English

Deep Learning Models for Global Coordinate Transformations that Linearize PDEs

Dynamical Systems 2020-09-30 v1 Machine Learning Computational Physics Machine Learning

Abstract

We develop a deep autoencoder architecture that can be used to find a coordinate transformation which turns a nonlinear PDE into a linear PDE. Our architecture is motivated by the linearizing transformations provided by the Cole-Hopf transform for Burgers equation and the inverse scattering transform for completely integrable PDEs. By leveraging a residual network architecture, a near-identity transformation can be exploited to encode intrinsic coordinates in which the dynamics are linear. The resulting dynamics are given by a Koopman operator matrix K\mathbf{K}. The decoder allows us to transform back to the original coordinates as well. Multiple time step prediction can be performed by repeated multiplication by the matrix K\mathbf{K} in the intrinsic coordinates. We demonstrate our method on a number of examples, including the heat equation and Burgers equation, as well as the substantially more challenging Kuramoto-Sivashinsky equation, showing that our method provides a robust architecture for discovering interpretable, linearizing transforms for nonlinear PDEs.

Keywords

Cite

@article{arxiv.1911.02710,
  title  = {Deep Learning Models for Global Coordinate Transformations that Linearize PDEs},
  author = {Craig Gin and Bethany Lusch and Steven L. Brunton and J. Nathan Kutz},
  journal= {arXiv preprint arXiv:1911.02710},
  year   = {2020}
}

Comments

23 pages, 18 figures

R2 v1 2026-06-23T12:08:06.410Z