Improved monthly runoff time series prediction using the SOA-SVM model based on ICEEMDAN-WD decomposition

In runoff prediction, the prediction accuracy is often affected by the non-linear and non-stationary characteristics of the runoff series. In this study, a coupled forecasting model is proposed that decomposes the original runoff series by an improved complete ensemble EMD (ICEEMDAN) combined with a wavelet decomposition (WD) and then forecasts the monthly runoff using a support vector machine (SVM) optimized by the seagull optimization algorithm (SOA). In this method, a series of IMF and a Res are obtained by decomposing the original runoff series with ICEEMDAN. The WD method is used to perform quadratic decomposition of high-frequency components decomposed by the ICEEMDAN method to make the runoff series as smooth as possible. Then the decomposed components are input into the SOA-SVM model for prediction. Finally, the prediction results of each component are superimposed and reconstructed to obtain the final monthly runoff prediction results. RMSE, MAPE, NSEC and R are selected to evaluate the prediction results and the model is compared with the SOA-SVM, EMD-SOA-SVM and CEEMDAN-SOA-SVM models. The proposed model is applied to the monthly runoff forecast of the Hongjiadu and Manwan Reservoirs. When compared with other benchmarking models, the ICEEMDAN-WD-SOA-SVM model attains the smallest RMSE and MAPE and the largest NSEC and R. The ICEEMDAN-WD-SOA-SVM model has the best prediction effect, the highest prediction accuracy and the lowest prediction error.

Automated summary

In this study, a coupled forecasting model combining ICEEMDAN, WD, and SVM optimized by SOA is proposed to predict monthly runoff. The model decomposes the original runoff series using ICEEMDAN and WD to obtain IMF and Res components, which are then input into the SOA-SVM model for prediction. The ICEEMDAN-WD-SOA-SVM model achieves the smallest RMSE and MAPE and the largest NSEC and R compared to other benchmarking models, demonstrating its superior prediction accuracy.