Data-driven and active learning of variance-based sensitivity indices with Bayesian probabilistic integration

Song, Jingwen, Wei, Pengfei, Valdebenito, Marcos A, Faes, Matthias and Beer, Michael ORCID: 0000-0002-0611-0345 (2022) Data-driven and active learning of variance-based sensitivity indices with Bayesian probabilistic integration. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 163. p. 108106.

Text
BPISensitivity_cleanVersion.pdf - Author Accepted Manuscript
Download (793kB) | Preview

Official URL: http://dx.doi.org/10.1016/j.ymssp.2021.108106

Abstract

Variance-based sensitivity indices play an important role in scientific computation and data mining, thus the significance of developing numerical methods for efficient and reliable estimation of these sensitivity indices based on (expensive) computer simulators and/or data cannot be emphasized too much. In this article, the estimation of these sensitivity indices is treated as a statistical inference problem. Two principle lemmas are first proposed as rules of thumb for making the inference. After that, the posterior features for all the (partial) variance terms involved in the main and total effect indices are analytically derived (not in closed form) based on Bayesian Probabilistic Integration (BPI). This forms a data-driven method for estimating the sensitivity indices as well as the involved discretization errors. Further, to improve the efficiency of the developed method for expensive simulators, an acquisition function, named Posterior Variance Contribution (PVC), is utilized for realizing optimal designs of experiments, based on which an adaptive BPI method is established. The application of this framework is illustrated for the calculation of the main and total effect indices, but the proposed two principle lemmas also apply to the calculation of interaction effect indices. The performance of the development is demonstrated by an illustrative numerical example and three engineering benchmarks with finite element models.

Item Type:	Article
Uncontrolled Keywords:	Variance-based sensitivity, Gaussian process regression, Bayesian probabilistic integration, Data-driven, Adaptive experiment design, Posterior variance contribution
Divisions:	Faculty of Science and Engineering > School of Engineering
Depositing User:	Symplectic Admin
Date Deposited:	28 Jun 2021 07:45
Last Modified:	18 Jan 2023 21:37
DOI:	10.1016/j.ymssp.2021.108106
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3127970