Monitoring of groundwater quality parameters using adaptive neural-fuzzy inference system (ANFIS) method(Case study: Ardabil plain)

Proper modeling of groundwater quality is an important planning and decision-making tool in water resources management. In this study, in order to model the changes in groundwater quality variables in Ardabil plain, data from 60 wells in May 2013 were used. The data were chemically analyzed in the University Jihad Laboratory by West Azerbaijan Province. Descriptive statistics of data and the correlation matrix of the studied parameters were obtained using SPSS software. The qualitative parameters studied in this paper are: EC, TDS and TH. After standardization, the data were entered into MATLAB environment and groundwater parameters were predicted using ANFIS-FCM method. In this method, 70% of the data (42 samples) for the training data set and 30% of the data (18 samples) for the test data set were randomly selected. For ANFIS-FCM model training data set, EC values (R2 = 0.9142, MSE = 0.009391), TDS (R2 = 0.9703, MSE = 0.00515), TH (R2 = 0.9741, 0.00388 = MSE values were also obtained for the ANFIS-FCM model test data set (EC = 0.987, R2 = 0.003383, MSE), TDS (R2 = 0.8381, MSE = 0.00510), TH (= 0.625). R2 (MSE = 0.072) was obtained. Using the results obtained from this model, it was found that the estimated groundwater parameters in the study area had very good accuracy and high correlation with the measured values. As a result, the ANFIS-FCM intelligent method is an effective, efficient and accurate method for estimating the physical and chemical parameters of water.