Trend analysis of groundwater using non-parametric methods (case study: Ardabil plain)

In the present study, the trends in groundwater level and fifteen hydro-geochemical elements at 32 piezometric stations located in the Ardabil plain of the northwest of Iran were analyzed using the non-parametric Mann-Kendall method after removing the effect of significant lag-1 serial correlation from the respective time series by pre-whitening. The magnitudes of trends were computed using the Sen's estimator method. The homogeneity of trend was tested using the method proposed by van Belle and Hughes as well. Results showed that significant (alpha < 0.1) negative trends in groundwater level were witnessed for all but five stations of the Ardabil plains during the last 22 years from 1988 to 2009. The groundwater levels over Ardabil plain have declined at the rate of about 18 cm/year, with the strongest decline (1.93 m/year) witnessed at Khalife-loo-sheikh station. The results of homogeneity of trends showed that trends were homogeneous for months but not for stations. Strong positive trends were detected in the groundwater quality concentration across the whole plain. Decline in groundwater level and increase in geochemical elements in the groundwater were attributed to the human activities in the Ardabil plain located in the northwest of Iran.