Parametric and non-parametric kriging techniques for delineating water quality in the major cities of Pakistan

Geostatistics is the knowledge of manifestations that vary in space and time. The analysis of spatial data is currently of great interest in statistical modeling. Various parametric and non-parametric kriging techniques are widely used for modeling and prediction of spatially reference data. In this article, we have applied and compared the parametric and non-parametric kriging techniques to model groundwater quality parameters. The data used in this study consists of 366 water samples collected from major cities of Pakistan by the Pakistan Council of Research in Water Resources (PCRWR) survey. The water quality parameters are grouped by spatial variation using cluster analysis and principal component analysis. In order to generate prediction maps and evaluate the probability of groundwater quality parameters, parametric and non-parametric kriging techniques are used. Non-parametric kriging techniques showed better performance than parametric kriging techniques when the normality assumption of kriging is violated.