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

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

arXiv commentarXiv admin note: text overlap with arXiv:2006.16144

References in corpus (9)

• An integrable shallow water equation with peaked solitons
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Fourier Neural Operator for Parametric Partial Differential Equations
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Physics Informed Neural Networks for Simulating Radiative Transfer
• Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs