Data-Driven Acceleration of Multi-Physics Simulations

TL;DR

This paper presents a data-driven method to accelerate multi-physics simulations by approximating complex interactions, demonstrated on semiconductor lasers, resulting in improved accuracy and efficiency over traditional methods.

Contribution

The paper introduces a novel data-driven approach that reduces computational costs in multi-physics simulations, outperforming traditional analytical approximations.

Findings

Significant reduction in simulation time.

Higher accuracy compared to analytical methods.

Effective for large-scale multi-physics systems.

Abstract

Multi-physics simulations play a crucial role in understanding complex systems. However, their computational demands are often prohibitive due to high dimensionality and complex interactions, such that actual calculations often rely on approximations. To address this, we introduce a data-driven approach to approximate interactions among degrees of freedom of no direct interest and thus significantly reduce computational costs. Focusing on a semiconductor laser as a case study, we demonstrate the superiority of this method over traditional analytical approximations in both accuracy and efficiency. Our approach streamlines simulations, offering promise for complex multi-physics systems, especially for scenarios requiring a large number of individual simulations.