Remote Sensing

19 pages, 10742 KB

Open AccessArticle

Deconstructing and Ameliorating Woody Volume Estimation Errors Arising from Leaves in Quantitative Structure Models of Trees

by David W. MacFarlane and Aidan Morales

Remote Sens. 2026, 18(14), 2342; https://doi.org/10.3390/rs18142342 (registering DOI) - 13 Jul 2026

Abstract

A major challenge for accurate characterization of tree architecture with LiDAR is distinguishing leaves from woody parts. Leaves may block scans of woody parts, or be confused with them, when quantitative structure models (QSMs) are applied. Leaf–wood separation algorithms (LWSAs) can be used [...] Read more.

A major challenge for accurate characterization of tree architecture with LiDAR is distinguishing leaves from woody parts. Leaves may block scans of woody parts, or be confused with them, when quantitative structure models (QSMs) are applied. Leaf–wood separation algorithms (LWSAs) can be used to simulate ‘leaf-off’ conditions before applying QSMs but need further study. We analyzed 110 deciduous trees of 25 species, scanned in leaf-on and leaf-off conditions, with a Faro Focus3D X330, to examine the influence of leaves-on errors in tree woody volume estimation from QSMs. TreeQSM (v2.4.1) was applied, with and without applying the GBSeparation LWSA, and Real Twig (rTwig) was used to create leaf-off woody tree ‘skeletons’ for reference. The results showed greatly overestimated volume with TreeQSM, because it constructed additional branches out of leaves and the noise generated by them, adding large amounts of non-existent branch volume. GBSeparation allowed for accurate total woody volume estimation, but via compensating errors; overallocation of volume to stems and lower-order branches and omission of smaller, higher-order ones. We tested a novel field-calibrated allometric model for predicting leaf-off tree volume from leaf-on tree volume, which showed promise as an accurate, time-efficient alternative pathway for processing leaf-on TLS data. Full article

(This article belongs to the Special Issue Integration of Remote Sensing and GIS to Forest and Grassland Ecosystem Monitoring (Second Edition))

► Show Figures

Figure 1

20 pages, 6018 KB

Open AccessArticle

Enhancing the Estimation and Mapping of Soil Cadmium by Using Geospatial Information-Guided Machine Learning and Principal Component Spectra

by Jianfei Cao, Yihui Liu, Xinrong Duan, Xiaoli Liu, Xiukun Zhang, Qixin Shi and Xibo Xu

Remote Sens. 2026, 18(14), 2341; https://doi.org/10.3390/rs18142341 - 13 Jul 2026

Abstract

Integrating machine learning with spectral data provides an effective and cost-efficient scheme for estimating cadmium (Cd) contents in soils compared with labor-intensive laboratory analyses. However, conventional machine learning–based spectral estimation methods often yield unsatisfactory performance because they rely on an unrealistic assumption that [...] Read more.

Integrating machine learning with spectral data provides an effective and cost-efficient scheme for estimating cadmium (Cd) contents in soils compared with labor-intensive laboratory analyses. However, conventional machine learning–based spectral estimation methods often yield unsatisfactory performance because they rely on an unrealistic assumption that the functional relationships across geographically distinct subregions are homogeneous, thereby reducing the accuracy and stability of soil Cd estimation. To address this issue, a geospatial information-guided XGBoost (GIGS) model was developed, in which a spatial weighting module was incorporated into the XGBoost framework to account for spatial heterogeneity in functional relationships among sampling locations. The spatial heterogeneity of each soil spectral sample was quantified and assigned a corresponding spatial weight, which was subsequently incorporated during model calibration. The optimal principal component spectra (PCS) derived from spectral data were used as model inputs, with measured soil Cd content as the dependent variable, thereby establishing a robust spectral estimation model for soil Cd. Results indicated that the GIGS model exhibited satisfactory performance in the spectral estimation of soil Cd content, with R², RMSE, and RPIQ values of 0.78, 0.04, and 2.02, respectively. Compared to commonly used spectral estimation models (e.g., XGBoost, random forest, support vector regression), the GIGS model achieved a maximum performance improvement of approximately 27.87% and a minimum improvement of approximately 16.42% (with reference to the R² value). Five PCS of soil spectral data were extracted as predictors for the model. PCS-1 was found to be closely associated with iron oxides, while PCS-2 primarily reflects the spectral characteristics of clay minerals. The spectral bands at 600 nm and 815 nm contribute most strongly to PCS-3, which is linked to soil organic matter and indirectly reflects the soil Cd status. PCS-4 and PCS-5 represent mixed spectral information derived from materials associated with soil Cd. An integrated framework combining the GIGS model and PCS data developed in this study provides an accurate and reliable tool for spectral estimation and mapping of soil Cd, thereby supporting cost-effective soil management and environmental sustainability worldwide. Full article

(This article belongs to the Special Issue Recent Advances in Hyperspectral Remote Sensing: Theories, Technologies and Applications)

► Show Figures

Figure 1

13 pages, 2075 KB

Open AccessCommunication

COSM: Satellite and Ground Segment

by Xiaofeng Ma, Wu Zhou, Ninghui Diao, Zhisheng Che and Xiaojiao Yang

Remote Sens. 2026, 18(14), 2340; https://doi.org/10.3390/rs18142340 - 13 Jul 2026

Abstract

The Chinese Ocean Salinity Mission (COSM) is an ocean observation mission performed by the National Satellite Ocean Application Service (NSOAS), China Academy of Space Technology (CAST) and National Space Science Center (NSSC). It is the first satellite that has been used to obtain [...] Read more.

The Chinese Ocean Salinity Mission (COSM) is an ocean observation mission performed by the National Satellite Ocean Application Service (NSOAS), China Academy of Space Technology (CAST) and National Space Science Center (NSSC). It is the first satellite that has been used to obtain global ocean salinity information in China. This article mainly introduces the working principles of the COSM satellite, which are composed of the platform, two payloads, and the components of the ground segment. This article focuses on the structure and layout of the satellite ground segment, as well as its workflow during satellite operation. It also describes the calibration of payloads and the expected ocean salinity products. At present, the status of the COSM is normal, including its satellite and ground segment, and NSOAS has officially released ocean salinity data products from the COSM. Full article

► Show Figures

Figure 1

24 pages, 46925 KB

Open AccessArticle

Multi-Method Identification and Spatiotemporal Evolution Analysis of Active Deformation Areas in the Binchang Mining Area

by Liuru Hu, Chenzhe Wang, Yanan Ji, Jun Deng, Chuang Song, Yaqing Li, Zeyu Zhang, Lin Yu and Chen Yu

Remote Sens. 2026, 18(14), 2339; https://doi.org/10.3390/rs18142339 - 13 Jul 2026

Abstract

Mining-induced land subsidence and geohazards have become increasingly prominent in loess mining areas. Accurate identification of Active Deformation Areas (ADAs) is of great significance for mining safety, ecological protection, and geohazard prevention. The study selected the Binchang mining and used SBAS-InSAR based on [...] Read more.

Mining-induced land subsidence and geohazards have become increasingly prominent in loess mining areas. Accurate identification of Active Deformation Areas (ADAs) is of great significance for mining safety, ecological protection, and geohazard prevention. The study selected the Binchang mining and used SBAS-InSAR based on Sentinel-1 SAR images from 2020 to 2025 to derive cumulative deformation and velocity. Three ADA identification approaches, including ADAfinder, MCAS-TO, and Light-UNet deep learning method, were quantitatively evaluated using IoU, F1-score, Boundary_F1-score, Precision, Recall, Area Error (%), and comparatively analyzed. ADAfinder identifies subsidence centers but produces fragmented results. MCAS-TO improves boundary continuity but is constrained by a 2% area threshold, while the deep learning method achieves the highest boundary detection accuracy and captures ADAs expansion and merging processes. Spatially, the identified ADAs are mainly distributed in the central and southern parts of the mining area and are highly consistent with underground coal mining faces. Comprehensive analysis of the three ADA identification results reveals the spatiotemporal evolution of mining-induced deformation. The results demonstrate that mining activities are the dominant driving factor controlling the formation and evolution of ADAs. The findings can provide important technical support for geohazard prevention in loess mining areas. Full article

(This article belongs to the Special Issue Advances in AI-Driven Remote Sensing for Geohazard Perception)

► Show Figures

Figure 1

24 pages, 14970 KB

Open AccessArticle

Physics-Guided cGAN with Multi-Scale Attention for Robust 2D Phase Unwrapping in Low-Coherence Regions

by Zhijun Yang, Hengdi Hu and Jianxi Yang

Remote Sens. 2026, 18(14), 2338; https://doi.org/10.3390/rs18142338 - 13 Jul 2026

Abstract

Two-dimensional (2D) phase unwrapping (PU) in interferometric synthetic aperture radar (InSAR) remains a challenging ill-posed inverse problem, particularly in low-coherence regions where the Itoh condition is violated. Although deep-learning methods have shown promise, existing networks often struggle to preserve phase continuity and structural [...] Read more.

Two-dimensional (2D) phase unwrapping (PU) in interferometric synthetic aperture radar (InSAR) remains a challenging ill-posed inverse problem, particularly in low-coherence regions where the Itoh condition is violated. Although deep-learning methods have shown promise, existing networks often struggle to preserve phase continuity and structural details under strong decorrelation noise. To address these limitations, a novel physics-guided conditional generative adversarial network (cGAN) is proposed in this work. Specifically, an adaptive atrous spatial pyramid pooling module mimics the multi-baseline observation mechanism to resolve multi-scale phase variations. Meanwhile, a multi-channel attention-augmented discriminator guides adversarial learning to focus on error-prone low-coherence regions. Additionally, a hybrid loss function enforces fundamental physical constraints, including phase-wrapping consistency and path continuity, explicitly embedding the prior knowledge of interferometric phase physics into the data-driven framework. Extensive experiments demonstrate that the proposed method achieves highly competitive performance in terms of root mean square error (RMSE) and structural similarity (SSIM) compared to State-of-the-Art approaches, especially in scenarios with severe noise and discontinuities. Full article

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

► Show Figures

Figure 1

24 pages, 9629 KB

Open AccessArticle

Decoupling Deep Mining and Tailings Consolidation-Induced Subsidence Using SBAS-InSAR and NMF: A Case Study at South Deep Gold Mine, South Africa

by Bright Adoko, Chaoying Zhao, Najeebullah Kakar, Wensong Lu, Basit Ali Khan and Jianqi Lou

Remote Sens. 2026, 18(14), 2337; https://doi.org/10.3390/rs18142337 - 13 Jul 2026

Abstract

Mining-induced land subsidence poses significant geohazard risks to critical on-site mining operational support infrastructure, such as tailings storage facilities (TSFs). This study investigates the Doornpoort TSF subsidence at the South Deep gold mine in South Africa, using multi-temporal Small Baseline Subset Interferometric Synthetic [...] Read more.

Mining-induced land subsidence poses significant geohazard risks to critical on-site mining operational support infrastructure, such as tailings storage facilities (TSFs). This study investigates the Doornpoort TSF subsidence at the South Deep gold mine in South Africa, using multi-temporal Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) and Non-negative Matrix Factorisation (NMF) algorithm approach to split the superimposed subsidence contributing drivers, alongside the incorporation of Global Navigation Satellite System (GNSS) data and underground mining layout plans. 78 Sentinel-1A Satellite Aperture Radar (SAR) ascending acquisitions between May 2022 and December 2024 were obtained and processed to determine the average annual deformation rates and cumulative time-series displacement for the study area. The InSAR-derived subsidence rates at the designated three benchmarks on the embankments of the Doornpoort TSF and TSF 1&2 are −26.09 mm/year, −13.40 mm/year and −16.25 mm/year, while the maximum cumulative subsidence was −57.45 mm, −42.76 mm and −36.44 mm. A comparison of the InSAR results with the GNSS-derived subsidence results showed correlation standard deviations of 1.87 mm, 0.93 mm, and 1.05 mm, respectively. The InSAR results revealed spatially coherent subsidence patterns and a good correlation between deformation boundaries and underground mining layouts, suggesting that mining-induced stress redistribution is the primary driver of regional surface subsidence. The NMF decomposition of the InSAR-derived deformation result at a selected benchmark on the Doornpoort TSF embankment, whose average annual deformation with a cumulative time series deformation of −26.09 mm/year and −57.45 mm, respectively, revealed that 92% of the observed cumulative deformation is associated directly with the underground mining, whilst the remaining 8% is associated with TSF embankment consolidation. Furthermore, the selected decomposition benchmark within the TSF basin showed that underground mining alone accounted for 100% of the observed subsidence there. These findings support a coupled deformation framework in which deep mining activities influence regional subsidence, while localised geological conditions modulate its surface manifestation. Full article

► Show Figures

Figure 1

11 pages, 2312 KB

Open AccessCommunication

A Dual-Perspective Analysis of Ozone Formation Sensitivity in the Yangtze River Delta: Satellite and Ground-Based Evidence

by Keqiang Cheng, Wei Dai, Mingjie Xie and Yuhang Wang

Remote Sens. 2026, 18(14), 2336; https://doi.org/10.3390/rs18142336 - 13 Jul 2026

Abstract

Surface ozone (O₃) pollution persists in the Yangtze River Delta (YRD) of China, with frequent exceedances despite stringent controls, driven by complex NO_x-VOC interactions. Current monitoring struggles to accurately identify O₃ formation regimes (VOC- vs. NO_x-limited) [...] Read more.

Surface ozone (O₃) pollution persists in the Yangtze River Delta (YRD) of China, with frequent exceedances despite stringent controls, driven by complex NO_x-VOC interactions. Current monitoring struggles to accurately identify O₃ formation regimes (VOC- vs. NO_x-limited) at urban scales during daytime. By integrating TROPOMI satellite data with high-resolution ground-based joint observations, we reveal scale-dependent regime transitions: megacities (G1 cities, population > 5 million and GDP > 1 trillion CNY yr⁻¹) exhibit narrow HCHO-to-NO₂ ratio (FNR) transition ranges (1.54–2.86), and O₃ pollution (≥160 μg/m⁻³) may occur under all regimes (VOC-limited, transitional, and NO_x-limited). In contrast, smaller G2 cities show wider transition ranges (1.85–3.43), with O₃ pollution occurring primarily under transitional and NO_x-limited conditions. Observations from a typical G1 city demonstrate that VOC reductions effectively control O₃ under VOC-limited regimes, while NO_x mitigation alone is insufficient in NO_x-limited environments due to persistently high VOC backgrounds. Our findings suggest city-specific strategies: G1 cities require adaptive co-control of VOCs and NO_x to accommodate localized chemistry, whereas G2 cities benefit from targeted measures aligned with dominant sensitivity regimes. This study provides observational verification of environment-dependent O₃ formation mechanisms, offering a methodological framework for precision air quality management in rapidly developing regions. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

22 pages, 3711 KB

Open AccessArticle

Category-Aware Global–Local Semantic Alignment for Remote Sensing Image–Text Retrieval

by Da Ha and Haisu Zhang

Remote Sens. 2026, 18(14), 2335; https://doi.org/10.3390/rs18142335 - 13 Jul 2026

Abstract

In remote sensing image–text retrieval (RSITR), precise cross-modal retrieval is often hindered by centroid drift and ambiguous decision boundaries caused by high inter-class visual similarity. To address these bottlenecks, this study proposes a Category-aware Global–Local Semantic Alignment (CGLSA) framework fine-tuned on the CLIP [...] Read more.

In remote sensing image–text retrieval (RSITR), precise cross-modal retrieval is often hindered by centroid drift and ambiguous decision boundaries caused by high inter-class visual similarity. To address these bottlenecks, this study proposes a Category-aware Global–Local Semantic Alignment (CGLSA) framework fine-tuned on the CLIP (ViT-B/16) backbone. The architecture orchestrates two complementary mechanisms: Global Semantic Collaborative Alignment that regularizes macro-level category centroids using momentum updates and Bayesian prior calibration, and Local Fine-grained Feature Alignment that refines instance-level matching via dynamic scale adjustment and category-aware topological masks. Extensive evaluations on three major benchmark datasets (RSICD, RSITMD, and UCM-Captions) validate the model’s efficacy. Compared to strictly controlled CLIP-family baselines under equivalent supervised conditions, CGLSA achieves new state-of-the-art performance across all R@K metrics and mean recall. Extensions adapting this robust centroid formation to semi-supervised and open-vocabulary scenarios are identified for future work. Full article

► Show Figures

Figure 1

23 pages, 42217 KB

Open AccessArticle

A New Deep Learning Method for Sea Fog Detection Using Fengyun-4A Satellite Data

by Yinhe Cheng, Danyu Hong, Tinghuai Ma, Shuwen Wang and Dawei Shi

Remote Sens. 2026, 18(14), 2334; https://doi.org/10.3390/rs18142334 - 13 Jul 2026

Abstract

Sea fog is a common maritime meteorological hazard that poses a serious threat to maritime traffic safety and coastal economic activities. Existing sea fog detection models still struggle to effectively capture both global structural information and local textural details, while spectral confusion between [...] Read more.

Sea fog is a common maritime meteorological hazard that poses a serious threat to maritime traffic safety and coastal economic activities. Existing sea fog detection models still struggle to effectively capture both global structural information and local textural details, while spectral confusion between clouds and fog further limits their performance. To address these challenges, a daytime sea fog detection model, HA-ENASnet, is developed using data from China’s Fengyun-4A (FY-4A) satellite and compared with six representative semantic segmentation models. Among the seven models, HA-ENASnet achieves the best performance, followed by SegMamba, scSE_LinkNet, SegMAN, ECA_TransUnet, DeepLabv3+, and UNet++. In terms of Intersection over Union (IoU), HA-ENASnet outperforms SegMamba and UNet++ by 3.08 and 17.26 percentage points, respectively. Ablation experiments for this model demonstrate that the introduction of a collaborative mechanism combining local and global linear attention effectively enhances the model’s perception capabilities for sea fog regions. Furthermore, the combination of Adaptive Architecture Search (NAS) and Efficient Channel Attention (ECA) facilitates the adaptive fusion of spectral and spatial multiscale features, thereby improving the model’s ability to distinguish between cloud and fog in spectrally confounded regions. Additionally, the proposed model is validated on Himawari-8 satellite data, exhibiting satisfactory detection performance and generalization capabilities. This provides methodological support for sea fog remote sensing monitoring using the FY satellite series. Full article

(This article belongs to the Special Issue Deep Learning-Driven Cloud and Haze Mitigation: Advancements in Remote Sensing Image Restoration)

► Show Figures

Figure 1

21 pages, 15030 KB

Open AccessArticle

Optimizing Spectral Inputs for Deep Learning-Based Vegetation Destruction Detection Using Sentinel-2 Imagery

by Chuanwu Zhao, Huijie Zhao, Yaozhong Pan and Guifei Jing

Remote Sens. 2026, 18(14), 2333; https://doi.org/10.3390/rs18142333 - 13 Jul 2026

Abstract

Deep learning models have been widely used for vegetation destruction detection, but their performance depends on input features in addition to sample size and model architecture. Using Sentinel-2 imagery, we constructed multiple feature combinations from visible, near-infrared, and short-wave infrared bands and several [...] Read more.

Deep learning models have been widely used for vegetation destruction detection, but their performance depends on input features in addition to sample size and model architecture. Using Sentinel-2 imagery, we constructed multiple feature combinations from visible, near-infrared, and short-wave infrared bands and several spectral indices, and evaluated them with nine deep learning models. The results show that adding extra bands to RGB input improved most models, with RGBS yielding the most robust performance improvement among the tested band combinations, consistently outperforming the RGB baseline across the majority of deep learning architectures. Spectral indices further improved most models, especially BVDI, NBR, and SVI. Some single-index or two-index inputs achieved accuracy comparable to or higher than that of RGB input, indicating their potential for information compression and band substitution. However, model responses varied, and more input channels did not guarantee stable gains. Accuracy–efficiency analysis showed that RGBS, RGB + BVDI, RGB + NBR, and selected RGBNS + index combinations achieved favorable performance at low computational cost. Overall, optimized spectral inputs improve vegetation destruction detection, but their selection should balance model architecture, accuracy, and computational cost. Full article

(This article belongs to the Special Issue Vegetation Dynamics Monitoring Using Satellite Remote Sensing)

► Show Figures

Figure 1

35 pages, 39681 KB

Open AccessArticle

Normalized Dynamic Fluorescence Height: An Alternative Algorithm for Chlorophyll a Estimation in Algae-Dominated Waters Using Hyperspectral Remote Sensing Reflectance from In Situ and Spaceborne Imagers

by Dongzhi Zhao, Qinshun Luo, Xuanhan Lai, Huizhen Sun, Zhongfeng Qiu, Haoran Zhang and Zhaohua Sun

Remote Sens. 2026, 18(14), 2332; https://doi.org/10.3390/rs18142332 - 13 Jul 2026

Abstract

The accurate determination of chlorophyll a (Chl a) is often limited by the instability of conventional fluorescence height algorithms in algal bloom waters characterized by diverse phytoplankton morphology and red-shifted reflectance peaks. In this study, we propose the Normalized Dynamic Fluorescence Height [...] Read more.

The accurate determination of chlorophyll a (Chl a) is often limited by the instability of conventional fluorescence height algorithms in algal bloom waters characterized by diverse phytoplankton morphology and red-shifted reflectance peaks. In this study, we propose the Normalized Dynamic Fluorescence Height (NDFH) as a novel hyperspectral algorithm for assessing sun-induced chlorophyll fluorescence. Using in situ bio-optical data and multi-source satellite observations (Advanced Hyperspectral Imager (AHSI) onboard ZY-1E, Hyperspectral Imager for the Coastal Ocean (HICO) onboard ISS, and Ocean Color Instrument (OCI) onboard PACE), NDFH was evaluated and compared with existing algorithms, such as the normalized Fluorescence Line Height, Cyanobacterial Index (CI), and Maximum Algal Line Height (MALH). The results show that NDFH has robust exponential correlations with Chl a concentrations in inland waters and can reliably detect fluorescence peak band shifts in bloom-dominated environments. Case studies in Lake Taihu confirm that NDFH is more effective at delineating bloom extent and Chl a distributions than conventional methods, particularly in algae-dominated waters. These findings show the potential of NDFH for operational monitoring of eutrophication and harmful algal blooms across diverse aquatic environments. Full article

► Show Figures

Figure 1

27 pages, 7942 KB

Open AccessArticle

Flood Regulation Service Responses to Urban Green Space Change in a Plateau Valley City: A Case Study of Lhasa, China

by Shouhang Zhao, Aibo Jin, Yuexin Xu, Yuqi Li, Qin Yang, Tingting Ding and Yunyuan Li

Remote Sens. 2026, 18(14), 2331; https://doi.org/10.3390/rs18142331 - 12 Jul 2026

Abstract

Plateau valley cities are increasingly exposed to flood risk because topographic constraints, ecological fragility, and rapid urbanization jointly intensify runoff sensitivity. Although dynamic and process-based assessments of flood regulation service (FRS) have advanced, limited attention has been given to how changes in urban [...] Read more.

Plateau valley cities are increasingly exposed to flood risk because topographic constraints, ecological fragility, and rapid urbanization jointly intensify runoff sensitivity. Although dynamic and process-based assessments of flood regulation service (FRS) have advanced, limited attention has been given to how changes in urban green space (UGS) components are associated with marginal runoff-retention responses in a plateau valley setting. Taking central Lhasa as a case, this study combined Sentinel-2-based UGS mapping, intPLUS land-use scenario simulation, Soil and Water Assessment Tool (SWAT) runoff modeling, XGBoost, SHapley Additive exPlanations (SHAP), and accumulated local effects (ALE) to evaluate the FRS responses under multiple scenarios. A pressure–response overlay was further used to diagnose spatial mismatches between runoff pressure and modeled regulation response. Results showed that UGS expanded by 5212.66 ha from 2017 to 2025, indicating a marked greening trend, but the natural development scenario projected a 1403.80 ha decline by 2033. In contrast, the ecological protection scenario projected a 915.98 ha increase and produced a stronger modeled runoff-retention response, although the improvement remained spatially uneven across subbasins. Model-based interpretation identified forest land as the most influential predictor of runoff-depth-based FRS response, while grassland, park green space, and waterfront green space were generally associated with runoff-depth reduction and showed distinct nonlinear response patterns. Specifically, forest land and grassland showed diminishing marginal effects after higher increment ranges, park green space exhibited delayed effectiveness before clearer regulation benefits emerged, and waterfront green space reached effective response ranges at relatively low proportional increments. Spatial diagnosis further showed that 19 subbasins, accounting for 18.88% of the study area, remained response-lagged, mainly along urban expansion fringes where runoff pressure was not matched by sufficient modeled regulation response. The integrated framework provides a transferable, spatially explainable basis for plateau valley FRS assessment, whereas the identified thresholds and zoning implications remain case-specific and require local validation. Full article

(This article belongs to the Special Issue Remote Sensing of Climate Change Influences on Urban Ecology)

► Show Figures

Figure 1

37 pages, 33542 KB

Open AccessArticle

Nighttime Thermal Patterns and County Life Expectancy: A 20-Year Multimodal Satellite Fusion for the Contiguous United States

by Faiz Ahmad, David J. Lary, Shisir Ruwali, Samyak Shrestha, Adam Aker, John Waczak and Prabuddha Madushanka

Remote Sens. 2026, 18(14), 2330; https://doi.org/10.3390/rs18142330 - 12 Jul 2026

Abstract

Satellite -derived environmental features can predict county-level life expectancy (LE) across the contiguous United States with a mean absolute error of 1.08 years over two decades, without using any census or sociodemographic inputs. We assembled 61,680 county-year observations across 3084 counties from 2000–2019, [...] Read more.

Satellite -derived environmental features can predict county-level life expectancy (LE) across the contiguous United States with a mean absolute error of 1.08 years over two decades, without using any census or sociodemographic inputs. We assembled 61,680 county-year observations across 3084 counties from 2000–2019, integrating features from 11 satellite and gridded data streams. The data streams include the Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature and vegetation indices, Sentinel-1 synthetic aperture radar, Sentinel-2 and Landsat optical imagery, the United States Department of Agriculture (USDA) Cropland Data Layer, the European Commission Joint Research Centre (JRC) Global Surface Water layer, the Copernicus Digital Elevation Model, the European Space Agency Climate Change Initiative (ESA CCI) soil moisture record, and the Food and Agriculture Organization (FAO) gridded livestock densities. After a supervised pruning step that removed low-importance variables, a Random Forest regressor was trained and evaluated using 5-fold cross-validation grouped by county. The grouping places all 20 years of each county exclusively in either the training set or the test set, which prevents spatial information leakage between folds. Coefficient of determination, mean absolute error, and root mean squared error are reported as

R^{2} = 0.631 \pm 0.013

, MAE

= 1.08 \pm 0.02

years, and RMSE

= 1.48 \pm 0.04

years. Moran’s I, a measure of residual spatial autocorrelation, is

0.0988

(

p = 0.001

), which supports geographic generalisation. Multimodal fusion reduces unexplained variance by approximately one-third relative to the strongest single-modality baseline (MODIS land surface temperature alone,

R^{2} = 0.442

). TreeSHAP attribution analysis reveals a feature hierarchy in which nighttime land surface temperature features carry roughly

6.16 \times

the cumulative attribution weight of all daytime channels combined. The model response shows a protective inflection near a minimum overnight temperature of about

7.5^{\circ}

C. Because all input streams are globally available, the framework is architecturally extensible to regions where civil registration and vital statistics systems are incomplete; however, the trained model and its thresholds require recalibration against local mortality data before application outside the contiguous United States. With that caveat, the approach supports satellite-based monitoring of United Nations Sustainable Development Goal (UN SDG) Target 3.9. Full article

(This article belongs to the Section Environmental Remote Sensing)

34 pages, 5786 KB

Open AccessArticle

Target Detection for UAV Inspection in Complex Illumination Environments: A Lightweight Dual-Modal Fusion Method with Multi-Directional Mamba Cross-Attention

by Ziyue Luo, Ziyi Zhou, Haishan Tian, Ziyi Zhong, Kewei Li, Yujie Ma, Weiwei Tang and Kui Wang

Remote Sens. 2026, 18(14), 2329; https://doi.org/10.3390/rs18142329 - 12 Jul 2026

Abstract

Unmanned aerial vehicles (UAVs) frequently operate under complex illumination conditions during urban and industrial security patrols, including low light, fog, and strong backlighting. These conditions severely degrade the performance of existing dual-modal object detection methods. To overcome this limitation, we introduce a lightweight [...] Read more.

Unmanned aerial vehicles (UAVs) frequently operate under complex illumination conditions during urban and industrial security patrols, including low light, fog, and strong backlighting. These conditions severely degrade the performance of existing dual-modal object detection methods. To overcome this limitation, we introduce a lightweight dual-modal object detection algorithm called M²CA-FFM, built upon multi-directional Mamba cross-attention feature fusion. First, a multi-directional Mamba enhancement module is developed to model spatial feature sequences via four-directional scanning. Second, a dedicated spectral enhancement module is designed to process spectral components in a differentiated manner. Together, these two modules enhance single-modal features from both the spatial and frequency domains, leading to improved feature robustness. For dual-modal object detection, we propose a Mixed Scanning Fusion Module that dynamically generates scanning paths focused on the target regions. This dynamic mechanism complements the fixed four-direction scanning and strengthens global modeling, enabling efficient fusion and deep complementarity between visible light and infrared features. Extensive experiments are conducted on a self-built dataset (OPVM-VIRD) and three public benchmarks (FLIR, M3FD, and VEDAI). Our method consistently outperforms current mainstream dual-modal detection algorithms across all datasets. On the OPVM-VIRD dataset, it achieves an mAP50 of 95.7%, which is 2.2% higher than the best result obtained with other fusion methods. Preliminary verification on the edge computing platform Atlas 200I DK A2 shows that the algorithm has significant lightweight advantages, with a parameter volume of only 72.07 M and a computational complexity of 134.41 GFLOPs, demonstrating the reasoning potential to meet real-time processing requirements. Overall, the proposed M²CA-FFM method offers a real-time detection strategy with strong generalization capabilities, holding significant practical value for around-the-clock security patrols in urban and industrial parks. Full article

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

26 pages, 3473 KB

Open AccessArticle

Significance-Preserving Progressive Network for Infrared and Visible Image Fusion

by Jingsui Li, Xiaorun Li, Shu Xiang and Shuhan Chen

Remote Sens. 2026, 18(14), 2328; https://doi.org/10.3390/rs18142328 - 12 Jul 2026

Abstract

Fusing infrared and visible images can effectively compensate for the inherent limitations of each modality in different scenes, resulting in fused images that contain richer information. However, existing methods often struggle to balance global dependency modeling with local detail preservation and to effectively [...] Read more.

Fusing infrared and visible images can effectively compensate for the inherent limitations of each modality in different scenes, resulting in fused images that contain richer information. However, existing methods often struggle to balance global dependency modeling with local detail preservation and to effectively coordinate heterogeneous local and global features during fusion. To address these issues, this paper proposes a Significance-Preserving Progressive Fusion Network (SiPFusion). First, a progressive feature extraction framework was designed, which hierarchically extracts multi-scale local features using CNNs and then models long-range dependencies across scales via a Transformer-based global module. To adaptively integrate local-global complementary features, a significance-preserving fusion module was designed to obtain significance attention maps with a spatial selection mechanism, enabling dynamic fusion of multi-source features. Furthermore, we propose a significance similarity loss function that leverages intermediate feature guidance to enhance structural consistency and preserve salient-region information in the fused image. Extensive experiments on the MSRS, RoadScene, and TNO datasets demonstrate that SiPFusion achieves competitive visual quality and strong overall quantitative performance against 15 state-of-the-art fusion methods, obtaining leading results on most evaluated metrics. Full article

(This article belongs to the Special Issue Image Fusion and Object Detection Using Multi-Modal Remote Sensing Data)

28 pages, 40573 KB

Open AccessArticle

CASA-Net: Context-Aware Small-Object Adaptation Network for UAV Aerial Images

by Kai Zheng, Yichen Zhong, Wenguang Song and Qiongqin Jiang

Remote Sens. 2026, 18(14), 2327; https://doi.org/10.3390/rs18142327 - 12 Jul 2026

Abstract

Detecting small targets in UAV aerial imagery is inherently difficult because these objects occupy only a small number of pixels and are highly susceptible to cluttered backgrounds, dense spatial arrangements, and pronounced scale variation. To address this problem, we propose CASA-Net (Context-Aware Small-object [...] Read more.

Detecting small targets in UAV aerial imagery is inherently difficult because these objects occupy only a small number of pixels and are highly susceptible to cluttered backgrounds, dense spatial arrangements, and pronounced scale variation. To address this problem, we propose CASA-Net (Context-Aware Small-object Adaptation Network), a context-aware detector built on a [d=R2]YOLOv26sYOLOv26 baseline with three coordinated improvements: an Enhanced Small-Target-Aware Label Assignment mechanism for stronger supervision of tiny instances, a Multi-scale Feature Enhancement Module for richer contextual representation and spatial discrimination, and an aerial-specific augmentation pipeline for improved robustness to viewpoint, scale, and motion blur. Experiments on the VisDrone and RSOD benchmarks demonstrate that CASA-Net consistently outperforms the baseline and competing methods. On VisDrone, it achieves 47.0% mAP

_{0.5}

and 25.2% small-object mAP

_{0.5}

, while on RSOD it reaches 78.3% mAP

_{0.5}

. In addition, the model achieves real-time inference speeds above 100 FPS on both datasets using an RTX 3090, with 13.9 M parameters and 26.2 GFLOPs. Taken together, these findings show that CASA-Net is an accurate and efficient framework for UAV small-object detection through the joint improvement of supervision, feature representation, and data adaptation. Full article

24 pages, 9569 KB

Open AccessArticle

Assessing the Capabilities of UAV-Based Observation for Marginalized Communities: A Case Study of Roma Settlements in Slovakia

by Farzaneh Dadrass Javan, Lukas Ihnacik, Peter Blistan, Mohammadreza Homaei, Ingrid Papajova and Carmen Anthonj

Remote Sens. 2026, 18(14), 2326; https://doi.org/10.3390/rs18142326 - 11 Jul 2026

Abstract

This study assesses the capabilities of UAV-based Earth observation for analyzing marginalized communities, using Roma settlements in southeastern Slovakia as a case study. Marginalized populations are often underrepresented in official spatial datasets, resulting in a limited understanding of their living conditions, infrastructure needs, [...] Read more.

This study assesses the capabilities of UAV-based Earth observation for analyzing marginalized communities, using Roma settlements in southeastern Slovakia as a case study. Marginalized populations are often underrepresented in official spatial datasets, resulting in a limited understanding of their living conditions, infrastructure needs, and environmental risks. To address this gap, we propose a multi-scalar, UAV-based observational approach that bridges the limitations of coarse satellite imagery and logistically constrained ground surveys. High-resolution RGB and thermal imagery were acquired across three settlements with varying spatial characteristics and processed using photogrammetric workflows to generate detailed orthophotos and spatial products. The results demonstrate that UAV data with centimeter-level spatial resolution enable precise mapping of settlement morphology, infrastructure, waste distribution, and thermal inequalities. Furthermore, UAV observations enable change detection and environmental risk assessment at scales that are not achievable with conventional remote sensing. However, the study also highlights critical operational and ethical challenges, including regulatory constraints, privacy concerns, and the need for community engagement. By integrating technical evaluation with socially sensitive research practices, this work proposes a methodological framework for responsible UAV deployment in marginalized contexts. The findings underscore the potential of UAV-based observation to improve spatial visibility and support evidence-based planning while emphasizing the importance of ethical implementation. Full article

► Show Figures

Figure 1

24 pages, 11433 KB

Open AccessArticle

ECDF-Stabilized Sentinel-1 InSAR Coherence for Verification-Oriented Heritage Monitoring: A TabICLv2-SHAP and Three-Horizon DEMATEL Architecture

by Salvatore Polverino, Hourakhsh Ahmadnia, Rokhsaneh Rahbarianyazd Ahmadnia, Abdollah Mobaraki and Behnam Mobaraki

Remote Sens. 2026, 18(14), 2325; https://doi.org/10.3390/rs18142325 - 11 Jul 2026

Abstract

Cultural-heritage monitoring increasingly requires evidence-to-decision architecture capable of moving beyond descriptive coherence maps toward analytically transparent and verification-oriented decision support. Within this evidential setting, the analysis presents a case-study-demonstrated architecture for multi-epoch Sentinel-1 interferometric synthetic aperture radar (InSAR) coherence analysis in a heritage-sensitive [...] Read more.

Cultural-heritage monitoring increasingly requires evidence-to-decision architecture capable of moving beyond descriptive coherence maps toward analytically transparent and verification-oriented decision support. Within this evidential setting, the analysis presents a case-study-demonstrated architecture for multi-epoch Sentinel-1 interferometric synthetic aperture radar (InSAR) coherence analysis in a heritage-sensitive landscape, designed to transform heterogeneous pairwise outputs into an interpretable, cross-epoch comparable, sector-level evidence register. Quantitatively, the architecture is demonstrated on 12 short-baseline intervals and 1193 valid fixed-support points; it is organized around four linked operations: (i) reliability-filtered coherence stabilization through fixed-support sampling, temporal point-history construction, ECDF-based rank alignment, and ordinal recoding; (ii) separation of the continuous radar response from the upstream four-state ordinal monitoring-support register before model fitting; (iii) leakage-controlled TabICLv2 learning on RAW/stabilized radar-meteorological descriptors, excluding SHAP-derived, prediction-derived, probability-derived, feature-importance-derived, and global mean-coherence proxy variables; and (iv) post hoc SHAP attribution transferred to a three-horizon DEMATEL prioritization register. Under the retained TabICLv2 configuration, holdout evaluation showed strong ordinal separability: accuracy = 0.9799, balanced accuracy = 0.9798, macro-F1 = 0.9798, and Cohen’s kappa = 0.9699. To delimit the performance claim, the corresponding holdout confusion matrix contained three observed ordinal labels after filtering and split construction; support was balanced across State 0, State 1, and State 2. At the decision-transfer stage, the SHAP-informed DEMATEL synthesis distinguished three prioritization regimes: an immediate coherence-led H1 structure, a seasonal hydro-meteorological amplification regime in H2, and a strategic coherence-selective prioritization structure in H3. The study is framed as a methodological demonstration for persistence-aware, verification-oriented heritage monitoring, not as field validation, archeological confirmation, structural diagnosis, or causal physical inference. Full article

(This article belongs to the Special Issue Advancing Synthetic Aperture Radar: Imaging, Processing, and Applications in Remote Sensing)

► Show Figures

Figure 1

27 pages, 5638 KB

Open AccessArticle

Spatiotemporal Variations in Terrestrial Water Storage and Water Scarcity Assessment Across China Based on TWSA_BTCH

by Yue Ma, Longfeng Wang, Ziyan Zheng, Wenpeng Li, Zhuguo Ma, Junjie Zhao, Yuejun Zheng, Yawen Duan and Xubo Gao

Remote Sens. 2026, 18(14), 2324; https://doi.org/10.3390/rs18142324 - 11 Jul 2026

Abstract

Clarifying the spatiotemporal variations of terrestrial water storage anomaly (TWSA) and the water scarcity is crucial for maintaining water resources, ecosystem and food security. This study adopts the Bayesian triple collocation method (BTCH) method to fuse three GRACE Mascon product datasets to generate [...] Read more.

Clarifying the spatiotemporal variations of terrestrial water storage anomaly (TWSA) and the water scarcity is crucial for maintaining water resources, ecosystem and food security. This study adopts the Bayesian triple collocation method (BTCH) method to fuse three GRACE Mascon product datasets to generate the TWSA_BTCH, covering the period from April 2002 to December 2023. The reliability of TWSA_BTCH is further verified using the water balance approach. The spatiotemporal variations of TWSA and the water scarcity index based on terrestrial water storage (WS_{TWS_based}) at the national and primary water resource regional level are then analyzed. The results indicate that: (1) The spatially averaged uncertainty of the TWSA_BTCH over China is 8.13 mm, which is lower than those of TWSA_average (12.51 mm), TWSA_CSR (23.43 mm), TWSA_GSFC (29.79 mm), and TWSA_JPL (31.76 mm). (2) From 2003 to 2023, the TWSA exhibited an overall significant declining trend with an annual depletion rate of 1.65 mm. The national average value of the WS_{TWS_based} index decreased from 0.32 during 2003–2012 to 0.28 over 2013–2023, which indicates that the pressure of nationwide water scarcity has been alleviated to a certain extent, while the whole country still faces a moderate water shortage status. Meanwhile, the mean annual TWSA across China during 2003–2023 was −10.28 mm, indicating a nationwide terrestrial water storage deficit. (3) Regional water resource risks require joint characterization from the dual perspectives of hydrological fluxes and storage. Northern arid and semi-arid regions feature inherent imbalances between water supply and demand. The latent risks of terrestrial water storage depletion within the SWRB cannot be ignored. In addition, insufficient water regulation capacity in the SRB deserves adequate attention. Full article

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