A Decomposition-Ensemble Learning Model Based on LSTM Neural Network for Daily Reservoir Inflow Forecasting

Reservoir inflow forecasting is one of the most important issues in delicacy water resource management at reservoirs. Considering the non-linearity and of daily reservoir inflow data, a decomposition-ensemble learning model based on the long short-term memory neural network (DEL-LSTM) is developed in this paper for daily reservoir inflow forecasting. DEL-LSTM employs the logarithmic transformation based preprocessing method to cope with the non-stationary of the inflow data. Then, the ensemble empirical mode decomposition and Fourier spectrum methods are used to decompose the inflow data into the trend term, period term, and random term. For each decomposed term, a regression model based on the LSTM neural network is built to obtain the corresponding prediction result. Finally, the prediction results of the three items are integrated to get the final prediction result. Case studies on the Ankang reservoir in China have been conducted by using data from 1/1/1943 to 12/31/1971. Experimental results illustrated the superiority of the decomposition-ensemble framework and the LSTM neural network in forecasting daily reservoir inflow with big fluctuations. Comparing with some representative models, the proposed DEL-LSTM performs better in prediction accuracy, the average absolute percentage error is reduced to 13.11%, and the normalized mean square error is reduced by 4%, the coefficient of determination was increased by 5%.