Non-intrusive and semi-intrusive uncertainty quantification of a multiscale in-stent restenosis model

The In-Stent Restenosis 2D model is a full y coupled multiscale simulation of post-stenting tissue growth, in which the most costly submodel blood flow simulation. This paper presents uncertainty estimations response this model, as obtained by both non-intrusive and semi-intrusive quantification. A surrogate based on Gaussian process regression for quantification takes whole black-box maps directly three uncertain inputs to quantity interest, neointimal area. corresponding estimates matched results from quasi-Monte Carlo simulations well. In quantification, expensive replaced with model. We developed using convolutional neural network. method new offered efficient sensitivity while keeping relatively high accuracy. It outperformed earlier models. also achieved comparable similar efficiency. Presented propagation metamodelling methods allow us draw some conclusions advantages limitations these methods.