Graph convolutional network for predicting abnormal grain growth in Monte Carlo simulations of microstructural evolution
This work addresses a challenging problem in materials science for researchers studying microstructural evolution, though it is incremental as it applies an existing graph neural network method to a specific domain.
The study tackled predicting abnormal grain growth in microstructures by training graph convolutional networks on Monte Carlo simulation data, achieving 73% prediction accuracy and outperforming a computer vision method with fewer false positives.
Recent developments in graph neural networks show promise for predicting the occurrence of abnormal grain growth, which has been a particularly challenging area of research due to its apparent stochastic nature. In this study, we generate a large dataset of Monte Carlo simulations of abnormal grain growth. We train simple graph convolution networks to predict which initial microstructures will exhibit abnormal grain growth, and compare the results to a standard computer vision approach for the same task. The graph neural network outperformed the computer vision method and achieved 73% prediction accuracy and fewer false positives. It also provided some physical insight into feature importance and the relevant length scale required to maximize predictive performance. Analysis of the uncertainty in the Monte Carlo simulations provides additional insights for ongoing work in this area.