas Storage Area, Kosakowo, Poland
by Anna Buczyńska, Aleksandra Kaczmarek, Dariusz Głąbicki and Jan Blachowski
Remote Sens. 2025, 17(23), 3912; https://doi.org/10.3390/rs17233912 - 2 Dec 2025
Viewed by 627
Abstract
Underground gas storage (UGS) facilities may cause ground displacements as a result of the cavern convergence or regular gas injection (alternate ground uplift and subsidence). The occurrence and scale of displacements are strongly dependent on the storage time and cavern capacity. At an [...] Read more.
Underground gas storage (UGS) facilities may cause ground displacements as a result of the cavern convergence or regular gas injection (alternate ground uplift and subsidence). The occurrence and scale of displacements are strongly dependent on the storage time and cavern capacity. At an early stage of facility operation, displacements can be difficult to detect in the presence of wetlands. The main objective of this study was to describe the global and local relationships between vertical ground displacements observed over a small and relatively new Kosakowo UGS facility (Poland) from 2014 to 2024 (dependent variable) and selected topographic, hydrological, and mining factors (independent variables). The dependent variable was determined through SBAS-InSAR analysis of Sentinel-1 SAR data, while the independent variables were developed using passive Sentinel-2 imagery and open geospatial data. The global relationships between variables were described using Ordinary Least Squares (OLS) and Generalized Linear Regression (GLR) models, while the Geographically Weighted Regression (GWR) model was utilized to analyze local relations. The results obtained indicate that ground displacements were characterized by seasonal fluctuations between 4 mm and 10 mm. The factors that had, both globally and locally, the strongest influence were soil moisture, vegetation water content, and the flora condition, indicating that the environmental hydrogeology had the greatest impact on the phenomenon under study. None of the considered models identified underground gas storage as a significant contributing factor to the observed ground displacements. The results confirm that the presence of wetlands can be a significant obstacle to an accurate description of the impact of gas storage on the ground movements, especially in UGS areas at an early stage of operation. Full article
Show Figures

Graphical abstract

31 pages, 37241 KB  
Article
DEM-Based UAV Geolocation of Thermal Hotspots on Complex Terrain
by Lucile Rossi, Frédéric Morandini, Antoine Burglin, Jean Bertrand, Clément Wandon, Aurélien Tollard and Antoine Pieri
Remote Sens. 2025, 17(23), 3911; https://doi.org/10.3390/rs17233911 - 2 Dec 2025
Viewed by 1051
Abstract
Reliable geolocation of thermal hotspots, such as smoldering embers that can reignite after vegetation fire suppression, deep-seated peat fires, or underground coal seam fires, is critical to prevent fire resurgence, limit prolonged greenhouse gas emissions, and mitigate environmental and health impacts. This study [...] Read more.
Reliable geolocation of thermal hotspots, such as smoldering embers that can reignite after vegetation fire suppression, deep-seated peat fires, or underground coal seam fires, is critical to prevent fire resurgence, limit prolonged greenhouse gas emissions, and mitigate environmental and health impacts. This study develops and tests an algorithm to estimate the GPS positions of thermal hotspots detected in infrared images acquired by an unmanned aerial vehicle (UAV), designed to operate over flat and mountainous terrain. Its originality lies in a reformulated Bresenham traversal of the digital elevation model (DEM), combined with a lightweight, ray-tracing-inspired strategy that efficiently detects the intersection of the optical ray with the terrain by approximating the ray altitude at the cell level. UAV flight experiments in complex terrain were conducted, with thermal image acquisitions performed at 60 m and 120 m above ground level and simulated hotspots generated using controlled heat sources. The tests were carried out with two thermal cameras: a Zenmuse H20T mounted on a Matrice 300 UAV flown both with and without Real-Time Kinematic (RTK) positioning, and a Matrice 30T UAV without RTK. The implementation supports both real-time and post-processed operation modes. The results demonstrated robust and reliable geolocation performance, with mean positional errors consistently below 4.2 m for all the terrain configurations tested. A successful real-time operation in the test confirmed the suitability of the algorithm for time-critical intervention scenarios. Since July 2024, the post-processed version of the method has been in operational use by the Corsica fire services. Full article
Show Figures

Graphical abstract

28 pages, 3284 KB  
Article
Diffusion-Enhanced Underwater Debris Detection via Improved YOLOv12n Framework
by Jianghan Tao, Fan Zhao, Yijia Chen, Yongying Liu, Feng Xue, Jian Song, Hao Wu, Jundong Chen, Peiran Li and Nan Xu
Remote Sens. 2025, 17(23), 3910; https://doi.org/10.3390/rs17233910 - 2 Dec 2025
Cited by 4 | Viewed by 1132
Abstract
Detecting underwater debris is important for monitoring the marine environment but remains challenging due to poor image quality, visual noise, object occlusions, and diverse debris appearances in underwater scenes. This study proposes UDD-YOLO, a novel detection framework that, for the first time, applies [...] Read more.
Detecting underwater debris is important for monitoring the marine environment but remains challenging due to poor image quality, visual noise, object occlusions, and diverse debris appearances in underwater scenes. This study proposes UDD-YOLO, a novel detection framework that, for the first time, applies a diffusion-based model to underwater image enhancement, introducing a new paradigm for improving perceptual quality in marine vision tasks. Specifically, the proposed framework integrates three key components: (1) a Cold Diffusion module that acts as a pre-processing stage to restore image clarity and contrast by reversing deterministic degradation such as blur and occlusion—without injecting stochastic noise—making it the first diffusion-based enhancement applied to underwater object detection; (2) an AMC2f feature extraction module that combines multi-scale separable convolutions and learnable normalization to improve representation for targets with complex morphology and scale variation; and (3) a Unified-IoU (UIoU) loss function designed to dynamically balance localization learning between high- and low-quality predictions, thereby reducing errors caused by occlusion or boundary ambiguity. Extensive experiments are conducted on the public underwater plastic pollution detection dataset, which includes 15 categories of underwater debris. The proposed method achieves a mAP50 of 81.8%, with 87.3% precision and 75.1% recall, surpassing eleven advanced detection models such as Faster R-CNN, RT-DETR-L, YOLOv8n, and YOLOv12n. Ablation studies verify the function of every module. These findings show that diffusion-driven enhancement, when coupled with feature extraction and localization optimization, offers a promising direction for accurate, robust underwater perception, opening new opportunities for environmental monitoring and autonomous marine systems. Full article
Show Figures

Figure 1

7 pages, 166 KB  
Editorial
Advancing Positioning, Navigation, and Timing (PNT) Service Using Satellite Navigation Technology
by Ke Su, Liangliang Yuan, Yulong Ge, Amir Allahvirdi-Zadeh and Guo Chen
Remote Sens. 2025, 17(23), 3909; https://doi.org/10.3390/rs17233909 - 2 Dec 2025
Viewed by 1066
Abstract
As a pivotal spatiotemporal infrastructure in the modern information society, satellite navigation provides global users with high-precision, all-weather, and round-the-clock Positioning, Navigation, and Timing (PNT) services [...] Full article
29 pages, 3652 KB  
Article
Application of MLS and UAS-SfM for Beach Management at the North Padre Island Seawall
by Isabel A. Garcia-Williams, Michael J. Starek, Deidre D. Williams, Philippe E. Tissot, Jacob Berryhill and James C. Gibeaut
Remote Sens. 2025, 17(23), 3908; https://doi.org/10.3390/rs17233908 - 2 Dec 2025
Viewed by 2262
Abstract
Collecting accurate and reliable beach morphology data is essential for informed coastal management. The beach adjacent to the seawall on North Padre Island, Texas, USA has experienced increased erosion and disrupted natural processes. City ordinance mandates the placement of bollards to restrict vehicular [...] Read more.
Collecting accurate and reliable beach morphology data is essential for informed coastal management. The beach adjacent to the seawall on North Padre Island, Texas, USA has experienced increased erosion and disrupted natural processes. City ordinance mandates the placement of bollards to restrict vehicular traffic when the beach width from the seawall toe to mean high water (MHW) is less than 45.7 m. To aid the City of Corpus Christi’s understanding of seasonal beach changes, mobile lidar scanning (MLS) surveys with a mapping-grade system were conducted in February, June, September, and November 2023, and post-nourishment in March 2024. Concurrent uncrewed aircraft system (UAS) photogrammetry surveys were performed in February and November 2023, and March 2024 to aid beach monitoring analysis and for comparative assessment to the MLS data. MLS-derived digital elevation models (DEMs) were used to evaluate seasonal geomorphology, including beach slope, width, shoreline position, and volume change. Because MHW was submerged during all surveys, highest astronomical tide (HAT) was used for shoreline analyses. HAT-based results indicated that bollards should be placed from approximately 390 to 560 m from the northern end of the seawall, varying seasonally. The March 2024 post-nourishment survey showed 102,462 m3 of sand was placed on the beach, extending the shoreline by more than 40 m in some locations. UAS photogrammetry-derived DEMs were compared to the MLS-derived DEMs, revealing mean HAT position differences of 0.02 m in February 2023 and 0.98 m in November 2023. Elevation and volume assessments showed variability between the MLS and UAS-SfM DEMs, with neither indicating consistently higher or lower values. Full article
Show Figures

Figure 1

25 pages, 4159 KB  
Article
Integrating Satellite and Field Data for Glacier Melt Modeling in High-Mountain Asia: A Case Study on Passu Glacier
by Blanka Barbagallo, Davide Fugazza, Guglielmina Adele Diolaiuti and Antonella Senese
Remote Sens. 2025, 17(23), 3907; https://doi.org/10.3390/rs17233907 - 2 Dec 2025
Viewed by 909
Abstract
Glaciers in High-Mountain Asia, the so-called “Third Pole,” are critical water sources but remain poorly monitored due to rugged topography and limited accessibility. We present an integrated approach that combines remote sensing with ground-based observations to model ice melt of the Passu Glacier [...] Read more.
Glaciers in High-Mountain Asia, the so-called “Third Pole,” are critical water sources but remain poorly monitored due to rugged topography and limited accessibility. We present an integrated approach that combines remote sensing with ground-based observations to model ice melt of the Passu Glacier (Pakistan) from 5 August to 13 October 2023. Meteorological data from two automatic weather stations and ablation measurements from four stakes were used together with satellite-derived albedo (Landsat 8 OLI), surface temperature (Landsat 9 TIRS), and topography (ALOS AW3D30 DSM) to implement an enhanced T-index melt model accounting for net shortwave and longwave radiation. Model performance was evaluated against station and satellite data and ablation stake measurements using leave-one-out cross-validation. The estimated total ice melt volume was 16 million m3 w.e. during the monitoring period, with an average melt of 3.60 m w.e. The model reproduced observed stake ablation with an uncertainty of 0.48 m w.e. (9% of average measured melt). Elevation was identified as the dominant melt driver (β = −0.501, unique R2 = 0.199), with aspect and slope exerting secondary influences through their effect on solar radiation and shading. Our findings demonstrate that combining minimal but strategically located field data with satellite products provides a physically consistent and scalable framework for glacier melt estimation in data-scarce regions of the Third Pole, with relevance for hydrological monitoring and climate adaptation. Full article
(This article belongs to the Special Issue Advances in Remote Sensing for Glacier Preservation)
Show Figures

Figure 1

27 pages, 10767 KB  
Article
HCTANet: Hierarchical Cross-Temporal Attention Network for Semantic Change Detection in Complex Remote Sensing Scenes
by Zhuli Xie, Gang Wan, Zhanji Wei, Nan Li and Guangde Sun
Remote Sens. 2025, 17(23), 3906; https://doi.org/10.3390/rs17233906 - 2 Dec 2025
Viewed by 633
Abstract
Semantic change detection has become a key technology for monitoring the evolution of land cover and land use categories at the semantic level. However, existing methods often lack effective information interaction and fail to capture changes at multiple granularities using single-scale features, resulting [...] Read more.
Semantic change detection has become a key technology for monitoring the evolution of land cover and land use categories at the semantic level. However, existing methods often lack effective information interaction and fail to capture changes at multiple granularities using single-scale features, resulting in inconsistent outcomes and frequent missed or false detections. To address these challenges, we propose a three-branch model HCTANet, which enhances spatial and semantic feature representations at each time stage and models semantic correlations and differences between multi-temporal images through three innovative modules. First, the multi-scale change mapping association module extracts and fuses multi-resolution dual-temporal difference features in parallel, explicitly constraining semantic segmentation results with the change area output. Second, an adaptive collaborative semantic attention mechanism is introduced, modeling the semantic correlations of dual-temporal features via dynamic weight fusion and cross-temporal cross-attention. Third, the spatial semantic residual aggregation module aggregates global context and high-resolution shallow features through residual connections to restore pixel-level boundary details. HCTANet is evaluated on the SECOND, SenseEarth 2020 and AirFC datasets, and the results show that it outperforms existing methods in metrics such as mIoU and SeK, demonstrating its superior capability and effectiveness in accurately detecting semantic changes in complex remote sensing scenarios. Full article
Show Figures

Figure 1

25 pages, 49354 KB  
Article
Displacement Time Series Forecasting Using Sentinel-1 SBAS-InSAR Results in a Mining Subsidence Case Study—Evaluation of Machine Learning and Deep Learning Methods
by Dariusz Głąbicki
Remote Sens. 2025, 17(23), 3905; https://doi.org/10.3390/rs17233905 - 2 Dec 2025
Viewed by 1416
Abstract
With an abundance of data provided by satellite-based measurements, such as Synthetic Aperture Radar Interferometry (InSAR) or the Global Navigation Satellite System (GNSS), an interest has grown in training highly complex data-driven models for geophysical applications, including displacement modeling. These methods, including machine [...] Read more.
With an abundance of data provided by satellite-based measurements, such as Synthetic Aperture Radar Interferometry (InSAR) or the Global Navigation Satellite System (GNSS), an interest has grown in training highly complex data-driven models for geophysical applications, including displacement modeling. These methods, including machine learning (ML) and deep learning (DL) algorithms, represent a new approach to forecasting ground surface displacements. Yet, the effectiveness of such methods, including their generalization capabilities and performance on non-linear data, remains underexplored. This paper examines the performance of various data-driven algorithms, including regression models and deep neural networks, in predicting mining-induced subsidence. Ground surface displacement data obtained from the Small Baseline Subset (SBAS) InSAR were used as time series samples for training and validation. ML and DL models were evaluated over varying forecast horizons. The results show that data-driven approaches can effectively model InSAR-derived ground subsidence in mining areas. Deep learning models outperform other ML-based models, indicating that increased model complexity can lead to better forecasting accuracy. Nevertheless, it is shown that careful examination of performance metrics and forecast errors in the spatial domain is essential for appropriate model evaluation. The findings demonstrate that combining SBAS-InSAR measurements with data-driven modeling offers a promising direction for developing automated systems for monitoring and forecasting mining-induced ground deformation. Full article
Show Figures

Figure 1

21 pages, 15129 KB  
Article
Vertical Characteristics of an Ozone Pollution Episode in Hong Kong Under the Typhoon Mawar—A Case Study
by Libin Zhu, Jie Wang, Yiwei Xu, Na Ma, Xiaoquan Song, Jie Qin, Beibei Li, Wilson B. C. Tsui, Lihui Lv and Tianshu Zhang
Remote Sens. 2025, 17(23), 3904; https://doi.org/10.3390/rs17233904 - 1 Dec 2025
Viewed by 939
Abstract
This study investigates a typical ozone pollution episode in Hong Kong from May 29 to 31, 2023. Based on the observations of a Differential Absorption Lidar (DIAL) system, both ozone and aerosols accumulated below 1.5 km during the pollution episode. Ozone exhibited distinct [...] Read more.
This study investigates a typical ozone pollution episode in Hong Kong from May 29 to 31, 2023. Based on the observations of a Differential Absorption Lidar (DIAL) system, both ozone and aerosols accumulated below 1.5 km during the pollution episode. Ozone exhibited distinct formation and accumulation characteristics, with concentrations exceeding 200 μg m−3. Aerosols presented evident features of regional transport and local coupling, with extinction coefficients surpassing 1.1 km−1. During late spring to early summer, the northward extension of the Western Pacific Subtropical High (WPSH) established favorable conditions for ozone production. This background was amplified by Typhoon Mawar, whose peripheral circulation channeled pollutants from the Pearl River Delta into Hong Kong through horizontal and vertical pathways, significantly worsening near-surface air quality. The episode was eventually mitigated, as enhanced vertical mixing facilitated the dispersion and removal of accumulated pollutants. These results highlight the critical role of meteorological–chemical interactions in shaping this ozone pollution episode. Full article
Show Figures

Graphical abstract

35 pages, 7641 KB  
Article
Versatile Fourier Transform Spectrometer Model for Earth Observation Missions Validated with In-Flight Systems Measurements
by Tom Piekarski, Christophe Buisset, Anne Kleinert, Felix Friedl-Vallon, Arnaud Heliere, Julian Hofmann, Ljubiša Babić, Micael Dias Miranda, Tobias Guggenmoser, Daniel Lamarre, Flavio Mariani, Felice Vanin and Ben Veihelmann
Remote Sens. 2025, 17(23), 3903; https://doi.org/10.3390/rs17233903 - 30 Nov 2025
Viewed by 803
Abstract
Fourier transform spectrometers (FTSs) are cornerstone instruments in Earth observation space missions, effectively monitoring atmospheric gases in missions such as Michelson Interferometer for Passive Atmospheric Sounding (MIPAS), and Infrared Atmospheric Sounding Interferometer (IASI). It will also be the core instrument of Meteosat Third [...] Read more.
Fourier transform spectrometers (FTSs) are cornerstone instruments in Earth observation space missions, effectively monitoring atmospheric gases in missions such as Michelson Interferometer for Passive Atmospheric Sounding (MIPAS), and Infrared Atmospheric Sounding Interferometer (IASI). It will also be the core instrument of Meteosat Third Generation—Sounding (MTG-S) and the future Earth Explorer (EE) mission Far-infrared Outgoing Radiation Understanding and Monitoring (FORUM). Building on this legacy, the European Space Agency (ESA) has developed an FTS instrument and an inverse model designed to estimate the radiometric and spectral performance from a set of instrumental parameters. The model and its validation using in-flight measurements of the FTS instrument Gimballed Limb Observer for Radiance Imaging of the Atmosphere (GLORIA)-Lite are described in this paper. The results indicate that the difference between the model predictions and the measured signal is less than 2% relative to the average of the measurements. Moreover, we can correctly predict the instrument’s radiometric gain and offset and reconstruct a scientific science spectrum. This model can be utilised effectively to evaluate the radiometric performance of future FTS missions. Full article
Show Figures

Figure 1

18 pages, 5147 KB  
Technical Note
Assessment of Instrument Performance of the FY3E/JTSIM/DARA Radiometer Through the Analysis of TSI Observations
by Jean-Philippe Montillet, Wolfgang Finsterle, Ping Zhu, Margit Haberreiter, Silvio Koller, Daniel Pfiffner, Duo Wu, Xin Ye, Dongjun Yang, Wei Fang, Jin Qi and Peng Zhang
Remote Sens. 2025, 17(23), 3902; https://doi.org/10.3390/rs17233902 - 30 Nov 2025
Viewed by 447
Abstract
Since the late 1970s, satellite missions have monitored Total Solar Irradiance (TSI), providing a long-term record of solar variability. The Digital Absolute Radiometer (DARA), onboard the Chinese Fengyun-3E (FY3E) spacecraft since 4 July 2021, contributes to extending this record. In this study, we [...] Read more.
Since the late 1970s, satellite missions have monitored Total Solar Irradiance (TSI), providing a long-term record of solar variability. The Digital Absolute Radiometer (DARA), onboard the Chinese Fengyun-3E (FY3E) spacecraft since 4 July 2021, contributes to extending this record. In this study, we evaluate the DARA observations in both World Radiometric Reference (WRR) and International System of Units (SI) scales. We compare these records with those from other instruments on different spacecraft (i.e., VIRGO/PMO6, TSIS-1/TIM) and with the co-located Solar Irradiance Absolute Radiometer (SIAR) on FY3E. A key finding is the identification and correction of an instrumental artifact: an issue in the thermal aperture model, linked to annual satellite maneuvers, repetitively introduced an artificial step of 0.15 ± 0.05 Wm−2 into the TSI measurements. A statistical analysis of the measurements in the SI scale shows that the mean value of the DARA TSI observations is approximately 1359.58 Wm−2 (6-hourly rate), which is lower than the ones recorded by VIRGO/PMO6 (1.82 Wm−2), TSIS-1/TIM (2.90 Wm−2), and SIAR (2.54 Wm−2). We estimate a degradation of ∼49 ppm over 46 months due to the exposure of the instrument to the (Extreme) Ultraviolet (UV/EUV) radiations. Finally, the corrected DARA observations are incorporated into the long-term TSI composite time series. Comparison with the PMOD/WRC composite shows only marginal differences (less than 0.015 Wm−2), confirming the consistency and reliability of including the new TSI product (i.e., JTSIM-DARAv1). Full article
(This article belongs to the Section Satellite Missions for Earth and Planetary Exploration)
Show Figures

Figure 1

26 pages, 13221 KB  
Article
Spectral Prototype Attention Domain Adaptation for Hyperspectral Image Classification
by Weina Zhang, Runshan Hu, Jierui Wang, Lanlan Zhang and Chenyang Zhu
Remote Sens. 2025, 17(23), 3901; https://doi.org/10.3390/rs17233901 - 30 Nov 2025
Cited by 2 | Viewed by 1259
Abstract
Hyperspectral image (HSI) classification is often challenged by cross-scene domain shifts and limited target annotations. Existing approaches relying on class-agnostic moment matching or confidence-based pseudo-labeling tend to blur decision boundaries, propagate noise, and struggle with spectral overlap and class imbalance. We propose Spectral [...] Read more.
Hyperspectral image (HSI) classification is often challenged by cross-scene domain shifts and limited target annotations. Existing approaches relying on class-agnostic moment matching or confidence-based pseudo-labeling tend to blur decision boundaries, propagate noise, and struggle with spectral overlap and class imbalance. We propose Spectral Prototype Attention Domain Adaptation (SPADA), a framework that integrates an attention-guided spectral–spatial backbone with dual prototype banks and distance-based posterior modeling. SPADA performs global and class-conditional alignment through source supervision, kernel-based distribution matching, and prototype coupling, followed by diversity-aware active adaptation and confidence-calibrated refinement via prior-adjusted self-training. Across multiple cross-scene benchmarks in urban and inter-city scenarios, SPADA consistently outperforms strong baselines in overall accuracy, average accuracy, and Cohen’s κ, achieving clear gains on classes affected by spectral overlap or imbalance and maintaining low variance across runs, demonstrating robust and stable domain transfer. Full article
Show Figures

Figure 1

36 pages, 106084 KB  
Article
Critical Factors for the Application of InSAR Monitoring in Ports
by Jaime Sánchez-Fernández, Alfredo Fernández-Landa, Álvaro Hernández Cabezudo and Rafael Molina Sánchez
Remote Sens. 2025, 17(23), 3900; https://doi.org/10.3390/rs17233900 - 30 Nov 2025
Viewed by 887
Abstract
Ports pose distinctive monitoring challenges due to harsh marine conditions, mixed construction typologies, and heterogeneous ground conditions. These factors complicate the routine use of satellite InSAR, especially when medium-resolution scatterers must be reliably attributed to specific assets for risk and asset management decisions. [...] Read more.
Ports pose distinctive monitoring challenges due to harsh marine conditions, mixed construction typologies, and heterogeneous ground conditions. These factors complicate the routine use of satellite InSAR, especially when medium-resolution scatterers must be reliably attributed to specific assets for risk and asset management decisions. In current practice, persistent and distributed scatterer (PS/DS) points are often interpreted in map view without an explicit positional uncertainty model or systematic linkage to three-dimensional infrastructure geometry. We present an end-to-end Differential InSAR framework tailored to large ports that fuses medium-resolution Sentinel-1 Level 2 Co-registered Single-Look Complex (L2-CSLC) stacks with high-resolution airborne LiDAR at the post-processing stage. For the Port of Bahía de Algeciras (Spain), we process 123 Sentinel-1A/B images (2020–2022) in ascending and descending geometry using PS/DS time-series analysis with ETAD-like timing corrections and RAiDER tropospheric/ionospheric mitigation. LiDAR is then used to (i) derive look-specific shadow/layover masks and (ii) perform a whitening-transformed nearest-neighbor association that assigns PS/DS points to LiDAR points under an explicit range–azimuth–cross-range (RAC) uncertainty ellipsoid. The RAC standard deviations (σr,σa,σc) are derived from the effective CSLC range/azimuth resolution and from empirical height correction statistics, providing a geometry- and data-informed prior on positional uncertainty. Finally, we render dual-geometry red–green composites (ascending to R, descending to G; shared normalization) on the LiDAR point cloud, enabling consistent inspection in plan and elevation. Across asset types, rigid steel/concrete elements (trestles, quay faces, and dolphins) sustain high coherence, small whitened offsets, and stable backscatter in both looks; cylindrical storage tanks are bright but exhibit look-dependent visibility and larger cross-range residuals due to height and curvature; and container yards and vessels show high amplitude dispersion and lower temporal coherence driven by operations. Overall, LiDAR-assisted whitening-based linking reduces effective positional ambiguity and improves structure-specific attribution for most scatterers across the port. The fusion products, geometry-aware linking plus three-dimensional dual-geometry RGB, enhance the interpretability of medium-resolution SAR and provide a transferable, port-oriented basis for integrating deformation evidence into risk and asset management workflows. Full article
Show Figures

Figure 1

16 pages, 3038 KB  
Article
Improvement of Snow Albedo Simulation Considering Water Content
by Fengyu Li and Kun Wu
Remote Sens. 2025, 17(23), 3899; https://doi.org/10.3390/rs17233899 - 30 Nov 2025
Viewed by 576
Abstract
By combining the Maxwell–Garnett mixing rule, Mie scattering, and the four-stream discrete ordinates adding method, a snow albedo model with explicit consideration of water content was constructed, and the influence of snow water content on snow albedo simulation was systematically analyzed. The results [...] Read more.
By combining the Maxwell–Garnett mixing rule, Mie scattering, and the four-stream discrete ordinates adding method, a snow albedo model with explicit consideration of water content was constructed, and the influence of snow water content on snow albedo simulation was systematically analyzed. The results indicate that liquid water content is the key factor contributing to significant changes in albedo in the near-infrared band. The albedo of snow with small particle sizes is more sensitive to water content. The water content in the surface layer of snow has a more pronounced effect on reducing albedo. The actual measurement cases at the stations on the Tibetan Plateau, Xinjiang, and Northeast China show that the model established here provides a good simulation of albedo accuracy, with a bias of −0.0069 and a Root Mean Square Error (RMSE) of 0.0583 compared to the observations. This indicates that the model has a strong ability to express physical mechanisms and performs stably in complex environments, thereby demonstrating good regional applicability. This model can also be applied to wet snow containing impurities in the future. Full article
(This article belongs to the Special Issue Remote Sensing Modelling and Measuring Snow Cover and Snow Albedo)
Show Figures

Figure 1

Previous Issue
Back to TopTop