Remote Sensing

22 pages, 3852 KB

Open AccessArticle

Radiometric Sensitivity Requirements for Detecting Live Coral and Seagrass Cover Using Spaceborne Imaging Spectroscopy

by Tim J. Malthus, Elizabeth J. Botha, Joshua Pease, Chris Roelfsema, Mitchell Lyons, Courtney Bright, David R. Thompson, Arnold G. Dekker, David R. Ardila, Robert O. Green and Alex Held

Remote Sens. 2026, 18(15), 2643; https://doi.org/10.3390/rs18152643 - 6 Aug 2026

Cited by 1 | Viewed by 545

Abstract

Detecting changes in coral and seagrass habitat composition from satellite imagery places exceptionally high demands on sensor design due to low underwater reflectance signals and variable water column conditions. Recent multispectral satellite-based attempts to assess such changes across large spatial extents illustrate this [...] Read more.

Detecting changes in coral and seagrass habitat composition from satellite imagery places exceptionally high demands on sensor design due to low underwater reflectance signals and variable water column conditions. Recent multispectral satellite-based attempts to assess such changes across large spatial extents illustrate this challenge through an inability to reliably distinguish live coral from algae, often resulting in broad confidence intervals. This study quantifies the radiometric sensitivity requirements for detecting 10% absolute changes in live coral and seagrass fractional cover from spaceborne imaging spectroscopy using representative parameters for an aquatic imaging spectrometer. The analysis combined representative benthic spectra with realistic, management-relevant co-occurrence scenarios informed by extensive regional knowledge and field measurements from Fiji, Australia, and the Solomon Islands to evaluate detection performance across depths from 0 to 30 m. We show that live coral is the most demanding of the benthic targets evaluated because of its low reflectance and spectral similarity to algal cover types, requiring SNRs of approximately 300–700 to detect 10% absolute changes in cover at depths up to 10 m. In contrast, the greater spectral separation between seagrass and adjacent sandy substrates allows detection of 10% absolute changes in cover to depths exceeding 20 m in clear water. These results highlight the importance of high radiometric sensitivity and contiguous spectral sampling for future aquatic imaging spectrometers intended to monitor benthic change. Approaches that increase effective SNR, such as ground motion compensation (GMC), can extend the depth and confidence with which changes in benthic composition are detected, supporting a transition from broad-area habitat mapping toward quantitative monitoring of benthic change from space. Full article

(This article belongs to the Section Satellite Missions for Earth and Planetary Exploration)

► Show Figures

Figure 1

25 pages, 10987 KB

Open AccessArticle

Trait-Specific Contributions of UAV Multispectral, RGB and Structural Features to Soybean SPAD and Plant Height Phenotyping

by Qing Li, Dalei Hao, Wenfeng Liu, Renan Caldas Umburanas and Yelu Zeng

Remote Sens. 2026, 18(15), 2642; https://doi.org/10.3390/rs18152642 - 6 Aug 2026

Viewed by 332

Abstract

Unmanned aerial vehicle (UAV) imagery can support plot-scale crop phenotyping, but spectral, RGB and structural predictors may contribute differently to different traits. We compared six predefined feature groups for predicting soybean SPAD and plant height (PH) in a 1.3 ha field experiment in [...] Read more.

Unmanned aerial vehicle (UAV) imagery can support plot-scale crop phenotyping, but spectral, RGB and structural predictors may contribute differently to different traits. We compared six predefined feature groups for predicting soybean SPAD and plant height (PH) in a 1.3 ha field experiment in Sanya, China. The field contained 6197 soybean planting plots, of which 234 had paired SPAD and PH measurements. Multispectral bands, vegetation indices (VIs), RGB descriptors and digital surface model (DSM) metrics were extracted from DJI Mavic 3 Multispectral imagery. Six regression algorithms were evaluated using random fivefold cross-validation, spatial block cross-validation and nested spatial cross-validation. Under random cross-validation, ExtraTrees with multispectral bands, VIs and RGB descriptors produced the numerically highest SPAD performance (R² = 0.589; RMSE = 6.66), while BayesianRidge with multispectral bands, VIs and DSM metrics produced the highest PH performance (R² = 0.760; RMSE = 7.14 cm). Nested spatial cross-validation yielded R² = 0.473 and RMSE = 7.56 for SPAD and R² = 0.690 and RMSE = 8.13 cm for PH. G4 was selected in four of the five outer folds for SPAD, although the selected algorithm varied, and G5 was selected in all five outer folds for PH. VIs improved prediction of both traits relative to the original bands. Adding RGB descriptors produced only a small and model-dependent improvement for SPAD, whereas adding DSM metrics produced a larger and more consistent improvement for PH. The complete feature set did not outperform G4 for SPAD or G5 for PH. The retained models were applied to all 6197 plots to map SPAD, PH and their field relative combinations. Because all of the validations used one field and one UAV acquisition date, the results describe performance within this experiment and do not establish transferability to other sites, years or growth stages. Full article

(This article belongs to the Special Issue Advanced Remote Sensing for Next-Generation Smart Agriculture: Innovations, Integration, and Applications)

► Show Figures

Figure 1

35 pages, 13924 KB

Open AccessArticle

A Hybrid Multicriteria Index for Assessing Documentary-Methodological Robustness in Flood Mapping: Integrating Documentary Evidence, Entropy-Based Weighting, Remote Sensing, DEMs, Hydrological Data, and Statistical Validation

by Jamilton Echeverri-Díaz, Oscar E. Coronado-Hernández and Modesto Pérez-Sánchez

Remote Sens. 2026, 18(15), 2641; https://doi.org/10.3390/rs18152641 - 6 Aug 2026

Viewed by 378

Abstract

Flood dynamics can be represented using a growing diversity of remote-sensing sources, digital elevation models (DEMs), hydrological/hydraulic models, and statistical validation techniques. However, no unified evidence-based framework is currently available for systematically comparing the documentary-methodological support of these alternatives. This study proposes a [...] Read more.

Flood dynamics can be represented using a growing diversity of remote-sensing sources, digital elevation models (DEMs), hydrological/hydraulic models, and statistical validation techniques. However, no unified evidence-based framework is currently available for systematically comparing the documentary-methodological support of these alternatives. This study proposes a hybrid multicriteria index for assessing the documentary-methodological robustness of flood-mapping methodologies integrating remote sensing, DEMs, hydrological/hydraulic information, and statistical validation methods. Here, documentary-methodological robustness refers to the recurrence, traceability, structural support, and reporting consistency of methodological alternatives within the reviewed corpus; it does not represent technical accuracy, predictive performance, local suitability, or universal methodological superiority. A global documentary review comprising 173 case-study records was organized into six thematic dimensions: optical imagery, SAR imagery, image fusion, DEM information, hydrological/hydraulic information, and statistical validation. Variables and categories were normalized on a 0–1 scale and integrated into thematic base indices using a hybrid weighting strategy that combines author-defined methodological relevance with entropy-derived objective weights. A documentary coverage adjustment was incorporated to account for unequal representation among thematic dimensions. The results showed stronger documentary-methodological support for optical imagery and hydrological/hydraulic information, particularly for Landsat, NDWI, change detection, discharge data, water levels, and hydrodynamic modelling. SAR, image fusion, DEM, and statistical validation dimensions showed comparatively lower but still relevant documentary support. Sensitivity analysis across five

λ

scenarios showed that five of the six representative methodological combinations retained their robustness class, whereas only the IRIH combination shifted from high to very high robustness. The proposed framework transforms a descriptive review into a quantitative and replicable decision-support instrument for screening methodological alternatives according to their documentary-methodological support. Independent empirical validation remains necessary before selecting a methodology for operational application. Full article

► Show Figures

Figure 1

18 pages, 4727 KB

Open AccessArticle

High-Squint Imaging Method for Spaceborne Bistatic SAR Considering Orbit Curvature Effect

by Congrui Yang, Weikun Yang and Haixia Yue

Remote Sens. 2026, 18(15), 2640; https://doi.org/10.3390/rs18152640 - 6 Aug 2026

Viewed by 233

Abstract

Bistatic Synthetic Aperture Radar (BiSAR) is an advanced radar imaging system in which the transmitter and receiver platforms are positioned at distinct spatial locations. This separated transmit–receive architecture enables coordinated observation of the target scene. In particular, the highly squinted spaceborne bistatic configuration [...] Read more.

Bistatic Synthetic Aperture Radar (BiSAR) is an advanced radar imaging system in which the transmitter and receiver platforms are positioned at distinct spatial locations. This separated transmit–receive architecture enables coordinated observation of the target scene. In particular, the highly squinted spaceborne bistatic configuration offers advantages in multi-angle observation, overcoming the insensitivity of conventional spaceborne interferometric SAR (InSAR) to north–south surface deformations, thereby enabling efficient and high-precision measurement of global three-dimensional (3D) surface deformations, which holds significant engineering application value. Focusing on the highly squinted spaceborne BiSAR imaging geometric model, this paper proposes a novel highly squinted imaging method based on a high-order model. Traditional imaging algorithms are founded on straight-line models and employ the method of series reversion (MSR) to achieve imaging. In contrast, the proposed method is specifically tailored to the highly squinted bistatic observation geometry, fully accommodating orbital curvature effects while simultaneously resolving the imaging challenges posed by two-dimensional (2D) spatial variations of imaging parameters. In this method, control points are judiciously distributed within the observation scene, and the imaging parameters are solved via high-order polynomial fitting. Based on this foundation, the 2D spectrum expression for the highly squinted bistatic configuration is rigorously derived, together with the frequency-domain resampling mapping relation that compensates for the 2D spatial variation of imaging parameters, thereby achieving full-scene high-accuracy focused imaging. The proposed approach broadens the applicability of conventional straight-line-model-based algorithms and is well suited for highly squinted bistatic SAR imaging. The validity of the method is ultimately demonstrated via extensive simulation experiments and thorough performance evaluations. Full article

(This article belongs to the Special Issue Advances in Bistatic and Multistatic SAR Technology)

► Show Figures

Figure 1

25 pages, 11576 KB

Open AccessArticle

Spatial Pattern of Extreme Rainfall-Induced Forest Aboveground Biomass Loss and Its Influencing Factors in the Tableland-Gully Region of the Loess Plateau, China

by Xiaoqing Luo, Yayi Li, Menghan Yang, Yuhang Zhang, Jiaxi Wang, Mengmeng Li, Runqiu Deng, Feng Yang and Juying Jiao

Remote Sens. 2026, 18(15), 2639; https://doi.org/10.3390/rs18152639 - 6 Aug 2026

Viewed by 310

Abstract

Extreme rainfall-induced forest aboveground biomass (AGB) loss poses a serious threat to ecosystem stability and carbon stocks amid intensifying climate extremes. However, quantitative assessments of this loss remain scarce, and the spatial patterns of biomass loss and the nonlinear effects of its controlling [...] Read more.

Extreme rainfall-induced forest aboveground biomass (AGB) loss poses a serious threat to ecosystem stability and carbon stocks amid intensifying climate extremes. However, quantitative assessments of this loss remain scarce, and the spatial patterns of biomass loss and the nonlinear effects of its controlling factors have been insufficiently explored. This study used a typical extreme rainfall event (26–29 July 2023) in the tableland-gully region of the Loess Plateau as a case study to quantify the spatial patterns of forest AGB loss and to disentangle the nonlinear responses of its controlling factors. GF-7 (0.65 m) and GF-2 (1 m) imagery, combined with band differencing and object-based image analysis (OBIA), were used to identify forest AGB loss patches. To enable patch-level loss estimation, the 30 m AGB dataset was statistically downscaled to 1 m. Global Moran’s I and Getis-Ord Gi* statistics were applied to characterize spatial clustering, and an XGBoost model coupled with Shapley Additive Explanations (SHAP) was employed to identify dominant predictors and their nonlinear responses. This event triggered a total of 67,855 forest AGB loss patches (overall accuracy = 0.93; F1 score = 0.93), with a cumulative area of 17.29 km² and a total loss of 119,825.38 Mg. AGB loss exhibited significant spatial clustering, displaying a west-high–east-low gradient consistent with rainfall distribution. Cumulative rainfall was the dominant predictor; the median grain size of the Last Glacial Maximum loess unit (L1-1 MD), elevation, proximity to roads and rivers, fractional vegetation cover (FVC), and slope aspect contributed additional spatial variation through distinct nonlinear relationships. These findings provide a quantitative basis for event-scale assessment of extreme rainfall-induced forest carbon loss and for informing vegetation restoration and carbon conservation strategies under climate extremes. Full article

(This article belongs to the Special Issue Multi-Temporal Remote Sensing of Forest Disturbance: Detection, Mapping and Impact Assessment)

► Show Figures

Figure 1

21 pages, 3025 KB

Open AccessArticle

TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split

by Yu Li, Jinxin He, Yongzhi Wang, Ye Zhan, Yongbin Yang and Hanya Zhang

Remote Sens. 2026, 18(15), 2638; https://doi.org/10.3390/rs18152638 - 6 Aug 2026

Viewed by 300

Abstract

Martian landslide segmentation is challenging because annotated samples are limited and landslide deposits can have weak boundaries, heterogeneous textures, and visual similarity to crater rims and canyon walls. This study evaluates a terrain-residual and boundary-assisted network (TRB-Net) on the locally available MMLSv2 train/validation/test [...] Read more.

Martian landslide segmentation is challenging because annotated samples are limited and landslide deposits can have weak boundaries, heterogeneous textures, and visual similarity to crater rims and canyon walls. This study evaluates a terrain-residual and boundary-assisted network (TRB-Net) on the locally available MMLSv2 train/validation/test split. TRB-Net combines RGB texture with digital elevation model (DEM), slope, thermal inertia, and grayscale information through terrain-residual fusion, an atrous spatial pyramid pooling decoder, and auxiliary boundary supervision. The compact evaluation checkpoint, using a validation-selected threshold of 0.55, achieves an mIoU of 0.8060, foreground IoU of 0.7502, F1-score of 0.8573, precision of 0.8473, and recall of 0.8676 with 5.255 million parameters. In same-split comparisons, DeepLabV3+ obtains the highest overlap scores, while TRB-Net provides competitive segmentation and an explicit architecture for tracing how terrain and boundary cues enter the prediction. These results apply only to the local MMLSv2 split; geographically isolated and large-area Martian mapping performance were not evaluated. Full article

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

► Show Figures

Figure 1

22 pages, 4414 KB

Open AccessArticle

A China-Specific Near-Real-Time GNSS Water Vapor Retrieval Model Based on LightGBM

by Mingchen Zhu, Hui Chang, Zhikang Li, Qian Zhang and Xingwang Fan

Remote Sens. 2026, 18(15), 2637; https://doi.org/10.3390/rs18152637 - 6 Aug 2026

Viewed by 277

Abstract

Atmospheric water vapor is a key atmospheric variable that regulates weather variability, the hydrological cycle, and climate processes. GNSS-based water vapor retrieval provides an effective approach for continuous and near-real-time monitoring of atmospheric water vapor. However, conventional meteorology-independent models still have limitations in [...] Read more.

Atmospheric water vapor is a key atmospheric variable that regulates weather variability, the hydrological cycle, and climate processes. GNSS-based water vapor retrieval provides an effective approach for continuous and near-real-time monitoring of atmospheric water vapor. However, conventional meteorology-independent models still have limitations in regional adaptability, vertical accuracy, and the representation of nonlinear atmospheric variability. To address these limitations, this study proposes a China-specific near-real-time GNSS water vapor retrieval model, termed China LightGBM-based Zenith Hydrostatic Delay and Precipitable Water Vapor Model (CLZP), by integrating LightGBM with near-real-time GNSS observations. First, a high-accuracy gridded ZHD model, CLZP-ZHD, was developed using LightGBM to estimate ZHD from the surface to near the tropopause. Subsequently, a PWV residual compensation model, CLZP-PWV, was developed by incorporating multi-source features, including near-real-time GNSS ZTD, to mitigate error propagation in PWV retrieval. Validation results from both ERA5 and independent radiosonde datasets indicate that CLZP-ZHD reduces RMSE by approximately 25.4% and 28.2% relative to GPT3-ZHD and CTrop-ZHD in the ERA5-based validation, and by 21.7% and 23.0% in the radiosonde-based validation, respectively, while maintaining stable accuracy across different heights. For PWV retrieval, the ERA5-based validation of CLZP-PWV shows that it reduces RMSE by approximately 32.7% and 38.2% relative to GPT3-PWV and CTrop-PWV, respectively, and demonstrates improved performance in humid and climatically complex regions. These results suggest that, once trained, CLZP improves the accuracy and stability of near-real-time GNSS water vapor retrieval over China without requiring in situ meteorological observations during operational application, providing a practical approach for regional GNSS meteorological applications. Full article

(This article belongs to the Special Issue Recent Progress in Monitoring the Troposphere with GNSS Techniques)

► Show Figures

Figure 1

36 pages, 12349 KB

Open AccessArticle

Robust Wheat Residue Cover Quantification Under Moisture Variability from ASD Spectroscopy Using Conditional Autoencoder Normalization and Linear Unmixing

by Nabil Farah, Rachid Bouabid, Jamal-Eddine Ouzemou, Abdelghani Chehbouni, Nawfel Roudies and Ahmed Laamrani

Remote Sens. 2026, 18(15), 2636; https://doi.org/10.3390/rs18152636 - 6 Aug 2026

Viewed by 515

Abstract

Crop residue cover (CRC) plays a crucial role in sustainable farming systems by improving soil structure, regulating water retention, and reducing soil erosion. Accurate CRC monitoring is therefore important for evaluating field management practices at scale. Existing field methods (e.g., line-transect and visual [...] Read more.

Crop residue cover (CRC) plays a crucial role in sustainable farming systems by improving soil structure, regulating water retention, and reducing soil erosion. Accurate CRC monitoring is therefore important for evaluating field management practices at scale. Existing field methods (e.g., line-transect and visual estimation) are labor-intensive and difficult to scale, while optical retrievals are often confounded by soil moisture. Moisture introduces nonlinear spectral distortions that can bias residue estimates, particularly in the shortwave infrared range. We propose a Deep Moisture-Invariant Autoencoder (DMIA) framework that performs conditional spectral normalization—referred to as moisture normalization (dry-equivalent spectral transformation)—before linear spectral unmixing. The workflow has two stages: (1) a conditional autoencoder that transforms moisture-affected spectra to dry-equivalent spectra, and (2) fully constrained linear unmixing on dry-equivalent spectra. The experiment included 63 controlled wheat-residue scenes at a semi-arid site in Morocco, spanning three moisture levels and seven residue proportions (0–100%) measured with ASD spectroscopy. Within this controlled experimental dataset, DMIA achieved a global coefficient of determination of R² = 0.93, outperforming ordinary least squares (R² = 0.65), fully constrained least squares (R² = 0.68), and ELMM (R² = 0.71), and matching the performance of MESMA (R² = 0.93) while requiring only a single forward pass at inference rather than iterative library matching. Although both methods showed similar overall accuracy, a closer analysis reveals that DMIA’s advantage over MESMA widens under wetter, coarser-resolution conditions, which are highly representative of operational monitoring. This finding is further validated by a Monte Carlo uncertainty propagation, proving the results are unaffected by reference noise. Using spectrally resampled ground data to simulate satellite responses, performance remained robust for PRISMA (R² = 0.93) and Sentinel-2 simulation (R² = 0.87). Reconstruction diagnostics (mean SAM below 5°) support the physical plausibility of the learned transformation. These results suggest that conditional spectral normalization can reduce moisture-related distortions while preserving compositional signals under controlled experimental conditions; however, the use of three discrete moisture levels represents an experimental simplification; in open operational fields, soil moisture varies continuously and pixel-level states are unknown. This framework provides a proof-of-concept basis for further investigation across diverse soils, residue types, and operational sensor configurations. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Integrating Multi-Source Data for Precision Agriculture and Environmental Management)

► Show Figures

Figure 1

19 pages, 4834 KB

Open AccessArticle

Machine Learning-Based Atmospheric Radiation Calculation Incorporating Earth Curvature

by Qingyang Gu, Kun Wu, Xinyi Wang, Mingze Yuan, Qizhe Xin and Zijie Xu

Remote Sens. 2026, 18(15), 2635; https://doi.org/10.3390/rs18152635 - 6 Aug 2026

Viewed by 272

Abstract

Plane-parallel atmospheric radiative transfer models neglect the Earth’s curvature, resulting in substantial optical path errors at large zenith angles and limiting the accuracy of satellite remote sensing retrievals. Fully spherical Monte Carlo models can accurately represent curvature and multiple-scattering effects, but their high [...] Read more.

Plane-parallel atmospheric radiative transfer models neglect the Earth’s curvature, resulting in substantial optical path errors at large zenith angles and limiting the accuracy of satellite remote sensing retrievals. Fully spherical Monte Carlo models can accurately represent curvature and multiple-scattering effects, but their high computational cost limits their application in rapid or operational calculations. Pseudo-spherical approximations offer greater computational efficiency but generally retain plane-parallel assumptions for multiple scattering, which may reduce their accuracy in aerosol- and cloud-laden atmospheres. To address these limitations, this study develops a physics-guided, data-driven framework for efficient spherical radiance estimation. Reference spherical radiances were generated using a Monte Carlo radiative transfer model for representative clear-sky, aerosol-laden, and cloudy atmospheric scenarios. An extreme gradient boosting (XGBoost) model was then trained to map plane-parallel radiances to their spherical counterparts at wavelengths of 450, 550, and 650 nm. The predictors included wavelength, solar zenith angle (SZA), viewing zenith angle, azimuth angle, asymmetry factor, surface albedo, optical depth, single scattering albedo, the central height of a single aerosol or cloud layer and plane-parallel radiance. On the independent test set, the XGBoost model achieved a mean absolute percentage error (MAPE) of 5.71%. For the common clear-sky subset used to compare all three methods, the corresponding MAPEs of the plane-parallel and pseudo-spherical models were 29.61% and 19.65%, respectively. These results indicate that the proposed model can substantially reduce curvature-related radiance errors while retaining high computational efficiency across the atmospheric scenarios considered in this study. Full article

(This article belongs to the Special Issue Novel Remote Sensing and Machine Learning Approaches for Aerosol and Cloud Physics Retrieval)

► Show Figures

Figure 1

24 pages, 36557 KB

Open AccessArticle

A Persistent Scatterer Interferometry-Based Parametric Framework for Characterizing Pre-, Co-, and Post-Seismic Surface Deformation: Application to the 2025 Dingri Earthquake (Southern Tibet)

by Evandro Balbi, Simone Barani, Leonardo Colavitti, Gabriele Tarchini, Shiba Subedi and Gabriele Ferretti

Remote Sens. 2026, 18(15), 2634; https://doi.org/10.3390/rs18152634 - 6 Aug 2026

Viewed by 610

Abstract

Persistent Scatterer Interferometry (PSI) provides dense and temporally continuous measurements of ground deformation, offering a robust framework for investigating, among other phenomena, earthquake-related surface deformation. However, most satellite-based investigations of large earthquakes remain focused on coseismic interferograms, source inversions, and short post-seismic observation [...] Read more.

Persistent Scatterer Interferometry (PSI) provides dense and temporally continuous measurements of ground deformation, offering a robust framework for investigating, among other phenomena, earthquake-related surface deformation. However, most satellite-based investigations of large earthquakes remain focused on coseismic interferograms, source inversions, and short post-seismic observation windows. In this study, we propose a PSI-based parametric approach that, given a Persistent Scatterer (PS) time series, uses a piecewise linear regression with an imposed coseismic step at the earthquake origin time to estimate the pre-event line-of-sight (LOS) velocity, the coseismic displacement step, and the post-event LOS velocity using ascending and descending satellite observations. The methodology is applied to the 7 January 2025 M_w 7.1 Dingri earthquake (southern Tibet), a recent large normal-faulting event for which previous studies have documented complex rupture behavior and significant co- and post-seismic surface deformation. The results show that our PSI-based approach enables, within a single framework, the isolation of the coseismic jump, the quantification of post-event velocity patterns, and the systematic comparison of pre- and post- event deformation. In addition, the combination of ascending and descending datasets yields a first-order reconstruction of the vertical and east–west deformation components. The proposed approach complements physics-based source modeling by offering a scalable, observation-driven, and point-wise characterization of deformation evolution. Full article

(This article belongs to the Special Issue InSAR Innovations: Advances in Remote Sensing for Geohazard Monitoring)

► Show Figures

Figure 1

21 pages, 16356 KB

Open AccessArticle

Comprehensive Use of GNSS Vertical Deformation and GRACE/GFO Data to Invert the Joint Drought Index of Three Central China Provinces

by Yinan Wang, Guangyu Xu, Tengxu Zhang and Leyang Wang

Remote Sens. 2026, 18(15), 2633; https://doi.org/10.3390/rs18152633 - 6 Aug 2026

Viewed by 249

Abstract

Terrestrial water storage (TWS) is a key parameter for understanding regional water cycles and climate change. To address the low spatial resolution and temporal gaps of Gravity Recovery and Climate Experiment (GRACE) and its successor satellites (GRACE Follow-On) data, as well as the [...] Read more.

Terrestrial water storage (TWS) is a key parameter for understanding regional water cycles and climate change. To address the low spatial resolution and temporal gaps of Gravity Recovery and Climate Experiment (GRACE) and its successor satellites (GRACE Follow-On) data, as well as the uneven spatial distribution of Global Navigation Satellite System (GNSS) stations, this study integrates GNSS vertical deformation with GRACE/GFO Mascon data to jointly invert and conduct an in-depth analysis of TWS changes and hydrological drought characteristics in three central Chinese provinces (Hubei, Hunan, and Jiangxi) from January 2011 to June 2023. For missing parts of GRACE and GNSS data, different methods were effectively employed to fill the gaps. The optimal weighting factors were then determined using the Akaike Bayesian Information Criterion (ABIC), leading to the inversion of TWS variations. Combined with hydrometeorological data (precipitation, evapotranspiration, and runoff), drought monitoring was further conducted. The results indicate that joint inversion effectively integrates the high-frequency spatial signals of GNSS with the large-scale smoothing features of GRACE. The spatial distribution of the annual TWS amplitude obtained from different methods (GRACE, GNSS-Green, GNSS-Slepian, and Joint) showed high consistency, generally exhibiting a pattern of lower values in the northwest and higher values in the southeast. Using the TWS derived from joint inversion, a drought index (Joint-DSI) was constructed, successfully identifying and tracking seven major drought events in the study area. Among these, the drought from April 2017 to November 2018 lasted the longest (20 months), while the event from August 2022 to June 2023 was the most severe, with a peak deficit of 142.303 km³. This study demonstrates that the joint inversion method can effectively overcome the spatiotemporal limitations of single observation techniques, providing a high-precision, high-resolution, and reliable geodetic approach for regional water resource management and extreme drought monitoring. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence and Multi-Source Remote Sensing for Surface Hydrology)

► Show Figures

Figure 1

26 pages, 38087 KB

Open AccessArticle

Fine-Scale Maturity Recognition of Eucalyptus Plantations Based on Deep Learning and Multimodal Feature Fusion

by Lizhi Liu, Jianwen Huang, Ying Guo, Qingwang Liu, Xin Tian, Erxue Chen, Zengyuan Li and Jie Zhang

Remote Sens. 2026, 18(15), 2632; https://doi.org/10.3390/rs18152632 - 6 Aug 2026

Viewed by 285

Abstract

Accurate identification of eucalyptus plantation maturity, which is hierarchically defined as young forests, middle-aged forests, and mature forests, corresponding to different growth and physiological development stages of eucalyptus stands, is critical for forestry management and sustainable development. Currently, research on fine-grained semantic segmentation [...] Read more.

Accurate identification of eucalyptus plantation maturity, which is hierarchically defined as young forests, middle-aged forests, and mature forests, corresponding to different growth and physiological development stages of eucalyptus stands, is critical for forestry management and sustainable development. Currently, research on fine-grained semantic segmentation of different eucalyptus growth stages remains insufficient, and there is a lack of systematic evaluation of classical deep learning architectures and multimodal data for eucalyptus plantation maturity identification. This limits the application of remote sensing technology in forestry management, and constrains the understanding of growth dynamics in subtropical planted forests. Taking Gaofeng Forest Farm in Nanning, Guangxi, as the study area, this study analyzes the adaptability of four generations of deep learning segmentation architectures—U-Net (convolutional baseline), Trans-UNet (CNN-Transformer hybrid), Swin-UNet (pure Transformer), and Mamba-UNet (state-space model)—in the fine identification of eucalyptus plantation maturity based on spectral indices (SIs), C-band SAR data (S1), and multispectral data (S2). The results show the following: (1) There is no positive correlation between model complexity and recognition performance. Among all architectures, Mamba-UNet achieves the best performance, with a validation set mIoU of 79.10% and an F1-score of 88.26%. The performance ranking of the different architectures evaluated is Mamba-UNet > Swin-UNet > U-Net > Trans-UNet. (2) The S2+SI combination achieves the highest accuracy (mIoU 79.10%), outperforming S2+S1+SI (78.55%), S2+S1 (78.38%), and single S2 (77.72%), which indicates the strong correlation between spectral indices and eucalyptus physiological characteristics. The backscattering features of S1 are limited by canopy penetration in the subtropical rainforest, introducing redundancy and triggering negative fusion effects. (3) Independent verification with field survey points verifies the strong generalization ability of the proposed approach, with OA of 94.08%, mIoU of 85.62%, Precision of 93.00%, Recall of 91.37% and F1-score of 92.15%, which indicates that the methodological framework can realize the identification of eucalyptus maturity with high precision. (4) Eucalyptus accounts for 60.15% of the total area of Gaofeng Forest Farm. Within the eucalyptus stand age structure, young, middle-aged, and mature forests account for 20.67%, 13.62%, and 25.86%, respectively. The overall distribution exhibits a polarized pattern with high proportions of young and mature forests. The findings offer theoretical support and insights for dynamic monitoring of fast-growing plantations and refined management of stand development stages. Full article

(This article belongs to the Special Issue Remote Sensing for Vegetation Dynamic Monitoring, Carbon and Ecological Assessment)

► Show Figures

Figure 1

34 pages, 16486 KB

Open AccessArticle

FAD-Net: Frequency Alignment Dual-Branch Network for Hyperspectral Image Super-Resolution

by Junge Bo, Chen Ling, Ji-Xuan He and Yanan Qiao

Remote Sens. 2026, 18(15), 2631; https://doi.org/10.3390/rs18152631 - 6 Aug 2026

Viewed by 308

Abstract

Hyperspectral image super-resolution (HSI SR) aims to recover high-resolution hyperspectral images from low-resolution observations while preserving spatial details and spectral fidelity. Accurate spectral preservation is a key distinction between HSI SR and natural image SR. Recent hybrid methods combining convolutional neural networks (CNNs) [...] Read more.

Hyperspectral image super-resolution (HSI SR) aims to recover high-resolution hyperspectral images from low-resolution observations while preserving spatial details and spectral fidelity. Accurate spectral preservation is a key distinction between HSI SR and natural image SR. Recent hybrid methods combining convolutional neural networks (CNNs) and Transformers have substantially improved spatial reconstruction performance, but spectral fidelity remains insufficiently explored. Our frequency perturbation analysis reveals that CNNs and Transformers exhibit complementary frequency-response characteristics. To explicitly exploit this complementarity, we propose a Frequency Alignment Dual-Branch Network (FAD-Net) for HSI SR. Specifically, the Multi-Scale Frequency Refinement Branch (MFRB) restores local high-frequency details through wavelet decomposition, while the Spatial–Spectral Frequency Interaction Branch (

S^{2}

FIB) models long-range spatial and spectral dependencies via window-based attention. The two branches are fused by a Frequency Alignment Block (FAB). During training, Hyperspectral Frequency Loss and Spectral Angle Mapper loss are further introduced to constrain the reconstructed results toward the ground truth. Experiments on Chikusei, Botswana, and Pavia Center at

\times 2

,

\times 3

, and

\times 4

scales show that FAD-Net achieves the best Spectral Angle Mapper (SAM) in all nine settings while maintaining competitive spatial performance. Full article

(This article belongs to the Special Issue Information Acquisition and Processing for Remote Sensing (IAP-RS))

► Show Figures

Figure 1

27 pages, 33398 KB

Open AccessArticle

Spatial Heterogeneity and Driving Mechanisms of Carbon Storage on the Chinese Loess Plateau

by Xiao Wang, Bing Liu, Arash Malekian, Wen Li, Pouyan Dehghan Rahimabadi, Bin Wang, Changkun Yang, Weihao Sun, Bekmamat Djenbaev, Davletbek Mamadzhanov and Reinhard Hinkelmann

Remote Sens. 2026, 18(15), 2630; https://doi.org/10.3390/rs18152630 - 6 Aug 2026

Viewed by 379

Abstract

The Chinese Loess Plateau is a vast semi-arid landscape that has experienced substantial vegetation recovery through afforestation since the late twentieth century, altering the regional carbon cycle and contributing to China’s carbon neutrality efforts. However, large-scale quantification of carbon storage (CS) remains challenging [...] Read more.

The Chinese Loess Plateau is a vast semi-arid landscape that has experienced substantial vegetation recovery through afforestation since the late twentieth century, altering the regional carbon cycle and contributing to China’s carbon neutrality efforts. However, large-scale quantification of carbon storage (CS) remains challenging in this heterogeneous and erosion-prone landscape. In this study, the PLUS land-use simulation model was coupled with an InVEST-based carbon storage accounting framework, and multi-source remote sensing and field survey data were integrated to quantify historical carbon storage from 1980 to 2020 and predict carbon storage in 2040 under three future land-use scenarios: natural development (ND), cultivated land protection (CLP), and ecological protection (EP). The results showed that NDVI exhibited a distinct southeast-to-northwest gradient, with peak values (>0.8) in the southeastern tablelands, where CS reached 10.27 ± 4.20 kg C m⁻². Carbon storage increased from 1980 to 2020, primarily due to afforestation, with higher CS in the humid southeastern plateau and lower CS in the arid northwest. Scenario simulation showed that CS maintained a baseline level of 7.07 ± 3.81 kg C m⁻² under the ND scenario, increased slightly to 7.08 ± 3.77 kg C m⁻² under the CLP scenario, and reached the highest value of 7.10 ± 3.80 kg C m⁻² under the EP scenario. SEM-based mechanism analysis indicated that topography exerted the strongest direct influence on CS, followed by vegetation, climate, and socioeconomic factors. These findings suggest that water availability and topographic constraints strongly regulate CS in semi-arid regions, while land-use policy can still modify CS through scenario-dependent land-use change. Full article

(This article belongs to the Special Issue Time-Series Mapping and Analysis of Land Surface Parameters and Changes Using Remote Sensing Data)

► Show Figures

Figure 1

19 pages, 28453 KB

Open AccessArticle

Joint Interpretation of Archaeological, Geological, Geophysical and Remotely Sensed Data for Fluvial Geomorphology: The Case of the Calore River Meander North of Benevento (Italy)

by Vincenzo Amato, Marilena Cozzolino, Vincenzo Gentile and Paolo Mauriello

Remote Sens. 2026, 18(15), 2629; https://doi.org/10.3390/rs18152629 - 6 Aug 2026

Viewed by 693

Abstract

This study presents a multidisciplinary investigation of the fluvial evolution of the northern meander of the Calore River at Cellarulo locality, near Benevento (southern Italy). The research integrates archaeological evidence, geological and geomorphological data, historical cartography, remote sensing imagery and geophysical surveys in [...] Read more.

This study presents a multidisciplinary investigation of the fluvial evolution of the northern meander of the Calore River at Cellarulo locality, near Benevento (southern Italy). The research integrates archaeological evidence, geological and geomorphological data, historical cartography, remote sensing imagery and geophysical surveys in a Geographic Information System (GIS) environment. Multi-temporal analysis of historical maps, aerial photographs and satellite images from 1824 to 2022 allowed the reconstruction of channel migration patterns and the identification of abandoned meanders and paleochannel traces. Stratigraphic data derived from boreholes revealed the presence of a channel of the Calore River dated at least in the Bronze Age (3900 years ago), abandoned in the nineteenth century. Geoelectrical investigations provided detailed information on subsurface resistivity anomalies, highlighting the presence of buried structures and possible ancient anthropogenic features located at shallow depths between 1 and 1.5 m. The combined interpretation of geomorphological, archaeological and geophysical data demonstrates significant data on the unveiling of an ancient river channel and its abandonment during the last 150 years, suggesting a strong interaction between natural fluvial dynamics and human occupation. The results confirm the effectiveness of an integrated multidisciplinary approach for reconstructing fluvial landscape evolution and for identifying buried archaeological and geomorphological features in complex floodplain environments. Full article

(This article belongs to the Special Issue Recent Achievements in Remote Sensing-Based Archaeological Research)

► Show Figures

Figure 1

29 pages, 49875 KB

Open AccessArticle

Multi-Agent Pipeline for Crop-Type Classification and Label Refinement Using Sentinel-1 SAR Time Series and Field-Level Temporal Features in the Nakasatsunai Region, Hokkaido

by Kohei Arai, Ria Maruta and Hiroshi Okumura

Remote Sens. 2026, 18(15), 2628; https://doi.org/10.3390/rs18152628 - 6 Aug 2026

Viewed by 320

Abstract

Reference labels for crop-type mapping are frequently coarse, and administrative land-use registries such as Japan’s eMAF (electronic Map of Agriculture and Forestry) database routinely group agronomically distinct crops under broad, ambiguous categories. This study addresses that problem for the Nakasatsunai region of Hokkaido, [...] Read more.

Reference labels for crop-type mapping are frequently coarse, and administrative land-use registries such as Japan’s eMAF (electronic Map of Agriculture and Forestry) database routinely group agronomically distinct crops under broad, ambiguous categories. This study addresses that problem for the Nakasatsunai region of Hokkaido, Japan, by combining Sentinel-1 synthetic aperture radar (SAR) time series with field-level optical vegetation-index analysis in a modular processing pipeline. The principal novelty of the work is not the pipeline architecture alone but a three-step, Normalized Difference Vegetation Index (NDVI)-driven label-refinement procedure—automatic removal of non-growing or low-amplitude field samples, Euclidean k-means subclass discovery within each coarse label, and trajectory-based label correction—that converts noisy nine-class eMAF labels into a more reliable training set prior to classifier training. The feature set combines the Radar Vegetation Index (RVI), VV and VH backscatter, the γVH/γVV polarization ratio, and NDVI, together with temporal-shape descriptors (phenological timing, peak magnitude, amplitude, maximum slope, and area under the curve) derived from monthly growth trajectories over the 2018 growing season. A Random Forest classifier, together with a gradient-boosting comparator, is evaluated before and after preprocessing under stratified k-fold cross-validation. Across n = 1208 field samples spanning the nine eMAF classes, classification accuracy improved from an overall accuracy of 71.8% on the raw labels to 82.6% after the three-step refinement; Cohen’s kappa increased from 0.63 to 0.77. Correlation analysis indicates that γVH/γVV tracks field-level NDVI more consistently (mean Pearson r = 0.68) than RVI does (mean Pearson r = 0.43) across the eight classes with sufficient samples, motivating its use as a SAR-only phenological proxy; this comparison is extended to the polarimetric PRVI, DPSVI, and DpRVI indices in the discussion. The underlying 80–90% label-accuracy estimate is derived from NDVI trajectory inspection rather than independent, field-surveyed ground truth, and a factorial ablation is used to characterize, to the extent the cross-validated evidence allows, how much of the reported accuracy gain is attributable to label-error correction as opposed to NDVI–SAR feature fusion; both this attribution and the label-accuracy estimate itself are identified as priorities for field validation in future work. The proposed framework is intended to convert coarse, noisy crop labels into a structured and reliable dataset while producing interpretable, field-level phenological insight for agricultural monitoring. Full article

(This article belongs to the Special Issue Remote Sensing and AI for Agricultural Land Mapping, Monitoring, and Management)

► Show Figures

Figure 1

31 pages, 981 KB

Open AccessArticle

Lightweight Bayesian SAR Image Object Detection and Recognition Method Based on Heavy-Tail Prior and Variational Inference

by Jiaqi Fang, Hemin Sun and Hongquan Li

Remote Sens. 2026, 18(15), 2627; https://doi.org/10.3390/rs18152627 - 6 Aug 2026

Viewed by 360

Abstract

Traditional Bayesian SAR detection methods suffer poor adaptability to speckle noise, fail to handle severe class imbalance within large-scale multi-target datasets, and incur prohibitive training overheads. To address these drawbacks, this paper develops a lightweight Bayesian detection and recognition framework built upon heavy-tailed [...] Read more.

Traditional Bayesian SAR detection methods suffer poor adaptability to speckle noise, fail to handle severe class imbalance within large-scale multi-target datasets, and incur prohibitive training overheads. To address these drawbacks, this paper develops a lightweight Bayesian detection and recognition framework built upon heavy-tailed Laplacian priors and variational inference. We adopt ResNet-50 as the feature extraction backbone and design a four-stage pipeline: First, a noise-aware Laplacian heavy-tailed prior is proposed to strengthen resistance against speckle outliers. Second, a multi-class variational inference module is constructed to eliminate detection bias induced by uneven sample distribution across target categories. Third, a lightweight uncertainty feedback strategy is introduced to cut computational costs for large-batch training. Evaluated on the MSAR-1.0 dataset, our approach achieves an mAP@0.5 of 94.98% and a macro balanced accuracy (

B A

) of 93.34%. Compared with existing Bayesian detectors, the mAP metric rises by 5.44–6.53%. The model only consumes 4.33 ms per inference frame and completes full training within 1.53 h on a single GPU. Ablation tests validate the independent and combined efficacy of all three core modules. This integrated architecture balances detection precision, classification reliability, and training efficiency, offering a promising prototype for multi-class SAR target interpretation under the evaluated benchmark constraints. Full article

(This article belongs to the Special Issue Recent Advances in SAR Images for Target Detection and Information Extraction)

► Show Figures

Figure 1

29 pages, 8074 KB

Open AccessArticle

Characterizing Free-Atmospheric Wind Fields and Their Statistical Associations with Aerosol Variability in the Huaihe River Basin

by Jianfeng Chen, Chenbo Xie and Yingjian Wang

Remote Sens. 2026, 18(15), 2626; https://doi.org/10.3390/rs18152626 - 6 Aug 2026

Viewed by 292

Abstract

The Huaihe River Basin (HRB) experiences pronounced seasonal circulation and recurrent aerosol pollution, yet continuous observations of wind structure above the atmospheric boundary layer remain limited. We integrate rotary Rayleigh Doppler wind lidar (RRDWL) measurements and radiosonde profiles with ERA5 re-analysis, MERRA-2 aerosol [...] Read more.

The Huaihe River Basin (HRB) experiences pronounced seasonal circulation and recurrent aerosol pollution, yet continuous observations of wind structure above the atmospheric boundary layer remain limited. We integrate rotary Rayleigh Doppler wind lidar (RRDWL) measurements and radiosonde profiles with ERA5 re-analysis, MERRA-2 aerosol optical depth (AOD), surface PM_2.5 observations, and selected HYSPLIT trajectories to characterize free-atmospheric wind variability and assess its statistical relationships with regional aerosol conditions. During periods of concurrent observation, RRDWL, radiosonde, and ERA5 profiles consistently capture the dominant features of the wind structure between 11 and 30 km, although agreement weakens near the tropopause. ERA5 data for 2017–2023 reveal pronounced seasonal variability, with stronger upper-tropospheric winds in spring, autumn, and winter than in summer. Enhanced boundary-layer ventilation generally coincides with lower surface PM_2.5 concentrations, but the strength and direction of this relationship vary among cities and time periods. The observed probability of elevated-PM_2.5 episodes is highest under westerly and northwesterly flow, while selected-event trajectories indicate air-mass pathways originating from, or passing through, western and northern sectors. Seasonal AOD distributions reveal substantial spatial and temporal variability in column-integrated aerosol loading. These results provide a vertically resolved, multi-dataset characterization of atmospheric wind variability over a monsoon-influenced basin and establish an observational framework for distinguishing statistical wind–aerosol relationships from mechanistic interpretations of aerosol transport. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

36 pages, 50473 KB

Open AccessArticle

Removal of RLAN Interference from C-Band Weather Radar Data: Algorithm and Case Studies

by Krystian Specht, Katarzyna Ośródka, Jan Szturc and Włodzimierz Freda

Remote Sens. 2026, 18(15), 2625; https://doi.org/10.3390/rs18152625 - 6 Aug 2026

Viewed by 518

Abstract

Interference in the local radio network (RLAN), referred to in this study as spike-type interference, is a significant problem in data from C-band weather radars, as it can degrade the accuracy of hydrometeor monitoring. The main challenge in removing these spikes is [...] Read more.

Interference in the local radio network (RLAN), referred to in this study as spike-type interference, is a significant problem in data from C-band weather radars, as it can degrade the accuracy of hydrometeor monitoring. The main challenge in removing these spikes is their spatial structure, particularly when they overlap with precipitation. At the Institute of Meteorology and Water Management—National Research Institute (IMGW-PIB), algorithms for removing such disturbances have been implemented as part of the RADVOL-QC system for radar data quality control. These algorithms primarily utilise polarimetric data. This paper describes them in detail and presents examples of how they work. Full article

(This article belongs to the Topic Radar Signal and Data Processing with Applications, 2nd Edition)

► Show Figures

Figure 1

30 pages, 7101 KB

Open AccessArticle

A Data-Driven InSAR Failure-Risk Index for Early Warning of Mining Infrastructure Instability: The Çöpler Case Study, İliç, Türkiye

by Mahmut Cavur

Remote Sens. 2026, 18(15), 2624; https://doi.org/10.3390/rs18152624 - 6 Aug 2026

Viewed by 431

Abstract

Failures at large-scale open-pit mines and tailing dams pose critical risks to human life, environmental systems, and economic sustainability. Although Interferometric Synthetic Aperture Radar (InSAR) has proven effective in detecting long-term surface deformation, a scientifically robust early-warning framework has not yet been established [...] Read more.

Failures at large-scale open-pit mines and tailing dams pose critical risks to human life, environmental systems, and economic sustainability. Although Interferometric Synthetic Aperture Radar (InSAR) has proven effective in detecting long-term surface deformation, a scientifically robust early-warning framework has not yet been established because standardized quantitative thresholds that are capable of distinguishing benign consolidation settlement from instability-driven deformation remain unavailable.InSAR has proven effective for detecting long-term surface deformation. However, a scientific early-warning framework has not yet been proposed or developed due to the absence of standardized quantitative thresholds that distinguish benign consolidation settlement from instability-driven deformation. This research proposes a novel InSAR-based Failure-Risk Index (FRI) that integrates displacement, velocity, and, most importantly, deformation acceleration into a single, normalized metric as an early warning system for mining infrastructure instability. The framework that we propose (i) emphasizes acceleration as a leading indicator of change in mechanical regime, (ii) incorporates a statistically guided separation of long-term consolidation settlement from anomalous deformation based on baseline variability, (iii) applies a statistical standardization and change-point detection system. The methodology is validated through a retrospective analysis of the heap leach failure—that occurred in Çöpler Gold Mine in Erzincan, Türkiye, on 13 February 2024—by using a set of Sentinel-1 time-series images collected between 2014 and 2024. The results prove that while displacement and velocity remained within ranges typically interpreted as stable, deformation acceleration exhibited a statistically significant increase that began around 2020, exceeded baseline variability by approximately two orders of magnitude, which is approximately four years before the collapse, and marked the onset of tertiary creep and progressive instability. The proposed FRI framework successfully captures this transition and provides a transferable, meaningful early-warning framework to support proactive risk management and improve the safety of mining infrastructure. Full article

► Show Figures

Figure 1

22 pages, 7908 KB

Open AccessArticle

Disentangling Spectrally Similar Urban Vegetation via Semantic Segmentation-Guided Object Analysis and Multi-Periodic Phenological Features

by Chenglong Zhu, Xi Cheng, Tao Liu, Haoyu Wang, Hao Lei, Haiyu Wang and Zhanfeng Shen

Remote Sens. 2026, 18(15), 2623; https://doi.org/10.3390/rs18152623 - 6 Aug 2026

Viewed by 246

Abstract

Fine-grained classification of urban green spaces (UGSs) is important for urban ecological assessment and management but remains challenging because of spectral similarity among vegetation types and inaccurate object delineation in complex urban environments. This study proposes a pixel-to-object framework that combines semantic segmentation-guided [...] Read more.

Fine-grained classification of urban green spaces (UGSs) is important for urban ecological assessment and management but remains challenging because of spectral similarity among vegetation types and inaccurate object delineation in complex urban environments. This study proposes a pixel-to-object framework that combines semantic segmentation-guided object construction with multi-periodic phenological modeling. A semantic green-space mask derived from 0.27 m very-high-resolution imagery constrains superpixel segmentation to generate spatially coherent, boundary-aware green space object-level patches (GSOPs). Pixel-level temporal representations are then derived from Sentinel-2 normalized difference vegetation index (NDVI) time series using TimesNet, aggregated into GSOP-level phenological features, and combined with spatial attributes to classify urban trees, grasslands, and farmlands. Applied to the built-up area of Chengdu, China, the framework achieved an overall accuracy of 91.6%, with F1-scores of 92.5%, 91.9%, and 87.6% for urban trees, grasslands, and farmlands, respectively. Ablation experiments showed that removing phenological features reduced overall accuracy by 13.1 percentage points and decreased the F1-scores of grasslands and farmlands by 16.0 and 23.0 percentage points, respectively. These results demonstrate that semantically constrained object delineation and phenological information jointly reduce boundary fragmentation and improve the discrimination of spectrally similar urban vegetation types. Full article

► Show Figures

Figure 1

36 pages, 7273 KB

Open AccessArticle

MSF-Net: A Multimodal SAR–Optical Fusion Network for Agricultural Land Use Classification in Smallholder Landscapes of Northern Benin

by Sabi Bruno Bio Nikki Sarè, Raffaele Gaetano, Yvon-Carmen Hountondji and Roberto Interdonato

Remote Sens. 2026, 18(15), 2622; https://doi.org/10.3390/rs18152622 - 6 Aug 2026

Viewed by 546

Abstract

Accurate crop type mapping in Sub-Saharan Africa is a challenging task, due to the presence of smallholder farming systems characterized by fragmented landscapes and heterogeneous cropping practices. Persistent cloud cover, particularly significant during the cropping season, systematically limits the exploitation of optical satellite [...] Read more.

Accurate crop type mapping in Sub-Saharan Africa is a challenging task, due to the presence of smallholder farming systems characterized by fragmented landscapes and heterogeneous cropping practices. Persistent cloud cover, particularly significant during the cropping season, systematically limits the exploitation of optical satellite image time series, making things even harder. This study proposes MSF-Net (Multimodal Sentinel Fusion Network), a convolutional neural network-based late-fusion framework that combines Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral time series for multi-class crop classification in the complex agricultural landscapes of central and northern Benin. The model was evaluated across six sites and three growing seasons (2022–2024) covering 12 land cover classes and compared with a Sentinel-2-only Temporal Convolutional Neural Network (TempCNN), a SAR-only baseline (S1-Branch), an ablated version of the proposed method, and two external state-of-the-art multimodal architectures, TSViT and TWINNS. MSF-Net achieved the highest or joint-highest overall accuracy in 10 of 14 site–year configurations, with overall accuracy ranging from 82.61% to 91.15% and kappa coefficients from 0.79 to 0.89, consistently outperforming both external baselines across all site–year configurations. The largest gains over TempCNN reached up to 30 percentage points for spectrally ambiguous classes such as Shrubby Savannah, Cotton, and Open Forest. In addition, MSF-Net produced more spatially coherent maps, with reduced salt-and-pepper noise, improved parcel-level homogeneity, and fewer modality-specific artefacts. These results demonstrate the value of SAR-optical fusion for operational crop monitoring in tropical West Africa. Full article

(This article belongs to the Special Issue Advances in Multi-Source Remote Sensing Data Fusion and Analysis)

► Show Figures

Figure 1

33 pages, 24281 KB

Open AccessArticle

Assessing Individual-Building Vertical Light Exposure in Urban Environments with a Residual Cascade Framework

by Xianghua Shi, Zhenxiang Ling, Zihao Zheng, Yingbiao Chen, Qinglan Qian, Zhifeng Wu, Jinnian Wang and Feng Gao

Remote Sens. 2026, 18(15), 2621; https://doi.org/10.3390/rs18152621 - 6 Aug 2026

Viewed by 219

Abstract

Artificial Light at Night (ALAN) is increasingly recognized as an environmental exposure in dense urban areas, where conventional two-dimensional nighttime-light remote sensing cannot adequately represent vertical illumination on building facades, while detailed three-dimensional simulations remain computationally expensive for wide-area application. To address this [...] Read more.

Artificial Light at Night (ALAN) is increasingly recognized as an environmental exposure in dense urban areas, where conventional two-dimensional nighttime-light remote sensing cannot adequately represent vertical illumination on building facades, while detailed three-dimensional simulations remain computationally expensive for wide-area application. To address this limitation, we developed the Physics-Informed Residual Cascade Framework (PIRCF) for estimating individual-building vertical light exposure from two-dimensional multisource geospatial data. Here, “physics-informed” refers to the incorporation of exposure-related geometric features, distance-related attenuation, spatial-topological relationships, and environmental occlusion priors as inductive biases, rather than the direct enforcement of physical governing equations in the loss function. PIRCF combines graph-based neighborhood inference with residual correction to represent both broad spatial relationships and localized environmental variation. In Guangzhou, the framework achieved

R^{2}

values of 0.78 for panchromatic exposure and 0.85 for blue-light exposure, outperforming the selected statistical baselines. In a zero-shot transfer experiment—that is, direct application of the Guangzhou-trained model to Shanghai without additional training or parameter adjustment—the corresponding

R^{2}

values were 0.70 and 0.73. The predicted patterns further indicated distinct spectral organizations: panchromatic exposure exhibited broader and more continuous gradients associated with the road network, whereas blue-light exposure showed more fragmented local clustering near commercial and vertically developed urban areas. These findings demonstrate the potential of PIRCF as a scalable screening tool for building-level urban light-exposure assessment and for prioritizing locations requiring more detailed field investigation. Full article

(This article belongs to the Special Issue Nighttime Light Remote Sensing Products for Sustainable Development Goals (SDGs))

► Show Figures

Figure 1

28 pages, 42013 KB

Open AccessArticle

HGRHDNet: Hierarchical Gated Residual Fusion and High-Frequency Guided Deformable Upsampler Network for Boundary-Enhanced Binary Urban Green Space Extraction

by Wang Man, Baoye Lin, Xiaofeng Du, Zigeng Song, Yuying Miao, Zhoupeng Ren, Qin Nie, Zongmei Li and Xinchang Zhang

Remote Sens. 2026, 18(15), 2620; https://doi.org/10.3390/rs18152620 - 6 Aug 2026

Viewed by 211

Abstract

High-resolution remote sensing imagery provides valuable data support for accurate binary urban green space extraction. However, due to complex urban backgrounds, existing methods still face challenges in accurately delineating green space boundaries and preserving fine-scale spatial details. To address these issues, this study [...] Read more.

High-resolution remote sensing imagery provides valuable data support for accurate binary urban green space extraction. However, due to complex urban backgrounds, existing methods still face challenges in accurately delineating green space boundaries and preserving fine-scale spatial details. To address these issues, this study proposes a novel network, termed Hierarchical Gated Residual Fusion and High-Frequency Guided Deformable Upsampler Network (HGRHDNet), for boundary-enhanced urban green space segmentation. The proposed framework adopts ConvNeXt-L as the encoder backbone and incorporates a Hierarchical Gated Residual Fusion Decoder (HGRFD) to adaptively fuse multi-scale features through dynamic weighting and residual feature propagation. In addition, a High-Frequency Guided Deformable Upsampler (HFGDU) is introduced to enhance high-frequency detail reconstruction and cross-resolution feature alignment, thereby improving boundary localization accuracy. The proposed method was evaluated on three public datasets with different spatial resolutions and spectral characteristics, including WHDLD, UGS-1m, and UBGG. Experimental results show that HGRHDNet achieves Boundary Intersection over Union (BIoU) values of 43.82%, 18.22%, and 64.55% on the three datasets, respectively, consistently outperforming state-of-the-art methods. Both quantitative and qualitative analyses demonstrate that HGRHDNet effectively preserves narrow gaps between adjacent green spaces, elongated vegetation structures, and fragmented green space patches while reducing boundary ambiguity in complex urban environments. These results indicate that HGRHDNet provides a robust and effective solution for high-resolution urban green space extraction and has considerable potential for applications in urban ecological assessment, green space inventory, and sustainable urban planning. Full article

(This article belongs to the Special Issue Applications of Remote Sensing in Landscapes and Human Settlements)

► Show Figures

Figure 1

25 pages, 27472 KB

Open AccessArticle

An Interpretable Uncertainty-Aware Framework for Landslide Susceptibility Mapping Based on Weak Supervision and Probabilistic Inference

by Boyun Yu, Weixuan Yuan, Takashi Oguchi, Kotaro Iizuka and Noé Delloye

Remote Sens. 2026, 18(15), 2619; https://doi.org/10.3390/rs18152619 - 6 Aug 2026

Viewed by 328

Abstract

Landslide susceptibility mapping infers future slope-failure potential from observed landslides. This inference is uncertain because locations without recorded failures cannot be confirmed as stable or used as reliable negatives, and incomplete inventories, geomorphic complexity, spatial representation, sampling, and model dependence further increase uncertainty. [...] Read more.

Landslide susceptibility mapping infers future slope-failure potential from observed landslides. This inference is uncertain because locations without recorded failures cannot be confirmed as stable or used as reliable negatives, and incomplete inventories, geomorphic complexity, spatial representation, sampling, and model dependence further increase uncertainty. To address these challenges, this study developed an interpretable, uncertainty-aware framework integrating joint SHAP–PFI feature assessment, weakly supervised negative-sample construction, and ensemble-based probabilistic inference. The framework yielded relative probabilistic susceptibility estimates, together with predictive uncertainty (

U_{p r e d}

), characterizing predictive ambiguity, and ensemble-based model uncertainty (

U_{m o d e l}

), characterizing bootstrap variability. The framework was applied in northern Noto, Japan, using a legacy inventory and an independent 2024 event-based landslide inventory at the pixel and slope-unit scales and across seven model families. Joint SHAP–PFI analysis combined contribution magnitude and predictive dependence to support scale-specific factor selection. Ablation analyses showed that weak supervision improved independent-event generalization and reduced uncertainty. For LightGBM, independent-positive Recall increased from 0.76 to 0.83,

U_{p r e d}

decreased from 0.18 to 0.065, and

U_{m o d e l}

from 0.019 to 0.0085. Ensemble learning quantified spatial uncertainty while maintaining independent-positive Recall comparable to both single-model controls. The framework was effective across tree-based, regression-based, and neural-network architectures, with LightGBM showing a stable cross-scale balance: independent-positive Recall was 0.83 and 0.77, and

U_{p r e d}

was 0.065 and 0.10 at the pixel and slope-unit scales, respectively. Spatial analysis further showed that uncertainty highlights areas where susceptibility estimates require caution. Overall, the framework quantifies and reduces uncertainty while improving independent-event generalization, thereby supporting more reliable landslide susceptibility assessment. Full article

(This article belongs to the Special Issue High-Resolution Remote Sensing Applications in Precision Geoscience and Infrastructure Planning)

► Show Figures

Figure 1

28 pages, 8163 KB

Open AccessArticle

Surface-Water Fragmentation and Heterogeneous Responses of Dish-Shaped Sub-Lakes in Poyang Lake During the 2022 Extreme Drought

by Chaoyang Li, Yuting Xu, Zhipeng He and Die Zhang

Remote Sens. 2026, 18(15), 2618; https://doi.org/10.3390/rs18152618 - 6 Aug 2026

Viewed by 364

Abstract

Extreme droughts can rapidly reshape surface-water patterns in river-connected floodplain wetlands, yet the fine-scale responses of individual dish-shaped sub-lakes remain insufficiently resolved. This study focused on the 2022 extreme drought in Poyang Lake, China’s largest freshwater lake and a globally important floodplain wetland [...] Read more.

Extreme droughts can rapidly reshape surface-water patterns in river-connected floodplain wetlands, yet the fine-scale responses of individual dish-shaped sub-lakes remain insufficiently resolved. This study focused on the 2022 extreme drought in Poyang Lake, China’s largest freshwater lake and a globally important floodplain wetland system. The objectives were to quantify wetland landscape changes during the 2022 extreme drought event and to compare the heterogeneous responses of dish-shaped sub-lakes under contrasting surface-water linkage and management-context settings. We developed a high-resolution wetland monitoring framework on the Google Earth Engine platform by integrating Sentinel-2 multispectral imagery, Sentinel-1 synthetic-aperture radar, and the Dynamic World land-cover product. This multi-source approach was designed to reduce spectral confusion among turbid water, saturated mudflats, and exposed lakebeds during extreme low-water stages. Monthly wetland maps were generated for the Poyang Lake National Nature Reserve and compared with a five-year historical baseline from 2017 to 2021. The framework achieved an overall accuracy of 87.44%, with a Kappa coefficient of 0.80. The results revealed a rapid wet-to-dry transition in 2022. The water area contracted by 78.1% from July to September and remained 73.6–74.7% below the historical baseline from September to November. This contraction was accompanied by extensive observable surface-water fragmentation, apparent loss of visible surface-water linkage among sub-lakes, and substantial wetland habitat contraction. Sub-lakes exhibited clearly differentiated drought responses. Sub-lakes with stronger visible surface-water linkage to the main lake generally experienced more rapid water loss during recession, whereas reserve-managed or facility-present sub-lakes retained residual water to varying degrees and may have provided important refugial habitats for waterbirds and aquatic species. These findings suggest that surface-water linkage condition, local topographic setting, and 2022 management context were jointly associated with the heterogeneous drought responses of sub-lakes. The proposed framework provides a tool for monitoring wetland landscape changes associated with extreme drought events, assessing ecological vulnerability, and supporting adaptive water-level management under intensifying climate extremes. Full article

(This article belongs to the Special Issue GeoAI and EO Big Data Driven Advances in Earth Environmental Science (Second Edition))

► Show Figures

Figure 1

32 pages, 50087 KB

Open AccessArticle

Landslide Susceptibility Evaluation Based on Deep Learning and Imbalanced Sampling at Multi-Scale

by Wei Chen, Yijing Zheng, Chao Guo, Caihua Liu, Paraskevas Tsangaratos, Ioanna Ilia and Xiaole Zheng

Remote Sens. 2026, 18(15), 2617; https://doi.org/10.3390/rs18152617 - 6 Aug 2026

Viewed by 377

Abstract

The main objective of the present study was to conduct landslide susceptibility assessment and zoning analysis based on multi-scale imbalanced sampling and deep learning methods. Jiangkou Town, China, was selected as the study area. Grid cells with resolutions of 12.5 m, 25 m, [...] Read more.

The main objective of the present study was to conduct landslide susceptibility assessment and zoning analysis based on multi-scale imbalanced sampling and deep learning methods. Jiangkou Town, China, was selected as the study area. Grid cells with resolutions of 12.5 m, 25 m, and 50 m were chosen. Imbalanced sampling was applied using landslide/non-landslide ratios of 1:1, 1:2, and 1:3 to construct multi-scale modeling datasets. Susceptibility conditioning factors were screened using the frequency ratio (FR), Pearson correlation coefficient, and multicollinearity diagnostics and nine factors were obtained: slope, aspect, plane curvature, profile curvature, lithology, distance to river, distance to fault, annual rainfall, and land use. Six models—Logistic Model Tree (LMT), Kernel Logistic Regression (KLR), EfficientNet, ResNet, Transformer, and U-Net—were selected to establish 54 susceptibility evaluation models under various combinations of resolution and sampling ratios. The predictive reliability of the models was evaluated using receiver operating characteristic (ROC) curves and Kappa coefficients. Among the evaluated configurations, ResNet at a 12.5 m resolution with a 1:3 sampling ratio was retained as the preferred overall mapping configuration. It achieved a validation AUC of 0.963 and a Kappa coefficient of 0.778, together with strong susceptibility-zonation selectivity. The highest individual Kappa coefficient (0.819) was obtained by ResNet at a 25 m resolution with a 1:3 sampling ratio. Thus, the preferred configuration was identified through an integrated interpretation of the validation AUC, Kappa agreement, and susceptibility-zonation performance rather than by maximizing a single metric. The landslide susceptibility maps produced were classified into five levels and validated using the landslide distribution, landslide density and frequency ratio within each susceptibility zone. Most models showed good predictive performance in areas characterized by very high and very low susceptibility. According to the results of the comparison of the different susceptibility levels, it appears that ResNet and EfficientNet produced the most similar spatial predictions, while ResNet and Transformer presented the largest deviations. The deviations are mainly located near river valleys and areas with intense human activity. The proposed methodological framework and results can support disaster prevention, land-use planning, and regional risk management, particularly in mountainous areas with complex geological and topographic conditions. Full article

(This article belongs to the Special Issue Application of Remote Sensing Approaches in Geohazard Risk (Second Edition))

► Show Figures

Figure 1

26 pages, 18039 KB

Open AccessArticle

LDM-PUNet: A Lightweight Network for Denoising and Phase Unwrapping SAR Interferograms in Mining Deformation Monitoring

by Qi Liu, Weitao Yan and Junjie Chen

Remote Sens. 2026, 18(15), 2616; https://doi.org/10.3390/rs18152616 - 6 Aug 2026

Viewed by 262

Abstract

Interferometric synthetic aperture radar (InSAR) enables large-scale, all-weather, day-and-night monitoring of surface deformation, but phase unwrapping remains challenging in mining areas with large-gradient deformation. Most conventional phase unwrapping methods rely on the Itoh condition. In mining interferograms, dense fringes, low coherence and deformation-related [...] Read more.

Interferometric synthetic aperture radar (InSAR) enables large-scale, all-weather, day-and-night monitoring of surface deformation, but phase unwrapping remains challenging in mining areas with large-gradient deformation. Most conventional phase unwrapping methods rely on the Itoh condition. In mining interferograms, dense fringes, low coherence and deformation-related noise can violate the Itoh condition, causing unwrapping errors to propagate into fragmented phase fields and unreliable deformation estimates. To address this problem, we propose a lightweight dilated multi-path phase unwrapping network, LDM-PUNet, for joint interferogram denoising and phase unwrapping in low-coherence mining environments. LDM-PUNet introduces multi-path parallel residual blocks with dilated depthwise separable convolutions to capture multi-scale fringe structures while reducing model complexity, and combines attention-based feature refinement with a phase-aware compound loss that integrates robust phase regression, wrapped-phase consistency and gradient consistency. To alleviate the shortage of labelled interferograms for mining deformation, we further develop a multi-effect deformation interferometric phase simulation strategy, M-DIPS, which generates training samples with controllable deformation, terrain, scattering, atmospheric and noise-related effects. Simulation tests were conducted on synthetic datasets with different deformation gradients and noise levels. LDM-PUNet improved RMSE accuracy by approximately 32.2–84.0% compared with the reference methods, while requiring only 0.02 s to process a single sample, demonstrating superior accuracy and efficiency. Real-data experiments in the Datong mining district and the 1071 working face of the Liangbei Coal Mine further demonstrate that, in long-term InSAR deformation monitoring, LDM-PUNet improves phase continuity and deformation inversion accuracy under dense fringes and decorrelation, producing highly consistent vertical displacement estimates. The proposed strategy and methods introduce deep learning into the time-series InSAR processing chain, providing an efficient and robust solution for rapid deformation monitoring in mining areas with large-gradient deformation. Full article

► Show Figures

Figure 1

25 pages, 9925 KB

Open AccessArticle

Remote Sensing-Based Identification of Sensitive Environmental Intervals Controlling Drought Propagation Time Across China

by Hu Tao, Yibo Wang, Zhongyang Zhang and Zeyong Gao

Remote Sens. 2026, 18(15), 2615; https://doi.org/10.3390/rs18152615 - 6 Aug 2026

Viewed by 199

Abstract

Drought early warning is important for reducing agricultural production risks and ensuring regional water security. However, existing warning systems often focus on drought propagation probabilities and average propagation times, with insufficient attention to the identification of changes in propagation time. This study constructs [...] Read more.

Drought early warning is important for reducing agricultural production risks and ensuring regional water security. However, existing warning systems often focus on drought propagation probabilities and average propagation times, with insufficient attention to the identification of changes in propagation time. This study constructs a meteorological drought–soil drought–groundwater drought propagation chain and uses both Granger causality and the maximum positive correlation coefficient method to quantify stage-specific propagation time. Random forest, PDP/LOWESS, and SHAP analyses are then applied to identify important environmental factors and determine their cross-method sensitive intervals. The results show that PET, NDVI, mean annual precipitation, and temperature exhibit high importance across multiple regions and stages. Additionally, sensitive intervals in which important environmental factors significantly affect propagation time were found. In Stage 1 in North China, the effect of the NDVI on propagation time decreases after it exceeds about 0.1. In Stage 2 in Southeast China, temperatures around 17–18 °C are associated with shortened propagation times. The changes are inconsistent across regions and stages. When important factors enter or approach sensitive intervals, propagation time is more likely to change. The propagation time–important factor–sensitive interval analysis framework proposed in this study provides supplementary evidence for determining whether drought propagation time exhibits nonlinear sensitivity to important environmental factors. This framework provides a new perspective for assessing drought early warning needs. The identified sensitive intervals can help recognize environmental conditions associated with rapid changes in drought propagation time, providing additional information for drought risk assessment and region-specific early warning strategies. Full article

► Show Figures

Figure 1

25 pages, 5564 KB

Open AccessArticle

A Cross-System Remote Sensing Framework for Diagnosing Event-Scale Soil Wetting, Vertical Propagation, and Precipitation Thresholds Across China’s Croplands

by Pingfan Fu, Xiaojing Yang, Dongya Sun, Juan Lv, Yanping Qu, Yuesheng Yan, Haiyang Dai, Huaiwei Sun, Yubo Li, Hanlin Zheng and Hao Sun

Remote Sens. 2026, 18(15), 2614; https://doi.org/10.3390/rs18152614 - 6 Aug 2026

Viewed by 392

Abstract

Soil moisture (SM) remote sensing is widely used for agricultural drought monitoring, yet most applications still emphasize static moisture states rather than event-scale wetting responses. We developed an interpretable Earth observation (EO) framework to evaluate precipitation–SM product consistency and diagnose wetting processes across [...] Read more.

Soil moisture (SM) remote sensing is widely used for agricultural drought monitoring, yet most applications still emphasize static moisture states rather than event-scale wetting responses. We developed an interpretable Earth observation (EO) framework to evaluate precipitation–SM product consistency and diagnose wetting processes across China’s croplands. Multi-source precipitation and SM products, including ERA5-Land, Soil Moisture Active Passive (SMAP), Soil Moisture of China by in situ data (SMCI), Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), and Grid-based Precipitation dataset for Mainland China (CHM_PRE), were assessed using lagged consistency between rainfall forcing and relative soil moisture increments. The selected pairing was then used to model daily wetting increments at three depths with eXtreme Gradient Boosting (XGBoost), Shapley additive explanations (SHAPs), generalized additive models (GAMs), and quantile regression (QR). ERA5-Land precipitation paired with ERA5-Land SM showed the strongest reanalysis-constrained event-scale consistency (peak mean r = 0.43 at a 1-day lag), providing an internal-consistency baseline for comparison with independent satellite-derived combinations rather than an absolute accuracy ranking. EO-derived wetting signals showed depth-dependent lags, with a 1-day surface response and an approximately 2-day delayed profile signal at 28–100 cm; this pattern should not be interpreted as direct evidence of rapid physical infiltration to 100 cm. Precipitation transition thresholds followed a U-shaped dependence on antecedent wetness, with higher rainfall requirements under extremely dry and near-saturated states. These findings indicate that event-scale EO diagnostics can characterize product consistency, lagged wetting responses, and state-dependent precipitation thresholds, while same-system and deep-layer interpretations remain constrained by reanalysis coupling and model-assisted root-zone products. Full article

(This article belongs to the Special Issue Multi-Source Remote Sensing for Agricultural Water and Soil Management)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 15 (August-1 2026) – 210 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI