The annual sediment load of a river is generally determined either from direct measurements of the sediment load throughout the year or from any of the many sediment transport equations that are available today. Due to lack of a long-term sediment concentration data, sediment rating curves and flux estimation are the most widely applied. This paper has investigated the abilities of statistical models to improve the accuracy of streamflow–suspended sediment relationships in daily and annual suspended sediment estimation. In this study, a comparison was made between suspended sediment rating curves and artificial neural networks (ANNs) for the El Kebir catchment. Daily water discharge and daily suspended sediment data from the gauging station of Ain Assel, were used as inputs and targets in the models which were based on the cascade-forward and feed-forward back-propagation using Levenberg–Marquardt and Bayesian regularization algorithms. The model results have shown that the ANN models have the highest efficiency to reproduce the daily sediment load and the global annual sediment yields. Our estimation based on the available data indicated that the areas along the El Kebir River have experienced high sediment fluxes that could have obvious impacts on the sediment trapping and siltation in the Mexa reservoir.