Remote Sensing

26 pages, 2860 KB

Open AccessReview

A Systematic Review on Remote Sensing of Dryland Ecological Integrity: Improvement in the Spatiotemporal Monitoring of Vegetation Is Required

by Andres Sutton, Adrian Fisher and Graciela Metternicht

Remote Sens. 2026, 18(1), 184; https://doi.org/10.3390/rs18010184 - 5 Jan 2026

Viewed by 619

Abstract

Remote sensing approaches to monitoring dryland ecosystem states and trends have been dominated by the binary distinction between degraded/non-degraded areas, leading to inconsistent results. We propose a different conceptual framework that better reflects the states and pressures of these ecosystems—ecological integrity—that is, the [...] Read more.

Remote sensing approaches to monitoring dryland ecosystem states and trends have been dominated by the binary distinction between degraded/non-degraded areas, leading to inconsistent results. We propose a different conceptual framework that better reflects the states and pressures of these ecosystems—ecological integrity—that is, the maintenance of ecosystem composition and its capacity to contribute to human needs and adapt to change. We systematically reviewed earth observation techniques for characterizing ecological integrity in trusted databases together with studies identified through expert-guided search. A total of 137 papers were included, and their metadata (i.e., location, year) and data (i.e., aspect of ecological integrity assessed, techniques employed) were analyzed. The results show that remote sensing ecological integrity is becoming an increasingly researched topic, especially in countries with extensive drylands. Vegetation was the most frequently monitored attribute and was often employed as an indicator of other attributes (i.e., soil and water quality) and as a key feature in approaches that aimed for a comprehensive ecosystem assessment. However, most of the literature employed the normalized difference vegetation index (NDVI) as a descriptor of vegetation characteristics (i.e., health, structure, cover), which has been shown not to be a good indicator of the litter/senescent vegetation components that tend to frequently dominate drylands. Methods to overcome this weakness have been identified, although more research is needed to demonstrate their application in ecological integrity monitoring. Specifically, knowledge gaps in the relationship between vegetation cover fractions (i.e., green, non-green, and bare soil), descriptors of ecosystem quality (e.g., soil condition or vegetation structure complexity), and management (i.e., how human intervention affects ecosystem quality) should be addressed. Notable potential has been identified in time series analysis as a means of operationalising remotely sensed vegetation fractional cover. Nevertheless, limitations in benchmarking must also be tackled for effective ecological integrity monitoring. Full article

(This article belongs to the Special Issue Remote Sensing and Modelling of Terrestrial Ecosystems Functioning)

► Show Figures

Figure 1

18 pages, 21035 KB

Open AccessArticle

Chlorophyll Retrieval in Sun Glint Region Based on VIIRS Rayleigh-Corrected Reflectance

by Dongyang Fu, Yan Wang, Bangyi Tao, Tianjing Luan, Yixian Zhu, Changpeng Li, Bei Liu, Guo Yu and Yongze Li

Remote Sens. 2026, 18(1), 183; https://doi.org/10.3390/rs18010183 - 5 Jan 2026

Viewed by 347

Abstract

Sun glint is commonly observed as interference in the imaging process of ocean color satellite sensors, making the extraction of water color information in sun glint-affected areas challenging and often leading to significant data gaps. The remote sensing baseline indices, calculated based on [...] Read more.

Sun glint is commonly observed as interference in the imaging process of ocean color satellite sensors, making the extraction of water color information in sun glint-affected areas challenging and often leading to significant data gaps. The remote sensing baseline indices, calculated based on Rayleigh-corrected reflectance (

R_{rc}

), are recognized as effective in reflecting water color variability in sun glint-affected regions. However, the accurate extraction of the

R_{rc}

baseline indices requires sun glint correction. The determination of sun glint correction coefficients for different bands lacks a clear methodology, and the currently available correction coefficients are not applicable to different sea regions. Therefore, this study focuses on the South China Sea, where VIIRS imagery is significantly affected by sun glint. Based on paired datasets comprising sun glint-affected and -unaffected images acquired over the same region on adjacent dates, sun glint correction coefficients for each spectral band were derived by maximizing the cosine similarity of histograms constructed from three baseline indices: SS486 (Spectral Shape index at 486 nm), CI551 (Color Index at 551 nm), and SS671 (Spectral Shape index at 671 nm). To further evaluate the effectiveness of the proposed correction, chlorophyll-a concentrations were retrieved using a Random Forest regression model trained with baseline indices derived from sun glint-free

R_{rc}

data and subsequently applied to baseline indices after sun glint correction. Comparative analyses of both baseline index extraction and chlorophyll-a retrieval demonstrate that the proposed optimal-value and mean-value correction approaches effectively mitigate sun glint effects. The mean sun glint correction coefficients

α

(443),

α

(486),

α

(551),

α

(671) and

α

(745) were determined to be 0.75, 0.83, 0.89, 0.95 and 0.94, respectively. These coefficients can be applied as sun glint correction coefficients for the VIIRS

R_{rc}

data in the South China Sea region. Furthermore, the proposed method for determining sun glint correction coefficients offers a transferable framework that can be extended to other sea areas. Full article

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

► Show Figures

Figure 1

21 pages, 4547 KB

Open AccessArticle

Attention-Gated U-Net for Robust Cross-Domain Plastic Waste Segmentation Using a UAV-Based Hyperspectral SWIR Sensor

by Soufyane Bouchelaghem, Marco Balsi and Monica Moroni

Remote Sens. 2026, 18(1), 182; https://doi.org/10.3390/rs18010182 - 5 Jan 2026

Viewed by 369

Abstract

The proliferation of plastic waste across natural ecosystems has created a global environmental and public health crisis. Monitoring plastic litter using remote sensing remains challenging due to the significant variability in terrain, lighting, and weather conditions. Although earlier approaches, including classical supervised machine [...] Read more.

The proliferation of plastic waste across natural ecosystems has created a global environmental and public health crisis. Monitoring plastic litter using remote sensing remains challenging due to the significant variability in terrain, lighting, and weather conditions. Although earlier approaches, including classical supervised machine learning techniques such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), applied to hyperspectral and multispectral data have shown promise in controlled settings, they often may face challenges in generalizing across diverse environmental conditions encountered in real-world scenarios. In this work, we present a deep learning framework for pixel-wise segmentation of plastic waste in short-wave infrared (900–1700 nm) hyperspectral imagery acquired from an Unmanned Aerial Vehicle (UAV). Our architecture integrates attention gates and residual connections within a U-Net backbone to enhance contextual modeling and spatial-spectral consistency. We introduce a multi-flight dataset spanning over 9 UAV missions across varied environmental settings, consisting of hyperspectral cubes with centimeter-level resolution. Using a leave-one-out cross-validation protocol, our model achieves test accuracy of up to 96.8% (average 90.5%) and a 91.1% F1 score, demonstrating robust generalization to unseen data collected in different environments. Compared to classical models, the deep network captures richer semantic representations, particularly under challenging conditions. This work offers a scalable and deployable tool for automated plastic waste monitoring and represents a significant advancement in remote environmental sensing. Full article

► Show Figures

Figure 1

28 pages, 4978 KB

Open AccessArticle

Oilseed Flax Yield Prediction in Arid Gansu, China Using a CNN–Informer Model and Multi-Source Spatio-Temporal Data

by Xingyu Li, Yue Li, Bin Yan, Yuhong Gao, Shunchang Su, Hui Zhou, Lianghe Kang, Huan Liu and Yongbiao Li

Remote Sens. 2026, 18(1), 181; https://doi.org/10.3390/rs18010181 - 5 Jan 2026

Cited by 1 | Viewed by 364

Abstract

Oilseed flax (Linum usitatissimum, L.) is an important specialty oilseed crop cultivated in arid and semi-arid regions, where timely, accurate yield prediction is crucial for regional oilseed security and agricultural decision-making. To address the lack of robust county-level yield prediction models [...] Read more.

Oilseed flax (Linum usitatissimum, L.) is an important specialty oilseed crop cultivated in arid and semi-arid regions, where timely, accurate yield prediction is crucial for regional oilseed security and agricultural decision-making. To address the lack of robust county-level yield prediction models for oilseed flax, this study proposes a CNN–Informer hybrid framework that integrates convolutional neural networks (CNNs) with the Informer architecture to model multi-source spatio-temporal data. Unlike conventional Transformer-based approaches, the proposed framework combines CNN-based local temporal feature extraction with the ProbSparse attention mechanism of Informer, enabling the efficient modeling of long-range temporal dependencies across multiple years while reducing the computational burden of attention-based time-series modeling. The model incorporates multi-source inputs, including remote sensing indices (NDVI, EVI, SAVI, KNDVI), TerraClimate meteorological variables, soil properties, and historical yield records. Comprehensive experiments conducted at the county level in Gansu Province, China, demonstrate that the CNN–Informer model consistently outperforms representative machine learning and deep learning baselines (Transformer, Informer, LSTM, and XGBoost), achieving an average performance of R² = 0.82, RMSE = 0.31 t/ha, MAE = 0.21 t/ha, and MAPE = 10.33%. Results from feature ablation and historical yield window analyses reveal that a three-year historical yield window yields optimal performance, with remote sensing features contributing most strongly to predictive accuracy, while meteorological and soil variables enhance spatial adaptability under heterogeneous environmental conditions. Model robustness was further verified through fivefold county-based spatial cross-validation, indicating stable performance and strong generalization capability in unseen regions. Overall, the proposed CNN–Informer framework provides a reliable and interpretable solution for county-level oilseed flax yield prediction and offers practical insights for precision management of specialty crops in arid and semi-arid regions. Full article

(This article belongs to the Topic Recent Advances in Artificial Intelligence for Security and Security for Artificial Intelligence)

► Show Figures

Figure 1

21 pages, 17692 KB

Open AccessTechnical Note

In-Orbit Assessment of Image Quality Metrics for the LuTan-1 SAR Satellite Constellation

by Mingxia Zhang, Liyuan Liu, Aichun Wang, Qijin Han, Minghui Hou and Yanru Li

Remote Sens. 2026, 18(1), 180; https://doi.org/10.3390/rs18010180 - 5 Jan 2026

Viewed by 342

Abstract

LuTan-1(LT-1) is the first Chinese civil L-band satellite constellation for geohazard observation, comprising LT-1A and LT-1B satellites. By employing interferometric altimetry and differential deformation measurement technologies, it achieves high-precision topographic mapping and establishes sub-millimeter-level deformation monitoring capabilities. To meet the high-precision measurement requirements [...] Read more.

LuTan-1(LT-1) is the first Chinese civil L-band satellite constellation for geohazard observation, comprising LT-1A and LT-1B satellites. By employing interferometric altimetry and differential deformation measurement technologies, it achieves high-precision topographic mapping and establishes sub-millimeter-level deformation monitoring capabilities. To meet the high-precision measurement requirements for applications such as topographic surveying and deformation monitoring, this study systematically evaluates four categories of image quality metrics—geometric, radiometric, and polarimetric characteristics, as well as orbital and baseline quality—based on in-orbit test data from the twin satellites. The test results demonstrate that all image quality indicators of the LT-1 SAR satellites meet the design specifications, confirming that the imagery can provide robust spatial technical support for applications including geological hazard monitoring, land resource investigation, earthquake assessment, disaster prevention and mitigation, fundamental surveying and mapping, and forestry monitoring. Full article

(This article belongs to the Special Issue Spaceborne SAR Calibration Technology)

► Show Figures

Graphical abstract

22 pages, 10194 KB

Open AccessArticle

MBFI-Net: Multi-Branch Feature Interaction Network for Semantic Change Detection

by Qing Ding, Fengyan Wang, Kaiyuan Sun, Weilong Chen, Mingchang Wang and Gui Cheng

Remote Sens. 2026, 18(1), 179; https://doi.org/10.3390/rs18010179 - 5 Jan 2026

Viewed by 353

Abstract

Semantic change detection (SCD) effectively captures ground object transition information within change regions, delivering more comprehensive and detailed results than binary change detection (BCD) tasks. The existing multi-task SCD models enable parallel processing of segmentation and BCD of bi-temporal remote sensing images, but [...] Read more.

Semantic change detection (SCD) effectively captures ground object transition information within change regions, delivering more comprehensive and detailed results than binary change detection (BCD) tasks. The existing multi-task SCD models enable parallel processing of segmentation and BCD of bi-temporal remote sensing images, but they still have shortcomings in feature mining, interaction, and cross-task transfer. To address these limitations, a multi-branch feature interaction network (MBFI-Net) is proposed. MBFI-Net designs parallel encoding branches with attention mechanisms that enhance semantic change perception by jointly modeling global contextual patterns and local details. In addition, MBFI-Net proposes bi-temporal feature interaction (BTFI) and cross-task feature transfer (CTFT) modules to improve feature diversity and representativeness, and combines with prior logical relationship constraints to improve SCD performance. Comparative and ablation studies on the SECOND and Landsat-SCD datasets highlight the superiority and robustness of MBFI-Net, which achieves SeKs of 0.2117 and 0.5543, respectively. Furthermore, MBFI-Net strikes a balance between SCD results and model complexity and has superior detection performance for semantic change categories with a small proportion. Full article

(This article belongs to the Special Issue Remote Sensing Image Change Detection and Feature Enhancement Based on Deep Learning)

► Show Figures

Figure 1

21 pages, 15843 KB

Open AccessArticle

A Feature-Enhanced Network-Based Target Detection Method for SAR Images of Ships in Complex Scenes

by Yunsheng Ba, Nan Xia, Weijia Lu and Junqiao Liu

Remote Sens. 2026, 18(1), 178; https://doi.org/10.3390/rs18010178 - 5 Jan 2026

Viewed by 294

Abstract

In the context of ship target detection with Synthetic Aperture Radar (SAR) images, misdetection and missed detection are often caused by complex background interference and the variability in target size. To address these challenges, this paper proposes an innovative method based on image [...] Read more.

In the context of ship target detection with Synthetic Aperture Radar (SAR) images, misdetection and missed detection are often caused by complex background interference and the variability in target size. To address these challenges, this paper proposes an innovative method based on image enhancement and feature fusion to reduce background noise and effectively handle the detection confusion caused by differences in ship sizes. Firstly, a feature-aware enhancement network is introduced, which preserves and strengthens the edge information of the target objects. Secondly, during the feature extraction phase, a dynamic hierarchical extraction module is proposed, significantly improving the feature capture ability of convolutional neural networks and overcoming the limitations of traditional fixed kernel receptive fields. Finally, a feature fusion module based on attention gating is employed to fully leverage the complementary information between the original and enhanced images, achieving precise modeling and efficient fusion of inter-feature correlations. The proposed method is integrated with the YOLOv8 detection framework for target detection. Experimental results in the publicly available SSDD and HRSID datasets demonstrate detection accuracies of 97.9% and 93.2%, respectively, thus validating the superiority and robustness of the proposed method. Full article

► Show Figures

Figure 1

27 pages, 3681 KB

Open AccessArticle

Absolute Radiometric Calibration of CAS500-1/AEISS-C: Reflectance-Based Vicarious Calibration and Cross-Calibration with Sentinel-2/MSI

by Kyung-Bae Choi, Kyoung-Wook Jin, Dong-Hwan Cha, Jin-Hyeok Choi, Yong-Han Jo, Kwang-Nyun Kim, Gwui-Bong Kang, Ho-Yeon Shin, Ji-Yun Lee, Eun-Young Kim and Yun Gon Lee

Remote Sens. 2026, 18(1), 177; https://doi.org/10.3390/rs18010177 - 5 Jan 2026

Viewed by 375

Abstract

The absolute radiometric calibration of a satellite sensor is an essential process that determines the coefficients required to convert the radiometric quantities of satellite images. This procedure is crucial for ensuring the applicability and enhancing the reliability of optical sensors onboard satellites. This [...] Read more.

The absolute radiometric calibration of a satellite sensor is an essential process that determines the coefficients required to convert the radiometric quantities of satellite images. This procedure is crucial for ensuring the applicability and enhancing the reliability of optical sensors onboard satellites. This study performs the absolute radiometric calibration of the Compact Advanced Satellite 500-1 (CAS500-1) Advanced Earth Imaging Sensor System-C (AEISS-C), a low Earth orbit satellite developed independently by Republic of Korea for precise ground observation. Field campaign using a tarp, an Analytical Spectral Devices FieldSpecIII spectroradiometer, and a MicrotopsII sunphotometer was conducted. Additionally, reflectance-based vicarious calibration was performed using observational data and the MODerate resolution atmospheric TRANsmission model (version 6) radiative transfer model (RTM). Cross-calibration was also performed using data from the Sentinel-2 MultiSpectral Instrument, RadCalNet observations, and MODIS Bidirectional nReflectance Distribution Function (BRDF) products (MCD43A1) to account for differences in spectral response functions, viewing/solar geometry, and atmospheric conditions between the two satellites. From these datasets, two correction factors were derived: the Spectral Band Adjustment Factor and the BRDF Correction Factor. CAS500-1/AEISS-C acquires satellite imagery using two Time Delay Integration (TDI) modes, and the absolute radiometric calibration coefficients were derived considering these TDI modes. The coefficient of determination (R²) ranged from 0.70 to 0.97 for the reflectance-based vicarious calibration and from 0.90 to 0.99 for the cross-calibration. For reflectance-based vicarious calibration, aerosol optical depth was identified as the primary source of uncertainty among atmospheric factors. For cross-calibration, the reference satellite and RTMs were the primary sources of uncertainty. The results of this study will support the monitoring of CAS500-1/AEISS-C, which produces high-resolution imagery with a spatial resolution of 2 m, and can serve as foundational material for absolute radiometric calibration procedures for other CAS500 satellites. Full article

(This article belongs to the Special Issue Advances in Calibration, Validation, and Quality Assurance for Optical Remote Sensors)

► Show Figures

Figure 1

22 pages, 5960 KB

Open AccessArticle

JFDet: Joint Fusion and Detection for Multimodal Remote Sensing Imagery

by Wenhao Xu and You Yang

Remote Sens. 2026, 18(1), 176; https://doi.org/10.3390/rs18010176 - 5 Jan 2026

Viewed by 322

Abstract

Multimodal remote sensing imagery, such as visible and infrared data, offers crucial complementary information that is vital for time-sensitive emergency applications like search and rescue or disaster monitoring, where robust detection under adverse conditions is essential. However, existing methods’ object detection performance is [...] Read more.

Multimodal remote sensing imagery, such as visible and infrared data, offers crucial complementary information that is vital for time-sensitive emergency applications like search and rescue or disaster monitoring, where robust detection under adverse conditions is essential. However, existing methods’ object detection performance is often suboptimal due to task-independent fusion and inherent modality inconsistency. To address this issue, we propose a joint fusion and detection approach for multimodal remote sensing imagery (JFDet). First, a gradient-enhanced residual module (GERM) is introduced to combine dense feature connections with gradient residual pathways, effectively enhancing structural representation and fine-grained texture details in fused images. For robust detection, we introduce a second-order channel attention (SOCA) mechanism and design a multi-scale contextual feature-encoding (MCFE) module to capture higher-order semantic dependencies, enrich multi-scale contextual information, and thereby improve the recognition of small and variably scaled objects. Furthermore, a dual-loss feedback strategy propagates detection loss to the fusion network, enabling adaptive synergy between low-level fusion and high-level detection. Experiments on the VEDAI and FLIR-ADAS datasets demonstrate that the proposed detection-driven fusion framework significantly improves both fusion quality and detection accuracy compared with state-of-the-art methods, highlighting its effectiveness and high potential for mission-critical multimodal remote sensing and time-sensitive application. 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

19 pages, 15134 KB

Open AccessArticle

An Optimized Approach for Methane Spectral Feature Extraction Under High-Humidity Conditions

by Yunze Li, Jun Wu, Wei Xiong, Dacheng Li, Yangyu Li, Anjing Wang and Fangxiao Cui

Remote Sens. 2026, 18(1), 175; https://doi.org/10.3390/rs18010175 - 5 Jan 2026

Viewed by 257

Abstract

Fourier transform infrared (FTIR) spectroscopy-based gas remote sensing has been widely applied for long-range atmospheric composition analysis. However, when deployed for longwave infrared methane detection, spectral features of methane are significantly interfered by water vapor variations at the edge of atmospheric window, which [...] Read more.

Fourier transform infrared (FTIR) spectroscopy-based gas remote sensing has been widely applied for long-range atmospheric composition analysis. However, when deployed for longwave infrared methane detection, spectral features of methane are significantly interfered by water vapor variations at the edge of atmospheric window, which compromises detection performance. To address the spectral fitting degradation caused by relative changes between methane and water vapor signals, this study incorporates temperature, relative humidity, and sensing distance into the cost function, establishing a continuous optimization space with concentration path lengths (CLs) as variables, which are the product of the concentration and path length. A hybrid differential evolution and Levenberg–Marquardt (D-LM) algorithm is developed to enhance parameter estimation accuracy. Combined with a three-layer atmospheric model for real-time reference spectrum generation, the algorithm identifies the optimal spectral combination that provides the best match to the measured data. Algorithm performance is validated through two experimental configurations: Firstly, adaptive detection using synthetic spectra covering various humidity–methane concentration combinations is conducted; simulation results demonstrate that the proposed method significantly reduces the mean squared error (MSE) of fitting residuals by 95.8% compared to the traditional LASSO method, effectively enhancing methane spectral feature extraction under high-water-vapor conditions. Then, a continuous monitoring of controlled methane releases over a 500 m open path under high-outdoor-humidity conditions is carried out to validate outdoor performance of the proposed algorithm; field measurement analysis further confirms the method’s robustness, achieving a reduction in fitting residuals of approximately 57% and improving spectral structure fitting. The proposed approach provides a reliable technical pathway for adaptive gas cloud detection under complex atmospheric conditions. Full article

► Show Figures

Figure 1

28 pages, 6225 KB

Open AccessArticle

Optimizing CO₂ Concentrations and Emissions Based on the WRF-Chem Model Integrated with the 3DVAR and EAKF Methods

by Wenhao Liu, Xiaolu Ling, Chenggang Li and Botao He

Remote Sens. 2026, 18(1), 174; https://doi.org/10.3390/rs18010174 - 5 Jan 2026

Viewed by 295

Abstract

This study developed a multi-source data assimilation system based on the WRF-Chem model integrated with 3DVAR and EAKF methods. By assimilating a multi-source satellite fused XCO₂ concentration dataset, the system achieved simultaneous optimization of CO₂ concentration fields and emission fluxes over [...] Read more.

This study developed a multi-source data assimilation system based on the WRF-Chem model integrated with 3DVAR and EAKF methods. By assimilating a multi-source satellite fused XCO₂ concentration dataset, the system achieved simultaneous optimization of CO₂ concentration fields and emission fluxes over China. During the December 2019 experiment, the system successfully reconstructed high-precision CO₂ concentration fields and dynamically corrected the MEIC inventory through emission error inversion derived from concentration differences before and after assimilation. Comparative analysis with the EDGAR inventory demonstrated the superior performance of the EAKF method, which reduced RMSE by 56% and increased the correlation coefficient to 0.360, while the 3DVAR method achieved a 9% RMSE reduction and improved the correlation coefficient to 0.294. In terms of total emissions, 3DVAR and EAKF increased national emissions by 13.6% and 5.1%, respectively, but reduced emissions in Xinjiang by 3.24 MT and 7.99 MT. A comparison of three simulation scenarios (prior emissions, 3DVAR-optimized, and EAKF-optimized) showed significant improvement over the EGG4 dataset, with systematic bias decreasing by approximately 75% and RMSE reduced by about 49%. The assimilation algorithm developed in this study provides a reliable methodological support for regional carbon monitoring and can be extended to multi-pollutant emissions and high-resolution satellite data integration. Full article

(This article belongs to the Special Issue Advanced Remote Sensing Approaches for Multi-Scale Atmospheric Components Monitoring and Impact Assessment)

► Show Figures

Figure 1

29 pages, 4806 KB

Open AccessArticle

KuRALS: Ku-Band Radar Datasets for Multi-Scene Long-Range Surveillance with Baselines and Loss Design

by Teng Li, Qingmin Liao, Youcheng Zhang, Xinyan Zhang, Zongqing Lu and Liwen Zhang

Remote Sens. 2026, 18(1), 173; https://doi.org/10.3390/rs18010173 - 5 Jan 2026

Viewed by 369

Abstract

Compared to cameras and LiDAR, radar provides superior robustness under adverse conditions, as well as extended sensing range and inherent velocity measurement, making it critical for surveillance applications. To advance research in deep learning-based radar perception technology, several radar datasets have been publicly [...] Read more.

Compared to cameras and LiDAR, radar provides superior robustness under adverse conditions, as well as extended sensing range and inherent velocity measurement, making it critical for surveillance applications. To advance research in deep learning-based radar perception technology, several radar datasets have been publicly released. However, most of these datasets are designed for autonomous driving applications, and existing radar surveillance datasets suffer from limited scene and target diversity. To address this gap, we introduce KuRALS, a range–Doppler (RD)-level radar surveillance dataset designed for learning-based long-range detection of moving targets. The dataset covers aerial (unmanned aerial vehicles), land (pedestrians and cars) and maritime (boats) scenarios. KuRALS is real-measured by two Kurz-under (Ku) band radars and contains two subsets (KuRALS-CW and KuRALS-PD). It consists of RD spectrograms with pixel-wise annotations of categories, velocity and range coordinates, and the azimuth and elevation angles are also provided. To benchmark performance, we develop a lightweight radar semantic segmentation (RSS) baseline model and further investigate various perception modules within this framework. In addition, we propose a novel interference-suppression loss function to enhance robustness against background interference. Extensive experimental results demonstrate that our proposed solution significantly outperforms existing approaches, with improvements of

10.0 %

in mIoU on the KuRALS-CW dataset and

9.4 %

on the KuRALS-PD dataset. Full article

(This article belongs to the Special Issue Technical Developments in Radar—Processing and Application (2nd Edition))

► Show Figures

Figure 1

29 pages, 19599 KB

Open AccessArticle

Interacting Factors Controlling Total Suspended Matter Dynamics and Transport Mechanisms in a Major River-Estuary System

by Zebin Tang, Yeping Yuan, Shuangyan He and Yingtien Lin

Remote Sens. 2026, 18(1), 172; https://doi.org/10.3390/rs18010172 - 5 Jan 2026

Viewed by 274

Abstract

The Changjiang estuary–Hangzhou Bay region is a critical zone of land–sea interaction, where Total Suspended Matter (TSM) dynamics significantly influence coastal ecology and engineering. While previous studies have examined individual factors affecting TSM variability, the synergistic effects of “tide–monsoon–current” interactions and the actual [...] Read more.

The Changjiang estuary–Hangzhou Bay region is a critical zone of land–sea interaction, where Total Suspended Matter (TSM) dynamics significantly influence coastal ecology and engineering. While previous studies have examined individual factors affecting TSM variability, the synergistic effects of “tide–monsoon–current” interactions and the actual pathways of turbid plume transport remain poorly understood. Using GOCI satellite data, in situ buoy measurements, and voyage data from 2020, this study applied Data Interpolating Empirical Orthogonal Functions (DINEOFs) and comprehensive spatio-temporal analysis to reconstruct continuous high-resolution TSM fields and elucidate multi-factor controls on TSM dynamics. Based on this high-resolution dataset of TSM, we found that, during the dry season, elevated TSM concentrations are primarily driven by wind–tide resuspension and transport under the comprehensive forcing of the Jiangsu Alongshore Current (JAC), the Yellow Sea Warm Current (YSWC), and wind–tide-induced flows. Contrary to the conventional understanding, the Jiangsu-origin surface TSM can transport to the outer sea without supplementing the TSM in the Turbidity Maximum Zone (TMZ). The YSWC in autumn can cause either low C_TSM gradients or high gradients nearshore depending on whether it is carrying Korean coastal turbid water or not. During the wet season, stratification induced by the Changjiang freshwater discharge suppresses wind–tide resuspension, reducing TSM concentrations in the TMZ and the Qidong water. However, the Changjiang freshwater combined with the Taiwan Warm Current (TWC) dilutes surface TSM in Hangzhou Bay, where the two water masses meet on the 10 m isobath. These insights into factor interactions and TSM plume pathways provide a scientific basis for improved environmental monitoring and coastal management. Full article

► Show Figures

Figure 1

21 pages, 8752 KB

Open AccessArticle

Remote Sensing Interpretation of Soil Elements via a Feature-Reinforcement Multiscale-Fusion Network

by Zhijun Zhang, Mingliang Tian, Wenbo Gao, Yanliang Wang, Fengshan Zhang and Mo Wang

Remote Sens. 2026, 18(1), 171; https://doi.org/10.3390/rs18010171 - 5 Jan 2026

Viewed by 283

Abstract

Accurately delineating soil elements from satellite imagery is fundamental for regional geological mapping and survey. However, vegetation cover and complex geomorphological conditions often obscure diagnostic surface information, weakening the visibility of key geological features. Additionally, long-term tectonic deformation and weathering processes reshape the [...] Read more.

Accurately delineating soil elements from satellite imagery is fundamental for regional geological mapping and survey. However, vegetation cover and complex geomorphological conditions often obscure diagnostic surface information, weakening the visibility of key geological features. Additionally, long-term tectonic deformation and weathering processes reshape the spatial organization of soil elements, resulting in substantial within-class variability, inter-class spectral overlap, and fragmented structural patterns—all of which hinder reliable segmentation performance for conventional deep learning approaches. To mitigate these challenges, this study introduces a Reinforced Feature and Multiscale Feature Fusion Network (RFMFFNet) tailored for semantic interpretation of soil elements. The model incorporates a rectangular calibration attention (RCA) module into a ResNet101 backbone to recalibrate feature responses in critical regions, thereby improving scale adaptability and the preservation of fine geological structures. A complementary multiscale feature fusion (MFF) component is further designed by combining sparse self-attention with pyramid pooling, enabling richer context aggregation while reducing computational redundancy. Comprehensive experiments on the Landsat-8 and Sentinel-2 datasets verify the effectiveness of the proposed framework. RFMFFNet consistently achieves superior segmentation performance compared with several mainstream deep learning models. On the Landsat-8 dataset, the oPA and mIoU increase by 2.4% and 2.6%, respectively; on the Sentinel-2 dataset, the corresponding improvements reach 4.3% and 4.1%. Full article

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

► Show Figures

Figure 1

19 pages, 3748 KB

Open AccessArticle

Exploring the Roles of Ancient Trees in Disturbance and Recovery Processes Using Monthly Landsat Time Series Analysis

by Yutong Wei, Lin Sun, Jingyi Jia, Yuanyuan Meng, Junwei Zhang, Xin Zhou, Jiaxuan Xie, Jun Yang and Li Huang

Remote Sens. 2026, 18(1), 170; https://doi.org/10.3390/rs18010170 - 5 Jan 2026

Viewed by 309

Abstract

Quantifying forest patch dynamics is essential for understanding how forest patch characteristics vary in relation to ancient tree locations. This study developed a satellite-based framework to analyze the differences among forest patches associated with natural and planted ancient trees across the Sichuan–Chongqing region, [...] Read more.

Quantifying forest patch dynamics is essential for understanding how forest patch characteristics vary in relation to ancient tree locations. This study developed a satellite-based framework to analyze the differences among forest patches associated with natural and planted ancient trees across the Sichuan–Chongqing region, China. Using monthly LandTrendr on Google Earth Engine, we analyzed long-term (1990–2024) and high-frequency observations of forest dynamics at a 180 m × 180 m (6 × 6 pixels) spatial scale. Disturbance and recovery events were characterized by their magnitude, rate, timing, and duration. Patches were classified into six categories based on ancient tree type and proximity and further subdivided by land use type. The results show that in natural forests, patches with natural ancient trees are associated with more stable change signatures, whereas in planted forests, patches containing planted ancient trees are associated with stronger recovery-related change patterns. Over 60% of detected changes were short-lived (≤5 years), indicating that most disturbances and recovery processes were transient rather than persistent. These findings show that the presence and spatial context of ancient trees are associated with differences in patch change patterns. The proposed workflow provides a scalable approach for integrating multi-temporal remote sensing into large-scale monitoring and management of ancient trees and their associated forest patches. Full article

► Show Figures

Figure 1

25 pages, 18950 KB

Open AccessArticle

Robust Object Detection for UAVs in Foggy Environments with Spatial-Edge Fusion and Dynamic Task Alignment

by Qing Dong, Tianxin Han, Gang Wu, Lina Sun and Yuchang Lu

Remote Sens. 2026, 18(1), 169; https://doi.org/10.3390/rs18010169 - 5 Jan 2026

Viewed by 336

Abstract

Robust scene perception in adverse environmental conditions, particularly under dense fog, presents a persistent and fundamental challenge to the reliability of object detection systems. To address this critical challenge, we propose Fog-UAVNet, a novel lightweight deep-learning architecture designed to enhance unmanned aerial vehicle [...] Read more.

Robust scene perception in adverse environmental conditions, particularly under dense fog, presents a persistent and fundamental challenge to the reliability of object detection systems. To address this critical challenge, we propose Fog-UAVNet, a novel lightweight deep-learning architecture designed to enhance unmanned aerial vehicle (UAV) object detection performance in foggy environments. Fog-UAVNet incorporates three key innovations: the Spatial-Edge Feature Fusion Module (SEFFM), which enhances feature extraction by effectively integrating edge and spatial information, the Frequency-Adaptive Dilated Convolution (FADC), which dynamically adjusts to fog density variations and further enhances feature representation under adverse conditions, and the Dynamic Task-Aligned Head (DTAH), which dynamically aligns localization and classification tasks and thus improves overall model performance. To evaluate the effectiveness of our approach, we independently constructed a real-world foggy dataset and synthesized the VisDrone-fog dataset using an atmospheric scattering model. Extensive experiments on multiple challenging datasets demonstrate that Fog-UAVNet consistently outperforms state-of-the-art methods in both detection accuracy and computational efficiency, highlighting its potential for enhancing robust visual perception under adverse weather. Full article

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

► Show Figures

Figure 1

19 pages, 5994 KB

Open AccessArticle

Optimal Ice Particle Models of Different Cloud Types for Radiative Transfer Simulation at 183 GHz Frequency Band

by Zhuoyang Li, Qiang Guo, Xin Wang, Wen Hui, Fangli Dou and Yiyu Chen

Remote Sens. 2026, 18(1), 168; https://doi.org/10.3390/rs18010168 - 4 Jan 2026

Viewed by 248

Abstract

The Fengyun-4 microwave satellite provides high-temporal-frequency observations at the 183 GHz band, providing unprecedented data for all-weather, three-dimensional measurements of atmospheric parameters. It is of importance to establish a simulated brightness temperature (BT) dataset for this band prior to launch, which can support [...] Read more.

The Fengyun-4 microwave satellite provides high-temporal-frequency observations at the 183 GHz band, providing unprecedented data for all-weather, three-dimensional measurements of atmospheric parameters. It is of importance to establish a simulated brightness temperature (BT) dataset for this band prior to launch, which can support the relevant quantitative applications significantly. Compared with clear-sky conditions, the accuracy of BT simulations under cloudy ones is considerably lower, primarily due to the influence of the adopted ice particle models. Up until now, few studies have systematically investigated ice particle model selection for different cloud types at the 183 GHz frequency band. In this paper, multi-sensor observations from Cloud Profiling Radar (CPR), Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), and Visible Infrared Imaging Radiometer Suite (VIIRS) were used as realistic atmospheric profiles. Using the high-precision radiative transfer model Atmospheric Radiative Transfer Simulator (ARTS), BT simulations at 183 GHz were performed to explore the optimal ice particle models for seven classical cloud types. The main conclusions are given as follows: (1) The sensitivity of simulated cloud radiances to ice particle habits differs with respect to different cloud phases. For altocumulus (Ac), stratocumulus (Sc), and cumulus (Cu) clouds, the different choices of ice particle model have little impacts on the simulated brightness temperatures (<1 K), with RMSEs below 3 K across multiple models, indicating that various models can be applied directly for such simulations. (2) For some mixed-phase clouds, including altostratus (As), nimbostratus (Ns), and deep convective (Dc) clouds, the Small Block Aggregate (SBA) and Small Plate Aggregate (SPA) models demonstrate good performance for As clouds, with RMSEs below 2.5 K, while the SBA, SPA, and Large Column Aggregate (LCA) models exhibit similarly good performance for Ns clouds, also achieving RMSEs below 2.5 K. For Dc clouds, although the SBA model yields RMSEs of approximately 10 K, it still provides a substantial improvement over the spherical model, whereas for cirrus (Ci) clouds, any non-spherical ice particle models are applicable, with RMSEs below 2 K. (3) Within the 183 GHz frequency band, channels with the higher weighting-function peaks are less sensitive to variable adoptions of ice particle models. These results offer valuable references for accurate radiative transfer simulations on 183 GHz frequency. Full article

► Show Figures

Figure 1

23 pages, 3943 KB

Open AccessArticle

High-Rise Building Area Extraction Based on Prior-Embedded Dual-Branch Neural Network

by Qiliang Si, Liwei Li and Gang Cheng

Remote Sens. 2026, 18(1), 167; https://doi.org/10.3390/rs18010167 - 4 Jan 2026

Viewed by 363

Abstract

High-rise building areas (HRBs) play a crucial role in providing social and environmental services during the process of modern urbanization. Their large-scale, long-term spatial distribution characteristics have significant implications for fields such as urban planning and regional climate analysis. However, existing studies are [...] Read more.

High-rise building areas (HRBs) play a crucial role in providing social and environmental services during the process of modern urbanization. Their large-scale, long-term spatial distribution characteristics have significant implications for fields such as urban planning and regional climate analysis. However, existing studies are largely limited to local regions and fixed-time-phase images. These studies are also influenced by differences in remote sensing image acquisition, such as regional architectural styles, lighting conditions, seasons, and sensor variations. This makes it challenging to achieve robust extraction across time and regions. To address these challenges, we propose an improved method for extracting HRBs that uses a Prior-Embedded Dual-Branch Neural Network (PEDNet). The dual-path design balances global features with local details. More importantly, we employ a window attention mechanism to introduce diverse prior information as embedded features. By integrating these features, our method becomes more robust against HRB image feature variations. We conducted extensive experiments using Sentinel-2 data from four typical cities. The results demonstrate that our method outperforms traditional models, such as FCN and U-Net, as well as more recent high-performance segmentation models, including DeepLabV3+ and BuildFormer. It effectively captures HRB features in remote sensing images, adapts to complex conditions, and provides a reliable tool for wide geographic span, cross-timestamp urban monitoring. It has practical applications for optimizing urban planning and improving the efficiency of resource management. Full article

(This article belongs to the Special Issue Multi-Source Remote Sensing and Spatial Statistical Analysis in Urban Sustainability Research)

► Show Figures

Figure 1

25 pages, 8526 KB

Open AccessArticle

Describing Land Cover Changes via Multi-Temporal Remote Sensing Image Captioning Using LLM, ViT, and LoRA

by Javier Lamar León, Vitor Nogueira, Pedro Salgueiro and Paulo Quaresma

Remote Sens. 2026, 18(1), 166; https://doi.org/10.3390/rs18010166 - 4 Jan 2026

Viewed by 462

Abstract

Describing land cover changes from multi-temporal remote sensing imagery requires capturing both visual transformations and their semantic meaning in natural language. Existing methods often struggle to balance visual accuracy with descriptive coherence. We propose MVLT-LoRA-CC (Multi-modal Vision Language Transformer with Low-Rank Adaptation for [...] Read more.

Describing land cover changes from multi-temporal remote sensing imagery requires capturing both visual transformations and their semantic meaning in natural language. Existing methods often struggle to balance visual accuracy with descriptive coherence. We propose MVLT-LoRA-CC (Multi-modal Vision Language Transformer with Low-Rank Adaptation for Change Captioning), a framework that integrates a Vision Transformer (ViT), a Large Language Model (LLM), and Low-Rank Adaptation (LoRA) for efficient multi-modal learning. The model processes paired temporal images through patch embeddings and transformer blocks, aligning visual and textual representations via a multi-modal adapter. To improve efficiency and avoid unnecessary parameter growth, LoRA modules are selectively inserted only into the attention projection layers and cross-modal adapter blocks rather than being uniformly applied to all linear layers. This targeted design preserves general linguistic knowledge while enabling effective adaptation to remote sensing change description. To assess performance, we introduce the Complementary Consistency Score (CCS) framework, which evaluates both descriptive fidelity for change instances and classification accuracy for no change cases. Experiments on the LEVIR-CC test set demonstrate that MVLT-LoRA-CC generates semantically accurate captions, surpassing prior methods in both descriptive richness and temporal change recognition. The approach establishes a scalable solution for multi-modal land cover change description in remote sensing applications. Full article

(This article belongs to the Special Issue Remote Sensing of Coastal Waters, Land Use/Cover, Lakes, Rivers and Watersheds III)

► Show Figures

Figure 1

25 pages, 6613 KB

Open AccessArticle

Satellite-Based Assessment of Marine Environmental Indicators and Their Variability in the South Pacific Island Regions: A National-Scale Perspective

by Qunfei Hu, Teng Li, Yan Bai, Xianqiang He, Xueqian Chen, Liangyu Chen, Xiaochen Huang, Meng Huang and Difeng Wang

Remote Sens. 2026, 18(1), 165; https://doi.org/10.3390/rs18010165 - 4 Jan 2026

Viewed by 400

Abstract

The marine environment in the South Pacific Island Countries (SPICs) is sensitive and vulnerable to climate change. While large-scale changes in this region are well-documented, national-scale analyses that address management needs remain limited. This study evaluated the performance of satellite-derived datasets—including sea surface [...] Read more.

The marine environment in the South Pacific Island Countries (SPICs) is sensitive and vulnerable to climate change. While large-scale changes in this region are well-documented, national-scale analyses that address management needs remain limited. This study evaluated the performance of satellite-derived datasets—including sea surface temperature (SST), sea surface salinity (SSS), Secchi disk depth (SDD), chlorophyll-a (Chl-a), net primary production (NPP), and sea level anomaly (SLA)—against in situ observations, and analyzed their spatial and temporal variability across 12 national Exclusive Economic Zones (EEZs) during 1998–2023. Validation results presented that current satellite datasets could provide applicable information for EEZ-scale analyses. In the past decades, the SPICs experienced a general increase in SST and SLA, accompanied by marked within-EEZ heterogeneity in Chl-a and NPP variations, with Papua New Guinea exhibiting the largest within-EEZ inter-annual variability. In addition to monitoring, satellite data would help to constrain the uncertainty of CMIP6 results in the SPICs, subject to the accuracy of specific products. By 2100, Nauru might experience the most vulnerable EEZ, while the marine environment in the French Polynesian EEZ can keep relatively stable among all 12 EEZs. Meanwhile, CMIP6 projections in the Southeastern EEZs are more sensitive to satellite-based constraints, showing pronounced adjustments. Our results demonstrate the potential of combining validated satellite data with CMIP6 models to provide national-scale decision support for climate adaptation and marine resource management in the SPICs. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Ocean Observation (Third Edition))

► Show Figures

Figure 1

32 pages, 43285 KB

Open AccessArticle

Polarimetric SAR Salt Crust Classification via Autoencoded and Attention-Enhanced Feature Representation

by Fabin Dong, Qiang Yin, Juan Zhang, Qunxiong Yan and Wen Hong

Remote Sens. 2026, 18(1), 164; https://doi.org/10.3390/rs18010164 - 4 Jan 2026

Viewed by 354

Abstract

Qarhan Salt Lake, located in the Qaidam Basin of northwestern China, is a highland lake characterized by diverse surface features, including salt lakes, salt crusts, and saline-alkali lands. Investigating the distribution and dynamic variations of salt crusts is essential for mineral resource development [...] Read more.

Qarhan Salt Lake, located in the Qaidam Basin of northwestern China, is a highland lake characterized by diverse surface features, including salt lakes, salt crusts, and saline-alkali lands. Investigating the distribution and dynamic variations of salt crusts is essential for mineral resource development and regional ecological monitoring. To this end, the surface of the study area was categorized into several types according to micro-geomorphological characteristics. Polarimetric synthetic aperture radar (PolSAR), which provides rich scattering information, is well suited for distinguishing these surface categories. To achieve more accurate classification of salt crust types, the scattering differences among various types were comparatively analyzed. Stable samples were further selected using unsupervised Wishart clustering with reference to field survey results. Besides, to address the weak inter-class separability among different salt crust types, this paper proposes a PolSAR classification method tailored for salt crust discrimination by integrating unsupervised feature learning, attention-based feature optimization, and global context modeling. In this method, convolutional autoencoder (CAE) is first employed to learn discriminative local scattering representations from original polarimetric features, enabling effective characterization of subtle scattering differences among salt crust types. Vision Transformer (ViT) is introduced to model global scattering relationships and spatial context at the image-patch level, thereby improving the overall consistency of classification results. Meanwhile, the attention mechanism is used to bridge local scattering representations and global contextual information, enabling joint optimization of key scattering features. Experiments on fully polarimetric Gaofen-3 and dual-polarimetric Sentinel-1 data show that the proposed method outperforms the best competing method by

2.34 %

and

1.17 %

in classification accuracy, respectively. In addition, using multi-temporal Sentinel-1 data, recent temporal changes in salt crust distribution are identified and analyzed. Full article

► Show Figures

Figure 1

18 pages, 5654 KB

Open AccessArticle

Thermal Deformation Correction for the FY-4A LMI

by Yuansheng Zhang, Xiushu Qie, Dongjie Cao, Shanfeng Yuan, Dongfang Wang, Hongbo Zhang, Dongxia Liu, Zhuling Sun, Mingyuan Liu, Kexin Zhu, Rubin Jiang and Jing Yang

Remote Sens. 2026, 18(1), 163; https://doi.org/10.3390/rs18010163 - 4 Jan 2026

Viewed by 234

Abstract

Affected by solar radiation in space, the FY-4A Lightning Mapping Imager (LMI) detection array exhibits daily periodic thermal expansion and contraction, leading to deviations in lightning positioning accuracy. While LMI’s detection efficiency is higher at night, the dual edge matching algorithm, which relies [...] Read more.

Affected by solar radiation in space, the FY-4A Lightning Mapping Imager (LMI) detection array exhibits daily periodic thermal expansion and contraction, leading to deviations in lightning positioning accuracy. While LMI’s detection efficiency is higher at night, the dual edge matching algorithm, which relies on surface features for correction, does not perform well during nighttime (around 3 pixels). Analysis shows that most of the lightning data corrected by this method exhibit significant deviations from the actual lightning locations in practical applications. Therefore, this paper proposes a new correction method based on high precision ground-based lightning location data from the 2019 summer World Wide Lightning Location Network (WWLLN) and the Beijing Broadband Lightning Network (BLNET). Using these datasets as reference standards, the periodic deviation of LMI is determined, and a correction curve is derived using a weighted Gaussian fitting approach. This method further improves the nighttime lightning location accuracy of LMI on the basis of the current operational algorithm. The results demonstrate that the corrected LMI data significantly reduces the positioning errors, with an accuracy within ±1 pixel in the Beijing area, as an example. Full article

(This article belongs to the Special Issue Application of Satellite Data for Lightning Mapping)

► Show Figures

Figure 1

21 pages, 10033 KB

Open AccessArticle

Comparison and Evaluation of Multi-Source Evapotranspiration Datasets in the Yarlung Zangbo River Basin

by Yao Jiang, Zihao Xia, Lvyang Xiong and Zongxue Xu

Remote Sens. 2026, 18(1), 162; https://doi.org/10.3390/rs18010162 - 4 Jan 2026

Viewed by 270

Abstract

Evapotranspiration (ET) data products has greatly facilitated the hydrological research in complex basins, and various ET datasets have been produced and applied. The applicability and reliability of ET dataset is significant for regional studies. Therefore, this study compared ET datasets from multisource remote [...] Read more.

Evapotranspiration (ET) data products has greatly facilitated the hydrological research in complex basins, and various ET datasets have been produced and applied. The applicability and reliability of ET dataset is significant for regional studies. Therefore, this study compared ET datasets from multisource remote sensing (GLEAM, MOD16, GLASS, PML-V2, Han, Chen and Ma), machine learning (Jung) and reanalysis products (ERA5-Land, MERRA2) for the Yarlung Zangbo River basin (YZB). ET was estimated using the terrestrial water balance (TWB) and was taken as baseline for comparisons of different ET datasets in terms of spatial distribution and temporal variation. Results indicate that (1) the TWB-based ET estimates are rational with acceptable uncertainties; (2) the multi-source ET datasets exhibit good correlations with TWB-ET across the entire basin (r = 0.78–0.90) in term of annual variation, with GLEAM-ET performing the best (r = 0.88, RMSE = 14.24 mm, Rbias = 18.55%); (3) Spatially, PML-ET and Ma-ET show higher consistency with TWB-ET, and temporally, MOD16-ET and GLASS-ET better capture the changing trend; (4) A comprehensive evaluation using the linear weighted method reveals that GLASS-ET and GLEAM-ET perform relatively well in all aspects and are reliable datasets for ET research in the YZB. These findings provide a scientific basis for ET estimation and data selection in the YZB, offering important references for ET analysis and hydrological research. Full article

► Show Figures

Figure 1

22 pages, 15952 KB

Open AccessArticle

Text-Injected Discriminative Model for Remote Sensing Visual Grounding

by Minhan Hu, Keke Yang and Jing Li

Remote Sens. 2026, 18(1), 161; https://doi.org/10.3390/rs18010161 - 4 Jan 2026

Viewed by 264

Abstract

Remote Sensing Visual Grounding (RSVG) requires fine-grained understanding of language descriptions to localize the specific image regions. Conventional methods typically employ a pipeline of separate visual and textual encoders and a fusion module. However, as visual and textual features are extracted independently, they [...] Read more.

Remote Sensing Visual Grounding (RSVG) requires fine-grained understanding of language descriptions to localize the specific image regions. Conventional methods typically employ a pipeline of separate visual and textual encoders and a fusion module. However, as visual and textual features are extracted independently, they tend to lack semantic focus on object features during extraction, leading to suboptimal object focus. While some recent attempts have incorporated textual cues into visual feature extraction, they often design complex fusion modules. To address this, we introduce a simple fusion strategy to integrate textual information into visual backbone networks with minimal architectural changes. Moreover, most of the current works use common object detection losses, which only focus on the features inside the bounding box and neglect the background features. In remote sensing images, the high visual similarity between objects can confuse models, making it difficult to locate the correct target accurately. To this end, we design a novel attention regularization strategy to enhance the model’s ability to distinguish similar features outside bounding box regions. Experiments on three benchmark datasets demonstrate the promising performance of our approach. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

21 pages, 10897 KB

Open AccessArticle

Vertically Resolved Supercooled Liquid Water over the North China Plain Revealed by Ground-Based Synergetic Measurements

by Yuxiang Lu, Qiang Li, Hongrong Shi, Jiwei Xu, Zhipeng Yang, Yongheng Bi, Xiaoqiong Zhen, Yunjie Xia, Jiujiang Sheng, Ping Tian, Disong Fu, Jinqiang Zhang, Shuzhen Hu, Fa Tao, Jiefan Yang, Xuehua Fan, Hongbin Chen and Xiang’ao Xia

Remote Sens. 2026, 18(1), 160; https://doi.org/10.3390/rs18010160 - 4 Jan 2026

Viewed by 427

Abstract

Supercooled liquid water (SLW) in mixed-phase clouds significantly influences precipitation efficiency and aviation safety. However, a comprehensive understanding of its vertical structure has been hampered by a lack of sustained, vertically resolved observations over the North China Plain. This study presents the first [...] Read more.

Supercooled liquid water (SLW) in mixed-phase clouds significantly influences precipitation efficiency and aviation safety. However, a comprehensive understanding of its vertical structure has been hampered by a lack of sustained, vertically resolved observations over the North China Plain. This study presents the first systematic analysis of SLW vertical distribution and microphysics in this region, utilizing a year-long dataset (2022) from synergistic ground-based instruments in Beijing. Our retrieval approach integrates Ka-band cloud radar, microwave radiometer, ceilometer, and radiosonde data, combining fuzzy-logic phase classification with a liquid water content inversion constrained by column liquid water path. Key findings reveal a distinct bimodal seasonality: SLW primarily occurs at mid-to-upper levels (4–7.5 km) during spring and summer, driven by convective lofting, while winter SLW is confined to lower altitudes (1–2 km) under stable atmospheric conditions. The temperature-dependent occurrence probability of SLW clouds has an annual maximum at −12 °C. The diurnal variation in SLW in summer shows peaks in the afternoon and at night, corresponding to convective cloud activity. Spring, autumn, and winter do not exhibit strong diurnal variations. Retrieved microphysical properties, including liquid water content and droplet effective radius, are consistent with in situ aircraft measurements, validating our methodology. This analysis provides a critical observational benchmark and offers actionable insights for improving cloud microphysics parameterizations in models and optimizing weather modification strategies, such as seeding altitude and timing, in this water-stressed region. Full article

(This article belongs to the Special Issue Estimating Atmospheric Aerosols and Cloud Physics with Optical and Multispectral Sensors)

► Show Figures

Figure 1

29 pages, 21548 KB

Open AccessArticle

MSCANet: Multi-Scale Spatial-Channel Attention Network for Urbanization Intelligent Monitoring

by Zhande Dong, Daoye Zhu, Min Huang, Qifeng Lin, Lasse Møller-Jensen and Elisabete A. Silva

Remote Sens. 2026, 18(1), 159; https://doi.org/10.3390/rs18010159 - 3 Jan 2026

Cited by 1 | Viewed by 329

Abstract

Rapid urbanization drives economic growth but also brings complex environmental and social issues, highlighting the urgent need for efficient urbanization monitoring techniques. However, datasets for urbanization monitoring are often lacking in rapidly developing urban areas. At the methodological level, Convolutional Neural Networks (CNNs) [...] Read more.

Rapid urbanization drives economic growth but also brings complex environmental and social issues, highlighting the urgent need for efficient urbanization monitoring techniques. However, datasets for urbanization monitoring are often lacking in rapidly developing urban areas. At the methodological level, Convolutional Neural Networks (CNNs) and Transformer-based models for urbanization monitoring exhibit limitations in balancing computational efficiency and global modeling. The recently emerging parallel large kernel convolutional networks partially alleviate the conflict between global modeling and computational efficiency, but they employ simple element-wise addition to fuse multi-scale features. This crude mechanism struggles to fully leverage multi-scale information. To address this, this paper takes Accra, the capital of Ghana, as a case study and proposes an urbanization monitoring framework covering both dataset construction and model design. Methodologically, we propose the Multi-Scale Spatial-Channel Attention Network (MSCANet). Its core component, the Multi-Scale Spatial-Channel Attention Module (MSCAM), jointly models spatial and channel dimensions to mitigate the common confusion problem in parallel large kernel convolutional architectures. Furthermore, we adaptively modified the MSCAM to propose the Multi-Scale Spatial-Channel Attention Feature Fusion Module (MSCA-FFM) module for effectively integrating multi-modal information during the fusion stage. Experimental results show that MSCANet achieves optimal performance on the self-built Accra dataset, with a mean intersection over union (mIoU) of 95.02%, an overall accuracy (OA) of 98.70%, and a mean F1 Score (mF1) of 97.43%. To further validate the model’s generalization capability, supplementary experiments were conducted on the public ISPRS Potsdam dataset. The results demonstrate that the MSCANet series of models remain competitive, achieving an overall mIoU of 80.92%, with particularly strong performance in the “Building” (mIoU 92.26%) and “Impervious surface” (mIoU 84.63%) categories. 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

19 pages, 5002 KB

Open AccessArticle

Deep Learning-Based Diffraction Identification and Uncertainty-Aware Adaptive Weighting for GNSS Positioning in Occluded Environments

by Chenhui Wang, Haoliang Shen, Yanyan Liu, Qingjia Meng and Chuang Qian

Remote Sens. 2026, 18(1), 158; https://doi.org/10.3390/rs18010158 - 3 Jan 2026

Viewed by 343

Abstract

In natural canyons and urban occluded environments, signal anomalies induced by the satellite diffraction effect are a critical error source affecting the positioning accuracy of deformation monitoring. This paper proposes a deep learning-based method for diffraction signal identification and mitigation. The method utilizes [...] Read more.

In natural canyons and urban occluded environments, signal anomalies induced by the satellite diffraction effect are a critical error source affecting the positioning accuracy of deformation monitoring. This paper proposes a deep learning-based method for diffraction signal identification and mitigation. The method utilizes a LSTM network to deeply mine the time-series characteristics of GNSS observation data. We systematically analyze the impact of azimuth, elevation, SNR, and multi-feature combinations on model recognition performance, demonstrating that single features suffer from incomplete information or poor discrimination. Experimental results show that the multi-dimensional feature scheme of “SNR + Elevation + Azimuth” effectively characterizes both signal strength and spatial geometric information, achieving complementary feature advantages. The overall recognition accuracy of the proposed method reaches 84.2%, with an accuracy of 88.0% for anomalous satellites that severely impact positioning precision. Furthermore, we propose an Adaptive Weighting Method for Diffraction Mitigation Based on Uncertainty Quantification. This method constructs a variance inflation model using the probability vector output from the LSTM Softmax layer and introduces Information Entropy to quantify prediction uncertainty, ensuring that the weighting model possesses protection capability when the model fails or is uncertain. In processing a set of GNSS data collected in a highly-occluded environment, the proposed method significantly outperforms traditional cut-off elevation and SNR mask strategies, improving the AFR to 99.9%, and enhancing the positioning accuracy in the horizontal and vertical directions by an average of 80.1% and 76.4%, respectively, thereby effectively boosting the positioning accuracy and reliability in occluded environments. Full article

(This article belongs to the Special Issue High-Precision Urban Positioning: GNSS and Multi-Sensor Fusion Technologies)

► Show Figures

Figure 1

22 pages, 46825 KB

Open AccessArticle

Delineating the Distribution Outline of Populus euphratica in the Mainstream Area of the Tarim River Using Multi-Source Thematic Classification Data

by Hao Li, Jiawei Zou, Qinyu Zhao, Jiacong Hu, Suhong Liu, Qingdong Shi and Weiming Cheng

Remote Sens. 2026, 18(1), 157; https://doi.org/10.3390/rs18010157 - 3 Jan 2026

Viewed by 310

Abstract

Populus euphratica is a key constructive species in desert ecosystems and plays a vital role in maintaining their stability. However, effective automated methods for accurately delineating its distribution outlines are currently lacking. This study used the mainstream area of the Tarim River as [...] Read more.

Populus euphratica is a key constructive species in desert ecosystems and plays a vital role in maintaining their stability. However, effective automated methods for accurately delineating its distribution outlines are currently lacking. This study used the mainstream area of the Tarim River as a case study and proposed a technical solution for identifying the distribution outline of Populus euphratica using multi-source thematic classification data. First, cropland thematic data were used to optimize the accuracy of the Populus euphratica classification raster data. Discrete points were removed based on density to reduce their impact on boundary identification. Then, a hierarchical identification scheme was constructed using the alpha-shape algorithm to identify the boundaries of high- and low-density Populus euphratica distribution areas separately. Finally, the outlines of the Populus euphratica distribution polygons were smoothed, and the final distribution outline data were obtained after spatial merging. The results showed the following: (1) Applying a closing operation to the cropland thematic classification data to obtain the distribution range of shelterbelts effectively eliminated misclassified pixels. Using the kd-tree algorithm to remove sparse discrete points based on density, with a removal ratio of 5%, helped suppress the interference of outlier point sets on the Populus euphratica outline identification. (2) Constructing a hierarchical identification scheme based on differences in Populus euphratica density is critical for accurately delineating its distribution contours. Using the alpha-shape algorithm with parameters set to α = 0.02 and α = 0.006, the reconstructed geometries effectively covered both densely and sparsely distributed Populus euphratica areas. (3) In the morphological processing stage, a combination of three methods—Gaussian filtering, equidistant expansion, and gap filling—effectively ensured the accuracy of the Populus euphratica outline. Among the various smoothing algorithms, Gaussian filtering yielded the best results. The equidistant expansion method reduced the impact of elongated cavities, thereby contributing to boundary accuracy. This study enhances the automation of Populus euphratica vector data mapping and holds significant value for the scientific management and research of desert vegetation. Full article

(This article belongs to the Special Issue Vegetation Mapping through Multiscale Remote Sensing)

► Show Figures

Figure 1

25 pages, 4974 KB

Open AccessArticle

Physics-Constrained Deep Learning with Adaptive Z-R Relationship for Accurate and Interpretable Quantitative Precipitation Estimation

by Ting Shu, Huan Zhao, Kanglong Cai and Zexuan Zhu

Remote Sens. 2026, 18(1), 156; https://doi.org/10.3390/rs18010156 - 3 Jan 2026

Viewed by 282

Abstract

Quantitative precipitation estimation (QPE) from radar reflectivity is fundamental for weather nowcasting and water resource management. Conventional Z-R relationship formulas, derived from Rayleigh scattering theory, rely heavily on empirical parameter fitting, which limits the estimation accuracy and generalization across different precipitation regimes. Recent [...] Read more.

Quantitative precipitation estimation (QPE) from radar reflectivity is fundamental for weather nowcasting and water resource management. Conventional Z-R relationship formulas, derived from Rayleigh scattering theory, rely heavily on empirical parameter fitting, which limits the estimation accuracy and generalization across different precipitation regimes. Recent deep learning (DL)-based QPE methods can capture the complex nonlinear relationships between radar reflectivity and rainfall. However, most of them overlook fundamental physical constraints, resulting in reduced robustness and interpretability. To address these issues, this paper proposes FusionQPE, a novel Physics-Constrained DL framework that integrates an adaptive Z-R formula. Specifically, FusionQPE employs a Dense convolutional neural network (DenseNet) backbone to extract multi-scale spatial features from radar echoes, while a modified squeeze-and-excitation (SE) network adaptively learns the parameters of the Z-R relationship. The final rainfall estimate is obtained through a linear combination of outputs from both the DenseNet backbone and the adaptive Z-R branch, where the trained linear weight and Z-R parameters provide interpretable insights into the model’s physical reasoning. Moreover, a physical-based constraint derived from the Z-R branch output is incorporated into the loss function to further strengthen physical consistency. Comprehensive experiments on real radar and rain gauge observations from Guangzhou, China, demonstrate that FusionQPE consistently outperforms both traditional and state-of-the-art DL-based QPE models across multiple evaluation metrics. The ablation and interpretability analysis further confirms that the adaptive Z-R branch improves both the physical consistency and credibility of the model’s precipitation estimation. Full article

(This article belongs to the Special Issue AI Applications to Remote Sensing of Cloud and Precipitation: Monitoring, Modeling, and Prediction)

► Show Figures

Figure 1

29 pages, 73612 KB

Open AccessArticle

DNMF-AG: A Sparse Deep NMF Model with Adversarial Graph Regularization for Hyperspectral Unmixing

by Kewen Qu, Xiaojuan Luo and Wenxing Bao

Remote Sens. 2026, 18(1), 155; https://doi.org/10.3390/rs18010155 - 3 Jan 2026

Viewed by 300

Abstract

Hyperspectral unmixing (HU) aims to extract constituent information from mixed pixels and is a fundamental task in hyperspectral remote sensing. Deep non-negative matrix factorization (DNMF) has recently attracted attention for HU due to its hierarchical representation capability. However, existing DNMF-based methods are often [...] Read more.

Hyperspectral unmixing (HU) aims to extract constituent information from mixed pixels and is a fundamental task in hyperspectral remote sensing. Deep non-negative matrix factorization (DNMF) has recently attracted attention for HU due to its hierarchical representation capability. However, existing DNMF-based methods are often sensitive to noise and outliers, and face limitations in incorporating prior knowledge, modeling feature structures, and enforcing sparsity constraints, which restrict their robustness, accuracy, and interpretability. To address these challenges, we propose a sparse deep NMF model with adversarial graph regularization for hyperspectral unmixing, termed DNMF-AG. Specifically, we design an adversarial graph regularizer that integrates local similarity and dissimilarity graphs to promote intraclass consistency and interclass separability in the spatial domain, thereby enhancing structural modeling and robustness. In addition, a Gram-based sparsity constraint is introduced to encourage sparse abundance representations by penalizing inner product correlations. To further improve robustness and computational efficiency, a truncated activation function is incorporated into the iterative update process, suppressing low-amplitude components and promoting zero entries in the abundance matrix. The overall model is optimized using the alternating direction method of multipliers (ADMM). Experimental results on multiple synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of estimation accuracy and robustness. Full article

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

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 1 (January-1 2026) – 184 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI