Remote Sensing

27 pages, 9039 KB

Open AccessArticle

Source(s) of the Smooth Caloris Exterior Plains on Mercury: Mapping, Remote Analyses, and Scenarios for Future Testing with BepiColombo Data

by Keenan B. Golder, Bradley J. Thomson, Lillian R. Ostrach, Devon M. Burr, Joshua P. Emery and Harald Hiesinger

Remote Sens. 2026, 18(1), 19; https://doi.org/10.3390/rs18010019 (registering DOI) - 20 Dec 2025

Abstract

Mercury hosts widespread smooth plains that are concentrated in the Caloris impact basin, in an annulus surrounding the Caloris basin, and in the adjacent northern smooth plains. The origins of these smooth plains are uncertain, although prior work suggests these plains in the [...] Read more.

Mercury hosts widespread smooth plains that are concentrated in the Caloris impact basin, in an annulus surrounding the Caloris basin, and in the adjacent northern smooth plains. The origins of these smooth plains are uncertain, although prior work suggests these plains in the northwestern Caloris annulus might reflect volcanic activity, impact ejecta, or a combination of the two. Deciphering the timing and mode of emplacement of these plains would provide a critical constraint on regional late-stage volcanism or impact effects. In this work, the region northwest of Caloris was investigated using geomorphological and color-based mapping, crater counting techniques, and spectral analyses with the goal of placing constraints on the source of the observed units and identifying the primary emplacement mechanism. Mapping and spectral analyses confirm previous findings of two distinct, yet intermingled, units within these plains, each with similar crater count model ages that postdate the formation of the Caloris impact basin. Mapping, spectra analysis, ages, and the identification of potential flow pathways are more consistent with a predominantly volcanic origin for the smooth plains materials, although these data do not rule out contributions from impact ejecta or impact melt. We propose several hypothetical scenarios, including post-emplacement modification by near-surface volatiles, to explain these observations and clarify the emplacement mechanism for these specific smooth plains regions. Further observations from the BepiColombo mission should provide data to potentially address the outstanding questions from this work. Full article

► Show Figures

Figure 1

22 pages, 26514 KB

Open AccessArticle

SiamDiff: A Diffusion-Driven Siamese Network for Scale-Aware Anti-UAV Tracking

by Hong Zhang, Yihao Kuang, Jiaqi Wang, Lingyu Jin, Chang Xu, Yanda Meng and Bo Huang

Remote Sens. 2026, 18(1), 18; https://doi.org/10.3390/rs18010018 (registering DOI) - 20 Dec 2025

Abstract

Unmanned aerial vehicle (UAV) tracking faces significant challenges due to small targets and background interference. Traditional anchor-based tracking algorithms require designing numerous proposals to capture such tiny targets, which entails unacceptable computational overhead. On the other hand, anchor-free tracking methods struggle to adapt [...] Read more.

Unmanned aerial vehicle (UAV) tracking faces significant challenges due to small targets and background interference. Traditional anchor-based tracking algorithms require designing numerous proposals to capture such tiny targets, which entails unacceptable computational overhead. On the other hand, anchor-free tracking methods struggle to adapt to target scale variations, resulting in suboptimal tracking accuracy in anti-UAV tracking scenarios. To address these limitations, we pioneer the integration of diffusion models into visual tracking, proposing SiamDiff—a scale-adaptive anti-UAV framework. We reformulate the tracking task as a bounding box prediction problem, where a diffusion model is leveraged to generate scale-adaptive proposals. Furthermore, we propose a Learnable Mask Module (LMM) and a Frequency Channel Fusion Module (FCFM) to enhance discriminative feature extraction for small targets. Additionally, we design a Scale-Aware Diffusion Strategy (SADA) to boost robustness to scale variations. Experimental results on the Anti-UAV and Anti-UAV410 benchmarks demonstrate the effectiveness of our approach, achieving a State Accuracy (SA) of 71.90% and 67.03%, respectively, outperforming the baseline and other trackers. Moreover, our method shows superior adaptability to scale variations, confirming its robustness in complex anti-UAV tracking scenarios. Full article

21 pages, 3985 KB

Open AccessArticle

Self-Supervised LiDAR Desnowing with 3D-KNN Blind-Spot Networks

by Junyi Li and Wangmeng Zuo

Remote Sens. 2026, 18(1), 17; https://doi.org/10.3390/rs18010017 (registering DOI) - 20 Dec 2025

Abstract

Light Detection and Ranging (LiDAR) is fundamental to autonomous driving and robotics, as it provides reliable 3D geometric information. However, snowfall introduces numerous spurious reflections that corrupt range measurements and severely degrade downstream perception. Existing desnowing techniques either rely on handcrafted filtering rules [...] Read more.

Light Detection and Ranging (LiDAR) is fundamental to autonomous driving and robotics, as it provides reliable 3D geometric information. However, snowfall introduces numerous spurious reflections that corrupt range measurements and severely degrade downstream perception. Existing desnowing techniques either rely on handcrafted filtering rules that fail under varying snow densities, or require paired snowy–clean scans, which are nearly impossible to collect in real-world scenarios. Self-supervised LiDAR desnowing approaches address these challenges by projecting raw 3D point clouds into 2D range images and jointly training a point reconstruction network (PR-Net) and a reconstruction difficulty network (RD-Net). Nevertheless, these methods remain limited by their reliance on the outdated Noise2Void training paradigm, which restricts reconstruction quality. In this paper, we redesign PR-Net with a blind-spot architecture to overcome the limitation. Specifically, we introduce a 3D-KNN encoder that aggregates neighborhood features directly in Euclidean 3D space, ensuring geometrically consistent representations. Additionally, we integrate residual state-space blocks (RSSB) to capture long-range contextual dependencies with linear computational complexity. Extensive experiments on both synthetic and real-world datasets, including SnowyKITTI and WADS, demonstrate that our method outperforms state-of-the-art self-supervised desnowing approaches by up to 0.06 IoU while maintaining high computational efficiency. Full article

22 pages, 11612 KB

Open AccessArticle

A Novel Method for Reducing Uncertainty in Subglacial Topography: Implications for Greenland Ice Sheet Volume and Stability

by Oliver T. Bartlett and Steven J. Palmer

Remote Sens. 2026, 18(1), 16; https://doi.org/10.3390/rs18010016 (registering DOI) - 20 Dec 2025

Abstract

Subglacial topography is a critical boundary condition for ice sheet models projecting past and future ice sheet–climate interactions. Contemporary ice-sheet-wide bed topography datasets are partially derived using mass conservation, but approximately 75% of the most widely used Greenland Ice Sheet (GrIS) dataset is [...] Read more.

Subglacial topography is a critical boundary condition for ice sheet models projecting past and future ice sheet–climate interactions. Contemporary ice-sheet-wide bed topography datasets are partially derived using mass conservation, but approximately 75% of the most widely used Greenland Ice Sheet (GrIS) dataset is based on simple interpolation of airborne radio-echo sounding (RES) measurements, such as kriging or streamline diffusion. Due to limited independent validation data, the errors and biases in this approach are poorly understood, creating largely unknown uncertainties in subglacial topography. Here, we interpolated synthetic RES observations of bed topography over ice-free areas with a known topography at a 5 m spatial resolution and quantify discrepancies. We found that the absolute error in kriged bed topography increases with distance from the input data, though at a reduced rate than previously estimated. The difference between an interpolated elevation estimate and the local mean elevation is a strong predictor of real bed errors (R² = 0.72), with further improvement as input observation sparsity increases (R² > 0.82). We propose a method to quantify and reduce uncertainty in kriged bed topography in sparsely surveyed regions, reducing uncertainty for at least 56% of the kriged interior at a 99% confidence interval. Our results suggest that subglacial depth is on average 5 m deeper than previous estimates, though individual areas may be shallower or deeper (σ = 41 m). Consequently, the area grounded below sea level is likely underestimated by 2%, increasing to 29% for regions deeper than 200 m. These findings have potential implications for the future stability of the GrIS under climate change. Full article

(This article belongs to the Special Issue Remote Sensing of the Cryosphere (Third Edition))

► Show Figures

Figure 1

25 pages, 33154 KB

Open AccessArticle

Combining Ground Penetrating Radar and a Terrestrial Laser Scanner to Constrain EM Velocity: A Novel Approach for Masonry Wall Characterization in Cultural Heritage Applications

by Giorgio Alaia, Maurizio Ercoli, Raffaella Brigante, Laura Marconi, Nicola Cavalagli and Fabio Radicioni

Remote Sens. 2026, 18(1), 15; https://doi.org/10.3390/rs18010015 (registering DOI) - 20 Dec 2025

Abstract

In this paper, the combined use of Ground Penetrating Radar (GPR) and a Terrestrial Laser Scanner (TLS) is illustrated to highlight multiple advantages arising from the integration of these two distinct Non-Destructive Testing (NDT) techniques in the investigation of a historical wall. In [...] Read more.

In this paper, the combined use of Ground Penetrating Radar (GPR) and a Terrestrial Laser Scanner (TLS) is illustrated to highlight multiple advantages arising from the integration of these two distinct Non-Destructive Testing (NDT) techniques in the investigation of a historical wall. In particular, thanks to the TLS point cloud, a precise evaluation of the medium’s thickness, as well as its irregularities, was carried out. Based on this accurate geometrical constraint, a first-order velocity model, to be used for a time-to-depth conversion and for a post-stack GPR data migration, was computed. Moreover, a joint visualization of both datasets (GPR and TLS) was achieved in a novel tridimensional workspace. This solution provided a more straightforward and efficient way of testing the reliability of the combined results, proving the efficiency of the proposed method in the estimation of a velocity model, especially in comparison to conventional GPR methods. This demonstrates how the integration of different remote sensing methodologies can yield a more solid interpretation, taking into account the uncertainties related to the geometrical irregularities of the external wall’s surface and the inner structure generating complex GPR signatures. Full article

(This article belongs to the Special Issue Remote, Proximal Sensing and Geophysics for Cultural Heritage Knowledge and Conservation (Second Edition))

20 pages, 12683 KB

Open AccessArticle

Corn Plant Detection Using YOLOv9 Across Different Soil Background Colors, Growth Stages, and UAV Flight Heights

by Thiago O. C. Barboza, Adão Felipe dos Santos, Emily K. Bedwell, George Vellidis and Lorena N. Lacerda

Remote Sens. 2026, 18(1), 14; https://doi.org/10.3390/rs18010014 (registering DOI) - 20 Dec 2025

Abstract

Accurate stand count and growth stage detection are essential for crop monitoring, since traditional methods often overlook field variability, leading to poor management decisions. This study evaluated the performance of the YOLOv9-small model for detecting and counting corn plants under real field conditions. [...] Read more.

Accurate stand count and growth stage detection are essential for crop monitoring, since traditional methods often overlook field variability, leading to poor management decisions. This study evaluated the performance of the YOLOv9-small model for detecting and counting corn plants under real field conditions. The model was tested across three soil background types, two flight heights (30 and 70 m), and four corn growth stages (V2, V3, V5, and V6). Unmanned aerial vehicle (UAV) imagery was collected from three distinct fields and cropped into 640 × 640 pixels. Datasets were split into training (70%), validation (20%), and testing (10%) datasets. Model performance was assessed using precision, recall, classification loss, and mean average precision of 50% and 50–90%. The results showed that the V3 and V5 stages yielded the highest detection accuracy, with mAP50 values exceeding 85% in conventional tillage fields and slightly lower performance in gray/red-brown conditions due to background interference. Increasing flight height to 70 m reduced accuracy by 8–12%, though precision remained high, particularly at V5, and performance was poorest for V2 and V6. In conclusion, YOLOv9-small is effective for early-stage corn detection, particularly at V3 and V5, with 30 m providing optimal results. However, 70 m may be acceptable at V5 to optimize mapping time. Full article

(This article belongs to the Special Issue Precision Agriculture and Crop Monitoring Based on Remote Sensing Methods)

► Show Figures

Figure 1

21 pages, 6531 KB

Open AccessArticle

Cross-Regional Detection and Precise GIS Localization of Old Landslides Using High-Resolution Remote Sensing Imagery and YOLOv5

by Xiaoxu Xie, Deying Li, Xin Liang, Qin Chen, Kunlong Yin and Fasheng Miao

Remote Sens. 2026, 18(1), 13; https://doi.org/10.3390/rs18010013 (registering DOI) - 19 Dec 2025

Abstract

Old landslide reactivation poses a significant risk to infrastructure and settlements in mountainous regions. Its identification and accurate localization are crucial for mitigating reactivation hazards, yet are hindered by blurred morphological signatures and vegetation cover. This study develops a cross-regional workflow for the [...] Read more.

Old landslide reactivation poses a significant risk to infrastructure and settlements in mountainous regions. Its identification and accurate localization are crucial for mitigating reactivation hazards, yet are hindered by blurred morphological signatures and vegetation cover. This study develops a cross-regional workflow for the detection and GIS-based localization of old landslides using one-meter-resolution optical imagery and an enhanced YOLOv5 model. The workflow strictly separates training and detecting areas (Wanzhou for training, Zigui for detecting) to simulate realistic, unsurveyed scenarios. A Python script converts model outputs into shapefiles with precise geographic coordinates.. The results show an F1 score of 0.96 in the training area and 0.62 (mAP@0.5 = 0.58, Precision = 0.56, Recall = 0.67) in the detecting area. The analysis identifies causes of cross-regional performance degradation, including geomorphic confusion and potential detection of previously unmapped old landslides. These results demonstrate the feasibility of cross-regional landslide detection and highlight the potential of deep learning–GIS integration for practical hazard management. Full article

(This article belongs to the Special Issue Remote Sensing Methods and Technical Developments in Geohazard Early Warning)

► Show Figures

Figure 1

24 pages, 4488 KB

Open AccessArticle

CAM-HRNet: A Multi-Scale Parallel Structure Change Detection Framework for Forest Land

by Xihan Li and Jianyu Yang

Remote Sens. 2026, 18(1), 12; https://doi.org/10.3390/rs18010012 (registering DOI) - 19 Dec 2025

Abstract

As a vital component of Earth’s ecosystem, forest land plays an irreplaceable role in maintaining ecological balance. To address the limitations of traditional deep learning methods in remote sensing data generalization, this paper proposes CAM-HRNet, a change detection framework that integrates the High-Resolution [...] Read more.

As a vital component of Earth’s ecosystem, forest land plays an irreplaceable role in maintaining ecological balance. To address the limitations of traditional deep learning methods in remote sensing data generalization, this paper proposes CAM-HRNet, a change detection framework that integrates the High-Resolution Net (HRNet) backbone with a convolutional attention mechanism. The method leverages HRNet’s multi-scale parallel structure and incorporates attention mechanisms at different scales, while a step-by-step up-sampling mechanism enables smooth multi-scale feature fusion with reduced information loss. By combining CAM-HRNet’s feature extraction capabilities with a twin network structure, we develop both binary and semantic change detection methods. The binary method identifies changed areas through difference feature calculation, while the semantic method adds segmentation branches to analyze specific change types. Focus loss is introduced to address sample imbalance. Experimental results demonstrate that our binary change detection achieved 75.24% IoU and 85.88% F1, outperforming comparable methods by 2.62% and 1.74%, respectively, while effectively filtering irrelevant changes. The semantic method maintained strong performance with 63.93% IoU and 77.53% F1, providing accurate monitoring of forest ecosystem dynamics to support resource protection and management. Full article

► Show Figures

Figure 1

26 pages, 6438 KB

Open AccessArticle

Wide-Area Spectrum Sensing for Space Targets Based on Low-Earth Orbit Satellite Constellations: A SRFlow Model for Electromagnetic Spectrum Map Reconstruction

by You Fu, Youchen Fan, Liu Yi, Shunhu Hou, Yufei Niu and Shengliang Fang

Remote Sens. 2026, 18(1), 11; https://doi.org/10.3390/rs18010011 (registering DOI) - 19 Dec 2025

Abstract

To address the need for wide-area electromagnetic spectrum sensing of space targets from sparse Low-Earth Orbit constellation observations, this paper proposes SRFlow, a flow-matching generative model. We first construct a high-fidelity dataset covering diverse scenarios via STK-MATLAB co-simulation. By integrating multi-source priors and [...] Read more.

To address the need for wide-area electromagnetic spectrum sensing of space targets from sparse Low-Earth Orbit constellation observations, this paper proposes SRFlow, a flow-matching generative model. We first construct a high-fidelity dataset covering diverse scenarios via STK-MATLAB co-simulation. By integrating multi-source priors and an iterative measurement injection strategy, SRFlow achieves high-quality reconstruction of full spectrum maps from sparse measurements. Experiments demonstrate that SRFlow significantly outperforms state-of-the-art baselines, including the physics-informed diffusion model RMDM, in both reconstruction accuracy (NMSE/SSIM) and computational efficiency (parameters/inference time), under both known and unknown target-position conditions. Moreover, it trains nearly an order of magnitude faster than diffusion models. This work contributes the first dedicated dataset for space-based spectrum sensing, introduces the accurate and efficient SRFlow model, and establishes a rigorous benchmark for future research. Full article

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

17 pages, 4858 KB

Open AccessArticle

Retrieving Woody Components from Time-Series Gap-Fraction and Multispectral Satellite Observations over Deciduous Forests

by Woohyeok Kim, Jaese Lee, Yoojin Kang, Jungho Im, Bokyung Son and Jiwon Lee

Remote Sens. 2026, 18(1), 10; https://doi.org/10.3390/rs18010010 - 19 Dec 2025

Abstract

Leaf area index (LAI) is essential for understanding vegetation dynamics, ecosystem processes, and land–atmosphere interactions. Various measurement methods exist, but gap-fraction-based indirect methods are preferred due to their reduced labor and field survey time in comparison to direct methods. However, gap-fraction-based field observations, [...] Read more.

Leaf area index (LAI) is essential for understanding vegetation dynamics, ecosystem processes, and land–atmosphere interactions. Various measurement methods exist, but gap-fraction-based indirect methods are preferred due to their reduced labor and field survey time in comparison to direct methods. However, gap-fraction-based field observations, often referred to as plant area index (PAI), frequently overestimate LAI because they include woody components. To mitigate this issue, the woody-to-total-area ratio (α) can be utilized to exclude these woody components from PAI, yielding more accurate LAI estimates (hereafter referred to as LAI_adjusted). In this study, we demonstrate a novel method to estimate α using Sentinel-2-based normalized difference vegetation index (NDVI) and time-series PAI measurements. The α estimates effectively reduce the influence of woody components in PAI within deciduous broadleaf forests (DBF). Moreover, LAI_adjusted shows good agreement with the Sentinel-2 LAI, which represents effective LAI derived from the PROSAIL model. Notably, the spatial distribution of α effectively captured the expected seasonal dynamics across various forest types. In DBF, α values increased during winter due to leaf fall when compared to the growing season, while seasonal variations were relatively small in evergreen needleleaf forest (ENF). We further confirmed that our method demonstrates greater robustness with NDVI than with other vegetation indices that are more susceptible to topographic variation. Ultimately, this framework presents a promising pathway to mitigate biases in most gap-fraction-based PAI measurements, thereby enhancing the accuracy of vegetation structural assessments and supporting broader ecological and climate-related applications. Full article

29 pages, 2573 KB

Open AccessArticle

A Green Synergy Index for Urban Green Space Assessment Based on Multi-Source Data Integration

by Yuefeng Wang, Deyuan Gan, Wei Jiao and Jiali Xie

Remote Sens. 2026, 18(1), 9; https://doi.org/10.3390/rs18010009 - 19 Dec 2025

Abstract

Current assessments of urban green spaces (UGS) rely largely on two-dimensional (2D) indicators, which fail to capture the three-dimensional (3D) structure necessary for evaluating ecological functions and human exposure. Among these, the Normalized Difference Vegetation Index (NDVI) describes top-down canopy greenness from a [...] Read more.

Current assessments of urban green spaces (UGS) rely largely on two-dimensional (2D) indicators, which fail to capture the three-dimensional (3D) structure necessary for evaluating ecological functions and human exposure. Among these, the Normalized Difference Vegetation Index (NDVI) describes top-down canopy greenness from a nadir perspective, whereas the Green View Index (GVI) quantifies vegetation visibility at street level from a pedestrian perspective. Because the relationship between NDVI and GVI remains unclear, multi-indicator assessments become difficult to interpret, limiting their ability to jointly characterize urban greenery. To address these gaps, we develop a synergy framework that integrates remote sensing with street-view images. First, we aligned the observation scales through street-view depth estimation and converted NDVI into fractional vegetation cover (FVC) through nonlinear mapping to unify measurement units. Correlation experiments revealed that the consistency between GVI and FVC was weak across the city (R² = 0.27) but substantially stronger along arterial roads with continuous vegetation (R² = 0.61). On this basis, we design a Green Synergy Index (GSI) that combines FVC and GVI using fractional power-law adjustments and an interaction term to capture their joint effects. Robustness tests indicate that GSI effectively handles extreme or mismatched cases, differentiates greening patterns, and integrates complementary information from nadir and street views without numerical instability. Furthermore, we assess the consistency between GSI and land surface temperature (LST), showing that the proposed index improves explanatory power compared with FVC and GVI alone (by 5.6% and 8.8%, respectively). Application to the study area yields a mean GSI value of 0.44 on a 0–1 scale, with spatial variations closely associated with road geometry and functional zoning. This enables the identification of mismatched canopy and visibility segments and supports targeted, climate-sensitive green infrastructure planning. Full article

(This article belongs to the Special Issue Advances in GeoAI with Remote Sensing Imagery for Urban Green Space Mapping and Monitoring)

24 pages, 7857 KB

Open AccessArticle

MTFM: Multi-Teacher Feature Matching for Cross-Dataset and Cross-Architecture Adversarial Robustness Transfer in Remote Sensing Applications

by Ravi Kumar Rogannagari and Kazi Aminul Islam

Remote Sens. 2026, 18(1), 8; https://doi.org/10.3390/rs18010008 - 19 Dec 2025

Abstract

Remote sensing plays a critical role in environmental monitoring, land use analysis, and disaster response by enabling large-scale, data-driven observation of Earth’s surface. Image classification models are central to interpreting remote sensing data, yet they remain vulnerable to adversarial attacks that can mislead [...] Read more.

Remote sensing plays a critical role in environmental monitoring, land use analysis, and disaster response by enabling large-scale, data-driven observation of Earth’s surface. Image classification models are central to interpreting remote sensing data, yet they remain vulnerable to adversarial attacks that can mislead predictions and compromise reliability. While adversarial training improves robustness, the challenge of transferring this robustness across models and domains remains underexplored. This study investigates robustness transfer as a defense strategy, aiming to enhance the resilience of remote sensing classifiers against adversarial patch attacks. We propose a novel Multi-Teacher Feature Matching (MTFM) framework to align feature spaces between clean and adversarially robust teacher models and the student model, aiming to achieve an optimal trade-off between accuracy and robustness against adversarial patch attacks. The proposed method consistently outperforms traditional standard models and matches—or in some cases, surpasses—conventional defense strategies across diverse datasets and architectures. The MTFM approach also supersedes the self-attention module-based adversarial robustness transfer. Importantly, it achieves these gains with less training effort compared to traditional adversarial defenses. These results highlight the potential of robustness-aware knowledge transfer as a scalable and efficient solution for building resilient geospatial AI systems. Full article

► Show Figures

Figure 1

27 pages, 10063 KB

Open AccessArticle

Evaluating Direct Georeferencing of UAV-LiDAR Data Through QGIS Tools: An Application to a Coastal Area

by Carmen Maria Giordano, Valentina Alena Girelli, Alessandro Lambertini, Emanuele Mandanici, Maria Alessandra Tini, Renata Archetti, Massimo Ponti and Antonio Zanutta

Remote Sens. 2026, 18(1), 7; https://doi.org/10.3390/rs18010007 - 19 Dec 2025

Abstract

Coastal monitoring requires a synthesis of accuracy, temporal and context flexibility. Unmanned aerial vehicles (UAVs) equipped with LiDAR (light detection and ranging) sensors are a valuable option, made more widespread by the commercialization of consumer-grade systems, although they often limit user control over [...] Read more.

Coastal monitoring requires a synthesis of accuracy, temporal and context flexibility. Unmanned aerial vehicles (UAVs) equipped with LiDAR (light detection and ranging) sensors are a valuable option, made more widespread by the commercialization of consumer-grade systems, although they often limit user control over data processing. This work quantifies the impact of the base station type (temporary, permanent, or virtual) and its distance from the survey site on UAV-LiDAR direct georeferencing accuracy. The comparison is carried out, in a specific coastal study site, on both the estimated trajectories and the final outputs, using novel QGIS tools (PT2DEM, DEM2DEM, T2T). While temporary base stations are affected by uncertainties of the base coordinates, virtual reference stations are affected by a wider range of errors, compromising the relative model reconstruction. In contrast, permanent stations may avoid base-coordinate uncertainties, but if their distance from the site exceeds the suggested limit (15 km), their use leads to a loss of accuracy in both the relative reconstruction of the model and the absolute georeferencing. Although the use of vertical constraints has proven to be a valuable tool for reducing the vertical bias induced by a suboptimal base station, their distribution may not be adequate for minimizing residual random deviations, and their deployment may be challenging in environmental contexts lacking stable and accessible areas. Full article

(This article belongs to the Special Issue Advancements in LiDAR Technology and Applications in Remote Sensing)

► Show Figures

Figure 1

25 pages, 6604 KB

Open AccessArticle

From MSG-SEVIRI to MTG-FCI: Advancing Volcanic Thermal Monitoring from Geostationary Satellites

by Federica Torrisi, Giovanni Salvatore Di Bella, Claudia Corradino, Simona Cariello, Arianna Beatrice Malaguti and Ciro Del Negro

Remote Sens. 2026, 18(1), 6; https://doi.org/10.3390/rs18010006 - 19 Dec 2025

Abstract

Continuous global monitoring of volcanic activity from space requires balancing spatial and temporal resolution, a long-standing trade-off between polar-orbiting and geostationary satellites. Polar sensors such as MODIS, VIIRS, and SLSTR provide high spatial resolution (375 m–1 km) but with limited temporal coverage. In [...] Read more.

Continuous global monitoring of volcanic activity from space requires balancing spatial and temporal resolution, a long-standing trade-off between polar-orbiting and geostationary satellites. Polar sensors such as MODIS, VIIRS, and SLSTR provide high spatial resolution (375 m–1 km) but with limited temporal coverage. In contrast, geostationary sensors like SEVIRI offer high temporal resolution (5–15 min) but with coarser spatial detail (~3 km), often missing lower-intensity thermal events. The recently launched Flexible Combined Imager (FCI) aboard the geostationary Meteosat Third Generation (MTG-I) satellite represents a major improvement, providing images every 10 min with a spatial resolution of 1–2 km, comparable to that of polar orbiters. Here, we adapted the established Remote Sensing Data Fusion (RSDF) algorithm to exploit the enhanced capabilities of FCI for detecting volcanic thermal anomalies and estimating Volcanic Radiative Power (VRP). The algorithm was applied to Mount Etna during three different eruptive phases that occurred in 2025. The VRP derived from FCI data was compared with that obtained from the geostationary SEVIRI and the polar-orbiting MODIS, SLSTR, and VIIRS sensors. The results show that FCI provides a more detailed and continuous characterization of volcanic thermal output than SEVIRI, while maintaining close agreement with polar sensors. These findings confirm the capability of FCI to deliver high-frequency, high-resolution thermal monitoring, representing a major step toward operational, near-real-time volcanic surveillance from space. Full article

► Show Figures

Figure 1

19 pages, 18529 KB

Open AccessArticle

A Global, Multidecadal Carbon Monoxide (CO) Record from the Sounder AIRS/CrIS System

by Tao Wang, Vivienne H. Payne, Evan Manning, Thomas S. Pagano, Bjorn Lambrigtsen and Ruth Monarrez

Remote Sens. 2026, 18(1), 5; https://doi.org/10.3390/rs18010005 - 19 Dec 2025

Abstract

Satellite observations of carbon monoxide (CO) are essential for monitoring global air quality, pollution transport, and climate-related emissions. This study evaluates the continuity and consistency of CO measurements derived from the Atmospheric Infrared Sounder (AIRS) and the Cross-track Infrared Sounder (CrIS), both operating [...] Read more.

Satellite observations of carbon monoxide (CO) are essential for monitoring global air quality, pollution transport, and climate-related emissions. This study evaluates the continuity and consistency of CO measurements derived from the Atmospheric Infrared Sounder (AIRS) and the Cross-track Infrared Sounder (CrIS), both operating in the thermal infrared band near 4.6 µm. By comparing retrievals from the AIRS Science Team v7 and the CLIMCAPS (Community Long-term Infrared Microwave Combined Atmospheric Product System) algorithms across AIRS and CrIS radiances, we demonstrate that the interannual CO variability is consistent across instruments and algorithms. These findings are validated using the long-term MOPITT record. Additionally, we show that mid-tropospheric CO variabilities correspond with fire detections from MODIS and surface vapor pressure deficit (VPD) anomalies, indicating a rise in wildfire activity in the Northern Hemisphere. The results shown here provide confidence in the utility of a combined AIRS/CrIS CO record. With the scheduled continuation of CrIS observations through future JPSS platforms, the combined CO record from U.S. hyperspectral sounders in the afternoon orbit is set to continue to 2045 and beyond, providing a possible means to quantify trends and interannual variability over multiple decades. Full article

► Show Figures

Figure 1

23 pages, 6967 KB

Open AccessArticle

Semantics- and Physics-Guided Generative Network for Radar HRRP Generalized Zero-Shot Recognition

by Jiaqi Zhou, Tao Zhang, Siyuan Mu, Yuze Gao, Feiming Wei and Wenxian Yu

Remote Sens. 2026, 18(1), 4; https://doi.org/10.3390/rs18010004 - 19 Dec 2025

Abstract

High-resolution range profile (HRRP) target recognition has garnered significant attention in radar automatic target recognition (RATR) research for its rich structural information and low computational costs. With the rapid advancements in deep learning, methods for HRRP target recognition that leverage deep neural networks [...] Read more.

High-resolution range profile (HRRP) target recognition has garnered significant attention in radar automatic target recognition (RATR) research for its rich structural information and low computational costs. With the rapid advancements in deep learning, methods for HRRP target recognition that leverage deep neural networks have emerged as the dominant approaches. Nevertheless, these traditional closed-set recognition methods require labeled data for every class in training, while in reality, seen classes and unseen classes coexist. Therefore, it is necessary to explore methods that can identify both seen and unseen classes simultaneously. To this end, a semantic- and physical-guided generative network (SPGGN) was innovatively proposed for HRRP generalized zero-shot recognition; it combines a constructed knowledge graph with attribute vectors to comprehensively represent semantics and reconstructs strong scattering points to introduce physical constraints. Specifically, to boost the robustness, we reconstructed the strong scattering points from deep features of HRRPs, where class-aware contrastive learning in the middle layer effectively mitigates the influence of target-aspect variations. In the classification stage, discriminative features are produced through attention-based feature fusion to capture multi-faceted information, while the design of balancing loss abates the bias towards seen classes. Experiments on two measured aircraft HRRP datasets validated the superior recognition performance of our method. Full article

(This article belongs to the Special Issue Advanced Image Processing Technologies and Applications for Remote Sensing)

► Show Figures

Figure 1

25 pages, 4557 KB

Open AccessArticle

Feature Disentanglement Based on Dual-Mask-Guided Slot Attention for SAR ATR Across Backgrounds

by Ruiqiu Wang, Tao Su, Yuan Liang and Jiangtao Liu

Remote Sens. 2026, 18(1), 3; https://doi.org/10.3390/rs18010003 - 19 Dec 2025

Abstract

Due to the limited number of SAR samples in the dataset, current networks for SAR automatic target recognition (SAR ATR) are prone to overfitting the environmental information, which diminishes their generalization ability under cross-background conditions. However, acquiring sufficient measured data to cover the [...] Read more.

Due to the limited number of SAR samples in the dataset, current networks for SAR automatic target recognition (SAR ATR) are prone to overfitting the environmental information, which diminishes their generalization ability under cross-background conditions. However, acquiring sufficient measured data to cover the entire environmental space remains a significant challenge. This paper proposes a novel feature disentanglement network, named FDSANet. The network is designed to decouple and distinguish the features of the target from the background before classification, thereby improving its adaptability to background changes. Specifically, the network consists of two sub-networks. The first is an autoencoder sub-network based on dual-mask-guided slot attention. This sub-network utilizes target mask to guide the encoder to distinguish between target and background features. It then outputs these features as independent representations, respectively, achieving feature disentanglement. The second is a classification sub-network. It includes an encoder and a classifier, which work together to perform the classification based on the extracted target features. This network enhances the causal relationship between the target and the classification result, while mitigating the background’s interference on the classification. Moreover, the network, trained under a fixed background, demonstrates strong adaptability when applied to a new background. Experiments conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, as well as the OpenSARShip dataset, demonstrate the superior performance of FDSANet. Full article

► Show Figures

Figure 1

28 pages, 8621 KB

Open AccessArticle

Performance Assessment of Satellite-Based Rainfall Products in the Abbay Basin, Ethiopia

by Tadela Terefe Gashaw, Assefa M. Melesse and Brook Abate

Remote Sens. 2026, 18(1), 2; https://doi.org/10.3390/rs18010002 - 19 Dec 2025

Abstract

Satellite-based rainfall products (SRPs) are indispensable for hydro-climatological research, particularly in data-limited environments such as Ethiopia. This study systematically evaluates the performance of three widely used SRPs: Climate Hazards Group InfraRed Precipitation with Station data version 2 (CHIRPS), Tropical Applications of Meteorology using [...] Read more.

Satellite-based rainfall products (SRPs) are indispensable for hydro-climatological research, particularly in data-limited environments such as Ethiopia. This study systematically evaluates the performance of three widely used SRPs: Climate Hazards Group InfraRed Precipitation with Station data version 2 (CHIRPS), Tropical Applications of Meteorology using Satellite and ground-based observations version 3.1 (TAMSAT), and Multi-Source Weighted Ensemble Precipitation version 2.8 (MSWEP) across the North and South Gojjam sub-basins of the Abbay Basin. Using ground observations as benchmarks, spatial and temporal accuracy was assessed under varying elevation and rainfall intensity conditions, employing bias decomposition, error analysis, and detection metrics. Results show that rainfall variability in the region is shaped more by the local climate and topography than elevation, with elevation alone proving a weak predictor (R² < 0.5). Among the products, MSWEP v2.8 demonstrated the highest daily rainfall detection skill (≈ 87–88%), followed by TAMSAT (≈78%), while CHIRPS detected only about half of rainfall events (≈54%) and tended to overestimate no-rain days. MSWEP’s error composition is dominated by low random error (~52%), though it slightly overestimates rainfall and rainy days. TAMSAT provides finer-resolution data that capture localized variability and dry conditions well, with the lowest false alarm rate and moderate random error (~59%). CHIRPS exhibits weaker daily performance, dominated by high random error (~66%) and missed bias, though it improves at monthly scales and better captures heavy and violent rainfall. Seasonally, SRPs reproduce MAM rainfall reasonably well across both sub-basins, but their performance deteriorates markedly in JJAS, particularly in the south. These findings highlight the importance of sub-basin scale analysis and demonstrate that random versus systematic error composition is critical for understanding product reliability. The results provide practical guidance for selecting and calibrating SRPs in mountainous regions, supporting improved water resource management, climate impact assessment, and hydrological modeling in data-scarce environments. Full article

(This article belongs to the Special Issue Hydrometeorological Modelling Based on Remotely Sensed Data)

► Show Figures

Figure 1

27 pages, 3305 KB

Open AccessArticle

SatViT-Seg: A Transformer-Only Lightweight Semantic Segmentation Model for Real-Time Land Cover Mapping of High-Resolution Remote Sensing Imagery on Satellites

by Daoyu Shu, Zhan Zhang, Fang Wan, Wang Ru, Bingnan Yang, Yan Zhang, Jianzhong Lu and Xiaoling Chen

Remote Sens. 2026, 18(1), 1; https://doi.org/10.3390/rs18010001 - 19 Dec 2025

Abstract

The demand for real-time land cover mapping from high-resolution remote sensing (HR-RS) imagery motivates lightweight segmentation models running directly on satellites. By processing on-board and transmitting only fine-grained semantic products instead of massive raw imagery, these models provide timely support for disaster response, [...] Read more.

The demand for real-time land cover mapping from high-resolution remote sensing (HR-RS) imagery motivates lightweight segmentation models running directly on satellites. By processing on-board and transmitting only fine-grained semantic products instead of massive raw imagery, these models provide timely support for disaster response, environmental monitoring, and precision agriculture. Many recent methods combine convolutional neural networks (CNNs) with Transformers to balance local and global feature modeling, with convolutions as explicit information aggregation modules. Such heterogeneous hybrids may be unnecessary for lightweight models if similar aggregation can be achieved homogeneously, and operator inconsistency complicates optimization and hinders deployment on resource-constrained satellites. Meanwhile, lightweight Transformer components in these architectures often adopt aggressive channel compression and shallow contextual interaction to meet compute budgets, impairing boundary delineation and recognition of small or rare classes. To address this, we propose SatViT-Seg, a lightweight semantic segmentation model with a pure Vision Transformer (ViT) backbone. Unlike CNN-Transformer hybrids, SatViT-Seg adopts a homogeneous two-module design: a Local-Global Aggregation and Distribution (LGAD) module that uses window self-attention for local modeling and dynamically pooled global tokens with linear attention for long-range interaction, and a Bi-dimensional Attentive Feed-Forward Network (FFN) that enhances representation learning by modulating channel and spatial attention. This unified design overcomes common lightweight ViT issues such as channel compression and weak spatial correlation modeling. SatViT-Seg is implemented and evaluated in LuoJiaNET and PyTorch; comparative experiments with existing methods are run in PyTorch with unified training and data preprocessing for fairness, while the LuoJiaNET implementation highlights deployment-oriented efficiency on a graph-compiled runtime. Compared with the strongest baseline, SatViT-Seg improves mIoU by up to 1.81% while maintaining the lowest FLOPs among all methods. These results indicate that homogeneous Transformers offer strong potential for resource-constrained, on-board real-time land cover mapping in satellite missions. Full article

(This article belongs to the Special Issue Geospatial Artificial Intelligence (GeoAI) in Remote Sensing)

► Show Figures

Figure 1

Journal Description

Remote Sensing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI