Deep Learning for Polarimetric Radar Quantitative Precipitation Estimation during Landfalling Typhoons in South China

Heavy rain associated with landfalling typhoons often leads to disasters in South China, which can be reduced by improving the accuracy of radar quantitative precipitation estimation (QPE). At present, raindrop size distribution (DSD)-based nonlinear fitting (QPE(DSD)) and traditional neural networks are the main radar QPE algorithms. The former is not sufficient to represent the spatiotemporal variability of DSDs through the generalized Z-R or polarimetric radar rainfall relations that are established using statistical methods since such parametric methods do not consider the spatial distribution of radar observables, and the latter is limited by the number of network layers and availability of data for training the model. In this paper, we propose an alternative approach to dual-polarization radar QPE based on deep learning (QPENet). Three datasets of "dual-polarization radar observations-surface rainfall (DPO-SR)" were constructed using radar observations and corresponding measurements from automatic weather stations (AWS) and used for QPENet(V1), QPENet(V2), and QPENet(V3). In particular, 13 x 13, 25 x 25, and 41 x 41 radar range bins surrounding each AWS location were used in constructing the datasets for QPENet(V1), QPENet(V2), and QPENet(V3), respectively. For training the QPENet models, the radar data and AWS measurements from eleven landfalling typhoons in South China during 2017-2019 were used. For demonstration, an independent typhoon event was randomly selected (i.e., Merbok) to implement the three trained models to produce rainfall estimates. The evaluation results and comparison with traditional QPE(DSD) algorithms show that the QPENet model has a better performance than the traditional parametric relations. Only when the hourly rainfall intensity is less than 5 mm (R < 5 mm center dot h(-1)), the QPE(DSD) model shows a comparable performance to QPENet. Comparing the three versions of the QPENet model, QPENet(V2) has the best overall performance. Only when the hourly rainfall intensity is less than 5 mm (R < 5 mm center dot h(-1)), QPENet(V3) performs the best.