The representation of point-observed environmental variables in Geographic Information Systems (GIS) has often been inadequate to meet the need of regional-scale ecological and environmental applications. To create a map of continuous surface that wou...
The representation of point-observed environmental variables in Geographic Information Systems (GIS) has often been inadequate to meet the need of regional-scale ecological and environmental applications. To create a map of continuous surface that would represent more reliable spatial variations for these applications, I present three spatial estimation methods. Using a secondary variable of the proximity to coast line together with rainfall acidity data collected at the 63 acid rain monitoring stations in Korea, average rainfall acidity map was created using co-kriging. For comparison, two other commonly used interpolation methods (inverse distance weighting and kriging) were also applied to rainfall acidity data without reference to the secondary variable. These estimation methods were evaluated by both visual assessments of the output maps and the quantitative comparison of error measures that were obtained from cross validation. The co-kriging method produced a rainfall acidity map that showed noticeable improvement in reproducing the inherent spatial pattern as well as provided lower statistical error as compared to the methods using only the primary variable.