PREDICTION OF BRIDGE PIER SCOUR USING GENETIC PROGRAMMING

This paper presents the use of genetic programming (GP) as a tool to predict pier scour depths based on clear-water conditions of laboratory measurements by past researchers. Four main dimensionless parameters-pier width, approaching flow depth, threshold flow velocity, and channel open-ratio-are considered for predicting the scour depth. The performance of the GP equation is verified by comparing the results with those obtained by empirical equations. It is found that the scour depth at bridge piers can be efficiently predicted using the GP model. The advantage of the GP model is confirmed by comparing the GP results of scour depths with the large-scale model studies and field data.