Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs
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
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
41
References
1
Citations
NaN
KQI