mozhgan dehghani

In this study, effectiveness of the intelligent method of ANFIS-FCM adaptive fuzzy neural inference system to predict the electrical conductivity in groundwater due to physical and chemical parameters in the Rayen plain was evaluated. To achieve this, 29 water samples were taken from wells and springs across the plain and the data were chemically analyzed in the laboratory. Descriptive statistics of data and the correlation matrix of the studied parameters were obtained using SPSS software. By forming a correlation matrix, it was found that the potassium (K+), sodium (Na+), calcium (Ca2+), magnesium (Mg2+), chlorine (Cl-), sulfate (SO42-), total soluble solids (TDS), total hardness (TH), compared to other available parameters, have the highest correlation with electrical conductivity (EC). Therefore, the model inputs included the mentioned parameters and electrical conductivity was also selected as the output according to the research purpose. After standardization, the data were entered into MATLAB environment and the electrical conductivity of groundwater was predicted using ANFIS-FCM method. In this method, 70% of the data (20 samples) were selected as the training data set and 30% of the data (9 samples) for the test data set. For the training data set of ANFIS-FCM model, R2 and RMSE values were 0.99994, 0.0001569, respectively, and also for test data set of ANFIS-FCM model, 0.9844 and 0.041652 were resulted for R2 and RMSE, respectively. Using the results of this model, it was found that the estimated electrical conductivity 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 to estimate the electrical conductivity of water.

In this study, in order to investigate the contamination of surface sediments in west and southwest rivers of Lake Urmia, 20 surface samples were taken from a depth of 0-10 cm. After passing the samples through a 2 mm sieve, the total amount of heavy metals was obtained by ICP-OES. Then the geo-accumulation index (Igeo), enrichment index (EF) and pollution index (PI) of metals was calculated. Based on the results, geo-accumulation indices of nickel, cobalt, chromium, arsenic and cadmium in all sediments are in the risk range of extremely high (1<I_geo<2) or high (I_geo>2). Nickel enrichment coefficient in Barandozchai and Gadarchai sediments is extremely high (EF>40) and in Shahrchai, Mahabadchai, Nazluchai and Simineh rivers in very high pollution range (20<EF<40). Arsenic enrichment coefficient in all sediments shows very high pollution. The enrichment index for cadmium, copper, cobalt and chromium indicates high pollution in almost all rivers and it is moderate to high for zinc. Arsenic shows the highest average for contamination index in Nazluchai deposits. Statistical correlation matrix shows the highest correlation between cobalt and chromium with nickel because of their common geogenic origin and the significant correlation between nickel and sand indicates the natural origin of the element. The correlation between zinc and organic matter and clay is significant and probably due to zinc uptake by clay and organic matter. There is a significant relationship between arsenic and cadmium. Principal component analysis indicates 4 sources for the studied heavy metals, the first 4 components with specific values higher than 1, determine more than 85% of data variance. In the first component, nickel and chromium along with sand have the highest weight. Zinc and copper are in second component along with pH, cadmium and arsenic in third component and organic matter and lead in fourth component have the highest weight.

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.

In the last decade, Poisson regression has been used for modeling count response variables. Poisson regression is not a suitable choice when count data bears superfluity of zero numbers. In this article, two models zero-inflated Poisson regression and bivariate zero-inflated Poisson regression with random effect are used to modeling count responses with a superfluity of zero numbers. Usually, distribution of the random effect is considered normal, but we intend to employ more flexible skew-normal distribution for the distribution of the random effect. Finally, the purpose model is applied to data which as obtained from the Shahid Chamran University of Ahvaz concerning the number of failed courses and fail grade point average semesters. we used a simulation method to verify parameter estimations.