Skillful Radar-Based Heavy Rainfall Nowcasting Using Task-Segmented Generative Adversarial Network

Rui Wang, Lin Su, Wai Kin Wong, Alexis Kai-Hon Lau, Jimmy C. H. 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 skills 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 mask prediction network (MaskPredNet) predicts the spatial coverage of different rainfall categories to provide bounding for rainfall with various intensities and the mask-to-intensity translation generative adversarial network (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 h 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.