Uncertainties assessment in global sensitivity indices estimation from metamodels

Alexandre Janon; Maëlle Nodet; Clémentine Prieur

HAL: inria-00567977, version 3

DOI: 10.1615/Int.J.UncertaintyQuantification.2012004291

See short view

BibTeX,EndNote,...

Uncertainties assessment in global sensitivity indices estimation from metamodels
Janon A., Nodet M., Prieur C.
International Journal for Uncertainty Quantification (2012) - http://hal.inria.fr/inria-00567977

Available versions

v1 (2011-02-23)

v2 (2011-11-16)

v3 (2012-06-15)

Type of document:

Articles in peer-reviewed journal

Domain:

Statistics/Computation

Mathematics/Statistics

Statistics/Statistics Theory

Mathematics/Numerical Analysis

Title:

Uncertainties assessment in global sensitivity indices estimation from metamodels

Author(s):

Alexandre Janon (

) ^1, 2, Maëlle Nodet (

) ¹, Clémentine Prieur (

) ^1, 2

Research team(s):

1:	MOISE (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)

	http://team.inria.fr/moise

	CNRS : UMR5224 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut Polytechnique de Grenoble - Grenoble Institute of Technology

	Laboratoire Jean Kuntzmann B. P. 53 38041 Grenoble Cedex 9

	France

2:	GdR MASCOT-NUM ((Méthodes d'Analyse Stochastique des Codes et Traitements Numériques))

	http://www.gdr-mascotnum.fr/doku.php

	CNRS : GDR3179

	France

Abstract:

Global sensitivity analysis is often impracticable for complex and resource intensive numerical models, as it requires a large number of runs. The metamodel approach replaces the original model by an approximated code that is much faster to run. This paper deals with the information loss in the estimation of sensitivity indices due to the metamodel approxima- tion. A method for providing a robust error assessment is presented, hence enabling significant time savings without sacrificing on precision and rigor. The methodology is illustrated on two different types of metamodels: one based on reduced basis, the other one on RKHS interpolation.

Full text language:

English

Journal title:

International Journal for Uncertainty Quantification

Publication date:

2012

Audience:

international

Commercial editor:

Begell House Publishers

Keywords:

sensitivity analysis – reduced basis method – Sobol indices – bootstrap method – Monte Carlo method.

ANR Project:

Project Id

ANR-09-COSI-015 COSTA BRAVA

Attached file list to this document:

PDF

BoundSA3.pdf

(252.5 KB)


inria-00567977, version 3
http://hal.inria.fr/inria-00567977
oai:hal.inria.fr:inria-00567977
From: Alexandre Janon <>
Submitted on: Friday, 15 June 2012 21:08:17
Updated on: Saturday, 23 February 2013 17:46:54