Search Results (348)

In recent years, precipitable water vapor has emerged as a key atmospheric parameter in weather prediction research. However, relying on only one parameter does not always accurately predict rainfall, as other atmospheric parameters also contribute to initiating rain events. In our previous study, we explored a methodology for rainfall forecasting based on the atmospheric delay gradient at an individual station in the tropical region. Commonly referred to as the atmospheric gradient, it accounts for the delay in GNSS signals due to changes in horizontal refractivity while propagating through the troposphere to the ground station. This paper discusses the spatial and temporal correlation of the gradient with precipitation occurring over a region. We have investigated different features, such as gradient magnitude, gradient convergence, and the flux of the atmospheric gradient, to propose potential nowcasting criteria for precipitation in the tropical climatic zone. The atmospheric gradient in the surrounding region orients toward the area of precipitation as the rain event approaches. This gradient gradually alters its orientation and converges toward the region of rainfall at the time of precipitation, introducing the concept of gradient convergence. This phenomenon results in an inward gradient flux at the time of the downpour, which presents a potential parameter for rainfall prediction over an area. We also proposed investigating area sizes of 4° × 4° or 8° × 8°, depending on the gradient feature, to establish a forecasting methodology for rainfall. The weather front in the tropical region begins to initiate 12 h before the actual time of occurrence and advances toward the area where it will have an impact from a more distant location. This article presents a detailed investigation of various features of the atmospheric gradient and its potential to nowcast rainfall for a region, as well as proposes the lead time for long-term weather predictions. Furthermore, a deep neural network has been employed to predict rainfall events for the next 6 h over an area in the tropical region. Full article

Extreme precipitation events often present significant risks to human life and property, making their accurate prediction an essential focus of current research. Recent studies have primarily concentrated on exploring the formation mechanisms of extreme precipitation. Existing prediction methods do not adequately account for the combined terrain and atmospheric effects, resulting in shortcomings in extreme precipitation forecasting accuracy. Additionally, the satellite data resolution used in prior studies fails to precisely capture nuanced details of abrupt changes in extreme precipitation. To address these shortcomings, this study introduces an innovative approach for accurately predicting extreme precipitation: the multimodal attention ConvLSTM-GAN for extreme rainfall nowcasting (ER-MACG). This model employs high-resolution Fengyun-4A(FY4A) satellite precipitation products, as well as terrain and atmospheric datasets as inputs. The ER-MACG model enhances the ConvLSTM-GAN framework by optimizing the generator structure with an attention module to improve the focus on critical areas and time steps. This model can alleviate the problem of information loss in the spatial–temporal convolutional long short-term memory network (ConvLSTM) and, compared with the standard ConvLSTM-GAN model, can better handle the detailed changes in time and space in extreme precipitation events to achieve more refined predictions. The main findings include the following: (a) The ER-MACG model demonstrated significantly greater predictive accuracy and overall performance than other existing approaches. (b) The exclusive consideration of DEM and LPW data did not significantly enhance the ability to predict extreme precipitation events in Zhejiang Province. (c) The ER-MACG model significantly improved in identifying and predicting extreme precipitation events of different intensity levels. Full article

This research work focuses on the development and application of a storm-tracking algorithm for identifying and tracking storm cells. The algorithm first identifies storm cells on the basis of reflectivity thresholds and then matches the cells in the tracking procedure on the basis of their geometrical characteristics and the distance within the weather radar image. A sensitivity analysis was performed to evaluate the preferable thresholds for each case and test the algorithm’s ability to perform in different time step resolutions. Following this, we applied the algorithm to 54 rainfall events recorded by the National Technical University X-Band weather radar, the rainscanner system, from 2018 to 2023 in the Attica region of Greece. Testing of the algorithm demonstrated its efficiency in tracking storm cells over various time intervals and reflecting changes such as merging or dissipation. The results reveal the predominant southwest-to-east storm directions in 40% of cases examined, followed by northwest-to-east and south-to-north patterns. Additionally, stratiform storms showed slower north-to-west trajectories, while convective storms exhibited faster west-to-east movement. These findings provide valuable insights into storm behavior in Athens and highlight the algorithm’s potential for integration into nowcasting systems, particularly for flood early warning systems. Full article

This study advances the precision and efficiency of precipitation nowcasting, particularly under extreme weather conditions. Traditional forecasting methods struggle with precision, spatial feature generalization, and recognizing long-range spatial correlations, challenges that intensify during extreme weather events. The Enhanced Temporal Correlation Jump Prediction Network (ETCJ-PredNet) introduces a novel attention mechanism that optimally leverages spatiotemporal data correlations. This model scrutinizes and encodes information from previous frames, enhancing predictions of high-intensity radar echoes. Additionally, ETCJ-PredNet addresses the issue of gradient vanishing through an innovative jump connection strategy. Comparative experiments on the Moving Modified National Institute of Standards and Technology (Moving-MNIST) and Hong Kong Observatory Dataset Number 7 (HKO-7) validate that ETCJ-PredNet outperforms existing models, particularly under extreme precipitation conditions. Detailed evaluations using Critical Success Index (CSI), Heidke Skill Score (HSS), Probability of Detection (POD), and False Alarm Ratio (FAR) across various rainfall intensities further underscore its superior predictive capabilities, especially as rainfall intensity exceeds 30 dbz,40 dbz, and 50 dbz. These results confirm ETCJ-PredNet’s robustness and utility in real-time extreme weather forecasting. Full article

The accurate prediction of lightning is crucial for forecasters to respond effectively to its related hazards. The rapid development and confined spatial extent of convective storms, in which lightning frequently occurs, pose considerable challenges for accurately predicting their locations using numerical weather prediction (NWP) models. Lightning occurrence is often prognosed using thermodynamic parameters, convective available potential energy (CAPE), the severe weather threat index (SWEAT), the lifted index (LI), etc. A high-resolution NWP model provides a prediction of these thermodynamic parameters at high spatiotemporal resolution with high accuracy for a few hours. However, a complicated algorithm is required to handle all the useful high-resolution variables from the NWP model. The recently emerging machine learning technique can solve this issue by properly handling these “big data” without any model distributional assumption. In this study, we developed a random forest algorithm for nowcasting and very short-range forecasting (useful for ~6 h), named LightningRF. LightningRF was trained by using lightning occurrence as a response variable and characteristic parameters from the NWP as predictors. It was also applied to analysis and forecast fields, showing a high probability of lightning within the observed lightning regions. This highlights the potential of helping forecasters improve their lightning forecasting skills using real-time probabilistic forecasts from a trained model. Full article

Radar echo extrapolation (REE) is a crucial method for convective nowcasting, and current deep learning (DL)-based methods for REE have shown significant potential in severe weather forecasting tasks. Existing DL-based REE methods use extensive historical radar data to learn the evolution patterns of echoes, they tend to suffer from low accuracy. This is because data of radar modality face difficulty adequately representing the state of weather systems. Inspired by multimodal learning and traditional numerical weather prediction (NWP) methods, we propose a Multimodal Asymmetric Fusion Network (MAFNet) for REE, which uses data from radar modality to model echo evolution, and data from satellite and ground observation modalities to model the background field of weather systems, collectively guiding echo extrapolation. In the MAFNet, we first extract overall convective features through a global shared encoder (GSE), followed by two branches of local modality encoder (LME) and local correlation encoders (LCEs) that extract convective features from radar, satellite, and ground observation modalities. We employ an multimodal asymmetric fusion module (MAFM) to fuse multimodal features at different scales and feature levels, enhancing radar echo extrapolation performance. Additionally, to address the temporal resolution differences in multimodal data, we design a time alignment module based on dynamic time warping (DTW), which aligns multimodal feature sequences temporally. Experimental results demonstrate that compared to state-of-the-art (SOTA) models, the MAFNet achieves average improvements of 1.86% in CSI and 3.18% in HSS on the MeteoNet dataset, and average improvements of 4.84% in CSI and 2.38% in HSS on the RAIN-F dataset. Full article

Accurate meteorological information is crucial for the safety of civil aviation flights. Complete wind field information is particularly helpful for planning flight routes. To address the challenge of accurately reconstructing wind fields, this paper introduces a deep learning neural network method based on the Vision Mamba Decoder. The goal of the method is to reconstruct the original complete wind field from incomplete wind data distributed along air routes. This paper proposes improvements to the Vision Mamba model to fit our mission, showing that the developed model can accurately reconstruct the complete wind field. The experimental results demonstrate a mean absolute error (MAE) of wind speed of approximately 1.83 m/s, a mean relative error (MRE) of around 7.87%, an R-square value of about 0.92, and an MAE of wind direction of 5.78 degrees. Full article

Intense rainfall events frequently occur in Brazil, often leading to rapid flooding. Despite their recurrence, there is a notable lack of sub-daily studies in the country. This research aims to assess patterns related to the structure and microphysics of clouds driving intense rainfall in Brazil, resulting in high accumulation within 1 h. Employing a 40 mm/h threshold and validation criteria, 83 events were selected for study, observed by both single and dual-polarization radars. Contoured Frequency by Altitude Diagrams (CFADs) of reflectivity, Vertical Integrated Liquid (VIL), and Vertical Integrated Ice (VII) are employed to scrutinize the vertical cloud characteristics in each region. To address limitations arising from the absence of polarimetric coverage in some events, one case study focusing on polarimetric variables is included. The results reveal that the generating system (synoptic or mesoscale) of intense rain events significantly influences the rainfall pattern, mainly in the South, Southeast, and Midwest regions. Regional CFADs unveil primary convective columns with 40–50 dBZ reflectivity, extending to approximately 6 km. The microphysical analysis highlights the rapid structural intensification, challenging the event predictability and the issuance of timely, specific warnings. Full article

Climate change is a major issue in wastewater management at local and regional levels, as it affects the frequency of flooding and therefore the need to update infrastructure and design regulations. To this end, rainfall data are the main input to hydraulic models used for the design of drainage systems and, in advanced contexts, for their real-time monitoring. Field observations are of great interest and water authorities are increasing the number of existing rain gauges, but at present they are scarce and require maintenance, so their number needs to be considered with their O&M costs. Remote sensors, including both the existing satellite rain products (SRPs) and radar imagery (RI), can complete the spatial distribution of rainfall and optimise the cost of observations. While most SRPs are based on re-analysis and have a lag in availability, RI can be obtained in near real time and is becoming increasingly popular in weather forecasting applications. Unfortunately, actual rainfall forecasts from RI observations are not accurate enough for real-time monitoring of drainage systems. In this paper, the Colour Pattern Regression (CPR) algorithm is used to recalibrate the 6 h rainfall values from RI provided by the Agencia Estatal de Meteorología (AEMET) with the observed rain gauge data, using as a case study the metropolitan area of Palma (Spain). Full article

Precipitation nowcasting, which involves the short-term, high-resolution prediction of rainfall, plays a crucial role in various real-world applications. In recent years, researchers have increasingly utilized deep learning-based methods in precipitation nowcasting. The exponential growth of spatiotemporal observation data has heightened interest in recent advancements such as denoising diffusion models, which offer appealing prospects due to their inherent probabilistic nature that aligns well with the complexities of weather forecasting. Successful application of diffusion models in rainfall prediction tasks requires relevant conditions and effective utilization to direct the forecasting process of the diffusion model. In this paper, we propose a probabilistic spatiotemporal model for precipitation nowcasting, named LLMDiff. The architecture of LLMDiff includes two networks: a conditional encoder–decoder network and a denoising network. The conditional network provides conditional information to guide the denoising network for high-quality predictions related to real-world earth systems. Additionally, we utilize a frozen transformer block from pre-trained large language models (LLMs) in the denoising network as a universal visual encoder layer, which enables the accurate estimation of motion trend by considering long-term temporal context information and capturing temporal dependencies within the frame sequence. Our experimental results demonstrate that LLMDiff outperforms state-of-the-art models on the SEVIR dataset. Full article

Accurate predictions are crucial for addressing the challenges posed by climate change. Given South Korea’s location within the East Asian summer monsoon domain, characterized by high spatiotemporal variability, enhancing prediction accuracy for regions experiencing heavy rainfall during the summer monsoon is essential. This study aims to derive temporal weighting functions using hybrid surface rainfall radar-observation data as the target, with input from two forecast datasets: the McGill Algorithm for Precipitation Nowcasting by Lagrangian Extrapolation (MAPLE) and the KLAPS Forecast System. The results indicated that the variability in the optimized parameters closely mirrored the variability in the rainfall events, demonstrating a consistent pattern. Comparison with previous blending results, which employed event-type-based weighting functions, showed significant deviation in the average AUC (0.076) and the least deviation (0.029). The optimized temporal weighting function effectively mitigated the limitations associated with varying forecast lead times in individual datasets, with RMSE values of 0.884 for the 1 h lead time of KLFS and 2.295 for the 4–6 h lead time of MAPLE. This blending methodology, incorporating temporal weighting functions, considers the temporal patterns in various forecast datasets, markedly reducing computational cost while addressing the temporal challenges of existing forecast data. Full article

Qualitative precipitation forecasting plays a vital role in marine operational services. However, predicting heavy precipitation over the open ocean presents a significant challenge due to the limited availability of ground-based radar observations far from coastal regions. Recent advancements in deep learning models offer potential for oceanic precipitation nowcasting using satellite images. This study implemented an enhanced UNet model with an attention mechanism and a residual architecture (RA-UNet) to predict the precipitation rate within a 90 min time frame. A comparative analysis with the standard UNet and UNet with an attention algorithm revealed that the RA-UNet method exhibited superior accuracy metrics, such as the critical ratio index and probability of detection, with fewer false alarms. Two typical cases demonstrated that RA-UNet had a better ability to forecast monsoon precipitation as well as intense precipitation in a tropical cyclone. These findings indicate the greater potential of the RA-UNet approach for nowcasting heavy precipitation over the ocean using satellite imagery. Full article

Based on C-band weather radar and ground precipitation data from the Helan Mountain area in Yinchuan between 2017 to 2020, we evaluated the forecasting performances of 15 mainstream deep learning models used in recent years, including recurrent-based and recurrent-free models. The critical success index (CSI), probability of detection (POD), false alarm rate (FAR), mean square error (MSE), mean absolute error (MAE), and learned perceptual image patch similarity (LPIPS), were used to evaluate the forecasting abilities. The results showed that (1) recurrent-free models have significant parameter quantity and computing power advantages, especially the SimVP model. Among the recurrent-based models, PredRNN and PredRNN++ demonstrate good predictive capabilities for changes in echolocation and intensity, PredRNN++ performs better in predicting long sequences (1 h); (2) SimVP uses Inception to extract temporal features, which cannot capture the complex physical changes in radar echo images and fails to extract spatial–temporal correlations and accurately predict heavy rainfall areas effectively. Therefore, we constructed the SimVP-GMA model, replacing the temporal prediction module in SimVP and modifying the spatial encoder part. Compared with SimVP, the MSE and LPIPS indicators were improved by 0.55 and 0.0193, respectively. It can be seen from the forecast images that the forecast details have been significantly improved, especially in the forecasting of heavy rainfall weather. Full article

The nowcasting of strong convective precipitation is highly demanded and presents significant challenges, as it offers meteorological services to diverse socio-economic sectors to prevent catastrophic weather events accompanied by strong convective precipitation from causing substantial economic losses and human casualties. With the accumulation of dual-polarization radar data, deep learning models based on data have been widely applied in the nowcasting of precipitation. Deep learning models exhibit certain limitations in the nowcasting approach: The evolutionary method is prone to accumulate errors throughout the iterative process (where multiple autoregressive models generate future motion fields and intensity residuals and then implicitly iterate to yield predictions), and the “regression to average” issue of autoregressive model leads to the “blurring” phenomenon. The evolution method’s generator is a two-stage model: In the initial stage, the generator employs the evolution method to generate the provisional forecasted data; in the subsequent stage, the generator reprocesses the provisional forecasted data. Although the evolution method’s generator is a generative adversarial network, the adversarial strategy adopted by this model ignores the significance of temporary prediction data. Therefore, this study proposes an Adversarial Autoregressive Network (AANet): Firstly, the forecasted data are generated via the two-stage generators (where FURENet directly produces the provisional forecasted data, and the Semantic Synthesis Model reprocesses the provisional forecasted data); Subsequently, structural similarity loss (SSIM loss) is utilized to mitigate the influence of the “regression to average” issue; Finally, the two-stage adversarial (Tadv) strategy is adopted to assist the two-stage generators to generate more realistic and highly similar generated data. It has been experimentally verified that AANet outperforms NowcastNet in the nowcasting of the next 1 h, with a reduction of 0.0763 in normalized error (NE), 0.377 in root mean square error (RMSE), and 4.2% in false alarm rate (FAR), as well as an enhancement of 1.45 in peak signal-to-noise ratio (PSNR), 0.0208 in SSIM, 5.78% in critical success index (CSI), 6.25% in probability of detection (POD), and 5.7% in F1. Full article

Precipitation nowcasting plays an important role in mitigating the damage caused by severe weather. The objective of precipitation nowcasting is to forecast the weather conditions 0–2 h ahead. Traditional models based on numerical weather prediction and radar echo extrapolation obtain relatively better results. In recent years, models based on deep learning have also been applied to precipitation nowcasting and have shown improvement. However, the forecast accuracy is decreased with longer forecast times and higher intensities. To mitigate the shortcomings of existing models for precipitation nowcasting, we propose a novel model that fuses spatiotemporal features for precipitation nowcasting. The proposed model uses an encoder–forecaster framework that is similar to U-Net. First, in the encoder, we propose a spatial and temporal multi-head squared attention module based on MaxPool and AveragePool to capture every independent sequence feature, as well as a global spatial and temporal feedforward network, to learn the global and long-distance relationships between whole spatiotemporal sequences. Second, we propose a cross-feature fusion strategy to enhance the interactions between features. This strategy is applied to the components of the forecaster. Based on the cross-feature fusion strategy, we constructed a novel multi-head squared cross-feature fusion attention module and cross-feature fusion feedforward network in the forecaster. Comprehensive experimental results demonstrated that the proposed model more effectively forecasted high-intensity levels than other models. These results prove the effectiveness of the proposed model in terms of predicting convective weather. This indicates that our proposed model provides a feasible solution for precipitation nowcasting. Extensive experiments also proved the effectiveness of the components of the proposed model. Full article