Search Results (1,438)

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

Using surface observations, ADTD lightning data, and radar reflectivity from April-September 2022–2024 in the Xi’an terminal area, this study classified severe convective events into four categories: ordinary thunderstorms, short-duration heavy precipitation, convective wind gust, and hail events. Their temporal variability, spatial distribution, life cycle characteristics, and propagation pathways were systematically analyzed. The results reveal significant differences among convective event types across multiple temporal and spatial scales. Convective wind gust events exhibited the strongest interannual variability, with a decrease of 44% from 2023 to 2024. Hail events occurred relatively infrequently, totaling only 16 cases from 2022 to 2024. Seasonally, convective wind gusts were concentrated in April-May, while ordinary thunderstorms and short-duration heavy precipitation events mainly occurred in July–August. Most events initiated during the afternoon and intensified toward evening, with short-duration heavy precipitation events showing a bimodal diurnal variation. Ordinary thunderstorms were dominated by short-lived events lasting 30–60 min, whereas heavy precipitation, convective wind gust, and hail events were primarily associated with long-lived convective systems exceeding 180 min. Spatially, severe convective weather generally initiated in the western part of the terminal area and propagated eastward. Lightning activity was more concentrated in the southeastern sector, indicating greater impacts on the SHX waypoint. Propagation paths were predominantly oriented toward the east-northeast. Full article

Stereo radargrammetry using Synthetic Aperture Radar (SAR) images is a powerful technique for all-weather 3D topographic measurements. However, conventional methods based on local template matching often struggle to establish accurate correspondences in mountainous or vegetated areas due to severe SAR-specific geometric modulations. In this paper, we propose a novel high-accuracy stereo radargrammetry framework by introducing RoMa, a robust Transformer-based deep learning model, for dense SAR image matching. Optical pre-trained deep learning models often suffer from a domain gap. To overcome this limitation, we develop an automated pipeline to construct a patch-based SAR image dataset using a reference Digital Surface Model (DSM) and an SAR projection model. By fine-tuning RoMa on this dataset, the model effectively adapts to the complex non-linear deformations of SAR images. Furthermore, unlike conventional methods, our approach establishes correspondences directly on the original slant-range images without requiring ground-range projection, thereby avoiding image quality degradation caused by pixel interpolation. Experimental results using airborne Pi-SAR2 images demonstrate that the fine-tuned RoMa significantly outperforms conventional methods, achieving an 82.86% matching accuracy at a 10-pixel threshold. In the 3D measurement evaluation, the proposed method achieves the lowest elevation mean error ($-1.24$ m) and the highest inlier ratio (74.1%), proving its effectiveness in generating accurate, dense, and wide-area 3D point clouds even in challenging terrains. Full article

Polarimetric Synthetic Aperture Radar (PolSAR) has significant advantages for land-cover classification for its all-weather, day-and-night, and multi-polarization observation capability. Traditional methods often exhibit limited classification accuracy in regions with strong noise and complex textures. Although deep learning methods can improve classification performance, they usually suffer from high model complexity, while lightweight models often show insufficient spatial consistency. To address these issues, this study proposes a PolSAR land-cover classification framework that integrates a Lightweight Dynamic Sequential Axial Network (LiteDSANet) with a polarization feature-guided Dense Conditional Random Field (PFG-DenseCRF). LiteDSANet is employed to generate the initial class probability map, and PFG-DenseCRF optimizes the classification results by introducing polarimetric features. Experiments were conducted on AIRSAR L-band and RADARSAT-2 C-band datasets from the San Francisco Bay and Flevoland regions, covering agricultural, urban, and natural land-cover scenes. The results show that the proposed method improves classification accuracy by 2.14~15.36% compared with other methods, while achieving a favorable balance between accuracy and computational efficiency. These results demonstrate the effectiveness of the proposed method for PolSAR land-cover classification in different regional environments. Full article

Thunderstorms are the most frequent type of severe convective weather, which pose great threats to buildings, power transmission, communication facilities, and air transportation. Their analysis and forecasting have long been challenges in meteorological operations. Currently, deep learning-based lightning forecasting has a short valid period, mostly relying on satellite imagery, radar echoes, and lightning location data, focusing on very-short-range forecasting. The longest valid period does not exceed 6 h, and the forecasting accuracy is not high. Based on the physical quantities of the ECMWF numerical prediction model and the actual observations of single-point thunderstorms, this paper constructs a single-point thunderstorm forecasting model with a long validity period (>6 h). The study integrates multi-dimensional parameters such as thermal, dynamic, water vapor, and stratification instability, introduces the second-order moist potential vorticity S as a comprehensive predictor, systematically compares the forecasting performance of eight models, such as 1D PreRNN and ConvLSTM, and verifies the actual operational capability of the model through independent cases. The results show that the 1D PreRNN model has the best overall performance in all periods, which can effectively capture the temporal evolution characteristics of meteorological physical quantities and still has stable generalization performance under unbalanced samples. The model performs well in the 1st, 2nd, and 4th periods, and especially still has significant operational reference value in the 4th period with the longest forecasting validity period; only the 3rd period is weakly affected by the small number of samples. The effect of second-order moist potential vorticity has significant time-dependent differences. Its overall improvement effect is limited in short-term forecasting, but it can provide key disturbance signals in the 4th period with the longest forecasting validity period, and the model forecasting performance drops significantly after removal. The original binary cross-entropy loss is most suitable for the unbalanced sample scenario in this study, and weighted losses are prone to overcorrection. The method in this paper can achieve stable and reliable single-point thunderstorm forecasting for more than 6 h, and can provide long-term fixed-point meteorological support for key scenarios such as aerospace and new energy stations. Full article

Bird migration is the regular, long-distance movement of birds between breeding and wintering grounds, influenced by climate change and human activities. The East Asia–Australasia Flyway (EAAF) is one of the largest migratory routes in the world, covering various species such as waders and waterfowl, with the eastern coastal areas of China serving as important stopover and wintering grounds. This paper selects the Qingdao area as the research object, and based on weather radar and meteorological data, explores the spatiotemporal characteristics of bird migration patterns in this region, discusses changes in regional bird activity and their causes, and investigates the influence of weather factors on migration altitude. By analyzing weather radar data from spring 2023, the peak migration period was found to occur mainly from mid-April to mid-May, with multiple large-scale migrations in late April exhibiting alternating peaks and troughs. Migration activity peaked between 8 p.m. and midnight, with altitudes below 600 m serving as the primary migration height range. Using correlation analysis, linear regression, and generalized additive models, the study further analyzed the contribution of various weather factors to birds’ altitude selection. Results showed that wind conditions, temperature, and humidity had significant effects on migration altitude. Full article

Short-term precipitation forecasting is essential for disaster prevention, urban management, and weather-sensitive decision making, yet radar-based nowcasting remains challenging because precipitation systems evolve nonlinearly and high-frequency echo structures are easily over-smoothed by deterministic sequence models. This paper proposes a ViT-modulated diffusion spatiotemporal prediction network (VSTPN) that cascades a spatiotemporal prediction module with a ViT-conditioned diffusion refinement module. The spatiotemporal module models the temporal evolution of radar echoes, whereas the ViT-Diffusion module uses global contextual features as conditional guidance during iterative denoising to refine spatial structures. Experiments on the HKO-7 benchmark show that VSTPN achieves lower MSE and higher SSIM than the tested baselines and improves CSI, HSS, and POD at the evaluated reflectivity thresholds. At the 40 dBZ threshold, the model improves CSI, HSS, and POD, while its FAR is slightly higher than that of ETCJ-PredNet, indicating a recall–false alarm trade-off for intense echoes. Additional post-hoc diagnostic analyses of relative gains, metric consistency, threshold sensitivity, and component effect sizes further support the stability of the reported improvements under the current experimental protocol. The results suggest that coupling spatiotemporal sequence modeling with diffusion-based radar echo refinement is a feasible direction for short-term precipitation forecasting; nevertheless, probabilistic uncertainty evaluation, multi-domain validation, and additional generative-quality metrics remain important directions for future work. Full article

With the increasing frequency of extreme weather and rapid growth of civil aviation, severe convective weather (thunderstorms, short-term heavy precipitation, and strong winds) poses growing threats to flight safety. This study proposes a multi-label CNN-ConvLSTM framework that fuses airport Doppler radar echoes, Himawari-8 satellite imagery, surface observations, and radar optical flow features to nowcast multiple severe convective events within the next 30 min. The model uses 2D-CNN for spatial extraction, ConvLSTM for temporal dynamics, and a weighted joint loss (Focal Loss and Dice Loss) to address class imbalance. Trained on 396 samples (positive-to-negative ratio 1:2.5) from 83 events at Guanghan Airport (2021–2024), incorporating optical flow features significantly boosted performance: macro-F1 increased from 0.719 to 0.792, and Threat Score (TS) from 0.567 to 0.705. Notably, false negatives for minority classes dropped sharply, with strong winds F1-score rising from 0.15 to 1.00. Ablation analysis showed optical flow as the top contributor (Mean Decrease in TS ≈ 0.5). Through multi-modal fusion and motion enhancement, this interpretable model provides high-precision nowcasting for airport severe convective weather, offering substantial value for aviation safety. Full article

Synthetic Aperture Radar (SAR) is one of mainstream remote sensing techniques, offering all-weather, day-and-night operational capabilities. However, throughout the processes of signal transmission, propagation, and reception, it is difficult to ensure that the amplitude and phase of the SAR signal strictly follow a linear frequency modulation (LFM) characteristic. The resulting signal distortion often leads to main lobe broadening and sidelobe elevation, degrading the focusing performance of SAR images. Traditionally, this issue has been addressed primarily through SAR system internal calibration and pre-distortion compensation, which makes it challenging to maintain the signal in an ideal state over the long term. At the same time, many simplified SAR systems also lack an internal calibration design, such as low-cost UAV-borne SAR payloads. In this paper, we propose a novel signal distortion compensation method based on SAR image data. Without relying on SAR system calibration signals, this method estimates and compensates for signal distortion directly using SAR image data, thereby improving SAR image focusing performance, achieving a resolution closer to the theoretical bandwidth and lower sidelobe. The processing and analysis of both manned and unmanned airborne SAR image data and calibration signals demonstrate that the proposed method effectively compensates for signal distortion phases, achieving performance comparable to that of real-time calibration-signal-based methods. Full article

Continuous monitoring and nowcasting of tornadic near-storm environments remain challenging, particularly in regions with limited ground-based weather radar coverage. High-spatiotemporal-resolution geostationary satellite remote sensing offers a valuable approach to track the evolution of severe convective storms. Combining 10 min cloud-top brightness temperature (TBB) data from the Himawari-8 satellite and ERA5 reanalysis, this study investigates the atmospheric environments of 177 documented tornadoes in China from 2016 to 2023. Tracking storm convective centers using TBB minima reveals clear regional differences in tornadogenesis paradigms. Southern China tornadoes exhibit a “dynamically driven” pattern within quasi-steady, warm, and moist environments. These environments feature low Lifted Condensation Levels (LCL; ~790 m) and weak Convective Inhibition (CIN). Intense low-level wind shear and storm-relative helicity (SRH) dominate the convective triggering. Northern China tornadoes follow a “coupled thermodynamic-kinematic” paradigm under relatively drier and cooler backgrounds. Their initiation relies on the rapid, synchronized accumulation of Mixed-Layer convective available potential energy (MLCAPE) and deep-layer SRH. Furthermore, intensity-based comparative analysis indicates that significant tornadoes (Enhanced Fujita [EF] scale, EF ≥ 2) are favored by higher MLCAPE, deep-layer shear, and lower LCLs compared to weak ones (EF ≤ 1). Himawari-8 TBB data capture a more rapid pre-storm convective cloud-top cooling for strong tornadoes, with medians reaching −73 °C. This study demonstrates that combining high-frequency satellite observations with reanalysis data provides quantitative precursor signals for regional severe tornado nowcasting. Full article

Predictive Maintenance (PdM) approach in Combined Sewer Systems (CSS) is gaining momentum due to advances in sensor technology, affordability and availability of data, and the rise of machine learning and data analytics. This study aims to characterize the general behavior of CSS under Dry and Wet weather conditions. To achieve this, 10 min resolution precipitation and water level data were collected from nearby SIAS stations and AMAP radar water level sensors, installed at the outlet chamber of the CSS, respectively. Precipitation data was used to segment continuous time series data into Dry Weather Flow (DWF) and Wet Weather Flow (WWF). DWF analysis exhibited unique flow patterns that strongly correlated with water consumption behaviors of households. For wet weather, a comparison was made between key rainfall parameters (depth, intensity) and peak water level data, and nonlinear relationships were observed that highlight the complex rainfall–runoff process. These findings underscore the need for separate predictive models tailored to DWF and WWF characteristics. Integrating high-resolution sensor data with machine learning models such as Long Short-Term Memory (LSTM) networks and anomaly detection, Autoencoders can enhance PdM, improving CSS management and reducing risks of blockage events and infrastructure failures. Full article

Rockfall events are significant natural hazards on fractured rock cliffs, often driven by environmental forcing, including thermal variations that induce stress and fatigue in rocks. This study presents the first application of Ground-Based Interferometric Synthetic Aperture Radar (GB-InSAR) for high-resolution monitoring of sub-millimeter thermally induced displacements on a rock slope. An eight-day pilot experiment conducted at the La Cornalle molasse cliff (Vaud, Switzerland) revealed cyclic displacement signals with a clear 24 h periodicity, identified through Fourier and wavelet analyses, with a mean amplitude of 5 × 10⁻⁴ m. Simultaneously, infrared thermography (IRT) and a weather station recorded rock surface and air temperature variations, allowing a first estimation of the time lag between thermal forcing and mechanical response, with delays of 1–8 h relative to air temperature and 1–6 h relative to solar radiation. An analytical deformation model based on thermal diffusion predicts a daily displacement amplitude of 4.2 × 10⁻⁵ m, highlighting a significant difference with GB-InSAR observations and emphasizing the influence of structural complexity and thermo-hydro-mechanical processes in rock slopes. These results demonstrate the capability of combined high-resolution remote sensing techniques to quantify thermo-mechanical behavior in rock masses and provide a methodological framework for future investigations of rockfall-prone slopes. Full article

Accurate smoke forecasting during wildfires is essential for hazard assessment and public health protection. Current operational models have limitations in representing dynamic fire-atmosphere interactions. This study aimed to assess the performance of the fire-atmosphere coupled version of the Warn-on-Forecast System (WoFS) and compare it with the classic WoFS in simulating wildfire smoke distribution and structure. Two Oklahoma wildfire events were simulated, and model outputs were compared against radar reflectivity observations for plume-top height, horizontal dispersion, and vertical structure. Both models showed comparable agreement with observations. WoFS-Smoke performed similarly or better in the early forecast period (0–1 h) due to direct smoke injection, whereas WRF-SFIRE, using a WoFS environment, required ~1 h spin-up before producing more realistic, continuous plume structures through fire-atmosphere coupling. SFIRE tended to overestimate plume height in one case and underestimate it in another. Coupling WoFS to SFIRE generally produced more realistic forecast smoke plume characteristics resulting from the dynamical coupling between the forecast environment and wildfire properties. The combination of WoFS and WRF-SFIRE opens up new possibilities in short-term wildfire smoke forecasting, setting the foundation for future operational models. Full article

Millimeter-wave radar imaging plays an increasingly important role in autonomous driving road perception due to its robustness under adverse weather conditions. However, radar images are inherently contaminated by multiplicative speckle noise, which severely degrades structural continuity, weakens target boundaries, and limits the perception of road scenes and surrounding objects. To address this problem, this paper proposes a structural-prior deep learning network for millimeter-wave radar image enhancement. The proposed framework first introduces an adaptive Otsu-based masking strategy to extract salient scattering structures and generate a coarse image structural prior for subsequent restoration. Guided by this prior, the network performs progressive feature enhancement through a continuous attention mechanism that integrates residual channel attention, context-aware feature extraction, and convolutional block attention, thereby enabling effective multi-scale representation learning while suppressing signal-dependent speckle interference. In addition, a composite loss function is designed by combining logarithmic denoising gain, total variation regularization, and a $\beta$-index edge-preservation term to jointly improve noise suppression, spatial smoothness, and structural fidelity. The proposed method is evaluated on the synthetic UC Merced dataset under different noise intensities and via cross-domain inference on the real-world RADIATE millimeter-wave radar dataset for autonomous driving scenarios. Experimental results demonstrate that the proposed network consistently outperforms conventional filtering methods and representative deep learning baselines in terms of PSNR, SSIM, $\beta$-index, and ENL while providing a superior preservation of road structures, target contours, and scene geometry. Ablation studies further confirm the effectiveness of the structural-prior guidance and continuous attention design. Furthermore, the network achieves a rapid inference latency of 12.35 milliseconds. These results indicate that the proposed method provides an effective and robust solution for millimeter-wave radar image enhancement and offers practical value for downstream road-scene perception in autonomous driving environments. Full article

Reliable person segmentation with sparse 3D sensors degrades significantly under adverse atmospheric conditions. This work presents a controlled comparative evaluation of four segmentation architectures—U-Net, Mask R-CNN, DeepLabV3+, and FCN-ResNet—on a fused Radar–LiDAR dataset for binary person–background segmentation and applies a dual-domain evaluation procedure that formally links 2D pixel-level overlap (IoU, Dice) to 3D geometric fidelity (Chamfer distance, Completeness) through mask back-projection onto fused point clouds. Raw point clouds are rasterized into range–intensity grids enriched with Radar reflectivity; the predicted masks are then reprojected into 3D space and evaluated using Chamfer distance and Completeness under three controlled visibility conditions. U-Net achieves the highest 2D overlap (IoU = 0.82, Dice = 0.89), while DeepLabV3+ delivers the best 3D reconstruction fidelity (Chamfer = 0.021 m, Completeness = 93.4%) and the highest overall accuracy (97.9%). This dissociation between 2D overlap and 3D fidelity is explained by DeepLabV3+’s multi-scale Atrous Spatial Pyramid Pooling (ASPP), which reduces boundary fragmentation during back-projection; more than 70% of the Chamfer deviation across competing architectures originates at object contours. Mask R-CNN performs well when instances are clearly separated, and FCN-ResNet offers the lowest computational cost at reduced boundary precision. Radar–LiDAR fusion sustains an IoU within 3% of clear-weather performance under dense fog, whereas LiDAR-only inputs degrade by more than 12%. Due to the 12:1 background-to-person class imbalance, overlap-based metrics (IoU, Dice) are prioritized over raw accuracy in all reported comparisons. These results provide actionable deployment guidance and constitute a reproducible evaluation procedure for future sparse-sensor fusion studies, independently of the architectures evaluated. Full article