FUSE: Fast Unified Simulation and Estimation for PDEs

Levi E. Lingsch, Dana Grund, Siddhartha Mishra, Georgios Kissas

Keywords: Forward and Inverse Problems, PDEs, Neural Operators, Neural Posterior Estimation

TL;DR: This work presents a framework to unify forward and inverse problems in scientific computing by optimizing a joint objective derived from operator learning.

Abstract: The joint prediction of continuous fields and statistical estimation of the underlying discrete parameters is a common problem for many physical systems, governed by PDEs. Hitherto, it has been separately addressed by employing operator learning surrogates for field prediction while using simulation-based inference (and its variants) for statistical parameter determination. Here, we argue that solving both problems within the same framework can lead to consistent gains in accuracy and robustness. To this end, we propose a novel and flexible formulation of the operator learning problem that jointly predicts continuous quantities and infers distributions of discrete parameters, thereby amortizing the cost of both the inverse and the surrogate models to a joint pre-training step. We present the capabilities of the proposed methodology for predicting continuous and discrete biomarkers in full-body haemodynamics simulations under different levels of missing information. We also consider a test case for atmospheric large-eddy simulation of a two-dimensional dry cold bubble, where we infer both continuous time-series and information about the system's conditions. We present comparisons against different baselines to showcase significantly increased accuracy in both the inverse and the surrogate tasks.

Primary Area: Machine learning for physical sciences (for example: climate, physics)

Submission Number: 11085