Global Precipitation Nowcasting of Integrated Multi-satellitE Retrievals for GPM: A U-Net Convolutional LSTM Architecture

Abstract This paper presents a deep supervised learning architecture for 30 min global precipitation nowcasts with a 4-hour lead time. The architecture follows a U-Net structure with convolutional long short-term memory (ConvLSTM) cells empowered by ConvLSTM-based skip connections to reduce information loss due to the pooling operation. The training uses data from the Integrated MultisatellitE Retrievals for GPM (IMERG) and a few key drivers of precipitation from the Global Forecast System (GFS). The impacts of different training loss functions, including the mean-squared error (regression) and the focal-loss (classification), on the quality of precipitation nowcasts are studied. The results indicate that the regression network performs well in capturing light precipitation (<1.6 mm hr−1) while the classification network can outperform the regression counterpart for nowcasting of high-intensity precipitation (>8 mm hr−1), in terms of the critical success index (CSI). It is uncovered that including the forecast variables can improve precipitation nowcasting, especially at longer lead times in both networks. Taking IMERG as a relative reference, a multi-scale analysis, in terms of fractions skill score (FSS), shows that the nowcasting machine remains skillful for precipitation rate above 1 mm hr−1 at the resolution of 10 km compared to 50 km for GFS. For precipitation rates greater than 4 mm hr−1, only the classification network remains FSS-skillful on scales greater than 50 km within a 2-hour lead time.