Remote Sensing

23 pages, 6270 KB

Open AccessArticle

Spatiotemporal Dynamics and Influencing Factors of Landscape Ecological Risk in the Shandong Peninsula Urban Agglomeration Based on Sub-Watershed Units

by Jue Xiao, Linyu Ma, Longqian Chen, Ting Zhang and Gan Teng

Remote Sens. 2026, 18(13), 2266; https://doi.org/10.3390/rs18132266 - 7 Jul 2026

Viewed by 460

Abstract

Quantifying landscape ecological risk (LER) using multi-period land use data and ecological indicators is essential for understanding regional ecological dynamics. However, LER assessment is sensitive to spatial delineation, introducing uncertainty. This study developed an integrated LER model that incorporates the remote sensing ecological [...] Read more.

Quantifying landscape ecological risk (LER) using multi-period land use data and ecological indicators is essential for understanding regional ecological dynamics. However, LER assessment is sensitive to spatial delineation, introducing uncertainty. This study developed an integrated LER model that incorporates the remote sensing ecological index and abundance index, and evaluated spatial unit effects through comparative analyses of fishnet, hexagonal, sub-watershed, and county units. LER dynamics in the Shandong Peninsula Urban Agglomeration (SPUA) from 2004 to 2024 were analyzed, and a boosted regression trees model was applied to quantify the relative importance of influencing factors and their nonlinear effects. The results indicate that: (1) sub-watershed units showed greater robustness and stability across multiple evaluation indicators, supporting their suitability for LER assessment; (2) LER in the SPUA exhibited a fluctuating but overall slightly increasing trend over the past two decades, with a persistent west-low and east-high spatial pattern; and (3) relief degree (29.13%) and nighttime light (17.78%) were the dominant factors shaping LER, showing an inverted U-shaped response and a saturating nonlinear increase, respectively. This study supports the use of sub-watershed units as an appropriate spatial unit for LER assessment and provides insights into terrain-sensitive conservation and sustainable land-use management in urbanizing regions. Full article

(This article belongs to the Special Issue Ecological Environment Remote Sensing and Sustainable Development Evaluation in Coastal Zones)

► Show Figures

Figure 1

27 pages, 16286 KB

Open AccessArticle

WCMNet: A Wavelet-Guided and CNN–Mamba Hybrid Network Approach for Unsupervised Domain Adaptation in Building Extraction

by Dongjie Yang, Kuikui Han, Yuanwei Yang, Xianjun Gao, Kangliang Guo, Xinlong Gao and Ruijing Huang

Remote Sens. 2026, 18(13), 2265; https://doi.org/10.3390/rs18132265 - 7 Jul 2026

Viewed by 415

Abstract

With the increasing diversity of remote sensing image acquisition conditions and imaging scenarios, building extraction models often experience significant performance degradation in cross-dataset applications due to variations in sensors and scene characteristics. Improving their cross-domain generalization ability has therefore become a critical research [...] Read more.

With the increasing diversity of remote sensing image acquisition conditions and imaging scenarios, building extraction models often experience significant performance degradation in cross-dataset applications due to variations in sensors and scene characteristics. Improving their cross-domain generalization ability has therefore become a critical research problem. To address the challenges of appearance style discrepancy and feature distribution shift in cross-domain building extraction, this paper proposes WCMNet, a wavelet-guided and CNN–Mamba hybrid network for unsupervised domain adaptation in building extraction. Specifically, a Mamba Wavelet Alignment (MWA) module is designed to align low-frequency style information in the wavelet domain while preserving directional high-frequency edge structures, thereby mitigating cross-domain appearance discrepancies and reducing structural degradation during domain translation. In addition, a Global–Local Mamba Block (GLMB) is developed to jointly model local textures and global semantic dependencies. In GLMB, the CNN branch captures fine-grained local details and boundary cues, while the Mamba branch models long-range contextual information; an adaptive gated fusion mechanism further integrates the two types of features. Experimental results on six cross-domain transfer tasks across the WHU, Massachusetts, and Potsdam datasets demonstrate that WCMNet consistently outperforms existing state-of-the-art domain adaptation methods. In particular, WCMNet achieves an average IoU of 65.13% and an average BIoU of 74.80% across all transfer settings, with improvements of up to 27.35 percentage points in IoU and 38.32 percentage points in BIoU compared with the strongest competing methods. These results demonstrate that the proposed MWA and GLMB effectively improve building completeness, boundary delineation accuracy, and cross-domain robustness. Full article

(This article belongs to the Special Issue Intelligent Interpretation of Remote Sensing Images and Intelligent Processing of Remote Sensing Information)

► Show Figures

Figure 1

28 pages, 1549 KB

Open AccessArticle

Few-Shot Remote Sensing Scene Classification via Fusion of Zigzag Scanning Feature Sequence and Riemannian Geometric Barycenter Network

by Xiliang Chen, Longwei Li, Yufeng Chen, Lei Liu, Zhenyu Wang, Mingqing Liu, Xiaojie Liu and Guobin Zhu

Remote Sens. 2026, 18(13), 2264; https://doi.org/10.3390/rs18132264 - 7 Jul 2026

Viewed by 308

Abstract

Few-shot remote sensing scene classification aims to accurately recognize unseen scene categories using only a scarce number of labeled samples, which has emerged as a research hotspot in the field of remote sensing image interpretation. However, remote sensing images intrinsically suffer from large [...] Read more.

Few-shot remote sensing scene classification aims to accurately recognize unseen scene categories using only a scarce number of labeled samples, which has emerged as a research hotspot in the field of remote sensing image interpretation. However, remote sensing images intrinsically suffer from large intra-class variations, high inter-class similarities, and complex background interferences. Traditional few-shot learning methods typically perform feature metric learning in Euclidean space, making it difficult to capture the non-Euclidean geometric distribution characteristics of remote sensing features, and they often neglect the spatial structural information embedded in feature maps. To address these issues, this paper proposes a novel few-shot remote sensing scene classification method, termed ZSFS-RGBN, which integrates a Zigzag Scanning Feature Sequence with a Riemannian Geometric Barycenter Network. Specifically, ResNet12 is first employed as the backbone to extract deep convolutional feature maps from both the support and query sets. Second, a Zigzag scanning strategy is introduced to reorganize the two-dimensional feature maps into one-dimensional feature sequences, thereby effectively preserving the spatial locality and structural continuity of the features. Third, an autoregressive moving average (ARMA) model is constructed to characterize the spatial dependencies of the feature sequences, and its state parameters are mapped onto a symmetric positive definite (SPD) matrix manifold, enabling the deep semantic representations of remote sensing scenes in a non-Euclidean geometric space. Finally, a Riemannian geometric barycenter network is designed to learn the Riemannian barycenter of each category on the SPD manifold, where a joint loss function is introduced to simultaneously optimize intra-class compactness and inter-class separability. Comprehensive experiments are conducted on three public remote sensing scene datasets: NWPU-RESISC45, UC Merced Land-Use, and WHU-RS19. Experimental results demonstrate that the proposed method consistently outperforms several representative state-of-the-art approaches under both 5-way 1-shot and 5-way 5-shot settings. Furthermore, ablation studies verify the effectiveness of each component within the proposed framework. Full article

(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Scene Classification)

► Show Figures

Figure 1

60 pages, 181045 KB

Open AccessArticle

A Scale-Invariance-Based Algorithm Application for Land Surface Temperature Downscaling in Denmark

by Élio Pereira, Manvel Khudinyan, Inês Girão, Bruno Marques, Vitor F. V. V. de Miranda, Hjalte Jomo Danielsen Sørup, Quentin Paletta and Ana Oliveira

Remote Sens. 2026, 18(13), 2263; https://doi.org/10.3390/rs18132263 - 7 Jul 2026

Viewed by 601

Abstract

With an ever-growing recognition of Land Surface Temperature (LST) as a key Essential Climate Variable (ECV), it becomes utmost important to have such a variable at the fine spatial and temporal scales of urban spaces and dynamics. Sentinel-3 provides coarse LST (1 km, [...] Read more.

With an ever-growing recognition of Land Surface Temperature (LST) as a key Essential Climate Variable (ECV), it becomes utmost important to have such a variable at the fine spatial and temporal scales of urban spaces and dynamics. Sentinel-3 provides coarse LST (1 km, daily) based on thermal imagery acquired by its Sea and Land Surface Temperature Radiometer (SLSTR) as well as fine Spectral Directional Reflectances (SDRs, 300 m, every two days) synergically inferred from both SLSTR and the Ocean and Land Colour Instrument (OLCI), which gives the opportunity for using the latter as a predictor in the downscaling of the former. Herein, two scale-invariance-based architectures were developed: a single-timestamp (STS) model, trained with coarse data of the timestamp whose fine target it infers; and a multi-timestamp (MTS) one, trained with multiple timestamps. Note that while several Machine Learning (ML) models besides Linear Regression (LR) were considered for the MTS architecture, only LR was used for the STS one due to the limited amount of available data which the former require for hyperparameter tuning. The models were developed over four Danish Functional Urban Areas (FUAs) using SRD-derived indices and seasonal and geospatial predictors and validated against Landsat data. While Gradient Boosting (GB) achieved the best coarse-scale performance it corresponded to the worst fine-scale performer together with Random Forest (RF), indicating scale invariance breakdown. Tree-based models performed poorly due to extrapolation limitations, whereas Neural Net (NN) and LR proved more robust. After residual correction, single-timestamp LR achieved the best fine-scale performance, making it the most reliable and recommended architecture for operations. The overall results showed that, although ML models may better predict the target at their training scale, their performance may not significantly generalise at others, therefore revealing scale specificity. Furthermore, the results suggested that usage of the more general multi-timestamp architecture instead of the single one may deteriorate performance. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

32 pages, 8738 KB

Open AccessArticle

Cross-Platform Comparison of Marine Boundary Layer Cloud and Drizzle Properties over the Southern Ocean Using Airborne, Shipborne, and Satellite Observations

by Anik Das, Xiquan Dong and Baike Xi

Remote Sens. 2026, 18(13), 2262; https://doi.org/10.3390/rs18132262 - 7 Jul 2026

Viewed by 281

Abstract

Marine boundary layer (MBL) clouds strongly influence radiation and precipitation over the Southern Ocean (SO), yet their vertical structures and microphysical properties remain poorly constrained across observational platforms. This study compares macrophysical and microphysical properties of single-layer, liquid-dominant MBL clouds below 3 km [...] Read more.

Marine boundary layer (MBL) clouds strongly influence radiation and precipitation over the Southern Ocean (SO), yet their vertical structures and microphysical properties remain poorly constrained across observational platforms. This study compares macrophysical and microphysical properties of single-layer, liquid-dominant MBL clouds below 3 km using aircraft observations from the SO Clouds, Radiation, Aerosol Transport Experimental Study (SOCRATES), ship-based observations from Measurements of Aerosols, Radiation, and Clouds over the SO (MARCUS), and satellite observations from CloudSat. An empirical reflectivity–microphysics retrieval framework developed from in situ droplet size distributions (DSDs) measured during SOCRATES was applied to MARCUS M-WACR and CloudSat CPR reflectivity observations to retrieve vertical profiles of number concentration (N), effective radius (r_e), and liquid water content (LWC) for cloud and drizzle particles. Cloud boundary heights and retrieved microphysical properties show broad agreement across the three platforms within the limitations imposed by instrumental sensitivity, sampling differences, and retrieval uncertainties. However, CloudSat CPR observations exhibit larger deviations because of their coarser vertical resolution and lower reflectivity sensitivity, including limited detection of low clouds below ~500 m. The observed vertical structures are consistent with condensational growth, entrainment, and collision–coalescence processes. Overall, the results demonstrate broad consistency in cloud and drizzle properties across the three platforms, while highlighting the impacts of instrumental sensitivity, vertical resolution, and sampling differences on cloud boundary detection and microphysical retrievals. Full article

(This article belongs to the Special Issue Remote Sensing of Aerosol–Cloud–Radiation Interactions and Quantifying Their Impact on Earth’s Energy Budget)

► Show Figures

Figure 1

24 pages, 9501 KB

Open AccessArticle

Phenology-Adaptive Maize Mapping Using an Enhanced Red-Edge NDVI from Sentinel-2 Across Representative Global Agroecosystems

by Han Zhang, Lingbo Yang, Ran Huang, Limin Wang and Jingcheng Zhang

Remote Sens. 2026, 18(13), 2261; https://doi.org/10.3390/rs18132261 - 7 Jul 2026

Viewed by 404

Abstract

Accurate maize distribution information is critical for crop-area statistics, food-security assessment, and agricultural monitoring, but large-scale maize-mapping remains difficult in regions with limited reference samples, heterogeneous crop calendars, and frequent optical data gaps. This study proposes a phenology-adaptive maize mapping framework based on [...] Read more.

Accurate maize distribution information is critical for crop-area statistics, food-security assessment, and agricultural monitoring, but large-scale maize-mapping remains difficult in regions with limited reference samples, heterogeneous crop calendars, and frequent optical data gaps. This study proposes a phenology-adaptive maize mapping framework based on Sentinel-2 time-series imagery and an Enhanced Red-edge NDVI (ENDVIre). ENDVIre was constructed from the Sentinel-2 red-edge 4 and red-edge 2 bands to enhance the spectral response of maize during the silking-to-grain-filling stage, when maize develops a dense canopy and high chlorophyll content but is often confused with soybean. The framework first reconstructed the NDVI time series using an upper-envelope-constrained Whittaker smoother to identify key phenological stages, including sowing–emergence, vigorous growth, and maturity–harvest. NDVI, ENDVIre, and LSWI were then integrated into an interpretable decision-tree model with phenology-aligned time windows to distinguish maize from soybean, rice, wheat, and other non-maize backgrounds. The method was evaluated in six representative maize-growing regions across the United States, Brazil, China, Kenya, and Ukraine, covering different crop calendars, field sizes, and agricultural systems. The mean overall accuracy, F1-score, and Kappa coefficient across the six regions reached 93.27%, 93.14%, and 0.8652, respectively. Cross-year experiments in a winter-wheat–summer-maize rotation region from 2020 to 2024 achieved overall accuracies of 89.80–96.80%, while spatial-transfer experiments in six independent regions achieved overall accuracies of 87.40–95.40%. A comparison with existing high-resolution maize products in the Huang-Huai-Hai Plain further showed that the proposed method better balanced omission and commission errors. These results indicate that ENDVIre-based phenology rules provide an interpretable and transferable solution for maize mapping under limited-sample conditions, although persistent cloud contamination and fragmented smallholder landscapes remain important challenges. Full article

► Show Figures

Figure 1

28 pages, 20617 KB

Open AccessArticle

Spectral Variability and Prediction of Nitrogen, Phosphorus, and Potassium in Fresh Sugarcane (Saccharum officinarum) Leaves by VIS–NIR–SWIR Spectroscopy

by Marta Laura de Souza Alexandre, Izabelle de Lima e Lima, Carlos Augusto Alves Cardoso Silva, Mateus Lima Silva, Rodnei Rizzo and Peterson Ricardo Fiorio

Remote Sens. 2026, 18(13), 2260; https://doi.org/10.3390/rs18132260 - 7 Jul 2026

Viewed by 507

Abstract

This study evaluated the potential of VIS–NIR–SWIR leaf spectroscopy to predict N, P, and K contents in sugarcane, considering spectral variability across two growing seasons (2023/2024 and 2024/2025), phenological stages, and five varieties. Spectral signatures (350–2500 nm) were acquired using a FieldSpec 3 [...] Read more.

This study evaluated the potential of VIS–NIR–SWIR leaf spectroscopy to predict N, P, and K contents in sugarcane, considering spectral variability across two growing seasons (2023/2024 and 2024/2025), phenological stages, and five varieties. Spectral signatures (350–2500 nm) were acquired using a FieldSpec 3 spectroradiometer and processed with MSC, smoothing, and the first Savitzky–Golay derivative. Diagnostic bands were identified by Spearman correlation, and prediction was performed using partial least squares regression (PLSR). PCA showed that spectral variability was driven mainly by seasonal and phenological factors, whereas varietal effects were secondary. In 2023/2024, greater spectral homogeneity was associated with lower predictive performance. In 2024/2025, greater spectral heterogeneity was associated with improved prediction for N (R² = 0.83; RMSE = 0.78 g kg⁻¹) and P (R² = 0.80; RMSE = 0.10 g kg⁻¹). Potassium remained the most challenging nutrient to predict (maximum R² = 0.25), mainly due to its ionic nature and the resulting lack of significant correlation with specific VIS, NIR, and SWIR spectral features. These results indicate strong potential for predicting N and P in fresh sugarcane leaves, although model robustness depends on the extent of spectral variability in the dataset. Full article

(This article belongs to the Special Issue AI-Enabled Precision Agriculture for Crop Monitoring and Yield Prediction Using Remote Sensing Technologies)

► Show Figures

Figure 1

38 pages, 12668 KB

Open AccessArticle

Earth Observation Data and Indigenous Perspectives: Two-Eyed Seeing Approach to Understanding Long-Term Wildfire and Landscape Changes

by Sandeep K. Agrawal, Nilusha P. Y. Welegedara, Tammy Steinwand and Tyanna Steinwand

Remote Sens. 2026, 18(13), 2259; https://doi.org/10.3390/rs18132259 - 7 Jul 2026

Viewed by 376

Abstract

High-latitude regions are witnessing unprecedented wildfires and accelerated warming. This study explored wildfire patterns and land changes within the high-latitude Indigenous Tłı̨chǫ territory in the Northwest Territories, Canada. It used the Two-Eyed Seeing approach, which combines Western science, or Scientific Ecological Knowledge (SEK), [...] Read more.

High-latitude regions are witnessing unprecedented wildfires and accelerated warming. This study explored wildfire patterns and land changes within the high-latitude Indigenous Tłı̨chǫ territory in the Northwest Territories, Canada. It used the Two-Eyed Seeing approach, which combines Western science, or Scientific Ecological Knowledge (SEK), with Indigenous knowledge, or Traditional Ecological Knowledge (TEK). This method integrated Earth observation data with insights from Tłı̨chǫ Elders and officials. We analyzed spatiotemporal variations in burned areas, land surface temperature (LST), albedo, snow cover, soil moisture, and land-cover types. A listening and storytelling session with community Elders provided an in-depth Indigenous perspective. Our findings indicate a concerning shift in wildfire activity on Tłı̨chǫ land, primarily driven by the interplay between climate change and land-cover changes. Land-cover estimates over the past fifteen years indicate that nearly half of the forested areas on Tłı̨chǫ-owned land have been converted to other land-cover types, with shrublands increasing twofold and grasslands expanding tenfold. We observed significant increases in spring and summer LSTs (p < 0.05), alongside decreases in precipitation and snow cover (p < 0.05), consistent with the Elders’ observations. The decline in topsoil moisture, coupled with rising temperatures, has triggered a positive feedback loop in forested areas, intensifying future wildfire risk. The study’s implications extend beyond the Tłı̨chǫ territory, suggesting a broader significance for climate resilience and Indigenous stewardship. It highlights the significance of place-based, integrated research for understanding complex wildfire behavior and land-cover transformations. The study indicates that the Two-Eyed Seeing approach, which weaves local Indigenous knowledge with quantitative Earth observations, not only improves analytical precision but also provides a collaborative framework for developing targeted strategies to mitigate the effects of increasingly severe fire regimes and land-cover changes. Full article

(This article belongs to the Section Earth Observation Data)

► Show Figures

Figure 1

45 pages, 51645 KB

Open AccessArticle

CT-TreeFlow: Probabilistic Groundwater-Potential Mapping Using Remote Sensing-Derived Environmental Predictors in Karst Aquifers

by Saeid Pourmorad, Mostafa Kabolizade, Rui Ferreira, Samira Abbasi and Luca Antonio Dimuccio

Remote Sens. 2026, 18(13), 2258; https://doi.org/10.3390/rs18132258 - 7 Jul 2026

Viewed by 622

Abstract

Groundwater-potential assessment in karst aquifers is complicated by pronounced spatial heterogeneity driven by structural permeability, lithological variability, recharge redistribution, and unresolved subsurface conduit connectivity. Although machine-learning approaches have improved regional groundwater mapping, most existing models provide only deterministic predictions and offer limited information [...] Read more.

Groundwater-potential assessment in karst aquifers is complicated by pronounced spatial heterogeneity driven by structural permeability, lithological variability, recharge redistribution, and unresolved subsurface conduit connectivity. Although machine-learning approaches have improved regional groundwater mapping, most existing models provide only deterministic predictions and offer limited information on predictive uncertainty and hydrogeological reliability. To address this limitation, we propose CT-TreeFlow. This probabilistic groundwater assessment framework goes beyond conventional machine-learning models by explicitly learning the full conditional probability distribution of groundwater favourability rather than a single deterministic estimate. The framework integrates sparse probabilistic environmental routing, conditional density estimation, hydrogeologically constrained pseudo-absence generation, geographically structured spatial validation, and explainability-driven interpretation within a unified modelling architecture, enabling simultaneous groundwater prediction, uncertainty quantification, and hydrogeological interpretation. The framework was applied to the Zagros karst system in Khuzestan Province, Iran, using remote-sensing-derived environmental predictors, Copernicus DEM-based morphometric variables, geological–structural datasets, and hydroclimatic indicators. Performance was evaluated against LightGBM and XGBoost using GroupKFold spatial cross-validation. CT-TreeFlow achieved a mean RMSE of 2.737 and a mean R² of 0.852, while also providing spatially explicit uncertainty estimates and probabilistic prediction intervals. Explainability analyses identified fracture density, lithology, drainage organisation, and terrain-controlled recharge conditions as the dominant controls on groundwater favourability. Predicted high-favourability zones showed strong spatial correspondence with major carbonate formations and independent spring–cave inventories, supporting the hydrogeological plausibility of the mapped patterns. These results demonstrate that probabilistic modelling can provide more reliable and physically interpretable groundwater assessments than deterministic approaches in structurally complex karst environments. CT-TreeFlow offers a transferable framework for uncertainty-aware groundwater exploration and regional hydrogeological decision support in heterogeneous aquifer systems. Full article

► Show Figures

Figure 1

37 pages, 38488 KB

Open AccessArticle

UAV-Based Photogrammetric Inspection in Deep Vertical Shafts: A Case Study from the KGHM GG-1 Mineshaft in Poland

by Wojciech Rutkowski, Jędrzej Szczepaniak, Tomasz Lipecki and Antoni Rzonca

Remote Sens. 2026, 18(13), 2257; https://doi.org/10.3390/rs18132257 - 7 Jul 2026

Viewed by 377

Abstract

Underground mining operations depend heavily on vertical shafts for access, ventilation, and ore transport, making their structural integrity and safety critical to overall mine performance. Traditional shaft inspections, though rigorous, are limited by human accessibility, environmental hazards, and subjective evaluation. This study presents [...] Read more.

Underground mining operations depend heavily on vertical shafts for access, ventilation, and ore transport, making their structural integrity and safety critical to overall mine performance. Traditional shaft inspections, though rigorous, are limited by human accessibility, environmental hazards, and subjective evaluation. This study presents the development and initial testing of a novel unmanned aerial vehicle (UAV) system designed specifically for shaft inspections in deep mining environments. The research focuses on the GG-1 shaft in Kwielice, Poland—the country’s deepest operational shaft—where challenging conditions such as high ventilation airflow, confined geometry, and absence of GNSS signals necessitated innovative solutions. A custom-built hexacopter equipped with high-resolution cameras and photogrammetric capabilities was deployed to capture detailed visual and spatial data. This article presents complementary path of UAV evolution, from concept, early development stage and results without positioning system through to the description of final results including positioning system and all six cameras until results of high-altitude flights. Results demonstrate that UAV-based inspection can deliver sufficient precision for identifying structural irregularities, documenting shaft infrastructure, and enhancing safety monitoring. The findings highlight the potential of UAV technology as a complementary tool to conventional inspections, offering improved data quality, reduced risk to personnel, and a new approach to shaft maintenance. Full article

(This article belongs to the Special Issue 3D Computer Vision for Remote Sensing: Point Clouds, Reconstruction and Scene Understanding)

► Show Figures

Figure 1

37 pages, 48009 KB

Open AccessArticle

Filling Satellite Microwave Observation Gaps via Generative Synthesis

by Han Du, Baoxiang Pan, Fan Ping, Jin Xu, Congyi Nai, Sencan Sun, Jie Chao, Jingnan Wang, Shangshang Yang, Xi Chen, Jingyuan Li, Jiahua Mao, Lei Yin, Yupeng Li and Ziniu Xiao

Remote Sens. 2026, 18(13), 2256; https://doi.org/10.3390/rs18132256 - 7 Jul 2026

Viewed by 552

Abstract

Polar-orbiting microwave radiometers provide indispensable all-weather measurements of the atmospheric state, yet revisit intervals of many hours leave critical gaps during rapidly evolving weather events. To address this limitation, we developed MIDAS (Microwave Inference via Diffusion Across Satellites), a probabilistic framework that estimates [...] Read more.

Polar-orbiting microwave radiometers provide indispensable all-weather measurements of the atmospheric state, yet revisit intervals of many hours leave critical gaps during rapidly evolving weather events. To address this limitation, we developed MIDAS (Microwave Inference via Diffusion Across Satellites), a probabilistic framework that estimates microwave brightness temperature (BT) fields across the geostationary full-disk domain from infrared observations at 10 min intervals. This study focuses on the five Microwave Humidity Sounder-2 (MWHS-2) humidity-sounding channels near 183 GHz, which provide vertically resolved water vapor information. MIDAS achieves relative errors below 0.5% for the majority of cases, with a channel-averaged mean absolute error of 1.15 K, outperforming a deterministic U-Net baseline (1.43 K). Beyond per-sample evaluation, MIDAS reproduces large-scale climatological patterns across the full-disk domain over a three-month summer period, consistent with Radiative Transfer for TOVS–Scattering (RTTOV-SCATT) simulations. In deep convective scenes where reconstruction is most difficult, the ensemble spread naturally tracks reconstruction difficulty, providing a built-in indicator of prediction confidence. Notably, MIDAS incorporates real-time polar-orbiting observations as physical constraints via a merge-sampling mechanism, reducing ensemble RMSE by over 20% and improving probabilistic calibration by more than 30%. Proof-of-concept assimilation experiments for two high-impact weather cases show that MIDAS-generated fields yield forecast improvements comparable to those from real satellite observations, reducing tropical cyclone track errors from approximately 110 km to 40 km and improving heavy precipitation forecasts at extreme rainfall thresholds where direct infrared assimilation shows no benefit. Overall, our framework demonstrates the potential of generative models to supplement sparse observational coverage and provide physically plausible microwave humidity fields for downstream applications. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

28 pages, 22183 KB

Open AccessArticle

Deep Learning Enables the Automatic Mapping of Tell Sites on Satellite Synthetic Aperture Radar Products

by Elena Chiricallo, Giulio Poggi, Sara Ferro, Sebastiano Vascon and Arianna Traviglia

Remote Sens. 2026, 18(13), 2255; https://doi.org/10.3390/rs18132255 - 7 Jul 2026

Viewed by 535

Abstract

Satellite Synthetic Aperture Radar (SAR) is an established technology for studying and monitoring archaeological landscapes, providing insights into surface morphology and the presence of near subsurface features. However, its application in large-scale archaeological prospection is limited by the lack of robust, automated methods [...] Read more.

Satellite Synthetic Aperture Radar (SAR) is an established technology for studying and monitoring archaeological landscapes, providing insights into surface morphology and the presence of near subsurface features. However, its application in large-scale archaeological prospection is limited by the lack of robust, automated methods for SAR data analysis. This study introduces a novel Deep Learning pipeline to automatically detect and segment archaeological settlement mounds, known as tells, in central Iraq on satellite SAR data. The pipeline leverages a state-of-the-art supervised method for instance segmentation, YOLOv8-Seg, and medium-resolution satellite SAR products, specifically the Copernicus Sentinel-1 Interferometric Wide Swath Mode Ground Range Detected and Copernicus Global 30-m Digital Elevation Model products. The model identifies tell sites with an Average Precision of

0.495 \pm 0.010

and a pixel-wise Intersection over Union of

0.361 \pm 0.048

over the test areas. Archaeological interpretation of the model’s inferences confirms its reliability in locating and segmenting archaeological sites, leading also to the identification of previously unmapped potential sites. After a main test in central Iraq, the proposed workflow demonstrates promising transferability to a nearby test area in Iran, although with a need for regional fine-tuning to account for inherent variations in feature morphology and environmental context. This research establishes a baseline for future Deep Learning applications in Synthetic Aperture Radar-based archaeological prospection. Full article

► Show Figures

Figure 1

27 pages, 27271 KB

Open AccessArticle

Reconstruction of Land Surface Temperature Based on EATC Constraints and Spatially Adaptive Residual Correction: A Case Study of the Qinghai–Tibet Engineering Corridor

by Minghan Xu, Qian Li, Shufang Tian, Shiqi Kuang and Tianqi Li

Remote Sens. 2026, 18(13), 2254; https://doi.org/10.3390/rs18132254 - 7 Jul 2026

Viewed by 419

Abstract

Satellite-based land surface temperature (LST) products are frequently affected by cloud cover and atmospheric conditions, resulting in missing data that significantly limits the continuous monitoring of the thermal environment in complex terrains, such as the Tibetan Plateau. Existing spatiotemporal interpolation methods face clear [...] Read more.

Satellite-based land surface temperature (LST) products are frequently affected by cloud cover and atmospheric conditions, resulting in missing data that significantly limits the continuous monitoring of the thermal environment in complex terrains, such as the Tibetan Plateau. Existing spatiotemporal interpolation methods face clear accuracy limitations when addressing extensive data gaps, while physical models often struggle due to insufficient meteorological inputs in complex landscapes. Moreover, conventional data-driven approaches usually overlook local spatial variations, resulting in smoothed thermal patterns and systematic errors. To overcome these issues, we propose a Physically Constrained Spatial Residual Learning framework. In this framework, we use the Enhanced Annual Temperature Cycle (EATC) model to capture the temporal baseline of LST first. Then, we integrate multi-source auxiliary data into the Geographical-XGBoost (G-XGBoost) algorithm to model spatial nonlinear residuals. Using simulated cloud masks on the 2017 MODIS LST dataset from the Qinghai–Tibet Engineering Corridor, we show that the hybrid model outperforms both individual physical models and global machine learning models in accuracy and spatial detail recovery. Validation results yield an R² of 0.88, an RMSE of 1.92 K, and a mean bias of 0.07 K. Seasonal evaluations indicate best performance in winter (RMSE = 1.19 K) with robust performance in summer. Furthermore, the framework reduces boundary artifacts and accurately reproduces thermal spatial patterns in complex terrain through adaptive local bandwidth and weight adjustments. This approach provides a reliable method for high-precision LST reconstruction over heterogeneous alpine surfaces. Full article

(This article belongs to the Special Issue Intelligent Interpretation of Remote Sensing Imagery: AI-Enhanced Monitoring of Geographical and Geological Environments)

► Show Figures

Figure 1

24 pages, 5363 KB

Open AccessArticle

Simulation of BepiColombo’s Gravity Investigation with Dynamical Mismodeling

by Ariele Zurria, Ivan di Stefano, Paolo Cappuccio, Umberto De Filippis and Luciano Iess

Remote Sens. 2026, 18(13), 2253; https://doi.org/10.3390/rs18132253 - 7 Jul 2026

Viewed by 436

Abstract

The BepiColombo spacecraft, designed by ESA and JAXA, is currently in its cruise phase toward Mercury. Among the scientific investigations is the Mercury Orbiter Radio-science Experiment (MORE), which will exploit a multi-frequency microwave tracking system with an advanced Ka-band transponder to achieve its [...] Read more.

The BepiColombo spacecraft, designed by ESA and JAXA, is currently in its cruise phase toward Mercury. Among the scientific investigations is the Mercury Orbiter Radio-science Experiment (MORE), which will exploit a multi-frequency microwave tracking system with an advanced Ka-band transponder to achieve its objectives pertaining to Mercury’s geodesy and fundamental physics. Leveraging precise measurements from this state-of-the-art radio tracking system, MORE is expected to provide new insights into Mercury’s interior, refining and expanding upon the findings of the MESSENGER mission. This work evaluates the performance of MORE’s gravity and rotation experiment, specifically assessing how BepiColombo’s improved radio tracking data can reduce uncertainties in the determination of Mercury’s gravity field, Love number

k_{2}

, and rotational state. Differently from previous covariance analyses, this work includes errors in the dynamical model to assess the experiment’s performance under controlled mismodeling conditions. We present the results of a numerical simulation covering BepiColombo’s extended two-year orbital phase, with scientific operations set to begin in 2027. Full article

(This article belongs to the Special Issue Precise Orbit Determination for Gravity Field Investigations)

► Show Figures

Figure 1

18 pages, 6977 KB

Open AccessArticle

Realistic Error Budget and Cross-Validation of Sentinel-1 3D Displacement for the 2025 Dingri Earthquake

by Zhangdi Xie

Remote Sens. 2026, 18(13), 2252; https://doi.org/10.3390/rs18132252 - 7 Jul 2026

Viewed by 385

Abstract

This study presents a systematic uncertainty quantification of the two-track InSAR three-dimensional (3D) deformation field of the 2025 Dingri earthquake (Mw 7.1). Using Sentinel-1 ascending and descending track data, a 3D coseismic displacement field was constructed via least-squares inversion. The results revealed that [...] Read more.

This study presents a systematic uncertainty quantification of the two-track InSAR three-dimensional (3D) deformation field of the 2025 Dingri earthquake (Mw 7.1). Using Sentinel-1 ascending and descending track data, a 3D coseismic displacement field was constructed via least-squares inversion. The results revealed that the earthquake produced a north–south-striking normal fault rupture, with the vertical component reaching a maximum subsidence of −403.3 mm and a maximum uplift of +621.1 mm, and the east–west component reaching a maximum westward displacement of −592.3 mm and an eastward displacement of +332.1 mm. Uncertainty analysis reveals a divergence between formal errors and actual accuracy: formal error propagation yields 1σ uncertainties of 1.09 mm and 1.38 mm for the vertical and east–west components, respectively; a realistic error budget based on Monte Carlo simulations indicates that the actual errors are approximately 13.8 mm for the vertical component and 17.2 mm for the east–west component, with systematic error contributions far exceeding random noise. Cross-validation against an independent Sentinel-1 processing chain supports the above error assessment: the correlation coefficient R for ascending track line-of-sight (LOS) displacement is 0.88, whereas it is 0.62 for the descending track; for the three-dimensional components, R reaches 0.88 for the vertical component and 0.59 for the east–west component, with discrepancies arising primarily from the greater sensitivity of the east–west component to processing strategies and observation geometry. This study demonstrates that formal error propagation underestimates the actual uncertainty of two-track InSAR inversion and that systematic error sources contribute far more than random noise does. Full article

(This article belongs to the Special Issue Recent Advances in InSAR for Deformation Monitoring and Earth Surface Process Analysis)

► Show Figures

Figure 1

22 pages, 63201 KB

Open AccessArticle

A Sentinel-2-Based Framework for Methane Point-Source Detection and Quantification Using Low-Reflectance Artifact Detection

by Kun Cai, Tiansheng Chen, Liang Zheng, Shenshen Li, Xinhui Zhou, Yunchen Liu and Xinglong Chen

Remote Sens. 2026, 18(13), 2251; https://doi.org/10.3390/rs18132251 - 7 Jul 2026

Viewed by 467

Abstract

Methane (CH₄) is the second most significant greenhouse gas after carbon dioxide (CO₂). Due to its high short-term global warming potential and the feasibility of emission abatement, monitoring methane point-source emissions has become a critical strategy for mitigating climate [...] Read more.

Methane (CH₄) is the second most significant greenhouse gas after carbon dioxide (CO₂). Due to its high short-term global warming potential and the feasibility of emission abatement, monitoring methane point-source emissions has become a critical strategy for mitigating climate change. To address existing technical bottlenecks associated with spatial coverage limitations and surface-induced signal interference in satellite-based monitoring, this study proposes an integrated methane monitoring framework termed Multi-Band Multi-Constraint (MBMC) using Sentinel-2 MSI imagery. The MBMC framework combines a Low-Reflectance Artifact Detection (LRAD) algorithm, a Multi-Band Multi-Pass (MBMP) differential absorption retrieval model, and Integrated Mass Enhancement (IME)-based emission quantification. The LRAD module effectively suppresses artifacts caused by low-reflectance surfaces and heterogeneous backgrounds, thereby improving the signal-to-noise ratio (SNR) and retrieval accuracy of methane column enhancements. In addition, a semi-automatic plume segmentation workflow integrating morphological operations with a spatial database is developed to improve methane plume extraction and source localization. The framework was validated using data from single-blind controlled methane release experiments conducted in Arizona, USA. Results show that the proposed method achieved a mean absolute percentage error (MAPE) of 21.6% for emission rates ranging from 0.5 to 3.0 t/h, demonstrating promising performance for Sentinel-2-based screening and quantification of methane point sources, particularly for emissions above approximately 0.5 t/h under favorable observation conditions. The framework was further applied to Sentinel-2 observations over a natural gas field in Northwest China, where multiple methane point sources associated with gas gathering stations were successfully identified and quantified. The proposed framework provides a practical approach for high-resolution and high-frequency satellite monitoring of methane point sources and supports the refinement of methane emission inventories and mitigation strategies in the oil and gas sector. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

22 pages, 7908 KB

Open AccessArticle

An Adaptive Wet Tropospheric Correction Method Using a Spaceborne Microwave Radiometer

by Xiaomeng Zheng, Yuhang Li, Jin Zhao, Jieying He and Dehai Zhang

Remote Sens. 2026, 18(13), 2250; https://doi.org/10.3390/rs18132250 - 7 Jul 2026

Viewed by 342

Abstract

High-precision WTC is essential for satellite altimetry and ocean dynamic environment monitoring. Existing WTC approaches often rely on globally unified statistical frameworks, which inadequately represent wind-speed-dependent nonlinear sea-surface microwave radiative responses and are prone to systematic bias under uneven observation distributions. To address [...] Read more.

High-precision WTC is essential for satellite altimetry and ocean dynamic environment monitoring. Existing WTC approaches often rely on globally unified statistical frameworks, which inadequately represent wind-speed-dependent nonlinear sea-surface microwave radiative responses and are prone to systematic bias under uneven observation distributions. To address these limitations, this study proposes an adaptive WTC method integrating overlapping wind-regime modeling, multi-scale collaborative sample balancing, and a model soft-fusion strategy. Firstly, a modeling framework with overlapping transition zones for low-, moderate-, and high-wind-speed regimes is established according to wind-speed-driven variations in sea-surface radiative responses, and sub-models are trained independently. Subsequently, a multi-scale sample balancing, combining global and local weights, is designed to enhance learning from sparse samples. Finally, a soft-fusion strategy based on a trapezoidal membership function is applied to dynamically weight sub-model outputs, ensuring retrieval continuity across transition zones. Using HY-2C Calibration Microwave Radiometer (CMR) observations, the proposed method is developed, trained, and evaluated against model-derived WTC and collocated Jason-3 AMR-2 measurements. Results show that the proposed method improves overall WTC retrieval accuracy and stability while effectively reducing systematic biases under wind-speed regimes with sparse observations, providing an effective and robust approach for high-accuracy WTC retrieval under various wind-speed conditions. Full article

(This article belongs to the Special Issue Microwave Remote Sensing on Ocean Observation)

► Show Figures

Figure 1

17 pages, 9655 KB

Open AccessArticle

Spatial-Temporal Evolution of Proglacial Lake Volumes and Estimation Models in the Himalaya and Nyainqentanglha Ranges

by Miaohui Zhang, Hao Wang, Peng Cui, Jinbo Tang, Yilong Yu, Jingxuan Cao, Xuan Liu, Jingxi Yang, Yunpeng Liu and Qingchun Li

Remote Sens. 2026, 18(13), 2249; https://doi.org/10.3390/rs18132249 - 7 Jul 2026

Viewed by 380

Abstract

Volume quantification of proglacial lakes is a fundamental prerequisite for reliable hydrodynamic modeling and peak discharge estimation during glacial lake outburst floods (GLOFs). In this study, we integrated in situ bathymetric surveys of 10 proglacial lakes across the Himalaya and Nyainqentanglha ranges with [...] Read more.

Volume quantification of proglacial lakes is a fundamental prerequisite for reliable hydrodynamic modeling and peak discharge estimation during glacial lake outburst floods (GLOFs). In this study, we integrated in situ bathymetric surveys of 10 proglacial lakes across the Himalaya and Nyainqentanglha ranges with a comprehensive regional dataset to derive optimized empirical models for lake volume and maximum depth. The predictive robustness of these models was rigorously validated using statistical error metrics and independent datasets. Comparative analysis with 14 established formulas demonstrates that our region-specific models yield superior performance in capturing local geomorphological characteristics. Leveraging these refined scaling relationships, we reconstructed the spatiotemporal volume changes in proglacial lakes across the study region from 1990 to 2020. Our analysis reveals significant lake expansion over the past three decades: lake volumes in the Western and Central Himalayas increased by 46.7% and 46.4%, respectively. Notably, the Eastern Himalayas exhibited a volume increase of 51.5%, while the Nyainqentanglha Mountains experienced a substantial expansion of approximately 92.9%. These findings provide critical parametric constraints for satellite-based hydrological monitoring and significantly enhance the reliability of GLOF hazard assessments in the Himalaya and Nyainqentanglha ranges. Full article

(This article belongs to the Section Remote Sensing in Geology, Geomorphology and Hydrology)

► Show Figures

Figure 1

23 pages, 38044 KB

Open AccessArticle

Estimation of High-Resolution Multi-Layer Soil Moisture Using Land Data Assimilation and the Three-Cornered Hat Method

by Xinlei He, Wenbin Zhu, Shaomin Liu, Tongren Xu, Zhitao Wu, Sayed M. Bateni, Zhen Hao, Xiang Li, Dongxin Wu and Hanxue Liang

Remote Sens. 2026, 18(13), 2248; https://doi.org/10.3390/rs18132248 - 7 Jul 2026

Viewed by 406

Abstract

Soil moisture (SM) plays a pivotal role in regulating terrestrial energy-water exchanges and exerts substantial influence on agricultural productivity. In this study, a high-resolution soil moisture (HRSM) dataset (16 m) was generated by integrating multi-source remote sensing data from SMAP, HJ-2, Sentinel-2, and [...] Read more.

Soil moisture (SM) plays a pivotal role in regulating terrestrial energy-water exchanges and exerts substantial influence on agricultural productivity. In this study, a high-resolution soil moisture (HRSM) dataset (16 m) was generated by integrating multi-source remote sensing data from SMAP, HJ-2, Sentinel-2, and Gaofen-6, together with the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model. The data assimilation (DA) method was implemented for assimilating HRSM within the Ensemble Kalman Filter (EnKF) framework using the Noah-MP model at a spatial resolution of 1 km. To enhance the spatial detail of SM, HRSM and its relative uncertainties derived from the three-cornered hat (TCH) method were used to update the observation error and Kalman gain in the EnKF framework, thereby improving SM profile estimates at a 16 m resolution. The performance of the DA method was evaluated against in situ measurements during the spring drought period in central Yunnan Province, China. The results show that assimilating HRSM (DA_HRSM) significantly improves surface and root-zone SM estimates in the Noah-MP model. The simulated SM from the DA_HRSM method demonstrates lower relative uncertainty. Compared to the assimilation of SMAP SM, the DA_HRSM method provides higher-resolution spatial features of SM and enhances spatial heterogeneity across 20 irrigation districts. The DA_HRSM method effectively captured the spring drought in central Yunnan, demonstrating good agreement with the Palmer Drought Severity Index (PDSI). The result highlights the advantages of incorporating high-resolution SM data into agricultural and drought monitoring systems. Full article

(This article belongs to the Special Issue Remote Sensing of Forests, Grasslands, and Lakes and Their Interactions)

► Show Figures

Figure 1

34 pages, 24430 KB

Open AccessArticle

Physically Consistent SAR Image Generation for Unseen Aspect Angles via Attributed Scattering Center Evolution

by Zihao Jiang, Chao Liu, Zhangzeyu Xing, Yamei Wang and Shuwen Xiao

Remote Sens. 2026, 18(13), 2247; https://doi.org/10.3390/rs18132247 - 7 Jul 2026

Viewed by 471

Abstract

Synthetic aperture radar (SAR) target images are highly sensitive to aspect angle, while practical data acquisition usually provides only sparse observations over limited viewpoints. This leads to severe data scarcity at unseen aspect angles and makes cross-angle generation prone to scattering-structure distortion and [...] Read more.

Synthetic aperture radar (SAR) target images are highly sensitive to aspect angle, while practical data acquisition usually provides only sparse observations over limited viewpoints. This leads to severe data scarcity at unseen aspect angles and makes cross-angle generation prone to scattering-structure distortion and background statistical mismatch. Existing SAR image generation methods either focus on distribution matching without sufficiently exploiting scattering-related structural cues, or emphasize angle conditioning while failing to jointly preserve physically plausible dominant scattering-response variations and realistic background speckle statistics at unseen aspect angles. To address this issue, we propose a physically consistent framework for SAR image generation at unseen aspect angles. The proposed method introduces an ASC-inspired sparse scattering-structure prior to approximate the dominant scattering responses in the SAR image plane. Rather than performing full parametric ASC inversion, this prior serves as a differentiable and angle-aware structural proxy that guides the generator toward synthesizing SAR images with structurally plausible scattering layouts. In addition, a dual-consistency scheme is introduced to jointly enforce target-region scattering consistency and background-region statistical consistency, thereby improving the physical realism of the generated results in both the target and background regions. Extensive experiments under strict unseen-angle interpolation and hold-out protocols demonstrate that the proposed method consistently outperforms representative baselines in image fidelity, target-region scattering consistency, background statistical consistency, and angle-conditioned consistency. Further visualization and ablation studies verify the critical role of the ASC-inspired sparse scattering-structure prior in physically consistent SAR view completion. Full article

(This article belongs to the Special Issue AI-Driven Remote Sensing Image Restoration and Generation)

► Show Figures

Figure 1

27 pages, 18480 KB

Open AccessArticle

The Impact of Dynamic Observation Error and Hydrometeor Control Variables on GK-2A AMI All-Sky Radiance Assimilation

by Seo-Youn Jo and Ki-Hong Min

Remote Sens. 2026, 18(13), 2246; https://doi.org/10.3390/rs18132246 - 7 Jul 2026

Viewed by 345

Abstract

Assimilation of all-sky radiance (ASR) observations informs atmospheric states and cloud distributions; however, it does not always lead to improved analyses or forecasts. In particular, directly updating hydrometeor fields introduces substantial uncertainty into ASR assimilation. This study examines the impact of dynamic observation [...] Read more.

Assimilation of all-sky radiance (ASR) observations informs atmospheric states and cloud distributions; however, it does not always lead to improved analyses or forecasts. In particular, directly updating hydrometeor fields introduces substantial uncertainty into ASR assimilation. This study examines the impact of dynamic observation errors on analyses and precipitation forecasts under different hydrometeor control variable (HCV) configurations. Observation errors are prescribed using a fifth-order polynomial model as a function of a cloud impact parameter, allowing spatiotemporally varying (i.e., scene-dependent) errors that adapt to cloud conditions. Results indicate that dynamic observation errors generally improve cloud analyses and associated thermodynamic fields. By contrast, constant errors tend to overweight ASR observations in heavily cloud-affected regions, thereby degrading analysis quality. The advantages of dynamic errors are more pronounced when solid-phase hydrometeors are included in the HCV, as these strongly influence brightness temperature (BT) analysis and the representation of convective cloud tops. Among all experiments, those combining dynamic errors with direct updates of solid-phase hydrometeors produce the most realistic BT and reflectivity analyses, as well as the greatest improvements in precipitation forecasts. These results underscore the importance of cloud-dependent observation error modeling in ASR assimilation, particularly when solid-phase HCVs are employed. Full article

► Show Figures

Figure 1

33 pages, 39435 KB

Open AccessArticle

Stereo Matching in Satellite Imagery: A Depth Estimation Foundation Model-Assisted Iterative Approach

by Kunpeng Hu and Wei Zhao

Remote Sens. 2026, 18(13), 2245; https://doi.org/10.3390/rs18132245 - 7 Jul 2026

Viewed by 407

Abstract

In optical remote sensing 3D reconstruction, high-resolution satellite stereo matching is a critical task, yet it is challenged by extreme imaging geometries, texture-less and repetitive patterns, occlusions, and scene variations caused by spatio-temporal heterogeneity. To address these issues, we propose IFMA-Stereo, an innovative [...] Read more.

In optical remote sensing 3D reconstruction, high-resolution satellite stereo matching is a critical task, yet it is challenged by extreme imaging geometries, texture-less and repetitive patterns, occlusions, and scene variations caused by spatio-temporal heterogeneity. To address these issues, we propose IFMA-Stereo, an innovative binocular disparity estimation method that leverages a monocular depth foundation model. Our approach constructs a multi-scale spatial information pyramid to jointly integrate the foundation model with a disparity extraction network. At the feature level, an attention interaction mechanism captures multi-dimensional contextual dependencies and transforms general scene understanding priors into long-range associative features suitable for stereo cost volume construction. At the pixel level, a cyclic iterative refinement module embeds depth information from the foundation model throughout the iteration process and performs joint optimization, enhancing the model’s adaptability in geometrically complex regions. Experiments on the US3D and GaoFen-7 datasets demonstrate that IFMA-Stereo achieves superior performance in challenging areas (texture-less regions, disparity discontinuities, repetitive patterns) and effectively mitigates prediction errors caused by spatio-temporal heterogeneity, albeit at the cost of increased inference time compared to baseline methods. Quantitatively, the method achieves an end-point error (EPE) of 1.347 and a D1 error of 7.26% on the US3D dataset, and an EPE of 1.585 and a D1 error of 13.41% on the GaoFen-7 dataset. Notably, the method also yields precise predictions for unseen urban areas, indicating strong generalization. These results confirm that IFMA-Stereo achieves state-of-the-art accuracy in remote sensing disparity estimation. Full article

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

► Show Figures

Figure 1

26 pages, 19234 KB

Open AccessArticle

On the Spectral–Phenological Features for Crop Mapping Under Complex Planting Patterns: A Case Study in Jiangsu Province, China

by Ziyin You, Jiajun Wu, Xinrui Wang, Bo Wang, Xuan Xu, Pei Zhan, Nan Li and Chitfai Yan

Remote Sens. 2026, 18(13), 2244; https://doi.org/10.3390/rs18132244 - 7 Jul 2026

Viewed by 459

Abstract

Accurate crop mapping in fragmented agricultural landscapes is challenged by overlapping crop calendars and redundancy among multi-source time-series variables. Using Sentinel-1/2 imagery from December 2022 to December 2023, we constructed 275 season-specific spectral–phenological feature–month variables (125 for summer crops and 150 for winter [...] Read more.

Accurate crop mapping in fragmented agricultural landscapes is challenged by overlapping crop calendars and redundancy among multi-source time-series variables. Using Sentinel-1/2 imagery from December 2022 to December 2023, we constructed 275 season-specific spectral–phenological feature–month variables (125 for summer crops and 150 for winter crops) for rice, maize, soybean, winter wheat, and winter rapeseed in Jiangsu Province, China. An auxiliary binary Random Forest (RF) was used to estimate out-of-bag (OOB) permutation-based predictive contributions and construct search priors. A prior-guided genetic algorithm (GA) then identified compact subsets, with crop-specific five-class RF models used both to evaluate candidate subsets and to produce the final classifications. A fixed stratified 80/20 development–validation split was maintained throughout the analysis, with the validation subset reserved for final assessment. August and April were the principal discriminative periods for summer and winter crops, respectively, while VH backscatter and SWIR-related indices, particularly STI and NDTI, showed recurrent predictive contributions across crops. On the independent validation subset, the optical/vegetation-index scheme, SAR-only scheme, and the complete feature library achieved mean target-crop

F_{1}

-scores of 78.42%, 83.74%, and 86.96%, respectively. The GA-selected subsets retained 9–39 variables and achieved a mean five-class overall accuracy of 91.77% and a mean target-crop

F_{1}

-score of 93.95%. After non-target classes were merged into a single background class, the integrated seasonal maps achieved overall accuracies of 81.20–95.03% on the same validation subset. Supplementary classifier comparisons indicated that subset effects depended on the crop and learning algorithm. The findings support crop-specific, interpretable dimensionality reduction within the RF workflow, while broader transferability requires multi-year and multi-region evaluation. Full article

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

► Show Figures

Figure 1

24 pages, 20492 KB

Open AccessArticle

Multi-Scale Assessment of Nighttime Heat Health Risk and Dominant Factors Using MODIS and SDGSAT-1 Observations

by Zhuang Tan, Qixia Man, Baolei Zhang, Pinliang Dong, Haiying Sun, Zhongchang Sun, Linlin Lu, Changyong Dou, Xinming Yang, Changyin Han, Cong Zhou, Xiaoqi Sun, Jian Wang and Zizhen Li

Remote Sens. 2026, 18(13), 2243; https://doi.org/10.3390/rs18132243 - 7 Jul 2026

Cited by 1 | Viewed by 450

Abstract

Climate change is amplifying heat-related health risks, making heat health risk assessment increasingly important for sustainable urban development. However, current studies still face three challenges: (1) macro-scale and fine-scale assessments remain weakly linked; (2) nighttime heat health risk has received limited attention; and [...] Read more.

Climate change is amplifying heat-related health risks, making heat health risk assessment increasingly important for sustainable urban development. However, current studies still face three challenges: (1) macro-scale and fine-scale assessments remain weakly linked; (2) nighttime heat health risk has received limited attention; and (3) dominant factor identification remains insufficient, especially within the Local Climate Zone (LCZ) framework. To address these gaps, this study developed a hazard–exposure–vulnerability-based, multi-scale framework for assessing nighttime heat health risk in Shandong Province, China. At the macro scale, MODIS nighttime land surface temperature (1 km) was used to characterize heat hazard, and district-level risk was assessed by integrating socio-statistical data. Hotspot analysis was then applied to identify high-risk clusters and select cities for fine-scale assessment. At the fine scale, SDGSAT-1 thermal infrared data (30 m) were used to characterize intra-urban nighttime heat hazard, and block-level risk was assessed by integrating socioeconomic and urban infrastructure data. Dominant risk factors were further identified for each spatial unit. Results show that (1) at the macro scale, high nighttime heat health risk districts are concentrated mainly in southern Shandong and major urban cores; (2) at the fine scale, overall risk is higher in inland cities than in the coastal city, and the inland cities show similar spatial patterns; (3) at both district and block units, higher risk levels are associated with more complex dominant factor configurations; and (4) compact high- and mid-rise zones (LCZ 1–2) are mainly characterized by multiple dominant factors, whereas open low-rise/sparsely built zones (LCZ 6/9) are mainly characterized by no dominant factor. This study provides a multi-level perspective for heat-risk governance, offers a scientific basis for both macro-scale policy formulation and fine-scale intervention, and contributes to more sustainable and resilient cities. Full article

(This article belongs to the Topic Applications of Spatial Science and Technology in Health Research, 2nd Edition)

► Show Figures

Figure 1

22 pages, 4937 KB

Open AccessArticle

Mapping Evapotranspiration Patterns in the Desert-Oasis Ecotone Using UAV-Based Thermal Infrared Imagery with a Three-Temperature Model

by Siying Li, Yuhua Xing, Dapeng Zhang and Pei Wang

Remote Sens. 2026, 18(13), 2242; https://doi.org/10.3390/rs18132242 - 7 Jul 2026

Viewed by 318

Abstract

Evapotranspiration (ET) estimation in desert-oasis ecotones remains challenging due to sparse meteorological observations and the coarse spatial resolution of satellite remote sensing, which limit the ability to resolve highly heterogeneous surface conditions. To address this issue, this study develops a high-resolution ET estimation [...] Read more.

Evapotranspiration (ET) estimation in desert-oasis ecotones remains challenging due to sparse meteorological observations and the coarse spatial resolution of satellite remote sensing, which limit the ability to resolve highly heterogeneous surface conditions. To address this issue, this study develops a high-resolution ET estimation framework by integrating unmanned aerial vehicle (UAV)-based thermal infrared remote sensing with a three-temperature (3T) model in the Hexi Corridor. UAV-derived land surface temperature (LST) at meter-scale resolution, together with meteorological and vegetation data, was used to drive the model and generate high-resolution ET maps. The model’s performance was validated spatially against the Surface Energy Balance Algorithm for Land (SEBAL) model and at the point-scale against a two-source model. The results show that: (1) The 3T model effectively captured the spatial gradient of decreasing ET from cropland (3–10.69 mm d⁻¹), through shelterbelts (3–6 mm d⁻¹), to desert areas (<3 mm d⁻¹). (2) Spatial validation against the SEBAL model was conducted using stratified pixel-wise comparisons across four land-cover types over 14 UAV transects, showing strong agreement (R² = 0.90–0.95; RMSE = 0.22–0.43 mm d⁻¹). The model achieved highest accuracy in cropland (R² = 0.92; RMSE = 0.24 mm d⁻¹), with slight overestimation in shelterbelts. (3) Point-scale validation against the two-source model yielded an MAE of 0.38 mm d⁻¹. This study demonstrates the effectiveness of combining UAV thermal infrared data with the 3T model for high-resolution ET simulation in complex ecological transition zones, offering a promising technical approach for ecohydrological monitoring and water resource assessment in arid regions. Full article

► Show Figures

Figure 1

22 pages, 67005 KB

Open AccessArticle

DEAF-Net: Dual-Domain Enhanced Adaptive Fusion Network for UAV Visible–Infrared Object Detection

by Qian Weng, Yu Zhang, Xiansheng Huang, Liming Deng and Jiawen Lin

Remote Sens. 2026, 18(13), 2241; https://doi.org/10.3390/rs18132241 - 7 Jul 2026

Viewed by 510

Abstract

In Unmanned Aerial Vehicle (UAV) object detection tasks, complex lighting conditions and variable weather render robust all-weather perception challenging when relying solely on the visible modality. Although infrared modalities can provide complementary information, the reliability of individual modalities is highly scene-dependent. Existing multimodal [...] Read more.

In Unmanned Aerial Vehicle (UAV) object detection tasks, complex lighting conditions and variable weather render robust all-weather perception challenging when relying solely on the visible modality. Although infrared modalities can provide complementary information, the reliability of individual modalities is highly scene-dependent. Existing multimodal detection methods typically adopt static fusion strategies, which ignore spatial heterogeneity of modal reliability and under-explore spatial-frequency collaborative representation, thus limiting detection robustness in dynamic environments. To address these issues, this paper proposes a Dual-domain Enhanced Adaptive Fusion Network (DEAF-Net), with two core innovative modules to tackle the above challenges. First, the Dual Domain Progressive Refinement (DDPR) module mitigates feature degradation caused by poor imaging conditions via the joint design of frequency-domain learnable filtering and scale-aware contextual refinement in the spatial domain, effectively suppressing noise, enhancing textures, and yielding a purified feature basis for fusion. Second, the Consistency–Discrepancy Guided Fusion (CDGF) strategy leverages the selective scanning mechanism of VMamba to model consistent and differential patterns across modalities, dynamically generates local modal contribution maps for adaptive fusion, and integrates global scene prior via entropy weights for calibration. Extensive experiments on the DroneVehicle and VEDAI datasets show that DEAF-Net outperforms mainstream multimodal detection methods, achieving mAP@0.5 scores of 81.9% and 76.2%, respectively, while delivering improved robustness in low-light, dense fog, and sparse-category scenarios. Full article

(This article belongs to the Special Issue Intelligent Processing of Multimodal Remote Sensing Data)

► Show Figures

Figure 1

29 pages, 61579 KB

Open AccessArticle

Mapping Acid Mine Drainage Areas with Sentinel-2 and WorldView-3 VNIR Satellite Images: An Example in the SE of Spain

by Inés Pereira, Eduardo García-Meléndez, Montserrat Ferrer-Julià and Harald van der Werff

Remote Sens. 2026, 18(13), 2240; https://doi.org/10.3390/rs18132240 - 7 Jul 2026

Viewed by 419

Abstract

Mining of sulfide-rich deposits enhances the oxidation of sulfide minerals, generating acid mine drainage (AMD) characterized by high sulphate and dissolved metal concentrations and the formation of secondary iron minerals (hematite, goethite, and jarosite). As these minerals display diagnostic features in the visible–near-infrared [...] Read more.

Mining of sulfide-rich deposits enhances the oxidation of sulfide minerals, generating acid mine drainage (AMD) characterized by high sulphate and dissolved metal concentrations and the formation of secondary iron minerals (hematite, goethite, and jarosite). As these minerals display diagnostic features in the visible–near-infrared (VNIR) region, multispectral satellite data provide a cost-effective means of monitoring. Here, the performances of Sentinel-2 and the VNIR bands from WorldView-3 are assessed and compared for the mapping and discrimination of secondary iron minerals in Sierra Minera de Cartagena–La Unión (SE Spain). Both datasets were analyzed using a band ratio and a parabola fitting technique focused on reflectance maxima. Band ratio results were interpreted as broad spectral patterns rather than definitive mineral identifications. Mineral maps were validated by applying X-ray diffraction on 74 surface soil samples. Although both sensors were able to reproduce the main spatial patterns of iron mineral distribution, Sentinel-2 data better discriminated hematite, goethite, and jarosite, especially when using the parabola fitting approach, whereas WorldView-3 VNIR data distinguished mainly hematite from the combined goethite–jarosite group. The better performance of Sentinel-2 is attributed to its red-edge and near-infrared band configuration. These findings indicate that freely available Sentinel-2 imagery can support systematic monitoring of oxidation processes in mining environments and contribute to environmental risk assessment in degraded landscapes. Full article

► Show Figures

Figure 1

25 pages, 15986 KB

Open AccessArticle

GHF-DETR: An Improved DETR Framework with a Multi-Path Backbone and Dual-Domain Downsampling for UAV Object Detection

by Lei Hu, Qingming Huang, Zhixiang Liu and Hongwei Ye

Remote Sens. 2026, 18(13), 2239; https://doi.org/10.3390/rs18132239 - 7 Jul 2026

Viewed by 487

Abstract

Detecting small targets in Unmanned Aerial Vehicle (UAV) imagery is challenging due to low pixel coverage, complex backgrounds, and information loss during downsampling. Existing detectors lack explicit mechanisms for enhancing weak target signals. We propose GHF-DETR, a Transformer-based detector featuring three collaboratively designed [...] Read more.

Detecting small targets in Unmanned Aerial Vehicle (UAV) imagery is challenging due to low pixel coverage, complex backgrounds, and information loss during downsampling. Existing detectors lack explicit mechanisms for enhancing weak target signals. We propose GHF-DETR, a Transformer-based detector featuring three collaboratively designed modules. First, a Heterogeneous Multi-Path Convolutional Network (HMC) backbone uses partial convolution and gated linear units to reduce computational redundancy while maintaining discrimination of small-object features. Second, a Dynamic Multi-Scale Focusing (DMSF) module integrates learned offset alignment with multi-kernel depthwise convolutions for cross-scale feature fusion. Third, a High-Frequency Selective Preservation (HSP) downsampling module combines space-to-depth convolution with 2D Discrete Wavelet Transform (DWT) to compensate for information loss in both spatial and frequency domains. On VisDrone2019, GHF-DETR achieves 33.1% mAP@0.5 and 18.6% mAP@0.5:0.95 with 15.4 GFLOPs and 7.59 M parameters, improving over the DFINE-n baseline by 5.4% and 3.1%, respectively, with AP_S reaching 10.1%. Generalization is validated on NWPU VHR-10. These results demonstrate that GHF-DETR achieves a favorable accuracy–efficiency balance for efficient UAV small-object detection. Full article

(This article belongs to the Special Issue Object Detection in Remote Sensing Images Based on Artificial Intelligence)

► Show Figures

Figure 1

37 pages, 16771 KB

Open AccessArticle

RepLite-YOLO: A Parameter-Efficient Residual-Enhanced Detector for Ship Recognition in Remote Sensing Imagery

by Ruijia Fu, Zuomin Wang, Zijun Lin, Ying Li and Bingxin Liu

Remote Sens. 2026, 18(13), 2238; https://doi.org/10.3390/rs18132238 - 6 Jul 2026

Viewed by 583

Abstract

Remote sensing ship detection plays a pivotal role in maritime surveillance, safety assurance, and traffic management. However, current detection methods often face significant challenges due to complex sea-surface background noise, large target-scale variations, and edge-hardware limitations. In this paper, we propose RepLite-YOLO, a [...] Read more.

Remote sensing ship detection plays a pivotal role in maritime surveillance, safety assurance, and traffic management. However, current detection methods often face significant challenges due to complex sea-surface background noise, large target-scale variations, and edge-hardware limitations. In this paper, we propose RepLite-YOLO, a lightweight detection framework based on YOLOv11n. Specifically, to alleviate irreversible spatial information loss during downsampling, we adopt the ADown module, originally introduced in YOLOv9, to generate spatially complementary features through its two-branch downsampling mechanism. This design helps preserve salient hull-edge responses while suppressing part of the random sea-surface interference, thereby improving feature robustness for small ship targets. To achieve substantial structural streamlining while maintaining competitive representational capacity under strict hardware constraints, we design the C3k2_OREPA_RS module, utilizing online re-parameterization (OREPA) to efficiently reconstruct deep layers without additional re-parameterization-induced inference operations. Furthermore, we construct the ELANFusion_Block by integrating Depthwise Separable Convolutions (DSC) into the ELAN paradigm to alleviate the multi-scale aggregation bottleneck, and tailor the Detect_DWLite head for highly compressed decoupled prediction. Experimental results show that RepLite-YOLO achieves a favorable balance between detection accuracy and computational efficiency. Compared with YOLOv11n, it reduces the number of parameters by 57.4% and GFLOPs by 49.2%, while maintaining competitive detection accuracy with slight mAP@50 improvements of 1.2 and 1.3 percentage points on the Vessel dataset and Ship Detection dataset, respectively. Full article

► Show Figures

Figure 1

39 pages, 17252 KB

Open AccessArticle

UAV-Based Soil Salinity Estimation Using Stagewise Feature Optimization and Dual-Backbone Deep Learning Fusion

by Chao Zhang, Yujie Hu, Min Tang, Shaoyuan Feng, Zhen Zheng, Ziang Xie, Zhijun Jia, Huailiang Wang and Lei Xie

Remote Sens. 2026, 18(13), 2237; https://doi.org/10.3390/rs18132237 - 6 Jul 2026

Viewed by 304

Abstract

Accurate soil salinity estimation under small-sample agricultural conditions continues to pose a formidable challenge, attributed to the scarcity of labeled data, inherent representational limitations of single-backbone neural networks, and the heightened complexity of subsurface salinity inversion. To mitigate these intertwined challenges, this study [...] Read more.

Accurate soil salinity estimation under small-sample agricultural conditions continues to pose a formidable challenge, attributed to the scarcity of labeled data, inherent representational limitations of single-backbone neural networks, and the heightened complexity of subsurface salinity inversion. To mitigate these intertwined challenges, this study developed a UAV-enabled soil salinity estimation framework that integrated lightweight convolutional neural networks and staged feature optimization, leveraging both RGB and multispectral imagery. A feature selection framework integrating random forest recursive feature elimination (RF-RFE), the one-standard-error (One-SE) criterion, and variance inflation factor (VIF) analysis was employed to reduce 129 candidate variables to a unified 16-channel feature set, which served as the common input for estimating both surface and subsurface soil salinity. Three lightweight single-backbone (VGGNet, ResNet, and DenseNet) and dual-backbone feature-level fusion networks (DenseResNet, DenseVGGNet, and ResVGGNet) were constructed and systematically evaluated for their performance in estimating both surface and subsurface soil salinity. Among the single-backbone networks, ResNet yielded the highest overall statistical accuracy, while DenseNet exhibited superior performance in preserving estimation trends. For surface soil salinity estimation, ResVGGNet achieved the best performance among all evaluated models, with an R² of 0.820, RMSE of 0.626 g/kg, MAE of 0.409 g/kg, and RPD of 2.31 on the test dataset. SHAP analysis further highlighted the dominant role of vegetation and salinity-sensitive indices, together with selected spectral mean features, and revealed spatially complementary response patterns among major input channels. Collectively, the integration of lightweight multi-backbone feature-level fusion with streamlined feature optimization strategies effectively enhances the accuracy, robustness, and interpretability of UAV-enabled soil salinity estimation, particularly under the constraint of small agricultural sample sizes. Full article

(This article belongs to the Special Issue Deep Learning Innovations: Small Samples and Foundation Models for Hyperspectral/Multispectral Imagery)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 13 (July-1 2026) – 207 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI