estimating suspended sediment by artificial neural network (ann), decision trees (dt) and sediment rating curve (src) models (case study: lorestan province, iran)

the aim of this study was to estimate suspended sediment by the ann model, dt with cart algorithm and different types of src, in ten stations from the lorestan province of iran. the results showed that the accuracy of ann with levenberg-marquardt back propagation algorithm is more than the two other models, especially in high discharges. comparison of different intervals in models showed that running models with monthly data,resulted in smaller error and better estimated results. moreover, results showed that using minimum variance unbiased estimator (mvue) bias correction factor modified the src results, especially in monthly time steps in almost all stations. hence, it can be said that if because of advantages such as simplicity, src models are preferred, it is better that msrc (modified sediment rating curve) is used in monthly period.