A comparison of artificial intelligence approaches in predicting discharge coefficient of streamlined weirs

Abstract

In the present research, three different data-driven models (DDMs) are developed to predict the discharge coefficient of streamlined weirs (Cdstw). Some machine-learning methods (MLMs) and intelligent optimization models (IOMs) such as Random Forest (RF), Adaptive Neuro-Fuzzy Inference System (ANFIS), and gene expression program (GEP) methods are employed for the prediction of Cdstw. To identify input variables for the prediction of Cdstw by these DMMs, among potential parameters on Cdstw, the most effective ones including geometric features of streamlined weirs, relative eccentricity (λ), downstream slope angle (β), and water head over the crest of the weir (h1) are determined by applying Buckingham π-theorem and cosine amplitude analyses. In this modeling, by changing architectures and fundamental parameters of the aforesaid approaches, many scenarios are defined to obtain ideal estimation results. According to statistical metrics and scatter plot, the GEP model is determined as a superior method to estimate Cdstw with high performance and accuracy. It yields an R2 of 0.97, a Total Grade (TG) of 20, RMSE of 0.032, and MAE of 0.024. Besides, the generated mathematical equation for Cdstw in the best scenario by GEP is likened to the corresponding measured ones and the differences are within 0–10%. HIGHLIGHT The discharge coefficient of streamlined weirs (Cdstw) was analyzed using intelligent models.; Random forest (RF), adaptive neuro-fuzzy inference system (ANFIS), and gene expression programming (GEP) methods are used and compared for predicting Cdstw.; The GEP model has been identified as a superior method for estimating Cdstw with high performance and accuracy.;

Keywords

• discharge coefficient
• intelligent optimization models
• joukowsky transform
• machine-learning models
• open-channel flow
• streamlined weirs