Monthly discharge forecasting using wavelet neural networks with extreme learning machine

Accurate and reliable hydrological forecasting is essential for water resource management. Feedforward neural networks can provide satisfactory forecast results in most cases, but traditional gradient-based training algorithms are usually time-consuming and may easily converge to local minimum. Hence, how to obtain more appropriate parameters for feedforward neural networks with more precise prediction within shorter time has been a challenging task. Extreme learning machine (ELM), a new training algorithm for single-hidden layer feedforward neural networks (SLFNs), has been proposed to avoid these disadvantages. In this study, a conjunction model of wavelet neural networks with ELM (WNN-ELM) is proposed for 1-month ahead discharge forecasting. The A trous wavelet transform is used to decompose the original discharge time series into several sub-series. The sub-series are then used as inputs for SLFNs coupled with ELM algorithm (SLFNs-ELM); the output is the next step observed discharge. For comparison, the SLFNs-ELM and support vector machine (SVM) are also employed. Monthly discharge time series data from two reservoirs in southwestern China are derived for validating the models. In addition, four quantitative standard statistical performance evaluation measures are utilized to evaluate the model performance. The results indicate that the SLFNs-ELM performs slightly better than the SVM for peak discharge estimation, and the proposed model WNN-ELM provides more accurate forecast precision than SLFNs-ELM and SVM.