Previous Issue
Volume 17, September-1
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.6
4.1
Journals
Remote Sensing
Volume 17
Issue 18
remotesensing-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Remote Sens., Volume 17, Issue 18 (September-2 2025) – 34 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
27 pages, 26146 KB  
Article
EfficientRDet: An EfficientDet-Based Framework for Precise Ship Detection in Remote Sensing Imagery
by Weikang Zuo and Shenghui Fang
Remote Sens. 2025, 17(18), 3160; https://doi.org/10.3390/rs17183160 - 11 Sep 2025
Abstract
Detecting arbitrarily oriented ships in remote sensing images remains challenging due to diverse orientations, complex backgrounds, and scale variations, leading to a struggle in balancing detector accuracy with efficiency. We propose EfficientRDet, an enhanced rotated-ship detection algorithm built upon the EfficientDet framework. EfficientRDet [...] Read more.
Detecting arbitrarily oriented ships in remote sensing images remains challenging due to diverse orientations, complex backgrounds, and scale variations, leading to a struggle in balancing detector accuracy with efficiency. We propose EfficientRDet, an enhanced rotated-ship detection algorithm built upon the EfficientDet framework. EfficientRDet adapts to rotated objects via an angle prediction branch and then significantly boosts accuracy with a novel pseudo-two-stage paradigm comprising a Rotated-Bounding-Box Refinement Branch (RRB) and a Class-Score Refinement Branch (CRB). Further precision is gained through an optimized Enhanced BiFPN (E-BiFPN), an Attention Head, and Distribution Focal (DF) angle representation. Extensive experiments on the HRSC2016 (optical) and RSDD-SAR datasets show that EfficientRDet consistently outperforms state-of-the-art methods, achieving 97.60% AP50 on HRSC2016 and 93.58% AP50 on RSDD-SAR. Comprehensive ablation studies confirm the effectiveness of all proposed mechanisms. EfficientRDet thus offers a promising and practical solution for precise, efficient ship detection across diverse remote sensing imagery. Full article
(This article belongs to the Special Issue Target Recognition and Detection Based on High Resolution Radar Images)
54 pages, 5223 KB  
Article
Leveraging Sentinel-2 Data and Machine Learning for Drought Detection in India: The Process of Ground Truth Construction and a Case Study
by Shubham Subhankar Sharma, Jit Mukherjee and Fabio Dell’Acqua
Remote Sens. 2025, 17(18), 3159; https://doi.org/10.3390/rs17183159 - 11 Sep 2025
Abstract
Droughts significantly impact agriculture, water resources, and ecosystems. Their timely detection is essential for implementing effective mitigation strategies. This study explores the use of multispectral Sentinel-2 remote sensing indices and machine learning techniques to detect drought conditions in three distinct regions of India, [...] Read more.
Droughts significantly impact agriculture, water resources, and ecosystems. Their timely detection is essential for implementing effective mitigation strategies. This study explores the use of multispectral Sentinel-2 remote sensing indices and machine learning techniques to detect drought conditions in three distinct regions of India, such as Jodhpur, Amravati, and Thanjavur, during the Rabi season (October–April). Twelve remote sensing indices were studied to assess different aspects of vegetation health, soil moisture, and water stress, and their possible joint use and influence as indicators of regional drought events. Reference data used to define drought conditions in each region were primarily sourced from official government drought declarations and regional and national news publications, which provide seasonal maps of drought conditions across the country. Based on this information, a district vs. year (3 × 10) ground truth is created, indicating the presence or absence of drought (Drought/No Drought) for each region across the ten-year period. Using this ground truth table, we extended the remote sensing dataset by adding a binary drought label for each observation: 1 for “Drought” and 0 for “No Drought”. The dataset is organized by year (2016–2025) in a two-dimensional format, with indices as columns and observations as rows. Each observation represents a single measurement of the remote sensing indices. This enriched dataset serves as the foundation for training and evaluating machine learning models aimed at classifying drought conditions based on spectral information. The resultant remote sensing dataset was used to predict drought events through various machine learning models, including Random Forest, XGBoost, Bagging Classifier, and Gradient Boosting. Among the models, XGBoost achieved the highest accuracy (84.80%), followed closely by the Bagging Classifier (83.98%) and Random Forest (82.98%). In terms of precision, Bagging Classifier and Random Forest performed comparably (82.31% and 81.45%, respectively), while XGBoost achieved a precision of 81.28%. We applied a seasonal majority voting strategy, assigning a final drought label for each region and Rabi season based on the majority of predicted monthly labels. Using this method, XGBoost and Bagging Classifier achieved 96.67% accuracy, precision, and recall, while Random Forest and Gradient Boosting reached 90% and 83.33%, respectively, across all metrics. Shapley Additive Explanation (SHAP) analysis revealed that Normalized Multi-band Drought Index (NMDI) and Day of Season (DOS) consistently emerged as the most influential features in determining model predictions. This finding is supported by the Borda Count and Weighted Sum analysis, which ranked NMDI, and DOS as the top feature across all models. Additionally, Red-edge Chlorophyll Index (RECI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), and Ratio Drought Index (RDI) were identified as important features contributing to model performance. These features help reveal the underlying spatiotemporal dynamics of drought indicators, offering interpretable insights into model decisions. To evaluate the impact of feature selection, we further conducted a feature ablation study. We trained each model using different combinations of top features: Top 1, Top 2, Top 3, Top 4, and Top 5. The performance of each model was assessed based on accuracy, precision, and recall. XGBoost demonstrated the best overall performance, especially when using the Top 5 features. Full article
(This article belongs to the Special Issue Deep Learning and Foundation Models: Advancing Remote Sensing Applications)
25 pages, 7059 KB  
Article
CSTC: Visual Transformer Network with Multimodal Dual Fusion for Hyperspectral and LiDAR Image Classification
by Yong Mei, Jinlong Fan, Xiangsuo Fan and Qi Li
Remote Sens. 2025, 17(18), 3158; https://doi.org/10.3390/rs17183158 - 11 Sep 2025
Abstract
Convolutional neural networks have made significant progress in multimodal remote sensing image classification, but traditional convolutional neural networks are limited by fixed-size convolutional kernels, which are unable to effectively model and adequately extract contextual information; hyperspectral imagery and LiDAR data have comparatively large [...] Read more.
Convolutional neural networks have made significant progress in multimodal remote sensing image classification, but traditional convolutional neural networks are limited by fixed-size convolutional kernels, which are unable to effectively model and adequately extract contextual information; hyperspectral imagery and LiDAR data have comparatively large information differences, which do not allow for effective information interaction and fusion. Based on this, this paper proposes a multimodal dual fusion network (CSTC) based on the Vision Transformer for the collaborative classification of HSI and LiDAR data. The model is designed through a two-branch architecture: the HSI branch extracts spectral–spatial features by dimensionality reduction using principal component analysis and inputs them into the cross-connectivity feature fusion module; the LiDAR branch mines spatial elevation features through the stacked MobileNetV2 module. The features of the two branches are encoded by a Transformer, and the modal interaction fusion is realized by the cross-attention module for the first time. Then, the features are spliced and input into the secondary Transformer for deep cross-modal fusion, and finally, the classification is completed by the multilayer perceptron. Experiments show that the CSTC model achieves overall classification accuracies of 92.32%, 99.81%, 97.90%, and 99.37% on the publicly available MUUFL dataset, Trento dataset, Augsburg dataset, and Houston2013 dataset, respectively, which is superior to the latest HSI–LiDAR separate classification algorithms. The ablation experiments and model performance evaluation experiments further show that the proposed CSTC model achieves excellent results in terms of robustness, adaptability, and parameter scale. Full article
23 pages, 1424 KB  
Review
Advancing Water Quality Management: Harnessing the Synergy of Remote Sensing, Process-Based Models, and Machine Learning to Enhance Monitoring and Prediction
by Peixin Wang, Shubin Zou, Jie Li, Hanyu Ju and Jingjie Zhang
Remote Sens. 2025, 17(18), 3157; https://doi.org/10.3390/rs17183157 - 11 Sep 2025
Abstract
Amid the intensifying challenges of climate change and human activities such as shifts in agricultural practices, the pressure on water resources, particularly regarding water quality, has intensified. As a result, improving water quality monitoring and prediction has emerged as an essential strategy to [...] Read more.
Amid the intensifying challenges of climate change and human activities such as shifts in agricultural practices, the pressure on water resources, particularly regarding water quality, has intensified. As a result, improving water quality monitoring and prediction has emerged as an essential strategy to tackle these challenges and ensure the sustainable management of water resources. Traditional water quality monitoring technologies have inherent limitations; however, integrating remote sensing (RS) technologies with modeling approaches has shown significant promise in enhancing water quality monitoring and prediction. This integrated approach significantly improves the accuracy and intelligence of monitoring and prediction, while extending spatiotemporal coverage, lowering monitoring costs, and enabling more comprehensive analysis through optimized monitoring design, multi-source data fusion, and the synergistic coupling of data-driven and process-based models (PBMs). Advanced models, particularly those combining PBMs with AI techniques, further enhance predictive capabilities for water quality. Despite these advances, the application of these integrated methods faces challenges in areas such as data management, monitoring elusive pollutants, model accuracy and efficiency, system integration, and real-world implementation. In response to these challenges, this paper reviews the current status of the integration of RS technology with multi-source data, machine learning (ML), and PBMs for water quality monitoring, modeling, and management, along with practical applications. It offers a thorough analysis of their advantages and challenges, identifies the current research gaps, and outlines future research directions. The goal is to enhance the role of integrated methods in improving water quality in aquatic ecosystems, support sustainable water resource management, and strengthen scientific decision-making in the face of climate change and growing anthropogenic pressures. Full article
(This article belongs to the Special Issue Integrating Remote Sensing, Machine Learning, and Process-Based Modelling for Monitoring Environmental and Agricultural Landscapes Under Climate Change)
►▼ Show Figures

Figure 1

21 pages, 12811 KB  
Article
Integrating Multi-Temporal Satellite Data and Machine Learning Approaches for Crop Rotation Pattern Mapping in Thailand
by Jaturong Som-ard, Mohammad D. Hossain, Surasak Keawsomsee, Savittri Ratanopad Suwanlee, Vorraveerukorn Veerachitt, Phattamon Heawchaiyaphum, Akkawat Puntura, Emma Izquierdo-Verdiguier, Markus Immitzer and Clement Atzberger
Remote Sens. 2025, 17(18), 3156; https://doi.org/10.3390/rs17183156 - 11 Sep 2025
Abstract
Accurate and timely information regarding the locations and types of crops cultivated is essential for sustainable agriculture and ensuring food security. However, accurately mapping season-specific crop types in tropical and subtropical regions is challenging due to smallholder farms, fragmented fields, predominant clouds, and [...] Read more.
Accurate and timely information regarding the locations and types of crops cultivated is essential for sustainable agriculture and ensuring food security. However, accurately mapping season-specific crop types in tropical and subtropical regions is challenging due to smallholder farms, fragmented fields, predominant clouds, and limited seasonal reference data. To address these limitations, this study employed optical and radar satellite data in conjunction with machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), and Gradient Tree Boosting (GBoost), utilizing a large number of reference datasets across crop seasons. To validate the results, extensive field visits were undertaken throughout the year. Our focus centered on two regions in Thailand recognized for their small fields and frequent overcast conditions. Utilizing over 8000 reference points, we mapped 12 crop types in Chaiyaphum province and 13 crop types in Suphan Buri province for three cropping seasons in 2023. The RF algorithm proved to be the most effective, demonstrating superior performance across all seasons in comparison to the other models, achieving an overall accuracy exceeding 85%, with classifications for sugarcane and rice exceeding 90%. The resultant maps identified sugarcane, rice, and cassava as the principal crops in the region. This research exemplifies a methodology for producing highly accurate seasonal crop maps, providing valuable tools for making informed decisions for crop sustainable management, thereby supporting sustainable agriculture practices. Our findings underscore the potential of Earth observation satellites and machine learning algorithms in addressing significant agricultural challenges and facilitating the development of more resilient strategies for food security. Full article
(This article belongs to the Special Issue Mapping Essential Elements of Agricultural Land Using Remote Sensing (2nd Edition))
►▼ Show Figures

Figure 1

23 pages, 42064 KB  
Article
A Spectral Mode Reconstruction Method for Floating Target Detection Under Strong Sea Clutter Conditions
by Ningbo Liu, Hankun Yang, Guoqing Wang, Hao Ding, Yunlong Dong and Wei Xue
Remote Sens. 2025, 17(18), 3155; https://doi.org/10.3390/rs17183155 - 11 Sep 2025
Abstract
In strong sea clutter conditions, floating target echo signals are easily overwhelmed. Conventional mode decomposition and reconstruction methods struggle to reliably identify and select the modes that actually contain the target components. This paper proposes a spectral mode reconstruction method based on an [...] Read more.
In strong sea clutter conditions, floating target echo signals are easily overwhelmed. Conventional mode decomposition and reconstruction methods struggle to reliably identify and select the modes that actually contain the target components. This paper proposes a spectral mode reconstruction method based on an adaptive selection criterion for target frequency intervals. Target modes are identified by combining the Doppler frequency shift of the target and the statistical spectral characteristics of sea clutter. An evaluation framework centered on relative feature gain and feature detection probability is then developed to validate the effectiveness of the proposed method. Experimental results on measured data demonstrate that the reconstructed signals significantly outperform the original signals on every metric evaluated, effectively suppressing sea clutter and enhancing target components. Full article
►▼ Show Figures

Figure 1

32 pages, 10828 KB  
Article
Comprehensive Assessment of GPM-IMERG and ERA5 Precipitation Products Across Ireland
by Safa Mohammed, Ahmed Nasr and Mohammed Mahmoud
Remote Sens. 2025, 17(18), 3154; https://doi.org/10.3390/rs17183154 - 11 Sep 2025
Abstract
Accurate precipitation estimates are essential for hydrological modeling and flood forecasting, particularly in regions like Ireland where rainfall patterns are highly variable and extreme events are becoming more frequent. This study evaluates the performance of two widely used gridded precipitation datasets, ERA5 reanalysis [...] Read more.
Accurate precipitation estimates are essential for hydrological modeling and flood forecasting, particularly in regions like Ireland where rainfall patterns are highly variable and extreme events are becoming more frequent. This study evaluates the performance of two widely used gridded precipitation datasets, ERA5 reanalysis and GPM IMERG (Early, Late, and Final run) precipitation products, against ground-based observations from 25 synoptic stations operated by Met Éireann, Ireland’s national meteorological service, over the period of 2014–2021. A grid-to-point matching method was applied to ensure spatial alignment between gridded and point-based data. The datasets were assessed using seven statistical and categorical metrics across hourly and daily timescales, meteorological seasons, and rainfall intensity classes. Results show that ERA5 consistently outperforms IMERG across most evaluation metrics, particularly for low-to-moderate intensity rainfall associated with winter frontal systems, and demonstrates strong temporal agreement and low bias in coastal regions. However, it tends to underestimate short-duration, high-intensity events and displays higher false alarm rates at the hourly scale. In contrast, IMERG-Final exhibits improved detection of extreme rainfall events, especially during summer, and performs more reliably at daily resolution. Its spatial performance is stronger than the Early and Late runs but still limited in Ireland’s western regions due to complex climatological settings. IMERG-Early and Late generally follow similar trends but tend to overestimate rainfall in mountainous regions. This study provides the first systematic intercomparison of ERA5 and IMERG datasets over Ireland and supports the recommendation of adopting a hybrid approach of combining ERA5’s seasonal consistency with IMERG-Final’s event responsiveness for enhanced rainfall monitoring and hydrological applications. Full article
(This article belongs to the Special Issue Precipitation Estimations Based on Satellite Observations)
►▼ Show Figures

Figure 1

18 pages, 5446 KB  
Article
High-Resolution Drone-Based Aeromagnetic Survey at the Tajogaite Volcano (La Palma, Canary Islands): Insights into Its Early Post-Eruptive Shallow Structure
by María C. Romero-Toribio, Fátima Martín-Hernández and Juanjo Ledo
Remote Sens. 2025, 17(18), 3153; https://doi.org/10.3390/rs17183153 - 11 Sep 2025
Abstract
The 2021 eruption of the Tajogaite volcano (La Palma, Canary Islands) provided a unique opportunity to investigate the early post-eruptive magnetic structure of a newly formed volcanic edifice. Understanding these structures is essential for improving hazard assessment and risk mitigation strategies. In this [...] Read more.
The 2021 eruption of the Tajogaite volcano (La Palma, Canary Islands) provided a unique opportunity to investigate the early post-eruptive magnetic structure of a newly formed volcanic edifice. Understanding these structures is essential for improving hazard assessment and risk mitigation strategies. In this study, we present the first high-resolution, drone-based aeromagnetic dataset over the Tajogaite volcano, aimed at clarifying its still-uncertain geodynamic framework at shallow depths. We describe the data acquisition and processing workflows for surveying volcanic terrains, providing insights into the challenges encountered and the methodologies applied. The magnetic dataset was analyzed and used to construct a 3D magnetic susceptibility model of the volcanic edifice and its surroundings. Our results revealed very low magnetic susceptibility values at very shallow depths (~50 m below the surface) over the main volcanic edifice, suggesting the presence of a likely vertical, dyke-like structure feeding the eruption. These findings indicate that these materials remain above their Curie temperature around two years after the eruption. Moreover, the magnetic anomalies display patterns that correlate with the previously inferred two-fault systems, which likely played a critical role in channelling magma toward the eruptive vents. An elongated zone of slightly low magnetic susceptibility was identified following the NE-SW Mazo fault orientation, extending toward the eruptive fissure. This feature was associated with a single, fault-controlled magma pathway that remained at high temperatures at the time of the survey, in agreement with studies in other volcanic environments. This study highlights the value of aeromagnetic surveys, particularly those conducted with drones, as effective tools for advancing our understanding of young and dynamic volcanic systems, especially regarding their shallow structures. Full article
(This article belongs to the Special Issue Multiplatform Remote Sensing Techniques for Active Tectonics, Seismotectonics, and Volcanic Hazard Assessment)
►▼ Show Figures

Figure 1

32 pages, 1358 KB  
Review
A Review of City-Scale Methane Flux Inversion Based on Top-Down Methods
by Xiaofan Li, Ying Zhang, Gerrit de Leeuw, Xingyu Yao, Zhuo He, Hailing Wu and Zhuolin Yang
Remote Sens. 2025, 17(18), 3152; https://doi.org/10.3390/rs17183152 - 11 Sep 2025
Abstract
As urbanization intensifies, the quantification of methane (CH4) emissions at city scales faces unprecedented challenges due to spatial heterogeneities from industrial and transportation activities and land use changes. This paper provides a review of the current state of top-down atmospheric CH [...] Read more.
As urbanization intensifies, the quantification of methane (CH4) emissions at city scales faces unprecedented challenges due to spatial heterogeneities from industrial and transportation activities and land use changes. This paper provides a review of the current state of top-down atmospheric CH4 emission inversion at the city scale, with a focus on CH4 emission inventories, CH4 observations, atmospheric transport models, and data assimilation methods. The Bayesian method excels in capturing spatial variability and managing posterior uncertainty at the kilometer-scale resolution, while the hybrid method of variational and ensemble Kalman approaches has the potential to balance computational efficiency in complex urban environments. This review highlights the significant discrepancy between top-down inversion results and bottom-up inventory estimates at the city scale, with inversion uncertainties ranging from 11% to 28%. This indicates the need for further efforts in CH4 inversion at the city level. A framework is proposed to fundamentally shape city-scale CH4 emission inversion by four synergistic advancements: developing high-resolution prior emission inventories at the city scale, acquiring observational data through coordinated satellite–ground systems, enhancing computational efficiency using artificial intelligence techniques, and applying isotopic analysis to distinguish CH4 sources. Full article
(This article belongs to the Special Issue Advances in Remote Sensing Observation of Aerosol Properties and Assessment of Their Effects)
►▼ Show Figures

Figure 1

22 pages, 35539 KB  
Article
Interval Determination Strategy for Bayesian Inversion of Seismic Source Parameters Under Uncertain Interval Conditions
by Leyang Wang, Can Xi, Guangyu Xu, Zhanglin Sun and Fei Wu
Remote Sens. 2025, 17(18), 3151; https://doi.org/10.3390/rs17183151 - 11 Sep 2025
Abstract
Using a Bayesian framework to invert earthquake source parameters from multi-source geodetic data has become an important research direction. To address the issue of Markov Chain Monte Carlo (MCMC) algorithms getting stuck in local optima during nonlinear inversion of fault geometric parameters, which [...] Read more.
Using a Bayesian framework to invert earthquake source parameters from multi-source geodetic data has become an important research direction. To address the issue of Markov Chain Monte Carlo (MCMC) algorithms getting stuck in local optima during nonlinear inversion of fault geometric parameters, which is often caused by improperly set parameter bounds or large deviations in the initial values, this study proposes two strategies: ‘CFI (Converge First, Then Interval)’ and ‘IVI (Interval Value Iteration)’. Tests with 12 different experimental setups show that both strategies can prevent the chain from getting trapped in local optima. Among them, the ‘IVI’ strategy, when used with MCMC algorithms where the step size follows a normal distribution, can also significantly reduce the root-mean-square error. To verify its applicability, the ‘IVI’ strategy was applied to the Bayesian inversion of the 2022 Menyuan Mw6.6 earthquake. The results show that the inverted values for fault depth, strike, dip, and rake angles are closer to the GCMT results, with ascending and descending track fitting residuals of 2.71 cm and 2.64 cm, respectively. The conclusion of this paper is to recommend the ‘IVI’ strategy when the range of source parameters is unclear. If the approximate range of parameters is known, the ‘CFI’ strategy can be applied. The original interval constraint method is recommended when the parameter bounds are fully determinable and a reliable initial model of seismic source parameters is obtainable. Full article
(This article belongs to the Special Issue Remote Sensing in Earth Surface Changes and Deformations Caused by Earthquake and Landslide (Third Edition))
►▼ Show Figures

Figure 1

23 pages, 7104 KB  
Article
Seasonal Effects of Urban Morphology on the Thermal Environment Based on Automated Machine Learning: A Case Study of Beijing
by Ni Wang, Lidu Shen, Wenli Fei, Yage Liu, Hujia Zhao, Luyao Liu, Anzhi Wang and Bao-Jie He
Remote Sens. 2025, 17(18), 3150; https://doi.org/10.3390/rs17183150 - 11 Sep 2025
Abstract
Understanding the seasonal nonlinear relationship between urban heat island (UHI) and multidimensional urban morphological patterns is crucial for regulating the urban thermal environment. To address this, this study quantified the contributions and sensitivities of urban morphology to land surface temperature (LST) variations and [...] Read more.
Understanding the seasonal nonlinear relationship between urban heat island (UHI) and multidimensional urban morphological patterns is crucial for regulating the urban thermal environment. To address this, this study quantified the contributions and sensitivities of urban morphology to land surface temperature (LST) variations and revealed their influencing pathways across four seasons in Beijing, using automated machine learning, SHapley Additive exPlanations interpretation, partial dependence analysis, and structural equation modeling. The results showed significant seasonal variations at the grid scale of 200 m. It was revealed that Normalized Difference Vegetation Index (NDVI) emerged as the most significant indicator affecting LST, followed by building height (BH) and building coverage ratio (BCR), while sky view factor and frontal area index had the least impact. BH was more influential than NDVI, affecting LST during winter. Additionally, sensitivity analysis revealed that impervious surface area, BCR, and mean building volume had positive relationships with LST. In contrast, NDVI and BH negatively affected LST with a noticeable cooling effect, particularly in summer. Furthermore, the total effects of all indicators on LST were negative, with the greatest in spring and the least in winter. Three-dimensional indicators generally exhibited more pronounced direct and total effects than two-dimensional indicators, except in winter. These findings can offer valuable insights for regulating seasonal surface UHI to maximize thermal environmental benefits. Full article
(This article belongs to the Special Issue Remote Sensing Applications in Urban Environment and Climate)
►▼ Show Figures

Figure 1

18 pages, 3246 KB  
Article
Cascaded Ambiguity Resolution for Pseudolite System-Augmented GNSS PPP
by Caoming Fan, Zheng Yao, Jinling Wang and Mingquan Lu
Remote Sens. 2025, 17(18), 3149; https://doi.org/10.3390/rs17183149 - 11 Sep 2025
Abstract
Global navigation satellite System (GNSS) precise point positioning (PPP) enables high-precision global positioning using a single receiver, yet its widespread application is hindered by long convergence times. In contrast, pseudolite system (PLS) transmitters are located relatively close to receivers, and the movement of [...] Read more.
Global navigation satellite System (GNSS) precise point positioning (PPP) enables high-precision global positioning using a single receiver, yet its widespread application is hindered by long convergence times. In contrast, pseudolite system (PLS) transmitters are located relatively close to receivers, and the movement of receivers induces rapid spatial geometry changes, which greatly facilitate fast parameter convergence. Therefore, leveraging the fast-converging PLS to augment GNSS PPP presents a promising solution. This study proposes a tightly coupled PLS and GNSS observation-level integration model. A key factor influencing the augmentation effectiveness is the strategy of ambiguity resolution. In this work, we design a novel strategy of ambiguity resolution, in which the fast convergence property of PLS is taken into account, and the PLS ambiguities are picked out to be fixed independently. This strategy can resolve the PLS ambiguities, GNSS wide-lane (WL) ambiguities, and GNSS L1 ambiguities cascadingly. Further, the fixed ambiguities can be treated as constraints in the filtering process. The experimental results demonstrate that the proposed strategy substantially improves the ambiguity fixing rates, especially in short-duration augmentation. Full article
(This article belongs to the Special Issue Advancing Position, Navigation, and Timing (PNT) Service Using Satellite Navigation Technology)
►▼ Show Figures

Figure 1

19 pages, 2497 KB  
Article
Oil Spill Identification with Marine Radar Using Feature Augmentation and Improved Firefly Optimization Algorithm
by Jin Xu, Boxi Yao, Haihui Dong, Zekun Guo, Bo Xu, Yuanyuan Huang, Bo Li, Sihan Qian and Bingxin Liu
Remote Sens. 2025, 17(18), 3148; https://doi.org/10.3390/rs17183148 - 10 Sep 2025
Abstract
Oil spill accidents pose a grave threat to marine ecosystems, human economy, and public health. Consequently, expeditious and efficacious oil spill detection technology is imperative for the pollution mitigation and the health preservation in the marine environment. This study proposed a marine radar [...] Read more.
Oil spill accidents pose a grave threat to marine ecosystems, human economy, and public health. Consequently, expeditious and efficacious oil spill detection technology is imperative for the pollution mitigation and the health preservation in the marine environment. This study proposed a marine radar oil spill detection method based on Local Binary Patterns (LBP), Histogram of Oriented Gradient (HOG), and an improved Firefly Optimization Algorithm (IFA). In the stage of image pre-processing, the oil film features were significantly enhanced through three steps. The LBP features were extracted from the preprocessed image. Then, the mean filtering was used to smooth out the LBP features. Subsequently, the HOG statistical features were extracted from the filtered LBP feature map. After the feature enhancement, the oil spill regions were accurately extracted by using K-Means clustering algorithm. Next, an IFA model was used to classify oil films. Compared with traditional Firefly Optimization Algorithm (FA) algorithm, the IFA method is suitable for oil film segmentation tasks in marine radar data. The proposed method can achieve accuracy segmentation and provide a new technical path for marine oil spill monitoring. Full article
19 pages, 4949 KB  
Article
Effects of Atmospheric Tide Loading on GPS Coordinate Time Series
by Yanlin Li, Na Wei, Kaiwen Xiao and Qiyuan Zhang
Remote Sens. 2025, 17(18), 3147; https://doi.org/10.3390/rs17183147 - 10 Sep 2025
Abstract
Loading of the Earth’s crust due to variations in global atmospheric pressure can displace the position of geodetic stations. However, the station displacements induced by the diurnal and semidiurnal atmospheric tides (S1-S2) are often neglected during Global Positioning System [...] Read more.
Loading of the Earth’s crust due to variations in global atmospheric pressure can displace the position of geodetic stations. However, the station displacements induced by the diurnal and semidiurnal atmospheric tides (S1-S2) are often neglected during Global Positioning System (GPS) processing. We first studied the magnitudes of S1-S2 deformation in the Earth’s center of mass (CM) frame and compared the global S1-S2 grid models provided by the Global Geophysical Fluid Center (GGFC) and the Vienna Mapping Function (VMF) data server. The magnitude of S1-S2 tidal displacement can reach 1.5 mm in the Up component at low latitudes, approximately three times that of the horizontal components. The most significant difference between the GGFC and VMF grid models lies in the phase of S2 in the horizontal components, with phase discrepancies of up to 180° observed at some stations. To investigate the effects of S1-S2 corrections on GPS coordinates, we then processed GPS data from 108 International GNSS Service (IGS) stations using the precise point positioning (PPP) method in two processing strategies, with and without the S1-S2 correction. We observed that the effects of S1-S2 on daily GPS coordinates are generally at the sub-millimeter level, with maximum root mean square (RMS) coordinate differences of 0.18, 0.08, and 0.51 mm in the East, North, and Up components, respectively. We confirmed that part of the GPS draconitic periodic signals was induced by unmodeled S1-S2 loading deformation, with the amplitudes of the first two draconitic harmonics induced by atmospheric tide loading reaching 0.2 mm in the Up component. Moreover, we recommend using the GGFC grid model for S1-S2 corrections in GPS data processing, as it reduced the weighted RMS of coordinate residuals for 45.37%, 46.30%, and 53.70% of stations in the East, North, and Up components, respectively, compared with 39.81%, 44.44%, and 50.00% for the VMF grid model. The effects of S1-S2 on linear velocities are very limited and remain within the Global Geodetic Observing System (GGOS) requirements for the future terrestrial reference frame at millimeter level. Full article
►▼ Show Figures

Figure 1

25 pages, 7225 KB  
Article
DeepSwinLite: A Swin Transformer-Based Light Deep Learning Model for Building Extraction Using VHR Aerial Imagery
by Elif Ozlem Yilmaz and Taskin Kavzoglu
Remote Sens. 2025, 17(18), 3146; https://doi.org/10.3390/rs17183146 - 10 Sep 2025
Abstract
Accurate extraction of building features from remotely sensed data is essential for supporting research and applications in urban planning, land management, transportation infrastructure development, and disaster monitoring. Despite the prominence of deep learning as the state-of-the-art (SOTA) methodology for building extraction, substantial challenges [...] Read more.
Accurate extraction of building features from remotely sensed data is essential for supporting research and applications in urban planning, land management, transportation infrastructure development, and disaster monitoring. Despite the prominence of deep learning as the state-of-the-art (SOTA) methodology for building extraction, substantial challenges remain, largely stemming from the diversity of building structures and the complexity of background features. To mitigate these issues, this study introduces DeepSwinLite, a lightweight architecture based on the Swin Transformer, designed to extract building footprints from very high-resolution (VHR) imagery. The model integrates a novel local–global attention module to enhance the interpretation of objects across varying spatial resolutions and facilitate effective information exchange between different feature abstraction levels. It comprises three modules: multi-scale feature aggregation (MSFA), improving recognition across varying object sizes; multi-level feature pyramid (MLFP), fusing detailed and semantic features; and AuxHead, providing auxiliary supervision to stabilize and enhance learning. Experimental evaluations on the Massachusetts and WHU Building Datasets reveal the superior performance of DeepSwinLite architecture when compared to existing SOTA models. On the Massachusetts dataset, the model attained an OA of 92.54% and an IoU of 77.94%, while on the WHU dataset, it achieved an OA of 98.32% and an IoU of 92.02%. Following the correction of errors identified in the Massachusetts ground truth and iterative enhancement, the model’s performance further improved, reaching 94.63% OA and 79.86% IoU. A key advantage of the DeepSwinLite model is its computational efficiency, requiring fewer floating-point operations (FLOPs) and parameters compared to other SOTA models. This efficiency makes the model particularly suitable for deployment in mobile and resource-constrained systems. Full article
(This article belongs to the Special Issue Advances in Deep Learning Approaches: UAV Data Analysis)
21 pages, 29411 KB  
Article
Deep Learning-Based Contrail Segmentation in Thermal Infrared Satellite Cloud Images via Frequency-Domain Enhancement
by Shenhao Shi, Juncheng Wu, Kaixuan Yao and Qingxiang Meng
Remote Sens. 2025, 17(18), 3145; https://doi.org/10.3390/rs17183145 - 10 Sep 2025
Abstract
Aviation contrails significantly impact climate via radiative forcing, but their segmentation in thermal infrared satellite images is challenged by thin-layer structures, blurry edges, and cirrus cloud interference. We propose MFcontrail, a deep learning model integrating multi-axis attention and frequency-domain enhancement for precise contrail [...] Read more.
Aviation contrails significantly impact climate via radiative forcing, but their segmentation in thermal infrared satellite images is challenged by thin-layer structures, blurry edges, and cirrus cloud interference. We propose MFcontrail, a deep learning model integrating multi-axis attention and frequency-domain enhancement for precise contrail segmentation. It uses a MaxViT encoder to capture long-range spatial features, a FreqFusion decoder to preserve high-frequency edge details, and an edge-aware loss to refine boundary accuracy. Evaluations on OpenContrails and Landsat-8 datasets show that MFcontrail outperforms state-of-the-art methods: compared with DeepLabV3+, it achieves a 5.03% higher F1-score and 5.91% higher IoU on OpenContrails, with 3.43% F1-score and 4.07% IoU gains on Landsat-8. Ablation studies confirm the effectiveness of frequency-domain enhancement (contributing 69.4% of IoU improvement) and other key components. This work provides a high-precision tool for aviation climate research, highlighting frequency-domain strategies’ value in satellite cloud image analysis. Full article
(This article belongs to the Special Issue Applications and Analysis of Satellite Cloud Imagery Using Deep Learning Techniques)
►▼ Show Figures

Figure 1

24 pages, 7007 KB  
Article
M4MLF-YOLO: A Lightweight Semantic Segmentation Framework for Spacecraft Component Recognition
by Wenxin Yi, Zhang Zhang and Liang Chang
Remote Sens. 2025, 17(18), 3144; https://doi.org/10.3390/rs17183144 - 10 Sep 2025
Abstract
With the continuous advancement of on-orbit services and space intelligence sensing technologies, the efficient and accurate identification of spacecraft components has become increasingly critical. However, complex lighting conditions, background interference, and limited onboard computing resources present significant challenges to existing segmentation algorithms. To [...] Read more.
With the continuous advancement of on-orbit services and space intelligence sensing technologies, the efficient and accurate identification of spacecraft components has become increasingly critical. However, complex lighting conditions, background interference, and limited onboard computing resources present significant challenges to existing segmentation algorithms. To address these challenges, this paper proposes a lightweight spacecraft component segmentation framework for on-orbit applications, termed M4MLF-YOLO. Based on the YOLOv5 architecture, we propose a refined lightweight design strategy that aims to balance segmentation accuracy and resource consumption in satellite-based scenarios. MobileNetV4 is adopted as the backbone network to minimize computational overhead. Additionally, a Multi-Scale Fourier Adaptive Calibration Module (MFAC) is designed to enhance multi-scale feature modeling and boundary discrimination capabilities in the frequency domain. We also introduce a Linear Deformable Convolution (LDConv) to explicitly control the spatial sampling span and distribution of the convolution kernel, thereby linearly adjusting the receptive field coverage range to improve feature extraction capabilities while effectively reducing computational costs. Furthermore, the efficient C3-Faster module is integrated to enhance channel interaction and feature fusion efficiency. A high-quality spacecraft image dataset, comprising both real and synthetic images, was constructed, covering various backgrounds and component types, including solar panels, antennas, payload instruments, thrusters, and optical payloads. Environment-aware preprocessing and enhancement strategies were applied to improve model robustness. Experimental results demonstrate that M4MLF-YOLO achieves excellent segmentation performance while maintaining low model complexity, with precision reaching 95.1% and recall reaching 88.3%, representing improvements of 1.9% and 3.9% over YOLOv5s, respectively. The mAP@0.5 also reached 93.4%. In terms of lightweight design, the model parameter count and computational complexity were reduced by 36.5% and 24.6%, respectively. These results validate that the proposed method significantly enhances deployment efficiency while preserving segmentation accuracy, showcasing promising potential for satellite-based visual perception applications. Full article
►▼ Show Figures

Figure 1

20 pages, 2089 KB  
Article
Estimating Methane Emissions by Integrating Satellite Regional Emissions Mapping and Point-Source Observations: Case Study in the Permian Basin
by Mozhou Gao and Zhenyu Xing
Remote Sens. 2025, 17(18), 3143; https://doi.org/10.3390/rs17183143 - 10 Sep 2025
Abstract
Methane (CH4) is known as the most potent greenhouse gas in the short term. With the growing urgency of mitigating climate change and monitoring CH4 emissions, many emerging satellite systems have been launched in the past decade to observe CH [...] Read more.
Methane (CH4) is known as the most potent greenhouse gas in the short term. With the growing urgency of mitigating climate change and monitoring CH4 emissions, many emerging satellite systems have been launched in the past decade to observe CH4 and other greenhouse gases from space. These satellites are either capable of pinpointing and quantifying super emitters or deriving regional emissions with a more frequent revisit time. This study aims to reconcile emissions estimated from point source satellites and those from regional mapping satellites, and to investigate the potential of integrating point-based quantification and regional-based quantification techniques. To do that, we quantified CH4 emissions from the Permian Basin separately by applying the divergence method to the TROPOMI Level-2 data product, as well as an event-based approach using CH4 plumes quantified by Carbon Mapper systems. The resulting annual CH4 emissions estimates from the Permian Basin in 2024 are 1.83 ± 0.96 Tg and 1.26 [0.78, 2.02] Tg for divergence and event-based methods, respectively. The divergence-based emissions estimate shows a more comprehensive spatial distribution of emissions across the Permian Basin, whereas the event-based approach highlights the grid cells with the short-duration super-emitters. The emissions from grids with detectable emissions under both methods show strong agreement (R2 ≈ 0.642). After substituting the overlap cells’ values from divergence-based emissions estimation with those from event-based estimation, the combined emissions estimate is 2.68 [1.88, 3.54] Tg, which is reconciled with Permian Basin emissions estimates from previous studies. We found that CH4 emissions from the Permian Basin gradually reduced over the past five years. Furthermore, this case study indicates the potential for integrating estimations from both methods to generate a more comprehensive regional emissions estimate. Full article
(This article belongs to the Special Issue Advances in Atmospheric Greenhouse Gases Observation and Remote Sensing Applications)
18 pages, 1401 KB  
Article
Geolocation of Distributed Acoustic Sampling Channels Using X-Band Radar and Optical Remote Sensing
by Robert Holman, Hannah Glover, Meagan Wengrove, Marcela Ifju, David Honegger and Merrick Haller
Remote Sens. 2025, 17(18), 3142; https://doi.org/10.3390/rs17183142 - 10 Sep 2025
Abstract
Distributed Acoustic Sensing (DAS) is a new oceanographic measurement technology that exploits the physical sensitivities of fiber-optic communication cables to changes in pressure, allowing time series measurements of pressure at meter-scale spacing for ranges up to 150 km. The along-cable measurement locations, called [...] Read more.
Distributed Acoustic Sensing (DAS) is a new oceanographic measurement technology that exploits the physical sensitivities of fiber-optic communication cables to changes in pressure, allowing time series measurements of pressure at meter-scale spacing for ranges up to 150 km. The along-cable measurement locations, called channels, are evenly distributed, but the specific locations of each are initially unknown. In terrestrial applications, channel locations are often found by the “tap test” where acoustic transients are created at surveyed locations along the cable. For submarine installations, tap tests are inconvenient or logistically impossible. Here we describe a new method for submarine channel geolocation by comparing DAS signals to ambient ocean wave time series using a variety of cross-spectral methods. Ground truth data were derived from two remote sensing sources: marine radar (X-band) and shore-based cameras. The methods were developed and tested at two coastal locations and showed an ability to geolocate DAS channels to within 10 m at ranges of up to 3 km (radar) or within 1.0 m at ranges up to 600 m (optical). Full article
(This article belongs to the Special Issue Application of Remote Sensing in Coastline Monitoring)
►▼ Show Figures

Figure 1

19 pages, 7290 KB  
Article
Assessing Pacific Madrone Blight with UAS Remote Sensing Under Different Skylight Conditions
by Michael C. Winfield, Michael G. Wing, Julia H. Wood, Savannah Graham, Anika M. Anderson, Dustin C. Hawks and Adam H. Miller
Remote Sens. 2025, 17(18), 3141; https://doi.org/10.3390/rs17183141 - 10 Sep 2025
Abstract
We investigated the relationship between foliar blight, tree structure, and spectral signatures in a Pacific Madrone (Arbutus menziesii) orchard in Oregon using unoccupied aerial system (UAS) multispectral imagery and ground surveying. Aerial data were collected under both cloudy and sunny conditions [...] Read more.
We investigated the relationship between foliar blight, tree structure, and spectral signatures in a Pacific Madrone (Arbutus menziesii) orchard in Oregon using unoccupied aerial system (UAS) multispectral imagery and ground surveying. Aerial data were collected under both cloudy and sunny conditions using a six-band sensor (red, green, blue, near-infrared, red edge, and longwave infrared), and ground surveying recorded foliar blight and tree height for 29 trees. We observed band- and index-dependent spectral variation within crowns and between lighting conditions. The Normalized Difference Vegetation Index (NDVI), Modified Simple Ratio Index Red Edge (MSRE), and Red Edge Chlorophyll Index (RECI) showed higher consistency across lighting changes (adjusted R2 ≈ 0.95), while the Green Chlorophyll Index (GCI), Modified Simple Ratio Index (MSR), and Green Normalized Difference Vegetation Index (GNDVI) showed slightly lower consistency (adjusted R2 ≈ 0.92) but greater sensitivity to blight under cloudy skies. Diffuse skylight increased blue and near-infrared reflectance, reduced red, and enhanced blight detection using GCI, MSR, and GNDVI. Tree height was inversely related to blight presence (p < 0.005), and spectral variation within crowns was significant (p < 0.01), suggesting a role for canopy architecture. The support vector machine classification of tree crowns achieved 92.5% accuracy (kappa = 0.87). Full article
(This article belongs to the Special Issue Plant Disease Detection and Recognition Using Remotely Sensed Data)
►▼ Show Figures

Figure 1

22 pages, 18040 KB  
Article
Assessing the Impacts of Marine Ranching Construction on Water Quality and Fishery Resources in Adjacent Coastal Waters
by Jianqu Chen, Xue Feng, Chunya Guo, Yuxiang Chen, Fei Tong, Lei Zhang, Zhangbin Liu, Jian Zhang, Huanrong Yuan and Pimao Chen
Remote Sens. 2025, 17(18), 3140; https://doi.org/10.3390/rs17183140 - 10 Sep 2025
Abstract
This paper aims to explore the impact of marine ranching construction on water quality and fishery resources in the surrounding marine areas. Utilizing in situ water quality and fishery resource data collected before and after the establishment of marine ranching, the study analyzes [...] Read more.
This paper aims to explore the impact of marine ranching construction on water quality and fishery resources in the surrounding marine areas. Utilizing in situ water quality and fishery resource data collected before and after the establishment of marine ranching, the study analyzes changes in water quality parameters from both temporal and spatial perspectives. A quantitative evaluation of the water quality data is conducted using several models to assess the accuracy of different evaluation methods. By integrating the SHAP algorithm with physical significance, the study examines the differences between optically sensitive and non-optically sensitive water quality parameters during the machine learning evaluation process. Finally, based on the inverted water quality data, the potential impact range and resource output following the deployment of artificial reefs are investigated. The results indicate that in the marine area near Wailingding Island, Zhuhai, the deployment of artificial reefs with a volume of 38,048 cubic meters led to an increase in fishery resources by 318 kg/km2 in spring and 660 kg/km2 in autumn. Additionally, deployment had varying degrees of impact on the concentrations of chlorophyll a (Chla), dissolved oxygen (DO), chemical oxygen demand (COD), and phosphate (PO4-P) in the surface water within an approximate range of 10 km. This study provides a valuable reference for calculating input–output ratios, as well as for the management and evaluation of marine ranching. Full article
►▼ Show Figures

Figure 1

27 pages, 6663 KB  
Article
Crater-MASN: A Multi-Scale Adaptive Semantic Network for Efficient Crater Detection
by Ruiqi Yu and Zhijing Xu
Remote Sens. 2025, 17(18), 3139; https://doi.org/10.3390/rs17183139 - 10 Sep 2025
Abstract
Automatic crater detection is crucial for planetary science, but still faces several long-standing challenges. The morphological characteristics of craters exhibit significant variability; combined with complex lighting conditions, this makes feature extraction difficult, especially for small or severely degraded features. These difficulties are further [...] Read more.
Automatic crater detection is crucial for planetary science, but still faces several long-standing challenges. The morphological characteristics of craters exhibit significant variability; combined with complex lighting conditions, this makes feature extraction difficult, especially for small or severely degraded features. These difficulties are further compounded by incomplete ground truth annotations, which limit the effectiveness of supervised learning. In addition, achieving a balance between detection accuracy and computational efficiency remains a critical bottleneck, especially in large-scale planetary surveys. Traditional postprocessing algorithms also often struggle to resolve complex spatial hierarchies in densely cratered regions, leading to substantial omissions and misclassifications. To address these interrelated challenges, we propose Crater-MASN, a lightweight adaptive detection framework specifically designed for lunar crater analysis. The architecture employs a compact GhostNet backbone to balance efficiency and accuracy, while enhancing multi-scale feature representation through a novel bidirectional integration and fusion module (BIFM) to better capture the morphological diversity of craters. To mitigate the impact of incomplete annotations, we introduce an adaptive semantic contrastive sampling (ASCS) mechanism which dynamically mines unlabeled craters through semantic clustering and contrastive learning. Additionally, we design the hierarchical soft NMS (H-SoftNMS) algorithm, a geometry-aware postprocessing method that selectively suppresses non-hierarchical overlaps to preserve nested craters, thereby achieving more accurate crater retention in dense regions. Experiments on a dedicated lunar crater dataset demonstrate the effectiveness of Crater-MASN. The model achieves an mAP50 of 91.0% with only 2.1 million parameters. When combined with H-SoftNMS, it achieves a recall rate of 95.0% and new discovery rate PNDR of 89.6%. These results highlight the potential of Crater-MASN as a scalable and reliable tool for high-precision crater cataloging and planetary surface analysis. Full article
(This article belongs to the Section Satellite Missions for Earth and Planetary Exploration)
►▼ Show Figures

Figure 1

21 pages, 4538 KB  
Article
Estimation of Downlink Signal Transmitting Antenna PCO and Equipment Delays for LEO Navigation Constellations with Limited Regional Stations
by Ziqiang Li, Wanke Liu and Jie Hu
Remote Sens. 2025, 17(18), 3138; https://doi.org/10.3390/rs17183138 - 10 Sep 2025
Abstract
In LEO constellation–augmented navigation, the transmitting antenna phase center offset (PCO) and the equipment delay associated with the downlink signals of LEO satellites constitute major error sources that must be precisely characterized. Previous studies primarily focused on single or small-scale satellite scenarios, lacking [...] Read more.
In LEO constellation–augmented navigation, the transmitting antenna phase center offset (PCO) and the equipment delay associated with the downlink signals of LEO satellites constitute major error sources that must be precisely characterized. Previous studies primarily focused on single or small-scale satellite scenarios, lacking comprehensive evaluations regarding the influence of constellation scale, orbital altitude, ground station configuration, and various error sources. To address this gap, we propose a joint estimation method utilizing observations from a limited number of regional ground stations in China that simultaneously track GNSS and LEO satellites. The method is specifically designed to accommodate practical constraints on ground station distribution within China. Initially, a batch least-squares estimation strategy is employed to simultaneously determine the ionosphere-free PCO and initial equipment delays for all LEO satellites in a constellation-wide solution. Subsequently, the estimated PCO parameters are fixed, and the equipment delays are further refined using a precise point positioning (PPP) approach. To systematically evaluate the method’s performance under realistic conditions, we analyze the impact of orbital altitude, constellation size, ground station number, data processing duration, and orbit/clock biases through comprehensive simulations. The results indicate: (1) the Z-direction component of the PCO (pointing toward the Earth’s center) and equipment delay is more sensitive to orbit and clock errors; (2) Increasing the number of LEO satellites generally improves the estimation accuracy of equipment delays, but the marginal gain diminishes as the constellation size expands; (3) sub-centimeter PCO accuracy and equipment delay accuracies better than 3 cm can still be achieved using only 3–4 regionally distributed ground stations over an observation period of 5–7 days. Full article
(This article belongs to the Special Issue Advanced Multi-GNSS Positioning and Its Applications in Geoscience)
►▼ Show Figures

Figure 1

32 pages, 8264 KB  
Article
SATRNet: Self-Attention-Aided Deep Unfolding Tensor Representation Network for Robust Hyperspectral Anomaly Detection
by Jing Yang, Jianbin Zhao, Lu Chen, Haorui Ning and Ying Li
Remote Sens. 2025, 17(18), 3137; https://doi.org/10.3390/rs17183137 - 10 Sep 2025
Abstract
Hyperspectral anomaly detection (HAD) aims to separate subtle anomalies of a given hyperspectral image (HSI) from its background, which is a hot topic as well as a challenging inverse problem. Despite the significant success of the deep learning-based HAD methods, they are hard [...] Read more.
Hyperspectral anomaly detection (HAD) aims to separate subtle anomalies of a given hyperspectral image (HSI) from its background, which is a hot topic as well as a challenging inverse problem. Despite the significant success of the deep learning-based HAD methods, they are hard to interpret due to their black-box nature. Meanwhile, deep learning methods suffer from the identity mapping (IM) problem, referring to the network excessively focusing on the precise reconstruction of the background while neglecting the appropriate representation of anomalies. To this end, this paper proposes a self-attention-aided deep unfolding tensor representation network (SATRNet) for interpretable HAD by solving the tensor representation (TR)-based optimization model within the framework of deep networks. In particular, a Self-Attention Learning Module (SALM) was first designed to extract discriminative features of the input HSI. The HAD problem was then formulated as a tensor representation problem by exploring both the low-rankness of the background and the sparsity of the anomaly. A Weight Learning Module (WLM) exploring local details was also generated for precise background reconstruction. Finally, a deep network was built to solve the TR-based problem through unfolding and parameterizing the iterative optimization algorithm. The proposed SATRNet prevents the network from learning meaningless mappings, making the network interpretable to some extent while essentially solving the IM problem. The effectiveness of the proposed SATRNet is validated on 11 benchmark HSI datasets. Notably, the performance of SATRNet against adversarial attacks is also investigated in the experimentation, which is the first work exploring adversarial robustness in HAD to the best of our knowledge. Full article
(This article belongs to the Special Issue Recent Advances in Hyperspectral Remote Sensing: Theories, Technologies and Applications)
►▼ Show Figures

Figure 1

22 pages, 15219 KB  
Article
Integrating UAS Remote Sensing and Edge Detection for Accurate Coal Stockpile Volume Estimation
by Sandeep Dhakal, Ashish Manandhar, Ajay Shah and Sami Khanal
Remote Sens. 2025, 17(18), 3136; https://doi.org/10.3390/rs17183136 - 10 Sep 2025
Abstract
Accurate stockpile volume estimation is essential for industries that manage bulk materials across various stages of production. Conventional ground-based methods such as walking wheels, total stations, Global Navigation Satellite Systems (GNSSs), and Terrestrial Laser Scanners (TLSs) have been widely used, but often involve [...] Read more.
Accurate stockpile volume estimation is essential for industries that manage bulk materials across various stages of production. Conventional ground-based methods such as walking wheels, total stations, Global Navigation Satellite Systems (GNSSs), and Terrestrial Laser Scanners (TLSs) have been widely used, but often involve significant safety risks, particularly when accessing hard-to-reach or hazardous areas. Unmanned Aerial Systems (UASs) provide a safer and more efficient alternative for surveying irregularly shaped stockpiles. This study evaluates UAS-based methods for estimating the volume of coal stockpiles at a storage facility near Cadiz, Ohio. Two sensor platforms were deployed: a Freefly Alta X quadcopter equipped with a Real-Time Kinematic (RTK) Light Detection and Ranging (LiDAR, active sensor) and a WingtraOne UAS with Post-Processed Kinematic (PPK) multispectral imaging (optical, passive sensor). Three approaches were compared: (1) LiDAR; (2) Structure-from-Motion (SfM) photogrammetry with a Digital Surface Model (DSM) and Digital Terrain Model (DTM) (SfM–DTM); and (3) an SfM-derived DSM combined with a kriging-interpolated DTM (SfM–intDTM). An automated boundary detection workflow was developed, integrating slope thresholding, Near-Infrared (NIR) spectral filtering, and Canny edge detection. Volume estimates from SfM–DTM and SfM–intDTM closely matched LiDAR-based reference estimates, with Root Mean Square Error (RMSE) values of 147.51 m3 and 146.18 m3, respectively. The SfM–intDTM approach achieved a Mean Absolute Percentage Error (MAPE) of ~2%, indicating strong agreement with LiDAR and improved accuracy compared to prior studies. A sensitivity analysis further highlighted the role of spatial resolution in volume estimation. While RMSE values remained consistent (141–162 m3) and the MAPE below 2.5% for resolutions between 0.06 m and 5 m, accuracy declined at coarser resolutions, with the MAPE rising to 11.76% at 10 m. This emphasizes the need to balance the resolution with the study objectives, geographic extent, and computational costs when selecting elevation data for volume estimation. Overall, UAS-based SfM photogrammetry combined with interpolated DTMs and automated boundary extraction offers a scalable, cost-effective, and accurate approach for stockpile volume estimation. The methodology is well-suited for both the high-precision monitoring of individual stockpiles and broader regional-scale assessments and can be readily adapted to other domains such as quarrying, agricultural storage, and forestry operations. Full article
(This article belongs to the Special Issue Photogrammetry and Remote Sensing in Environmental and Engineering Applications (Second Edition))
►▼ Show Figures

Figure 1

15 pages, 2044 KB  
Article
Assessing Spectral Reflectance in African Smallholder Cereal Farms Using Sentinel-2 Imagery
by Aicha Biaou, Steve Phillips, Ivan Adolwa, Jean Sogbedji, Mouna Mechri and Basil Kavishe
Remote Sens. 2025, 17(18), 3135; https://doi.org/10.3390/rs17183135 - 10 Sep 2025
Abstract
Achieving food security in Africa requires the sustainable intensification of cereal production, particularly for wheat, rice, and maize, which form the foundation of daily caloric intake in Africa. Smallholder farmers, who dominate cereal production in Africa, face challenges such as low productivity, limited [...] Read more.
Achieving food security in Africa requires the sustainable intensification of cereal production, particularly for wheat, rice, and maize, which form the foundation of daily caloric intake in Africa. Smallholder farmers, who dominate cereal production in Africa, face challenges such as low productivity, limited resources, and varying climatic conditions. Remote sensing, specifically through Sentinel-2 satellite imagery, offers a cost-effective method to monitor and improve farming practices. This study evaluates the possibility of extracting spectral reflectance curves of cereal crops from Sentinel-2 imagery across 68 smallholder farms in Togo, Tunisia, and Tanzania from 2021 to 2023. The farms ranged in size from 1 to 2 ha. We also assessed the separability of reflectance values following improved management practices (IPs), which included optimized seeding, fertilization, and pest control, and traditional farmers’ practices (FPs), which are typically characterized by inconsistent plant spacing and sub-optimal fertilization and pest management. Additionally, we analyzed regional variability in reflectance values to understand how climatic and management differences affect crop performance. Results showed that Sentinel-2 successfully captured spectral reflectance curves in all the countries and delineated management practice differences in Togo and Tunisia. Full article
(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
►▼ Show Figures

Figure 1

21 pages, 33616 KB  
Article
CycloneWind: A Dynamics-Constrained Deep Learning Model for Tropical Cyclone Wind Field Downscaling Using Satellite Observations
by Yuxiang Hu, Kefeng Deng, Qingguo Su, Di Zhang, Xinjie Shi and Kaijun Ren
Remote Sens. 2025, 17(18), 3134; https://doi.org/10.3390/rs17183134 - 10 Sep 2025
Abstract
Tropical cyclones (TCs) rank among the most destructive natural hazards globally, with core damaging potential originating from regions of intense wind shear and steep wind speed gradients within the eyewall and spiral rainbands. Accurately characterizing these fine-scale structural features is therefore critical for [...] Read more.
Tropical cyclones (TCs) rank among the most destructive natural hazards globally, with core damaging potential originating from regions of intense wind shear and steep wind speed gradients within the eyewall and spiral rainbands. Accurately characterizing these fine-scale structural features is therefore critical for understanding TC intensity evolution, wind hazard distribution, and disaster mitigation. Recently, the deep learning-based downscaling methods have shown significant advantages in efficiently obtaining high-resolution wind field distributions. However, existing methods are mainly used to downscale general wind fields, and research on downscaling extreme wind field events remains limited. There are two main difficulties in downscaling TC wind fields. The first one is that high-quality datasets for TC wind fields are scarce; the other is that general deep learning frameworks lack the ability to capture the dynamic characteristics of TCs. Consequently, this study proposes a novel deep learning framework, CycloneWind, for downscaling TC surface wind fields: (1) a high-quality dataset is constructed by integrating Cyclobs satellite observations with ERA5 reanalysis data, incorporating auxiliary variables like low cloud cover, surface pressure, and top-of-atmosphere incident solar radiation; (2) we propose CycloneWind, a dynamically constrained Transformer-based architecture incorporating three wind field dynamical operators, along with a wind dynamics-constrained loss function formulated to enforce consistency in wind divergence and vorticity; (3) an Adaptive Dynamics-Guided Block (ADGB) is designed to explicitly encode TC rotational dynamics using wind shear detection and wind vortex diffusion operators; (4) Filtering Transformer Layers (FTLs) with high-frequency filtering operators are used for modeling wind field small-scale details. Experimental results demonstrate that CycloneWind successfully achieves an 8-fold spatial resolution reconstruction in TC regions. Compared to the best-performing baseline model, CycloneWind reduces the Root Mean Square Error (RMSE) for the U and V wind components by 9.6% and 4.9%, respectively. More significantly, it achieves substantial improvements of 23.0%, 22.6%, and 20.5% in key dynamical metrics such as divergence difference, vorticity difference, and direction cosine dissimilarity. Full article
(This article belongs to the Special Issue Advances in Oceanic Dynamics by SAR and Numeric Model in Tropical Cyclone)
►▼ Show Figures

Figure 1

21 pages, 6709 KB  
Article
Multi-Source Retrieval of Thermodynamic Profiles from an Integrated Ground-Based Remote Sensing System Using an EnKF1D-Var Framework
by Qi Zhang, Bin Deng, Shudong Wang, Fangyou Dong and Min Shao
Remote Sens. 2025, 17(18), 3133; https://doi.org/10.3390/rs17183133 - 10 Sep 2025
Abstract
In this study, we present a novel data assimilation framework, the Ensemble Kalman Filter One-Dimensional Variational (EnKF1D-Var) framework, which assimilates observations from a Ground-based Microwave Radiometer (GMWR), a Mie–Raman Aerosol Lidar (MRL), and a Global Navigation Satellite System Meteorology sensor (GNSS/MET). The framework [...] Read more.
In this study, we present a novel data assimilation framework, the Ensemble Kalman Filter One-Dimensional Variational (EnKF1D-Var) framework, which assimilates observations from a Ground-based Microwave Radiometer (GMWR), a Mie–Raman Aerosol Lidar (MRL), and a Global Navigation Satellite System Meteorology sensor (GNSS/MET). The framework integrates multi-source vertical observations of water vapor and temperature with hourly temporal and 15 m vertical resolutions, driven by GFS forecasts. Three-month-long studies from May to July 2024 at Anqing Station in subtropical China demonstrate that the EnKF1D-Var retrievals reduce biases in temperature and humidity within the low troposphere, especially for daytime retrievals, by dynamically updating the observational error covariance matrices. Maximum humidity corrections reach up to 0.075 g/kg (120 PPMV), and temperature bias reductions exceed 3%. Incremental analysis reveals that the contribution to bias correction differs across instruments. GNSS/MET plays a dominant role in temperature adjustment, while GMWR provides supplementary support. In contrast, the majority of the improvements in water vapor retrieval can be attributed to MRL observations. This study achieved a reasonable application of multiple ground-based remote sensing observations, providing a new approach for the inversion of temperature and humidity profiles in the atmospheric boundary layer. 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, 6399 KB  
Article
Assessing the Performance of GNSS-IR for Sea Level Monitoring During Hurricane-Induced Storm Surges
by Runtao Zhang, Kai Liu, Xue Wang, Zhao Li, Tao Xie, Qusen Chen and Xin Chang
Remote Sens. 2025, 17(18), 3132; https://doi.org/10.3390/rs17183132 - 9 Sep 2025
Abstract
With the intensification of extreme climate change, hurricanes are becoming increasingly frequent, and coastal regions are often impacted by hurricane-induced storm surges. While GNSS-IR (Global Navigation Satellite System–Interferometric Reflectometry) has been widely used for sea level monitoring, its application in extreme weather events [...] Read more.
With the intensification of extreme climate change, hurricanes are becoming increasingly frequent, and coastal regions are often impacted by hurricane-induced storm surges. While GNSS-IR (Global Navigation Satellite System–Interferometric Reflectometry) has been widely used for sea level monitoring, its application in extreme weather events such as storm surges remains limited. This study focuses on GNSS-IR-based storm surge monitoring and investigates six hurricane events using data from two GNSS stations (CALC and FLCK) located in the Gulf of Mexico. The monitoring accuracy and effectiveness are systematically evaluated. Results indicate that GNSS-IR achieves a sea level accuracy of approximately 7 cm under non-storm surge conditions. Compared with the FLCK station, the CALC station has a wider field of water reflection and higher precision observation results. This further confirms that an open environment is a prerequisite for ensuring the accuracy of GNSS-IR measurements. However, accuracy degrades significantly during storm surges, reaching only a decimeter-level precision. Multi-GNSS observations notably improve temporal resolution, with valid observation periods covering 83% to 97% of the total time, compared with only 40% to 60% for single-system observations. Moreover, dynamic sea level variations are closely correlated with hurricane trajectories, which affects GNSS-IR measurement accuracy to some extent. The GPS L2 band is particularly sensitive, likely due to the complex surface-reflected condition caused by hurricanes. Despite reduced accuracy during storm surges, GNSS-IR remains capable of capturing dynamic sea level changes effectively, demonstrating its potential as a valuable supplement to the existing observation networks for extreme weather monitoring. Full article
(This article belongs to the Special Issue Advanced Multi-GNSS Positioning and Its Applications in Geoscience)
►▼ Show Figures

Figure 1

19 pages, 10212 KB  
Article
Data-Driven Prediction of Deep-Sea Near-Seabed Currents: A Comparative Analysis of Machine Learning Algorithms
by Hairong Bao, Zhixiong Yao, Dongfeng Xu, Jun Wang, Chenghao Yang, Nuan Liu and Yuntian Pang
Remote Sens. 2025, 17(18), 3131; https://doi.org/10.3390/rs17183131 - 9 Sep 2025
Abstract
Deep-sea mining has garnered significant global attention, and accurate prediction of ocean currents plays a critical role in optimizing the design of sediment plume monitoring networks associated with mining activities. Using near-seabed mooring data from the Western Pacific M2 block (Beijing Pioneer polymetallic [...] Read more.
Deep-sea mining has garnered significant global attention, and accurate prediction of ocean currents plays a critical role in optimizing the design of sediment plume monitoring networks associated with mining activities. Using near-seabed mooring data from the Western Pacific M2 block (Beijing Pioneer polymetallic nodule Exploration Area, BPEA), this study trained four machine learning models—LSTM, XGBoost, ARIMA, and SVR—on current velocity to generate 96 h forecasts. Key findings include the following: LSTM and ARIMA models outperformed XGBoost and SVR in near-seabed current prediction. 1 h ahead forecasts substantially improved accuracy over rolling predictions (an iterative process where predicted values are treated as observed values for subsequent prediction steps), reducing zonal current (east–west component) RMSE from 2.395 cm/s to 1.120 cm/s and meridional current (north–south component) RMSE from 2.024 cm/s to 1.224 cm/s. For practical deployment, 3 h ahead forecasts achieved a zonal current RMSE of 1.412 cm/s. Full article
(This article belongs to the Special Issue Linking Marine Heatwaves/Cold-Spells, Eddies, and Sea Surface Features)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-34
Previous Issue
Back to TopTop