Global sensitivity analysis in Monte Carlo radiation transport

Abstract

We consider Global Sensitivity Analysis for Monte Carlo radiation transport applications. GSA is usually combined with Uncertainty Quantification, where the latter quantifies the variability of a model output in the presence of uncertain inputs and the former attributes this variability to the inputs. The additional noise inherent to MC RT solvers due to the finite number of particle histories presents an additional challenge to GSA and UQ, which are well-established for deterministic solvers. In this contribution, we apply variance deconvolution to the Saltelli method to address MC RT solver noise without having to over-resolve the MC RT simulation.