Using of gene expression programming method for prediction of daily components of tidal cycle in tidal rivers

The forecasting of tide or ebb elevation is a conventional issue. However, prediction of different components of tidal cycle in tidal rivers is a new aspect in geology and river engineering. For this purpose, this study utilizes the Gene Expression Programming (GEP) method in the Khosro-Abad, Khorramshahr, and Arvand Rood tidal stations (from 2001 to 2008). For short-term forecasts, normality and stationary of data time series are necessary. Existence of trends and skewness reduces accuracy of short-term predictions. Therefore, the modified Mann-Kendall trend test (MK3) method was applied and this test did not show any significant trend in daily tidal data time series. Due to the large skewness in a number of data time series, the Box-Cox transformation function was applied for minimization of skewness coefficient. Then, Augmented Dickey-Fuller (ADF) and Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) tests showed that different normalized tidal data time series are stationary. The autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams illustrate that maximum number of effective lags is 3 days and the GEP must use data of 1 to 3 days ago. The GEP method stated different equations for forecasting of different components of tidal cycle in three tidal stations. By comparison between observed data and predicted values by these derived equations, it is observed that the range of R and root mean square error (RMSE) are from 0.867 to 0.944 and from 0.058 to 0.149 m.