On the performance of multi-fidelity and reduced-dimensional neural emulators for inference of physiological boundary conditions

Abstract

Solving inverse problems in cardiovascular modeling is particularly challenging due to the high computational cost of running high-fidelity simulations. In this work, we focus on Bayesian parameter estimation and explore different methods to reduce the computational cost of sampling from the posterior distribution by leveraging low-fidelity approximations. A common approach is to construct a surrogate model for the high-fidelity simulation itself. Another is to build a surrogate for the discrepancy between high- and low-fidelity models. This discrepancy, which is often easier to approximate, is modeled with either a fully connected neural network or a nonlinear dimensionality reduction technique that enables surrogate construction in a lower-dimensional space. A third possible approach is to treat the discrepancy between the high-fidelity and surrogate models as random noise and estimate its distribution using normalizing flows. This allows us to incorporate the approximation error into the Bayesian inverse problem by modifying the likelihood function. We validate five different methods which are variations of the above on analytical test cases by comparing them to posterior distributions derived solely from high-fidelity models, assessing both accuracy and computational cost. Finally, we demonstrate our approaches on two cardiovascular examples of increasing complexity: a lumped-parameter Windkessel model and a patient-specific three-dimensional anatomy.

References in corpus (13)

• Normalizing Flows: An Introduction and Review of Current Methods
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• Inferring solutions of differential equations using noisy multi-fidelity data
• Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantities
• A Generalized Approximate Control Variate Framework for Multifidelity Uncertainty Quantification
• Multilevel and multifidelity uncertainty quantification for cardiovascular hemodynamics
• Automated generation of 0D and 1D reduced-order models of patient-specific blood flow
• Bayesian Optimization with Output-Weighted Optimal Sampling
• Iterative Updating of Model Error for Bayesian Inversion
• normflows: A PyTorch Package for Normalizing Flows
• Geometric Uncertainty in Patient-Specific Cardiovascular Modeling with Convolutional Dropout Networks
• A survey on multi-fidelity surrogates for simulators with functional outputs: unified framework and benchmark
• Ensemble Kalman filter for multiscale inverse problems