Certified data-driven physics-informed greedy auto-encoder simulator

TL;DR

This paper introduces a novel adaptive greedy auto-encoder framework for high-dimensional nonlinear dynamical systems that achieves significant speed-ups and maintains accuracy through physics-informed sampling and local interpolation.

Contribution

The paper presents a new adaptive greedy sampling method with physics-informed error indicators and an efficient local interpolation scheme for improved data-driven dynamical system simulation.

Findings

Achieves 121 to 2,658x speed-up over traditional methods.

Maintains 1 to 5% relative error in complex dynamical problems.

Outperforms conventional uniform sampling techniques.

Abstract

A parametric adaptive greedy Latent Space Dynamics Identification (gLaSDI) framework is developed for accurate, efficient, and certified data-driven physics-informed greedy auto-encoder simulators of high-dimensional nonlinear dynamical systems. In the proposed framework, an auto-encoder and dynamics identification models are trained interactively to discover intrinsic and simple latent-space dynamics. To effectively explore the parameter space for optimal model performance, an adaptive greedy sampling algorithm integrated with a physics-informed error indicator is introduced to search for optimal training samples on the fly, outperforming the conventional predefined uniform sampling. Further, an efficient k-nearest neighbor convex interpolation scheme is employed to exploit local latent-space dynamics for improved predictability. Numerical results demonstrate that the proposed method achieves 121 to 2,658x speed-up with 1 to 5% relative errors for radial advection and 2D Burgers dynamical problems.