Remote Sensing

30 pages, 11197 KiB

Open AccessArticle

Few-Shot Unsupervised Domain Adaptation Based on Refined Bi-Directional Prototypical Contrastive Learning for Cross-Scene Hyperspectral Image Classification

by Xuebin Tang, Hanyi Shi, Chunchao Li, Cheng Jiang, Xiaoxiong Zhang, Lingbin Zeng and Xiaolei Zhou

Remote Sens. 2025, 17(13), 2305; https://doi.org/10.3390/rs17132305 (registering DOI) - 4 Jul 2025

Abstract

Hyperspectral image cross-scene classification (HSICC) tasks are confronted with tremendous challenges due to spectral shift phenomena across scenes and the tough work of obtaining labels. Unsupervised domain adaptation has proven its effectiveness in tackling this issue, but it has a fatal limitation of [...] Read more.

Hyperspectral image cross-scene classification (HSICC) tasks are confronted with tremendous challenges due to spectral shift phenomena across scenes and the tough work of obtaining labels. Unsupervised domain adaptation has proven its effectiveness in tackling this issue, but it has a fatal limitation of intending to narrow the disparity between source and target domains by utilizing fully labeled source data and unlabeled target data. However, it is costly even to attain labels from source domains in many cases, rendering sufficient labeling as used in prior work impractical. In this work, we investigate an extreme and realistic scenario where unsupervised domain adaptation methods encounter sparsely labeled source data when handling HSICC tasks, namely, few-shot unsupervised domain adaptation. We propose an end-to-end refined bi-directional prototypical contrastive learning (RBPCL) framework for overcoming the HSICC problem with only a few labeled samples in the source domain. RBPCL captures category-level semantic features of hyperspectral data and performs feature alignment through in-domain refined prototypical self-supervised learning and bi-directional cross-domain prototypical contrastive learning, respectively. Furthermore, our framework introduces the class-balanced multicentric dynamic prototype strategy to generate more robust and representative prototypes. To facilitate prototype contrastive learning, we employ a Siamese-style distance metric loss function to aggregate intra-class features while increasing the discrepancy of inter-class features. Finally, extensive experiments and ablation analysis implemented on two public cross-scene data pairs and three pairs of self-collected ultralow-altitude hyperspectral datasets under different illumination conditions verify the effectiveness of our method, which will further enhance the practicality of hyperspectral intelligent sensing technology. Full article

► Show Figures

Figure 1

25 pages, 7408 KiB

Open AccessArticle

Multi-Temporal Dual Polarimetric SAR Crop Classification Based on Spatial Information Comprehensive Utilization

by Qiang Yin, Yuming Du, Fangfang Li, Yongsheng Zhou and Fan Zhang

Remote Sens. 2025, 17(13), 2304; https://doi.org/10.3390/rs17132304 - 4 Jul 2025

Abstract

Dual polarimetric SAR is capable of reflecting the biophysical and geometrical information of terrain with open access data availability. When it is combined with time-series observations, it can effectively capture the dynamic evolution of scattering characteristics of crops in different growth cycles. However, [...] Read more.

Dual polarimetric SAR is capable of reflecting the biophysical and geometrical information of terrain with open access data availability. When it is combined with time-series observations, it can effectively capture the dynamic evolution of scattering characteristics of crops in different growth cycles. However, the actual planting of crops often shows spatial dispersion, and the same crop may be dispersed in different plots, which fails to adequately consider the correlation information between dispersed plots of the same crop in spatial distribution. This study proposed a crop classification method based on multi-temporal dual polarimetric data, which considered the utilization of information between near and far spatial plots, by employing superpixel segmentation and a HyperGraph neural network, respectively. Firstly, the method utilized the dual polarimetric covariance matrix of multi-temporal data to perform superpixel segmentation on neighboring pixels, so that the segmented superpixel blocks were highly compatible with the actual plot shapes from a long-term period perspective. Then, a HyperGraph adjacency matrix was constructed, and a HyperGraph neural network (HGNN) was utilized to better learn the features of plots of the same crop that are distributed far from each other. The method fully utilizes the three dimensions of time, polarization and space information, which complement each other so as to effectively realize high-precision crop classification. The Sentinel-1 experimental results show that, under the optimal parameter settings, the classified accuracy of combined temporal superpixel scattering features using the HGNN was obviously improved, considering the near and far distance spatial correlations of crop types. Full article

(This article belongs to the Special Issue Cutting-Edge PolSAR Imaging Applications and Techniques)

19 pages, 16060 KiB

Open AccessArticle

Synergic Lidar Observations of Ozone Episodes and Transport During 2023 Summer AGES+ Campaign in NYC Region

by Dingdong Li, Yonghua Wu, Thomas Ely, Thomas Legbandt and Fred Moshary

Remote Sens. 2025, 17(13), 2303; https://doi.org/10.3390/rs17132303 - 4 Jul 2025

Abstract

We present coordinated observations from ozone Differential Absorption lidar (DIAL), aerosol lidar, and Doppler wind lidar at the City College of New York (CCNY) in northern Manhattan during the summer 2023 AGES+ campaigns across the New York City (NYC) region and Long Island [...] Read more.

We present coordinated observations from ozone Differential Absorption lidar (DIAL), aerosol lidar, and Doppler wind lidar at the City College of New York (CCNY) in northern Manhattan during the summer 2023 AGES+ campaigns across the New York City (NYC) region and Long Island Sound (LIS) areas. The results highlight significant ozone formation within the planetary boundary layer (PBL) and the concurrent transport of ozone/aerosol plumes aloft and mixing into the PBL during 26–28 July 2023. Especially, 26 July experienced the highest ozone concentration within the PBL during the three-day ozone episode despite having a lower temperature than the following two days. In addition, the onset of the afternoon sea breeze contributed to increased ozone levels in the PBL. A mobile ozone DIAL was also deployed at Columbia University’s Lamont–Doherty Earth Observatory (LDEO) in Palisades, NY, 29 km north of NYC, from 11 August to 8 September 2023. A notable high-ozone episode was observed by both ozone DIALs at the CCNY and the LDEO site during an unusual heatwave event in early September. On 7 September, the peak ozone concentration at the LDEO reached 120 ppb, exceeding the ozone levels observed in NYC. This enhancement was associated with urban plume transport, as indicated by wind lidar measurements, the HRRR (High-Resolution Rapid Refresh) model, and the Copernicus Sentinel-5 TROPOMI (TROPOspheric Monitoring Instrument) tropospheric column NO₂ product. The results also show that, during both heatwave events, those days with slow southeast to southwest winds experienced significantly higher ozone pollution. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

25 pages, 10429 KiB

Open AccessArticle

Robust Feature Matching of Multi-Illumination Lunar Orbiter Images Based on Crater Neighborhood Structure

by Bin Xie, Bin Liu, Kaichang Di, Wai-Chung Liu, Yuke Kou, Yutong Jia and Yifan Zhang

Remote Sens. 2025, 17(13), 2302; https://doi.org/10.3390/rs17132302 - 4 Jul 2025

Abstract

Lunar orbiter image matching is a critical process for achieving high-precision lunar mapping, positioning, and navigation. However, with the Moon's weak-texture surface and rugged terrain, lunar orbiter images generally suffer from inconsistent lighting conditions and exhibit varying degrees of non-linear intensity distortion, which [...] Read more.

Lunar orbiter image matching is a critical process for achieving high-precision lunar mapping, positioning, and navigation. However, with the Moon's weak-texture surface and rugged terrain, lunar orbiter images generally suffer from inconsistent lighting conditions and exhibit varying degrees of non-linear intensity distortion, which pose significant challenges to image traditional matching. This paper presents a robust feature matching method based on crater neighborhood structure, which is particularly robust to changes in illumination. The method integrates deep-learning based crater detection, Crater Neighborhood Structure features (CNSFs) construction, CNSF similarity-based matching, and outlier removal. To evaluate the effectiveness of the proposed method, we created an evaluation dataset, comprising Multi-illumination Lunar Orbiter Images (MiLOIs) from different latitudes (a total of 321 image pairs). And comparative experiments have been conducted using the proposed method and state-of-the-art image matching methods. The experimental results indicate that the proposed approach exhibits greater robustness and accuracy against variations in illumination. Full article

(This article belongs to the Special Issue Remote Sensing and Photogrammetry Applied to Deep Space Exploration)

16 pages, 2462 KiB

Open AccessTechnical Note

Precipitable Water Vapor Retrieval Based on GNSS Data and Its Application in Extreme Rainfall

by Tian Xian, Ke Su, Jushuo Zhang, Huaquan Hu and Haipeng Wang

Remote Sens. 2025, 17(13), 2301; https://doi.org/10.3390/rs17132301 - 4 Jul 2025

Abstract

Water vapor plays a crucial role in maintaining global energy balance and water cycle, and it is closely linked to various meteorological disasters. Precipitable water vapor (PWV), as an indicator of variations in atmospheric water vapor content, has become a key parameter for [...] Read more.

Water vapor plays a crucial role in maintaining global energy balance and water cycle, and it is closely linked to various meteorological disasters. Precipitable water vapor (PWV), as an indicator of variations in atmospheric water vapor content, has become a key parameter for meteorological and climate monitoring. However, due to limitations in observation costs and technology, traditional atmospheric monitoring techniques often struggle to accurately capture the distribution and variations in space–time water vapor. With the continuous advancement of Global Navigation Satellite System (GNSS) technology, ground-based GNSS monitoring technology has shown rapid development momentum in the field of meteorology and is considered an emerging monitoring tool with great potential. Hence, based on the GNSS observation data from July 2023, this study retrieves PWV using the Global Pressure and Temperature 3 (GPT3) model and evaluates its application performance in the “7·31” extremely torrential rain event in Beijing in 2023. Research has found the following: (1) Tropospheric parameters, including the PWV, zenith tropospheric delay (ZTD), and zenith wet delay (ZWD), exhibit high consistency and are significantly affected by weather conditions, particularly exhibiting an increasing-then-decreasing trend during rainfall events. (2) Through comparisons with the PWV values through the integration based on fifth-generation European Centre for Medium-Range Weather Forecasts (ERA-5) reanalysis data, it was found that results obtained using the GPT3 model exhibit high accuracy, with GNSS PWV achieving a standard deviation (STD) of 0.795 mm and a root mean square error (RMSE) of 3.886 mm. (3) During the rainfall period, GNSS PWV remains at a high level (>50 mm), and a strong correlation exists between GNSS PWV and peak hourly precipitation. Furthermore, PWV demonstrates the highest relative contribution in predicting extreme precipitation, highlighting its potential value for monitoring and predicting rainfall events. Full article

► Show Figures

Figure 1

24 pages, 11020 KiB

Open AccessArticle

Monitoring and Assessment of Slope Hazards Susceptibility Around Sarez Lake in the Pamir by Integrating Small Baseline Subset InSAR with an Improved SVM Algorithm

by Yang Yu, Changming Zhu, Majid Gulayozov, Junli Li, Bingqian Chen, Qian Shen, Hao Zhou, Wen Xiao, Jafar Niyazov and Aminjon Gulakhmadov

Remote Sens. 2025, 17(13), 2300; https://doi.org/10.3390/rs17132300 - 4 Jul 2025

Abstract

Sarez Lake, situated at one of the highest altitudes among naturally dammed lakes, is regarded as potentially hazardous due to its geological setting. Therefore, developing an integrated monitoring and risk assessment framework for slope-related geological hazards in this region holds significant scientific and [...] Read more.

Sarez Lake, situated at one of the highest altitudes among naturally dammed lakes, is regarded as potentially hazardous due to its geological setting. Therefore, developing an integrated monitoring and risk assessment framework for slope-related geological hazards in this region holds significant scientific and practical value. In this study, we processed 220 Sentinel-1A SAR images acquired between 12 March 2017 and 2 August 2024, using the Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technique to extract time-series deformation data with millimeter-level precision. These deformation measurements were combined with key environmental factors to construct a susceptibility evaluation model based on the Information Value and Support Vector Machine (IV-SVM) methods. The results revealed a distinct spatial deformation pattern, characterized by greater activity in the western region than in the east. The maximum deformation rate along the shoreline increased from 280 mm/yr to 480 mm/yr, with a marked acceleration observed between 2022 and 2023. Geohazard susceptibility in the Sarez Lake area exhibits a stepped gradient: the proportion of area classified as extremely high susceptibility is 15.26%, decreasing to 29.05% for extremely low susceptibility; meanwhile, the density of recorded hazard sites declines from 0.1798 to 0.0050 events per km². The spatial configuration is characterized by high susceptibility on both flanks, a central low, and convergence of hazardous zones at the front and distal ends with a central expansion. These findings suggest that mitigation efforts should prioritize the detailed monitoring and remediation of steep lakeside slopes and fault-associated fracture zones. This study provides a robust scientific and technical foundation for the emergency warning and disaster management of high-altitude barrier lakes, which is applicable even in data-limited contexts. Full article

(This article belongs to the Special Issue Latest Improvements and Applications of Ground Deformation Monitoring Based on Remote Sensing Data (Second Edition))

► Show Figures

Figure 1

21 pages, 5726 KiB

Open AccessArticle

A Novel Copula-Based Multi-Feature CFAR Framework for Radar Target Detection

by Juan Li, Yunlong Dong, Ningbo Liu, Yong Huang, Xingyu Jiang and Jinping Sun

Remote Sens. 2025, 17(13), 2299; https://doi.org/10.3390/rs17132299 - 4 Jul 2025

Abstract

Multi-feature radar target detection enhances the discrimination between targets and clutter, thereby improving detection accuracy. However, the complex nonlinear dependencies among features present significant challenges for precise control of the false alarm rate (FAR). In this paper, a novel constant false alarm rate [...] Read more.

Multi-feature radar target detection enhances the discrimination between targets and clutter, thereby improving detection accuracy. However, the complex nonlinear dependencies among features present significant challenges for precise control of the false alarm rate (FAR). In this paper, a novel constant false alarm rate (CFAR) framework for multi-feature detection is proposed. First, a Copula-CFAR theorem is established, which models the feature dependence structure and enables the derivation of closed-form expressions for probability of false alarm (PFA) and detection probability across various Copula models. Based on this theory, a multi-feature target detection algorithm is developed to achieve a predefined PFA. Simulation and experimental results validate the effectiveness of the approach. The method outperforms conventional CFAR detectors, including CA-CFAR, OS-CFAR, GO-CFAR, and SO-CFAR. Furthermore, compared to state-of-the-art detectors that utilize three features derived from convex hull, concave hull, convex hull principal component analysis (PCA), and concave hull PCA, the proposed method, which uses only two features, achieves relative improvements of 130.53%, 12.26%, 48.09%, and 34.62%, respectively, at a measured FAR of 0.001. Full article

► Show Figures

Figure 1

19 pages, 3097 KiB

Open AccessArticle

Evaluating the Efficiency of Two Ecological Indices in Monitoring Forest Degradation in the Drylands of Sudan

by Emad H. E. Yasin, Ahmed A. H. Siddig, Eiman E. Diab and Kornel Czimber

Remote Sens. 2025, 17(13), 2298; https://doi.org/10.3390/rs17132298 - 4 Jul 2025

Abstract

With increasing threats to forest resources, there is a growing demand for accurate, timely, and quantitative information on their status, trends, and sustainability. Satellite remote sensing provides an effective means of consistently monitoring large forest areas. Vegetation Indices (VIs) are commonly used to [...] Read more.

With increasing threats to forest resources, there is a growing demand for accurate, timely, and quantitative information on their status, trends, and sustainability. Satellite remote sensing provides an effective means of consistently monitoring large forest areas. Vegetation Indices (VIs) are commonly used to assess forest conditions, but their effectiveness remains a key question. This study aimed to assess and map forest degradation status and trends in Lagawa locality, West Kordofan State, Sudan using the soil adjusted and atmospheric resistant vegetation index (SARVI) to quantify the relationship between SARVI and the Normalized Difference Vegetation Index (NDVI) and compare the efficiency of both indices in detecting and monitoring changes in forest conditions. The study utilized four free cloud images (TM 1988, TM 1998, TM 2008, and OLI 2018), which were processed using Google Earth Engine (GEE) to derive the indices. The study found significant forest degradation over time, with 63% of the area categorized as moderately to severely degraded. A strong, positive relationship between SARVI and NDVI (R² = 0.9085, p < 0.001) was identified, indicating that both are effective in detecting forest changes. Both indices proved efficacy, cost-effectiveness, and applicable for monitoring forest changes across Sudan’s drylands. The study recommends applying similar methods in other dryland forests in other regions. Full article

► Show Figures

Figure 1

20 pages, 4973 KiB

Open AccessArticle

Remote Sensing and Critical Slowing Down Modeling Reveal Vegetation Resilience in the Three Gorges Reservoir Area, China

by Liangliang Zhang, Nan Yang, Bingkun Zhao, Jun Xie, Xiaofei Sun, Shunlin Liang, Huaiyong Shao and Jinhui Wu

Remote Sens. 2025, 17(13), 2297; https://doi.org/10.3390/rs17132297 - 4 Jul 2025

Abstract

Globally, ecosystems are affected by climate change, human activities, and natural disasters, which impact ecosystem quality and stability. Vegetation plays a crucial role in ecosystem material cycle and energy transformation, making it important to monitor its resilience under disturbance stress. The Critical Slowing [...] Read more.

Globally, ecosystems are affected by climate change, human activities, and natural disasters, which impact ecosystem quality and stability. Vegetation plays a crucial role in ecosystem material cycle and energy transformation, making it important to monitor its resilience under disturbance stress. The Critical Slowing Down (CSD) indicates that as ecosystems near collapse, the autocorrelation of lag temporal increases and resilience decreases. We used the lag Temporal Autocorrelation (TAC) of long-term remote sensing Leaf Area Index (LAI) to monitor vegetation resilience in the Three Gorges Reservoir Area (TGRA). The Disturbance Event Model (DEM) was used to validate the CSD. The results showed the following: (1) The eastern TGRA exhibited high and increasing vegetation resilience, while most areas showed a decline. (2) Among the various vegetation types, forests demonstrated higher resilience than other vegetation types. (3) Precipitation, temperature, and soil moisture significantly influenced vegetation resilience dynamics within the TGRA. (4) For model accuracy, the CSD’s results were consistent with the DEM, confirming its applicability in the TGRA. Overall, the CSD when applied to long-term remote sensing data, provided valuable quantitative indicators for vegetation resilience. Furthermore, more CSD-based indicators are needed to analyze vegetation resilience dynamics and better understand the biological processes determining vegetation degradation and restoration. Full article

(This article belongs to the Special Issue Remote Sensing Applications to Ecology: Opportunities and Challenges II)

► Show Figures

Figure 1

26 pages, 9399 KiB

Open AccessArticle

An Investigation of Pre-Seismic Ionospheric TEC and Acoustic–Gravity Wave Coupling Phenomena Using BDS GEO Measurements: A Case Study of the 2023 Jishishan Ms6.2 Earthquake

by Xiao Gao, Lina Shu, Zongfang Ma, Penggang Tian, Lin Pan, Hailong Zhang and Shuai Yang

Remote Sens. 2025, 17(13), 2296; https://doi.org/10.3390/rs17132296 - 4 Jul 2025

Abstract

This study investigates pre-seismic ionospheric anomalies preceding the 2023 Jishishan Ms6.2 earthquake using total electron content (TEC) data derived from BDS geostationary orbit (GEO) satellites. Multi-scale analysis integrating Butterworth filtering and wavelet transforms resolved TEC disturbances into three distinct frequency regimes: (1) high-frequency [...] Read more.

This study investigates pre-seismic ionospheric anomalies preceding the 2023 Jishishan Ms6.2 earthquake using total electron content (TEC) data derived from BDS geostationary orbit (GEO) satellites. Multi-scale analysis integrating Butterworth filtering and wavelet transforms resolved TEC disturbances into three distinct frequency regimes: (1) high-frequency perturbations (0.56–3.33 mHz) showed localized disturbances (amplitude ≤ 4 TECU, range < 300 km), potentially associated with near-field acoustic waves from crustal stress adjustments; (2) mid-frequency signals (0.28–0.56 mHz) exhibited anisotropic propagation (>1200 km) with azimuth-dependent N-shaped waveforms, consistent with the characteristics of acoustic–gravity waves (AGWs); and (3) low-frequency components (0.18–0.28 mHz) demonstrated phase reversal and power-law amplitude attenuation, suggesting possible lithosphere–atmosphere–ionosphere (LAI) coupling oscillations. The stark contrast between near-field residuals and far-field weak fluctuations highlighted the dominance of large-scale atmospheric gravity waves over localized acoustic disturbances. Geometry-based velocity inversion revealed incoherent high-frequency dynamics (5–30 min) versus anisotropic mid/low-frequency traveling ionospheric disturbance (TID) propagation (30–90 min) at 175–270 m/s, aligning with theoretical AGW behavior. During concurrent G1-class geomagnetic storm activity, spatial attenuation gradients and velocity anisotropy appear primarily consistent with seismogenic sources, providing insights for precursor discrimination and contributing to understanding multi-scale coupling in seismo-ionospheric systems. Full article

(This article belongs to the Special Issue State of the Art of Geomagnetic/Electromagnetic Satellites: Science and Applications (Second Edition))

► Show Figures

Figure 1

23 pages, 25321 KiB

Open AccessArticle

Spatiotemporal Monitoring of Cyanobacterial Blooms and Aquatic Vegetation in Jiangsu Province Using AI Earth Platform and Sentinel-2 MSI Data (2019–2024)

by Xin Xie, Ting Song, Ge Liu, Tiantian Wang and Qi Yang

Remote Sens. 2025, 17(13), 2295; https://doi.org/10.3390/rs17132295 - 4 Jul 2025

Abstract

Cyanobacterial blooms and aquatic vegetation dynamics are critical indicators of freshwater ecosystem health, increasingly shaped by climate change, nutrient enrichment, and ecological restoration efforts. Here, we present an automated monitoring system optimized for small- and medium-sized lakes. This system integrates phenology-based algorithms with [...] Read more.

Cyanobacterial blooms and aquatic vegetation dynamics are critical indicators of freshwater ecosystem health, increasingly shaped by climate change, nutrient enrichment, and ecological restoration efforts. Here, we present an automated monitoring system optimized for small- and medium-sized lakes. This system integrates phenology-based algorithms with Sentinel-2 MSI imagery, leveraging the AI Earth (AIE) platform developed by Alibaba DAMO Academy. Applied to monitor 12 ecologically sensitive lakes and reservoirs in Jiangsu Province, China, the system enables multi-year tracking of spatiotemporal changes from 2019 to 2024. A clear north-south gradient in cyanobacterial bloom intensity was observed, with southern lakes exhibiting higher bloom levels. Although bloom intensity decreased in lakes such as Changdang, Yangcheng, and Dianshan, Ge Lake displayed fluctuating patterns. In contrast, ecological restoration efforts in Cheng and Yuandang Lakes led to substantial increases in bloom intensity in 2024, with affected areas reaching 33.16% and 33.11%, respectively. Although bloom intensity remained low in northern lakes, increases were recorded in Hongze, Gaoyou, and Luoma Lakes after 2023, particularly in Hongze Lake, where bloom coverage surged to 3.29% in 2024. Aquatic vegetation dynamics displayed contrasting trends. In southern lakes—particularly Cheng, Dianshan, Yuandang, and Changdang Lakes—vegetation coverage significantly increased, with Changdang Lake reaching 44.56% in 2024. In contrast, northern lakes, including Gaoyou, Luoma, and Hongze, experienced a long-term decline in vegetation coverage. By 2024, compared to 2019, coverage in Gaoyou, Luoma, and Hongze Lakes decreased by 11.28%, 16.02%, and 47.32%, respectively. These declines are likely linked to increased grazing pressure following fishing bans, which may have disrupted vegetation dynamics and reduced their ability to suppress cyanobacterial blooms. These findings provide quantitative evidence supporting adaptive lake restoration strategies and underscore the effectiveness of satellite-based phenological monitoring in assessing freshwater ecosystem health. Full article

(This article belongs to the Special Issue River and Lake Dynamic Monitoring and Ecological Assessment Based on Remote Sensing)

► Show Figures

Figure 1

32 pages, 13821 KiB

Open AccessArticle

Spatiotemporal Evolution and Driving Factors of Karst Rocky Desertification in Guangxi, China, Under Climate Change and Human Activities

by Jialei Su, Meiling Liu, Qin Yang, Xiangnan Liu, Zeyan Wu and Yanan Wen

Remote Sens. 2025, 17(13), 2294; https://doi.org/10.3390/rs17132294 - 4 Jul 2025

Abstract

Guangxi is among China’s regions most severely affected by karst rocky desertification (KRD). Over the past two decades, global climate change and human activities have jointly led to significant changes in the extent and intensity of KRD in Guangxi. Given this context, it [...] Read more.

Guangxi is among China’s regions most severely affected by karst rocky desertification (KRD). Over the past two decades, global climate change and human activities have jointly led to significant changes in the extent and intensity of KRD in Guangxi. Given this context, it is crucial to comprehensively analyze the spatiotemporal evolution of KRD in Guangxi and its driving forces. This study proposed a novel three-dimensional feature space model for monitoring KRD in Guangxi. We then applied transition matrices, dynamic degree indices, and landscape metrics to analyze the spatiotemporal evolution of KRD. We also proposed a Spatiotemporal Interaction Intensity Index (STII) to quantify mutual influences among KRD patches. Finally, we used GeoDetector to analyze the driving factors of KRD. The results indicate the following: (1) The three-dimensional model showed high applicability for large-scale KRD monitoring, with an overall accuracy of 92.86%. (2) KRD in Guangxi exhibited an overall recovery–deterioration–recovery trend from 2000 to 2023. The main recovery phases were 2005–2015 and 2020–2023. During these phases, both severe and moderate KRD showed strong signals of recovery, including significant declines in area, number of patches, and Landscape Shape Index, along with persistently low STII values. In contrast, from 2015 to 2020, KRD predominantly deteriorated, primarily characterized by transitions from no KRD to potential KRD and from potential KRD to light KRD. (3) For severe KRD patches, the intensity of interaction required from neighboring patches to promote recovery exceeded that which led to deterioration, indicating the difficulty of reversing severe KRD. (4) Slope, land use, and elevation were the main drivers of KRD in Guangxi from 2000 to 2023. Erosive rainfall exhibited a higher explanatory power for KRD than average precipitation. Two-factor interactions significantly enhanced the driving forces of KRD. These findings provide a scientific basis for KRD management. Full article

► Show Figures

Figure 1

23 pages, 37536 KiB

Open AccessArticle

Underwater Sound Speed Profile Inversion Based on Res-SACNN from Different Spatiotemporal Dimensions

by Jiru Wang, Fangze Xu, Yuyao Liu, Yu Chen and Shu Liu

Remote Sens. 2025, 17(13), 2293; https://doi.org/10.3390/rs17132293 - 4 Jul 2025

Abstract

The sound speed profile (SSP) is an important feature in the field of ocean acoustics. The accurate estimation of SSP is significant for the development of underwater position, communication, and associated fundamental marine research. The Res-SACNN model is proposed for SSP inversion based [...] Read more.

The sound speed profile (SSP) is an important feature in the field of ocean acoustics. The accurate estimation of SSP is significant for the development of underwater position, communication, and associated fundamental marine research. The Res-SACNN model is proposed for SSP inversion based on the convolutional neural network (CNN) embedded with the residual network and self-attention mechanism. It combines the spatiotemporal characteristics of sea level anomaly (SLA) and sea surface temperature anomaly (SSTA) data and establishes a nonlinear relationship between satellite remote sensing data and sound speed field by deep learning. The single empirical orthogonal function regression (sEOF-r) method is used in a comparative experiment to confirm the model’s performance in both the time domain and the region. Experimental results demonstrate that the proposed model outperforms sEOF-r regarding both spatiotemporal generalization ability and inversion accuracy. The average root mean square error (RMSE) is decreased by 0.92 m/s in the time-domain experiment in the South China Sea, and the inversion results for each month are more consistent. The optimization ratio hits 71.8% and the average RMSE decreases by 7.39 m/s in the six-region experiment. The Res-SACNN model not only shows more superior inversion ability in the comparison with other deep-learning models, but also achieves strong generalization and real-time performance while maintaining low complexity, providing an improved technical tool for SSP estimation and sound field perception. Full article

► Show Figures

Figure 1

25 pages, 6042 KiB

Open AccessArticle

SPA-Net: An Offset-Free Proposal Network for Individual Tree Segmentation from TLS Data

by Yunjie Zhu, Zhihao Wang, Qiaolin Ye, Lifeng Pang, Qian Wang, Xiaolong Zheng and Chunhua Hu

Remote Sens. 2025, 17(13), 2292; https://doi.org/10.3390/rs17132292 - 4 Jul 2025

Abstract

Individual tree segmentation (ITS) from terrestrial laser scanning (TLS) point clouds is foundational for deriving detailed forest structural parameters, crucial for precision forestry, biomass calculation, and carbon accounting. Conventional ITS algorithms often struggle in complex forest stands due to reliance on heuristic rules [...] Read more.

Individual tree segmentation (ITS) from terrestrial laser scanning (TLS) point clouds is foundational for deriving detailed forest structural parameters, crucial for precision forestry, biomass calculation, and carbon accounting. Conventional ITS algorithms often struggle in complex forest stands due to reliance on heuristic rules and manual feature engineering. Deep learning methodologies proffer more efficacious and automated solutions, but their segmentation accuracy is restricted by imprecise center offset predictions, particularly in intricate forest environments. To address this issue, we proposed a deep learning method, SPA-Net, for achieving tree instance segmentation of forest point clouds. Unlike methods heavily reliant on potentially error-prone global offset vector predictions, SPA-Net employs a novel sampling-shifting-grouping paradigm within its sparse geometric proposal (SGP) module to directly generate initial proposal candidates from raw point data, aiming to reduce dependence on the offset branch. Subsequently, an affinity aggregation (AA) module robustly refines these proposals by assessing inter-proposal relationships and merging fragmented segments, effectively mitigating oversegmentation of large or complex trees; integrating with SGP eliminates the postprocessing step of scoring/NMS. SPA-Net was rigorously validated on two different forest datasets. On both BaiMa and Hong-Tes Lake datasets, the approach demonstrated superior performance compared to several contemporary segmentation approaches evaluated under the same conditions. It achieved 95.8% precision, 96.3% recall, and 92.9% coverage on BaiMa dataset, and achieved 92.6% precision, 94.8% recall, and 88.8% coverage on the Hong-Tes Lake dataset. This study provides a robust tool for individual tree analysis, advancing the accuracy of individual tree segmentation in challenging forest environments. Full article

(This article belongs to the Section Forest Remote Sensing)

► Show Figures

Figure 1

18 pages, 10338 KiB

Open AccessArticle

Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information

by Maoan Zhou, Dongfang Yang, Jieyu Liu, Weibo Xu, Xiong Qiu and Yongfei Li

Remote Sens. 2025, 17(13), 2291; https://doi.org/10.3390/rs17132291 - 4 Jul 2025

Abstract

Visual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and the other assumes [...] Read more.

Visual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and the other assumes a flat ground surface, ignoring elevation differences. This paper presents a novel aerial vehicle geolocalization method. It integrates 2D information and relative depth information, which are both from Earth observation images. Firstly, the aerial and reference remote sensing satellite images are fed into a feature-matching network to extract pixel-level feature-matching pairs. Then, a depth estimation network is used to estimate the relative depth of the satellite remote sensing image, thereby obtaining the relative depth information of the ground area within the field of view of the aerial image. Finally, high-confidence matching pairs with similar depth and uniform distribution are selected to estimate the geographic location of the aerial vehicle. Experimental results demonstrate that the proposed method outperforms existing ones in terms of geolocalization accuracy and stability. It eliminates reliance on elevation data or planar assumptions, thus providing a more adaptable and robust solution for aerial vehicle geolocalization in GNSS-denied environments. Full article

(This article belongs to the Special Issue Intelligent Perception and Robust Positioning Methods in GNSS-Denied Environments)

► Show Figures

Figure 1

37 pages, 13906 KiB

Open AccessReview

Accelerated Adoption of Google Earth Engine for Mangrove Monitoring: A Global Review

by K. M. Ashraful Islam, Paulo Murillo-Sandoval, Eric Bullock and Robert Kennedy

Remote Sens. 2025, 17(13), 2290; https://doi.org/10.3390/rs17132290 - 3 Jul 2025

Abstract

Mangrove forests support coastal resilience, biodiversity, and significant carbon sequestration, yet they face escalating threats from climate change, urban expansion, and land-use change. Traditional remote sensing workflows often struggle with large data volumes, complex preprocessing, and limited computational resources. Google Earth Engine (GEE) [...] Read more.

Mangrove forests support coastal resilience, biodiversity, and significant carbon sequestration, yet they face escalating threats from climate change, urban expansion, and land-use change. Traditional remote sensing workflows often struggle with large data volumes, complex preprocessing, and limited computational resources. Google Earth Engine (GEE) addresses these challenges through scalable, cloud-based computation, extensive, preprocessed imagery catalogs, built-in algorithms for rapid feature engineering, and collaborative script sharing that improves reproducibility. To evaluate how the potential of GEE has been harnessed for mangrove research, we systematically reviewed peer-reviewed articles published between 2017 and 2022. We examined the spectrum of GEE-based tasks, the extent to which studies incorporated mangrove-specific preprocessing, and the challenges encountered. Our analysis reveals a noteworthy yearly increase in GEE-driven mangrove studies but also identifies geographic imbalances, with several high-mangrove-density countries remaining underrepresented. Although most studies leveraged streamlined preprocessing and basic classification workflows, relatively few employed advanced automated methods. Persistent barriers include limited coding expertise, platform quotas, and sparse high-resolution data in certain regions. We outline a generalized workflow that includes automated tidal filtering, dynamic image composite generation, and advanced classification pipelines to address these gaps. By synthesizing achievements and ongoing limitations, this review offers guidance for future GEE-based mangrove studies and conservation efforts and aims to improve methodological rigor and maximize the potential of GEE. Full article

(This article belongs to the Special Issue Remote Sensing in Mangroves III)

► Show Figures

Figure 1

19 pages, 4349 KiB

Open AccessArticle

Assessment of Glacier Transformation in China over the Past 40 Years Using a China-Specific Glacier Classification System

by Tianya Li, Yuzhe Wang, Baojuan Huai, Hongmin An, Lei Wang and Weijun Sun

Remote Sens. 2025, 17(13), 2289; https://doi.org/10.3390/rs17132289 - 3 Jul 2025

Abstract

Glacier classification offers a structured framework for assessing glacier characteristics and understanding their responses to climate change. In this study, we apply the Shi–Xie glacier classification system, proposed by Chinese glaciologists Shi and Xie, to evaluate the transformation of extremely continental, subcontinental, and [...] Read more.

Glacier classification offers a structured framework for assessing glacier characteristics and understanding their responses to climate change. In this study, we apply the Shi–Xie glacier classification system, proposed by Chinese glaciologists Shi and Xie, to evaluate the transformation of extremely continental, subcontinental, and maritime glaciers across China over the past four decades. Our results show a widespread rise in equilibrium line altitudes (ELAs), alongside complex changes in climatic and glaciological parameters. Notably, despite ongoing warming trends, nearly half of the glaciers experienced cooling at the ELA, and over two-thirds showed a decline in summer mean temperatures. This apparent contradiction is explained by elevation-induced cooling; as ELAs rise to higher altitudes, the corresponding summer air temperatures decline due to the lapse rate effect. Near-surface ice temperatures (20 m depth) were strongly consistent with changes in annual air temperature. Precipitation trends were spatially heterogeneous, yet around 70% of glaciers experienced stable or slightly increasing annual precipitation. In contrast, maritime glaciers, particularly those in the southeastern glacierized regions, exhibited marked decreases. Glacier surface velocities generally declined, with 90% of glaciers flowing at speeds below 50 m a⁻¹. Threshold-based analysis reveals that glaciers in transitional zones frequently exhibit multi-indicator deviations. Extremely continental glaciers near classification boundaries showed a shift toward warmer, wetter subcontinental conditions, while maritime glaciers tended toward drier, colder subcontinental characteristics. These findings offer new insights into the differentiated responses and ongoing transformation of glacier types in China under climate change. Full article

(This article belongs to the Special Issue ERA5 Climate Application in Cold and Arid Regions)

► Show Figures

Figure 1

28 pages, 8102 KiB

Open AccessArticle

Multi-Neighborhood Sparse Feature Selection for Semantic Segmentation of LiDAR Point Clouds

by Rui Zhang, Guanlong Huang, Fengpu Bao and Xin Guo

Remote Sens. 2025, 17(13), 2288; https://doi.org/10.3390/rs17132288 - 3 Jul 2025

Abstract

LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations [...] Read more.

LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations such as convolution and pooling, yet fail to adequately consider sparse features that significantly influence the final results of point cloud-based scene perception, resulting in insufficient feature representation capability. To address these problems, a sparse feature dynamic graph convolutional neural network, abbreviated as SFDGNet, is constructed in this paper for LiDAR point clouds of complex scenes. In the context of this paper, sparse features refer to feature representations in which only a small number of activation units or channels exhibit significant responses during the forward pass of the model. First, a sparse feature regularization method was used to motivate the network model to learn the sparsified feature weight matrix. Next, a split edge convolution module, abbreviated as SEConv, was designed to extract the local features of the point cloud from multiple neighborhoods by dividing the input feature channels, and to effectively learn sparse features to avoid feature redundancy. Finally, a multi-neighborhood feature fusion strategy was developed that combines the attention mechanism to fuse the local features of different neighborhoods and obtain global features with fine-grained information. Taking S3DIS and ScanNet v2 datasets, we evaluated the feasibility and effectiveness of SFDGNet by comparing it with six typical semantic segmentation models. Compared with the benchmark model DGCNN, SFDGNet improved overall accuracy

(O A)

, mean accuracy

(m A c c)

, mean intersection over union

(m I o U)

, and

s p a r s i t y

by

1.8 %

,

3.7 %, 3.5 %

, and

85.5 %

on the S3DIS dataset, respectively. The

m I o U

on the ScanNet v2 validation set,

m I o U

on the test set, and

s p a r s i t y

were improved by

3.2 %, 7.0 %

, and

54.5 %

, respectively. Full article

(This article belongs to the Special Issue Remote Sensing for 2D/3D Mapping)

► Show Figures

Figure 1

19 pages, 34272 KiB

Open AccessArticle

Sequential SAR-to-Optical Image Translation

by Jingbo Wei, Huan Zhou, Peng Ke, Yaobin Ma and Rongxin Tang

Remote Sens. 2025, 17(13), 2287; https://doi.org/10.3390/rs17132287 - 3 Jul 2025

Abstract

There is a common need for optical sequence images with high spatiotemporal resolution. As a solution, Synthetic Aperture Radar (SAR)-to-optical translation tends to bring high temporal continuity of optical images and low interpretation difficulty of SAR images. Existing studies have been focused on [...] Read more.

There is a common need for optical sequence images with high spatiotemporal resolution. As a solution, Synthetic Aperture Radar (SAR)-to-optical translation tends to bring high temporal continuity of optical images and low interpretation difficulty of SAR images. Existing studies have been focused on converting a single SAR image into a single optical image, failing to utilize the advantages of repeated observations from SAR satellites. To make full use of periodic SAR images, it is proposed to investigate the sequential SAR-to-optical translation, which represents the first effort in this topic. To achieve this, a model based on a diffusion framework has been constructed, with twelve Transformer blocks utilized to effectively capture spatial and temporal features alternatively. A variational autoencoder is employed to encode and decode images, enabling the diffusion model to learn the distribution of features within optical image sequences. A conditional branch is specifically designed for SAR sequences to facilitate feature extraction. Additionally, the capture time is encoded and embedded into the Transformers. Two sequence datasets for the sequence translation task were created, comprising Sentinel-1 Ground Range Detected data and Sentinel-2 red/green/blue data. Our method was tested on new datasets and compared with three state-of-the-art single translation methods. Quantitative and qualitative comparisons validate the effectiveness of the proposed method in maintaining radiometric and spectral consistency. Full article

(This article belongs to the Special Issue SAR Images Processing and Analysis (2nd 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