Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs

04/12/2021

∙

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 andBenjamin-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 thatPINNs can approximate solutions of these dispersive PDEs very accurately

READ FULL TEXT

Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs

Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs

Generic bounds on the approximation error for physics-informed (and) operator learning

wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation laws

PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks

The effect of time discretization on the solution of parabolic PDEs with ANNs

Rademacher Complexity and Numerical Quadrature Analysis of Stable Neural Networks with Applications to Numerical PDEs

Nonlinear model order reduction for problems with microstructure using mesh informed neural networks

Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs

Related Research

Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs

Generic bounds on the approximation error for physics-informed (and) operator learning

wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation laws

PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks

The effect of time discretization on the solution of parabolic PDEs with ANNs

Rademacher Complexity and Numerical Quadrature Analysis of Stable Neural Networks with Applications to Numerical PDEs

Nonlinear model order reduction for problems with microstructure using mesh informed neural networks