نویسندگان | محمد ساکی زاده-روح اله میرزایی محمد آبادی-هادی قربانی |
---|---|
نشریه | ENVIRON EARTH SCI |
تاریخ انتشار | ۰-۰-۰۱ |
نمایه نشریه | ISI ,SCOPUS |
چکیده مقاله
To identify the principal geochemical processes controlling groundwater quality in eastern part of Semnan Province, a total of 257 groundwater samples from wells and springs were collected. Since groundwater is the only source of water for various purposes, preservation of the quality of available groundwater resources in this region is of great importance. The order of abundance of anions was Cl−>SO42−>HCO3−>NO3−>F−, and for them the average values were 509.41, 404.24, 120.48, 14.51, 0.59 mg/l, respectively. On the other hand, for cations, Na+ and Ca2+ with average values of 442.10 and 135.09 mg/l were the most abundant parameters. Geochemical characteristics based on bivariate diagrams indicated that Na release from silicate weathering is an important process whereas the dissolution of dolomite and the effect of silicate materials on the aquifer were other determinative processes influencing the quality of groundwater in the area. In order to predict the overall quality of groundwater with respect to a calculated water quality index (WQI), support vector machine (SVM) and artificial neural network (ANN) were utilized. The correlation coefficients between the predicted and observed WQI for the training and test data set related to SVM were 0.97 and 0.96, respectively. On the contrary, the results of ANNs with early stopping showed roughly the same performance resulting in correlation coefficients of 0.98 and 0.96 for the training and test data set, respectively. As a whole, the WQI for 8 % of the sampling stations was <50 and for 17 %, the calculated index was <60 which are important concerns.