Research on Monthly Precipitation Prediction Based on the Least Square Support Vector Machine with Multi-Factor Integration

Accurate precipitation prediction is of great significance for regional flood control and disaster mitigation. This study introduced a model based on the least square support vector machine (LSSVM) optimized by genetic algorithm (GA). The was used to estimate each meteorological station over source region Yellow River (SRYE) in China 12 months. Ensemble empirical mode decomposition (EEMD) method select factors realize prediction, without dependence historical data as training set. results were compared with other, according determination coefficient (R2), mean absolute errors (MAE), root error (RMSE). show that sea surface temperature (SST) Niño 1 + 2 exerts largest influence accuracy SRYE (RSST2= 0.856, RMSESST= 19.648, MAESST= 14.363). It followed potential energy gravity waves (Ep) (T) have similar effects prediction. sensitive altitude influences accurate are easily obtained at high altitudes. provides new reliable research regions data.