Graph Neural Network for Predicting the Effective Properties of Polycrystalline Materials: A Comprehensive Analysis

TL;DR

This paper introduces a graph neural network model for accurately predicting the effective properties of polycrystalline materials, demonstrating high accuracy and transfer learning capabilities on a large dataset of microstructures.

Contribution

The paper presents a novel PGNN model trained on a large dataset, with feature importance analysis and transfer learning for elastic properties prediction.

Findings

Achieved <1.4% error in conductivity prediction

Outperformed linear regression and CNN baselines

Demonstrated effective transfer learning for elastic properties

Abstract

We develop a polycrystal graph neural network (PGNN) model for predicting the effective properties of polycrystalline materials, using the Li7La3Zr2O12 ceramic as an example. A large-scale dataset with >5000 different three-dimensional polycrystalline microstructures of finite-width grain boundary is generated by Voronoi tessellation and processing of the electron backscatter diffraction images. The effective ion conductivities and elastic stiffness coefficients of these microstructures are calculated by high-throughput physics-based simulations. The optimized PGNN model achieves a low error of <1.4% in predicting all three diagonal components of the effective Li-ion conductivity matrix, outperforming a linear regression model and two baseline convolutional neural network models. Sequential forward selection method is used to quantify the relative importance of selecting individual grain (boundary) features to improving the property prediction accuracy, through which both the critical and unwanted node (edge) feature can be determined. The extrapolation performance of the trained PGNN model is also investigated. The transfer learning performance is evaluated by using the PGNN model pretrained for predicting conductivities to predict the elastic properties of the same set of microstructures.