Skillful Radar-Based Heavy Rainfall Nowcasting Using Task-Segmented Generative Adversarial Network
Rui Wang, Lin Su, Wai Kin Wong, Alexis K.H. Lau, Jimmy Chi Hung Fung
Abstract
Accurate and timely rainfall nowcasting is important for protecting the public from heavy rainfall-induced disasters. In recent years, deep-learning models have been demonstrated to significantly outperform traditional methods in heavy rainfall nowcasting. However, the performance of existing deep-learning-based nowcasting models is still restricted by limited forecast skill, and the rapid growth of blurriness increases in forecast time. In this work, we propose a novel heavy rainfall nowcasting model based on an innovative task-segmented architecture, namely the TS-RainGAN, consisting of two modules: the MaskPredNet predicts the spatial coverage of different rainfall categories to provide bounding for rainfall with various intensities, and the IntensityGAN predicts the intensity of rainfall based on the rainfall coverage produced by the MaskPredNet. The TS-RainGAN can accurately capture the spatiotemporal features and evolutions of rainfall systems and provide skillful precipitation prediction with high skill scores up to 2 hours compared with the results of the widely used baseline models. Meanwhile, the blurriness of the predicted images is significantly reduced. This enables district-level heavy rainfall nowcasting with competitive forecast skills.