Search Results (199)

Traditional Virtual Power Plant (VPP) dispatch is mainly based on numerical time-series forecasting, which may respond slowly to extreme market events and early-warning signals expressed in unstructured text. This paper proposes a Retrieval-Augmented Generation Virtual Power Plant (RAG-VPP) framework that integrates ISO-style market notices, emergency alerts, weather warnings, and regulatory updates into risk-aware dispatch optimization. The framework includes a semantic perception engine, a hybrid numerical forecasting engine, and a human-in-the-loop dispatch gateway. Unstructured market text is converted into a bounded semantic uncertainty metric and embedded into stochastic MIQP dispatch through semantic-conditioned scenario generation, a semantic exposure penalty, Dynamic Semantic Reserve Margin, and Semantic Demand Response Pre-Activation constraints. The framework is evaluated using a 7-day ERCOT-style controlled stress-test with synthetic ISO-like EEA1/EEA2 alerts and 5 min market resolution. The results show that RAG-VPP achieved a total profit of $285.8 k, representing a 32% improvement over the deterministic baseline. It also improved CVaR by $85.2 k, showed a four-hour semantic lead in the controlled stress-test scenario, achieved 0.92 semantic alignment, and maintained zero reserve-margin violation hours. These results indicate the potential of linguistically informed dispatch for improving VPP resilience under extreme-event conditions. Full article

Extreme weather events exacerbated by global warming pose severe threats to urban safety, underscoring the urgent need for highly accurate precipitation nowcasting. Short-term local heavy precipitation remains a particular challenge for traditional forecasting due to its suddenness and high disaster potential. To address this, we propose a multi-modal fusion framework that integrates ground-based GNSS-derived Precipitable Water Vapor (GNSS-PWV) and ground-based Radar Composite Reflectivity (CR). While GNSS-PWV keenly captures pre-convective atmospheric water vapor accumulation, radar CR details the morphological distribution of hydrometeors. Specifically, we developed the Spatio-Temporal Enhanced Attention Swin U-Net (STEA-Swin) model to synergize these heterogeneous datasets over the Beijing–Tianjin–Hebei region. High-precision PWV was retrieved from 250 Continuously Operating Reference Stations (CORS) using the dual-frequency ionosphere-free Precise Point Positioning (PPP) method, achieving a strong correlation (>0.97) with ERA5 reanalysis data. Validated against measured data from the 2025 flood season, the STEA-Swin model achieved a Probability of Detection (POD) of 0.68 for torrential rain events at a +1 h forecast lead time. Notably, compared to single-source models, the Critical Success Index (CSI) and POD for torrential rain improved by 18.5% and 21.5%, respectively. These findings demonstrate that coupling deep learning with ground-based GNSS-derived atmospheric thermodynamic information can significantly enhance early warning capabilities, providing a promising technical approach for regional disaster prevention and climate resilience. Full article

The key parameters of atmospheric convective stability, the K index (KI) and the Showalter index (SI), are important indicators for severe convective weather warnings. This study adopts a variational mode decomposition, bidirectional gated recurrent unit, and attention mechanism weighting combined model (VMD–BiGRU–Attention) to optimize core hyperparameters and verify model stability. Global Navigation Satellite System-derived precipitable water vapor (PWV) and relative humidity (RH) are incorporated as key parameters representing atmospheric water vapor conditions, thereby assisting VMD decomposition in accurately separating effective signals related to severe convection. The results show that the optimal VMD decomposition parameter K for the KI is 10 (minimum root mean square error [RMSE] = 3.96), whereas the optimal K for the SI is 11 (minimum RMSE = 1.87), verifying the applicability of VMD decomposition. In the validation using extreme rainfall events (2021–2025) at three meteorological stations in Guangxi (Baise, Nanning, and Hepu), the model, with the auxiliary contributions of PWV and RH, stably and accurately predicts the KI and SI for the next three hours, effectively capturing the critical characteristics of severe convection. The predicted results are consistent with the observed precipitation, demonstrating significant practical application value. Full article

Forest fires occur frequently around the world due to extreme weather conditions of high temperatures and drought. Vision-based convolutional neural networks (CNNs) have greatly improved forest fire detection accuracy. However, slow inference speed severely restricts real-time deployment in actual forest scenes. Existing models generally adopt group convolution (GConv) or depthwise convolution (DWConv) to reduce computational complexity, which causes frequent memory access and result in a practical inference speed far below theoretical expectations. Therefore, we propose a novel fast neural network named FasterNetFire for forest fire detection, which introduces partial convolution (PConv) as the basic feature extraction operator to reduce redundant computation as well as memory access overhead simultaneously. FasterNetFire is composed of four cascaded stages, each stage contains several stacked FasterNet Blocks, and the core of each FasterNet Block is an inverted residual module built upon PConv. The proposed network significantly improves inference efficiency while maintaining the effectiveness of spatial feature extraction. Experiments conducted on the FD and Foggia’s fire detection dataset demonstrate that our FasterNetFire achieves an impressive inference speed of up to 290 frames per second (FPS) on graphics processing unit (GPU) platforms. Compared with current representative methods, its inference speed is 4.5× and 4× faster than that of EFDNet and DFAN. Furthermore, FasterNetFire achieves the best results among 17 state-of-the-art methods, achieving an excellent balance between detection accuracy and real-time response performance. This advantage fully verifies the high efficiency of PConv in vision forest fire detection tasks and provides a novel lightweight solution for real-time monitoring and early warning of forest fires in resource-constrained environments. Full article

Galloping of overhead transmission lines is a low-frequency, large-amplitude vibration hazard that poses a severe threat to power grid safety, yet existing monitoring approaches fail to simultaneously provide flexible deployment, quantitative measurement, and robustness under severe weather conditions. This paper makes three primary contributions. First, we propose a novel line-structure center adsorption algorithm that converts a single operator touch-point into a sub-pixel-precision conductor prompt, achieving prompt accuracy above 95% with one round of interactive correction. Second, we introduce—for the first time—SAM2’s streaming memory architecture for continuous zero-shot pixel-level tracking of galloping conductors under complex outdoor backgrounds including snow, ice, and poor illumination, achieving a segmentation IoU of 93.8% and zero identity switches over 500 consecutive frames, outperforming XMem (87.4%) and DeAOT (88.9%). Third, we develop a two-stage spatial correction framework combining vanishing-point-based inverse perspective mapping (IPM) with equidistant linear transformation (ELT), which eliminates perspective distortion inherent in non-orthogonal field imaging and enables quantitative measurement of galloping amplitude (error < 0.5 m), frequency (error < 0.1 Hz), and inter-phase spacing (ranging error < 1 m). The complete pipeline is implemented on a portable, tripod-mounted device (≤15 kg) integrating a monocular camera, laser rangefinder, and high-precision PTZ gimbal. Field validation at three 110/500 kV sites in Jiangsu Province under extreme winter conditions ($-4$ °C, Level 5 wind, continuous snowfall) confirms engineering-grade accuracy and practical robustness, providing a viable technical pathway for real-time non-contact galloping monitoring and disaster early warning. Full article

Extreme meteorological phenomena—characterized by gale-force winds, torrential rainfall, and ice-snow accumulation—pose significant threats to the operational safety of high-speed railways, with wind-induced hazards being especially critical. Such events can trigger catastrophic incidents, including train derailments and service disruptions, as evidenced by numerous documented cases worldwide. To bolster the wind resilience of high-speed railway systems, high-precision wind speed prediction has become a cornerstone for ensuring operational safety. This research presents a systematic review of international advancements in railway wind early warning systems, critically evaluating the technical attributes and performance constraints of four primary paradigms: physical numerical models, statistical methods, machine learning algorithms, and hybrid frameworks. Moving beyond a simple taxonomy, this paper delineates the strengths, limitations, and domain-specific applicability of each approach within the high-speed railways context. Furthermore, it assesses the transformative potential of emerging large-scale Artificial Intelligence (AI) meteorological models for wind speed forecasting. A quantitative comparison is provided to facilitate rigorous methodological assessment. The findings reveal four critical technical bottlenecks: (1) low computational efficiency of numerical models; (2) insufficient spatiotemporal resolution of monitoring data; (3) poor generalization of predictive models; and (4) the “black-box” nature and weak interpretability of AI models. To address these, this paper posits that future research should prioritize key technologies including multi-source heterogeneous data fusion, algorithmic optimization, design of intelligent algorithms, probabilistic risk forecasting, and the synergistic integration of AI with numerical weather prediction (NWP). Such advancements will catalyze the development of more robust HSR wind warning systems, ensuring sustained safety and operational efficiency under volatile meteorological conditions. Full article

Post-processing of numerical weather prediction (NWP) models constitutes a pivotal link in enhancing forecast performance. Despite their recognition as cutting-edge point-based post-processing techniques, systematic comparative evaluations of ecPoint (ECWMF for point forecasts) and Ensemble Model Output Statistics (EMOS)—particularly assessments of their applicability outside Europe and to Chinese ensemble forecasting systems—remain sparse. In this study, we evaluate two advanced post-processing techniques—EMOS and the ecPoint—for calibrating ensemble precipitation forecasts. A comprehensive assessment of the performance of these ensemble post-processing methods is conducted using the CMA-GEPS (China Meteorological Administration’s Global Ensemble Forecasting System forecast over eastern China. The results demonstrate that both methods significantly mitigate systematic biases and improve the reliability and dispersion of ensemble forecasts. Notably, improvement in forecast accuracy is observed even under convective weather conditions and early-warning capability of extreme precipitation events is improved. Overall, while both methods show comparable performance, they exhibit distinct behaviours across different regions. The ecPoint method slightly outperforms EMOS in terms of Continuous Ranked Probability Score (CRPS) and provides improved resolution and early-warning capabilities at various precipitation thresholds. Full article

The power system is the backbone of the energy network, and overhead lines are its vital structures. Weather threats may jeopardise the reliability of lines and make them a weak link. In particular, heavy rainfall episodes can cause failures, especially in mountain areas. Current climate changes may exacerbate the effects on the ground, intensifying rainfall episodes and increasing the frequency of extreme events. In this context, debris flows triggered by rather intense precipitation and characterised by fast kinematics can destroy pylons and electric connections, affecting the infrastructures not only in the upper ridges but also downstream across the fan apex, where powerlines are much more distributed. This study presents an in-depth back-analysis of two debris flow events triggered in concomitance with a heavy cloudburst that occurred in Talamona (Sondrio Province, Italy) in July 2008 and in Campo Tartano (Sondrio Province, Italy) in April 2024. These events hit onsite powerlines, causing blackouts and showing the potential vulnerabilities of the local electricity system. An analysis of rainfall-induced landslide failure is carried out using the numerical model CRHyME (Climatic Rainfall Hydrogeological Modelling Experiment) and MIST-DF (Modelling Impulsive Sediment Transport—Debris Flow) with the aim of reconstructing the dynamics of the first (i.e., Talamona) geo-hydrological event. Powerline vulnerability is also investigated against debris flow dynamics, discussing possible strategies to reduce pylon exposure and to increase the resilience of the local electro-energetic network. Since, under climate change scenarios, heavy rainfall episodes are projected to intensify, an alternative approach based on rainfall-threshold curves is presented and applied to both cases of study. The latter, already implemented for civil protection purposes, could be useful in early-warning procedures against potential debris flow hazards. For both methodologies, the findings from the study confirm the strength of the approaches and foster their application in different situations (back-analysis and early warning) to reduce powerlines’ geo-hydrological risks. Full article

Tornado is a localized, small-scale severe convective weather phenomenon characterized by extreme destructiveness. Tornado detecting and warning mainly rely on Doppler weather radar, which identifies and tracks tornadoes by recognizing the tornado vortex signature and supercells in radar data. Artificial intelligence technology has been applied to tornado recognition in recent years. However, existing monitoring methods, especially those using unsupervised learning algorithms, still have limited recognition accuracy and timely warning, and usually struggle to strike a balance between detection accuracy and false alarm rate. A novel tornado detection algorithm TDA-DARKNet has been proposed to address the aforementioned issues. The algorithm integrates a dual attention mechanism, dense residual connections, and Kolmogorov–Arnold network (KAN). A tornado dataset suitable for deep learning has been formed, which utilizes features including radial velocity, reflectivity, velocity spectrum width, differential reflectivity, and correlation coefficient in radar data. The TDA-DARKNet algorithm was trained and tested using the tornado dataset, and evaluated in tornado cases. The experimental results show that TDA-DARKNet improves the detection probability and extends the lead time to a maximum of 42 min in strong tornado situations, while achieving 97.11% accuracy, 95.08% precision, indicating strong overall identification performance. In addition, by directly leveraging radar-based data for tornado identification, the algorithm eliminates the need for manual feature engineering, simplifies data processing, reduces complexity, and further enhances detection effectiveness. Full article

The accurate and timely nowcasting of severe weather events such as short-term torrential rainfall is essential for disaster preparedness and early warning systems. Our prior studies have demonstrated a high correlation (0.92) and ~10 min time lag between in-cloud (IC) lightning and ground rainfall. In this study, based on the approach introduced by Shimizu and Uyeda, an automatic method for identifying and tracking convective storm cells, we integrate total lightning data and heavy precipitation data for further improving the prediction accuracy of torrential rainfall. High-resolution 2D weather radar composite precipitation data are collected from XRAIN, operated by MLIT, Japan, and total lightning data (TL, i.e., IC and CG) are collected from the Japanese Total Lightning Network (JTLN). The adapted algorithm is used to track lightning-frequent areas (≥5 and ≥2 pulses per 5 min) as well as heavy (≥50 mm/h) and torrential (≥80 mm/h) precipitation cells. To evaluate the predictive capability of TL, cross-correlation analyses are performed across multiple intensity thresholds and time lags. The results of correlation matrix analysis for identifying the movement of the storm and utilization towards spatiotemporal nowcasting of extreme rainfall is discussed. Full article

Against the background of intensifying global climate change, extreme precipitation events have become increasingly frequent. Improving the accuracy of short-term precipitation nowcasting is therefore essential for disaster prevention and mitigation. Traditional numerical weather prediction (NWP) approaches are constrained by computational latency and errors arising from physical parameterizations, making it difficult to satisfy real-time forecasting requirements at high spatiotemporal resolution. Using the SEVIR dataset, this study conducts a systematic comparison of two Transformer-based deep learning models—Earthformer and LLMDiff—for short-term extreme precipitation nowcasting. Model performance is evaluated using the Critical Success Index (CSI), Probability of Detection (POD), and Success Ratio (SUCR). Results indicate that, for 0–30 min lead times, Earthformer more efficiently captures both local and long-range spatiotemporal dependencies via its Cuboid Attention mechanism and shows a slight advantage for low-intensity precipitation. As the lead time extends to 60 min, LLMDiff demonstrates stronger longer-horizon skill due to its diffusion-based probabilistic modeling and a frozen large language model (LLM) module, which enhance the representation of uncertainty and longer-term evolution of precipitation systems. However, LLMDiff tends to produce a higher false-alarm rate. Overall, Earthformer is better suited for rapid early warning of light precipitation, whereas LLMDiff is more appropriate for high-accuracy nowcasting of heavy precipitation, offering useful insights for intelligent forecasting of extreme weather. Full article

Urban waterlogging has become a critical challenge to urban sustainability under the combined pressures of rapid urbanization and increasingly frequent extreme weather events. However, traditional predictive models struggle to achieve real-time, point-specific early warning effectively, primarily due to the interference of redundant high-dimensional data and the inability to handle severe data imbalance. This study proposes a lightweight and interpretable machine learning framework for real-time waterlogging hotspot prediction, based on a multi-dimensional feature space. Specifically, we implement a Lasso-based mechanism to distill 37 multi-source variables into five core determinants. This process effectively isolates dominant environmental drivers while filtering noise. To further overcome the recall bottleneck, we propose a Synthetic Minority Over-sampling Technique based on Weighted Distance and Cleaning (SMOTE-WDC) algorithm that incorporates weighted feature distances and density-based noise cleaning. Validating the framework on datasets from Shenzhen (2023–2024), we demonstrate that the integrated Gradient Boosting Decision Tree (GBDT) model integrated with this strategy achieves optimal performance using only five features, yielding an F1-score of 0.808 and an Area Under the Precision-Recall Curve (AUC-PR) of 0.895. Notably, a Recall of 0.882 is attained, representing a 4.6% improvement over the baseline. This study contributes a cost-effective, high-sensitivity approach to disaster risk reduction, advancing predictive urban waterlogging management. Full article

The frequency of extreme weather events has become higher, and electricity consumption has also become more complex. These changes increase the risk of overload in distribution transformers (DTs), and this risk threatens the stability and reliability of the power grid. Existing methods have significant limitations. Traditional static threshold methods (based on DGA gas ratios and electrical signal thresholds) fail to consider temporal changes and complex links between factors, while modern machine learning models lack cause–effect relationships over time and clear ways to describe uncertainty. With such motivations, this paper proposes a causal-enhanced hybrid framework, which combines Long Short-Term Memory (LSTM) networks and Random Forest (RF) algorithms. The framework uses causal Seasonal Trend decomposition using Loess (STL) to reveal load patterns at different time scales. The mutual information index and spatiotemporal graph convolutional network (ST-GCN) are used to explore nonlinear relations and reveal how temperature affects load changes. The LSTM model captures time dependence in load series, and the Bayesian optimized Random Forest is used to solve the problem of data imbalance and quantify uncertainty. In addition, the framework constructs an early warning system that combines data from many sources in real time. Test results show that the proposed algorithm exhibits excellent performance in multi-source data environments. Full article

Spaceborne infrared small-target detection plays a critical role in space-sky early warning, disaster rescue, and reconnaissance tracking, benefiting from all-time, all-weather, and wide-area monitoring capabilities. The deployment of high-spatial-resolution infrared payloads (ground sampling distance, GSD < 10 m) has introduced pronounced scale diversity among targets, leading to size-sensitive performance degradation in existing detectors and heightened risks of missed detections or false alarms in mixed-size scenarios. Furthermore, multi-frame infrared small-target detection methods often face challenges in maintaining consistent temporal coherence during feature propagation across sequences. To overcome these limitations in high-resolution spaceborne infrared videos, we propose DTRFR, an end-to-end unified detection framework built on an enhanced recurrent feature refinement architecture. This approach incorporates a realistic SITP-QLSD dataset derived from QLSAT-2 infrared backgrounds, featuring diverse scenes, multi-size small targets, and a dedicated generalization sub-test set with extremely small targets partially unseen in training; a multi-scale IRFeatureExtractor leveraging parallel convolutions and dilated receptive fields for improved cross-scale discrimination and clutter suppression; and an adaptive gating pyramid deformable alignment module to optimize sequence alignment and enhance temporal consistency, enabling robust performance across various clutter levels and dynamic backgrounds. Extensive evaluations on SITP-QLSD demonstrate that DTRFR attains competitive performance, achieving mIoU of 74.32% and Pd of 94.51% on the main set, with strong robustness on the generalization sub-test set (Pd = 92.37%). Compared to single-frame and multi-frame baselines, the proposed method achieves higher detection accuracy with significantly reduced false alarms, benefiting from multi-scale feature extraction that enables robust detection of small targets of different sizes in infrared videos. Full article

In the Yingjiang area of western Yunnan, precipitation is high throughout the year, making it one of the regions with the highest annual precipitation in mainland China. Extreme rainfall in this region often triggers severe flooding, yet the key mechanism of water vapor transport underlying abnormally heavy precipitation remains unclear. This study used automatic weather station observations of precipitation, the fifth-generation atmospheric reanalysis produced by the European Centre for Medium-Range Weather Forecasts, and Global Data Assimilation System (GDAS) data to analyze, for the first time, large-scale water vapor transport, precipitation mechanisms, and the primary water vapor sources and their contributions in this region. The results show the following: In the Yingjiang area, the water vapor sources at all height levels in summer are dominated by the southwest monsoon water vapor transport pathways, such as the Bay of Bengal and the Arabian Sea, with their total contributions to specific humidity and water vapor flux exceeding 70%. This indicates that low-latitude sea areas such as the Bay of Bengal and the Arabian Sea serve as key moisture source regions for Yingjiang in the global water vapor cycle. Water vapor transport over the windward slope causes strong low-level convergence and high-level divergence phenomena, and the suction effect leads to strong upward motion near the 850 hPa level. The pseudo-equivalent potential temperature isolines tilt along the mountain slope, maintaining an unstable stratification characterized by warm, humid lower layers and cold, dry upper layers, providing favorable thermal conditions for precipitation. In addition, in the summer of 2020, abnormally high southwest seasonal wind and air transport, combined with strong low-level convergence and high-level divergence of the vertical circulation structure, were key factors causing the abnormally high precipitation. This study provides an important reference for the prediction of extreme precipitation and the early warning of rainstorm disasters in the southwest monsoon region in the context of global climate change. Full article