Deep Residual Network for Probabilistic Forecast of the Extended Range Persistent Extreme Precipitation

Based on the Subseasonal~to~Seasonal (S2S) datasets from four models (ECMWF, CMA, UKMO, and NCEP) and ground~observed precipitation data from April to September between 1997 and 2022, an improved Deep Residual Network (ResNet) model was developed for extended~range probabilistic forecasting of Persistent Extreme Precipitation (PEP). The deterministic and probabilistic forecasts of the improved ResNet model were compared with five other methods—single~model ensemble (EC), multi~model ensemble (MME), principal component regression (PCR), and Bayesian model averaging (BMA)—over eastern China. The results demonstrated that the improved ResNet model outperformed other methods in probabilistic forecasting. The enhanced performance of the ResNet model is attributed to the improvement in spatial correlation coefficients, which stems from its ability to deeply extract PEP features from the ECMWF S2S data and the optimization of the ResNet network structure. As a result, the improved ResNet model achieves a positive Brier Skill Score (BSS) for forecast lead times of up to 30 days, highlighting its significant potential for extended~range probabilistic forecasting of PEP in eastern China.