Equation identification for fluid flows via physics-informed neural networks

TL;DR

This paper evaluates the performance of physics-informed neural networks (PINNs) in inverse problems involving fluid flows, introducing a new benchmark and strategies that improve parameter estimation, while highlighting current limitations in highly inviscid flows.

Contribution

The paper introduces a new benchmark for inverse PINNs using 2D Burgers' equation, proposes an alternating optimization strategy, and develops a data-driven method to assess PINN effectiveness.

Findings

Alternating optimization improves parameter estimation accuracy.

PINNs leverage small data more efficiently than baseline methods.

Both PINNs and baselines struggle with highly inviscid flows.

Abstract

Scientific machine learning (SciML) methods such as physics-informed neural networks (PINNs) are used to estimate parameters of interest from governing equations and small quantities of data. However, there has been little work in assessing how well PINNs perform for inverse problems across wide ranges of governing equations across the mathematical sciences. We present a new and challenging benchmark problem for inverse PINNs based on a parametric sweep of the 2D Burgers' equation with rotational flow. We show that a novel strategy that alternates between first- and second-order optimization proves superior to typical first-order strategies for estimating parameters. In addition, we propose a novel data-driven method to characterize PINN effectiveness in the inverse setting. PINNs' physics-informed regularization enables them to leverage small quantities of data more efficiently than the data-driven baseline. However, both PINNs and the baseline can fail to recover parameters for highly inviscid flows, motivating the need for further development of PINN methods.