Evaluation of Genetic Expression Programming model for Suspended Sediment Load estimation based on data preprocessing using Gamma Test method (Case study: Rood Zard watershed)

In this research, the data of the machine hydrometric station was used in the Rood Zard watershed with a statistical period of 36 years (1977-2012). In order to reduce time and cost, pre-processing of input data into the GEP model was obtained using gamma test method and entered the GEP model along with non-preprocessing combinations of the test and error method. The results of comparison between all models showed that the best combination of input variable from gamma test with the lowest standard error is zero, gamma statistic is 0.000092 and Vratio statistic is 0.012 and the combination of variables including average daily flow discharge with two steps of time delay and average daily precipitation with three steps of time delay, had the most accurate and correct estimate for suspended sediment load. This model had the lowest value of RMSE=1671.90 (ton/day) and MAE=475.68 (ton/day) and the highest value of R2=0.99 and NSE=0.99 compared to other models. Therefore, the use of gamma test method as a data preprocessing method, by selecting combinations of appropriate input variables to models, an average of up to 40% of the estimated error (RMSE) of daily suspended sediment load compared to the inputs from the test and reduce the error and increase the performance of the GEP model in estimating the suspended sediment load by increasing the similarity between the values of observational data with computational data.