Interface learning of multiphysics and multiscale systems

TL;DR

This paper introduces an interface learning paradigm for multiphysics and multiscale systems, using data-driven closure with memory embedding to improve boundary conditions and domain decomposition, aiming to enhance high-performance computing efficiency.

Contribution

It proposes a novel interface learning approach with memory embedding and upwind learning for hyperbolic systems, addressing multiscale, multiphysics boundary challenges.

Findings

Demonstrates effectiveness on canonical problems

Reduces communication costs in high-performance computing

Enables physics-informed domain decomposition

Abstract

Complex natural or engineered systems comprise multiple characteristic scales, multiple spatiotemporal domains, and even multiple physical closure laws. To address such challenges, we introduce an interface learning paradigm and put forth a data-driven closure approach based on memory embedding to provide physically correct boundary conditions at the interface. To enable the interface learning for hyperbolic systems by considering the domain of influence and wave structures into account, we put forth the concept of upwind learning towards a physics-informed domain decomposition. The promise of the proposed approach is shown for a set of canonical illustrative problems. We highlight that high-performance computing environments can benefit from this methodology to reduce communication costs among processing units in emerging machine learning ready heterogeneous platforms toward exascale era.