Remote Sensing

30 pages, 3561 KB

Open AccessArticle

Cross-View Localization Based on Few-Shot Learning for Mars Rover via MarsCVFP Guidance

by Yuke Kou, Wenhui Wan, Kaichang Di, Zhaoqin Liu, Man Peng, Yexin Wang, Bin Xie, Biao Wang and Waichung Liu

Remote Sens. 2026, 18(4), 668; https://doi.org/10.3390/rs18040668 - 23 Feb 2026

Viewed by 780

Abstract

High-precision localization of Mars rovers is essential for safe path planning and efficient navigation toward scientific targets. As planetary rovers traverse the surface, their positional uncertainty accumulates, which can be corrected through global localization by registering rover images to orbital maps. To date, [...] Read more.

High-precision localization of Mars rovers is essential for safe path planning and efficient navigation toward scientific targets. As planetary rovers traverse the surface, their positional uncertainty accumulates, which can be corrected through global localization by registering rover images to orbital maps. To date, image-based solutions are widely adopted; however, substantial manual intervention is often required, which is time-consuming and limits the range of autonomous navigation. To address these challenges, we propose a two-stage localization framework, comprising the Mars cross-view few-shot training paradigm (MarsCVFP), Mars cross-view feature extraction network (MCVN) trained under MarsCVFP, and a robust template matching algorithm. Specifically, the MarsCVFP model can leverage implicit cross-view feature as guidance without relying on a large amount of high-precision location-level supervision and explicitly annotated, specific learning targets in the scene. MCVN can capture discriminative fine-grained features on the weakly textured and unstructured surface of Mars by constructing the multi-scale feature pyramid structure (MSFPS) and the feature interaction module (FIM). We validate our framework on 85 unit-planned sites and 20 panoramic sites, respectively, as traversed by the Zhurong rover. The experimental results demonstrate that our framework consistently outperforms both the traditional approaches and the representative learning-based methods across diverse terrains, including dunes, bedrock, craters, and flat plains, achieving a localization success rate above 82% while maintaining a localization accuracy of better than 4 pixels, even under coarse prior positions uncertainties spanning 40 m × 40 m. Full article

(This article belongs to the Special Issue Planetary Geologic Mapping and Remote Sensing (Third Edition))

► Show Figures

Figure 1

25 pages, 3178 KB

Open AccessArticle

A Machine Learning Framework for Daily Mangrove Net Ecosystem Exchange Prediction from 2000 to 2025

by Linlin Ruan, Li Zhang, Min Yan, Bowei Chen, Bo Zhang, Yuqi Dong and Jian Zuo

Remote Sens. 2026, 18(4), 667; https://doi.org/10.3390/rs18040667 - 22 Feb 2026

Viewed by 1192

Abstract

Mangrove ecosystems are important blue carbon systems and play a critical role in understanding carbon cycling and responses to climate change. However, accurate regional estimation of Net Ecosystem Exchange (NEE) remains challenging due to the environmental complexity and spatial heterogeneity. This study combined [...] Read more.

Mangrove ecosystems are important blue carbon systems and play a critical role in understanding carbon cycling and responses to climate change. However, accurate regional estimation of Net Ecosystem Exchange (NEE) remains challenging due to the environmental complexity and spatial heterogeneity. This study combined eddy covariance observations from four mangrove sites along China’s southeastern coast (natural and restored mangrove forests) with multi-source remote sensing and environmental reanalysis data to construct three variable schemes (site observations only, with added vegetation indices, and comprehensive multi-source variables). We compared three machine learning models for daily NEE prediction, including eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM). The results showed that: (1) Restored and natural mangroves exhibited similar temporal NEE dynamics and consistently functioned as carbon sinks, restored mangrove sites showed greater cross-site variability. Among the study sites, CN-LZR exhibited the strongest cumulative carbon uptake. (2) Scheme 3 combined with the XGBoost algorithm achieved the highest predictive accuracy, reaching an R² of 0.73 across sites. Differences among machine learning models were primarily associated with their ability to capture nonlinear interactions between atmospheric and hydrological variables, with tree-based models outperforming SVM. (3) SHAP analysis indicated that radiation-related variables were the dominant drivers of NEE, while hydrological influences were site-dependent; and (4) Regional upscaling indicated that all sites consistently functioned as long-term carbon sinks, with CN-LZR exhibiting slightly higher daily mean carbon uptake than the other sites. This study presented the first machine learning framework for estimating daily-scale NEE in mangroves, providing methodological and data support for regional carbon flux assessment and blue carbon management. Full article

(This article belongs to the Special Issue Advanced Remote Sensing Technology for Precision Forestry and Carbon Sink Assessment)

► Show Figures

Figure 1

26 pages, 20096 KB

Open AccessArticle

Enhanced Sea Ice Classification Method for Dual-Polarization TOPSAR via Limited Full-Polarimetric Knowledge Distillation

by Di Yin, Jiande Zhang, Jiayuan Shen, Jitong Duan, Xiaochen Wang, Guangyao Zhou, Bing Han and Wen Hong

Remote Sens. 2026, 18(4), 666; https://doi.org/10.3390/rs18040666 - 22 Feb 2026

Viewed by 432

Abstract

Accurate large-scale sea ice classification is vital for Arctic maritime activities. However, this task faces a fundamental challenge. Operational surveillance is restricted to wide-swath dual-polarization data, which limits classification precision due to polarimetric information deficiency. Conversely, while the quad-polarization mode offers the comprehensive [...] Read more.

Accurate large-scale sea ice classification is vital for Arctic maritime activities. However, this task faces a fundamental challenge. Operational surveillance is restricted to wide-swath dual-polarization data, which limits classification precision due to polarimetric information deficiency. Conversely, while the quad-polarization mode offers the comprehensive scattering details required for more accurate classification, its narrow swath width prevents efficient large-scale monitoring. To address this challenge, we propose an enhanced sea ice classification method relying on limited co-region quad-polarization information to enhance dual-polarization data classification accuracy across larger spatiotemporal scales. Specifically, we construct a polarization-guided cross-mode knowledge distillation framework featuring an asymmetric teacher–student architecture. In this design, a hybrid CNN-Transformer teacher extracts robust scattering features from quad-polarization data to guide a lightweight student network operating on dual-polarization inputs. Through this transfer, the student acquires rich feature representations comparable to quad-polarization data, effectively compensating for the missing polarimetric scattering information. Experimental results on GF3-02 data demonstrate that the proposed method significantly outperforms the standalone dual-polarization network baseline, achieving an overall accuracy of 86.15%. This validates the effectiveness of the proposed method in enabling high-precision sea ice classification for large-scale monitoring. Full article

(This article belongs to the Special Issue Cutting-Edge PolSAR Imaging Applications and Techniques)

► Show Figures

Figure 1

26 pages, 6145 KB

Open AccessArticle

Using Multispectral UAV Imagery for Rye Biomass Estimation and SEM-Based Attribution Analysis

by Wenyi Lu, Xiang Zhang, Masakazu Komatsuzaki, Tsuyoshi Okayama, Shuang Yang and Nengcheng Chen

Remote Sens. 2026, 18(4), 665; https://doi.org/10.3390/rs18040665 - 22 Feb 2026

Viewed by 579

Abstract

Effective management of rye cover crops in cash-crop systems relies heavily on accurate biomass estimation. Low-altitude Unmanned Aerial Vehicle (UAV) imagery offers a promising high-resolution alternative, yet unlocking its full potential requires moving beyond basic estimation models to more integrative and explanatory models. [...] Read more.

Effective management of rye cover crops in cash-crop systems relies heavily on accurate biomass estimation. Low-altitude Unmanned Aerial Vehicle (UAV) imagery offers a promising high-resolution alternative, yet unlocking its full potential requires moving beyond basic estimation models to more integrative and explanatory models. This study obtains the measured height (MH), SPAD (Soil and Plant Analyzer Development) values, and measured dry biomass (MDB) and applies UAV remote sensing and machine learning to acquire the crop canopy height, vegetation indices (VIs), and vegetation fraction (VF) across growth stages. Among single-parameter biomass estimation models, the estimated height yields the best at the overall growth stage (R² = 0.935), whereas selected VIs perform the best at the non-seedling stage (R² = 0.851). For multi-parameters modeling, models combining height, VF, and VIs significantly outperform the single-parameter models, achieving better estimation results throughout each growth stage (Best R² = 0.951). Structural equation modeling clarifies the direct and indirect contributions of these parameters to biomass accumulation, revealing their synergistic effects. This study demonstrates the potential of UAV-based multi-parameter biomass estimation model to support more informed decisions in cover crop management and to advance broader precise agriculture practices. Additionally, the analytical framework developed here offers a transferable approach for high-resolution biomass monitoring in other crop systems. Full article

(This article belongs to the Special Issue Crop Yield Prediction Using Remote Sensing Techniques)

► Show Figures

Figure 1

37 pages, 34025 KB

Open AccessArticle

Individual Tree Segmentation from LiDAR Point Clouds: A Mamba-Enhanced Sparse CNN Approach for Accurate Forest Inventory

by Xiangji Peng, Jizheng Yi, Rong Liu, Xiangyu Shen and Xiaoyao Li

Remote Sens. 2026, 18(4), 664; https://doi.org/10.3390/rs18040664 - 22 Feb 2026

Viewed by 1019

Abstract

Individual tree segmentation is critical for automated forest inventory systems, enabling detailed individual tree records that support precision forest management. While current airborne LiDAR systems can acquire high-density, high-accuracy point clouds of dense forests, significant challenges remain in analyzing the diversity of forest [...] Read more.

Individual tree segmentation is critical for automated forest inventory systems, enabling detailed individual tree records that support precision forest management. While current airborne LiDAR systems can acquire high-density, high-accuracy point clouds of dense forests, significant challenges remain in analyzing the diversity of forest samples across different regions. An improved method of instance segmentation using a Mamba-Enhanced Sparse Convolutional Neural Network is proposed to address the problem of misallocation caused by ambiguous boundaries and overlapping canopies of individual trees. An innovative offset prediction method further reduces the high error rate in low-canopy datasets. On the basis of a variety of features, the designed network customizes the HDBSCAN clustering algorithm and the W-KNN neighborhood search algorithm for fine-grained instance segmentation to achieve optimal performance. To address the lack of block coherence in the FOR-instance dataset and to reduce redundant noisy trees in some regions, this work develops a novel pipeline to simulate real woodland scenes and evaluates the robustness of the network in composite forests. Extensive validation on real and benchmark data demonstrates the method’s superior generalization capability, yielding robust segmentation results across varied forest structures. The most marked gains are achieved in low-canopy settings, confirming the method’s enhanced ability to handle complex structural overlaps. Our method provides a more comprehensive solution for the inventory management of structurally heterogeneous or regionally diverse woodlands, thereby enhancing both the automation and precision of forest resource assessment. Full article

(This article belongs to the Section Forest Remote Sensing)

► Show Figures

Figure 1

25 pages, 5932 KB

Open AccessArticle

China Aerosol Raman Lidar Network (CARLNET)—Part II: Quality Assessment of Lidar Raw Data

by Zhichao Bu, Yaru Dai, Song Mao, Qin Wang, Zhenping Yin, Yubin Wei, Xuan Wang, Yubao Chen and Peng Zhang

Remote Sens. 2026, 18(4), 663; https://doi.org/10.3390/rs18040663 - 22 Feb 2026

Viewed by 780

Abstract

The China Aerosol Raman Lidar Network (CARLNET), developed by the China Meteorological Administration, currently comprises 49 multiwavelength polarization Raman lidars used for meteorological and atmospheric-environment monitoring. Timely and automatic quality assessment of the lidar raw signal is vital for a large atmospheric lidar [...] Read more.

The China Aerosol Raman Lidar Network (CARLNET), developed by the China Meteorological Administration, currently comprises 49 multiwavelength polarization Raman lidars used for meteorological and atmospheric-environment monitoring. Timely and automatic quality assessment of the lidar raw signal is vital for a large atmospheric lidar network. This study proposes a quality assessment method of lidar raw data for the CARLNET. By scoring three factors, signal saturation at near-range, Rayleigh fit and effective detection range, and weighting each influence factor according to its importance, each lidar raw data is tagged by a composite score. These scores reflect the quality of lidar raw data, as well as potential issues of lidar systems. Three lidars under three typical weather scenarios are used to analyze the impact of observation scenarios on lidar raw data, and the results show that the proposed method can effectively distinguish the lidar raw data quality under different scenarios. By analyzing the scores of lidar raw data, two potential hardware issues (optical-axis misalignment and signal-receiving issues) are identified, which provide guidance for equipment maintenance. In addition, we applied the method to one-year CARLNET measurement data. Temporally, five representative sites were selected for analysis of their annual data, revealing the seasonal and overall scores of the raw data. Spatially, the signals at the 355 nm, 532 nm, and 1064 nm channels of 49 nationwide distributed lidars were evaluated and categorized into six groups based on their scores, which provides support for lidar network data quality monitoring, operational applications, and scientific research. Full article

(This article belongs to the Special Issue Advances in Atmospheric Aerosol Monitoring Based on Lidar and Satellites)

► Show Figures

Figure 1

26 pages, 17126 KB

Open AccessArticle

Towards Discriminative and Consistent Cross-Modal Alignment for Remote Sensing Image–Text Retrieval

by Zihan Song, Yulou Shu, Wengen Li, Jihong Guan and Yichao Zhang

Remote Sens. 2026, 18(4), 662; https://doi.org/10.3390/rs18040662 - 22 Feb 2026

Viewed by 808

Abstract

As large-scale remote sensing data continue to proliferate, research on remote sensing image–text retrieval (RSITR) has become progressively more prominent. Nevertheless, RSITR still faces two primary challenges. First, remote sensing data exhibit substantially higher intra-modal similarity than typical natural image–text corpora, complicating the [...] Read more.

As large-scale remote sensing data continue to proliferate, research on remote sensing image–text retrieval (RSITR) has become progressively more prominent. Nevertheless, RSITR still faces two primary challenges. First, remote sensing data exhibit substantially higher intra-modal similarity than typical natural image–text corpora, complicating the discrimination of positive and negative pairs. Second, vision–language models pretrained on natural images (VLP), such as CLIP, are not readily adaptable to remote sensing scenarios without undergoing large-scale remote sensing pretraining that entails substantial cost. To tackle these challenges, we introduce DCCA, a novel framework designed for discriminative and consistent cross-modal alignment. We develop a global contrastive learning strategy with negative pair expansion mechanism to boost representation discrimination when intra-modal similarity is pronounced. Additionally, we introduce a bidirectional distribution matching constraint that jointly aligns intra- and inter-modal distributions, promoting consistent cross-modal alignment beyond the instance level. To further enhance domain adaptation, we propose a remote sensing information injection module that transfers knowledge from a pretrained remote sensing image recognition model into VLP, thereby improving its visual discriminability in remote sensing scenarios. Evaluations conducted on publicly available RSITR benchmarks indicate that DCCA consistently surpasses baseline methods, while attaining performance on par with models trained using large-scale remote sensing datasets under markedly reduced data requirements. These findings verify that the framework is both effective and well-suited for practical deployment. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

19 pages, 5637 KB

Open AccessArticle

Can the Subsidence of High-Fill Airports Be Avoided Using Engineering Approaches? A National-Scale SBAS-InSAR-Based Examination in China

by Meixuan Lan, Qiong Wu, Jun Wang, Liwei Gong, Na Ta and Kuiwen Wang

Remote Sens. 2026, 18(4), 661; https://doi.org/10.3390/rs18040661 - 21 Feb 2026

Viewed by 487

Abstract

With the rapid expansion of airport construction projects in China, high-fill airports are frequently built under complex geological conditions, where the high risk of surface stability may significantly affect flight safety and operational costs. In this study, 17 high-fill airports and 11 non-high-fill [...] Read more.

With the rapid expansion of airport construction projects in China, high-fill airports are frequently built under complex geological conditions, where the high risk of surface stability may significantly affect flight safety and operational costs. In this study, 17 high-fill airports and 11 non-high-fill airports across China, all characterized by high subsidence risks, were selected to investigate vertical ground deformation. Utilizing multi-temporal Sentinel-1A radar imagery spanning from 2017 to 2024, Small Baseline Subset InSAR (SBAS-InSAR) was employed to retrieve the annual average deformation velocities and time-series cumulative displacements. The results revealed that among the selected sites, only 25% were relatively stable, while the others exhibited significant deformation characteristics. Notably, high-fill airports demonstrated greater deformation magnitudes compared to those in plain areas, especially in the area of prevalent slope subsidence. In addition, significantly positive correlation was found between fill height and deformation magnitude, while differential settlement was widespread in runway zones. Furthermore, foundations involving special ground conditions manifested continuedly and distinct deformation patterns despite ground treatments. This study demonstrates the limitations of current engineering approaches in completely eliminating airport deformation, and offers valuable insights for the site selection, engineering design, and maintenance of high-fill airports. Full article

(This article belongs to the Special Issue Advances in InSAR Processing: Algorithmic Developments and Diverse Applications)

► Show Figures

Figure 1

27 pages, 9820 KB

Open AccessArticle

Normalized Satellite-Derived Bathymetry Model from Landsat 8 Single-Band Image with Underwater Topography Trend for Nearshore Shallow Waters

by Jiasheng Xu, Jinfeng Ge, Guoqing Zhou, Ertao Gao, Xiang Zhou, Yuejun Huang, Juanfeng Li, Yang Yu, Zhenyin Yang, Yao Lei, Qiang Zhu, Yuhang Bai and Qinghu Teng

Remote Sens. 2026, 18(4), 660; https://doi.org/10.3390/rs18040660 - 21 Feb 2026

Viewed by 748

Abstract

Satellite-derived bathymetry holds significant value for acquiring nearshore bathymetric data. However, in coastal waters, bathymetry is affected by in-water particle scattering and seafloor substrate variability, leading to spatial inconsistency between the logarithmic green band profile derived from multispectral satellite imagery and the actual [...] Read more.

Satellite-derived bathymetry holds significant value for acquiring nearshore bathymetric data. However, in coastal waters, bathymetry is affected by in-water particle scattering and seafloor substrate variability, leading to spatial inconsistency between the logarithmic green band profile derived from multispectral satellite imagery and the actual water depth profile. According to the position information of interpolated points and the inverse distance square relationship with the surrounding 16 points from low-reference bathymetric data (such as the bathymetric map from GEBCO, NOAA Electronic Navigational Charts), this model adopts a third-order inverse distance square bicubic convolution interpolation method to resample a high-resolution bathymetric map with the size of the satellite image. Normalized underwater topography trend data (derived from the low-resolution reference bathymetric map) were combined with normalized green band data to compute an averaged dataset. In this way, a linear bathymetric model was constructed. We invert this model’s parameters and calculate the water depth by using the average data and reference points from reference bathymetric data. Validation tests were conducted across three test areas using independent validation bathymetric data: Weizhou Island, China (Case II waters); Saipan, Northern Mariana Islands, USA (Case I waters); and Molokai Island, Hawaii, USA (Case I waters). Each test area was studied using five error analysis methods (i.e., scatterplot, error histogram, regional bathymetric error, three check lines, and seven check points). Compared to four classic bathymetric models (i.e., single-band model, log-ratio model, ratio-log model, and multi-band model), the proposed model achieved lower root mean square errors (RMSE) of 2.08 m, 1.40 m, and 2.01 m in the three test areas, representing reductions of 35%, 43%, 45%, and 20% and overall averages of 48%, 62%, 64%, and 43%, respectively. Its goodness of fit (R²) reached 0.87, 0.97, and 0.97, showing improvements of at least 5%, 5%, 9%, and 9% and overall averages of 17%, 77%, 84%, and 12%, respectively. The results demonstrate that the proposed model significantly improves bathymetry accuracy while maintaining algorithmic simplicity, providing a new model for acquiring nearshore foundational bathymetric maps. Full article

(This article belongs to the Special Issue Remote Sensing in Monitoring Coastal and Inland Waters)

► Show Figures

Figure 1

32 pages, 3485 KB

Open AccessSystematic Review

A Systematic Review of Available Multispectral UAV Image Datasets for Precision Agriculture Applications

by Andrea Caroppo, Giovanni Diraco and Alessandro Leone

Remote Sens. 2026, 18(4), 659; https://doi.org/10.3390/rs18040659 - 21 Feb 2026

Cited by 3 | Viewed by 1742

Abstract

The proliferation of Unmanned Aerial Vehicles (UAVs) equipped with multispectral imaging sensors has revolutionized data collection in precision agriculture. These platforms provide high-resolution, temporally dense data crucial for monitoring crop health, optimizing resource management, and predicting yield. However, the development and validation of [...] Read more.

The proliferation of Unmanned Aerial Vehicles (UAVs) equipped with multispectral imaging sensors has revolutionized data collection in precision agriculture. These platforms provide high-resolution, temporally dense data crucial for monitoring crop health, optimizing resource management, and predicting yield. However, the development and validation of robust data-driven algorithms, from vegetation index analysis to complex deep learning models, are contingent upon the availability of high-quality, standardized, and publicly accessible datasets. This review systematically surveys and characterizes the current landscape of available datasets containing multispectral imagery acquired by UAVs in agricultural contexts. Following guidelines for reporting systematic reviews and meta-analyses (PRISMA methodology), 39 studies were selected and analyzed, categorizing them based on key attributes including spectral bands (e.g., RGB, Red Edge, Near-Infrared), spatial and temporal resolution, types of crops studied, presence of complementary ground-truth data (e.g., biomass, nitrogen content, yield maps), and the specific agricultural tasks they support (e.g., disease detection, weed mapping, water stress assessment). However, the review underscores a critical gap in standardization, with significant variability in data formats, annotation quality, and metadata completeness, which hampers reproducibility and comparative analysis. Furthermore, we identify a need for more datasets targeting specific challenges like early-stage disease identification and anomaly detection in complex crop canopies. Finally, we discuss future directions for the creation of more comprehensive, benchmark-ready open datasets that will be instrumental in accelerating research, fostering collaboration, and bridging the gap between algorithmic innovation and practical agricultural deployment. This work serves as a foundational guide for researchers and practitioners seeking suitable data for their work and contributes to the ongoing effort of standardizing open data practices in agricultural remote sensing. Full article

(This article belongs to the Special Issue Applications of Unmanned Aerial Remote Sensing in Precision Agriculture)

► Show Figures

Figure 1

38 pages, 5701 KB

Open AccessArticle

TiARA (Version 2.1): Simulations of Particle Microphysical Parameters Retrievals Based on MERRA-2 Synthetic Organic Carbon–Dust Mixtures in the Context of Multiwavelength Lidar Data

by Alexei Kolgotin, Detlef Müller, Lucia Mona and Giuseppe D’Amico

Remote Sens. 2026, 18(4), 658; https://doi.org/10.3390/rs18040658 - 21 Feb 2026

Viewed by 496

Abstract

Numerical simulations of (1) two aerosol types such as organic carbon (i.e., spherical) and dust (i.e., non-spherical) particles, and (2) their mixtures are carried out. Optical and microphysical parameters of these aerosols in our simulations are provided by MERRA-2 (Modern-Era Retrospective Analysis for [...] Read more.

Numerical simulations of (1) two aerosol types such as organic carbon (i.e., spherical) and dust (i.e., non-spherical) particles, and (2) their mixtures are carried out. Optical and microphysical parameters of these aerosols in our simulations are provided by MERRA-2 (Modern-Era Retrospective Analysis for Research and Applications, version 2). The inversion routine is performed with TiARA (Tikhonov Advanced Regularization Algorithm) using the Lorenz–Mie (i.e., spherical) light-scattering model in unsupervised and automated, i.e., autonomous mode. The results of our numerical simulations show that the accuracy of the inversion results for the aerosol mixtures from synthetic optical data perturbed by ±10% random error is comparable to the accuracy observed for the inversion results of the “pure” spherical particles. In particular, the retrieval uncertainties of effective radius, and number, surface-area, and volume concentrations of these mixtures are ±30%, ±10%, between −50% and +100% and ±30%, respectively. However, we need to apply a modified version of the gradient correlation method (GCM) to stabilize the inversion results. The results of this study will form the baseline for future work, where we plan to apply TiARA to optical data products obtained from real lidar observations in the framework of the SCC (Single Calculus Chain) of EARLINET (European Aerosol Research Lidar Network). Full article

► Show Figures

Figure 1

30 pages, 6011 KB

Open AccessArticle

Climatic and Fuel Drivers of Lightning-Induced Forest Fire Burned Area in the Da Hinggan Ling Region, Northeast China

by Liming Lou, Wenbo Ma, Pengle Cheng, Hui Liu and Ying Huang

Remote Sens. 2026, 18(4), 657; https://doi.org/10.3390/rs18040657 - 21 Feb 2026

Cited by 1 | Viewed by 736

Abstract

Lightning-induced forest fires represent a dominant natural ignition source in boreal and temperate ecosystems, yet their climatic and biophysical controls remain poorly understood. This study investigates the spatiotemporal patterns and environmental drivers of 646 lightning-induced forest fires across the Da Hinggan Ling region, [...] Read more.

Lightning-induced forest fires represent a dominant natural ignition source in boreal and temperate ecosystems, yet their climatic and biophysical controls remain poorly understood. This study investigates the spatiotemporal patterns and environmental drivers of 646 lightning-induced forest fires across the Da Hinggan Ling region, Northeast China, during 2001–2024. Multi-source datasets from ERA5-Land, MODIS, and ETCCDI were integrated to quantify short-term meteorological variability, vegetation water status, and long-term climatic extremes. Using Random Forest and XGBoost models combined with SHAP interpretability analysis, we identified key predictors and nonlinear responses of burned area to environmental forcing. Results reveal pronounced interannual fluctuations in fire activity, with 2010, 2016, and 2022 emerging as compound extreme years characterized by co-occurring drought and heatwaves. Vegetation moisture index (NDMI), diurnal temperature range (DTR), and heatwave duration (HWDI) were the most influential variables controlling burned area variability. The total burned area and fire duration showed significant declining trends, while high burned-area fires exhibited spatial clustering in dry, low-LAI regions. These findings demonstrate that compound dry–hot conditions coupled with vegetation desiccation are the primary drivers of large lightning fires. The study provides a process-based understanding of climate–fuel–fire linkages and supports improved fire risk forecasting under a warming climate. Full article

(This article belongs to the Special Issue Remote Sensing-Based Assessments in the Forest Fire Disturbance Continuum)

► Show Figures

Figure 1

20 pages, 6717 KB

Open AccessArticle

Unraveling Patch Size Effects in Vision Transformers: Adversarial Robustness in Hyperspectral Image Classification

by Shashi Kiran Chandrappa, Sidike Paheding and Abel A. Reyes-Angulo

Remote Sens. 2026, 18(4), 656; https://doi.org/10.3390/rs18040656 - 21 Feb 2026

Viewed by 724

Abstract

Vision Transformers (ViTs) have demonstrated strong performance in hyperspectral image (HSI) classification; however, their robustness is highly sensitive to patch size. This study investigates the impact of spatial patch size on clean accuracy and adversarial robustness using a standard ViT and a Channel [...] Read more.

Vision Transformers (ViTs) have demonstrated strong performance in hyperspectral image (HSI) classification; however, their robustness is highly sensitive to patch size. This study investigates the impact of spatial patch size on clean accuracy and adversarial robustness using a standard ViT and a Channel Attention Fusion variant (ViT-CAF). Patch sizes from 1 × 1 to 19 × 19 are evaluated across four benchmark datasets under FGSM, BIM, CW, PGD, and RFGSM attacks. Descriptive results show that smaller patches, particularly 1 × 1 and 3 × 3, generally yield higher adversarial accuracy, while larger patches amplify localized perturbations and degrade robustness. Parameter analysis indicates that patch-size-dependent variations arise mainly from the embedding layer, with the Transformer backbone remaining fixed, confirming that robustness differences are driven primarily by spatial context rather than model capacity. These findings reveal a trade-off between spatial granularity and adversarial resilience and provide guidance for patch size selection in ViT-based HSI applications. Full article

(This article belongs to the Special Issue Deep Neural Networks for Hyperspectral Remote Sensing Image Processing (Second Edition))

► Show Figures

Figure 1

20 pages, 9237 KB

Open AccessArticle

Transferring RGB-Pretrained CNNs to Multispectral UAV Imagery for Salt Marsh Vegetation Classification

by Sadiq Olayiwola Macaulay, Eleonora Maset, Francesco Boscutti, Paolo Cingano, Francesco Trevisan, Giacomo Trotta, Marco Vuerich and Andrea Fusiello

Remote Sens. 2026, 18(4), 655; https://doi.org/10.3390/rs18040655 - 21 Feb 2026

Viewed by 687

Abstract

Accurate classification of salt marsh vegetation is crucial for coastal wetland monitoring, but fine-grained species discrimination remains difficult, particularly when only limited training data are available for deep learning approaches. To address this challenge, this paper presents a transfer learning-based framework for classifying [...] Read more.

Accurate classification of salt marsh vegetation is crucial for coastal wetland monitoring, but fine-grained species discrimination remains difficult, particularly when only limited training data are available for deep learning approaches. To address this challenge, this paper presents a transfer learning-based framework for classifying salt marsh vegetation using UAV multispectral imagery, focusing on a seven-class taxonomy representative of dominant species and water surfaces. Multispectral orthophotos acquired with a MicaSense Dual-Camera system (10 spectral bands) are combined with five vegetation indices to create rich multi-channel inputs. A classification architecture inspired by heterogeneous transfer learning is developed, where a feature-encoding branch compresses the 15-channel input into three channels before processing through a VGG-16 Convolutional Neural Network (CNN), pre-trained on RGB imagery. By leveraging transfer learning from VGG-16, the proposed model achieves high classification accuracy even with limited training data. Performance is compared with traditional machine learning classifiers, namely Support Vector Machines (SVMs) and Random Forest (RF). Results show that the deep learning approach significantly outperforms SVM and RF, achieving an overall accuracy of 98.4% when jointly using spectral bands and vegetation indices. These findings demonstrate the potential of integrating multispectral UAV data and CNN-based classification to support accurate mapping of heterogeneous salt marsh communities for ecological monitoring and coastal management. Full article

► Show Figures

Figure 1

29 pages, 6342 KB

Open AccessArticle

Calculation of Excavation Volume in Open-Pit Mines Under Complex Conditions Based on Multi-Source Stereo Remote Sensing

by Yi Wen, Xin Yao, Cai Li, Zhenkai Zhou and Shizheng Shen

Remote Sens. 2026, 18(4), 654; https://doi.org/10.3390/rs18040654 - 20 Feb 2026

Viewed by 1023

Abstract

The accurate calculation of excavation volume is critical for open-pit mine planning and management. Traditional methods are often inefficient and constrained by operational conditions. In contrast, digital surface model (DSM) differential analysis using stereophotogrammetry enables rapid acquisition of excavation volume, which holds significant [...] Read more.

The accurate calculation of excavation volume is critical for open-pit mine planning and management. Traditional methods are often inefficient and constrained by operational conditions. In contrast, digital surface model (DSM) differential analysis using stereophotogrammetry enables rapid acquisition of excavation volume, which holds significant value for retrospective excavation process. However, the actual mining process is not a simple matter of “excavation” or “backfilling”, but rather a complex mining pattern involving repeated excavation as new coal seams are exposed. This study utilized multi-source stereo remote sensing data (ZY-3, GF-7 satellite and UAV data) to construct a high-precision DSM time series spanning 2013 to 2025, focusing on analyzing the topographical evolution patterns of three representative mining pits. Research indicates that constructing DSMs during summer and autumn yields higher conformity with actual terrain, RMSE = 1.67 m and ME = −0.07 m. To address diverse mining patterns, we propose two calculation methods: the Cumulative Method (CM), which captures iterative excavation-backfilling cycles, and the First-Last Subtraction Method (FLSM), which mitigates cumulative DSM errors during continuous excavation. For phased mining operations, a hybrid method combining both approaches yields optimal results. Validation in three typical pits showed relative calculation errors of 1.36%, −0.49%, and 1.68%, respectively. The study indicates that the surface morphology changes in open-pit mines exhibit distinct non-linear characteristics. The method proposed herein not only enhances computational accuracy but also provides technical support for tracing historical coal excavation volumes. Full article

(This article belongs to the Special Issue Application of Advanced Remote Sensing Techniques in Mining Areas)

► Show Figures

Figure 1

31 pages, 4226 KB

Open AccessArticle

Enhancement of Cyanobacterial Bloom Monitoring in Lake Taihu Using Dual Red-Edge Bands of GF-6/WFV: Multi-Dimensional Feature Combination and Extraction Accuracy Analysis

by Yunxiao Sun, Ruolin Zhang, Chunhong Zhao, Qingyan Meng, Zhenhui Sun, Jialong Wang, Jun Wu, Yao Wang, Decai Gao and Shuyi Guan

Remote Sens. 2026, 18(4), 653; https://doi.org/10.3390/rs18040653 - 20 Feb 2026

Viewed by 677

Abstract

Cyanobacterial blooms pose a serious threat to freshwater ecosystems, necessitating accurate remote sensing monitoring. Although red-edge bands show potential in terrestrial monitoring, their multi-dimensional features (i.e., spectral, textural, and index-based characteristics) remain underutilized for aquatic blooms. This study leverages the dual red-edge bands [...] Read more.

Cyanobacterial blooms pose a serious threat to freshwater ecosystems, necessitating accurate remote sensing monitoring. Although red-edge bands show potential in terrestrial monitoring, their multi-dimensional features (i.e., spectral, textural, and index-based characteristics) remain underutilized for aquatic blooms. This study leverages the dual red-edge bands (710 nm and 750 nm) of GF-6/WFV to enhance cyanobacterial bloom identification in Lake Taihu. Multi-temporal images from 2019–2023 were used to construct red-edge features in three dimensions: spectral (evaluated via adaptive band selection method) and Jeffries–Matusita–Bhattacharyya distance), texture (based on Gray Level Co-occurrence Matrix and principal component analysis), and indices (nine vegetation indices ranked by Random Forest importance). Twelve feature-combination schemes were designed and implemented with a Random Forest classifier. Results show that red-edge features consistently improve identification accuracy. Quantitatively, compared to the basic four-band (RGBN) combination, the 710 nm band improved spectral separability by an average of 9.63%, whereas the 750 nm band yielded a lower average improvement of 5.69%. Red-edge indices, especially the modified chlorophyll absorption reflectance index 1 (MCARI1) and normalized difference red-edge index (NDRE), exhibited higher importance than non-red-edge indices. All schemes incorporating red-edge features achieved mean overall accuracies of 92.8–94.9% and Kappa coefficients of 0.86–0.94, surpassing the basic four-band scheme. Among these features, red-edge indices contributed most significantly to accuracy gains, increasing the overall accuracy by an average of 0.36–6.06% and the Kappa coefficient by up to 0.06. The enhancement effect of the red-edge 710 nm band features was superior to that of the 750 nm band. This study demonstrates that multi-dimensional red-edge features effectively enhance the identification accuracy of cyanobacterial blooms and provides a methodological reference for operational GF-6 applications in water quality monitoring. Full article

(This article belongs to the Special Issue Remote Sensing in Water Quality Monitoring)

► Show Figures

Figure 1

31 pages, 23527 KB

Open AccessArticle

SLC-Domain SAR RFI Suppression via Sliding-Window Local Tensorization and Energy-Guided CUR Projection

by Qiang Guo, Yuhang Tian, Shuai Huang, Liangang Qi and Sergiy Shulga

Remote Sens. 2026, 18(4), 652; https://doi.org/10.3390/rs18040652 - 20 Feb 2026

Viewed by 595

Abstract

Synthetic aperture radar (SAR) imaging is highly vulnerable to radio-frequency interference (RFI) in complex electromagnetic environments, which can introduce structured artifacts and obscure targets in single-look complex (SLC) products. Most existing suppression methods rely on separability along a single dimension or require interference-specific [...] Read more.

Synthetic aperture radar (SAR) imaging is highly vulnerable to radio-frequency interference (RFI) in complex electromagnetic environments, which can introduce structured artifacts and obscure targets in single-look complex (SLC) products. Most existing suppression methods rely on separability along a single dimension or require interference-specific parameter tuning, limiting robustness under multidimensional coupling and strong scatterers. We propose a range-domain sliding-window local tensorization that rearranges SLC data into localized range–azimuth–block-index tensors to better expose multi-mode correlations. On this representation, an energy-guided tensor CUR low-rank projector is embedded into an alternating-projection scheme that alternates complex-valued soft-thresholding for the sparse scene-plus-noise term and CUR-based projection for the structured RFI term. The cleaned SLC image is obtained by de-tensorizing the estimated RFI component and subtracting it from the input SLC. Experiments on semi-synthetic data, where controlled RFI is superimposed on real SLC scenes, and on real Sentinel-1 SLC data containing RFI demonstrate improved Pearson correlation coefficient (PCC) and perceptual image quality while preserving target signatures and scene textures, particularly under strong interference and strong coupling. The proposed approach provides a practical SLC-domain RFI mitigation tool for post-focusing SAR products without requiring explicit interference parameterization. Full article

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

► Show Figures

Figure 1

26 pages, 29834 KB

Open AccessArticle

Self-Training Based Image–Text Multimodal Unsupervised Domain Adaptation Segmentation Model for Remote Sensing Images

by Qianqian Liu and Xili Wang

Remote Sens. 2026, 18(4), 651; https://doi.org/10.3390/rs18040651 - 20 Feb 2026

Viewed by 572

Abstract

Deep self-training-based unsupervised domain adaptation (UDA) semantic segmentation methods learn from labeled source domain images and unlabeled target domain images, performing more stably than those based on adversarial training. We propose a self-training-based image–text multimodal unsupervised domain adaptation semantic segmentation model (SIT-UDA) for [...] Read more.

Deep self-training-based unsupervised domain adaptation (UDA) semantic segmentation methods learn from labeled source domain images and unlabeled target domain images, performing more stably than those based on adversarial training. We propose a self-training-based image–text multimodal unsupervised domain adaptation semantic segmentation model (SIT-UDA) for remote sensing images. Unlike UDA methods, which rely solely on images, SIT-UDA enhances generalization performance by integrating category hint information from textual descriptions with image data to segment images. SIT-UDA employs a teacher–student self-training framework consisting of two components: the teacher multimodal segmentation model, which predicts pseudo-labels for target domain images, and the student multimodal segmentation model, which is trained to learn feature representations from both the source and target domains with guidance from the teacher model. To enhance the adaptability of image–text pretrained models in remote sensing domains, SIT-UDA introduces text prompt tuning to optimize the text features in the student model, and two learning strategies are proposed to optimize the model’s training objectives: One is the entropy-guided pixel-level weighting (EGPW) strategy, which adaptively weights the loss obtained by self-training on target domain images, leveraging the pseudo-labels rationally according to the entropy value at the pixel level. The other is the contrastive text constraint (CTC) strategy, which maximizes the similarity of text features for the same category between teacher and student models while minimizing the similarity of text features across different categories, improving text feature discriminability to promote cross-domain image–text alignment. Experiments in various domain adaptation scenarios among three remote sensing datasets (Potsdam, Vaihingen and LoveDA) demonstrate that the SIT-UDA is superior to the comparative domain adaptation semantic segmentation methods in terms of qualitative and quantitative segmentation results. Full article

(This article belongs to the Special Issue Advances in Deep Learning and Machine Learning for Remote Sensing Image Analysis)

► Show Figures

Figure 1

25 pages, 6477 KB

Open AccessArticle

Characteristics of Thunderstorms in the Hinterland of the Tibetan Plateau and Impact of the Topographic Slope

by Siyu Chen, Chunsong Lu and Jinghua Chen

Remote Sens. 2026, 18(4), 650; https://doi.org/10.3390/rs18040650 - 20 Feb 2026

Viewed by 571

Abstract

Deep convection strongly influences regional water cycles over the Tibetan Plateau (TP), often referred to as the “Asian Water Tower.” Using FY-2E thundercloud observations, we examined the deep convection characteristics over the central TP. Deep convective storms over the TP exhibit pronounced spatiotemporal [...] Read more.

Deep convection strongly influences regional water cycles over the Tibetan Plateau (TP), often referred to as the “Asian Water Tower.” Using FY-2E thundercloud observations, we examined the deep convection characteristics over the central TP. Deep convective storms over the TP exhibit pronounced spatiotemporal heterogeneity. The frequency distribution of storm areas follows an exponential pattern in all seasons, and the cloud-top black body temperature (TBB) distribution is negatively skewed, with values concentrated between −40 and −36 °C. Deep convection is most active in summer, with storms that are larger and have colder cloud tops. In spring, storms are less frequent but tend to cover larger areas, whereas autumn is dominated by small- to medium-sized systems. Spatially, the southeastern and southwestern TP are high-frequency centers, with storm occurrence 2–3 times higher than in the northern TP. Associations between deep-convection properties and precipitation vary by season and region. In summer, storm-related precipitation is primarily linked to large storm areas, whereas in autumn it is more strongly associated with storms with lower TBB. In the southwestern TP, precipitation intensity is more strongly related to TBB, whereas in the northwestern TP, it is more sensitive to storm area. Topographic slope also modulates both precipitation and storm properties. Most storm precipitation occurs over slopes ≤14°, and heavy precipitation shows a bimodal dependence on slope, with peaks at 3–4° and 11–13°. Gentle slopes favor storm growth and horizontal expansion; as the slope increases, mean TBB increases, and deep convection weakens. Full article

► Show Figures

Figure 1

26 pages, 3736 KB

Open AccessArticle

EIMGDNet: An Edge-Induced and Multi-Dimensional Grouped Difference Network for Remote Sensing Image Change Detection

by Le Sun, Mingxuan Ding, Qiaolin Ye, Yuhui Zheng, Zebin Wu and Wen Lu

Remote Sens. 2026, 18(4), 649; https://doi.org/10.3390/rs18040649 - 20 Feb 2026

Viewed by 611

Abstract

Change detection in remote sensing imagery is crucial for monitoring temporal variations in surface characteristics; nevertheless, it presents significant challenges owing to indistinct boundaries, limited semantic differentiation, and inadequate incorporation of multi-scale contextual information. To solve these problems, we propose EIMDGNet (Edge-Induced and [...] Read more.

Change detection in remote sensing imagery is crucial for monitoring temporal variations in surface characteristics; nevertheless, it presents significant challenges owing to indistinct boundaries, limited semantic differentiation, and inadequate incorporation of multi-scale contextual information. To solve these problems, we propose EIMDGNet (Edge-Induced and Multi-Dimensional Grouped Difference Network), a novel architecture that enhances boundary representation and cross-scale feature interaction for accurate and robust change detection. EIMDGNet adopts a dual-branch ResNet18 backbone to extract multi-scale features from bi-temporal images, capturing both fine spatial detail and high-level semantic context. To improve boundary awareness and reduce pseudo-change interference, we introduce the Edge-Induced Differential Multi-Dimensional Group Enhancement Module (EID-MDGEM). This module enriches fine-grained spatial features through grouped pooling across spatial and channel dimensions, enabling precise localization of change contours. Within EID-MDGEM, the Edge Feature Enhancement Module (EFEM) integrates a parameter-free attention mechanism to generate edge-saliency maps, highlighting true change regions while suppressing background noise and irrelevant variations. To further enhance semantic consistency across feature scales, we design the Multi-Scale Hierarchical Progressive Fusion Module (MSHPM). This component employs a bottom-up progressive strategy to hierarchically integrate low-level spatial details with high-level semantic abstractions, thus increasing the continuity and completeness of detected change regions. By tightly coupling edge-aware enhancement with multi-scale hierarchical fusion, EIMDGNet effectively addresses major obstacles in change detection, including boundary ambiguity, inconsistent scale information, and feature misalignment. We evaluated EIMDGNet on five remote sensing change detection datasets: LEVIR-CD, DSIFN-CD, S2Looking, CLCD-CD and GVLM-CD. Our method consistently outperformed state-of-the-art approaches, achieving 91.49% F1 and 82.93% IoU on LEVIR-CD, 77.32% F1 and 69.39% IoU on DSIFN-CD, the highest 49.19% IoU and 99.20% OA on S2Looking, 81.65% F1 and 72.91% IoU on CLCD-CD, and 85.49% F1 and 76.08% IoU on GVLM-CD. These results demonstrate the superior accuracy and robustness of EIMDGNet across diverse change detection scenarios. Full article

► Show Figures

Figure 1

25 pages, 4669 KB

Open AccessArticle

Optimizing Surface Type Definitions in Radiance-to-Irradiance Conversions for Future Earth Radiation Budget Satellite Measurements

by Mathew van den Heever, Jake J. Gristey and Peter Pilewskie

Remote Sens. 2026, 18(4), 648; https://doi.org/10.3390/rs18040648 - 20 Feb 2026

Viewed by 397

Abstract

Angular Distribution Models (ADMs) are essential for converting observed radiances from satellite sensors to the energy-budget–relevant quantity of irradiance. In preparation for the NASA Libera mission, this study presents a data-driven framework to identify optimal groupings of International Geosphere–Biosphere Programme (IGBP) surface types [...] Read more.

Angular Distribution Models (ADMs) are essential for converting observed radiances from satellite sensors to the energy-budget–relevant quantity of irradiance. In preparation for the NASA Libera mission, this study presents a data-driven framework to identify optimal groupings of International Geosphere–Biosphere Programme (IGBP) surface types for Libera’s split-shortwave ADMs, in an effort to minimize the uncertainty associated with radiance-to-irradiance conversions while maintaining operational feasibility. Using data from the Clouds and the Earth’s Radiant Energy System (CERES) Flight Model 5 (FM-5), K-means clustering is applied within angular bins to capture viewing-geometry-dependent radiometric behavior. These angular clustering solutions are then assessed via hierarchical consensus clustering to derive consistent surface groups. The analysis suggests seven surface groups (K = 7) optimize the surface clustering space. The resulting classifications are broadly consistent with historical CERES–TRMM ADM surface definitions, preserving radiometrically distinct surfaces such as water bodies and snowy surfaces while highlighting opportunities to consolidate vegetative IGBP surface classes. This study provides an objective and physically grounded basis for defining Libera ADM surface groups, ensuring a robust balance between model accuracy and operational simplicity. Full article

► Show Figures

Figure 1

30 pages, 50903 KB

Open AccessArticle

A Realistic Instance-Level Data Augmentation Method for Small-Object Detection Based on Scene Understanding

by Chuwei Li, Zhilong Zhang, Ping Zhong and Jun He

Remote Sens. 2026, 18(4), 647; https://doi.org/10.3390/rs18040647 - 20 Feb 2026

Viewed by 906

Abstract

Instance-level data augmentation methods, exemplified by “copy-paste”, serve as a conventional strategy for improving the performance of small object detectors. The core idea involves leveraging background redundancy by compositing object instances with suitable backgrounds—drawn either from the same image or from different images—to [...] Read more.

Instance-level data augmentation methods, exemplified by “copy-paste”, serve as a conventional strategy for improving the performance of small object detectors. The core idea involves leveraging background redundancy by compositing object instances with suitable backgrounds—drawn either from the same image or from different images—to increase both the quantity and diversity of training samples. However, existing methods often struggle with mismatches in background, scale, illumination, and viewpoint between instances and backgrounds. More critically, their predominant reliance on background information, without a joint understanding of instance-background characteristics, results in augmented images lacking visual realism. Empirical studies have demonstrated that such unrealistic images not only fail to improve detection performance but can even be detrimental. To tackle this problem, we propose a scene-understanding-driven approach that systematically addresses these mismatches via joint instance-background understanding. This is achieved through a unified framework that integrates image inpainting, image tagging, open-set object detection, the Segment Anything Model (SAM), and pose estimation to jointly model instance attributes, background semantics, and their interrelationships, thereby abandoning the random operation paradigm of existing methods and synthesizing highly realistic augmented images while preserving data diversity. On the VisDrone dataset, our method improves the mAP@0.5:0.95 and mAP@0.5 of the baseline detector by 1.6% and 2.2%, respectively. Both quantitative gains and qualitative visualizations confirm that the systematic resolution of these mismatches directly translates into significantly higher visual realism and detection performance improvements. Full article

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

► Show Figures

Figure 1

20 pages, 4719 KB

Open AccessArticle

Cropland Extraction Based on PlanetScope Images and a Newly Developed CAFM-Net Model

by Jianhua Ren, Yating Jing, Xingming Zheng, Sijia Li, Kai Li and Guangyi Mu

Remote Sens. 2026, 18(4), 646; https://doi.org/10.3390/rs18040646 - 19 Feb 2026

Viewed by 545

Abstract

Cropland constitutes a foundational resource for global food security and agricultural sustainability, and its accurate extraction from high-resolution remote sensing imagery is essential for agricultural monitoring and land management. However, existing deep learning-based segmentation methods often struggle to balance global contextual modeling and [...] Read more.

Cropland constitutes a foundational resource for global food security and agricultural sustainability, and its accurate extraction from high-resolution remote sensing imagery is essential for agricultural monitoring and land management. However, existing deep learning-based segmentation methods often struggle to balance global contextual modeling and fine-grained boundary representation, leading to boundary blurring and omission of small cropland parcels. To address these challenges, this study proposes a novel CNN–Transformer dual-branch fusion network, named CAFM-Net, which integrates a convolution and attention fusion module (CAFM) and an edge-assisted supervision head (EH) to jointly enhance global–local feature interaction and boundary delineation capability. Experiments were conducted on a self-built PlanetScope cropland dataset from Suihua City, China, and the GID public dataset to evaluate the effectiveness and generalization ability of the proposed model. On the self-built dataset, CAFM-Net achieved an overall accuracy (OA) of 96.75%, an F1-score of 96.80%, and an Intersection over Union (IoU) of 93.79%, outperforming mainstream models such as UNet, DeepLabV3+, TransUNet, and Swin Transformer by a clear margin. On the GID public dataset, CAFM-Net obtained an OA of 94.58%, an F1-score of 94.19%, and an IoU of 89.02%, demonstrating strong robustness across different data sources. Ablation experiments further confirm that the CAFM contributes most significantly to performance improvement, while the EH module effectively enhances boundary accuracy. Overall, the proposed CAFM-Net provides a quantitatively validated and robust solution for fine-grained cropland segmentation from high-resolution remote sensing imagery, with clear advantages in boundary precision and small-parcel detection. Full article

(This article belongs to the Special Issue Land Cover Change Detection: Emerging Algorithms and Applications in Remote Sensing)

► Show Figures

Figure 1

22 pages, 21660 KB

Open AccessArticle

YOSDet: A YOLO-Based Oriented Ship Detector in SAR Imagery

by Chushi Yu, Oh-Soon Shin and Yoan Shin

Remote Sens. 2026, 18(4), 645; https://doi.org/10.3390/rs18040645 - 19 Feb 2026

Cited by 1 | Viewed by 788

Abstract

Synthetic aperture radar (SAR) serves as a prominent remote sensing (RS) technology, permitting continuous maritime surveillance regardless of weather or time. Although deep learning-based detectors have achieved promising results in SAR imagery, the majority of current algorithms rely on axis-aligned bounding boxes, which [...] Read more.

Synthetic aperture radar (SAR) serves as a prominent remote sensing (RS) technology, permitting continuous maritime surveillance regardless of weather or time. Although deep learning-based detectors have achieved promising results in SAR imagery, the majority of current algorithms rely on axis-aligned bounding boxes, which are insufficient for accurately representing arbitrarily oriented ships, especially under speckle noise, complex coastal clutter, and real-time deployment constraints. To address this limitation, we propose a YOLO-based oriented ship detector (YOSDet). Specifically, a dynamic aggregation module (DAM) is incorporated into the backbone to enhance feature representation against non-stationary backscattering. An objective-guided detection head (OGDH) is developed to decouple classification and localization, complemented by a localization quality estimator (LQE) to calibrate classification confidence by mitigating the impact of scattering center shifts. Comparative evaluations conducted on three public SAR ship detection benchmarks validate the effectiveness of YOSDet. The proposed model outperforms existing detectors, achieving

m A P

scores of 96.8%, 88.5%, and 67.3% on the SSDD+, HRSID, and SRSDD-v1.0 datasets, respectively. Furthermore, the consistency of our approach in both nearshore and offshore environments is confirmed through rigorous quantitative and qualitative assessments. Full article

► Show Figures

Figure 1

22 pages, 3215 KB

Open AccessArticle

Spatiotemporal Evolution Monitoring of Small Water Body Coverage Associated with Land Subsidence Using SAR Data: A Case Study in Geleshan, Chongqing, China

by Tianhao Jiang, Faming Gong, Qiankun Kong and Kui Zhang

Remote Sens. 2026, 18(4), 644; https://doi.org/10.3390/rs18040644 - 19 Feb 2026

Viewed by 472

Abstract

Monitoring small water body coverage spatiotemporal evolution in karst areas of complex hydrogeology is pivotal for water resource management and disaster assessment. With recent infrastructure expansion, intensive tunnel excavation has occurred in Chongqing’s Geleshan, a typical karst region with fragile aquifers. It has [...] Read more.

Monitoring small water body coverage spatiotemporal evolution in karst areas of complex hydrogeology is pivotal for water resource management and disaster assessment. With recent infrastructure expansion, intensive tunnel excavation has occurred in Chongqing’s Geleshan, a typical karst region with fragile aquifers. It has disrupted hydrogeological systems, triggering ground subsidence, groundwater leakage, and subsequent reservoir desiccation, as well as threatening regional water security and ecology. Thus, monitoring reservoir coverage evolution is critical to clarify dynamics and driving mechanisms. Synthetic Aperture Radar (SAR) is ideal for water body mapping, enabling data acquisition independent of illumination and weather. However, traditional SAR-based water extraction methods are hampered by low-scatter noise and poor adaptability to hydrological fluctuations. To address this, a two-stage dual-polarization SAR clustering algorithm (TSDPS-Clus) was developed using 452 time-series Sentinel-1 images (7 February 2017–24 August 2025). Specifically, the Kolmogorov–Smirnov test via pixel-wise time-series statistics screened core water areas, built candidate regions, and mitigated noise. Subsequently, dual-polarization and positional features were fused via singular value decomposition (SVD) to generate a high-discrimination low-dimensional feature set, followed by the Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA) clustering for high-precision extraction. Results demonstrate that the algorithm suits reservoir storage-desiccation dynamics; dual-polarization complementarity boosts accuracy and clarifies six reservoirs’ spatiotemporal evolution. Notably, post-2023, tunnel excavation-induced land subsidence increased drying frequency and duration, with a 24-month maximum cumulative desiccation period. Full article

(This article belongs to the Special Issue Interpretation and Attribution of Land Subsidence: A Remote Sensing and Machine Learning Perspective)

► Show Figures

Figure 1

38 pages, 11992 KB

Open AccessArticle

Combining Large Language Models with Satellite Embedding to Comprehensively Evaluate the Tibetan Plateau’s Ecological Quality

by Yuejuan Yang, Junbang Wang, Pengcheng Wu, Yang Liu and Xinquan Zhao

Remote Sens. 2026, 18(4), 643; https://doi.org/10.3390/rs18040643 - 19 Feb 2026

Viewed by 947

Abstract

As an important ecological obstacle prone to climatic changes, the Tibetan Plateau has been transformed by retreating glaciers, degrading permafrost, and deteriorating grasslands. Recent ecological remote sensing evaluations typically use medium-resolution and single-source optical imagery, highlight natural factors while ignoring human impacts, and [...] Read more.

As an important ecological obstacle prone to climatic changes, the Tibetan Plateau has been transformed by retreating glaciers, degrading permafrost, and deteriorating grasslands. Recent ecological remote sensing evaluations typically use medium-resolution and single-source optical imagery, highlight natural factors while ignoring human impacts, and encounter difficulties with time-focused interpretability and continuity within complex terrains. This research proposes a theory combining large language models with satellite embedding to holistically examine the ecology of the Tibetan Plateau between 2000 and 2024. We created an ecological satellite embedding (ESE) model applying self-supervised learning to integrate 12 ecological variables into combined space and time representations as of 2024, according to the Prithvi-Earth Observation (Prithvi-EO) foundational model involving low-rank adaptation (LoRA). GeoChat reasoning was applied to turn the embedded variables into a comprehensive representation feature (CRF). Field research demonstrated strong accuracy for the fraction of absorbed photosynthetically active radiation (FAPAR, R² = 0.9923) and aboveground biomass (AGB, R² = 0.8690). Space and temporal analyses demonstrated a general ecology-dependent enhancement accompanied by significant space-based clustering (Moran’s I = 0.50–0.80), hotspots in humid southeastern areas, major upward trends in vegetation indices and productivity metrics (p < 0.05), and higher shifts in transition regions. Despite the marginal degradation risk, the grassland carrying capacity has expanded extensively in the main farming regions. The comprehensible CRF schema identified three management areas: potential risk, enhancement potential, and stable conservation management. This transferable modular approach connects expert reasoning with data-driven modeling, presenting adaptable methods for assessing ecosystems in high-altitude, data-sparse environments, and practical ways to promote ecological management. Full article

► Show Figures

Figure 1

26 pages, 5823 KB

Open AccessArticle

A Topographic Shadow Effect Correction (TSEC) Method for Correcting Surface Reflectance of Optical Remote Sensing Images in Rugged Terrain

by Xu Yang, Wenbin Xie, Xiaoqing Zuo, Shipeng Guo, Daming Zhu, Yongfa Li, Jiangqi Li and Yan Luo

Remote Sens. 2026, 18(4), 642; https://doi.org/10.3390/rs18040642 - 19 Feb 2026

Viewed by 798

Abstract

The topographic shadow effect can cause surface reflectance distortions in the shadow areas of remote sensing images, particularly in complex mountainous areas. In this study, based on the difference in solar radiation received at the surface of sunlit and shadow areas, we introduced [...] Read more.

The topographic shadow effect can cause surface reflectance distortions in the shadow areas of remote sensing images, particularly in complex mountainous areas. In this study, based on the difference in solar radiation received at the surface of sunlit and shadow areas, we introduced the shadow intensity, vegetation index, and band adjustment factors, and proposed a topographic shadow effect correction (TSEC) method. The method was then tested using eight Landsat 8 OLI scenes under different illumination conditions from two different regions. The results indicate that TSEC effectively corrected the topographic shadow effect. The corrected images exhibited good visual quality without obvious shadow pixels. Importantly, TSEC retained spectral information in sunlit areas while correcting spectral distortion in shadow areas, resulting in strong agreement between spectral curves of shady and sunny slopes. The method demonstrated high stability in normalized difference vegetation index (NDVI) correction, as the difference in NDVI before and after correction was less than 0.07 for the four scenes within the Changjiang study area. Moreover, the TSEC corrected the enhanced vegetation index (EVI) effectively, reducing an initial EVI difference of over 0.35 between the shady and sunny slopes to a maximum of 0.074 for the four scenes within the Wuyi Mountain study area. Relative to four established topographic correction models, the proposed method suppresses the over-correction phenomena typical of self-shadows and minimizes under-correction in cast shadows, resulting in stable overall correction results with few outliers. The TSEC provides a simple and effective method to correct the distorted reflectance in shadow areas using only image and DEM data, which can be adapted to complex mountainous areas and for images with different illumination conditions. Full article

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

► Show Figures

Figure 1

26 pages, 8605 KB

Open AccessArticle

The Application of Amino Acids as a Sustainable Strategy for Managing Water Stress in Vineyards

by Fabrício Lopes Macedo, Carla Ragonezi, José Filipe Teixeira Ganança, Humberto Nóbrega, José G. R. de Freitas, Andrés A. Borges, David Jiménez-Arias and Miguel A. A. Pinheiro de Carvalho

Remote Sens. 2026, 18(4), 641; https://doi.org/10.3390/rs18040641 - 19 Feb 2026

Viewed by 553

Abstract

Water scarcity increasingly threatens viticulture in the Macaronesian region due to climatic variability and recurrent droughts. This study evaluated the physiological and productive responses of grapevines (Vitis vinifera L.) to foliar applications of two amino acid-based biostimulants, pyroglutamic acid and pipecolic acid, [...] Read more.

Water scarcity increasingly threatens viticulture in the Macaronesian region due to climatic variability and recurrent droughts. This study evaluated the physiological and productive responses of grapevines (Vitis vinifera L.) to foliar applications of two amino acid-based biostimulants, pyroglutamic acid and pipecolic acid, under contrasting water availability conditions on Madeira Island, Portugal. Three non-irrigated treatments were arranged in a randomized complete block design: T1 (no irrigation and no amino acids), T2 (pyroglutamic acid, without irrigation), and T3 (pipecolic acid, without irrigation), while conventional irrigation (T4) was included as a non-randomized reference. Agronomic parameters and UAV-derived multispectral and thermal data were analyzed during the 2023 (moderate drought) and 2024 (severe drought) growing seasons. Vegetation indices (NDVI, GNDVI, NDRE, NGRDI, and GLI) and the Simplified Crop Water Stress Index (CWSI_si) were used to assess canopy vigor and plant water status. In 2023, T4 showed significantly higher bunch number and total yield, whereas differences among non-irrigated treatments were not statistically significant. Nevertheless, T2 showed consistent numerical trends toward higher yield components and a comparatively more stable canopy thermal response than the untreated control. In 2024, severe drought reduced productivity across all treatments, with no significant difference detected. Yield components were generally strongly correlated, while CWSI_si was negatively associated with vegetation indices, particularly under moderate drought. The NGRDI demonstrated potential as a low-cost RGB-based indicator but requires cautious interpretation. Overall, pyroglutamic acid may represent a complementary strategy to irrigation and UAV-based precision monitoring in drought-prone viticulture, although confirmation through longer-term and higher-powered field studies is required. Full article

(This article belongs to the Special Issue Application of UAV Images in Precision Agriculture)

► Show Figures

Figure 1

27 pages, 6565 KB

Open AccessArticle

Environmental Degradation in Iraq: Attribution of Climatic Change and Human Influences Through Multi-Factor Analysis

by Akram Alqaraghuli, Peter North, Iain Bye, Jacqueline Rosette and Sietse Los

Remote Sens. 2026, 18(4), 640; https://doi.org/10.3390/rs18040640 - 19 Feb 2026

Viewed by 688

Abstract

Environmental degradation in Iraq is a critical issue that requires strong monitoring. One indication of land degradation is a decrease in or loss of vegetation cover. This study examines changes in vegetation and productivity in the Thi-Qar region from 2001 to 2022, using [...] Read more.

Environmental degradation in Iraq is a critical issue that requires strong monitoring. One indication of land degradation is a decrease in or loss of vegetation cover. This study examines changes in vegetation and productivity in the Thi-Qar region from 2001 to 2022, using the normalized difference vegetation index (NDVI) and net primary production (NPP), and their response to climatic and hydrological factors. To address the gap in assessments that simultaneously quantify the influence of streamflow, rainfall, and temperature across distinct land cover classes in arid and semi-arid regions, we developed a replicable multi-source geospatial framework. We used MODIS data within the Google Earth Engine platform to perform spatiotemporal analysis. We applied models to detect NDVI trends on a pixel-by-pixel basis. This study provides the first integrated, data-driven assessment of vegetation sensitivity to streamflow versus climate in the Thi-Qar Governorate using a harmonized multi-source dataset. This combines the FAO WaPOR NPP dataset with hydrological (streamflow) and climatic (CHIRPS rainfall, MODIS LST) variables within an analytical workflow to extract anthropogenic water management from climatic drivers. The results showed variations in the NDVI and productivity in the southern and southwestern regions, indicating areas of both degradation and improvement. The analysis found that 12% of the study area showed improvement, while 56.5% of the area showed degradation. Additionally, we classified the study area as either vegetation (cropland) or non-vegetation (fallow arable land, bare areas, and sand dunes). A multiple regression model was then applied to these categories to examine the relationships between streamflow, precipitation, land surface temperature (LST), and the NDVI. The multiple regression for the entire region showed that these factors explained 45.1% of NDVI variation, with streamflow being the most significant positive driver (p < 0.001). The result showed that the NDVI in cropland and arable land was strongly positively correlated with both precipitation and streamflow (R = 0.78, R = 0.75). In contrast, bare land and dunes showed weaker relationships (R = 0.26 and 0.51, respectively). Of these factors, streamflow had the most significant influence in explaining vegetation change (partial correlation p = 0.53), indicating the importance of human management in addition to climate. Full article

► Show Figures

Figure 1

25 pages, 7450 KB

Open AccessArticle

Estimation of Topsoil Moisture on Bare Agricultural Soils at the Intra-Plot Spatial Scale Using a Statistical Algorithm and X- and C-Bands SAR Satellite Data

by Remy Fieuzal and Frédéric Baup

Remote Sens. 2026, 18(4), 639; https://doi.org/10.3390/rs18040639 - 19 Feb 2026

Viewed by 447

Abstract

Accurate estimation of topsoil moisture (TSM) is essential for optimizing agricultural practices, particularly in the context of precision farming. This study evaluates the use of high-resolution synthetic aperture radar (SAR) imagery from TerraSAR-X (X-band) and Radarsat-2 (C-band) for estimating TSM over bare agricultural [...] Read more.

Accurate estimation of topsoil moisture (TSM) is essential for optimizing agricultural practices, particularly in the context of precision farming. This study evaluates the use of high-resolution synthetic aperture radar (SAR) imagery from TerraSAR-X (X-band) and Radarsat-2 (C-band) for estimating TSM over bare agricultural soils, at both plot and intra-plot spatial scales. The experiment was conducted over a 420 km² area in southwest France, comprising 29 agricultural plots with varying topography, soil texture, and land management practices. Extensive in situ measurements of TSM, soil texture, and surface roughness were collected over multiple dates. A random forest regression model was developed to estimate soil moisture, using radar backscatter coefficients, incidence angles, soil texture components (clay, silt, sand), and roughness parameters (Hrms, correlation length) as input features. The modeling approach was applied at multiple spatial scales by extracting satellite signals within circular buffers of varying radius (5 to 30 m), as well as at the plot scale. Results indicate that estimation performance improves with increasing buffer size, with the best results achieved at the 30 m intra-plot scale (R² > 0.8, RMSE < 4 m³·m⁻³), outperforming plot-scale estimates. Both C-band and X-band data provided reliable results, with a slight advantage when combining data from multiple incidence angles. The inclusion of surface roughness and soil texture significantly improved model accuracy, underlining the importance of accounting for local soil properties in radar-based moisture retrieval. The intra-plot variability of TSM was found to be substantial, often exceeding inter-plot differences, highlighting the necessity for high spatial resolution in moisture monitoring. This study demonstrates the value of combining ground observations with multi-frequency SAR data and machine learning for high-resolution soil moisture mapping. The approach supports more precise water management strategies and contributes to sustainable agricultural development through informed decision-making. Full article

(This article belongs to the Special Issue Remote Sensing for Soil Moisture and Vegetation Parameters Retrieval (Second Edition))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 4 (February-2 2026) – 134 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI