Remote Sensing

19 pages, 4739 KB

Open AccessArticle

Retrieval of Significant Wave Height in Coastal Seas of China from GaoFen-3 Satellites Based on Deep Learning

by Fengjia Sun, Xing Li, Xiao-Ming Li, Yongzheng Ren and Ke Wu

Remote Sens. 2026, 18(6), 966; https://doi.org/10.3390/rs18060966 - 23 Mar 2026

Viewed by 417

The acquisition of significant wave height (SWH) in coastal seas is significantly important to human activities. The Gaofen-3 (GF-3) satellites, comprising GF-3, GF-3B and GF-3C, are independently developed operational SAR of China, capable of providing high-precision, high-resolution, multi-polarization coastal ocean wave observations. In [...] Read more.

The acquisition of significant wave height (SWH) in coastal seas is significantly important to human activities. The Gaofen-3 (GF-3) satellites, comprising GF-3, GF-3B and GF-3C, are independently developed operational SAR of China, capable of providing high-precision, high-resolution, multi-polarization coastal ocean wave observations. In order to obtain SWH in coastal seas, the retrieval of SWH using Quad-Polarization Stripmap (QPS) mode data from GF-3 satellites based on the deep learning method is implemented in this study. Furthermore, to obtain more SWH data, the polarization ratio model was applied to the Fine Stripmap (FS) mode data and Ultra Fine Stripmap (UFS) mode data to extend the model application. Comparisons with ECMWF Reanalysis v5 (ERA5) wave heights show that the QPS mode SWH retrieval achieves a root mean square error (RMSE) of 0.33 m. For the FS mode, the RMSE is 0.44 m (vs. ERA5) and 0.52 m (vs. altimeter). For the UFS mode, the RMSE is 0.39 m (vs. ERA5). Evaluation results indicate the feasibility of the proposed method for coastal SWH retrieval. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Ocean Observation—4th Edition)

► Show Figures

Figure 1

28 pages, 22901 KB

Open AccessArticle

IAMS (Interior-Anchored Mean-Shift) Algorithm for Supervoxel Segmentation of Airborne LiDAR Roof Points

by Hanyu Zhou, Liang Zhang, Zhiyue Zhang, Haiqiong Yang, Xiongfei Tang, Hongchao Ma and Chunjing Yao

Remote Sens. 2026, 18(6), 965; https://doi.org/10.3390/rs18060965 - 23 Mar 2026

Viewed by 326

Abstract

Accurate building roof classification from airborne LiDAR point clouds is fundamental to reliable three-dimensional (3D) urban reconstruction. While supervoxel-based methods offer efficiency and resilience to uneven point density, their performance is critically undermined by cross-boundary segmentation errors—a direct consequence of random seed initialization [...] Read more.

Accurate building roof classification from airborne LiDAR point clouds is fundamental to reliable three-dimensional (3D) urban reconstruction. While supervoxel-based methods offer efficiency and resilience to uneven point density, their performance is critically undermined by cross-boundary segmentation errors—a direct consequence of random seed initialization that merges geometrically similar yet semantically distinct objects. To address this root cause, this study proposes Interior-Anchored Mean-Shift (IAMS), a novel supervoxel segmentation framework that rethinks seed placement as a geometry-aware interior localization problem. By integrating local geometric consistency point density, and spatial correlation into a unified kernel density estimator, supplemented by density-adaptive voxel weighting and a semi-variogram-driven bandwidth, IAMS reliably anchors seeds within object interiors, yielding highly homogeneous supervoxels without post-processing. Extensive experiments on three diverse airborne LiDAR datasets demonstrated that IAMS consistently outperformed state-of-the-art baselines. On the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen benchmark, our approach improved roof classification completeness, correctness, and quality by up to 7.1% (per-object) over the conventional Voxel Cloud Connectivity Segmentation (VCCS) algorithm while being significantly faster than recent boundary-preserving alternatives. Critically, IAMS maintains robust performance under challenging conditions, including sparse sampling and dense vegetation occlusion, making it a practical solution for real-world urban remote sensing. Full article

(This article belongs to the Section Urban Remote Sensing)

► Show Figures

Figure 1

20 pages, 8955 KB

Open AccessArticle

Language-Guided Contrastive Learning and Difference Enhancement for Semantic Change Detection in Remote Sensing Images

by Yongli Hu, Lintian Ren, Huajie Jiang, Kan Guo, Tengfei Liu, Junbin Gao, Yanfeng Sun and Baocai Yin

Remote Sens. 2026, 18(6), 964; https://doi.org/10.3390/rs18060964 - 23 Mar 2026

Viewed by 487

Abstract

Semantic change detection (SCD) in remote sensing images aims not only to localize changed regions but also to identify their specific “from–to” semantic transitions. This task remains challenging due to the inherent semantic ambiguity of spectral changes and the presence of pseudo-change noise. [...] Read more.

Semantic change detection (SCD) in remote sensing images aims not only to localize changed regions but also to identify their specific “from–to” semantic transitions. This task remains challenging due to the inherent semantic ambiguity of spectral changes and the presence of pseudo-change noise. While recent vision–language models have shown promise in remote sensing, existing approaches like RemoteCLIP predominantly focus on static scene classification, lacking the ability to explicitly model dynamic temporal transitions. Other adaptations of foundation models (e.g., AdaptVFMs-RSCD) often rely on heavy backbones, incurring prohibitive computational costs. To address these limitations, this paper proposes LGDENet, a lightweight, end-to-end framework that unifies Language-Guided Temporal Contrastive Learning with a noise-robust difference enhancement mechanism. Specifically, we construct a temporal transition prompt learning strategy that aligns visual difference features with textual descriptions of dynamic processes, thereby resolving directional semantic ambiguities. Furthermore, we introduce a Difference Enhancement Module (DEM) that leverages the channel–spatial decoupling property of depthwise separable convolutions to adaptively isolate and suppress irrelevant variations (e.g., registration errors) before feature fusion. Experiments on the SECOND and Landsat-SCD datasets demonstrate that LGDENet achieves state-of-the-art performance, yielding a semantic F1 score (

F_{s c d}

) of 87.90% and 88.71%, respectively. Moreover, with a modest parameter count of 33.45 M, it offers a superior trade-off between accuracy and efficiency compared to heavy foundation model-based approaches. Full article

► Show Figures

Figure 1

22 pages, 6238 KB

Open AccessArticle

Fusion-Based Regional ZTD Modeling Using ERA5 and GNSS via Residual Correction Kriging

by Yang Cai, Hongyang Ma, Zhiliang Wang, Shuaishuai Jia, Xin Duan, Ge Shi and Chuang Chen

Remote Sens. 2026, 18(6), 963; https://doi.org/10.3390/rs18060963 - 23 Mar 2026

Viewed by 460

Abstract

Zenith Tropospheric Delay (ZTD) and its associated atmospheric water vapor information constitute essential environmental variables for Earth observation (EO)-based atmospheric monitoring and environmental variable retrieval. High-quality ZTD products are therefore of great importance for the post-processing, refinement, and reconstruction of atmospheric environmental variables [...] Read more.

Zenith Tropospheric Delay (ZTD) and its associated atmospheric water vapor information constitute essential environmental variables for Earth observation (EO)-based atmospheric monitoring and environmental variable retrieval. High-quality ZTD products are therefore of great importance for the post-processing, refinement, and reconstruction of atmospheric environmental variables at regional scales. Among existing observation techniques, Global Navigation Satellite System (GNSS) measurements provide high-precision ZTD estimates and have become an important means for retrieving tropospheric delay and water vapor. However, the sparse and uneven spatial distribution of GNSS stations limits their direct applicability for continuous environmental monitoring. Reanalysis-based products, such as ERA5 provided by the European Centre for Medium-Range Weather Forecasts (ECMWF), offer EO big data with excellent spatiotemporal continuity but suffer from pronounced systematic biases compared to precision GNSS retrievals, restricting their direct use in high-accuracy regional applications. To address these limitations, this study proposes a Residual Correction Kriging method for ZTD (RK ZTD) that integrates GNSS ZTD and ERA5 ZTD grids through a multi-source data fusion framework. High-precision GNSS ZTD is treated as reference data, and the differences between GNSS ZTD and ERA5 ZTD at modeling stations are defined as residuals to characterize the systematic bias in ERA5 ZTD grids. A Kriging interpolation algorithm is then employed to model the spatial distribution of these residuals and generate residual correction grids. By superimposing the interpolated residual grids onto the ERA5 ZTD grids, a refined and high-precision regional ZTD product is reconstructed. Experiments were conducted using observations collected in 2023 from 36 GNSS stations in the Netherlands, including 10 modeling stations and 26 independent validation stations, together with concurrent ERA5-derived ZTD grids. The results demonstrate that the proposed RK ZTD model provides spatially robust and high-precision ZTD products across the study region. The RK ZTD achieves a Root Mean Square Error (RMSE) of 5.70 mm, representing improvements of 58.4% and 35.4% compared with the original ERA5 ZTD (13.69 mm) and the GNSS-Kriging ZTD (8.82 mm), respectively. Moreover, the absolute bias is reduced to 0.41 mm, in contrast to 5.15 mm for the ERA5 ZTD, indicating that systematic biases are effectively mitigated. Spatial and seasonal analyses further confirm that the proposed method maintains stable performance across all seasons and significantly alleviates interpolation inaccuracies caused by sparse GNSS stations, even under extreme weather conditions such as Storm Ciarán, proving its value for advanced Earth environmental science applications. 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

30 pages, 2362 KB

Open AccessArticle

SGCAD: A SAR-Guided Confidence-Gated Distillation Framework of Optical and SAR Images for Water-Enhanced Land-Cover Semantic Segmentation

by Junjie Ma, Zhiyi Wang, Yanyi Yuan and Fengming Hu

Remote Sens. 2026, 18(6), 962; https://doi.org/10.3390/rs18060962 - 23 Mar 2026

Viewed by 451

Abstract

Multimodal fusion of synthetic aperture radar (SAR) and optical imagery is widely used in Earth observation for applications such as land-cover mapping and surface-water mapping (including post-event flood mapping under near-synchronous acquisitions) and land-use inventory. Optical images provide rich spectral and texture cues, [...] Read more.

Multimodal fusion of synthetic aperture radar (SAR) and optical imagery is widely used in Earth observation for applications such as land-cover mapping and surface-water mapping (including post-event flood mapping under near-synchronous acquisitions) and land-use inventory. Optical images provide rich spectral and texture cues, whereas SAR offers all-weather structural information that is complementary but heterogeneous. In practice, this heterogeneity often introduces fusion conflicts in multi-class segmentation, causing critical categories such as water bodies to be under-optimized. To address this issue, this paper presents a SAR-guided class-aware knowledge distillation (SGCAD) method for multimodal semantic segmentation. First, a SAR-only HRNet is trained as a water-expert teacher to learn discriminative backscattering and boundary priors for water extraction. Second, a lightweight multimodal student model (LightMCANet) is optimized using a class-aware distillation strategy that transfers teacher knowledge only within high-confidence water regions, thereby suppressing noisy supervision and reducing interference to other classes. Third, a SAR edge guidance module (SEGM) is introduced in the decoder to enhance boundary continuity for slender structures such as water bodies and roads. Overall, SGCAD improves targeted category learning while maintaining stable performance across the remaining classes. Experiments on a self-built dataset from GF-1 optical and LuTan-1 SAR imagery demonstrate higher overall accuracy and more coherent water/road predictions than representative baselines. Future work will extend the proposed distillation scheme to additional categories and broader geographic scenes. Full article

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

► Show Figures

Figure 1

29 pages, 12904 KB

Open AccessArticle

Evaluating the Impact of Multi-Source Digital Elevation Model Quality on Archeological Predictive Modeling: An Integrated Framework Based on Machine Learning and SHAP-Based Interpretability Analysis

by Jia Yang, Jianghong Zhao, Pengcheng Hao, Aomeng Zhang, Xiaopeng Li, Ran Tu and Zhi Zhang

Remote Sens. 2026, 18(6), 961; https://doi.org/10.3390/rs18060961 - 23 Mar 2026

Viewed by 640

Abstract

Digital Elevation Models (DEMs) constitute a core data source for Archeological Predictive Modeling. However, how quality differences among multi-source DEM propagate through complex models and subsequently affect predictive accuracy and geographic interpretation remains insufficiently understood. This study aims to develop an integrated evaluation [...] Read more.

Digital Elevation Models (DEMs) constitute a core data source for Archeological Predictive Modeling. However, how quality differences among multi-source DEM propagate through complex models and subsequently affect predictive accuracy and geographic interpretation remains insufficiently understood. This study aims to develop an integrated evaluation framework that combines machine learning with SHAP-based interpretability analysis to systematically compare the suitability of mainstream open access DEM products for archeological site prediction. The results indicate that (1) in terms of vertical accuracy, Copernicus DEM and TanDEM-X achieved the best performance, with RMSE values of 2.19 m and 2.31 m, respectively, whereas ASTER exhibited the lowest accuracy (RMSE = 6.44 m) and exaggerated terrain. (2) Regarding model performance, Copernicus DEM-driven models demonstrated the highest robustness, achieving an AUC of 0.966 under the XGBoost algorithm. (3) Interpretability analysis revealed that different DEM products significantly reallocate the importance of key variables such as slope and the Topographic Wetness Index, potentially distorting scientific interpretations of ancient military defensive site-selection patterns. Copernicus DEM is recommended as a priority data source. Moreover, while pursuing higher spatial resolution, equal attention must be paid to vertical accuracy and consistency with geomorphological logic. Full article

(This article belongs to the Special Issue GIS and RS for Spatial Documentation, Analysis and Interpretation in Multi-Scale Archaeological Applications)

► Show Figures

Figure 1

17 pages, 2223 KB

Open AccessArticle

Extending the KLIMA Radiative Transfer Model to Cloudy Atmospheres: Towards an All-Sky Analysis of FORUM

by Elisa Butali, Samuele Del Bianco, Ugo Cortesi, Gianluca Di Natale and Marco Ridolfi

Remote Sens. 2026, 18(6), 960; https://doi.org/10.3390/rs18060960 - 23 Mar 2026

Viewed by 365

Abstract

In recent times, increasing attention has been devoted to the investigation of atmospheric processes through remote sensing in order to improve our understanding of climate dynamics and atmospheric physics. This requires accurate simulation of the spectra emitted by the Earth, from which atmospheric [...] Read more.

In recent times, increasing attention has been devoted to the investigation of atmospheric processes through remote sensing in order to improve our understanding of climate dynamics and atmospheric physics. This requires accurate simulation of the spectra emitted by the Earth, from which atmospheric composition and thermodynamic conditions can be retrieved. The FORUM mission focuses on observations of the Earth’s outgoing radiation in the far-infrared spectral region, which has been only sparsely explored due to observational challenges, despite its significant contribution to the characterization of atmospheric processes. As part of the mission activities, dedicated simulations of the measurements expected from the FORUM instrument are required. Different models and codes can be employed for this purpose. Fast radiative transfer models, such as SIGMA-FORUM, efficiently simulate all-sky conditions, whereas detailed line-by-line models, such as KLIMA, have generally been limited to clear-sky applications. In this context, SIGMA-FORUM, an all-sky fast radiative transfer model operating in the 10–2760 cm⁻¹ spectral range and KLIMA, a FORTRAN-based line-by-line algorithm extensively validated under clear-sky conditions, are used to simulate FORUM radiances in both clear and cloudy atmospheres. This study extends the comparison between SIGMA-IASI/F2N and KLIMA to cloudy-sky scenarios by incorporating cloud optical properties into KLIMA using the same parametrization approach adopted in SIGMA-FORUM version 2.4. By combining complementary modeling approaches, this work enables KLIMA to simulate atmospheric radiances under all-sky conditions, thereby broadening its applicability. Full article

(This article belongs to the Special Issue Advances in Aerosol and Cloud Properties Observation in the Middle and Upper Layers Based on Remote Sensing (Second Edition))

► Show Figures

Figure 1

27 pages, 3395 KB

Open AccessArticle

Probabilistic Water Quality Monitoring Using Multi-Temporal Sentinel-2 Data: A Situational Awareness Framework for Harmful Algal Bloom Forecasting

by Muhammad Zaid Qamar, Cristiano Ciccarelli, Mohammed Ajaoud and Massimiliano Lega

Remote Sens. 2026, 18(6), 959; https://doi.org/10.3390/rs18060959 - 23 Mar 2026

Viewed by 584

Abstract

Environmental monitoring systems require robust uncertainty quantification for effective decision-making in complex ecological processes. Harmful algal blooms represent a critical challenge where prediction uncertainty directly impacts resource allocation and response timing, yet current remote sensing-based prediction systems provide only deterministic classifications without confidence [...] Read more.

Environmental monitoring systems require robust uncertainty quantification for effective decision-making in complex ecological processes. Harmful algal blooms represent a critical challenge where prediction uncertainty directly impacts resource allocation and response timing, yet current remote sensing-based prediction systems provide only deterministic classifications without confidence measures. This gap between algorithmic predictions and actionable risk assessment limits operational utility for stakeholders managing water quality under varying risk tolerances. This study developed a transferable probabilistic forecasting framework integrating Sentinel-2 multispectral imagery with quantile regression and ensemble machine learning to generate continuous confidence indicators for cyanobacteria density prediction, demonstrated through its application to Lake Okeechobee, Florida. The methodology combines spectral indices extracted from Sentinel-2 data with XGBoost for quantile regression at 0.05, 0.50, and 0.95 probability levels, and LightGBM for multi-horizon temporal forecasting. Sentinel-2’s 13 spectral bands spanning visible to shortwave infrared wavelengths, combined with its 5-day revisit frequency provide a spectrally rich and temporally dense input space that is well-suited to gradient boosting methods such as XGBoost, which can exploit complex nonlinear interactions among spectral features to distinguish cyanobacterial signatures from background water constituents. LightGBM achieved mean absolute percentage errors of 2.9% for 10-day forecasts and 5.7% for 20-day forecasts, outperforming conventional regression models. The framework generates 90% prediction intervals that enable reliable risk classifications for operational bloom management. This approach bridges the gap between satellite-based algal bloom detection and actionable decision-making by quantifying predictive uncertainty, representing a shift from binary classifications to probability-based environmental monitoring systems that accommodate varying stakeholder risk tolerances in water quality management applications. Full article

(This article belongs to the Special Issue Recent Advances in Remote Sensing Products for Water and Environment Monitoring)

► Show Figures

Figure 1

27 pages, 61924 KB

Open AccessArticle

Estimating Discharge Time Series in Data-Scarce Mountainous Areas Using Remote Sensing Inversion and Regionalization Methods

by Adilai Wufu, Shengtian Yang, Junqing Lei, Hezhen Lou and Alim Abbas

Remote Sens. 2026, 18(6), 958; https://doi.org/10.3390/rs18060958 - 23 Mar 2026

Viewed by 314

Abstract

The Tianshan–Pamir mountain region, serving as the core “water tower” for countries in Central Asia east of the Aral Sea, is a critical bulwark for sustaining downstream socioeconomic systems. However, constrained by complex topography and harsh climatic conditions, this region suffers from a [...] Read more.

The Tianshan–Pamir mountain region, serving as the core “water tower” for countries in Central Asia east of the Aral Sea, is a critical bulwark for sustaining downstream socioeconomic systems. However, constrained by complex topography and harsh climatic conditions, this region suffers from a severe scarcity of long-term, continuous hydrological observation data. This study focuses on a typical data-scarce mountainous area, coupling UAV and satellite imagery-based (e.g., Landsat/Sentinel) flow inversion with a hybrid spatial regionalization method—integrating spatial proximity, basin similarity, and regression-based hydrograph reconstruction—to quantitatively estimate long-term discharge time series. The results indicate that, for the validation of instantaneous discharge inversion, the Nash–Sutcliffe efficiency coefficient (NSE) at 29 river cross-sections was consistently greater than 0.80, with the coefficient of determination (R²) reached 0.94 (p < 0.01). Subsequently, for the long-term discharge series reconstructed using the regionalization method, the NSE values at three representative verification sites—each corresponding to a distinct basin type—were 0.88, 0.84, and 0.86, respectively. These findings exhibit higher precision compared to direct temporal upscaling, confirming the reliability of the regionalization method across varying temporal scales. An analysis of monthly discharge trends from 1989 to 2020 revealed a decreasing trend in the discharge of glacier-dominated rivers, with an average rate of change of −2.89 ± 2.54% (p < 0.05); the Pamir Plateau experienced the largest decline (−4.89 ± 6.58%), which is closely linked to large-scale glacial retreat within the basins. Conversely, the discharge of non-glacier-dominated rivers showed an increasing trend, with a multi-year average rate of change of +0.32 ± 8.43% (n.s.), primarily driven by shifts in precipitation and vegetation cover. This research introduces a new approach for hydrological monitoring in data-scarce regions and provides essential data and methodological support for water resource management decisions in arid zones. Full article

► Show Figures

Figure 1

20 pages, 7591 KB

Open AccessArticle

Research on Landslide Hazard Detection in Ya’an Region Based on an Improved YOLO Model

by Kewei Cui, Meng Huang, Weiling Zhang, Guang Yang, Yongxiong Huang, Zhengyi Wu, Zhiwei Zhai and Chao Cheng

Remote Sens. 2026, 18(6), 957; https://doi.org/10.3390/rs18060957 - 23 Mar 2026

Viewed by 546

Abstract

Landslide hazards occur frequently in the Ya’an region; therefore, accurately identifying and delineating potential landslide areas is crucial for disaster prevention and mitigation. Although deep learning-based detection methods using optical remote sensing imagery are widely adopted, the complex terrain and diverse land cover [...] Read more.

Landslide hazards occur frequently in the Ya’an region; therefore, accurately identifying and delineating potential landslide areas is crucial for disaster prevention and mitigation. Although deep learning-based detection methods using optical remote sensing imagery are widely adopted, the complex terrain and diverse land cover in this area often result in blurred boundaries and weakened textural features, making it difficult to precisely define spatial extents. To overcome these challenges, this study proposes an improved YOLOv11 model for landslide detection. Building on the YOLOv11 baseline, we designed a novel Multi-Scale Detail Enhancement module and integrated it into the neck network to effectively aggregate shallow-level details with deep-level semantic information, thereby enhancing the model’s ability to represent ambiguous boundaries. Additionally, we incorporated the lightweight SimAM attention mechanism into the backbone network. This mechanism dynamically suppresses background noise based on an energy minimization principle, improving feature discriminability within landslide regions and enabling precise boundary boxes. We conducted validation experiments in the Ya’an region using a custom dataset constructed from high-resolution UAV orthoimagery, comparing our method against mainstream models such as YOLOv8 and YOLOv10. The results show that the proposed improved YOLOv11 model achieves a precision of 90.2%, a recall of 84.8%, and an mAP of 92.7%. This enhanced performance demonstrates the model’s effectiveness in detecting landslides under complex terrain conditions, providing a practical technical reference for efficient hazard screening and dynamic monitoring. Full article

► Show Figures

Figure 1

25 pages, 10489 KB

Open AccessArticle

An Unsupervised Machine Learning-Based Approach for Combining Sentinel 1 and 2 to Assess the Severity of Fires over Large Areas Using a Google Earth Engine

by Ciro Giuseppe Riccardi, Nicodemo Abate and Rosa Lasaponara

Remote Sens. 2026, 18(6), 956; https://doi.org/10.3390/rs18060956 - 23 Mar 2026

Viewed by 809

Abstract

Wildfires represent a significant global environmental challenge, necessitating advanced monitoring and assessment techniques. This study explores the integration of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data within a Google Earth Engine (GEE) framework to enhance wildfire detection, burned area estimation, and [...] Read more.

Wildfires represent a significant global environmental challenge, necessitating advanced monitoring and assessment techniques. This study explores the integration of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data within a Google Earth Engine (GEE) framework to enhance wildfire detection, burned area estimation, and severity assessment. By leveraging SAR’s capability to penetrate atmospheric obstructions and optical data’s spectral sensitivity to vegetation changes, the proposed methodology addresses limitations of single-sensor approaches. The results demonstrate strong correlations between SAR-based indices, such as the Radar Vegetation Index (RVI) and Dual-Polarized SAR Vegetation Index (DPSVI), and traditional optical indices, including the Normalized Burn Ratio (NBR) and differenced NBR (ΔNBR). Despite challenges related to terrain influence, sensor resolution differences, and computational demands, the integration of multi-sensor data in a cloud-based environment offers a scalable and efficient solution for wildfire monitoring. During the peak of the fire events, significant atmospheric obstruction was technically verified using Sentinel-2 metadata and the QA60 cloud mask band, which confirmed persistent cloud cover and thick smoke plumes over the study areas. This interference limited the reliability of purely optical monitoring, further justifying the integration of SAR data. Future research should focus on refining data fusion techniques, incorporating additional datasets such as thermal infrared imagery and meteorological variables, and enhancing automation through artificial intelligence (AI). This study underscores the potential of remote sensing advancements in improving fire management strategies and global wildfire mitigation efforts. Full article

(This article belongs to the Special Issue Advances in Remote Sensing for Burned Area Mapping)

► Show Figures

Figure 1

25 pages, 72089 KB

Open AccessArticle

Soil Salinity Assessment and Cross-Regional Validation Based on Multiple Feature Optimization Methods and SHAP

by Shuaishuai Shi, Yu Wang, Jiawen Wang, Jibang Yang, Zijin Bai and Jie Peng

Remote Sens. 2026, 18(6), 955; https://doi.org/10.3390/rs18060955 - 23 Mar 2026

Viewed by 513

Abstract

Soil salinity severely threatens global ecosystems and agriculture, making accurate monitoring an ongoing priority. Currently, efficiently utilizing multi-source datasets to enhance monitoring accuracy while minimizing computational resources remains a critical challenge. This study evaluated several modeling strategies, including full-dataset modeling, variance inflation factor [...] Read more.

Soil salinity severely threatens global ecosystems and agriculture, making accurate monitoring an ongoing priority. Currently, efficiently utilizing multi-source datasets to enhance monitoring accuracy while minimizing computational resources remains a critical challenge. This study evaluated several modeling strategies, including full-dataset modeling, variance inflation factor (VIF), Boruta, particle swarm optimization, ant colony optimization and recursive feature elimination (RFE), and validated results across diverse regions (Almaty, Kazakhstan; Shandong, China). We further validated the results using multiple algorithms, including linear regression, partial least squares regression, extreme gradient boosting, k-nearest neighbor and random forest (RF), with topsoil (0–20 cm) electrical conductivity inverted via the optimal method. Results indicate that input feature numbers substantially impact model performance: regional-scale feature selection is indispensable, with RFE outperforming full-dataset modeling (R² improves by up to 0.28, while RMSE decreases by 2.21 dS m⁻¹) and VIF performing the worst. Transferability is also demonstrated in Almaty and Shandong. Additionally, the RF algorithm shows superior performance in soil salinity mapping (overall accuracy = 0.73; kappa coefficient = 0.65). And, the RFE and SHAP results highlight CRSI, BI, and MSAVI2 as particularly important predictors for estimating soil salinity in our study area. Collectively, this study highlights the critical importance of feature optimization and interpretability in soil attribute mapping through the integration of multi-source remote sensing data. Full article

(This article belongs to the Special Issue Environmental Monitoring Based on Remote Sensing, Earth Observation and Geoinformation)

► Show Figures

Figure 1

23 pages, 129074 KB

Open AccessArticle

High-Resolution Air Temperature Estimation Using the Full Landsat Spectral Range and Information-Based Machine Learning

by Daniel Eitan, Asher Holder, Zohar Yakhini and Alexandra Chudnovsky

Remote Sens. 2026, 18(6), 954; https://doi.org/10.3390/rs18060954 - 22 Mar 2026

Viewed by 495

Abstract

Accurate mapping of near-surface air temperature (

T_{air}

) at the fine spatial resolution is required for city-scale monitoring and remains a critical challenge in Earth Observation (EO). Reliance on ground-based measurements is constrained by their sparse spatial coverage and high operational [...] Read more.

Accurate mapping of near-surface air temperature (

T_{air}

) at the fine spatial resolution is required for city-scale monitoring and remains a critical challenge in Earth Observation (EO). Reliance on ground-based measurements is constrained by their sparse spatial coverage and high operational costs. We present a novel, scalable machine learning framework designed to overcome this limitation. Our method utilizes interpretable Convolutional Neural Networks (CNNs) to fuse high-resolution Landsat data, integrating both thermal and reflective spectral bands, with contextual spatiotemporal metadata. This approach allows for inference, at 30 m resolution, of

T_{air}

fields without relying on dense, localized ground monitoring networks. Our hybrid CNN architecture is optimized for spatial generalization, maintaining strong and transferable performance (station-wise

R^{2} \approx 0.88

) across diverse environments from humid coasts (

R^{2} \approx 0.89

) to arid interiors (

R^{2} \approx 0.84

). Although focused on a specific geographical region, our results suggest a robust and reproducible pathway for generating spatially consistent temperature fields from globally available EO archives, directly supporting urban heat island mitigation, climate policy development, and high-resolution public health assessment worldwide. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

20 pages, 39023 KB

Open AccessArticle

Lightweight Insulator Defect Detection in High-Resolution UAV Imagery via System-Level Co-Design

by Yujie Zhu, Guanhua Chen, Linghao Zhang, Jiajun Zhou, Junwei Kuang and Jiangxiong Zhu

Remote Sens. 2026, 18(6), 953; https://doi.org/10.3390/rs18060953 - 21 Mar 2026

Viewed by 466

Abstract

The inspection of minuscule insulator defects from high-resolution (HR) UAV imagery presents a significant algorithmic challenge. The severe scale mismatch between HR images and low-resolution model inputs often leads to feature distortion for sparsely distributed targets. To address these issues, this paper proposes [...] Read more.

The inspection of minuscule insulator defects from high-resolution (HR) UAV imagery presents a significant algorithmic challenge. The severe scale mismatch between HR images and low-resolution model inputs often leads to feature distortion for sparsely distributed targets. To address these issues, this paper proposes an integrated data–model collaborative framework. At the data level, an offline label-guided optimal tiling (LGOT) strategy is introduced to alleviate scale mismatch by curating information-dense training tiles. At the model level, we design the semi-decoupled prior-driven detection head (SDPD-Head), which leverages evolutionary priors to stabilize the learning of microscopic spatial features. During inference, an online inference-time adaptive tiling (ITAT) strategy is used to match the spatial scale distribution between training and inference and to reduce feature loss caused by direct downscaling. Experiments on a real-world inspection dataset show that the proposed framework achieves an mAP@50 of 92.9% with 2.17 M parameters and 4.7 GFLOPs. Full article

(This article belongs to the Special Issue Lightweight Artificial-Intelligence Techniques for Remote-Sensing Image Processing)

► Show Figures

Figure 1

35 pages, 21617 KB

Open AccessArticle

Nonlinear Impacts of Interannual Temperature and Precipitation Changes on Spring Phenology in China’s Provincial Capitals

by Zhengming Zhou, Shaodong Huang, Longhuan Wang, Yujie Li, Rui Li, Xinyang Zhang and Jia Wang

Remote Sens. 2026, 18(6), 952; https://doi.org/10.3390/rs18060952 - 21 Mar 2026

Viewed by 459

Abstract

Spring vegetation phenology is highly sensitive to climate change; however, climate drivers and their threshold responses at the urban scale remain insufficiently and systematically quantified. Focusing on 31 provincial capitals and municipalities in mainland China, this study integrated MODIS MCD12Q2-derived start-of-season (SOS) for [...] Read more.

Spring vegetation phenology is highly sensitive to climate change; however, climate drivers and their threshold responses at the urban scale remain insufficiently and systematically quantified. Focusing on 31 provincial capitals and municipalities in mainland China, this study integrated MODIS MCD12Q2-derived start-of-season (SOS) for spring green-up and TerraClimate climate data (2001–2023) at a 500 m grid resolution. SOS trends were characterized using the Mann–Kendall test and the Theil–Sen slope estimator. Building on these trend metrics, we developed an XGBoost–SHAP framework using the interannual rate of temperature change (tem_slope) and the interannual rate of precipitation change (pre_slope) as input features, to quantify the nonlinear contributions of climate-change rates to SOS trends and to identify key thresholds. Results indicate that the multi-year mean SOS across China’s provincial capitals and municipalities is primarily distributed between approximately DOY 74 and 138, exhibiting a clear spatial pattern of earlier green-up in the south, later green-up in the north, and delayed green-up on plateaus, with pronounced shifts in distribution centers and dispersion among climatic zones and cities. At the city level, the mean SOS trend shows an overall advancing rate of 0.81 d·year⁻¹ (i.e., the average of city-mean Sen slopes across the 31 cities). Pixel-level trend analyses show that advancing and delaying trends commonly coexist within most cities; among pixels with significant or marginally significant SOS trends identified by the Mann–Kendall test (MK p < 0.10) across all cities, advancing and delaying SOS pixels account for 75.02% and 24.98%, respectively. At the city scale, the proportions of advancing versus delaying pixels vary markedly among cities, forming directional structures characterized by advance-dominant, delay-dominant, or bidirectional coexistence patterns. SHAP dependence relationships further reveal that the effects of tem_slope and pre_slope on SOS trends are generally nonlinear and piecewise, with substantial heterogeneity across climate zones and cities. The identified tipping points and associated sensitive ranges collectively delineate spatially differentiated climate-sensitive intervals, which define the nonlinear response boundaries of spring SOS to sustained warming and precipitation changes. This study provides quantitative evidence for regional differences in urban spring phenological responses to climate change across major Chinese cities and offers a methodological reference for identifying actionable climate thresholds in urban greening design and climate-adaptive management. Full article

► Show Figures

Figure 1

25 pages, 45583 KB

Open AccessArticle

Terrain-Aware Self-Supervised Representation Learning for Tree Species Mapping in Mountainous Regions Under Limited Field Samples

by Li He, Leiguang Wang, Liang Hong, Qinling Dai, Wei Gu, Xingyue Du, Mingqi Yang, Juanjuan Liu and Yaoming Feng

Remote Sens. 2026, 18(6), 951; https://doi.org/10.3390/rs18060951 - 21 Mar 2026

Viewed by 345

Abstract

Accurate tree species mapping is critical for forest inventory, biodiversity assessment, and ecosystem management. In mountainous regions, terrain-induced radiometric non-stationarity and limited field access often produce scarce, clustered, and environmentally biased samples, limiting model generalization. To address this issue, this study proposes a [...] Read more.

Accurate tree species mapping is critical for forest inventory, biodiversity assessment, and ecosystem management. In mountainous regions, terrain-induced radiometric non-stationarity and limited field access often produce scarce, clustered, and environmentally biased samples, limiting model generalization. To address this issue, this study proposes a terrain-aware self-supervised representation learning framework for tree species classification under small-sample conditions. The framework integrates terrain information into representation learning and adopts a hybrid contrastive–generative self-supervised strategy to learn discriminative and terrain-robust features from large volumes of unlabeled multi-source remote sensing data. These learned representations are subsequently combined with limited field samples to produce regional-scale tree species maps. Experiments conducted across Yunnan Province, China, using Sentinel-1, Sentinel-2 and Landsat time-series data show that the proposed framework substantially improvesa class separability and classification robustness in complex mountainous environments. The framework achieves an overall accuracy of 75.8%, significantly outperforming conventional feature engineering (38.3–40.6%) and supervised deep learning models (37.3–47.8%). Species with relatively homogeneous structure and strong ecological niche dependence can be accurately mapped with limited training samples, whereas structurally complex forest communities require broader environmental sample coverage. Overall, the results highlight the potential of terrain-aware self-supervised representation learning as a scalable and data-efficient paradigm for forest mapping in mountainous and environmentally heterogeneous regions. Full article

► Show Figures

Figure 1

30 pages, 18176 KB

Open AccessArticle

CRECA-Net: Class Representation-Enhanced Class-Aware Network for Semantic Segmentation of High-Resolution Remote Sensing Images

by Ruolan Liu, Bingcai Chen, Lin Yu and Shaodong Zhang

Remote Sens. 2026, 18(6), 950; https://doi.org/10.3390/rs18060950 - 21 Mar 2026

Viewed by 346

Abstract

High-resolution remote sensing (RS) images exhibit complex backgrounds, large intra-class variability, and low inter-class differences, posing substantial challenges for semantic segmentation. Although existing class-level contextual modeling methods partially alleviate these issues, they often overlook the importance of accurate and discriminative class representations and [...] Read more.

High-resolution remote sensing (RS) images exhibit complex backgrounds, large intra-class variability, and low inter-class differences, posing substantial challenges for semantic segmentation. Although existing class-level contextual modeling methods partially alleviate these issues, they often overlook the importance of accurate and discriminative class representations and fail to effectively handle hard samples during training. To address these limitations, we propose CRECA-Net, a class representation-enhanced class-aware network designed from two complementary perspectives: class prototype refinement and difficulty-aware learning. Specifically, we introduce a class prototype refinement (CPR) module that improves class representations through pixel selection, confidence-aware contribution weighting, and an inter-class prototype separation loss, yielding more reliable and discriminative class centers. In addition, class-level context aggregation (CLCA) modules capture pixel-to-class prototype correlations via cross-attention to inject class-aware semantics into decoder features, thereby reducing interference from cluttered backgrounds and visually similar categories. Furthermore, a difficulty-aware (DA) loss dynamically estimates pixel-wise difficulty and redistributes the loss weights within each image, gradually shifting the learning focus from easy to hard samples while maintaining training stability. Extensive experiments on two benchmark RS segmentation datasets demonstrate that CRECA-Net consistently outperforms state-of-the-art methods across multiple evaluation metrics. Full article

► Show Figures

Figure 1

22 pages, 8074 KB

Open AccessArticle

High-Performance Parallel Direct Georeferencing for Massive ULS LiDAR Measurements

by Mei Yu, Yuhao Zhou, Hua Liu and Bo Liu

Remote Sens. 2026, 18(6), 949; https://doi.org/10.3390/rs18060949 - 20 Mar 2026

Viewed by 406

Abstract

The rapid increase in point density and acquisition rate of UAV laser scanning (ULS) systems has shifted the primary bottleneck of LiDAR workflows from data acquisition to post-processing, particularly during direct georeferencing of massive LiDAR measurements. This study presents a systematic evaluation of [...] Read more.

The rapid increase in point density and acquisition rate of UAV laser scanning (ULS) systems has shifted the primary bottleneck of LiDAR workflows from data acquisition to post-processing, particularly during direct georeferencing of massive LiDAR measurements. This study presents a systematic evaluation of parallel computing strategies for accelerating ULS direct georeferencing while preserving geodetic accuracy. Two georeferencing models are investigated: (1) a rigorous model that strictly follows the full geodetic transformation chain from sensor owned coordinates system (SOCS) to projected map coordinates, and (2) an approximate model that incorporates meridian convergence angle compensation and preprocessing of platform trajectories to reduce per-point computational complexity. For each model, a shared-memory multicore CPU implementation based on OpenMP and a heterogeneous GPU implementation based on CUDA are designed. Experiments were conducted on seven real-world ULS datasets, ranging from 2.9 × 10⁷ to 7.0 × 10⁸ points and covering diverse terrain types. Accuracy analysis shows that, in typical urban, plain, and industrial scenarios, the approximate model achieves millimeter-level mean errors and centimeter-level RMSEs relative to the rigorous model, satisfying the requirements of most engineering surveying applications. Performance evaluation demonstrates that parallelization yields substantial speedups: OpenMP-based method achieves 7–9 times acceleration, while GPU computing attains up to 24.6 times acceleration for the rigorous model and up to 16.7 times for the approximate model. The results highlight the complementary strengths of the two models and provide practical guidance for selecting accuracy-efficiency trade-offs in large-scale ULS production workflows. Full article

(This article belongs to the Special Issue Point Cloud Data Analysis and Applications)

► Show Figures

Figure 1

21 pages, 5652 KB

Open AccessArticle

Analysis of Generalization Performance of Tornado Detection Models: A Cross-Domain Evaluation from U.S. to Chinese Weather Radar Observations

by Biao Jiang, Shuai Zhang, Yubao Chen, Xuehua Li and Yancheng Wang

Remote Sens. 2026, 18(6), 948; https://doi.org/10.3390/rs18060948 - 20 Mar 2026

Viewed by 371

Abstract

Tornadoes pose severe threats, yet their low frequency in China creates a labeled data scarcity that hinders training robust detection models. Leveraging abundant U.S. data offers a solution, though cross-domain generalization remains challenging due to distinct climatic environments and heterogeneous radar systems. This [...] Read more.

Tornadoes pose severe threats, yet their low frequency in China creates a labeled data scarcity that hinders training robust detection models. Leveraging abundant U.S. data offers a solution, though cross-domain generalization remains challenging due to distinct climatic environments and heterogeneous radar systems. This study systematically evaluates the generalization capability of three representative models—TORP, TORP-XGB, and TDA-CNN—trained on the U.S. TorNet dataset and applied to Chinese CINRAD observations (2020–2024) via a zero-shot transfer strategy. The results indicate that while all models demonstrated robust performance in the source domain (with POD values of 0.75, 0.72, and 0.71 for TORP, TORP-XGB, and TDA-CNN, respectively), they experienced varying degrees of performance attenuation in the target domain (with POD values dropping to 0.56, 0.48, and 0.41, respectively). Notably, the TORP model exhibited superior robustness with minimal performance degradation. Further analysis primarily attributes this cross-domain degradation to three factors: disparities in radar systems, magnitude differences in tornado rotational features, and data quality issues. Crucially, sensitivity experiments confirm that linear feature enhancement substantially improves the detection rate and effectively mitigates the cross-domain performance gap, albeit at the cost of increased false alarms. These findings provide a reference for the cross-domain deployment of tornado identification models and future improvements in transfer learning strategies. Full article

(This article belongs to the Special Issue State-of-the-Art Remote Sensing in Precipitation and Thunderstorm)

► Show Figures

Figure 1

31 pages, 21235 KB

Open AccessArticle

Historical Mangrove Changes on Bangka Island Derived from Thirty Years of Landsat Data

by Suci Puspita Sari, Nico Koedam, Tom Van der Stocken and Frieke Van Coillie

Remote Sens. 2026, 18(6), 947; https://doi.org/10.3390/rs18060947 - 20 Mar 2026

Viewed by 574

Abstract

Bangka’s mangroves contribute to Indonesia’s species-rich coastal ecosystems, yet they have experienced substantial degradation, largely driven by human activities such as tin mining. Establishing long-term records of mangrove extent is essential for understanding distribution dynamics, assessing impacts, and guiding conservation strategies. In this [...] Read more.

Bangka’s mangroves contribute to Indonesia’s species-rich coastal ecosystems, yet they have experienced substantial degradation, largely driven by human activities such as tin mining. Establishing long-term records of mangrove extent is essential for understanding distribution dynamics, assessing impacts, and guiding conservation strategies. In this study, we applied change detection techniques, a random forest classifier, and the LandTrendr algorithm to analyze Landsat time-series data from 1994 to 2023 across Bangka Island. We quantified multi-decadal changes in mangrove extent, periods of disturbance and recovery, and discrepancies between local and global datasets. Mangrove dynamics were spatially heterogeneous, with both expansion and loss observed across regions in landward and seaward settings. Over the 30-year period, total gains reached 4956.39 ha (10.30% of the baseline), yet the net change indicated an overall loss of 1055.85 ha. LandTrendr analysis further revealed sustained mangrove expansion since 1989. Observed changes reflect the combined influence of natural processes, including accretion and erosion, and human pressures, particularly tin mining. Although net area loss aligns with national trends, the drivers in this mining-dominated region differ from those elsewhere, and some mangrove areas remain absent from global datasets. These findings emphasize the need to better capture local gain–loss dynamics to support effective management and conservation. Full article

(This article belongs to the Special Issue Remote Sensing in Mangroves (Fourth Edition))

► Show Figures

Figure 1

19 pages, 1890 KB

Open AccessArticle

PolSAR Forest Height Inversion Based on Multi-Class Feature Fusion

by Bing Zhang, Jinze Li, Jichao Zhang, Dongfeng Ren, Weidong Song, Jianjun Zhu and Cui Zhou

Remote Sens. 2026, 18(6), 946; https://doi.org/10.3390/rs18060946 - 20 Mar 2026

Viewed by 367

Abstract

Forest height is a key structural parameter for characterizing forest architecture and estimating carbon storage. However, under complex terrain and heterogeneous forest conditions, Polarimetric synthetic aperture radar (PolSAR)-based forest height inversion using multi-category features still faces several challenges, including feature redundancy, insufficient characterization [...] Read more.

Forest height is a key structural parameter for characterizing forest architecture and estimating carbon storage. However, under complex terrain and heterogeneous forest conditions, Polarimetric synthetic aperture radar (PolSAR)-based forest height inversion using multi-category features still faces several challenges, including feature redundancy, insufficient characterization of the nonlinear couplings among high-dimensional features by deep learning models, and the difficulty of jointly achieving model stability and interpretability. In this paper, to address these issues, we propose a method for SHapley Additive exPlanations (SHAP) interpretability-driven PolSAR forest height inversion based on deep learning and multi-category feature fusion. Firstly, a deep neural network (DNN) is constructed, and SHAP is introduced to interpret the model decision process, enabling the identification of key feature interactions with clear physical significance and guiding the iterative model optimization in an explainability-driven manner. Furthermore, a SHAP-guided feature attention DNN is developed, in which the feature contribution scores are incorporated as prior knowledge for attention weight initialization, thereby establishing a closed-loop modeling framework from “interpretation” to “optimization”. Experiments were conducted at the site of the Huangfengqiao forest farm, Youxian County, Hunan province, China, using ALOS-2 L-band fully polarimetric SAR imagery. The experimental results demonstrated that the proposed method can significantly outperform the conventional machine learning approaches and various deep learning architectures for forest height inversion. The final model achieved a coefficient of determination (R²) score of 0.75 and a root-mean-square error (RMSE) of 1.35 m on the test dataset. These findings indicate that the combination of SHAP-driven multi-category feature fusion and deep learning can effectively enhance both the inversion accuracy and physical interpretability, providing a reliable solution for PolSAR-based forest structural parameter retrieval at the Huangfengqiao study site, with potential applicability to complex terrain conditions. Full article

(This article belongs to the Special Issue Advances in Polarimetric and Interferometric Radar Remote Sensing: From Electromagnetic Scattering Characterization to Earth Observation Applications)

► Show Figures

Figure 1

26 pages, 20660 KB

Open AccessArticle

Sea Ice and Water Segmentation in SAR Imagery Based on Polarization Channel Interaction and Edge Selective Fusion

by Wei Song, Yixun Chen, Bin Liu, Mengying Ge, Yiji Zhou and Huifang Xu

Remote Sens. 2026, 18(6), 945; https://doi.org/10.3390/rs18060945 - 20 Mar 2026

Viewed by 439

Abstract

Sea ice segmentation based on Synthetic Aperture Radar (SAR) images has become an important technical means for polar climate change monitoring and navigation safety guarantee. However, the existing methods have limitations in the utilization of SAR polarization information and the modeling of local [...] Read more.

Sea ice segmentation based on Synthetic Aperture Radar (SAR) images has become an important technical means for polar climate change monitoring and navigation safety guarantee. However, the existing methods have limitations in the utilization of SAR polarization information and the modeling of local diversity details of sea ice, which leads to insufficient segmentation, especially in complex ice-water boundary regions. To address these issues, this paper proposes a novel Polarization-Fused Edge-Enhanced UNet (PFEE-UNet) designed specifically for sea ice segmentation from high-resolution SAR images. Specifically, we design the Cross-Polarization Channel Interaction (CPCI) module, which employs a dual interaction strategy of hierarchical inter-group cascading and symmetric cross-fusion. This approach effectively leverages the complementary features of the HH and HV polarization channels, significantly enhancing the distinction between sea ice and open water. Additionally, we present the Dense–Sparse Diversity Enhancement (DSDE) module, which combines a spatial-channel joint attention mechanism to strengthen the model’s ability to capture spatial relationships within complex ice–water structures, effectively alleviating misclassifications caused by abrupt local texture changes. Finally, we design the Selective Edge Fusion (SEF) module, which dynamically selects and integrates multi-level edge features, improving the continuity of sea ice boundaries and preserving its morphological integrity. The experimental results show that the proposed PFEE-UNet model outperforms mainstream segmentation methods on the AI4Arctic/ASIP sea ice dataset, achieving an average Intersection over Union (IoU) of 84.48%, which surpasses existing methods such as HRNet (82.52%) and DeepLabv3+ (82.40%). Additionally, PFEE-UNet was applied for end-to-end ice–water segmentation on real-world Sentinel-1 SAR scenes, demonstrating its effectiveness and robustness for practical sea ice monitoring. Full article

(This article belongs to the Special Issue Innovative Remote-Sensing Technologies for Sea Ice Observing)

► Show Figures

Figure 1

26 pages, 9198 KB

Open AccessArticle

Towards Pseudo-Labeling with Dynamic Thresholds for Cross-View Image Geolocalization

by Yuanyuan Yuan, Jianzhong Guo, Ruoxin Zhu, Ning Li, Ziwei Li and Weiran Luo

Remote Sens. 2026, 18(6), 944; https://doi.org/10.3390/rs18060944 - 20 Mar 2026

Viewed by 415

Abstract

Cross-view image geolocalization aims to achieve accurate localization of geo-tagged images without geo-tagging by matching ground-view images with satellite images. However, there are huge imaging differences between ground and satellite viewpoints, and existing methods usually rely on a large number of accurately labeled [...] Read more.

Cross-view image geolocalization aims to achieve accurate localization of geo-tagged images without geo-tagging by matching ground-view images with satellite images. However, there are huge imaging differences between ground and satellite viewpoints, and existing methods usually rely on a large number of accurately labeled cross-view image pairs. Therefore, to address issues such as significant perspective differences, high annotation costs, and low utilization of unpaired data, this paper proposes a cross-view generation model that integrates multi-scale contrastive learning and dynamic optimization, designs a multi-scale contrast loss function to strengthen the semantic consistency between the generated images and the target domain, adaptively balances the quality and quantity of pseudo-labels according to a dynamic threshold screening mechanism, and introduces a hard-sample triplet loss to enhance the model discriminative ability. Ablation experiments on the CVUSA and CVACT datasets show that the BEV-CycleGAN+CL (Bird’s-Eye View Cycle-Consistent Generative Adversarial Network with Contrastive Learning) model proposed in this paper significantly outperforms the comparative models in PSNR, SSIM, and RMSE metrics. Specifically, on the CVACT dataset, compared with the BEV-CycleGAN, BEV, and CycleGAN baselines, PSNR increased by 2.83%, 16.02%, and 42.30%, SSIM increased by 6.12%, 8.00%, and 18.48%, and RMSE decreased by 9.28%, 15.51%, and 25.35%, respectively. Similar advantages are observed on the CVUSA dataset. Compared with current state-of-the-art models, the dynamic threshold pseudo-label localization method in this paper demonstrates overall superiority in recall metrics such as R@1, R@5, R@10, and R@1%, for example achieving an R@1 of 98.94% on CVUSA, outperforming the best comparative model, Sample4G^†, which reached 98.68%. This study provides innovative methodological support for disaster emergency response, high-precision map construction for autonomous driving, military reconnaissance, and other applications. Full article

(This article belongs to the Special Issue Image Matching and Target Recognition Technologies: Prospects and Challenges)

► Show Figures

Figure 1

21 pages, 6097 KB

Open AccessArticle

HySIMU: An Open-Source Toolkit for Hyperspectral Remote Sensing Forward Modelling

by Fadhli Atarita and Alexander Braun

Remote Sens. 2026, 18(6), 943; https://doi.org/10.3390/rs18060943 - 20 Mar 2026

Viewed by 551

Abstract

Hyperspectral remote sensing (HRS) is gaining widespread adoption within the geoscience and Earth observation communities. It fosters diverse applications, including precision agriculture, soil science, mineral exploration, and carbon detection, to name a few. Recent technological advancements facilitated a growing number of satellite missions [...] Read more.

Hyperspectral remote sensing (HRS) is gaining widespread adoption within the geoscience and Earth observation communities. It fosters diverse applications, including precision agriculture, soil science, mineral exploration, and carbon detection, to name a few. Recent technological advancements facilitated a growing number of satellite missions as well as an increase in the availability of commercial sensors and platforms, such as drones. A significant challenge in deploying the varied platforms and sensors is the design and optimization of the hyperspectral surveys. Forward modelling simulators are valuable for optimizing mission parameters and estimating imaging performance. Limited accessibility of open-source simulators presents an obstacle for users who seek to benefit from such tools. To bridge this gap, HySIMU (Hyperspectral SIMUlator) was developed and described herein. It is an open-source, forward modelling toolkit that combines and integrates a primary processing pipeline with various open-source packages into a transparent and modular workflow. It offers a cost-effective approach to evaluating the performance of hyperspectral surveys. HySIMU is designed to simulate hyperspectral imagery based on user-defined targets, platforms, and sensor parameters. Features include (i) a ground truth data cube builder for customizable input parameters, (ii) a terrain-based solar and view geometry calculator for illumination modelling, (iii) integrated open-source radiative transfer models for incorporating atmospheric effects, and (iv) spatial resampling filters. In this manuscript, the initial framework for HySIMU is presented with some example applications, including two validation studies with real hyperspectral images. As remote sensing technologies advance, forward modelling toolkits such as HySIMU play a crucial role in refining mission designs and assessing survey feasibility. The scalability for arbitrary hyperspectral sensors, platforms, and spectral libraries ensures broad applicability. Of particular importance is support for parameter optimization for both scientific and commercial HRS campaigns. Full article

(This article belongs to the Special Issue Recent Advances in the Processing of Hyperspectral Images (Second Edition))

► Show Figures

Figure 1

29 pages, 886 KB

Open AccessReview

Estimating the Aboveground Biomass of Shrubland and Savanna Ecosystems Using High-Resolution Small UAV Systems: A Systematic Review

by Tracy L. Shane, Andrew Waaswa, Perry J. Williams, Matthew C. Reeves, Robert A. Washington-Allen and Barry L. Perryman

Remote Sens. 2026, 18(6), 942; https://doi.org/10.3390/rs18060942 - 20 Mar 2026

Viewed by 745

Abstract

Global biomass estimates suggest that plants hold 81% of the Earth’s 550 GT C, yet carbon stocks in non-forested and dryland ecosystems remain the largest source of uncertainty in the global carbon budget. Small uncrewed aerial vehicle (UAV) platforms are increasingly used to [...] Read more.

Global biomass estimates suggest that plants hold 81% of the Earth’s 550 GT C, yet carbon stocks in non-forested and dryland ecosystems remain the largest source of uncertainty in the global carbon budget. Small uncrewed aerial vehicle (UAV) platforms are increasingly used to estimate aboveground biomass at landscape scales. We conducted a systematic review of the remote sensing literature to determine: (1) which plant traits and related remote sensing indicators were used to develop aboveground biomass models; (2) statistical approaches; and (3) the key sources of uncertainty among these methods and models. We found that tundra, dryland, and savanna ecosystems were most underrepresented in the remote sensing literature. Within our systematic review process, we found no consistent UAV sensor combination, platform, or workflow that improved the accuracy and reduced the uncertainty in aboveground biomass estimates. Machine learning and regression models resulted in similar uncertainty levels in shrubland and savanna ecosystems. Expanding allometric equation development in shrublands and savanna ecosystems could reduce uncertainty and improve aboveground biomass estimation. Improved reporting on UAV logistics and workflows would further strengthen comparability. Standardized and validated UAV methods for estimating biomass, carbon stocks, and fuel loads will be essential for producing consistent datasets and enabling robust future meta-analyses. Full article

► Show Figures

Figure 1

25 pages, 6486 KB

Open AccessArticle

ECO-DEAU: An Ecologically Constrained Deep Learning Autoencoder for Sub-Pixel Land Cover Unmixing in Arid and Semi-Arid Regions

by Leixuan Zhou, Long Li, Dehui Li, Yong Bo, Hang Li, Kai Liu and Shudong Wang

Remote Sens. 2026, 18(6), 941; https://doi.org/10.3390/rs18060941 - 19 Mar 2026

Viewed by 359

Abstract

Arid and semi-arid regions are critical to terrestrial ecosystems and regional carbon cycle regulation, directly contributing to peak carbon and carbon neutrality goals. However, the fragmented landscapes in these regions pose significant challenges to conventional pixel-based classification, which often struggles with mixed pixel [...] Read more.

Arid and semi-arid regions are critical to terrestrial ecosystems and regional carbon cycle regulation, directly contributing to peak carbon and carbon neutrality goals. However, the fragmented landscapes in these regions pose significant challenges to conventional pixel-based classification, which often struggles with mixed pixel issues and lacks biophysical interpretability. To address these limitations, this study develops an Ecologically Constrained Deep Learning Autoencoder (ECO-DEAU) framework for sub-pixel land cover mapping by integrating biophysical constraints. Specifically, ECO-DEAU employs spectral indices to extract standard spectral signatures for five primary land cover types, which serve as initial weights to guide the autoencoder in estimating fractional abundances. The model was trained across ten representative landscape zones in the Inner Mongolia section of the Yellow River Basin and validated against high-resolution Gaofen-2 data. Results demonstrated that ECO-DEAU yielded an average

R^{2}

of 0.687, reaching a maximum

R^{2}

of 0.749 in spatially heterogeneous transition zones, representing a substantial improvement over the baseline unconstrained Deep Autoencoder (DEAU). By effectively resolving the blind source separation problem and improving decomposition accuracy, ECO-DEAU serves as a robust tool for addressing mixed pixel challenges in heterogeneous environments, thereby facilitating large-scale, high-resolution carbon sink monitoring. Full article

(This article belongs to the Special Issue Remote Sensing for Landscape Dynamics)

► Show Figures

Figure 1

25 pages, 7911 KB

Open AccessArticle

A High-Resolution Dataset for Arabica Coffee Distribution in Yunnan, Southwestern China

by Hongyu Shan, Tao Ye, Zhe Chen, Wenzhi Zhao, Xuehong Chen and Hao Sun

Remote Sens. 2026, 18(6), 940; https://doi.org/10.3390/rs18060940 - 19 Mar 2026

Viewed by 536

Abstract

Coffee, as a perennial commodity crop, plays a crucial role in global agricultural markets, regional livelihoods, and poverty alleviation. Yunnan Province of China (21°8′–29°15′N) represents the northernmost coffee-growing region worldwide, and its production has gained increasing attention in international markets. However, the absence [...] Read more.

Coffee, as a perennial commodity crop, plays a crucial role in global agricultural markets, regional livelihoods, and poverty alleviation. Yunnan Province of China (21°8′–29°15′N) represents the northernmost coffee-growing region worldwide, and its production has gained increasing attention in international markets. However, the absence of a spatially explicit and high-resolution coffee distribution dataset has constrained environmental assessment, land-use analysis, and policy-making in this subtropical and marginal growing region. In this study, we developed the first 10 m resolution Arabica coffee distribution dataset for Yunnan Province for the year 2023 using Sentinel-2 optical imagery and Shuttle Radar Topographic Mission (SRTM) terrain data within the Google Earth Engine (GEE) platform. An object-based workflow was implemented to generate spatially coherent mapping units, followed by supervised classification to identify coffee plantations. The resulting map achieved an overall accuracy (OA) of 0.87, with user accuracy (UA), producer accuracy (PA), and F1 score of 0.90, 0.96, and 0.93 for the coffee class, demonstrating its reliability for regional-scale applications. Feature contribution analysis indicates that shortwave infrared (SWIR) and red-edge information, particularly during the dry season, plays an important role in coffee discrimination. These results enhance confidence in the ecological relevance and stability of the mapping framework. The proposed workflow provides a practical and transferable approach for perennial crop mapping in complex mountainous environments. More importantly, the generated high-resolution coffee distribution dataset establishes a spatial baseline for monitoring land-use dynamics, assessing ecological impacts, and supporting sustainable coffee development in southwestern China. Full article

(This article belongs to the Special Issue AI-Driven Mapping Using Remote Sensing Data)

► Show Figures

Figure 1

18 pages, 1895 KB

Open AccessArticle

Multimodal Remote Sensing Image Clustering on Superpixel Manifolds

by Shujun Liu, Yuhong Yao and Luxi Xiao

Remote Sens. 2026, 18(6), 939; https://doi.org/10.3390/rs18060939 - 19 Mar 2026

Viewed by 418

Abstract

Despite offering rich complementary information, multimodal remote sensing images collected by diverse sensors increase the computational burden in clustering. To alleviate this issue, we devise an efficient multimodal clustering approach (MCSM) on superpixel manifolds formed by superpixel segmentation. The MCSM jointly learns cluster [...] Read more.

Despite offering rich complementary information, multimodal remote sensing images collected by diverse sensors increase the computational burden in clustering. To alleviate this issue, we devise an efficient multimodal clustering approach (MCSM) on superpixel manifolds formed by superpixel segmentation. The MCSM jointly learns cluster representation of all modalities and a consensus cluster membership graph that fuses the multimodal representation to yield clusters. To capture the local geometric structure of the superpixel manifolds, the optimization is constrained by manifold regularization of the consensus graph. In contrast to vanilla multiview subspace clustering techniques, the proposed approach does not rely on spectral clustering, and only involves element-wise product and multiplication on small-scale matrices. In addition, we prove that the MSCM is a special case of classic low-rank subspace clustering models, providing a perspective for understanding the learned cluster graphs. Extensive experiments are conducted on three popular multimodal remote sensing datasets, showing that the proposed method achieves competitive clustering performance compared to state-of-the-art methods, and significantly outperforms the latter in computational efficiency. Full article

► Show Figures

Figure 1

46 pages, 33541 KB

Open AccessArticle

AIFloodSense: A Global Aerial Imagery Dataset for Semantic Segmentation and Understanding of Flooded Environments

by Georgios Simantiris, Konstantinos Bacharidis, Apostolos Papanikolaou, Petros Giannakakis and Costas Panagiotakis

Remote Sens. 2026, 18(6), 938; https://doi.org/10.3390/rs18060938 - 19 Mar 2026

Cited by 1 | Viewed by 480

Abstract

Accurate flood detection is critical for disaster response, yet the scarcity of diverse annotated datasets hinders robust model development. Existing resources typically suffer from limited geographic scope and insufficient annotation granularity, restricting the generalization capabilities of computer vision methods. To bridge this gap, [...] Read more.

Accurate flood detection is critical for disaster response, yet the scarcity of diverse annotated datasets hinders robust model development. Existing resources typically suffer from limited geographic scope and insufficient annotation granularity, restricting the generalization capabilities of computer vision methods. To bridge this gap, we introduce AIFloodSense, a comprehensive evaluation benchmark designed to advance domain-generalized Artificial Intelligence for climate resilience. The dataset comprises 470 high-resolution aerial images capturing 230 distinct flood events across 64 countries and six continents. Unlike prior benchmarks, AIFloodSense ensures exceptional global diversity and temporal relevance (2022–2024), supporting three complementary tasks: (i) Image Classification, featuring novel sub-tasks for environment type, camera angle, and continent recognition; (ii) Semantic Segmentation, providing precise pixel-level masks for flood, sky, buildings, and background; and (iii) Visual Question Answering (VQA), enabling natural language reasoning for disaster assessment. We provide baseline benchmarks for all tasks using state-of-the-art architectures, demonstrating the dataset’s complexity and its utility in fostering robust AI tools for environmental monitoring. Crucially, we show that despite its compact size, AIFloodSense enables better generalization on external test sets than much larger alternatives, validating the premise that rigorous diversity is more effective than scale for training robust flood detection models, and is made publicly available to accelerate further research in the field. Full article

(This article belongs to the Special Issue Advanced Application of Artificial Intelligence and Machine Vision in Remote Sensing (Fourth Edition))

► Show Figures

Figure 1

41 pages, 14137 KB

Open AccessArticle

Hierarchical Extraction and Multi-Feature Optimization of Complex Crop Planting Structures in the Hetao Irrigation District Based on Multi-Source Remote Sensing Data

by Shan Yu, Rong Li, Wala Du, Lide Su, Buqi Na and Liangliang Yu

Remote Sens. 2026, 18(6), 937; https://doi.org/10.3390/rs18060937 - 19 Mar 2026

Viewed by 421

Abstract

Accurate extraction of crop planting structures is important for crop area and yield estimation, but complex and fragmented cropping patterns with overlapping phenology in the Hetao Irrigation District hinder reliable crop discrimination. This study proposes a hierarchical workflow that integrates vegetation masking with [...] Read more.

Accurate extraction of crop planting structures is important for crop area and yield estimation, but complex and fragmented cropping patterns with overlapping phenology in the Hetao Irrigation District hinder reliable crop discrimination. This study proposes a hierarchical workflow that integrates vegetation masking with multi-source feature optimization for crop mapping. First, dual-temporal Sentinel-2 imagery (May and August) is used to generate a vegetation region-of-interest(ROI) mask via Otsu thresholding applied to the Normalized Difference Vegetation Index (NDVI), combined with pixel-wise maximum-value fusion to reduce phenology-driven omissions and background interference. Second, within the vegetation mask, Sentinel-2 spectral, vegetation-index, and texture features are combined with Sentinel-1 synthetic aperture radar (SAR) backscatter and SAR texture features to construct a multi-source feature set. Random Forest(RF) feature-importance ranking is used to select an effective feature subset, and four classifiers (RF, support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and convolutional neural network (CNN)) are compared under the same training/validation setting. The vegetation extraction achieves an overall accuracy of 91% (Kappa = 0.80). Using Sentinel-2 features only, the optimized subset with CNN attains the best performance (overall accuracy = 95%, Kappa = 0.93). Adding Sentinel-1 SAR texture features provides an additional improvement (overall accuracy = 96%, Kappa = 0.94), particularly for classes prone to confusion in fragmented plots. Area proportions derived from the final map are consistent with statistical yearbook data (percentage errors: maize 3.45%, sunflower 2.66%, wheat 0.11%, tomato 0.92%) under the study conditions. This workflow supports practical crop-structure monitoring in complex irrigation districts. Full article

(This article belongs to the Special Issue Applications of Multi-Scale Remote Sensing and Machine Learning to Study Agriculture and Agriculture Water Management)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 6 (March-2 2026) – 124 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI