Remote Sensing

29 pages, 8182 KB

Open AccessArticle

CResDAE: A Deep Autoencoder with Attention Mechanism for Hyperspectral Unmixing

by Chong Zhao, Jinlin Wang, Qingqing Qiao, Kefa Zhou, Jiantao Bi, Qing Zhang, Wei Wang, Dong Li, Tao Liao, Chao Li, Heshun Qiu and Guangjun Qu

Remote Sens. 2025, 17(21), 3622; https://doi.org/10.3390/rs17213622 (registering DOI) - 31 Oct 2025

Abstract

Hyperspectral unmixing aims to extract pure spectral signatures (endmembers) and estimate their corresponding abundance fractions from mixed pixels, enabling quantitative analysis of surface material composition. However, in geological mineral exploration, existing unmixing methods often fail to explicitly identify informative spectral bands, lack inter-layer [...] Read more.

Hyperspectral unmixing aims to extract pure spectral signatures (endmembers) and estimate their corresponding abundance fractions from mixed pixels, enabling quantitative analysis of surface material composition. However, in geological mineral exploration, existing unmixing methods often fail to explicitly identify informative spectral bands, lack inter-layer information transfer mechanisms, and overlook the physical constraints intrinsic to the unmixing process. These issues result in limited directionality, sparsity, and interpretability. To address these limitations, this paper proposes a novel model, CResDAE, based on a deep autoencoder architecture. The encoder integrates a channel attention mechanism and deep residual modules to enhance its ability to assign adaptive weights to spectral bands in geological hyperspectral unmixing tasks. The model is evaluated by comparing its performance with traditional and deep learning-based unmixing methods on synthetic datasets, and through a comparative analysis with a nonlinear autoencoder on the Urban hyperspectral scene. Experimental results show that CResDAE consistently outperforms both conventional and deep learning counterparts. Finally, CResDAE is applied to GF-5 hyperspectral imagery from Yunnan Province, China, where it effectively distinguishes surface materials such as Forest, Grassland, Silicate, Carbonate, and Sulfate, offering reliable data support for geological surveys and mineral exploration in covered regions. Full article

(This article belongs to the Special Issue AI-Driven Hyperspectral Remote Sensing of Atmosphere and Land)

23 pages, 2222 KB

Open AccessArticle

Shallow Sea Bathymetric Inversion of Active–Passive Satellite Remote Sensing Data Based on Virtual Control Point Inverse Distance Weighting

by Zhipeng Dong, Junlin Tao, Yanxiong Liu, Yikai Feng, Yilan Chen and Yanli Wang

Remote Sens. 2025, 17(21), 3621; https://doi.org/10.3390/rs17213621 (registering DOI) - 31 Oct 2025

Abstract

Satellite-derived bathymetry (SDB) using Ice, Cloud, and Land Elevation satellite-2 (ICESat-2) LiDAR data and remote sensing images faces challenges in the difficulty of uniform coverage of the inversion area by the bathymetric control points due to the linear sampling pattern of ICESat-2. This [...] Read more.

Satellite-derived bathymetry (SDB) using Ice, Cloud, and Land Elevation satellite-2 (ICESat-2) LiDAR data and remote sensing images faces challenges in the difficulty of uniform coverage of the inversion area by the bathymetric control points due to the linear sampling pattern of ICESat-2. This study proposes a novel virtual control point optimization framework integrating inverse distance weighting (IDW) and spectral confidence analysis (SCA). The methodology first generates baseline bathymetry through semi-empirical band ratio modeling (control group), then extracts virtual control points via SCA. An optimization scheme based on spectral confidence levels is applied to the control group, where high-confidence pixels utilized a residual correction-based strategy, while low-confidence pixels employed IDW interpolation based on a virtual control point. Finally, the preceding optimization scheme uses weighting-based fusion with the control group to generate the final bathymetry map, which is also called the optimized group. Accuracy assessments over the three research areas revealed a significant increase in accuracy from the control group to the optimized group. When compared with in situ data, the determination coefficient (R²), RMSE, MRE, and MAE in the optimized group are better than 0.83, 1.48 m, 12.36%, and 1.22 m, respectively, and all these indicators are better than those in the control group. The key innovation lies in overcoming ICESat-2’s spatial sampling limitation through spectral confidence stratification, which uses SCA to generate virtual control points and IDW to adjust low-confidence pixel values. It is also suggested that when applying ICESat-2 satellite data in active–passive-fused SDB, the distribution of training data in the research zone should be adequately considered. Full article

(This article belongs to the Special Issue Applications of Remote Sensing in Oceanography: Prospects and Challenges (3rd Edition))

24 pages, 4796 KB

Open AccessArticle

Forest Height Estimation in Jiangsu: Integrating Dual-Polarimetric SAR, InSAR, and Optical Remote Sensing Features

by Fangyi Li, Yiheng Jiang, Yumei Long, Wenmei Li and Yuhong He

Remote Sens. 2025, 17(21), 3620; https://doi.org/10.3390/rs17213620 (registering DOI) - 31 Oct 2025

Abstract

Forest height is a key structural parameter for evaluating ecological functions, biodiversity, and carbon dynamics. While LiDAR and Synthetic Aperture Radar (SAR) provide vertical structure information, their large-scale use is restricted by sparse sampling (LiDAR) and temporal decorrelation (SAR). Optical remote sensing offers [...] Read more.

Forest height is a key structural parameter for evaluating ecological functions, biodiversity, and carbon dynamics. While LiDAR and Synthetic Aperture Radar (SAR) provide vertical structure information, their large-scale use is restricted by sparse sampling (LiDAR) and temporal decorrelation (SAR). Optical remote sensing offers complementary spectral information but lacks direct height retrieval. To address these limitations, we developed a multi-modal framework integrating GEDI waveform LiDAR, Sentinel-1 SAR (InSAR and PolSAR), and Sentinel-2 multispectral data, combined with machine learning, to estimate forest canopy height across Jiangsu Province, China. GEDI L2A footprints were used as training labels, and a suite of structural and spectral features was extracted from SAR, GEDI, and Sentinel-2 data as input variables for canopy height estimation. The performance of two ensemble algorithms, Random Forest (RF) and Gradient Tree Boosting (GTB) for canopy height estimation, was evaluated through stratified five-fold cross-validation. RF consistently outperformed GTB, with the integration of SAR, GEDI, and optical features achieving the best accuracy (R² = 0.708, RMSE = 2.564 m). The results demonstrate that InSAR features substantially enhance sensitivity to vertical heterogeneity, improving forest height estimation accuracy. These findings highlight the advantage of incorporating SAR, particularly InSAR with optical data, in enhancing sensitivity to vertical heterogeneity and improving the performance of RF and GTB in estimating forest height. The framework we proposed is scalable to other regions and has the potential to contribute to global sustainable forest monitoring initiatives. Full article

(This article belongs to the Special Issue Monitoring and Managing Environmental Sustainability Using Remote Sensing (Second Edition))

► Show Figures

Figure 1

28 pages, 1629 KB

Open AccessReview

Dual-Polarization Radar Quantitative Precipitation Estimation (QPE): Principles, Operations, and Challenges

by Zhe Zhang, Zhanfeng Zhao, Youcun Qi and Muqi Xiong

Remote Sens. 2025, 17(21), 3619; https://doi.org/10.3390/rs17213619 (registering DOI) - 31 Oct 2025

Abstract

Quantitative precipitation estimation (QPE) is one of the primary applications of weather radar. Over the last several decades, dual-polarization radars have significantly improved QPE accuracy by providing additional observational variables that offer more microphysical information about precipitation particles. In this work, we review [...] Read more.

Quantitative precipitation estimation (QPE) is one of the primary applications of weather radar. Over the last several decades, dual-polarization radars have significantly improved QPE accuracy by providing additional observational variables that offer more microphysical information about precipitation particles. In this work, we review QPE methods for dual-polarization radars and summarize their advantages and disadvantages from both theoretical and practical perspectives. The development paths and current status of operational QPE systems in the United States, China, and France are examined. We demonstrate how dual-polarization radars have improved QPE accuracy in these systems not only directly through the application of polarimetric QPE methods, but also indirectly through the more accurate identification of non-meteorological echoes, the mitigation of the partial blockage effect, and the detection of melting layers. The challenges are discussed for dual-polarization radar QPE, including the quality of polarimetric variables, QPE quality in complex terrain, estimation of surface precipitation with observations within or above the melting layer, and polarimetric QPE methods for snow. Full article

(This article belongs to the Special Issue Monitoring and Early Warning for Heavy Precipitation, Flash Floods and Waterlogging Disasters Using Remote Sensing)

29 pages, 10850 KB

Open AccessReview

RTM Surrogate Modeling in Optical Remote Sensing: A Review of Emulation for Vegetation and Atmosphere Applications

by Jochem Verrelst, Miguel Morata, José Luis García-Soria, Yilin Sun, Jianbo Qi and Juan Pablo Rivera-Caicedo

Remote Sens. 2025, 17(21), 3618; https://doi.org/10.3390/rs17213618 (registering DOI) - 31 Oct 2025

Abstract

Radiative transfer models (RTMs) are foundational to optical remote sensing for simulating vegetation and atmospheric properties. However, their significant computational cost, especially for 3D RTMs and large-scale applications, severely limits their utility. Emulation, or surrogate modeling, has emerged as a highly effective strategy, [...] Read more.

Radiative transfer models (RTMs) are foundational to optical remote sensing for simulating vegetation and atmospheric properties. However, their significant computational cost, especially for 3D RTMs and large-scale applications, severely limits their utility. Emulation, or surrogate modeling, has emerged as a highly effective strategy, accurately and efficiently replicating RTM outputs. This review comprehensively surveys recent developments in emulating vegetation and atmospheric RTMs. We discuss the methodological underpinnings, including suitable machine learning regression algorithms (MLRAs), effective training sampling strategies (e.g., Latin Hypercube Sampling, active learning), and spectral dimensionality reduction (DR) methods (e.g., PCA, autoencoders). Emulators commonly achieve

10^{2} - 10^{6} \times

per-evaluation acceleration, but accuracy–efficiency trade-offs remain inherently context-dependent, governed by the MLRA design and the coverage/quality of training data. DR consistently shifts this trade-off toward lower cost at comparable accuracy, positioning latent-space training as a pragmatic choice for hyperspectral applications. We synthesize key emulation applications such as global sensitivity analysis, synthetic scene generation, scene-to-scene translation (e.g., multispectral-to-hyperspectral), and retrieval of geophysical variables using remote sensing data. The paper concludes by outlining persistent challenges in generalizability, interpretability, and scalability, while also proposing future research avenues: investigating advanced deep learning algorithms (e.g., physics-informed and explainable architectures), developing multimodal/multitemporal frameworks, and establishing community benchmarks, tools and libraries. Emulation ultimately empowers remote sensing workflows with unparalleled scalability, transforming previously unmanageable tasks into viable solutions for operational Earth observation applications. Full article

(This article belongs to the Special Issue Remote Sensing and Machine Learning in Vegetation Biophysical Parameters Estimation (Second Edition))

29 pages, 10037 KB

Open AccessArticle

Assessing the Feasibility of Satellite-Based Machine Learning for Turbidity Estimation in the Dynamic Mersey Estuary (Case Study: River Mersey, UK)

by Deelaram Nangir, Manolia Andredaki and Iacopo Carnacina

Remote Sens. 2025, 17(21), 3617; https://doi.org/10.3390/rs17213617 (registering DOI) - 31 Oct 2025

Abstract

The monitoring of turbidity in estuarine environments is a challenging essential task for managing water quality and ecosystem health. This study focuses on the lower reaches of the River Mersey, Liverpool. Harmonized Sentinel-2 MSI Level-2A imagery was integrated with in situ measurements from [...] Read more.

The monitoring of turbidity in estuarine environments is a challenging essential task for managing water quality and ecosystem health. This study focuses on the lower reaches of the River Mersey, Liverpool. Harmonized Sentinel-2 MSI Level-2A imagery was integrated with in situ measurements from seven Environment Agency monitoring stations for two consecutive years (January 2023–January 2025). The workflow included image preprocessing, spectral index calculation, and the application of four machine learning algorithms: Gradient Boosting Regressor, XGBoost, Support Vector Regressor, and K-Nearest Neighbors. Among these, Gradient Boosting Regressor achieved the highest predictive accuracy (R² = 0.84; RMSE = 15.0 FTU), demonstrating the suitability of ensemble tree-based methods for capturing non-linear interactions between spectral indices and water quality parameters. Residual analysis revealed systematic errors linked to tidal cycles, depth variation, and salinity-driven stratification, underscoring the limitations of purely data-driven approaches. The novelty of this study lies in demonstrating the feasibility and proof-of-concept of using machine learning to derive spatially explicit turbidity estimates under data-limited estuarine conditions. These results open opportunities for future integration with Computational Fluid Dynamics models to enhance temporal forecasting and physical realism in estuarine monitoring systems. The proposed methodology contributes to sustainable coastal management, pollution monitoring, and climate resilience, while offering a transferable framework for other estuaries worldwide. Full article

(This article belongs to the Special Issue Recent Advances in Remote Sensing Products for Water and Environment Monitoring)

24 pages, 10066 KB

Open AccessArticle

CSLTNet: A CNN-LSTM Dual-Branch Network for Particulate Matter Concentration Retrieval

by Linjun Yao, Zhaobin Wang and Yaonan Zhang

Remote Sens. 2025, 17(21), 3616; https://doi.org/10.3390/rs17213616 (registering DOI) - 31 Oct 2025

Abstract

The concentrations of atmospheric particulate matter (PM₁₀ and PM_2.5) significantly impact global environment, human health, and climate change. This study developed a particulate matter concentration retrieval method based on multi-source data, proposing a dual-branch retrieval network architecture named CSLTNet that [...] Read more.

The concentrations of atmospheric particulate matter (PM₁₀ and PM_2.5) significantly impact global environment, human health, and climate change. This study developed a particulate matter concentration retrieval method based on multi-source data, proposing a dual-branch retrieval network architecture named CSLTNet that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. The CNN branch is designed to extract spatial features, while the LSTM branch captures temporal characteristics, with attention modules incorporated into both the CNN and LSTM branches to enhance feature extraction capabilities. Notably, the model demonstrates robust spatial generalization capability across different geographical regions.Comprehensive experimental evaluations demonstrate the outstanding performance of the CSLTNet model. For the Beijing–Tianjin–Hebei region in China: in PM₁₀ retrieval, sample-based 10-fold cross-validation achieved R² = 0.9427 (RMSE =

16.47 μ g / m^{3}

), while station-based validation yielded R² = 0.9213 (RMSE =

19.50 μ g / m^{3}

); for PM_2.5 retrieval, sample-based 10-fold cross-validation resulted in R² = 0.9579 (RMSE =

6.49 μ g / m^{3}

), with station-based validation reaching R² = 0.9296 (RMSE =

8.32 μ g / m^{3}

). For Northwest China: in PM₁₀ retrieval, sample-based 10-fold cross-validation achieved R² = 0.9236 (RMSE =

34.52 μ g / m^{3}

), while station-based validation yielded R² = 0.9046 (RMSE =

37.24 μ g / m^{3}

); for PM_2.5 retrieval, sample-based 10-fold cross-validation resulted in R² = 0.9279 (RMSE =

10.56 μ g / m^{3}

), with station-based validation reaching R² = 0.8787 (RMSE =

13.71 μ g / m^{3}

). Full article

(This article belongs to the Section Atmospheric Remote Sensing)

23 pages, 8342 KB

Open AccessArticle

Digital Twin-Ready Earth Observation: Operationalizing GeoML for Agricultural CO₂ Flux Monitoring at Field Scale

by Asima Khan, Muhammad Ali, Akshatha Mandadi, Ashiq Anjum and Heiko Balzter

Remote Sens. 2025, 17(21), 3615; https://doi.org/10.3390/rs17213615 (registering DOI) - 31 Oct 2025

Abstract

Operationalizing Earth Observation (EO)-based Machine Learning (ML) algorithms (or GeoML) for ingestion in environmental Digital Twins remains a challenging task due to the complexities associated with balancing real-time inference with cost, data, and infrastructure requirements. In the field of GHG monitoring, most GeoML [...] Read more.

Operationalizing Earth Observation (EO)-based Machine Learning (ML) algorithms (or GeoML) for ingestion in environmental Digital Twins remains a challenging task due to the complexities associated with balancing real-time inference with cost, data, and infrastructure requirements. In the field of GHG monitoring, most GeoML models of land use CO₂ fluxes remain at the proof-of-concept stage, limiting their use in policy and land management for net-zero goals. In this study, we develop and demonstrate a Digital Twin-ready framework to operationalize a pre-trained Random Forest model that estimates the Net Ecosystem Exchange of CO₂ (NEE) from drained peatlands into a biweekly, field-scale CO₂ flux monitoring system using EO and weather data. The system achieves an average response time of 6.12 s, retains 98% accuracy of the underlying model, and predicts the NEE of CO₂ with an R² of 0.76 and NRMSE of 8%. It is characterized by hybrid data ingestion (combining non-time-critical and real-time retrieval), automated biweekly data updates, efficient storage, and a user-friendly front-end. The underlying framework, which is part of an operational Digital Twin under the UK Research & Innovation AI for Net Zero project consortium, is built using open source tools for data access and processing (including the Copernicus Data Space Ecosystem OpenEO API and Open-Meteo API), automation (Jenkins), and GUI development (Leaflet, NiceGIU, etc.). The applicability of the system is demonstrated through running real-world use-cases relevant to farmers and policymakers concerned with the management of arable peatlands in England. Overall, the lightweight, modular framework presented here integrates seamlessly into Digital Twins and is easily adaptable to other GeoMLs, providing a practical foundation for operational use in environmental monitoring and decision-making. Full article

(This article belongs to the Topic The Geography of Digital Twin: Concepts, Architectures, Modeling, AI and Applications)

► Show Figures

Figure 1

25 pages, 10121 KB

Open AccessArticle

Bidirectional Reflectance Sensitivity to Hemispherical Samplings: Implications for Snow Surface BRDF and Albedo Retrieval

by Jing Guo, Ziti Jiao, Anxin Ding, Zhilong Li, Chenxia Wang, Fangwen Yang, Ge Gao, Zheyou Tan, Sizhe Chen and Xin Dong

Remote Sens. 2025, 17(21), 3614; https://doi.org/10.3390/rs17213614 (registering DOI) - 31 Oct 2025

Abstract

Multi-angular remote sensing plays a critical role in the study domains of ecological monitoring, climate change, and energy balance. The successful retrieval of the surface Bidirectional Reflectance Distribution Function (BRDF) and albedo from multi-angular remote sensing observations for various applications relies on the [...] Read more.

Multi-angular remote sensing plays a critical role in the study domains of ecological monitoring, climate change, and energy balance. The successful retrieval of the surface Bidirectional Reflectance Distribution Function (BRDF) and albedo from multi-angular remote sensing observations for various applications relies on the sensitivity of an appropriate BRDF model to both the number and the sampling distribution of multi-angular observations. In this study, based on selected high-quality multi-angular datasets, we designed three representative angular sampling schemes to systematically analyze different illuminating–viewing configurations of the retrieval results in a kernel-driven BRDF model framework. We first proposed an angular information index (AII) by incorporating a weighting mechanism and information effectiveness to quantify the angular information content for the angular sampling distribution schemes. In accordance with the principle that observations on the principal plane (PP) provide the most representative anisotropic scattering features, the assigned weight gradually decreases from the PP towards the cross-principal plane (CPP). The information effectiveness is determined based on the cosine similarity between the observations, effectively reducing the information redundancy. With such a method, we assess the AII of the different sampling schemes and further analyze the impact of angular distribution on both BRDF inversion and the estimation of snow surface albedo, including White-Sky Albedo (WSA) and Black-Sky Albedo (BSA) based on the RossThick-LiSparseReciprocal-Snow (RTLSRS) BRDF model. The main conclusions are as follows: (1) The AII approach can serve as a robust indicator of the efficiency of different sampling schemes in BRDF retrieval, which indicates that the RTLSRS model can provide a robust inversion when the AII value exceeds a threshold of −2. (2) When the AII value reaches such a reliable level, different sampling schemes can reproduce the BRDF shapes of snow across different bands to somehow varying degrees. Specifically, observations with smaller view zenith angle (VZA) ranges can reconstruct a BRDF shape that amplifies the anisotropic effect of snow; in addition, the forward scattering tends to be more pronounced at larger solar zenith angles (SZAs), while the variations in BRDF shape reconstructed from off-PP observations depend on both wavelength and SZAs. (3) The relative differences in both BSA and WSA grow with increasing wavelength for all these sampling schemes, mostly within 5% for short bands but up to 30% for longer wavelengths. With this novel AII method to quantify the information contribution of multi-angular sampling distributions, this study offers valuable insights into several main multi-angular BRDF sampling strategies in satellite sensor missions, which relate to most of the fields of multi-angular remote sensing applications in engineering. Full article

(This article belongs to the Special Issue Remote Sensing in Civil and Environmental Engineering (Second Edition))

► Show Figures

Figure 1

23 pages, 3927 KB

Open AccessArticle

Performance Assessment of IMERG V07 Versus V06 for Precipitation Estimation in the Parnaíba River Basin

by Flávia Ferreira Batista, Daniele Tôrres Rodrigues, Cláudio Moises Santos e Silva, Lara de Melo Barbosa Andrade, Pedro Rodrigues Mutti, Miguel Potes and Maria João Costa

Remote Sens. 2025, 17(21), 3613; https://doi.org/10.3390/rs17213613 (registering DOI) - 31 Oct 2025

Abstract

Accurate satellite-based precipitation estimates are crucial for climate studies and water resource management, particularly in regions with sparse meteorological station coverage. This study evaluates the improvements of the Integrated Multi-satellite Retrievals for GPM (IMERG) Final Run version 07 (V07) relative to the previous [...] Read more.

Accurate satellite-based precipitation estimates are crucial for climate studies and water resource management, particularly in regions with sparse meteorological station coverage. This study evaluates the improvements of the Integrated Multi-satellite Retrievals for GPM (IMERG) Final Run version 07 (V07) relative to the previous version (V06). The evaluation employed gridded data from the Brazilian Daily Weather Gridded Data (BR-DWGD) product and ground observations from 58 rain gauges distributed across the Parnaíba River Basin in Northeast Brazil. The analysis comprised three main stages: (i) an intercomparison between BR-DWGD gridded data and rain gauge records using correlation, bias, and Root Mean Square Error (RMSE) metrics; (ii) a comparative assessment of the IMERG Final V06 and V07 products, evaluated with statistical metrics (correlation, bias, and RMSE) and complemented by performance indicators including the Kling-Gupta Efficiency (KGE), Probability of Detection (POD), and False Alarm Ratio (FAR); and (iii) the application of cluster analysis to identify homogeneous regions and characterize seasonal rainfall variations across the basin. The results show that the IMERG Final V07 product provides notable improvements, with lower bias, reduced RMSE, and greater accuracy in representing the spatial distribution of precipitation, particularly in the central and southern regions of the basin, which feature complex topography. IMERG V07 also demonstrated higher consistency, with reduced random errors and improved seasonal performance, reflected in higher POD and lower FAR values during the rainy season. The cluster analysis identified four homogeneous regions, within which V07 more effectively captured seasonal rainfall patterns influenced by systems such as the Intertropical Convergence Zone (ITCZ) and Amazonian moisture advection. These findings highlight the potential of the IMERG Final V07 product to enhance precipitation estimation across diverse climatic and topographic settings, supporting applications in hydrological modeling and extreme-event monitoring. Full article

► Show Figures

Figure 1

29 pages, 21764 KB

Open AccessArticle

Noise Reduction for the Future ODYSEA Mission: A UNet Approach to Enhance Ocean Current Measurements

by Anaëlle Tréboutte, Cécile Anadon, Marie-Isabelle Pujol, Renaud Binet, Gérald Dibarboure, Clément Ubelmann and Lucile Gaultier

Remote Sens. 2025, 17(21), 3612; https://doi.org/10.3390/rs17213612 (registering DOI) - 31 Oct 2025

Abstract

The ODYSEA (Ocean DYnamics and Surface Exchange with the Atmosphere) mission will provide simultaneous two-dimensional measurements of currents and winds for the first time. According to the ODYSEA radar concept, with a high incidence angle, current noise is primarily driven by backscattered power, [...] Read more.

The ODYSEA (Ocean DYnamics and Surface Exchange with the Atmosphere) mission will provide simultaneous two-dimensional measurements of currents and winds for the first time. According to the ODYSEA radar concept, with a high incidence angle, current noise is primarily driven by backscattered power, which is triggered by wind speed. Therefore, random noise will affect the quality of observations. In low wind conditions, the absence of surface roughness increases the noise level considerably, to the point where the measurement becomes unusable, as the error can exceed 3 m/s at 5 km posting compared to mean current amplitudes of tens of cm/s. Winds higher than 7.5 m/s enable current measurements at 5 km posting with an RMS accuracy below 50 cm/s, but derivatives of currents will amplify noise, hampering the understanding of ocean dynamics and the interaction between the ocean and the atmosphere. In this context, this study shows the advantages and limitations of using noise-reduction algorithms. A convolutional neural network, a UNet inspired by the work of the SWOT (Surface Water and Ocean Topography) mission, is trained and tested on simulated radial velocities that are representative of the global ocean. The results are compared with those of classical smoothing: an Adaptive Gaussian Smoother whose filtering transfer function is optimized based on local wind speed (e.g., more smoothing in regions of low wind). The UNet outperforms the kernel smoother everywhere with our simulated dataset, especially in low wind conditions (SNR << 1) where the smoother essentially removes all velocities whereas the UNet mitigates random noise while preserving most of the signal of interest. Error is reduced by a factor of 30 and structures down to 30 km are reconstructed accurately. The UNet also enables the reconstruction of the main eddies and fronts in the relative vorticity field. It shows good robustness and stability in new scenarios. Full article

(This article belongs to the Section Ocean Remote Sensing)

19 pages, 1443 KB

Open AccessTechnical Note

Geometric Error Analysis and Correction of Long-Term In-Orbit Measured Calibration Data of the LuTan-1 SAR Satellite

by Liyuan Liu, Aichun Wang, Mingxia Zhang, Qijin Han, Minghui Hou and Yanru Li

Remote Sens. 2025, 17(21), 3611; https://doi.org/10.3390/rs17213611 (registering DOI) - 31 Oct 2025

Abstract

LuTan-1(LT-1) is China’s first L-band differential interferometric synthetic aperture radar system, comprising two multi-polarization SAR satellites, LT-1A and LT-1B. The satellite uses differential deformation measurement and interferometric altimetry technology to realize surface deformation monitoring and topographic mapping in designated areas. It has the [...] Read more.

LuTan-1(LT-1) is China’s first L-band differential interferometric synthetic aperture radar system, comprising two multi-polarization SAR satellites, LT-1A and LT-1B. The satellite uses differential deformation measurement and interferometric altimetry technology to realize surface deformation monitoring and topographic mapping in designated areas. It has the characteristics of all-weather, all-time, and multi-polarization and can be applied to military and civilian fields. In order to further improve the accuracy of image geometric positioning, this paper analyzes the error sources of geometric positioning for the differential deformation measurement mode (strip 1) of the satellite service. The in-orbit data of three years since the launch (2022–2024) are selected to analyze the positioning accuracy and stability of the uncontrolled plane based on the corner reflector and active calibrator deployed in the calibration field. The experimental results show that the positioning accuracy of the satellite strip 1 image without a control plane meets the requirements of the in-orbit index and remains relatively stable. The geometric precision correction positioning accuracy after error source compensation is better than 3.0 m, providing a favorable support for the subsequent application. Full article

(This article belongs to the Special Issue Spaceborne SAR Calibration Technology)

22 pages, 3999 KB

Open AccessArticle

Seagrass Mapping in Cyprus Using Earth Observation Advances

by Despoina Makri, Spyridon Christofilakos, Dimitris Poursanidis, Dimosthenis Traganos, Christodoulos Mettas, Neophytos Stylianou and Diofantos Hadjimitsis

Remote Sens. 2025, 17(21), 3610; https://doi.org/10.3390/rs17213610 (registering DOI) - 31 Oct 2025

Abstract

Seagrass meadows are vital for biodiversity and provide a plethora of ecosystem services, but significant losses due to human activity and climate change have been observed in recent decades. This study aims to evaluate whether the integration of Sentinel-2 composites, cloud computing (Google [...] Read more.

Seagrass meadows are vital for biodiversity and provide a plethora of ecosystem services, but significant losses due to human activity and climate change have been observed in recent decades. This study aims to evaluate whether the integration of Sentinel-2 composites, cloud computing (Google Earth Engine, GEE), and machine learning (ML) classifiers can produce accurate, scalable maps of seagrass habitats, enabling reliable estimates of associated carbon stocks. In this case study, we developed a methodological workflow for local-scale seagrass mapping in Cyprus, covering a total area of 310 km². ML techniques, specifically the Random Forest (RF) classifier and Classification And Regression Tree (CART), were employed in the main processing stage. The RF classifier achieved an overall accuracy of 73.5%, with a seagrass-specific F1-score of 69.4%. Class-specific F1-scores ranged from 63.2% for hard bottoms to 98.2% for deep water, accounting for variability in habitat separability. The workflow is designed to be scalable across Cyprus and potentially the broader EMMENA region (Eastern Mediterranean, Middle East, and North Africa). Based on the mapped extent of Posidonia oceanica meadows, preliminary estimates suggest a carbon stock of approximately 19,000 Mg C in Cyprus. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

24 pages, 26768 KB

Open AccessArticle

Robust Synthesis Weather Radar from Satellite Imagery: A Light/Dark Classification and Dual-Path Processing Approach

by Wei Zhang, Hongbo Ma, Yanhai Gan, Junyu Dong, Renbo Pang, Xiaojiang Song, Cong Liu and Hongmei Liu

Remote Sens. 2025, 17(21), 3609; https://doi.org/10.3390/rs17213609 (registering DOI) - 31 Oct 2025

Abstract

Weather radar reflectivity plays a critical role in precipitation estimation and convective storm identification. However, due to terrain limitations and the uneven spatial distribution of radar stations, oceanic regions have long suffered from a lack of radar observations, resulting in extensive monitoring gaps. [...] Read more.

Weather radar reflectivity plays a critical role in precipitation estimation and convective storm identification. However, due to terrain limitations and the uneven spatial distribution of radar stations, oceanic regions have long suffered from a lack of radar observations, resulting in extensive monitoring gaps. Geostationary meteorological satellites have wide-area coverage and near-real-time observation capability, offering a viable solution for synthesizing radar reflectivity in these regions. Most previous synthesis studies have adopted fixed time-window data partitioning, which introduces significant noise into visible-light observations under large-scale, low-illumination conditions, thereby degrading synthesis quality. To address this issue, we propose an integrated deep-learning method that combines illumination-based classification and reflectivity synthesis to enhance the accuracy of radar reflectivity synthesis from geostationary meteorological satellites. This approach integrates a classification network with a synthesis network. First, visible-light observations from the Himawari-8 satellite are classified based on illumination conditions to separate valid signals from noise; then, noise-free infrared observations and multimodal fused data are fed into dedicated synthesis networks to generate composite reflectivity products. In experiments, the proposed method outperformed the baseline approach in regions with strong convection (≥35 dBZ), with a 9.5% improvement in the critical success index, a 7.5% increase in the probability of detection, and a 6.1% reduction in the false alarm rate. Additional experiments confirmed the applicability and robustness of the method across various complex scenarios. Full article

(This article belongs to the Special Issue Satellite Remote Sensing for Meteorological Disaster Monitoring and Forecasting)

18 pages, 2441 KB

Open AccessArticle

Persistent Urban Park Cooling Effects in Krakow: A Satellite-Based Analysis of Land Surface Temperature Patterns (1990–2018)

by Ewa Głowienka and Marcin Kucza

Remote Sens. 2025, 17(21), 3608; https://doi.org/10.3390/rs17213608 (registering DOI) - 31 Oct 2025

Abstract

Urban green spaces provide measurable cooling that can mitigate urban heat islands, yet few studies have quantified these effects over multiple decades. This study analyzed Landsat imagery from four epochs (1990, 2000, 2013, 2018) to derive land surface temperature (LST) and vegetation indices—NDVI [...] Read more.

Urban green spaces provide measurable cooling that can mitigate urban heat islands, yet few studies have quantified these effects over multiple decades. This study analyzed Landsat imagery from four epochs (1990, 2000, 2013, 2018) to derive land surface temperature (LST) and vegetation indices—NDVI for greenness and NDMI for moisture content—for four large urban parks in Krakow. Late spring/summer LST in parks was compared with that of urban areas within 0–150 m and 150–300 m of park boundaries. Statistical significance was evaluated using bootstrapped confidence intervals, long-term trends were assessed via the Mann–Kendall test, and correlation analysis was used to examine relationships between LST and each vegetation index. Results show a persistent park cooling effect, with park interiors ~2–3 °C cooler than adjacent urban areas in all years. Despite an overall city-wide LST rise of ~5–6 °C from 1990 to 2018, the park cool island intensity (temperature difference between park and city) remained stable (no significant long-term trend, p > 0.7). Bootstrapped 95% confidence intervals confirmed that each park’s cooling effect was statistically significant in each year analyzed. NDMI (vegetation moisture content) correlated more strongly with LST (r ~ −0.90) than NDVI (r ~ −0.7 to −0.9), highlighting the importance of vegetation moisture in park cooling. These findings demonstrate that well-watered urban parks can sustain substantial cooling benefits over decades of urban development. The persistent ~2–3 °C daytime cooling observed underscores the value of water-sensitive green space planning as a long-term urban heat mitigation strategy. Full article

► Show Figures

Figure 1

23 pages, 12097 KB

Open AccessArticle

Optical Properties and Radiative Forcing Estimations of High-Altitude Aerosol Transport During Saharan Dust Events Based on Laser Remote Sensing Techniques (CLIMPACT Campaign 2021, Greece)

by Alexandros Papayannis, Ourania Soupiona, Marilena Gidarakou, Christina-Anna Papanikolaou, Dimitra Anagnou, Romanos Foskinis, Maria Mylonaki, Krystallia Mandelia and Stavros Solomos

Remote Sens. 2025, 17(21), 3607; https://doi.org/10.3390/rs17213607 (registering DOI) - 31 Oct 2025

Abstract

We present two case studies of tropospheric aerosol transport observed over the high-altitude Helmos observatory (1800–2300 m a.s.l.) in Greece during September 2021. Two cases were linked to Saharan dust intrusions, of which one was additionally linked to a mixture of biomass-burning and [...] Read more.

We present two case studies of tropospheric aerosol transport observed over the high-altitude Helmos observatory (1800–2300 m a.s.l.) in Greece during September 2021. Two cases were linked to Saharan dust intrusions, of which one was additionally linked to a mixture of biomass-burning and continental aerosols. Aerosol vertical profiles from the AIAS mobile backscatter/depolarization lidar (532 nm, NTUA) revealed distinct aerosol layers between 2 and 6 km a.s.l., with particle linear depolarization ratio values of up to 0.30–0.40, indicative of mineral dust. The elevated location of Helmos allows lidar measurements in the free troposphere, minimizing planetary boundary layer influence and improving the attribution of long-range transported aerosols. Radiative impacts were quantified using the LibRadtran model. For the 27 September dust outbreak, simulations showed strong shortwave absorption within 3–7 km, peaking at 5–6 km, with surface forcing reaching −25 W m⁻² and TOA forcing around −12 W m⁻², thus, implying a net cooling by 13 W m⁻² on the Earth’s atmosphere system. In contrast, the 30 September mixed aerosol case produced substantial solar attenuation, a surface heating rate of 2.57 K day⁻¹, and a small positive forcing aloft (~0.05 K day⁻¹). These results emphasize the contrasting radiative roles of dust and smoke over the Mediterranean and the importance of high-altitude observatories for constraining aerosol–radiation interactions. Full article

(This article belongs to the Section Environmental Remote Sensing)

19 pages, 14252 KB

Open AccessArticle

Physical-Guided Transfer Deep Neural Network for High-Resolution AOD Retrieval

by Debao Chen, Hong Guo, Xingfa Gu, Jinnian Wang, Yan Liu, Yuecheng Li and Yifan Wu

Remote Sens. 2025, 17(21), 3606; https://doi.org/10.3390/rs17213606 (registering DOI) - 31 Oct 2025

Abstract

Urban-scale aerosol pollution monitoring is of critical importance for both climate regulation and public health. To overcome the limitations of conventional kilometer-scale satellite aerosol optical depth (AOD) products in resolving urban pollution heterogeneity, this study develops a physical-guided transfer deep neural network (PT-DNN) [...] Read more.

Urban-scale aerosol pollution monitoring is of critical importance for both climate regulation and public health. To overcome the limitations of conventional kilometer-scale satellite aerosol optical depth (AOD) products in resolving urban pollution heterogeneity, this study develops a physical-guided transfer deep neural network (PT-DNN) model based on high-resolution Landsat 8 data. The PT-DNN introduces a novel physics-guided training framework, in which radiative transfer simulations are integrated to physically constrain the AOD retrieval. Pre-training was conducted using multi-scenario radiative transfer simulations, with subsequent fine-tuning via ground-based AERONET measurements. The model architecture integrates convolutional neural network (CNN) with residual connection. Validation results over impervious surfaces indicate that the PT-DNN model outperforms conventional data-driven models, with the coefficient of determination (R²) increasing from 0.81 to 0.86 and root mean square error (RMSE) decreasing from 0.122 to 0.104. Moreover, the AOD distributions retrieved at a high spatial resolution of 30 m effectively reveal fine-scale pollution gradients within urban environments, especially in densely built-up and industrial areas. Full article

(This article belongs to the Special Issue The Advancements in Aerosol, Cloud and Cloud–Aerosol Interaction by Remote Sensing)

► Show Figures

Figure 1

32 pages, 1307 KB

Open AccessSystematic Review

Machine and Deep Learning for Wetland Mapping and Bird-Habitat Monitoring: A Systematic Review of Remote-Sensing Applications (2015–April 2025)

by Marwa Zerrouk, Kenza Ait El Kadi, Imane Sebari and Siham Fellahi

Remote Sens. 2025, 17(21), 3605; https://doi.org/10.3390/rs17213605 (registering DOI) - 31 Oct 2025

Abstract

Wetlands, among the most productive ecosystems on Earth, shelter a diversity of species and help maintain ecological balance. However, they are witnessing growing anthropogenic and climatic threats, which underscores the need for regular and long-term monitoring. This study presents a systematic review of [...] Read more.

Wetlands, among the most productive ecosystems on Earth, shelter a diversity of species and help maintain ecological balance. However, they are witnessing growing anthropogenic and climatic threats, which underscores the need for regular and long-term monitoring. This study presents a systematic review of 121 peer-reviewed articles published between January 2015 and 30 April 2025 that applied machine learning (ML) and deep learning (DL) for wetland mapping and bird-habitat monitoring. Despite rising interest, applications remain fragmented, especially for avian habitats; only 39 studies considered birds, and fewer explicitly framed wetlands as bird habitats. Following PRISMA 2020 and the SPIDER framework, we compare data sources, classification methods, validation practices, geographic focus, and wetland types. ML is predominant overall, with random forest the most common baseline, while DL (e.g., U-Net and Transformer variants) is underused relative to its broader land cover adoption. Where reported, DL shows a modest but consistent accuracy over ML for complex wetland mapping; this accuracy improves when fusing synthetic aperture radar (SAR) and optical data. Validation still relies mainly on overall accuracy (OA) and Kappa coefficient (

κ

), with limited class-wise metrics. Salt marshes and mangroves dominate thematically, and China geographically, whereas peatlands, urban marshes, tundra, and many regions (e.g., Africa and South America) remain underrepresented. Multi-source fusion is beneficial yet not routine; The combination of unmanned aerial vehicles (UAVs) and DL is promising for fine-scale avian micro-habitats but constrained by disturbance and labeling costs. We then conclude with actionable recommendations to enable more robust and scalable monitoring. This review can be considered as the first comparative synthesis of ML/DL methods applied to wetland mapping and bird-habitat monitoring, and highlights the need for more diverse, transferable, and ecologically/socially integrated AI applications in wetland and bird-habitat monitoring. Full article

► Show Figures

Figure 1

23 pages, 3266 KB

Open AccessArticle

A 3D Reconstruction Technique for UAV SAR Under Horizontal-Cross Configurations

by Junhao He, Dong Feng, Chongyi Fan, Beizhen Bi, Fengzhuo Huang, Shuang Yue, Zhuo Xu and Xiaotao Huang

Remote Sens. 2025, 17(21), 3604; https://doi.org/10.3390/rs17213604 (registering DOI) - 31 Oct 2025

Abstract

Synthetic Aperture Radar (SAR) three-dimensional (3D) imaging has considerable potential in disaster monitoring and topographic mapping. Conventional 3D SAR imaging techniques for unmanned aerial vehicle (UAV) formations require rigorously regulated vertical or linear flight trajectories to maintain signal coherence. In practice, however, restricted [...] Read more.

Synthetic Aperture Radar (SAR) three-dimensional (3D) imaging has considerable potential in disaster monitoring and topographic mapping. Conventional 3D SAR imaging techniques for unmanned aerial vehicle (UAV) formations require rigorously regulated vertical or linear flight trajectories to maintain signal coherence. In practice, however, restricted collaboration precision among UAVs frequently prevents adherence to these trajectories, resulting in blurred scattering characteristics and degraded 3D localization accuracy. To address this, a 3D reconstruction technique based on horizontal-cross configurations is proposed, which establishes a new theoretical framework. This approach reduces stringent flight restrictions by transforming the requirement for vertical baselines into geometric flexibility in the horizontal plane. For dual-UAV subsystems, a geometric inversion algorithm is developed for initial scattering center localization. For multi-UAV systems, a multi-aspect fusion algorithm is proposed; it extends the dual-UAV inversion method and incorporates basis transformation theory to achieve coherent integration of multi-platform radar observations. Numerical simulations demonstrate an 80% reduction in implementation costs compared to tomographic SAR (TomoSAR), along with a 1.7-fold improvement in elevation resolution over conventional beamforming (CBF), confirming the framework’s effectiveness. This work presents a systematic horizontal-cross framework for SAR 3D reconstruction, offering a practical solution for UAV-based imaging in complex environments. Full article

(This article belongs to the Special Issue Target Recognition and Detection Based on High Resolution Radar Images (Second Edition))

► 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