Skip to Main content Skip to Navigation
Journal articles

ANOVA decomposition of conditional Gaussian processes for sensitivity analysis with dependent inputs

Gaëlle Chastaing 1, 2 Loic Le Gratiet 1, 3, 2
2 AIRSEA - Mathematics and computing applied to oceanic and atmospheric flows
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, UGA - Université Grenoble Alpes
Abstract : Complex computer codes are widely used in science to model physical systems. Sensitivity analysis aims to measure the contributions of the inputs on the code output variability. An efficient tool to perform such analysis are the variance-based methods which have been recently investigated in the framework of dependent inputs. One of their issue is that they require a large number of runs for the complex simulators. To handle it, a Gaussian process regression model may be used to approximate the complex code. In this work, we propose to decompose a Gaussian process into a high dimensional representation. This leads to the definition of a variance-based sensitivity measure well tailored for non-independent inputs. We give a methodology to estimate these indices and to quantify their uncertainty. Finally, the approach is illustrated on toy functions and on a river flood model.
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download
Contributor : Loic Le Gratiet <>
Submitted on : Friday, October 11, 2013 - 3:01:43 PM
Last modification on : Saturday, March 28, 2020 - 2:14:25 AM
Document(s) archivé(s) le : Sunday, January 12, 2014 - 4:36:18 AM


Files produced by the author(s)



Gaëlle Chastaing, Loic Le Gratiet. ANOVA decomposition of conditional Gaussian processes for sensitivity analysis with dependent inputs. Journal of Statistical Computation and Simulation, Taylor & Francis, 2015, 85 (11), pp.2164-2186. ⟨10.1080/00949655.2014.925111⟩. ⟨hal-00872250⟩



Record views


Files downloads