Accelerate Microstructure Evolution Simulation Using Graph Neural Networks with Adaptive Spatiotemporal Resolution

TL;DR

This paper introduces a graph neural network-based framework for microstructure evolution simulation that achieves high accuracy and efficiency, with adaptive resolution and remeshing capabilities for faster computations.

Contribution

The authors develop a novel GNN-based surrogate model that outperforms previous CNN approaches in accuracy and efficiency, incorporating adaptive spatiotemporal resolution for microstructure simulations.

Findings

High agreement with phase-field and theoretical models

Enhanced accuracy and computational speed

Adaptive remeshing improves efficiency during coarsening

Abstract

Surrogate models driven by sizeable datasets and scientific machine-learning methods have emerged as an attractive microstructure simulation tool with the potential to deliver predictive microstructure evolution dynamics with huge savings in computational costs. Taking 2D and 3D grain growth simulations as an example, we present a completely overhauled computational framework based on graph neural networks with not only excellent agreement to both the ground truth phase-field methods and theoretical predictions, but enhanced accuracy and efficiency compared to previous works based on convolutional neural networks. These improvements can be attributed to the graph representation, both improved predictive power and a more flexible data structure amenable to adaptive mesh refinement. As the simulated microstructures coarsen, our method can adaptively adopt remeshed grids and larger timesteps to achieve further speedup. The data-to-model pipeline with training procedures together with the source codes are provided.