Towards Spatio-Temporal Extrapolation of Phase-Field Simulations with Convolution-Only Neural Networks

TL;DR

This paper presents a convolutional neural network surrogate model that accurately and efficiently extrapolates phase-field simulations of liquid metal dealloying over large spatial and temporal scales, significantly reducing computational costs.

Contribution

It introduces a novel fully convolutional, conditionally parameterized U-Net architecture with physical and data-driven enhancements for long-term, large-scale phase-field simulation extrapolation.

Findings

Achieves less than 5% error in training regime

Maintains under 15% error in long-term extrapolations

Provides up to 36,000x speed-up in simulation time

Abstract

Phase-field simulations of liquid metal dealloying (LMD) can capture complex microstructural evolutions but can be prohibitively expensive for large domains and long time horizons. In this paper, we introduce a fully convolutional, conditionally parameterized U-Net surrogate designed to extrapolate far beyond its training data in both space and time. The architecture integrates convolutional self-attention, physically informed padding, and a flood-fill corrector method to maintain accuracy under extreme extrapolation, while conditioning on simulation parameters allows for flexible time-step skipping and adaptation to varying alloy compositions. To remove the need for costly solver-based initialization, we couple the surrogate with a conditional diffusion model that generates synthetic, physically consistent initial conditions. We train our surrogate on simulations generated over small domain sizes and short time spans, but, by taking advantage of the convolutional nature of U-Nets, we are able to run and extrapolate surrogate simulations for longer time horizons than what would be achievable with classic numerical solvers. Across multiple alloy compositions, the framework is able to reproduce the LMD physics accurately. It predicts key quantities of interest and spatial statistics with relative errors typically below 5% in the training regime and under 15% during large-scale, long time-horizon extrapolations. Our framework can also deliver speed-ups of up to 36,000 times, bringing the time to run weeks-long simulations down to a few seconds. This work is a first stepping stone towards high-fidelity extrapolation in both space and time of phase-field simulation for LMD.