• Citation: S. Attarian, C. Shen, D. Morgan, and I. Szlufarska (2025), "Best practices for fitting machine learning interatomic potentials for molten salts: A case study using NaCl-MgCl2", Computational Materials Science 246, 113409. DOI: 10.1016/j.commatsci.2024.113409.
    Abstract: In this work, we developed a compositionally transferable machine learning interatomic potential using atomic cluster expansion potential and PBE-D3 method for (NaCl)1-x(MgCl2)x molten salt and we showed that it is possible to fit a robust potential for this pseudo-binary system by only including data from x={0, 1/3, 2/3, 1}. We also assessed the performance of several DFT methods including PBE-D3, PBE-D4, R2SCAN-D4, and R2SCANrVV10 on unary NaCl and MgCl2 salts. Our results show that the R2SCAN-D4 method calculates the thermophysical properties of NaCl and MgCl2 with an overall modestly better accuracy compared to the other three methods.

    Notes: This listing is for the NaCl-MgCl2 model referred to as "Pot_3" in the paper that used PBE_D3 data.

  • See Computed Properties
    Notes: These files were provided by Sergei Starikov on July 15, 2026. The .yaml file is the fitted potential in the original format, while the .yace file is in the LAMMPS-compatible format. The link was pulled from the paper and contains all associated potentials and training and testing data.
    File(s): Link(s):
Date Created: October 5, 2010 | Last updated: August 12, 2026