Data-driven Kriging models based on FANOVA-decomposition

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
Type de document :
Autre publication
Preprint, Working Paper, Document sans référence, etc. 2010
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00537781
Contributeur : Olivier Roustant <>
Soumis le : vendredi 19 novembre 2010 - 12:16:17
Dernière modification le : mardi 23 octobre 2018 - 14:36:09
Document(s) archivé(s) le : dimanche 20 février 2011 - 02:52:30

Fichier

Data-Driven_Kriging_models_bas...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00537781, version 1

Citation

Thomas Muehlenstaedt, Olivier Roustant, Laurent Carraro, Sonja Kuhnt. Data-driven Kriging models based on FANOVA-decomposition. Preprint, Working Paper, Document sans référence, etc. 2010. 〈hal-00537781〉

Partager

Métriques

Consultations de la notice

496

Téléchargements de fichiers

555