Application of machine learning models in predicting discharge coefficient of side B-type piano key weir

Abstract

Side weir is a hydraulic structure within a channel which is usually used to discharge excess water, to divert the flow, and to regulate water surface levels in rivers and irrigation and drainage networks. In general, piano key weirs (PKW) have been used as weirs perpendicular to the flow direction in straight channels. However, the use of the PKW as a side weir in the outer arch of the channels is a new approach to enhance the weir's performance. In this study, 289 tests were first performed on the B-type rectangular side piano key weir (RSPKW) at two arc angles of 30 and 120°. Then, Fuzzy Inference System (FIS), Adaptive Neuro-Fuzzy Inference System (ANFIS), ANFIS and Teaching Learning Based Optimization (TLBO), ANFIS and Grasshopper Optimization Algorithm (GOA), Extreme Learning Machine (ELM) and Outlier Robust ELM (ORELM) models were used to predict the weir discharge coefficient. The results showed that two optimization models of TLBO and GOA increased the accuracy of the ANFIS model. The results showed that the ANFIS-GOA model has accuracy of Root Mean Squared Error (RMSE) = 0.0361, Coefficient of determination (R²) = 0.9772, and Kling Gupta coefficient (KGE) = 0.9858. The ANFIS-TLBO, ANFIS, and FIS models were ranked, respectively. Also, the results showed that ELM and ORELM models have accuracy close to ANFIS-GOA and can be a suitable alternative for complex fuzzy models. According to the statistical analysis, it was found that the parameters of the ratio of weir height to flow depth at the upstream edge of weir (P/h₁), arc angle (α), and the ratio of height of the foundation to the main channel width (p_d/B) had the greatest role in the development of the models, respectively.