S. Yusefzadeh; A. A. Nadiri
Abstract
Today Ground water is the main source of drinking, agriculture and other uses for humans. The demand for this critical and strategic natural resource increased with population growth and development of society. This increasing has been declining water resources and damage aquifers environment. Therefore, ...
Read More
Today Ground water is the main source of drinking, agriculture and other uses for humans. The demand for this critical and strategic natural resource increased with population growth and development of society. This increasing has been declining water resources and damage aquifers environment. Therefore, we need to manage aquifers and understanding the hydrogeological parameters to deal with the water crisis and prevent the distraction of aquifers. The one of most important parameter is hydraulic conductivity. Although, the ground water system is a complex system and estimation of hydrogeological parameters is associated with inherent uncertainty and also is costly and time consuming that usually done with classical methods such as laboratory tests, slug test, tracing test and pumping tests. So recently use artificial intelligence methods for estimation of hydraulic conductivity, reduced the uncertainty of this parameter and it adds up some accuracy. So that it can overcome on the shortcoming of classical methods. In this study, four artificial intelligence methods; mamdani fuzzy logic(MFL) system, sugeno fuzzy logic(SFL) system, Wavelet-neural network method and Least square support vector machine(LS-SVM) method were used as individual models to estimate the hydraulic conductivity by using of surface geophysical data in Maragheh-Bonab aquifer. Given that each these models based on their inherent properties, they presented good results in some parts of area. Therefore, for concurrent use of performance of all these models the nonlinear combination method as a supervised committee machine artificial intelligence (SCMAI) model were used to estimate the hydraulic conductivity in maragheh-bonab aquifer. The result of this model showed that this new combinational model has high performance than other single models that presented by using different evaluation criteria. Therefore, this model could also be used for estimation hydrogeological parameters in areas with high complexity. The SCMAI model was tested against 15 data. The RMSE and for SCMAI prediction were computed as 0.045 and 0.97, respectively. Comparing the error measure values with dose of individual models above, it is seen that SCMAI outperforms individual AI models with low RMSE and high values. This result implies that SCMAI model shows high performance for estimation the hydraulic conductivity values in the heterogeneous unconfined aquifer in Maragheh-Boanb plain.