Speaker
Description
When dealing with uncertainty quantification (UQ) in numerical simulation models, one of the most critical hypotheses is the choice of the probability distributions of the uncertain input variables which are propagated through the model. Bringing stringent justifications to these choices, especially in a safety study, requires quantifying the impact of potential uncertainty on the input variable distribution. To solve this problem, the robustness analysis method based on the ‘‘Perturbed Law-based sensitivity Indices’’ (PLI) can be used [1]. The PLI quantifies the impact of a perturbation of an input distribution on the quantity of interest (e.g. a quantile the model output). One of its interest is that it can be computed using a unique Monte-Carlo sample containing the model inputs and outputs. In this communication, we present new results and recent insights about the mathematical formalism and numerical validation tests of the PLI [2,3].
[1] S. Da Veiga, F. Gamboa, B. Iooss and C. Prieur. Basics and trends in sensitivity analysis - Theory and practice in R, SIAM, 2021.
[2] C. Gauchy and J. Stenger and R. Sueur and B. Iooss, An information geometry approach for robustness analysis in uncertainty quantification of computer codes, Technometrics, 64:80-91, 2022.
[3] B. Iooss, V. Vergès and V. Larget, BEPU robustness analysis via perturbed-law based sensitivity indices, Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, doi:10.1177/1748006X211036569, 2021.
| Keywords | Computer experiments, Density perturbation, Sensitivity analysis |
|---|