Litcius/Paper detail

Physics Informed Neural Networks (PINNs) For Approximating Nonlinear Dispersive PDEs

Genming Bai, Ujjwal Koley, Siddhartha Mishra, Roberto Molinaro

2021Journal of Computational Mathematics27 citationsDOI

Abstract

We propose a novel algorithm, based on physics-informed neural networks (PINNs) to efficiently approximate solutions of nonlinear dispersive PDEs such as the KdV-Kawahara, Camassa-Holm and Benjamin-Ono equations. The stability of solutions of these dispersive PDEs is leveraged to prove rigorous bounds on the resulting error. We present several numerical experiments to demonstrate that PINNs can approximate solutions of these dispersive PDEs very accurately.

Topics & Concepts

Artificial neural networkPhysicsNonlinear systemApplied mathematicsStatistical physicsArtificial intelligenceComputer scienceMathematicsQuantum mechanicsModel Reduction and Neural NetworksMeteorological Phenomena and SimulationsFluid Dynamics and Turbulent Flows