Forecasting of runoff in the lower Yellow River based on the CEEMDAN–ARIMA model

Abstract

Abstract Runoff is one of the important hydrological variables of rivers, and its accurate prediction can provide a reliable basis for water resources system characterization and efficient utilization. In this paper, based on the advantages that the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) model can effectively overcome modal mixing and white noise interference, and the Auto-Regressive Integrated Moving Average (ARIMA) model can effectively overcome gradient disappearance and other problems, the coupled CEEMDAN–ARIMA prediction model is established, and the CEEMDAN–ARIMA model is used in the runoff prediction of the Lijin hydrological station in the lower Yellow River. The results show that the coupled CEEMDAN–ARIMA model has an R2 of 0.9398 and a Nash efficiency coefficient (NSE) of 0.918, with a prediction accuracy of Grade A. This shows that the CEEMDAN–ARIMA model has the ability to handle complex information in hydrological factor simulations, providing a new method for non-linear, non-stationary runoff prediction that has broad application prospects.