A new data-driven model to predict monthly runoff at watershed scale: insights from deep learning method applied in data-driven model

Abstract

Accurate forecasting of mid to long-term runoff is essential for water resources management and planning. However, the traditional model can’t predict well and the precision of runoff forecast needs to be further improved. Here, we proposed a noval data-driven model called RLMD -SMA-GRU for mid to long-term runoff prediction in three hydrographic stations (Heishiguan, Baimasi and Longmenzhen) of Yiluo River Watershed (middle of China) using monthly runoff data from 2007 to 2022. The results showed that (1) the new data-driven model (RLMD -SMA-GRU) had the highest monthly runoff prediction accuracy. Both RLMD and SMA can improve the prediction accuracy of the model (NSE=0.9466). (2) The accuracy of Models in wet season outperformed in dry season. (3) The hydrological stations with large discharge and stable runoff sequence have better forecasting effect. The RLMD-SMA-GRU model has good applicability and can be applied to the monthly runoff forecast at watershed scale.