Investigation of possibility of suspended sediment prediction using the combination of sediment rating curve and artificial neural network (case study: Ghatorchai river, Yazdakan bridge)

The estimation of sediment loads in rivers is one of the most important and difficult part of sediment transport studies and river engineering. Then، accessing the new methods (that can be effective in this background)، are more important and weird. In this research، using the artificial neural network (ANN) for optimization of the results of sediment rating curve (SRC) has been investigated to predict the suspended sediment loads. For doing that، the Yadakan station on Ghatoor-Chai River was considered. An equation by SRC method was obtained and then an ANN method by the same data was used and finally by combining them، the new model was built. It should be mentioned that before using the combined model، each method was used and the obtained results were compared with the observed data. Based on this research، the results of using the combined model is more precise than the using ANN and SRC separately as the Dr value from 1. 402 (in SRC) and -2. 395 (in ANN) is changed to 0. 963 in combined model. The RMSE has also obtained 692. 286 and 616. 96 for SRC and ANN respectively while this value is decreased to 603. 094 for combined model.