TABLE OF CONTENTS So far, none of the interpolation methods discussed in the previous chapter can provide a direct estimate of the quality of the interpolation made in terms of a variance for the interpolated elevation at a certain location. In all methods, the only way to determine the goodness of the interpolation would be to compute estimates for a set of extra checkpoints that had not been used in the original interpolation (this is rarely done in practice).
A further objection of all the previous interpolation methods is that there is no a priori method of determining whether the best values have been chosen for the weighting parameters or if the size of the search neighborhood is appropriate. Moreover, no method studied so far provides sensible information on (Davis, 1986):
The number of points needed to compute the local coverage;
The size, orientation, and shape of the neighborhood from which those points are drawn;
Whether there are better ways to estimate the interpolation weights than as a simple deterministic function of distance;
The errors associated with the interpolated values.
KRIGING is a geostatistical interpolation technique that addresses the above-mentioned questions and concerns. Conceptually, KRIGING is similar to previously discussed interpolation techniques in the sense that an estimate of the elevation at the interpolation point is determined as a weighted average of the observed elevations at the reference points. The main difference between KRIGING and other interpolation methods is that the weights are determined according to the distances between the interpolation...
