Remote Sensing

25 pages, 7045 KB

Open AccessArticle

3DV-Unet: Eddy-Resolving Reconstruction of Three-Dimensional Upper-Ocean Physical Fields from Satellite Observations

by Qiaoshi Zhu, Hongping Li, Haochen Sun, Tianyu Xia, Xiaoman Wang and Zijun Han

Remote Sens. 2025, 17(19), 3394; https://doi.org/10.3390/rs17193394 - 9 Oct 2025

Viewed by 317

Three-dimensional (3D) ocean physical fields are essential for understanding ocean dynamics, but reconstructing them solely from sea-surface remote sensing remains challenging. We present 3DV-Unet, an end-to-end deep learning framework that reconstructs eddy-resolving three-dimensional essential ocean variables (temperature, salinity, and currents) from multi-source satellite [...] Read more.

Three-dimensional (3D) ocean physical fields are essential for understanding ocean dynamics, but reconstructing them solely from sea-surface remote sensing remains challenging. We present 3DV-Unet, an end-to-end deep learning framework that reconstructs eddy-resolving three-dimensional essential ocean variables (temperature, salinity, and currents) from multi-source satellite data. The model employs a 3D Vision Transformer bottleneck to capture cross-depth and cross-variable dependencies, ensuring physically consistent reconstruction. Trained on 2011–2019 reanalysis and satellite data, 3DV-Unet achieves RMSEs of ~0.30 °C for temperature, 0.11 psu for salinity, and 0.05 m/s for currents, with all R² values above 0.93. Error analyses further indicate higher reconstruction errors in dynamically complex regions such as the Kuroshio Extension, while spectral analysis indicates good agreement at 100 km+ but systematic deviation in the 20–100 km band. Independent validation against 6113 Argo profiles confirms its ability to reproduce realistic vertical thermohaline structures. Moreover, the reconstructed 3D fields capture mesoscale eddy structures and their life cycle, offering a valuable basis for investigating ocean circulation, energy transport, and regional variability. These results demonstrate the potential of end-to-end volumetric deep learning for advancing high-resolution 3D ocean reconstruction and supporting physical oceanography and climate studies. Full article

► Show Figures

Figure 1

21 pages, 6369 KB

Open AccessArticle

Validation of Multi-Scale LAI Products in Heterogeneous Terrain-Based UAV Images

by Meng Liu, Wenping Yu, Dandan Li, Fangfang Shang, Longlong Zhang, Shuangjie Wang, Wen Yang, Ruoyi Zhao and Xuemei Wang

Remote Sens. 2025, 17(19), 3393; https://doi.org/10.3390/rs17193393 - 9 Oct 2025

Viewed by 157

Abstract

Significant uncertainties persist across different Leaf Area Index (LAI) products due to multiple factors; therefore, the accuracy assessment of the global LAI products is an indispensable step before their application. In this study, comprehensive validation of multi-scale LAI products including Sentinel-2, Landsat-8/9, and [...] Read more.

Significant uncertainties persist across different Leaf Area Index (LAI) products due to multiple factors; therefore, the accuracy assessment of the global LAI products is an indispensable step before their application. In this study, comprehensive validation of multi-scale LAI products including Sentinel-2, Landsat-8/9, and MCD15A3H was implemented utilizing fine-resolution LAI maps which were based on UAV images and field-measured LAI data. The validation results demonstrated a consistent, systematic underestimation across all the LAI products within the study area, the RMSE of these products ranged from 0.56 to 1.63, and the coarse-resolution MCD15A3H LAI product demonstrated highest accuracy (RMSE = 0.56, R² = 0.69). The Sentinel-2 products exhibited intermediate accuracy among all those products (RMSE: 1.16–1.36). The Landsat-8/9 LAI product showed markedly lower accuracy relative to Sentinel-2; its RMSE (1.63) exceeded that of Sentinel-2 10 m LAI and 20 m LAI by 40.52% and 21.64%, respectively. In addition, all these LAI products showed consistent seasonal variation patterns with the reference LAI maps. Moreover, Sentinel-2 10 m LAI products showed serious underestimation for all vegetation types, with forests providing the highest RMSE = 0.89. This study serves as a valuable reference for the application of multi-scale LAI products in heterogeneous terrain and provides directions for the improvement of fine-resolution LAI retrieval algorithms. Full article

► Show Figures

Figure 1

22 pages, 11631 KB

Open AccessArticle

Local Surface Environmental Changes in a Basin in the Permafrost Region of Qinghai-Tibet Plateau Affected by Lake Outburst Event

by Saize Zhang, Shifen Wu, Zekun Ding, Fujun Niu and Yanhu Mu

Remote Sens. 2025, 17(19), 3392; https://doi.org/10.3390/rs17193392 - 9 Oct 2025

Viewed by 163

Abstract

The outburst of Zonag Lake in the permafrost region of the Qinghai-Tibet Plateau (QTP) has significantly altered the local environment, particularly affecting surface conditions and permafrost dynamics. By employing remote sensing and GIS tools, this study analyzed the spatial and temporal variations in [...] Read more.

The outburst of Zonag Lake in the permafrost region of the Qinghai-Tibet Plateau (QTP) has significantly altered the local environment, particularly affecting surface conditions and permafrost dynamics. By employing remote sensing and GIS tools, this study analyzed the spatial and temporal variations in surface environmental changes (surface temperature, vegetation, and dryness) within the Zonag–Salt Lake basin. The results indicate that the outburst caused higher surface temperatures and reduced vegetation cover around Zonag Lake. Analysis using the Temperature–Vegetation Dryness Index (TVDI) reveals higher dryness levels in downstream areas, especially from Kusai Lake to Salt Lake, compared to the upstream Zonag Lake. Temporal trends from 2000 to 2023 show a decrease in average Land Surface Temperature (LST) and an increase in the Normalized Difference Vegetation Index (NDVI). Geographical centroid shifts in environmental indices demonstrate migration patterns influenced by seasonal climate changes and the outburst event. Desertification around Zonag Lake accelerates permafrost development, while the wetting environment around Salt Lake promotes permafrost degradation. The Zonag Lake region is also an ecologically significant area, serving as a key calving ground for the Tibetan antelope (Pantholops hodgsonii), a nationally protected species. Thus, the environmental changes revealed in this study carry important implications for biodiversity conservation on the Tibetan Plateau. These findings highlight the profound impact of the Zonag Lake outburst on the surface environment and permafrost dynamics in the region, providing critical insights for understanding environmental responses to lake outbursts in high-altitude regions. Full article

(This article belongs to the Special Issue Remote Sensing of Water Dynamics in Permafrost Regions)

► Show Figures

Figure 1

18 pages, 21941 KB

Open AccessArticle

Phenological Shifts of Vegetation in Seasonally Frozen Ground and Permafrost Zones of the Qinghai–Tibet Plateau

by Tianyang Fan, Xinyan Zhong, Chong Wang, Lingyun Zhou and Zhinan Zhou

Remote Sens. 2025, 17(19), 3391; https://doi.org/10.3390/rs17193391 - 9 Oct 2025

Viewed by 176

Abstract

Vegetation phenology serves as a crucial indicator reflecting vegetation responses to the growth environment and climate change. Existing studies have demonstrated that in permafrost regions, the impact of frozen soil changes on vegetation phenology is more direct and pronounced compared to climate factors. [...] Read more.

Vegetation phenology serves as a crucial indicator reflecting vegetation responses to the growth environment and climate change. Existing studies have demonstrated that in permafrost regions, the impact of frozen soil changes on vegetation phenology is more direct and pronounced compared to climate factors. Amid the slowdown of global warming in the 21st century, permafrost dynamics continued to drive uncertain variations in vegetation phenological stages across the Qinghai–Tibet Plateau (QTP). Using MODIS Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) data during 2001–2024, this study derived vegetation phenological parameters and analyzed their spatiotemporal patterns on the QTP. The results indicate that overall, the start of growing season (SOS) was advanced, the end of growing season (EOS) was delayed, and the length of growing season (LOG) was extended throughout the study period. Additionally, divergent phenological trends were observed across three distinct phases, and regarding frozen soil types, vegetation phenology in permafrost and seasonally frozen ground regions exhibited distinct characteristics. From 2001 to 2024, both permafrost and seasonally frozen ground regions showed an advanced SOS and prolonged LOG, but significant differences were observed in EOS dynamics. For vegetation types, alpine meadow displayed advanced SOS and EOS, alongside an extended LOG. The alpine steppe exhibited advanced SOS and delayed EOS with an extended LOG. Alpine desert displayed SOS advancement and EOS delay, alongside LOG extension. These findings revealed variations in vegetation phenological changes under different frozen soil types and highlighted divergent responses of distinct frozen soil types to climate change. They suggested that the influence of frozen soil types should be considered when investigating vegetation phenological dynamics at the regional scale. Full article

► Show Figures

Figure 1

15 pages, 55607 KB

Open AccessArticle

An Enhanced SAR-Based ISW Detection Method Using YOLOv8 with an Anti-Interference Strategy and Repair Module and Its Applications

by Zheyu Lu, Hui Du, Shaodong Wang, Jianping Wu and Pai Peng

Remote Sens. 2025, 17(19), 3390; https://doi.org/10.3390/rs17193390 - 9 Oct 2025

Viewed by 184

Abstract

The detection of internal solitary waves (ISWs) in the ocean using Synthetic Aperture Radar (SAR) images is important for the safety of marine engineering structures. Based on 4120 Sentinel SAR images obtained from 2014 to 2024, an ISW dataset covering the Andaman Sea [...] Read more.

The detection of internal solitary waves (ISWs) in the ocean using Synthetic Aperture Radar (SAR) images is important for the safety of marine engineering structures. Based on 4120 Sentinel SAR images obtained from 2014 to 2024, an ISW dataset covering the Andaman Sea (AS), the South China Sea (SCS), the Sulu Sea (SS), and the Celebes Sea (CS) is constructed, and a deep learning dataset containing 3495 detection samples and 2476 segmentation samples is also established. Based on the YOLOv8 lightweight model, combined with an anti-interference strategy, a multi-size block detection strategy, and a post-processing repair module, an ISW detection method is proposed. This method reduces the false detection rate by 44.20 percentage points in terms of anti-interference performance. In terms of repair performance, the repair rate reaches 85.2%, and the error connection rate is less than 3.1%. The detection results of applying this method to Sentinel images in multiple sea areas show that there are significant regional differences in ISW activities in different sea areas: in the AS, ISW activities peak in the dry season of March and are mainly concentrated in the eastern and southern regions; the western part of the SS and the southern part of the CS are also the core areas of ISW activities. From the perspective of temporal characteristics, the SS maintains a relatively high ISW activity level throughout the dry season, while the CS exhibits more complex seasonal dynamic features. The lightweight detection method proposed in this study has good applicability and can provide support for marine disaster prevention work. Full article

(This article belongs to the Section Ocean Remote Sensing)

► Show Figures

Figure 1

23 pages, 8993 KB

Open AccessArticle

Automatic Rooftop Solar Panel Recognition from UAV LiDAR Data Using Deep Learning and Geometric Feature Analysis

by Joel Coglan, Zahra Gharineiat and Fayez Tarsha Kurdi

Remote Sens. 2025, 17(19), 3389; https://doi.org/10.3390/rs17193389 - 9 Oct 2025

Viewed by 270

Abstract

As drone-based Light Detection and Ranging (LiDAR) becomes more accessible, it presents new opportunities for automated, geometry-driven classification. This study investigates the use of LiDAR point cloud data and Machine Learning (ML) to classify rooftop solar panels from building surfaces. While rooftop solar [...] Read more.

As drone-based Light Detection and Ranging (LiDAR) becomes more accessible, it presents new opportunities for automated, geometry-driven classification. This study investigates the use of LiDAR point cloud data and Machine Learning (ML) to classify rooftop solar panels from building surfaces. While rooftop solar detection has been explored using satellite and aerial imagery, LiDAR offers geometric and reflectance-based attributes for classification. Two datasets were used: the University of Southern Queensland (UniSQ) campus, with commercial-sized panels, both elevated and flat, and a suburban area in Newcastle, Australia, with residential-sized panels sitting flush with the roof surface. UniSQ was classified using RANSAC (Random Sample Consensus), while Newcastle’s dataset was processed based on reflectance values. Geometric features were selected based on histogram overlap and Kullback–Leibler (KL) divergence, and models were trained using a Multilayer Perceptron (MLP) classifier implemented in both PyTorch and Scikit-learn libraries. Classification achieved F1 scores of 99% for UniSQ and 95–96% for the Newcastle dataset. These findings support the potential for ML-based classification to be applied to unlabelled datasets for rooftop solar analysis. Future work could expand the model to detect additional rooftop features and estimate panel counts across urban areas. Full article

► Show Figures

Figure 1

18 pages, 3107 KB

Open AccessArticle

Eutrophication Assessment Revealed by the Distribution of Chlorophyll-a in the South China Sea

by Jingwen Wu, Dong Jiang, Zhichao Cai, Jing Lv, Guowei Liu and Bingtian Li

Remote Sens. 2025, 17(19), 3388; https://doi.org/10.3390/rs17193388 - 9 Oct 2025

Viewed by 141

Abstract

Chlorophyll-a is a key indicator characterizing the health of marine ecosystems. This study aimed to assess eutrophication risk by investigating the spatio-temporal evolution of chlorophyll-a in the South China Sea (SCS). Based on MODIS-Aqua remote sensing data from 2003 to 2024, five spatial [...] Read more.

Chlorophyll-a is a key indicator characterizing the health of marine ecosystems. This study aimed to assess eutrophication risk by investigating the spatio-temporal evolution of chlorophyll-a in the South China Sea (SCS). Based on MODIS-Aqua remote sensing data from 2003 to 2024, five spatial interpolation methods were compared, and Ordinary Kriging was selected as the optimal method (r = 0.96) for reconstructing the chlorophyll-a distribution. The findings indicate that chlorophyll-a is higher in winter and autumn than in summer and spring, with significant enrichment observed near coastal areas. Concentrations decrease with increasing distance from the shore. The Mekong River estuary consistently exhibits high values, while the concentration in the SCS Basin remains persistently low. Furthermore, the spatial extent where chlorophyll concentrations exceed the bloom threshold was evaluated to highlight potential eutrophication risk. These results provide a scientific basis for understanding the response mechanism of the SCS ecosystem to climate change and have important implications for regional marine environmental management and ecological conservation. Full article

(This article belongs to the Special Issue Satellite Remote Sensing for Ocean and Coastal Environment Monitoring (Second Edition))

► Show Figures

Figure 1

23 pages, 20718 KB

Open AccessArticle

PSLRC-Net: A PolInSAR and Spaceborne LiDAR Fusion Method for High-Precision DEM Inversion in Forested Areas

by Xiaoshuai Li, Huihua Hu, Xiaolei Lv and Zenghui Huang

Remote Sens. 2025, 17(19), 3387; https://doi.org/10.3390/rs17193387 - 9 Oct 2025

Viewed by 299

Abstract

The Digital Elevation Model (DEM) is widely used in fields such as geoscience and environmental management. However, the existing DEMs struggle to meet the current requirements for timeliness and accuracy, especially in forested areas where vegetation cover can lead to overestimation of elevation. [...] Read more.

The Digital Elevation Model (DEM) is widely used in fields such as geoscience and environmental management. However, the existing DEMs struggle to meet the current requirements for timeliness and accuracy, especially in forested areas where vegetation cover can lead to overestimation of elevation. To address this issue, this paper proposes a PolInSAR and Spaceborne LiDAR Regression/Classification Network (PSLRC-Net) for refining external DEMs. Additionally, a forest/non-forest classification labeling method for spaceborne LiDAR footprints is introduced to provide labeled data for the classification branch during the training phase. PSLRC-Net adopts a multi-task learning framework and uses an expert selection mechanism based on a gating network to provide targeted support for the regression and classification branches. The regression branch consists of two task towers, and their outputs are weighted and fused by the output of the classification branch. This approach directs the regression branch to focus on the feature differences between forested and non-forested areas, resulting in more accurate elevation predictions. The network was trained on SAOCOM data from two sites, and the fitting results are evaluated for accuracy using an airborne LiDAR-derived DEM. Compared to different DEM datasets, the RMSE decreased by 51.7–64.6% and 51.9–63.7% at the two sites, while the MAE decreased by 55.5–66.8% and 55.5–68.6%. The experimental results confirm the validity of the model and demonstrate the potential of spaceborne LiDAR fusion with spaceborne PolInSAR to improve DEM accuracy. Full article

(This article belongs to the Section Forest Remote Sensing)

► Show Figures

Figure 1

19 pages, 1949 KB

Open AccessArticle

Fire Regions of a Northern Amazonian Landscape Relative to Indigenous Peoples’ Lands

by Anthony R. Cummings, Benjamin J. Kennady and Adewole M. Adeuga

Remote Sens. 2025, 17(19), 3386; https://doi.org/10.3390/rs17193386 - 9 Oct 2025

Viewed by 291

Abstract

Remotely sensed data have been instrumental in improving our understanding of the nature of fires within tropical landscapes. However, most studies have depicted fires in a negative light, highlighting how land-use and land-cover changes make forests more vulnerable to fire damage. In contrast [...] Read more.

Remotely sensed data have been instrumental in improving our understanding of the nature of fires within tropical landscapes. However, most studies have depicted fires in a negative light, highlighting how land-use and land-cover changes make forests more vulnerable to fire damage. In contrast to such fires, indigenous peoples utilize fires as a key part of their livelihood practices, and such relationships have not been extensively examined using remotely sensed data. In this paper, we utilize MODIS Active Fire data to examine the spatial and temporal distribution of fires relative to indigenous lands across Guyana. We employed the DBSCAN clustering algorithm and Voronoi polygons to examine the patterns of fire distribution across the Guyanese landscape. We found that while indigenous territories accounted for approximately 15% of Guyana’s terrestrial landscape, 25% of fires occurred within Amerindian lands, and 71% within 16 km of village boundaries. A strong linear distance decay (R² = 0.97) was observed between the occurrence of fires and Amerindian village boundaries. Four previously undefined fire regions emerged for Guyana–Coastal, Forest, Forest Edge North, and Forest Edge South–with the Forest Edge regions hosting the second highest number of fires but the highest indigenous peoples’ presence. The spatial distribution of fires relative to each region suggested that Forest Edge indigenous villages had a strong reliance on fires as a part of their toolkit for maintaining the rich ecological processes characteristically observed around their lands. Full article

► Show Figures

Figure 1

24 pages, 4764 KB

Open AccessArticle

Mask-Guided Teacher–Student Learning for Open-Vocabulary Object Detection in Remote Sensing Images

by Shuojie Wang, Yu Song, Jiajun Xiang, Yanyan Chen, Ping Zhong and Ruigang Fu

Remote Sens. 2025, 17(19), 3385; https://doi.org/10.3390/rs17193385 - 9 Oct 2025

Viewed by 272

Abstract

Open-vocabulary object detection in remote sensing aims to detect novel categories not seen during training, which is crucial for practical aerial image analysis applications. While some approaches accomplish this task through large-scale data construction, such methods incur substantial annotation and computational costs. In [...] Read more.

Open-vocabulary object detection in remote sensing aims to detect novel categories not seen during training, which is crucial for practical aerial image analysis applications. While some approaches accomplish this task through large-scale data construction, such methods incur substantial annotation and computational costs. In contrast, we focus on efficient utilization of limited datasets. However, existing methods such as CastDet struggle with inefficient data utilization and class imbalance issues in pseudo-label generation for novel categories. We propose an enhanced open-vocabulary detection framework that addresses these limitations through two key innovations. First, we introduce a selective masking strategy that enables direct utilization of partially annotated images by masking base category regions in teacher model inputs. This approach eliminates the need for strict data separation and significantly improves data efficiency. Second, we develop a dynamic frequency-based class weighting that automatically adjusts category weights based on real-time pseudo-label statistics to mitigate class imbalance issues. Our approach integrates these components into a student–teacher learning framework with RemoteCLIP for novel category classification. Comprehensive experiments demonstrate significant improvements on both datasets: on VisDroneZSD, we achieve 42.7% overall mAP and 41.4% harmonic mean, substantially outperforming existing methods. On DIOR dataset, our method achieves 63.7% overall mAP with 49.5% harmonic mean. Our framework achieves more balanced performance between base and novel categories, providing a practical and data-efficient solution for open-vocabulary aerial object detection. Full article

(This article belongs to the Special Issue Multi-Object Detection and Feature Extraction of Remote Sensing Images)

► Show Figures

Figure 1

22 pages, 6335 KB

Open AccessArticle

Impact of Assimilating Doppler Radar Data on Short-Term Numerical Weather Forecasting at Different Spatial Scales

by Guanting Luo, Tingting Li, Ganlin Qiu, Zhizhong Su and Deqiang Liu

Remote Sens. 2025, 17(19), 3384; https://doi.org/10.3390/rs17193384 - 8 Oct 2025

Viewed by 511

Abstract

This study explores the impact of assimilating Doppler radar data on short-term numerical weather forecasting for a heavy rainfall event in Southern China, focusing on different spatial scales. Results show that radar data assimilation significantly improves the initial analysis and enhances the accuracy [...] Read more.

This study explores the impact of assimilating Doppler radar data on short-term numerical weather forecasting for a heavy rainfall event in Southern China, focusing on different spatial scales. Results show that radar data assimilation significantly improves the initial analysis and enhances the accuracy of hourly precipitation forecasts by providing more detailed mesoscale system information, compared to assimilating only wind profiler radar data. The Barnes filter analysis reveals that radar data assimilation has a more pronounced effect on mesoscale systems, with improvements primarily concentrated in the first 2 h of the forecast. However, this improvement diminishes rapidly beyond the 2 h lead time, indicating the inherent predictability limits of mesoscale systems. In contrast, large-scale systems exhibit a greater stability and predictability, with radar data assimilation having a relatively smaller but still positive impact. The study emphasizes the importance of radar data assimilation for short-term forecasts at different spatial scales and suggests that future work prioritize extending mesoscale predictability. Full article

(This article belongs to the Special Issue Multi-Source Atmospheric Remote Sensing: Enabling High-Precision Meteorological Monitoring and Forecasting)

► Show Figures

Figure 1

18 pages, 7245 KB

Open AccessArticle

Simulation Study of the Effect of Multi-Angle ATI-SAR on Sea Surface Current Retrieval Accuracy

by Jiabao Chen, Xiangying Miao, Yong Wan, Jiahui Zhang and Hongli Miao

Remote Sens. 2025, 17(19), 3383; https://doi.org/10.3390/rs17193383 - 8 Oct 2025

Viewed by 250

Abstract

This study investigates the effects of multi-angle along-track interferometric synthetic aperture radar (ATI-SAR) observations on the accuracy of sea surface current retrieval. Utilizing a high-fidelity, full-link SAR ocean simulator, this study systematically assesses the influence of three key factors—the angle between observation directions, [...] Read more.

This study investigates the effects of multi-angle along-track interferometric synthetic aperture radar (ATI-SAR) observations on the accuracy of sea surface current retrieval. Utilizing a high-fidelity, full-link SAR ocean simulator, this study systematically assesses the influence of three key factors—the angle between observation directions, the relative orientation of wind and current, and wind speed—on the precision of two-dimensional (2D) current vector retrievals. Results demonstrate that observation geometry is a dominant factor: retrieval errors are minimized when the two viewing directions are near-orthogonal (~90°), while near-parallel (0° or 180°) geometries result in significant error amplification. Furthermore, the angle between wind and current introduces complex, non-linear error characteristics, with a perpendicular alignment minimizing velocity error but maximizing direction error. Higher wind speeds are found to degrade both velocity and direction retrieval accuracy. Collectively, these findings provide crucial quantitative guidance for optimizing the mission design, observation planning, and algorithm development for future multi-angle ATI-SAR satellite constellations dedicated to ocean current monitoring. Full article

► Show Figures

Figure 1

20 pages, 6167 KB

Open AccessArticle

Spatial/Spectral-Frequency Adaptive Network for Hyperspectral Image Reconstruction in CASSI

by Hejian Liu, Yan Yuan, Xiaorui Yin and Lijuan Su

Remote Sens. 2025, 17(19), 3382; https://doi.org/10.3390/rs17193382 - 8 Oct 2025

Viewed by 301

Abstract

Coded-Aperture Snapshot Spectral Imaging (CASSI) systems acquire 3D spatial–spectral information on dynamic targets by converting 3D hyperspectral images (HSIs) into 2D compressed measurements. Various end-to-end networks have been proposed for HSI reconstruction from these measurements. However, these methods have not explored the frequency-domain [...] Read more.

Coded-Aperture Snapshot Spectral Imaging (CASSI) systems acquire 3D spatial–spectral information on dynamic targets by converting 3D hyperspectral images (HSIs) into 2D compressed measurements. Various end-to-end networks have been proposed for HSI reconstruction from these measurements. However, these methods have not explored the frequency-domain information of HSIs. This research presents the spatial/spectral-frequency adaptive network (SSFAN) for CASSI image reconstruction. A frequency-division transformation (FDT) decomposes HSIs into distinct Fourier frequency components, enabling multiscale feature extraction in the frequency domain. The proposed dual-branch architecture consists of a spatial–spectral module (SSM) to preserve spatial–spectral consistency and a frequency division module (FDM) to model inter-frequency dependencies. Channel compression/expansion modules are integrated into the FDM to balance computational efficiency and reconstruction quality. Frequency-division loss supervises feature learning across divided frequency channels. Ablation experiments validate the contributions of each network module. Furthermore, comparison experiments on synthetic and real CASSI datasets demonstrate that SSFAN outperforms state-of-the-art end-to-end methods in reconstruction performance. Full article

(This article belongs to the Special Issue Advances in Hyperspectral Remote Sensing Image Processing: 2nd Edition)

► Show Figures

Figure 1

19 pages, 4779 KB

Open AccessArticle

Diffractive Neural Network Enabled Spectral Object Detection

by Yijun Ma, Rui Chen, Shuaicun Qian and Shengli Sun

Remote Sens. 2025, 17(19), 3381; https://doi.org/10.3390/rs17193381 - 8 Oct 2025

Viewed by 186

Abstract

This article introduces a diffractive neural network-enabled spectral object detection approach (DNN-SOD) to efficiently process massive sky-based multidimensional light field data. DNN-SOD combines the novel exploitation of target spectral features with the intrinsic parallelism of optical computing to process multidimensional information efficiently. DNN-SOD [...] Read more.

This article introduces a diffractive neural network-enabled spectral object detection approach (DNN-SOD) to efficiently process massive sky-based multidimensional light field data. DNN-SOD combines the novel exploitation of target spectral features with the intrinsic parallelism of optical computing to process multidimensional information efficiently. DNN-SOD detects targets by segmenting the spectral data cube and processing it with the DNN. The DNN maps spectral intensity to the designated area of the detector, then reconstructs spectral curves, and differentiates targets by comparing them with reference spectral signatures. Classification results from individual sub-spectral data cubes are compiled in sequence, enabling accurate target detection. Simulation results indicate that the architecture achieved an accuracy of 91.56% on the MNIST multi-spectral dataset and 84.27% on the infrared target multi-spectral dataset, validating its feasibility for target detection. This architecture represents an innovative outcome at the intersection of remote sensing and optical computing, significantly advancing the dissemination and practical adoption of optical computing in the field. Full article

► Show Figures

Figure 1

21 pages, 4796 KB

Open AccessArticle

Deep Bayesian Optimization of Sparse Aperture for Compressed Sensing 3D ISAR Imaging

by Zongkai Yang, Jingcheng Zhao, Mengyu Zhang, Changyu Lou and Xin Zhao

Remote Sens. 2025, 17(19), 3380; https://doi.org/10.3390/rs17193380 - 7 Oct 2025

Viewed by 302

Abstract

High-resolution three-dimensional (3D) Inverse Synthetic Aperture Radar (ISAR) imaging is essential for the characterization of target scattering in various environments. The practical application of this technique is frequently impeded by the lengthy measurement time necessary for comprehensive data acquisition with turntable-based systems. Sub-sampling [...] Read more.

High-resolution three-dimensional (3D) Inverse Synthetic Aperture Radar (ISAR) imaging is essential for the characterization of target scattering in various environments. The practical application of this technique is frequently impeded by the lengthy measurement time necessary for comprehensive data acquisition with turntable-based systems. Sub-sampling the aperture can decrease acquisition time; however, traditional reconstruction algorithms that utilize matched filtering exhibit significantly impaired imaging performance, often characterized by a high peak side-lobe ratio. A methodology is proposed that integrates compressed sensing(CS) theory with sparse-aperture optimization to achieve high-fidelity 3D imaging from sparsely sampled data. An optimized sparse sampling aperture is introduced to systematically balance the engineering requirement for efficient, continuous turntable motion with the low mutual coherence desired for the CS matrix. A deep Bayesian optimization framework was developed to automatically identify physically realizable optimal sampling trajectories, ensuring that the sensing matrix retains the necessary properties for accurate signal recovery. This method effectively addresses the high-sidelobe problem associated with traditional sparse techniques, significantly decreasing measurement duration while maintaining image quality. Quantitative experimental results indicate the method’s efficacy: the optimized sparse aperture decreases the number of angular sampling points by roughly 84% compared to a full acquisition, while reconstructing images with a high correlation coefficient of 0.98 to the fully sampled reference. The methodology provides an effective solution for rapid, high-performance 3D ISAR imaging, achieving an optimal balance between data acquisition efficiency and reconstruction fidelity. Full article

(This article belongs to the Special Issue Advances in Imaging Radar Signal Processing, Target Feature Extraction and Recognition)

► Show Figures

Figure 1

25 pages, 12740 KB

Open AccessArticle

GM-DETR: Infrared Detection of Small UAV Swarm Targets Based on Detection Transformer

by Chenhao Zhu, Xueli Xie, Jianxiang Xi and Xiaogang Yang

Remote Sens. 2025, 17(19), 3379; https://doi.org/10.3390/rs17193379 - 7 Oct 2025

Viewed by 250

Abstract

Infrared object detection is an important prerequisite for small unmanned aerial vehicle (UAV) swarm countermeasures. Owing to the limited imaging area and texture features of small UAV targets, accurate infrared detection of UAV swarm targets is challenging. In this paper, the GM-DETR is [...] Read more.

Infrared object detection is an important prerequisite for small unmanned aerial vehicle (UAV) swarm countermeasures. Owing to the limited imaging area and texture features of small UAV targets, accurate infrared detection of UAV swarm targets is challenging. In this paper, the GM-DETR is proposed for the detection of densely distributed small UAV swarm targets in infrared scenarios. Specifically, high-level and low-level features are fused by the Fine-Grained Context-Aware Fusion module, which augments texture features in the fused feature map. Furthermore, a Supervised Sampling and Sparsification module is proposed as an explicit guiding mechanism, which assists the GM-DETR to focus on high-quality queries according to the confidence value. The Geometric Relation Encoder is introduced to encode geometric relation among queries, which makes up for the information loss caused by query serialization. In the second stage of the GM-DETR, a long-term memory mechanism is introduced to make UAV detection more stable and distinguishable in motion blur scenes. In the decoder, the self-attention mechanism is improved by introducing memory blocks as additional decoding information, which enhances the robustness of the GM-DETR. In addition, we constructed a small UAV swarm dataset, UAV Swarm Dataset (USD), which comprises 7000 infrared images of low-altitude UAV swarms, as another contribution. The experimental results on the USD show that the GM-DETR outperforms other state-of-the-arts detectors and obtains the best scores (90.6 on

{AP}_{75}

and 63.8 on

{AP}_{S}

), which demonstrates the effectiveness of the GM-DETR in detecting small UAV targets. The good performance of the GM-DETR on the Drone Vehicle dataset also demonstrates the superiority of the proposed modules in detecting small targets. Full article

► Show Figures

Figure 1

29 pages, 9465 KB

Open AccessArticle

Modeling Seasonal Fire Probability in Thailand: A Machine Learning Approach Using Multiyear Remote Sensing Data

by Enikoe Bihari, Karen Dyson, Kayla Johnston, Daniel Marc G. dela Torre, Akkarapon Chaiyana, Karis Tenneson, Wasana Sittirin, Ate Poortinga, Veerachai Tanpipat, Kobsak Wanthongchai, Thannarot Kunlamai, Elijah Dalton, Chanarun Saisaward, Marina Tornorsam, David Ganz and David Saah

Remote Sens. 2025, 17(19), 3378; https://doi.org/10.3390/rs17193378 - 7 Oct 2025

Viewed by 579

Abstract

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, [...] Read more.

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts. Full article

(This article belongs to the Special Issue Remote Sensing in Hazards Monitoring and Risk Assessment)

► Show Figures

Figure 1

27 pages, 67113 KB

Open AccessArticle

DBYOLO: Dual-Backbone YOLO Network for Lunar Crater Detection

by Yawen Liu, Fukang Chen, Denggao Qiu, Wei Liu and Jianguo Yan

Remote Sens. 2025, 17(19), 3377; https://doi.org/10.3390/rs17193377 - 7 Oct 2025

Viewed by 311

Abstract

Craters are among the most prominent and significant geomorphological features on the lunar surface. The complex and variable environment of the lunar surface, which is characterized by diverse textures, lighting conditions, and terrain variations, poses significant challenges to existing crater detection methods. To [...] Read more.

Craters are among the most prominent and significant geomorphological features on the lunar surface. The complex and variable environment of the lunar surface, which is characterized by diverse textures, lighting conditions, and terrain variations, poses significant challenges to existing crater detection methods. To address these challenges, this study introduces DBYOLO, an innovative deep learning framework designed for lunar crater detection, leveraging a dual-backbone feature fusion network, with two key innovations. The first innovation is a lightweight dual-backbone network that processes Lunar Reconnaissance Orbiter Camera (LROC) CCD images and Digital Terrain Model (DTM) data separately, extracting texture and edge features from CCD images and terrain depth features from DTM data. The second innovation is a feature fusion module with attention mechanisms that is used to dynamically integrate multi-source data, enabling the efficient extraction of complementary information from both CCD images and DTM data, enhancing crater detection performance in complex lunar surface environments. Experimental results demonstrate that DBYOLO, with only 3.6 million parameters, achieves a precision of 77.2%, recall of 70.3%, mAP50 of 79.4%, and mAP50-95 of 50.4%, representing improvements of 3.1%, 1.8%, 3.1%, and 2.6%, respectively, over the baseline model before modifications. This showcases an overall performance enhancement, providing a new solution for lunar crater detection and offering significant support for future lunar exploration efforts. Full article

(This article belongs to the Special Issue New Views of the Moon: Recent Advances in Lunar Remote Sensing and Applications)

► Show Figures

Figure 1

24 pages, 8595 KB

Open AccessArticle

Integrated Geomatic Approaches for the 3D Documentation and Analysis of the Church of Saint Andrew in Orani, Sardinia

by Giuseppina Vacca and Enrica Vecchi

Remote Sens. 2025, 17(19), 3376; https://doi.org/10.3390/rs17193376 - 7 Oct 2025

Viewed by 292

Abstract

Documenting cultural heritage sites through 3D reconstruction is crucial and can be accomplished using various geomatic techniques, such as Terrestrial Laser Scanners (TLS), Close-Range Photogrammetry (CRP), and UAV photogrammetry. Each method comes with different levels of complexity, accuracy, field times, post-processing requirements, and [...] Read more.

Documenting cultural heritage sites through 3D reconstruction is crucial and can be accomplished using various geomatic techniques, such as Terrestrial Laser Scanners (TLS), Close-Range Photogrammetry (CRP), and UAV photogrammetry. Each method comes with different levels of complexity, accuracy, field times, post-processing requirements, and costs, making them suitable for different types of restitutions. Recently, research has increasingly focused on user-friendly and faster techniques, while also considering the cost–benefit balance between accuracy, times, and costs. In this scenario, photogrammetry using images captured with 360-degree cameras and LiDAR sensors integrated into Apple devices have gained significant popularity. This study proposes the application of various techniques for the geometric reconstruction of a complex cultural heritage site, the Church of Saint Andrew in Orani, Sardinia. Datasets acquired from different geomatic techniques have been evaluated in terms of quality and usability for documenting various aspects of the site. The TLS provided an accurate model of both the interior and exterior of the church, serving as the ground truth for the validation process. UAV photogrammetry offered a broader view of the exterior, while panoramic photogrammetry from 360° camera was applied to survey the bell tower’s interior. Additionally, CRP and Apple LiDAR were compared in the context of a detailed survey. Full article

(This article belongs to the Section Remote Sensing Image Processing)

► Show Figures

Figure 1

41 pages, 4705 KB

Open AccessArticle

Full-Cycle Evaluation of Multi-Source Precipitation Products for Hydrological Applications in the Magat River Basin, Philippines

by Jerome G. Gacu, Sameh Ahmed Kantoush and Binh Quang Nguyen

Remote Sens. 2025, 17(19), 3375; https://doi.org/10.3390/rs17193375 - 7 Oct 2025

Viewed by 270

Abstract

Satellite Precipitation Products (SPPs) play a crucial role in hydrological modeling, particularly in data-scarce and climate-sensitive basins such as the Magat River Basin (MRB), Philippines—one of Southeast Asia’s most typhoon-prone and infrastructure-critical watersheds. This study presents the first full-cycle evaluation of nine widely [...] Read more.

Satellite Precipitation Products (SPPs) play a crucial role in hydrological modeling, particularly in data-scarce and climate-sensitive basins such as the Magat River Basin (MRB), Philippines—one of Southeast Asia’s most typhoon-prone and infrastructure-critical watersheds. This study presents the first full-cycle evaluation of nine widely used multi-source precipitation products (2000–2024), integrating raw validation against rain gauge observations, bias correction using quantile mapping, and post-correction re-ranking through an Entropy Weight Method–TOPSIS multi-criteria decision analysis (MCDA). Before correction, SM2RAIN-ASCAT demonstrated the strongest statistical performance, while CHIRPS and ClimGridPh-RR exhibited robust detection skills and spatial consistency. Following bias correction, substantial improvements were observed across all products, with CHIRPS markedly reducing systematic errors and ClimGridPh-RR showing enhanced correlation and volume reliability. Biases were decreased significantly, highlighting the effectiveness of quantile mapping in improving both seasonal and annual precipitation estimates. Beyond conventional validation, this framework explicitly aligns SPP evaluation with four critical hydrological applications: flood detection, drought monitoring, sediment yield modeling, and water balance estimation. The analysis revealed that SM2RAIN-ASCAT is most suitable for monitoring seasonal drought and dry periods, CHIRPS excels in detecting high-intensity and erosive rainfall events, and ClimGridPh-RR offers the most consistent long-term volume-based estimates. By integrating validation, correction, and application-specific ranking, this study provides a replicable blueprint for operational SPP assessment in monsoon-dominated, data-limited basins. The findings underscore the importance of tailoring product selection to hydrological purposes, supporting improved flood early warning, drought preparedness, sediment management, and water resources governance under intensifying climatic extremes. Full article

(This article belongs to the Special Issue Monitoring and Assessment of Ecohydrological Evolution of River–Lake–Wetland Systems Based on Remote Sensing Big Data)

► Show Figures

Figure 1

34 pages, 13615 KB

Open AccessArticle

Seamless Reconstruction of MODIS Land Surface Temperature via Multi-Source Data Fusion and Multi-Stage Optimization

by Yanjie Tang, Yanling Zhao, Yueming Sun, Shenshen Ren and Zhibin Li

Remote Sens. 2025, 17(19), 3374; https://doi.org/10.3390/rs17193374 - 7 Oct 2025

Viewed by 318

Abstract

Land Surface Temperature (LST) is a critical variable for understanding land–atmosphere interactions and is widely applied in urban heat monitoring, evapotranspiration estimation, near-surface air temperature modeling, soil moisture assessment, and climate studies. MODIS LST products, with their global coverage, long-term consistency, and radiometric [...] Read more.

Land Surface Temperature (LST) is a critical variable for understanding land–atmosphere interactions and is widely applied in urban heat monitoring, evapotranspiration estimation, near-surface air temperature modeling, soil moisture assessment, and climate studies. MODIS LST products, with their global coverage, long-term consistency, and radiometric calibration, are a major source of LST data. However, frequent data gaps caused by cloud contamination and atmospheric interference severely limit their applicability in analyses requiring high spatiotemporal continuity. This study presents a seamless MODIS LST reconstruction framework that integrates multi-source data fusion and a multi-stage optimization strategy. The method consists of three key components: (1) topography- and land cover-constrained spatial interpolation, which preliminarily fills orbit-induced gaps using elevation and land cover similarity criteria; (2) pixel-level LST reconstruction via random forest (RF) modeling with multi-source predictors (e.g., NDVI, NDWI, surface reflectance, DEM, land cover), coupled with HANTS-based temporal smoothing to enhance temporal consistency and seasonal fidelity; and (3) Poisson-based image fusion, which ensures spatial continuity and smooth transitions without compromising temperature gradients. Experiments conducted over two representative regions—Huainan and Jining—demonstrate the superior performance of the proposed method under both daytime and nighttime scenarios. The integrated approach (Step 3) achieves high accuracy, with correlation coefficients (CCs) exceeding 0.95 and root mean square errors (RMSEs) below 2K, outperforming conventional HANTS and standalone interpolation methods. Cross-validation with high-resolution Landsat LST further confirms the method’s ability to retain spatial detail and cross-scale consistency. Overall, this study offers a robust and generalizable solution for reconstructing MODIS LST with high spatial and temporal fidelity. The framework holds strong potential for broad applications in land surface process modeling, regional climate studies, and urban thermal environment analysis. Full article

► Show Figures

Figure 1

16 pages, 2923 KB

Open AccessArticle

Assessing the Capability of Visible Near-Infrared Reflectance Spectroscopy to Monitor Soil Organic Carbon Changes with Localized Predictive Modeling

by Na Dong, Dongyan Wang, Hongguang Cai, Qi Sun and Pu Shi

Remote Sens. 2025, 17(19), 3373; https://doi.org/10.3390/rs17193373 - 6 Oct 2025

Viewed by 282

Abstract

Visible near-infrared (VNIR) spectroscopy offers a cost-effective solution to quantify the spatiotemporal dynamics of soil organic carbon (SOC), especially in the context of rapid advances in spectra-based local modeling approaches using large-scale soil spectral libraries. And yet, direct temporal transferability of VNIR spectroscopic [...] Read more.

Visible near-infrared (VNIR) spectroscopy offers a cost-effective solution to quantify the spatiotemporal dynamics of soil organic carbon (SOC), especially in the context of rapid advances in spectra-based local modeling approaches using large-scale soil spectral libraries. And yet, direct temporal transferability of VNIR spectroscopic modeling (applying historical models to new spectral data) and its capability to monitor temporal changes in SOC remain underexplored. To address this gap, this study uses the LUCAS Soil dataset (2009 and 2015) from France to evaluate the effectiveness of localized spectral models in detecting SOC changes. Two local learning algorithms, memory-based learning (MBL) and GLOBAL-LOCAL algorithms, were adapted to integrate spectral and soil property similarities during local training set selection, while also incorporating LUCAS 2009 soil measurements (clay, silt, sand, CEC) as covariates. These adapted local learning algorithms were then compared against global partial least squares regression (PLSR). The results demonstrated that localized models substantially outperformed global PLSR, with MBL achieving the highest accuracy for croplands, grasslands, and woodlands (R² = 0.72–0.79, RMSE = 4.73–20.92 g/kg). Incorporating soil properties during the local learning procedure reduced spectral heterogeneity, leading to improved SOC prediction accuracy. This improvement was particularly pronounced after excluding organic soils from grasslands and woodlands, as evidenced by 13.3–21.1% decreases in the RMSE. Critically, for SOC monitoring, spectrally predicted SOC successfully identified over 70% of samples experiencing significant SOC changes (>10% loss or gain), effectively capturing the spatial patterns of SOC changes. This study demonstrated the potential of localized spectral modeling as a cost-effective tool for monitoring SOC dynamics, enabling efficient and large-scale assessments critical for sustainable soil management. Full article

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)

► Show Figures

Figure 1

24 pages, 38672 KB

Open AccessArticle

RMTDepth: Retentive Vision Transformer for Enhanced Self-Supervised Monocular Depth Estimation from Oblique UAV Videos

by Xinrui Zeng, Bin Luo, Shuo Zhang, Wei Wang, Jun Liu and Xin Su

Remote Sens. 2025, 17(19), 3372; https://doi.org/10.3390/rs17193372 - 6 Oct 2025

Viewed by 411

Abstract

Self-supervised monocular depth estimation from oblique UAV videos is crucial for enabling autonomous navigation and large-scale mapping. However, existing self-supervised monocular depth estimation methods face key challenges in UAV oblique video scenarios: depth discontinuity from geometric distortion under complex viewing angles, and spatial [...] Read more.

Self-supervised monocular depth estimation from oblique UAV videos is crucial for enabling autonomous navigation and large-scale mapping. However, existing self-supervised monocular depth estimation methods face key challenges in UAV oblique video scenarios: depth discontinuity from geometric distortion under complex viewing angles, and spatial ambiguity in weakly textured regions. These challenges highlight the need for models that combine global reasoning with geometric awareness. Accordingly, we propose RMTDepth, a self-supervised monocular depth estimation framework for UAV imagery. RMTDepth integrates an enhanced Retentive Vision Transformer (RMT) backbone, introducing explicit spatial priors via a Manhattan distance-driven spatial decay matrix for efficient long-range geometric modeling, and embeds a neural window fully-connected CRF (NeW CRFs) module in the decoder to refine depth edges by optimizing pairwise relationships within local windows. To mitigate noise in COLMAP-generated depth for real-world UAV datasets, we constructed a high-fidelity UE4/AirSim simulation environment, which generated a large-scale precise depth dataset (UAV SIM Dataset) to validate robustness. Comprehensive experiments against seven state-of-the-art methods across UAVID Germany, UAVID China, and UAV SIM datasets demonstrate that our model achieves SOTA performance in most scenarios. Full article

► Show Figures

Figure 1

21 pages, 2239 KB

Open AccessReview

Unequal Horizons: Global North–South Disparities in Archaeological Earth Observation (2000–2025)

by Athos Agapiou

Remote Sens. 2025, 17(19), 3371; https://doi.org/10.3390/rs17193371 - 6 Oct 2025

Viewed by 302

Abstract

This systematic review analyzes 4359 archaeologically relevant publications spanning 25 years to examine global disparities in archaeological remote sensing research between Global North and Global South participation. This study reveals deep inequalities among these regions, with 72.1% of research output originating from Global [...] Read more.

This systematic review analyzes 4359 archaeologically relevant publications spanning 25 years to examine global disparities in archaeological remote sensing research between Global North and Global South participation. This study reveals deep inequalities among these regions, with 72.1% of research output originating from Global North-only institutions, despite these regions hosting less than half of UNESCO World Heritage Sites. The temporal analysis demonstrates exponential growth, with 47.2% of all research published in the last five years, indicating rapid technological advancement concentrated in well-resourced institutions. Sub-Saharan Africa produces only 0.6% of research output while hosting 9.4% of World Heritage Sites, highlighting a technology gap in heritage protection. The findings suggest an urgent need for coordinated interventions to address structural inequalities and promote technological fairness in global heritage preservation. The research employed bibliometric analysis of Scopus database records from four complementary search strategies, revealing that just three countries—Italy (20.3%), the United States (16.7%), and the United Kingdom (10.0%)—account for nearly half of all archaeological remote sensing research and applications worldwide. This study documents patterns that have profound implications for cultural heritage preservation and sustainable development in an increasingly digital world where advanced Earth observation technologies have become essential for effective heritage protection and archaeological research. Full article

► Show Figures

Figure 1

29 pages, 62517 KB

Open AccessArticle

Coastal Vulnerability Index Assessment Along the Coastline of Casablanca Using Remote Sensing and GIS Techniques

by Anselme Muzirafuti and Christos Theocharidis

Remote Sens. 2025, 17(19), 3370; https://doi.org/10.3390/rs17193370 - 6 Oct 2025

Viewed by 444

Abstract

This study explores the potential of Digital Earth Africa (DE Africa) coastlines products for assessing the Coastal Vulnerability Index (CVI) along the Casablanca coastline, Morocco. The analysis integrates remotely sensed shoreline data with elevation, slope, and geomorphological information from ASTER GDEM and geological [...] Read more.

This study explores the potential of Digital Earth Africa (DE Africa) coastlines products for assessing the Coastal Vulnerability Index (CVI) along the Casablanca coastline, Morocco. The analysis integrates remotely sensed shoreline data with elevation, slope, and geomorphological information from ASTER GDEM and geological maps within a GIS environment. Shoreline change metrics, including Shoreline Change Envelope (SCE), Net Shoreline Movement (NSM), Linear Regression Rate (LRR), and End Point Rate (EPR), were used to evaluate erosion trends from 2000 to 2023. Results show that sandy beach areas, particularly those below 12 m elevation, are highly exposed to erosion (up to 1.5 m/yr) and vulnerable to coastal hazards. Approximately 44% and 23% of the study area were classified as having very high and high vulnerability, respectively. The results indicate that remotely sensed data and GIS techniques are valuable and cost-effective tools for multi-scale geo-hazard coastal assessment studies. The study demonstrates that DE Africa products, combined with local landscape data, provide a valuable tool for coastal vulnerability assessment and monitoring in Africa. Full article

(This article belongs to the Special Issue Application of Remote Sensing in Coastline Monitoring)

► Show Figures

Figure 1

28 pages, 5791 KB

Open AccessArticle

Tree Health Assessment Using Mask R-CNN on UAV Multispectral Imagery over Apple Orchards

by Mohadeseh Kaviani, Brigitte Leblon, Thangarajah Akilan, Dzhamal Amishev, Armand LaRocque and Ata Haddadi

Remote Sens. 2025, 17(19), 3369; https://doi.org/10.3390/rs17193369 - 6 Oct 2025

Viewed by 356

Abstract

Accurate tree health monitoring in orchards is essential for optimal orchard production. This study investigates the efficacy of a deep learning-based object detection single-step method for detecting tree health on multispectral UAV imagery. A modified Mask R-CNN framework is employed with four different [...] Read more.

Accurate tree health monitoring in orchards is essential for optimal orchard production. This study investigates the efficacy of a deep learning-based object detection single-step method for detecting tree health on multispectral UAV imagery. A modified Mask R-CNN framework is employed with four different backbones—ResNet-50, ResNet-101, ResNeXt-101, and Swin Transformer—on three image combinations: (1) RGB images, (2) 5-band multispectral images comprising RGB, Red-Edge, and Near-Infrared (NIR) bands, and (3) three principal components (3PCs) computed from the reflectance of the five spectral bands and twelve associated vegetation index images. The Mask R-CNN, having a ResNeXt-101 backbone, and applied to the 5-band multispectral images, consistently outperforms other configurations, with an F1-score of 85.68% and a mean Intersection over Union (mIoU) of 92.85%. To address the class imbalance, class weighting and focal loss were integrated into the model, yielding improvements in the detection of the minority class, i.e., the unhealthy trees. The tested method has the advantage of allowing the detection of unhealthy trees over UAV images using a single-step approach. Full article

► Show Figures

Figure 1

26 pages, 12151 KB

Open AccessArticle

Toward Automatic 3D Model Reconstruction of Building Curtain Walls from UAV Images Based on NeRF and Deep Learning

by Zeyu Li, Qian Wang, Hongzhe Yue and Xiang Nie

Remote Sens. 2025, 17(19), 3368; https://doi.org/10.3390/rs17193368 - 5 Oct 2025

Viewed by 355

Abstract

The Automated Building Information Modeling (BIM) reconstruction of existing building curtain walls is crucial for promoting digital Operation and Maintenance (O&M). However, existing 3D reconstruction technologies are mainly designed for general architectural scenes, and there is currently a lack of research specifically focused [...] Read more.

The Automated Building Information Modeling (BIM) reconstruction of existing building curtain walls is crucial for promoting digital Operation and Maintenance (O&M). However, existing 3D reconstruction technologies are mainly designed for general architectural scenes, and there is currently a lack of research specifically focused on the BIM reconstruction of curtain walls. This study proposes a BIM reconstruction method from unmanned aerial vehicle (UAV) images based on neural radiance field (NeRF) and deep learning-based semantic segmentation. The proposed method compensates for the lack of semantic information in traditional NeRF methods and could fill the gap in the automatic reconstruction of semantic models for curtain walls. A comprehensive high-rise building is selected as a case study to validate the proposed method. The results show that the overall accuracy (OA) for semantic segmentation of curtain wall point clouds is 71.8%, and the overall dimensional error of the reconstructed BIM model is less than 0.1m, indicating high modeling accuracy. Additionally, this study compares the proposed method with photogrammetry-based reconstruction and traditional semantic segmentation methods to further validate its effectiveness. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

22 pages, 5361 KB

Open AccessArticle

LMVMamba: A Hybrid U-Shape Mamba for Remote Sensing Segmentation with Adaptation Fine-Tuning

by Fan Li, Xiao Wang, Haochen Wang, Hamed Karimian, Juan Shi and Guozhen Zha

Remote Sens. 2025, 17(19), 3367; https://doi.org/10.3390/rs17193367 - 5 Oct 2025

Viewed by 495

Abstract

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing [...] Read more.

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

(This article belongs to the Special Issue Advances in Deep Learning and Machine Learning for Remote Sensing Image Analysis)

► Show Figures

Graphical abstract

36 pages, 51143 KB

Open AccessArticle

UAV-PPK Photogrammetry, GIS, and Soil Analysis to Estimate Long-Term Slip Rates on Active Faults in a Seismic Gap of Northern Calabria (Southern Italy)

by Daniele Cirillo, Anna Chiara Tangari, Fabio Scarciglia, Giusy Lavecchia and Francesco Brozzetti

Remote Sens. 2025, 17(19), 3366; https://doi.org/10.3390/rs17193366 - 5 Oct 2025

Viewed by 617

Abstract

The study of faults in seismic gap areas is essential for assessing the potential for future seismic activity and developing strategies to mitigate its impact. In this research, we employed a combination of geomorphological analysis, aerophotogrammetry, high-resolution topography, and soil analysis to estimate [...] Read more.

The study of faults in seismic gap areas is essential for assessing the potential for future seismic activity and developing strategies to mitigate its impact. In this research, we employed a combination of geomorphological analysis, aerophotogrammetry, high-resolution topography, and soil analysis to estimate the age of tectonically exposed fault surfaces in a seismic gap area. Our focus was on the Piano delle Rose Fault in the northern Calabria region, (southern Italy), which is a significant regional tectonic structure associated with seismic hazards. We conducted a field survey to carry out structural and pedological observations and collect soil samples from the fault surface. These samples were analyzed to estimate the fault’s age based on their features and degree of pedogenic development. Additionally, we used high-resolution topography and aerophotogrammetry to create a detailed 3D model of the fault surface, allowing us to identify features such as fault scarps and offsets. Our results indicate recent activity on the fault surface, suggesting that the Piano delle Rose Fault may pose a significant seismic hazard. Soil analysis suggests that the onset of the fault surface is relatively young, estimated in an interval time from 450,000 to ~ 300,000 years old. Considering these age constraints, the long-term slip rates are estimated to range between ~0.12 mm/yr and ~0.33 mm/yr, which are values comparable with those of many other well-known active faults of the Apennines extensional belt. Analyses of key fault exposures document cumulative displacements up to 21 m. These values yield long-term slip rates ranging from ~0.2 mm/yr (100,000 years) to ~1.0 mm/yr (~20,000 years LGM), indicating persistent Late Quaternary activity. A second exposure records ~0.6 m of displacement in very young soils, confirming surface faulting during recent times and suggesting that the fault is potentially capable of generating ground-rupturing earthquakes. High-resolution topography and aerophotogrammetry analyses show evidence of ongoing tectonic deformation, indicating that the area is susceptible to future seismic activity and corresponding risk. Our study highlights the importance of integrating multiple techniques for examining fault surfaces in seismic gap areas. By combining geomorphological analysis, aerophotogrammetry, high-resolution topography, and soil analysis, we gain a comprehensive understanding of the structure and behavior of faults. This approach can help assess the potential for future seismic activity and develop strategies for mitigating its impact. Full article

(This article belongs to the Special Issue Multiplatform Remote Sensing Techniques for Active Tectonics, Seismotectonics, and Volcanic Hazard Assessment (Second Edition))

► Show Figures

Figure 1

23 pages, 2760 KB

Open AccessArticle

Improving the Accuracy of Seasonal Crop Coefficients in Grapevine from Sentinel-2 Data

by Diego R. Guevara-Torres, Hankun Luo, Chi Mai Do, Bertram Ostendorf and Vinay Pagay

Remote Sens. 2025, 17(19), 3365; https://doi.org/10.3390/rs17193365 - 4 Oct 2025

Viewed by 314

Abstract

Accurate assessment of a crop’s water requirement is essential for optimising irrigation scheduling and increasing the sustainability of water use. The crop coefficient (K_c) is a dimensionless factor that converts reference evapotranspiration (ET₀) into actual crop evapotranspiration (ET [...] Read more.

Accurate assessment of a crop’s water requirement is essential for optimising irrigation scheduling and increasing the sustainability of water use. The crop coefficient (K_c) is a dimensionless factor that converts reference evapotranspiration (ET₀) into actual crop evapotranspiration (ET_c) and is widely used for irrigation scheduling. The K_c reflects canopy cover, phenology, and crop type/variety, but is difficult to measure directly in heterogeneous perennial systems, such as vineyards. Remote sensing (RS) products, especially open-source satellite imagery, offer a cost-effective solution at moderate spatial and temporal scales, although their application in vineyards has been relatively limited due to the large pixel size (~100 m²) relative to vine canopy size (~2 m²). This study aimed to improve grapevine K_c predictions using vegetation indices derived from harmonised Sentinel-2 imagery in combination with spectral unmixing, with ground data obtained from canopy light interception measurements in three winegrape cultivars (Shiraz, Cabernet Sauvignon, and Chardonnay) in the Barossa and Eden Valleys, South Australia. A linear spectral mixture analysis approach was taken, which required estimation of vine canopy cover through beta regression models to improve the accuracy of vegetation indices that were used to build the K_c prediction models. Unmixing improved the prediction of seasonal K_c values in Shiraz (R² of 0.625, RMSE = 0.078, MAE = 0.063), Cabernet Sauvignon (R² = 0.686, RMSE = 0.072, MAE = 0.055) and Chardonnay (R² = 0.814, RMSE = 0.075, MAE = 0.059) compared to unmixed pixels. Furthermore, unmixing improved predictions during the early and late canopy growth stages when pixel variability was greater. Our findings demonstrate that integrating open-source satellite data with machine learning models and spectral unmixing can accurately reproduce the temporal dynamics of K_c values in vineyards. This approach was also shown to be transferable across cultivars and regions, providing a practical tool for crop monitoring and irrigation management in support of sustainable viticulture. Full article

(This article belongs to the Special Issue Remote Sensing for Agricultural Water Management (RSAWM) (Second Edition))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 17, Issue 19 (October-1 2025) – 132 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI