Bedload transport predictions based on field measurement data by combination of artificial neural network and genetic programming

Abstract

Bedload transport is an essential component of river dynamics and estimation of its rate is important to many aspects of river management. In this study, measured bedload by Helley- Smith sampler was used to estimate the bedload transport of Kurau River in Malaysia. An artificial neural network, genetic programming and a combination of genetic programming and a neural network were used to estimate the bedload carried in Kurau River, based on bedload transport measurement data and hydraulic variables. A statistical analysis was carried out to validate methods by computing RMSE, MARE and inequality ratio (U). In general, the ability of the artificial neural network combined with genetic programming with R2 equal to 0.95, RMSE equal to 0.1 as a precipitation predictive tool for predicting the bedload transport rate was observed as being acceptable.