Prediction of hourly inflow for reservoirs at mountain catchments using residual error data and multiple-ahead correction technique

Abstract

This study coupled the ensemble learning method with residual error (RE) correction to propose a more accurate hydrologic model for the time-series prediction of the reservoir inflow. To enhance the prediction capability of the model in mountain catchments, three deep learning (DL) models, namely the encoder–decoder gated recurrent units (ED-GRU), encoder–decoder long short-term memory network (ED-LSTM), and combined convolutional neural network with LSTM (CNN-LSTM), were deployed to train reservoir inflow prediction model for the lead times of 1–24 h. The prediction outputs from three DL models were then incorporated into the categorical gradient boosting regression (CGBR) model to resolve the highly non-linear relationship between model inputs and outputs. In the final procedure, the RE correction method was implemented by using the outcomes of the CGBR model to construct the proposed hybrid model. The proposed model was applied to simulate the hourly inflow in the Shihmen and Feitsui Reservoirs. The proposed model achieved improved performance by an average proportion of 66.2% compared to the three DL models. It is demonstrated that the proposed model is accurate in predicting the reservoir peak and total inflows and also performs well for storm events with multi-peak hydrographs. HIGHLIGHTS An augmented hydrologic model is proposed by integrating ensemble learning with residual error correction methods.; The proposed model can accurately simulate the reservoir inflow with multi-peak and prolonged periods.; The overall improved accuracy for the lead times of 1–24 h was obtained by an averaging factor of 66.2%.;

Keywords

• convolutional neural network
• deep learning
• ensemble learning
• long short-term memory network
• reservoir inflow
• residual error correction