Mohammad K. Ayoubloo, Hazi Md. Azamathulla, Zulfequar Ahmad, Aminuddin Ab. Ghani, Javad Mahjoobi, and Amin Rasekh
CART, model tree, scour, soft computing, spillways, svm, neural networks
Scour of bed in downstream of a ski-jump spillway is a critical
phenomenon that can endanger the spillway stability. The present
paper deals with application of soft computing techniques like
classiﬁcation and regression tree (CART), support vector machine
(SVM) and M5 for the prediction of downstream scour of the
spillways. The results of testing data set present CART model
as the best among the other computing methods. The results of
models showed that CART produces better prediction of the scour
in the downstream of the spillway compared to other techniques.
However, the other techniques are better than the available empirical
relationships for the prediction of scour.