DYffCast: Regional Precipitation Nowcasting Using IMERG Satellite Data. A case study over South America

Climate change is increasing the frequency of extreme precipitation events, making weather disasters such as flooding and landslides more likely. The ability to accurately nowcast precipitation is therefore becoming more critical for safeguarding society by providing immediate, accurate information to decision makers. Motivated by the recent success of generative models at precipitation nowcasting, this paper: extends the DYffusion framework to this task and evaluates its performance at forecasting IMERG satellite precipitation data up to a 4-hour horizon; modifies the original DYffusion framework to improve its ability to model rainfall data; and introduces a novel loss function that combines MAE, MSE and the LPIPS perceptual score. In a quantitative evaluation of forecasts up to a 4-hour horizon, the modified DYffusion framework trained with the novel loss function outperforms three competitor models. It has the highest CSI scores for weak, moderate and heavy rain thresholds and retains an LPIPS score < 0.2 for the entire roll-out, degrading the least as lead-time increases. The proposed nowcasting model demonstrates visually stable and sharp forecasts up to a 2-hour horizon on a heavy rain case study.