Aggregation-cokriging for highly multivariate spatial data

Reinhard Furrer*, Marc G. Genton

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Scopus citations


Best linear unbiased prediction of spatially correlated multivariate random processes, often called cokriging in geostatistics, requires the solution of a large linear system based on the covariance and cross-covariance matrix of the observations. For many problems of practical interest, it is impossible to solve the linear system with direct methods. We propose an efficient linear unbiased predictor based on a linear aggregation of the covariables. The primary variable together with this single meta-covariable is used to perform cokriging. We discuss the optimality of the approach under different covariance structures, and use it to create reanalysis type high-resolution historical temperature fields.

Original languageEnglish (US)
Pages (from-to)615-631
Number of pages17
Issue number3
StatePublished - Sep 2011
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research was sponsored by the National Science Foundation, U.S.A., and by an awardmade by the King Abdullah University of Science and Technology. We acknowledge the internationalmodelling groups for providing their data for analysis. We also thank the editor, theassociate editor and two referees for comments that led to a substantial improvement of the paper.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.


  • Climate
  • Cokriging
  • Eigendecomposition
  • Intrinsic process
  • Linear unbiased prediction

ASJC Scopus subject areas

  • Applied Mathematics
  • Agricultural and Biological Sciences (miscellaneous)
  • General Agricultural and Biological Sciences
  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • General Mathematics


Dive into the research topics of 'Aggregation-cokriging for highly multivariate spatial data'. Together they form a unique fingerprint.

Cite this