performance evaluation of artificial intelligence models in estimating the discharge coefficient of labyrinth weirs with semicircular crests

In this study, the performance of ann and svm in estimation of the discharge coefficient of the labyrinth weirs with semicircular crests was investigated. for this purpose, 454 experimental data were used. dimensionless parameters of ht/p, l/w, w/p, and a were introduced as inputs and cd parameters as outputs in the models. the performance of the ann model with rmse, r and, dc was 0.019, 0.971 and 0.971 respectively more acceptable and closer to the experimental data than the svm model.