Google Research

Learning latent field dynamics of PDEs

  • Alvaro Sanchez
  • Dmitrii Kochkov
  • Jamie Alexander Smith
  • Michael Brenner
  • Peter Battaglia
  • Tobias Joachim Pfaff
NeurIPS 2020 (2020)

Abstract

We present a new approach to learning surrogate models for simulation of complex physical systems described by partial differential equations. It aims to capture three features of PDEs: locality, time continuity and formation of elementary patterns in the solution by learning a local latent representation and corresponding time evolution. We show that this approach can be leveraged to obtain a class of low dimensional models that are competitive in accuracy and are faster at inference due to time evolution in the reduced representation. Additionally we demonstrate model generalization to larger system sizes without retraining and remark on the challenge of model comparison based on pointwise accuracy.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work