Regularized kriging as a generalization of simple, universal, and bayesian kriging
- 204 Downloads
In this article the properties of regularized kriging (RK) are studied. RK is obtained as a result of relaxing the universal kriging (UK) non-bias condition by using the support vectors methodology. More specifically, we demonstrate how RK is a continuum of solutions in function of the regularizing parameter, which includes as particular and extreme cases, simple kriging (SK) and UK, and as an intermediate case, Bayesian kriging (BK). Likewise, expressions are obtained for the mean, variance and mean squared error (MSE), as also the expression for the corresponding estimator of the coefficients of the mean. Finally, we investigate the relationship between RK and the support vector machines. By means of simulations we compare the MSE for RK with those for BK and UK, for different association models, for different levels of noise, and for differently sized mean coefficients. The RK results prove to be an improvement on the UK and BK results, and, moreover, these improvements are proportionally greater for greater levels of noise.
KeywordsBias-variance trade-off Cauchy class Kernel methods Matérn class Kriging Support vector machines
The research of W. González-Manteiga was supported by the Spanish Ministry of Science and Technology under Project BFM2002-03213. The authors wish to express their thanks to the three anonymous referees whose comments and suggestions greatly improved this article.
- Christakos G (1992) Random field models in earth sciences. Academic, San DiegoGoogle Scholar
- Cressie N (1993) Statistics for spatial data. Wiley, New YorkGoogle Scholar
- Diggle PJ, Tawn JA, Moyeed RA (1998) Model-based geostatistics. Appl Stat 47:299–350Google Scholar
- MacKay DJC (1998) Introduction to Gaussian processes. In: Bishop CM (ed) Neural networks and machine learning. Proceedings of the NATO advanced Study Institute on Generalization in Neural Networks and Machine Learning. Springer, Berlin Heidelberg New York, pp 133–165Google Scholar
- Matías JM, González-Manteiga W (2003) Regularized kriging: the support vector method applied to kriging. In: Proceedings of the joint 13th international conference on artificial neural networks and 10th international conference on neural information processing, Istambul. Springer, Berlin Heidelberg New York, LCNS 2714, pp 209–216Google Scholar
- Matías JM, González-Manteiga W, Francisco-Fernández M, Taboada J, Ordóñez C (2004c) Variography for model selection in local polynomial regression with spatial data. In: Proceedings of the conference on computational and mathematical methods on science and engineering, CMMSE-2004, Uppsala, pp 226–235Google Scholar
- Schölkopf B, Smola AJ (2002) Learning with Kernels. MIT Press, CambridgeGoogle Scholar
- Smola A, Frieß J, Scholköpf B (1999) Semiparametric support vector and linear programming machines. In: Kearns MS, Solla SA, Cohn DA (eds) Advances in neural information processing systems. MIT Press, Cambridge, pp 585–591Google Scholar
- Stein ML (1999) Interpolation of spatial data. Springer, Berlin Heidelberg New YorkGoogle Scholar
- Vapnik V (1998) Statistical learning theory. Wiley, New YorkGoogle Scholar
- Williams CKI (1998) Prediction with gaussian processes: from linear regression to linear prediction and beyond. In: Jordan MI (ed) Learning and inference in graphical models. Kluwer, Dordrecht, 599–621Google Scholar