Bayesian extreme learning machines for predicting discharge coefficient of A-type piano key weir

In this study, three machine learning based techniques for prediction of discharge coefficient of an A-type Piano Key Weir (PK-Weir) located on the straight open channel flume were considered. These techniques are consisted of Least Square Support Vector Machine (LS-SVM), Extreme Learning Machine (ELM) and Bayesian ELM (BELM). For this purpose, 70 laboratory test results are used for determining discharge coefficient of PK-Weir for a wide range of discharge values. Root Mean Squared Error (RMSE), Nash–Sutcliffe model efficiency coefficient (NSE) and Threshold Statistics (TS) are used for comparing the performance of the models. The simulation results indicate that an improvement in predictive accuracy could be achieved by the ELM approach in comparison with LSSVM (RMSE of 0.016 and NSE of 0.986) while the BELM model’s generalization capacity enhanced, with RMSE of 0.011and NSE of 0.989 in testing dataset.