Skip to main content

Research Repository

Advanced Search

Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions

Zhang, B.; Konomi, B.; Sang, H.; Karagiannis, G.; Lin, G.

Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions Thumbnail


Authors

B. Zhang

B. Konomi

H. Sang

G. Lin



Abstract

Gaussian process emulator with separable covariance function has been utilized extensively in modeling large computer model outputs. The assumption of separability imposes constraints on the emulator and may negatively affect its performance in some applications where separability may not hold. We propose a multi-output Gaussian process emulator with a nonseparable auto-covariance function to avoid limitations of using separable emulators. In addition, to facilitate the computation of nonseparable emulator, we introduce a new computational method, referred to as the Full-Scale approximation method with block modulating function (FSA-Block) approach. The FSA-Block is an effective and accurate covariance approximation method to reduce computations for Gaussian process models, which applies to both nonseparable and partially separable covariance models. We illustrate the effectiveness of our method through simulation studies and compare it with emulators with separable covariances. We also apply our method to a real computer code of the carbon capture system.

Citation

Zhang, B., Konomi, B., Sang, H., Karagiannis, G., & Lin, G. (2015). Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions. Journal of Computational Physics, 300, 623-642. https://doi.org/10.1016/j.jcp.2015.08.006

Journal Article Type Article
Acceptance Date Aug 2, 2015
Online Publication Date Aug 10, 2015
Publication Date Nov 1, 2015
Deposit Date Nov 10, 2016
Publicly Available Date Mar 29, 2024
Journal Journal of Computational Physics
Print ISSN 0021-9991
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 300
Pages 623-642
DOI https://doi.org/10.1016/j.jcp.2015.08.006

Files




You might also like



Downloadable Citations