Advertisement

Statistics and Computing

, Volume 22, Issue 3, pp 723–738 | Cite as

Data-driven Kriging models based on FANOVA-decomposition

  • Thomas Muehlenstaedt
  • Olivier Roustant
  • Laurent Carraro
  • Sonja Kuhnt
Article

Abstract

Kriging models have been widely used in computer experiments for the analysis of time-consuming computer codes. Based on kernels, they are flexible and can be tuned to many situations. In this paper, we construct kernels that reproduce the computer code complexity by mimicking its interaction structure. While the standard tensor-product kernel implicitly assumes that all interactions are active, the new kernels are suited for a general interaction structure, and will take advantage of the absence of interaction between some inputs. The methodology is twofold. First, the interaction structure is estimated from the data, using a first initial standard Kriging model, and represented by a so-called FANOVA graph. New FANOVA-based sensitivity indices are introduced to detect active interactions. Then this graph is used to derive the form of the kernel, and the corresponding Kriging model is estimated by maximum likelihood. The performance of the overall procedure is illustrated by several 3-dimensional and 6-dimensional simulated and real examples. A substantial improvement is observed when the computer code has a relatively high level of complexity.

Keywords

Sensitivity analysis Computer experiments Functional ANOVA decomposition Graph Kriging 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bach, F.: High-dimensional non-linear variable selection through hierarchical kernel learning. Technical report (2009). http://arxiv.org/abs/0909.0844
  2. Cressie, N.: Statistics for Spatial Data. Wiley Series in Probability and Mathematical Statistics. Wiley, New York (1993) Google Scholar
  3. Diestel, R.: Graph Theory. Springen, New York (2000) Google Scholar
  4. Durrande, N., Ginsbourger, D., Roustant, O.: Additive kernels for high-dimensional Gaussian process modeling. Technical report (2010). http://hal.archives-ouvertes.fr/hal-00446520/en/
  5. Edwards, D.: Introduction to Graphical Modelling, 2nd edn. Springer, New York (2000) zbMATHCrossRefGoogle Scholar
  6. Efron, B., Stein, C.: The jackknife estimate of variance. Ann. Stat. 9(3), 586–596 (1981) MathSciNetzbMATHCrossRefGoogle Scholar
  7. Fang, K.T., Li, R., Sudjianto, A.: Design and Modeling for Computer Experiments. Computer Science and Data Analysis Series. Chapman & Hall/CRC, Boca Raton (2006) zbMATHGoogle Scholar
  8. Goesling, M., Kracker, H., Brosius, A., Kuhnt, S., Tekkaya, A.: Simulation und kompensation rueckfederungsbedingter formabweichungen. In: Tillmann, W. (ed.) SFB 708–3 oeffentliches Kolloquium, pp. 155–170. Praxiswissen, Dortmund (2009) Google Scholar
  9. Joseph, Hung Y. V, Sudjianto, A.: Blind kriging: A new method for developing metamodels. J. Mech. Des. 130(3), 031,102 (2008) (8 pages) CrossRefGoogle Scholar
  10. Krige, D.: A statistical approach to some basic mine valuation problems on the witwatersrand. J. Chem. Metall. Min. Soc. S. Afr. 52(6), 119–139 (1951) Google Scholar
  11. Marrel, A., Iooss, B., Van Dorpe, F., Volkova, E.: An efficient methodology for modeling complex computer codes with Gaussian processes. Comput. Stat. Data Anal. 52(10), 4731–4744 (2008) zbMATHCrossRefGoogle Scholar
  12. Martin, J., Simpson, T.: Use of kriging models to approximate deterministic computer models. AIAA J. 43(4), 853–863 (2005) CrossRefGoogle Scholar
  13. Matheron, G.: Les cahiers du centre de morphologie mathématique de fontainebleau. Tech. Rep. 1, Ecole Nationale Supérieure des Mines de Paris (1969) Google Scholar
  14. Park, J., Baek, J.: Efficient computation of maximum likelihood estimators in a spatial linear model with power exponential covariogram. Comput. Geosci. 27, 1–7 (2001) CrossRefGoogle Scholar
  15. Plate, T.: Accuracy versus interpretability in flexible modeling: implementing a tradeoff using Gaussian process models. Behaviourmetrika 26(1), 29–50 (1999). Special issue on Analysis of knowledge representations in neural network (NN) models CrossRefGoogle Scholar
  16. R Development Core Team: R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2010), http://www.R-project.org/, ISBN 3-900051-07-0 Google Scholar
  17. Rasmussen, C., Williams, C.: Gaussian processes for machine learning. Adaptive Computation and Machine Learning. MIT, Cambridge (2006) Google Scholar
  18. Roustant, O., Ginsbourger, D., Deville, Y.: DiceKriging, DiceOptim: Two R packages for the analysis of computer experiments by kriging-based metamodeling and optimization. Technical report (2010). http://hal.archives-ouvertes.fr/hal-00495766/fr/
  19. Sacks, J., Welch, W., Mitchell, T., Wynn, H.: Design and analysis of computer experiments. Stat. Sci. 4(4), 409–435 (1989) MathSciNetzbMATHCrossRefGoogle Scholar
  20. Saltelli, A., Chan, K.: A quantitative, model independent method for global sensitivity analysis of model output. Technometrics 41, 39–56 (1999) CrossRefGoogle Scholar
  21. Saltelli, A., Chan, K., Scott, E.: Sensitivity Analysis. Wiley Series in Probability and Statistics. Wiley, Chichester (2000) zbMATHGoogle Scholar
  22. Santner, T., Williams, B., Notz, W.: The Design and Analysis of Computer Experiments. Springer Series in Statistics. Springer, New York (2003) zbMATHGoogle Scholar
  23. Sobol’, I.: Sensitivity estimates for nonlinear mathematical models. Math. Model. Comput. Exp. 1(4), 407–414 (1993) MathSciNetGoogle Scholar
  24. Stein, M.: Interpolation of Spatial Data, Some Theory for Kriging. Springer Series in Statistics. Springer, New York (1999) zbMATHCrossRefGoogle Scholar
  25. Welch, W.J., Buck, R.J., Sacks, J., Wynn, H.P., Mitchell, T.J., Morris, M.D.: Screening, predicting and computer experiments. Technometrics 34, 15–25 (1992) CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Thomas Muehlenstaedt
    • 1
  • Olivier Roustant
    • 2
  • Laurent Carraro
    • 3
  • Sonja Kuhnt
    • 1
  1. 1.Faculty of StatisticsTU Dortmund UniversityDortmundGermany
  2. 2.Ecole des Mines de St-EtienneSaint EtienneFrance
  3. 3.Telecom St-EtienneSaint EtienneFrance

Personalised recommendations