The potential of ensemble WT-EEMD-kernel extreme learning machine techniques for prediction suspended sediment concentration in successive points of a river

Sediment transport is one of the most important issues in river engineering. In this study, the capability of the Kernel Extreme Learning Machine (KELM) approach for predicting the river daily Suspended Sediment Concentration (SSC) and Discharge (SSD) was assessed. Three successive hydrometric stations of Mississippi river were considered and based on the sediment and flow characteristics during the period of 2005–2008. Several models were developed and tested for SSC and SSD modeling. For improving the applied model efficiency, two post-processing techniques, namely Wavelet Transform (WT) and Ensemble Empirical Mode Decomposition (EEMD), were used. Also, two states of modeling based on stations' own data (state 1) and previous stations' data (state 2) were considered. The single and integrated KELM model results comparison indicated that the integrated WT and EEMD-KELM models resulted in more accurate outcomes. Results showed that data processing with WT was more effective than EEMD in increasing the models' efficiency. Data processing enhanced the models' capability by up to 15%. The results showed that the state 1 modeling led to better results, however, using the integrated KELM approaches the previous stations data could be applied successfully for SSC and SSD modeling when the stations' own data were not available. HIGHLIGHT The suspended sediment concentration (SSC) and suspended sediment discharge (SSD) were predicted via artificial intelligence approach in successive hydrometric stations. The data pre-processing impacts on models' efficiency improvement was assessed. The sensitivity analysis showed the most effective subseries was obtained from pre-processing models.