Amirkabir University of Technology AUT Journal of Civil Engineering 2588-2899 1 2 2017 12 01 Support Vector Machine to predict the discharge coefficient of Sharp crested w-planform weirs 195 204 2733 10.22060/ceej.2017.13005.5309 EN A. Parsaie Water Engineering Department, Lorestan University, Khorramabad, Iran 0000-0001-7312-0634 A. H. Haghiabi Water Engineering Department, Lorestan University, Khorramabad, Iran Journal Article 2017 06 11 In this paper, the discharge coefficient (Cd) of triangular labyrinth weir was predicted<br />using Multilayer Perceptron Neural Network (MLPNN), Radial Basis Neural Network (RBFNN) and<br />support vector machine (SVM). To this end, 223 data sets related to the effective parameters on Cd were<br />collected. Using dimensional analysis techniques, the involved dimensionless parameters on Cd were<br />derived. To find out the most effective parameters on Cd, the Gamma test (GT) was analyzed. Results of<br />GT demonstrated that H/P, Lw/Lc, and Lw/Wm are the most effective parameters on Cd. To develop ANN<br />and SVM, different types of transfer and kernel functions were tested. During the testing of transfer and<br />kernel functions for developing the ANN and SVM models, respectively, it was found that tensing and<br />RBFNN have the best performance for predicting the Cd. Overall evaluation of the results of developed<br />models indicated that both models have a suitable accuracy in predicting the Cd; however, the SVM is a<br />bit more accurate. Comparing the outcomes of the applied models in terms of DDR index shows that the<br />data dispersivity of SVM is less than the others; therefore, this model is more reliable. https://ajce.aut.ac.ir/article_2733_ec1f850d934f440cfa8e4a18d2cf5463.pdf