Physical‐Dynamic‐Driven AI‐Synthetic Precipitation Nowcasting Using Task‐Segmented Generative Model

Abstract

AbstractPrecise and timely rainfall nowcasting plays a critical role in ensuring public safety amid disasters triggered by heavy precipitation. While deep‐learning models have exhibited superior performance over traditional nowcasting methods in recent years, their efficacy is still hampered by limited forecasting skill, insufficient training data, and escalating blurriness in forecasts. To address these challenges, we present the Synthetic‐data Task‐segmented Generative Model (STGM), an innovative physical‐dynamic‐driven heavy rainfall nowcasting model. The STGM encompasses three key components: the Long Video Generation (LVG) model generating synthetic radar data from observed radar images and data provided by the Weather Research and Forecasting (WRF) model, MaskPredNet predicting the spatial coverage of various rainfall intensities, and SPADE determining rainfall intensity based on the coverage provided by MaskPredNet. The STGM has demonstrated promising skill for precipitation forecasts for up to six hours, and significantly reduce the blurriness of predicted images, thus showcasing advances in rainfall nowcasting.