Train Small, Model Big: Scalable Physics Simulators via Reduced Order Modeling and Domain Decomposition

TL;DR

This paper introduces a scalable physics-constrained reduced order modeling approach combined with domain decomposition, enabling large-scale simulations that are significantly faster and more memory-efficient than traditional methods.

Contribution

The paper presents a novel combination of reduced order modeling and domain decomposition techniques for scalable, physics-constrained simulations at large scales.

Findings

Achieves 15-40 times faster solutions with ~1% error.

Uses an order of magnitude less memory than full models.

Demonstrates effectiveness on Poisson and Stokes flow equations.

Abstract

Numerous cutting-edge scientific technologies originate at the laboratory scale, but transitioning them to practical industry applications is a formidable challenge. Traditional pilot projects at intermediate scales are costly and time-consuming. An alternative, the E-pilot, relies on high-fidelity numerical simulations, but even these simulations can be computationally prohibitive at larger scales. To overcome these limitations, we propose a scalable, physics-constrained reduced order model (ROM) method. ROM identifies critical physics modes from small-scale unit components, projecting governing equations onto these modes to create a reduced model that retains essential physics details. We also employ Discontinuous Galerkin Domain Decomposition (DG-DD) to apply ROM to unit components and interfaces, enabling the construction of large-scale global systems without data at such large scales. This method is demonstrated on the Poisson and Stokes flow equations, showing that it can solve equations about $15 - 40$ times faster with only $\sim$ $1\%$ relative error. Furthermore, ROM takes one order of magnitude less memory than the full order model, enabling larger scale predictions at a given memory limitation.