Physics-Informed Neural Networks with Adaptive Localized Artificial Viscosity

by   E. J. R. Coutinho, et al.

Physics-informed Neural Network (PINN) is a promising tool that has been applied in a variety of physical phenomena described by partial differential equations (PDE). However, it has been observed that PINNs are difficult to train in certain "stiff" problems, which include various nonlinear hyperbolic PDEs that display shocks in their solutions. Recent studies added a diffusion term to the PDE, and an artificial viscosity (AV) value was manually tuned to allow PINNs to solve these problems. In this paper, we propose three approaches to address this problem, none of which rely on an a priori definition of the artificial viscosity value. The first method learns a global AV value, whereas the other two learn localized AV values around the shocks, by means of a parametrized AV map or a residual-based AV map. We applied the proposed methods to the inviscid Burgers equation and the Buckley-Leverett equation, the latter being a classical problem in Petroleum Engineering. The results show that the proposed methods are able to learn both a small AV value and the accurate shock location and improve the approximation error over a nonadaptive global AV alternative method.


page 5

page 6

page 8

page 9

page 12

page 13


Physics-informed attention-based neural network for solving non-linear partial differential equations

Physics-Informed Neural Networks (PINNs) have enabled significant improv...

PINNs for the Solution of the Hyperbolic Buckley-Leverett Problem with a Non-convex Flux Function

The displacement of two immiscible fluids is a common problem in fluid f...

Numerical Approximations of the Allen-Cahn-Ohta-Kawasaki (ACOK) Equation with Modified Physics Informed Neural Networks (PINNs)

The physics informed neural networks (PINNs) has been widely utilized to...

Physics informed neural networks for continuum micromechanics

Recently, physics informed neural networks have successfully been applie...

Rethinking the Importance of Sampling in Physics-informed Neural Networks

Physics-informed neural networks (PINNs) have emerged as a powerful tool...

A novel analytic method for solving linear and nonlinear Telegraph Equation

The modeling of many phenomena in various fields such as mathematics, ph...

Learning and Meta-Learning of Stochastic Advection-Diffusion-Reaction Systems from Sparse Measurements

Physics-informed neural networks (PINNs) were recently proposed in [1] a...