The impact of autocorrelated error on the interpolation of statistical surfaces

A basic problem in environmental analyses is to generate mapped surfaces from point observations. Effective incorporation of surface generation techniques into GIS-based analyses requires that they be systematically evaluated. In this paper, we evaluate kriging and inverse distance weighting in a computational experiment, using synthetic, realistic datasets that exhibit the type of autocorrelation expected in environmental data. The datasets were generated by sampling points from a mathematical surface, then adding autocorrelated error. Two levels of spatially autocorrelated error were used. Differences between the true surface and estimated values at evaluation points were used to visualize error and calculate summary statistics.