An equivariant graph neural network for the elasticity tensors of all seven crystal systems
Mingjian Wen, Matthew K. Horton, Jason M. Munro, Patrick Huck, Kristin A. Persson
Abstract
An equivariant graph neural network model enables the rapid and accurate prediction of complete fourth-rank elasticity tensors of inorganic materials, facilitating the discovery of materials with exceptional mechanical properties.
Topics & Concepts
Equivariant mapElasticity (physics)GraphMathematicsPure mathematicsMaterials scienceDiscrete mathematicsComposite materialMachine Learning in Materials ScienceX-ray Diffraction in CrystallographyMaterial Properties and Failure Mechanisms