Search Results (728)

Oil and gas pipelines are crucial component of the strategic infrastructure in China, but they are severely threatened by geological disasters in complex terrains. These disasters may cause pipeline rupture, leakage or explosion, resulting in significant economic losses, environmental pollution and casualties. Traditional manual disaster investigation is inefficient because the pipelines are widely distributed, access is limited and the terrain may be rugged. Therefore, efficient and accurate disaster identification and risk assessment have become a priority that the industry urgently needs to address. Taking the Jiangxi section of the West Line II Zhangshu–Xiangtan connection line as the research area, this study combines the SBAS-InSAR technology with spatial analysis based on GIS to support early disaster identification, surface deformation monitoring and vulnerability assessment. The analysis of 48 Sentinel-1A satellite images shows that the regional ground deformation range is −19.5 to 19.1 mm per year, and most areas show a slow deformation of within ±10 mm per year. The preliminary visual interpretation of the SBAS-InSAR ground deformation data yields 121 preliminary high-deformation disaster points. Combined with the 9 key assessment factors in the GIS platform and the entropy-weighted information model obtained from the geological disaster susceptibility evaluation map and using the optical remote sensing images, 21 human interference points are excluded, and finally 100 potential geological disaster hazard areas are retained. Field verification was conducted through ground reconnaissance surveys and confirmed that 78 of these areas have geological disaster hazards such as landslide, collapses, and slope water damage, providing solid technical support for geological disaster management, monitoring and early warning along the pipeline route. This study proposes a multi-source integrated framework combining SBAS-InSAR, GIS-based susceptibility assessment, and optical validation for improving the reliability of early geological hazard identification. Full article

As a crucial grassland management practice, mowing plays a key role in maintaining the stability, productivity, and economic value of grassland ecosystems. The development of large-scale monitoring techniques for detecting whether mowing has occurred is of significant scientific and practical importance for improving the understanding of grassland ecosystem response mechanisms and optimizing management strategies. This study focuses on the concentrated grassland area of the Xilingol League in Inner Mongolia, restricted to the SAR-covered western sub-region. All classification accuracies reported here are obtained under spatially random train/test splits and represent an upper bound; generalization to geographically disjoint blocks remains unverified. By utilizing Sentinel-1, Sentinel-2, and Landsat-8 remote sensing images during the mowing season (August to September 2023) along with field survey data, we first applied the random forest-SHAP algorithm to select the optimal features from 70 texture features and construct a multimodal remote sensing dataset. Subsequently, we proposed the MAD-Net (Multi-Modal Attention Fusion Network with Dynamic Weighting) model to fully exploit information related to mowing identification from both optical and SAR data and conducted comparative analyses with other models. The results indicate that the CNN_LSTM_Attention model, which integrates convolutional neural networks, long short-term memory networks, and convolutional block attention modules, performed best in terms of capturing spatiotemporal variations in time series NDVI data. The U-Net model achieved the highest performance on the optimized texture dataset, while the MAD-Net model, which consists of three subnetworks that target different feature data, reached an identification accuracy of 92.59% in the SAR-covered western sub-region under a spatially random train/test split. This result represents an optimistic upper bound, as generalization to geographically independent blocks has not been evaluated. Ablation studies reveal that NDVI time series is the most informative single modality, while texture and SAR features provide complementary information; the proposed dynamic weighting module outperforms conventional fusion strategies. This study provides a new perspective for the large-scale binary classification of mown vs. non-mown grassland and effectively combines multimodal remote sensing data with deep learning models. Thus, this work not only offers a comparative basis for timely and effective identification of mowed grasslands but also provides insights for formulating optimized regional grassland management policies. Full article

Satellite-derived bathymetry (SDB) provides a cost-effective means for mapping shallow-water depths, yet its scalability and cross-regional generalizability remain challenging in optically complex coastal environments. This study systematically evaluates machine learning (ML) and deep learning (DL) approaches for transferable SDB over the 0–20 m depth range using multispectral Sentinel-2 imagery. A Random Forest model and four deep learning architectures–ResNet-50, ResNet-101, EfficientNet-B4, and ConvNeXt-Large–are developed and trained using data from Pratas Island (South China Sea) and selected reef regions of the Great Barrier Reef (GBR), and subsequently evaluated on spatially independent intra-regional and cross-regional test areas to assess generalization performance. Model sensitivity is investigated with respect to key training configurations, including loss-function design and data-splitting strategy. To enhance shallow-water learning, we introduce a Smooth Weight Function (SWF)-weighted RMSE loss that emphasizes near-surface depths and compare it with conventional RMSE and relative percentage error (RPE) objectives. In terms of training data, preserving spatial continuity during training substantially improves both numerical accuracy and structural consistency of predictions compared with random patch splitting. While the Random Forest model performs competitively in intra-regional tests, its accuracy degrades under cross-regional transfer (RMSE increasing from 1.53 m to 2.99–3.78 m). Deep learning models, although not always outperforming Random Forest in intra-regional settings, exhibit greater robustness to geographic shift. Using the spatially continuous training strategy, intra-regional RMSE ranges from 1.15 to 1.92 m over the full 0–20 m range, with shallow-water RMSE as low as 0.26 m for depths ≤ 3 m. Cross-regional transfer to geographically independent reefs yields moderate RMSE values of approximately 2.46–2.98 m (0–20 m range), indicating that geographic transfer remains challenging despite meaningful improvements over Random Forest. We further benchmark the proposed architectures against a task-specific bathymetry network using the public MagicBathyNet dataset. Under a unified 0–16 m shallow-water configuration using aerial RGB imagery, the proposed models achieve RMSE values between 0.19 and 0.22 m, outperforming both the baseline U-Net and the transformer-based bathymetry architecture while using substantially fewer parameters. In addition, we exploit multi-temporal repeat imagery for both training and inference, which increases training diversity and improves robustness to temporal variability arising from changing sun angles, atmospheric conditions, water properties, and tides. During inference, predictions from multiple repeat images are aggregated using the median to reduce noise and improve stability. Finally, we release optimized network architectures and pretrained weights to facilitate scalable application to new sites. This work demonstrates a practical pathway toward transferable, large-area SDB from multispectral satellite imagery using deep learning. Full article

Floods are among the most catastrophic natural disasters globally, causing significant damage to both life and infrastructure. Consequently, immediate and accurate assessment of inundated areas is critical for effective emergency response. While optical remote sensing is typically used for flood assessment, it is often ineffective during active flood events due to persistent cloud cover and precipitation. To address this, this research develops a deep learning method utilizing Synthetic Aperture Radar (SAR), which offers all-weather, 24 h imaging capabilities. Specifically, an attention-based differential Siamese U-Net was developed to detect temporal changes in bi-temporal SAR imagery (e.g., Sentinel-1) acquired before and after flood events. The method was evaluated on the S1GFloods dataset, comprising 5360 bi-temporal Sentinel-1 SAR image pairs across 46 flood incidents on six continents. Experimental results demonstrate a flood Intersection over Union (IoU) of 92.43%, an F1 score of 96.07%, and a recall of 97.64%. These metrics rank the proposed approach third overall among top-performing methods on this dataset. Notably, the high recall rate indicates the model is particularly beneficial for emergency response, as it minimizes the number of undetected flooded areas. Despite utilizing a CNN-based architecture that is less complex than Vision Transformer models, this method achieves results comparable to the state-of-the-art DAM-Net, with a performance difference of only 0.77%. Full article

Flood monitoring in dry tropical basins, such as the Tumbes River (Peru), faces critical challenges due to persistent cloud cover that restricts the operability of optical sensors during extreme events, coupled with the operational gap between satellite products and conventional hydrological monitoring. To overcome these limitations, this research developed a comprehensive methodological framework in Google Earth Engine that unifies automated image thresholding and Sentinel-1 SAR time series analysis for flood detection and the estimation of early warning thresholds. The Bmax Otsu and Edge Otsu algorithms were evaluated, previously calibrated using high-resolution imagery (PlanetScope) as reference data, topographically constrained by the HAND (Height Above the Nearest Drainage) model, and validated against established change detection algorithms. The analysis of seven hydrological events between 2017 and 2024 confirmed the statistical superiority of Bmax Otsu; although both methods achieved high overall accuracy (Bmax 95.8% versus Edge 95.7%), Bmax Otsu outperformed Edge Otsu in spatial consistency (Kappa 66.1% vs. 63.7%; IoU 45.6% vs. 45.0%). Based on this, a time series analysis was applied to discriminate permanent water bodies and isolate flood dynamics. Subsequently, the functional discharge–impact response was evaluated by linking the instantaneous flood extent captured by the SAR overpasses to their corresponding peak discharges. Validated against official INDECI damage reports, it was determined that significant impacts begin at an activation threshold of 743.49 m³/s (151 flooded ha, 157 affected inhabitants) and scale linearly up to extreme peak events of 1629.02 m³/s, compromising 1234 agricultural ha and 749 inhabitants. This methodology provides a validated, low-cost tool to translate SAR observations into critical thresholds for early warning systems in data-scarce regions. Full article

Net primary productivity (NPP) is an important indicator of ecosystem carbon accumulation capacity and vegetation productivity potential, and its accurate estimation is of great significance for agricultural management and regional carbon cycle research. To address the problem that the temporal continuity of single-source optical remote sensing data is easily affected by cloud cover, this study used Sentinel-2 imagery and the Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) product as data sources and constructed an NDVI time series with high spatial and temporal resolution for the study area based on the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) method. On this basis, the Simple Ratio (SR) index was incorporated to supplement canopy information, and the key parameters of the Carnegie–Ames–Stanford Approach (CASA) model were differentially optimized for different crop types, thereby enabling remote sensing-based estimation of crop NPP. The results showed that the fused NDVI effectively compensated for observation gaps caused by cloud interference, and its temporal variation was generally consistent with the crop growth process. In addition, the Fraction of Photosynthetically Active Radiation (FPAR) improved with the fused NDVI, which effectively characterized phenological differences among crops. Compared with the unoptimized model, the improved model significantly improved NPP estimation accuracy for both maize and rice. Specifically, for maize, the coefficient of determination ($R^2$) increased from 0.75 to 0.88, and the mean absolute percentage error (MAPE) decreased from 67.00% to 34.68%. For rice, the MAPE decreased from 78.51% to 23.43%, while the mean absolute error (MAE) decreased from 345.1 $\mathrm{gC}·{\mathrm{m}}^{-2}·{\mathrm{a}}^{-1}$ to 95.6 $\mathrm{gC}·{\mathrm{m}}^{-2}·{\mathrm{a}}^{-1}$. These results indicate that constructing a highly continuous vegetation index time series through spatiotemporal fusion, together with optimizing the CASA model by incorporating the SR index and crop-specific parameterization, can effectively improve the stability and accuracy of NPP estimation for agricultural crops. Full article

Accurate crop classification in complex and heterogeneous agricultural landscapes is often challenged by mixed-pixel effects and spatial autocorrelation. This study proposes a prior-guided crop classification framework that integrates accessible Moderate Resolution Imaging Spectroradiometer (MODIS) optical and Sentinel-1 synthetic aperture radar (SAR) time-series data with explicit phenological and structural priors. By embedding physically meaningful constraints into temporal feature learning, the model shifts from purely data-driven learning toward biophysically interpretable discrimination between crop types and background classes. Performance was rigorously evaluated using spatial cross-validation (SCV) to ensure geographic independence. Results demonstrate that the prior-guided CNN achieves an overall accuracy (OA) of 98.66% and a Kappa of 0.9832, outperforming unguided deep learning and conventional machine learning models. Notably, the framework exhibits high spatial robustness, with a minimal performance gap between random and spatial validation (ΔOA = 0.0049). In addition to improving classification accuracy, integrating phenological features with SAR-based prior information enhances the stability of non-crop categories in fragmented scenarios, while leveraging readily available medium-resolution data to support large-scale applications. These findings demonstrate that embedding physically meaningful prior knowledge into multi-source time-series learning improves classification accuracy while enhancing spatial generalizability and interpretability. More broadly, the proposed framework offers a transferable paradigm for integrating domain knowledge with deep learning, providing a practical and scalable solution for crop mapping in heterogeneous agricultural landscapes using widely accessible medium-resolution data. Full article

Alpine wetlands in the Qinghai Lake Basin, located on the northeastern Qinghai–Tibetan Plateau, are ecologically important but highly vulnerable to climate change and anthropogenic disturbance. Traditional field-based surveys are labor-intensive and spatially constrained, underscoring the need for automated remote sensing approaches for large-scale wetland mapping. In this study, an object-based image analysis (OBIA) framework was developed by integrating Sentinel-2 optical imagery with Sentinel-1 synthetic aperture radar (SAR) data to classify two representative plateau wetland types: marsh meadows and inland tidal flats. Seven categories of features were evaluated, including spectral features, vegetation indices, water indices, red-edge features, topographic variables, radar backscatter, and geometric-textural metrics. The Separability and Thresholds (SEaTH) algorithm was employed for feature selection and optimization prior to classification using a Random Forest model. The results indicate that the incorporating geometric and textural features significantly improved classification performance, achieving an overall accuracy (OA) of 82.53% and a Kappa coefficient of 0.74. Moreover, the SEaTH-based feature optimization scheme yielded the best performance, with an OA of 86.24% and a Kappa coefficient of 0.79. Compared with the full feature set, this approach improved producer’s accuracy by 3.96–6.11% and increased overall accuracy by 1.48%. The proposed framework provides an effective and computationally efficient approach for mapping ecologically fragile alpine wetlands and offers valuable support for wetland conservation in the Qinghai Lake Basin. Full article

Synthetic Aperture Radar (SAR) images offer significant advantages for monitoring the dynamics of water bodies in tropical regions, mainly due to their ability to acquire data under adverse weather conditions, which frequently limit optical sensors. However, the automated classification of water bodies using SAR data still faces methodological challenges, particularly regarding the selection of the most suitable parameters and polarizations. This study proposes a multitemporal classification methodology using Sentinel-1 data to map the flood regimes of lagoon complexes in the State of Rio de Janeiro (Brazil). The approach integrates SAR image time series with the Random Forest machine learning algorithm, evaluating the performance of different polarization configurations (VV, VH, and VV–VH). The results show that the combined use of single and cross polarizations (VV–VH) achieved excellent performance, with a Kappa index of 0.83, F-score of 0.90, and overall accuracy of 0.96, demonstrating methodological robustness. The multitemporal analysis identified approximately 294 km² of permanently flooded areas, while seasonally flooded areas, associated with the seasonal variation in coastal lagoons, exhibited variations exceeding 30 km² over the time series. Full article

The identification of potential landslides and targeted risk analysis is crucial for the warning and prevention of geological landslide disasters. This article presents a time series deformation prediction framework based on a Long Short-Term Memory (LSTM) network deep learning model for analyzing Interferometric Synthetic Aperture Radar (InSAR) data. By employing an advanced stacked LSTM network model, we effectively capture temporal dependencies and move beyond traditional methods that depend on explicit deformation. This approach enables short- to medium-term deformation prediction through structured time dynamic modeling, identifies potential landslide targets in the high-altitude regions upstream of Lake Sarez, and classifies associated risk levels. The results indicate that: (1) In short-term forecasting, the stacked LSTM model effectively captures trend turning points, producing stable and reliable predictions with a Mean Absolute Error (MAE) of 0.164 mm and a Root Mean Square Error (RMSE) of 0.194 mm; (2) From 2019 to 2022, regional surface deformation characteristics exhibited significant spatial heterogeneity, with the potential landslide on the right bank identified as the most critical settlement center, demonstrating a line of sight (LOS) deformation rate consistently exceeding 49 mm per year, while the Usoi Dam displayed relatively good stability during this period; (3) By integrating InSAR deformation rate maps with Sentinel-2 optical images, we identified a total of 72 potential landslide targets in the region, four of which exhibited deformation rates exceeding −30 mm per year, indicating significant activity and classifying them as high-risk areas requiring attention. This provides a targeted reference list for the prevention and control of geological landslides around Lake Sarez and establishes a reliable technical pathway for the early identification of landslides under complex geological conditions in high-altitude mountainous areas. Full article

The Ieodo plume is a distinctive suspended sediment plume near the Ieodo Ocean Research Station (I-ORS), located in the middle of the northern East China Sea. Because the Ieodo plume exhibits multiple different spatial scales, this study conducted an integrated remote sensing observation using satellites and unmanned aerial vehicles (UAVs) to observe its development and dispersion. Sentinel-2 and Geostationary Ocean Color Imager-II (GOCI-II) data were used to determine the plume’s spatial characteristics, broad-scale behavior, hourly variability, and turbidity characteristics. Also, TPXO model outputs were employed to evaluate the relationship between plume occurrence and tides, together with satellite imagery. Plume was repeatedly observed near the top of the Ieodo Seamount, with an affected extent of 11.4 ± 3.2 km in the east–west direction and 14.3 ± 4.1 km in the north–south direction. Moreover, hourly variations observed using GOCI-II showed that the Ieodo plume rotated clockwise with shifting tidal currents, forming a counterclockwise curved band or a ring-shaped structure. Total suspended solids (TSSs) in the plume reached their maximum when the southward component of the TPXO tidal current was dominant. Based on UAV optical surveys at the I-ORS, fine-scale morphology at the early stage of plume development was revealed, and it was confirmed that the Ieodo plume can occur even when it is not detected by satellite imagery. Furthermore, the u- and v-velocity vectors of the propagating Ieodo plume were derived by applying large-scale particle image velocimetry (LSPIV) to geometrically corrected sequential UAV imagery obtained in I-ORS. Plume speed was greatest near the source during the initial stage (0.81 ± 0.30 m s⁻¹) and gradually decreased to 0.34 ± 0.29 m s⁻¹ over distance. Based on the results above, we propose that the Ieodo plume is primarily generated by a pressure reduction associated with tidally accelerated currents over topography, driven by the Bernoulli effect. This study shows that an integrated satellite and UAV observation framework can effectively monitor rapidly evolving suspended sediment plumes. It can further help improve our understanding of dynamically driven submesoscale marine events. Full article

This study addresses the critical need for accurate, continuous monitoring of surface water quality parameters (SWQPs) using remote sensing, overcoming limitations in existing models that often rely on pre-trained networks ill-suited for complex aquatic environments. We present a customized convolutional neural network (CNN) architecture, implemented in the MATLAB environment, designed to simultaneously predict optically active (Total Organic Carbon, TOC) and non-optically active (Dissolved Oxygen, DO) parameters from eighteen Sentinel-2 Level-2A satellite images, acquired between 2023 and 2024. Our approach integrates spatial and spectral data through a customized CNN with three convolutional layers and two dense layers, optimized via adaptive learning strategies, data augmentation, and rigorous regularization to enhance predictive performance and prevent overfitting. The models were trained and validated on fused datasets of satellite imagery and in situ measurements, organized into comprehensive four-dimensional arrays capturing spectral, spatial, and sample dimensions. The results demonstrated high accuracy, with coefficient of determination (R²) values exceeding 0.97 and low root mean square error (RMSE) across training, validation, and testing subsets. Spatial prediction maps generated at high resolution revealed realistic ecological and hydrological patterns consistent with known regional water quality dynamics in New Brunswick. Our contribution, accessible to users with MATLAB, lies in the development of a transparent, adaptable, and reproducible CNN framework tailored for multiparameter water quality estimation, which extends beyond traditional empirical, site-specific regression models by enabling non-invasive, cost-effective, and continuous monitoring from satellite platforms over a large, heterogeneous province-scale domain. Additionally, model interpretability was enhanced through SHapley Additive exPlanations (SHAP) analysis, which identified key spectral bands influencing predictions and provided ecological insights, offering guidance for future sensor design and data reduction strategies. This study addresses a significant research gap by providing a dual-parameter focused, end-to-end deep learning solution optimized for province-scale remote sensing data, facilitating more informed environmental management. This study can support water managers and agencies by providing province-wide DO and TOC maps derived from freely available Sentinel-2 imagery, reducing reliance on sparse field sampling alone and helping to identify areas of low oxygen or high organic carbon. Future work will extend this framework temporally and spatially and explore hybrid CNN architectures incorporating temporal dependencies for improved generalization and accuracy. Full article

Monitoring the biophysical parameters of agricultural surfaces is a key issue for food security in the context of climate change. Since 2016, agricultural surfaces can be monitored from space at high spatial resolution (~10/30 m) in the microwave and optical domains owing to radiometer and SAR sensors onboard Sentinel-1, -2 and Landsat-8 satellites. This paper draws on multi-temporal acquisitions over a six-year period to analyze satellite time series for the main winter and summer crops (corn, sunflower, soybean, sorghum, rapeseed, wheat) grown in southwestern France and more widely cultivated around the world. From January 2016 to December 2021, satellite signals extracted at the field spatial scale offer a unique opportunity to monitor agricultural surfaces with a high temporal resolution (every 1 or 2 days) never achieved before thanks to the combination of multi-sensor and multi-orbit data. Analyses on the impact of the topography and satellites’ viewing angles showed that the NDVI values derived from Sentinel-2 and Landsat-8 are very close (r > 0.92) and can be merged to construct multi-annual time series. Angular sensitivity is much more pronounced for radar images; while it demonstrates a weaker cross-polarization and polarization ratio, it is greater for co-polarization. Optical and radar time series are modulated in time and amplitude depending on yearly climatic conditions and agricultural practices. The combined use of the ascending and descending orbits of the two Sentinel-1 satellites makes it possible to detect specific periods (harvest, flowering) for certain crops (wheat and sunflower). The long-term approach has enabled the modeling of satellite time series using double logistic functions with good performance (r > 0.92 on average), allowing the identification of interannual variations of crop development driven by climatic conditions and agricultural practices. Full article

The rapid development of remote sensing satellite technology has enabled remote sensing images to be widely used in agriculture, meteorology, environmental monitoring and other fields. However, the presence of clouds in these images can lead to blurred and incomplete observations of the Earth’s surface, limiting the quality and applicability of the data. Current cloud detection networks usually adopt a single encoder–decoder structure that uniformly processes all spectral features without distinguishing between various spectral bands. To overcome this limitation, this paper proposes an Optical characteristics-guided Asymmetric Dual Encoder Feature Fusion cloud detection algorithm (OADEF²). The algorithm adopts an asymmetric dual encoder framework to divide the spectral bands of Sentinel-2A into two groups: RGB visible light bands and infrared/atmospheric correction bands, which are subsequently input into two different encoder branches. This method utilizes the unique physical characteristics of different spectral bands to improve the accuracy of cloud detection. In order to direct the focus of the network to cloud-related optical characteristics, an Optical characteristics-guided Multi-Scale cloud feature module (OCGMSCFM) based on Dynamic HOT Index and Full-Band Cloud Index is introduced. This module effectively solves the problem of insufficient representation of cloud features. In order to improve the efficiency of feature fusion, a Feature Aggregation and Filtering module (FAFM) is proposed. This module uses aggregation and techniques to filter basic features, thereby improving the accuracy of cloud detection. In order to overcome the limitations of feature modeling, a dual attention module that fuses Multi-interaction Local Spatial Attention mixed Channel Attention (MILSAMCAM) is added to the decoder. The experimental results validated the effectiveness of this algorithm in cloud detection tasks, achieving an F1-score of 97.30% on the S2-CMC dataset. Full article

The latest advances in remote sensing play a central role in providing Earth observation (EO) data for numerous applications in the scope of reaching environmentally sustainable goals. However, over tropical rainforests, optical imaging is often hindered by extensive cloud coverage, which means that analysis-ready images are mostly restricted to the dry season. In this study, we propose combining radar features extracted from short time series of Sentinel-1 Interferometric Wide Swath (IW) data with a deep learning-based classification scheme to continuously monitor the state of forests. The proposed methodology is based on the joint use of SAR backscatter and interferometric coherences at different temporal baselines to perform pixel-wise classification of land cover classes of interest. However, we show that for a sequence of Sentinel-1 time series, different land cover classes exhibit particular seasonal-dependent variations. Another challenge in performing short-term predictions stems from the fact that ground truths are usually available only on a yearly basis. To address these challenges, we propose a seasonal sampling of the training data, masked by potential deforestation, along with a classification based on a modified U-Net model. The classification results show that overall accuracies above 90% can be achieved throughout the whole year with the proposed method, emerging as a potential tool for mapping rainforests with unprecedented temporal resolution. Full article