M5 model tree for pier scour prediction using field dataset

Abstract

This paper investigates the potential of M5 model tree, a tree based regression approach to predict the local scour around bridge piers using field dataset. The dataset consisting of 232 pier scour measurements were used. Out of the total dataset, 154 measurements were used to train M5 model tree and the remaining 78 to test the trained model. Comparison of results with four predictive equations suggests an improved performance by M5 model tree in predicting the pier scour depth with dimensioned data and found it performing equally well to a back propagation neural network. A sensitivity analysis with field dataset indicates that the pier width, depth and flow velocity are important factors in predicting the scour depth with M5 model tree. Furthermore, M5 model tree based regression approach provides a linear regression function that can be used by field engineers to predict the pier scour.