An equivariant graph neural network for the elasticity tensors of all seven crystal systems

Abstract

The elasticity tensor that describes the elastic response of a material to external forces is among the most fundamental properties of materials. The availability of full elasticity tensors for inorganic crystalline compounds, however, is limited due to experimental and computational challenges. Here, we report the materials tensor (MatTen) model for rapid and accurate estimation of the full fourth-rank elasticity tensors of crystals. Based on equivariant graph neural networks, MatTen satisfies the two essential requirements for elasticity tensors: independence of the frame of reference and preservation of material symmetry. Consequently, it provides a unified treatment of elasticity tensors for all seven crystal systems across diverse chemical spaces, without the need to deal with each separately.. MatTen was trained on a dataset of first-principles elasticity tensors garnered by the Materials Project over the past several years (we are releasing the data herein) and has broad applications in predicting the isotropic elastic properties of polycrystalline materials, examining the anisotropic behavior of single crystals, and discovering new materials with exceptional mechanical properties. Using MatTen, we have discovered a hundred new crystals with extremely large maximum directional Young's modulus and eleven polymorphs of elemental cubic metals with unconventional spatial orientation of Young's modulus.

References in corpus (13)

• Necessary and Sufficient Elastic Stability Conditions in Various Crystal Systems
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Recent Progress of the Computational 2D Materials Database (C2DB)
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• MechElastic: A Python Library for Analysis of Mechanical and Elastic Properties of Bulk and 2D Materials
• e3nn: Euclidean Neural Networks
• Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
• Deep-learning electronic-structure calculation of magnetic superstructures

Cited by in corpus (4)

• 3DReact: Geometric deep learning for chemical reactions
• Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening
• Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design
• FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties