Search for: All records

Machine learning‐based approaches demonstrate a significant potential in radar quantitative precipitation estimation (QPE) applications. In contrast to conventional methods that depend on local raindrop size distributions, deep learning (DL) can establish an effective mapping from three‐dimensional radar observations to ground rain rates. However, the lack of transparency in DL models poses challenges toward understanding the underlying physical mechanisms that drive their outcomes. This study aims to develop a DL‐based QPE system and provide a physical explanation of radar precipitation estimation process. This research is designed by employing a deep neural network consisting of two modules. The first module is a quantitative precipitation estimation network that has the capability to learn precipitation patterns and spatial distribution from multidimensional polarimetric radar observations. The second module introduces a quantitative precipitation estimation shapley additive explanations method to quantify the influence of each radar observable on the model estimate across various precipitation intensities.

 

Real-time and accurate precipitation estimation is critical for environmental protection and water resources management. Compared to traditional methods, i.e., radar reflectivity (Z) and rainfall rate (R) relations, relying on local raindrop size distributions, the deep learning model can fit the functional relationship between radar observations and rainfall rate measurements. However, the black-box nature of deep learning models makes it difficult to explain the physical mechanisms behind their results. To address this problem, this study proposes DQPENet, a deep learning model for polarimetric radar QPE utilizing dense blocks. We employ a permutation test to understand the relative importance of different radar data input variables. Additionally, we propose a regression importance value (RIV) method for the precipitation estimation task to visualize feature importance regions. Our experimental results show that radar reflectivity and specific differential phase at the lowest elevation angle are the two most important observables for the model’s precipitation estimation. Furthermore, we find that radar data closer to the rain gauge are more influential on the model’s results, indicating that the deep learning model is able to capture the underlying physical mechanism of atmospheric data. 

The task of nowcasting by deep learning using multivariate, rather than just reflectivity, is limited by poor interpretability. The previous experiment designed MCT (Multivariate Channel Transformer), a deep learning model capable of nowcasting with dual-polarization radar data. Four analytical methods are designed to further explore the contribution of polarization parameters: (i) Case studies of different meteorological processes. (ii) A permutation test ranking the significance of each variable. (iii) Visualization of the feature maps obtained by forward propagation of the input data. (iv) Data downscaling of polarimetric radar data. The results show that the polarization parameters serve as a guide to predict the location and shape of strong reflectivity, as well as the energy retention of strong echoes at 40-50 dBZ. The contributions of Zdr and Kdp are more evident in the prediction results after 30 min, and the importance of Kdp exceeds that of Zdr in case of strong convective weather. 

Research on nowcasting through dual-polarization weather radar data using deep learning approach is rare but worth exploring. This paper lightens a previous work, the MCT (Multivariate Channel Transformer) model, which leads to the design of the MSF (Multivariate Swin Fusion) model. The commonalities between the two are as follows: on one hand, both fuses several dual-polarization observables including reflectivity (Z), specific differential phase (Kdp ), and differential reflectivity (Zdr ) to more comprehensively consider meteorological particle features; on the other hand, they introduces the attention mechanism to more fully fuse multi-frame, multi-variate, and multi-scale features. In the experimental evaluation, this study first selects observation data from KMLB radar in FL, USA, and uses traditional optical flow method, deep learning TrajGRU method, etc. as controls. The results show that both MCT and MSF perform better than the control, and the 60min forecast scores of both are 8.78/9.31 for RMSE and 0.46/0.18/0.07 for CSI (20/35/45dBZ), and this conclusion is verified by case study. Further, the role of the attention mechanism is verified by ablation experiments. 

Accurate estimation of surface precipitation with high spatial and temporal resolution is critical for decision making regarding severe weather and water resources management. Polarimetric weather radar is the main operational instrument used for quantitative precipitation estimation (QPE). However, conventional parametric radar QPE algorithms such as the radar reflectivity (Z) and rain rate (R) relations cannot fully represent clouds and precipitation dynamics due to their dependency on local raindrop size distributions and the inherent parameterization errors. This article develops four deep learning (DL) models for polarimetric radar QPE (i.e., RQPENetD1, RQPENetD2, RQPENetV, RQPENetR) using different core building blocks. In particular, multi-dimensional polarimetric radar observations are utilized as input and surface gauge measurements are used as training labels. The feasibility and performance of these DL models are demonstrated and quantified using U.S. Weather Surveillance Radar - 1988 Doppler (WSR-88D) observations near Melbourne, Florida. The experimental results show that the dense blocks-based models (i.e., RQPENetD1 and RQPENetD2) have better performance than residual blocks, RepVGG blocks-based models (i.e., RQPENetR and RQPENetV) and five traditional Z-R relations. RQPENetD1 has the best quantitative performance scores, with a mean absolute error (MAE) of 1.58 mm, root mean squared error (RMSE) of 2.68 mm, normalized standard error (NSE) of 26%, and correlation of 0.92 for hourly rainfall estimates using independent rain gauge data as references. These results suggest that deep learning performs well in mapping the connection between polarimetric radar observations aloft and surface rainfall. 

Tornadoes, as highly destructive weather events, require accurate detection for effective decision‐making. Traditional radar‐based tornado detection algorithms (TDA) face challenges with limited tornado feature extraction capabilities, leading to high false alarm rates and low detection probabilities. This study introduces the Multi‐Task Identification Network (MTI‐Net), leveraging Doppler radar data to enhance tornado recognition. MTI‐Net integrates tornado detection and estimation tasks to acquire comprehensive spatial and locational information. As part of MTI‐Net, we introduce a novel backbone network of Multi‐Head Convolutional Block (MHCB), which incorporates Spatial and Channel Attention Units (SAU and CAU). SAU optimizes local tornado feature extraction, while CAU reduces false alarms by enhancing dependencies among input variables. Experiments demonstrate the superiority of MTI‐Net over TDA, with a decrease in false alarm rates from 0.94 to 0.46 and an increase in hit rates from 0.23 to 0.81, highlighting the effectiveness of MTI‐Net in handling small‐scale tornado events.