Estimation of Daily Suspended Sediment Load by Using Wavelet Conjunction Models

Abstract

Accurate estimation of sediment loads is important for the management and construction of water resources projects. In the first part of this study, the convenient gene expression programming (GEP), neuro-fuzzy (NF), and artificial neural network (ANN) techniques were applied to estimate suspended sediment loads by using recorded daily river discharge and sediment load data. These models were compared with one another in terms of the coefficient of determination, root mean square error, mean absolute error, variance accounted for, and Nash-Sutcliffe statistic criteria. It was found that the GEP model performed better than the NF and ANN models. In the second part of this study, the discrete wavelet conjunction models with convenient GEP, NF, and ANN techniques were constructed and compared with one another. Comparison results indicated that the wavelet conjunction models significantly increased the accuracy of single GEP, NF, and ANN models in suspended sediment estimation. The wavelet-GEP model performed better than the wavelet-NF and wavelet-ANN models.