Novel hybrid approaches based on evolutionary strategy for streamflow forecasting in the Chellif River, Algeria

In this study, the feedforward neural networks (FFNNs) were proposed to forecast the multi-day-ahead streamflow. The parameters of FFNNs model were optimized utilizing genetic algorithm (GA). Moreover, discrete wavelet transform was utilized to enhance the accuracy of FFNNs model’s forecasting. Therefore, the wavelet-based feedforward neural networks (WFFNNs-GA) model was developed for the multi-day-ahead streamflow forecasting based on three evolutionary strategies [i.e., multi-input multi-output (MIMO), multi-input single-output (MISO), and multi-input several multi-output (MISMO)]. In addition, the developed models were evaluated utilizing five different statistical indices including root mean squared error, signal-to-noise ratio, correlation coefficient, Nash–Sutcliffe efficiency, and peak flow criteria. Results provided that the statistical values of WFFNNs-GA model based on MISMO evolutionary strategy were superior to those of WFFNNs-GA model based on MISO and MIMO evolutionary strategies for the multi-day-ahead streamflow forecasting. Results indicated that the performance of WFFNNs-GA model based on MISMO evolutionary strategy provided the best accuracy. Results also explained that the hybrid model suggested better performance compared with stand-alone model based on the corresponding evolutionary strategies. Therefore, the hybrid model can be an efficient and robust implement to forecast the multi-day-ahead streamflow in the Chellif River, Algeria.