Prediction error certification for PINNs: Theory, computation, and application to Stokes flow
This work provides incremental improvements for researchers using PINNs in computational fluid dynamics by enabling error certification in broader applications.
The authors tackled the problem of rigorous error estimation for physics-informed neural networks (PINNs) by extending a semigroup-based framework to certify predictions in more realistic scenarios, as demonstrated with Stokes flow around a cylinder.
Rigorous error estimation is a fundamental topic in numerical analysis. With the increasing use of physics-informed neural networks (PINNs) for solving partial differential equations, several approaches have been developed to quantify the associated prediction error. In this work, we build upon a semigroup-based framework previously introduced by the authors for estimating the PINN error. While this estimator has so far been limited to academic examples - due to the need to compute quantities related to input-to-state stability - we extend its applicability to a significantly broader class of problems. This is accomplished by modifying the error bound and proposing numerical strategies to approximate the required stability parameters. The extended framework enables the certification of PINN predictions in more realistic scenarios, as demonstrated by a numerical study of Stokes flow around a cylinder.