Systematic Atomic Structure Datasets for Machine Learning Potentials: Application to Defects in Magnesium

Abstract

We present a physically motivated strategy for the construction of training sets for transferable machine learning interatomic potentials. It is based on a systematic exploration of all possible space groups in random crystal structures, together with deformations of cell shape, size, and atomic positions. The resulting potentials turn out to be unbiased and generically applicable to studies of bulk defects without including any defect structures in the training set or employing any additional Active Learning. Using this approach we construct transferable potentials for pure Magnesium that reproduce the properties of hexagonal closed packed (hcp) and body centered cubic (bcc) polymorphs very well. In the process we investigate how different types of training structures impact the properties and the predictive power of the resulting potential.

References in corpus (2)

• Dislocation Core Energies and Core Fields from First Principles
• Exploring the robust extrapolation of high-dimensional machine learning potentials

Cited by in corpus (6)

• Developments and Further Applications of Ephemeral Data Derived Potentials
• Modeling Extensive Defects in Metals through Classical Potential-Guided Sampling and Automated Configuration Reconstruction
• Development of an Atomic Cluster Expansion potential for iron and its oxides
• Universal machine learning interatomic potentials poised to supplant DFT in modeling general defects in metals and random alloys
• Automated atomistic simulations of dissociated dislocations with ab initio accuracy
• SPEA -- an analytical thermodynamic model for defect phase diagram