New secondary decomposition ensemble support vector regression for monthly drought index forecasting

Abstract

Drought prediction on a monthly timescale is conducive to the timely identification of drought characteristics and provides a reference for drought mitigation. Current research is generally based on drought indices on timescales of three months or more for drought prediction, whereas the presence of highly nonlinear and drastic changes in the characteristics of drought indices leads to suboptimal drought prediction for drought index sequences on monthly timescales. In this study, a secondary decomposition model based on extreme-point symmetric mode decomposition (ESMD), variational mode decomposition (VMD), and support vector regression (SVR) was investigated to predict a monthly-scale drought index. To evaluate the predictive ability of the model, it was applied to 100 meteorological stations in the Pearl River Basin of China and compared and analyzed using four comparative models. The results showed that the model proposed in this study has better performance index values, and the prediction accuracies of all stations are improved compared with the four comparative models, with the most significant improvement in the Nash–Sutcliffe efficiency (NSE) index value, followed by the root mean square error (RMSE) and mean absolute error (MAE) index values, and the smallest improvement in the Wilmot consistency index (WIA) index value. The monthly-scale drought quadratic decomposition (ESMD-VMD) combined prediction model established in this study provides a novel method for drought prediction.