Rethinking materials simulations: Blending direct numerical simulations with neural operators

TL;DR

This paper introduces a hybrid approach combining numerical solvers with neural operators to significantly accelerate materials evolution simulations, maintaining accuracy while reducing computational costs.

Contribution

A novel framework integrating numerical solvers with neural operators, enabling fast and accurate long-term simulations of complex materials evolution processes.

Findings

Achieved up to 16.5× speed-up over traditional DNS.

Demonstrated effective extrapolation of microstructure evolution.

Applicable to various physical models beyond materials science.

Abstract

Direct numerical simulations (DNS) are accurate but computationally expensive for predicting materials evolution across timescales, due to the complexity of the underlying evolution equations, the nature of multiscale spatio-temporal interactions, and the need to reach long-time integration. We develop a new method that blends numerical solvers with neural operators to accelerate such simulations. This methodology is based on the integration of a community numerical solver with a U-Net neural operator, enhanced by a temporal-conditioning mechanism that enables accurate extrapolation and efficient time-to-solution predictions of the dynamics. We demonstrate the effectiveness of this framework on simulations of microstructure evolution during physical vapor deposition modeled via the phase-field method. Such simulations exhibit high spatial gradients due to the co-evolution of different material phases with simultaneous slow and fast materials dynamics. We establish accurate extrapolation of the coupled solver with up to 16.5$\times$ speed-up compared to DNS. This methodology is generalizable to a broad range of evolutionary models, from solid mechanics, to fluid dynamics, geophysics, climate, and more.