Cross validation of kriging in a unique neighborhood

  • Olivier Dubrule
Article

Abstract

Cross validation is an appropriate tool for testing interpolation methods: it consists of leaving out one data point at a time, and determining how well this point can be estimated from the other data. Cross validation is often used for testing “moving neighborhood” kriging models; in this case, each unknown value is predicted from a small number of surrounding data. In “unique neighborhood” kriging algorithms, each estimation uses all the available data; as a result, cross validation would spend much computer time. For instance, with ndata points it would cost at least the resolution of nsystems of n × nlinear equations (each with a different matrix).Here, we present a much faster method for cross validation in a unique neighborhood. Instead of solving nsystems n × n,it only requires the inversion of one n × nmatrix. We also generalized this method to leaving out several points instead of one.

Key words

cross validation kriging moving neighborhood unique neighborhood 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Delfiner, P. and Delhomme, J. P., 1973, Optimum interpolation by kriging: Proceedings of NATO-ASI, Display and Analysis of Spatial Data, Nottingham, John Wiley & Sons, New York/London, p. 96–114.Google Scholar
  2. Dubrule, O., 1981, Krigeage et splines en cartographie automatique—application a des exemples petroliers: Thesis, ENSMP, Centre de Geostatistique, 35 rue St. Honore, Fontainebleau, France, 150 p.Google Scholar
  3. Journel, A. G. and Huijbregts, Ch. J., 1978, Mining geostatistics: Academic Press, London, 598 p.Google Scholar
  4. Matheron, G., 1971, The theory of regionalized variables and its applications: les cahiers du CMM, Fasc. 5, ENSMP, Paris, 211 p.Google Scholar

Copyright information

© Plenum Publishing Corporation 1983

Authors and Affiliations

  • Olivier Dubrule
    • 1
  1. 1.Fluor Mining & Metals, Inc.Redwood CityUSA

Personalised recommendations