Improving Global Subseasonal to Seasonal Precipitation Forecasts Using a Support Vector Machine-Based Method

Subseasonal to seasonal (S2s) precipitation forecasts provide great potential for hydrological forecasting at an extended range. The study proposed a support vector machine (SVM) regression-based method to improve S2s precipitation forecasts from the European Center for Medium-Range Weather Forecasts (ECMWF) across the globe (60 degrees N to 60 degrees S). Results suggested that the SVM-based method significantly improved ECMWF daily precipitation forecasts in representing the spatiotemporal variation of precipitation with higher consistency and reduced errors when compared against observations. Furthermore, the SVM-based method enhanced the probabilistic skill of ECMWF forecasts, providing improved ranked probability skill score (RPSS) for real-time forecasts in 2020 (e.g., RPSSECMWF = -0.03 and RPSSrg3 = 0.08 for lead week 1). The most substantial improvement from the SVM-based method is witnessed in regions with complex terrains where ECMWF yielded the worst skill, such as the Andes mountain range, Congo River Basin, and the Tibet Plateau. However, the SVM-based post-processing method did not alter the characteristics of precipitation forecasts regarding climate zone and lead time. Both ECMWF and post-processed forecasts showed higher skill in the temperate and continental climate zones when the lead time is shorter than 2 weeks. In comparison, low-latitude regions exhibited higher predictability when the lead time is longer than 5 weeks, which is attributed to the slow variation of boundary conditions such as the El Nino-Southern Oscillation (ENSO).