Moldeling Of Dissolved Solids By Using Hybrid Soft Computing Methods (Case Study: Nazluchay Basin)

Rivers has important roles in providing drinking and agricultural water supply. In this study, single and hybrid-wavelet methods of artificial neural networks, adaptive neuro fuzzy inference system and Gene expression programming were validated total dissolved solids modelling of Nazluchay Basin. Therefore, water quality data with 19 years length (1993-2011), four hydrometric stations at Nazluchay Basin, were used. After validating of data and selected stations, the data were analyzed by using Daubechies-4 wavelet transform. For modelling 80% of data for training and 20% of data for testing of the model were used. The evaluation of models performance is applied based on different statistical tests, correlation coefficient, and mean root of error squares and mean absolute error. The results indicate acceptable performance of all single and hybrid-wavelet methods of artificial neural networks, adaptive neuro fuzzy inference system and Gene expression programming for modeling the total dissolved solids in the Nazluchay basin. Based on WGEP, GEP, WANFIS, ANFIS-SC, WANN, ANFIS-GP and ANN have best performance, respectively. In addition Gene expression programming-wavelet hybrid model with the minimum RMSE amounted 21.078 has best performance compared with other single and hybrid models.