Automated parameterization of the atomic cluster expansion for predicting phase stability and mechanical properties

The atomic cluster expansion (ACE) provides a general and mathematically complete representation of the properties of interacting atoms [1-3]. ACE has been implemented in the LAMMPS molecular dynamics simulation software package and its numerical efficiency is competitive or superior to other ML potentials [4]. In this presentation I will focus on the parameterization of ACE from first principles reference data and the computation of thermodynamic and mechanical properties.

Three factors are critical for obtaining accurate and transferable ACE, (i) an extensive, diverse and high-quality reference dataset, (ii) a robust and efficient training procedure, and (iii) a thorough validation including assessment of uncertainty. I will show how our parameterization strategy incorporates the three factors and enables near automatic construction and convergence of ACE. I will then discuss ACE for a number of elements, compounds and molecules and review their properties against reference data. Analysis of mechanical properties and automated free energy and phase diagram calculations [5] will be presented. A perturbation analysis of uncertainties and limitations of the reference data enables error estimates for the phase diagrams.

 

[1] R.  Drautz, Phys. Rev. B99, 014104 (2019).

[2]  G. Dusson, M. Bachmayr, G. Csanyi, R. Drautz, S. Etter, C. van der Oord, and C. Ortner, (2020), arXiv:1911.03550v3.

[3] R. Drautz, Phys. Rev. B102, 024104 (2020).

[4] Y. Lysogorskiy, C. van der Oord, A. Bochkarev, S. Menon, M. Rinaldi, T. Hammerschmidt, M. Mrovec, A. Thompson, G. Csanyi, C. Ortner, et al., Npj  Computational Materials  (2021).

[5] S. Menon, Y. Lysogorskiy, J. Rogal, and R. Drautz, Phys. Rev. Materials 5, 103801 (2021).