Graph Neural Networks for an Accurate and Interpretable Prediction of the Properties of Polycrystalline Materials

Abstract

Various machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of individual grains but also their interactions. The embedding is then linked to the target property using a feed-forward neural network. Using the magnetostriction of polycrystalline Tb0.3Dy0.7Fe2 alloys as an example, we show that a single GNN model with fixed network architecture and hyperparameters allows for a low prediction error of ~10% over a group of remarkably different microstructures as well as quantifying the importance of each feature in each grain of a microstructure to its magnetostriction. Such microstructure-graph-based GNN model therefore enables an accurate and interpretable prediction of the properties of polycrystalline materials.

arXiv comment28 pages, 6 figures;

References in corpus (6)

• A Comprehensive Survey on Graph Neural Networks
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions

Cited by in corpus (15)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Machine learning-assisted design of material properties
• Perspective: strain and strain gradient engineering in membranes of quantum materials
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Differentiable graph-structured models for inverse design of lattice materials
• AtomVision: A machine vision library for atomistic images
• Integrating Machine Learning with Triboelectric Nanogenerators: Optimizing Electrode Materials and Doping Strategies for Intelligent Energy Harves
• FIP-GNN: Graph neural networks for scalable prediction of grain-level fatigue indicator parameters
• Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Features
• Predicting elastic and plastic properties of small iron polycrystals by machine learning
• Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training
• Unraveling impacts of polycrystalline microstructures on ionic conductivity of ceramic electrolytes by computational homogenization and machine learning
• Learning from 2D: machine learning of 3D effective properties of heterogeneous materials based on 2D microstructure sections
• Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks