Polarimetric Radar Quantitative Precipitation Estimation Using Deep Convolutional Neural Networks

Accurate estimation of surface precipitation with high spatial and temporal resolution is critical for decision-making regarding severe weather and water resources management. A 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 dependence on local raindrop size distributions and the inherent parameterization errors. This article develops four deep learning (DL) models for polarimetric radar QPE (i.e., RQPENet(D1), RQPENet(D2), RQPENet(V), and RQPENet(R)) using different core building blocks. In particular, multidimensional 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, FL, USA. The experimental results show that the dense blocks-based models (i.e., RQPENet(D1) and RQPENet(D2)) have better performance than residual blocks, RepVGG blocks-based models (i.e., RQPENet(R) and RQPENet(V)), and five traditional $Z$ - $R$ relations. RQPENet(D1) 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 DL performs well in mapping the connection between polarimetric radar observations aloft and surface rainfall.