Kriging

Kriging is a method of interpolation named after a South African mining engineer named D. G. Krige who developed the technique in an attempt to more accurately predict ore reserves. Over the past several decades kriging has become a fundamental tool in the field of geostatistics.

Kriging is based on the assumption that the parameter being interpolated can be treated as a regionalized variable. A regionalized variable is intermediate between a truly random variable and a completely deterministic variable in that it varies in a continuous manner from one location to the next and therefore points that are near each other have a certain degree of spatial correlation, but points that are widely separated are statistically independent (Davis, 1986). Kriging is a set of linear regression routines which minimize estimation variance from a predefined covariance model.

The kriging routines implemented in GMS are based on the Geostatistical Software Library (GSLIB) routines published by Deutsch and Journel (1992). Since kriging is a rather complex interpolation technique and includes numerous options, a complete description of kriging is beyond the scope of this reference manual. The user is strongly encouraged to the GSLIB textbook (Deutsch and Journel, 1992) for more information. Other good references on kriging include Royle et. al. (1981), Davis (1986), Lam (1983), Heine (1986), Olea (1974), Journel & Huijbregts (1978).

A powerful set of kriging techniques with varying degrees of sophistication have been implemented in GMS. The supported techniques include:

The selection of the Kriging method and the definition of the variograms are accomplished using the Kriging Options dialog.

There are several differences between 2D and 3D Kriging.