This paper compares two spatial interpolation techniques – Radial Basis Functions (RBF) and Inverse Distance Weighting (IDW) – with the goal of determining which method creates the best representation of reality for measured groundwater levels in catchment area. The study used the results of research and field observations from the year 2011, in Sosnowica (West Polesie). The data set consists of groundwater levels measured at 15 points in three series of tests. Surface generation was obtained for each method. The water prediction maps showed spatial variation in the groundwater level in the study area and they are quite different. RBF method resulted in a smoother map. The analysis of the methods of interpolation of analyzed data with the help of cross validation statistics and plots showed that Radial Basis Functions creates better representation of reality for measured groundwater levels.