Best Practices for Fitting Machine Learning Interatomic Potentials for Molten Salts: A Case Study Using NaCl-MgCl2

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 R2SCAN-rVV10 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.

40 Pages, 9 Figures

References in corpus (6)

• Active learning of linearly parametrized interatomic potentials
• 86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy
• r2SCAN-D4: Dispersion corrected meta-generalized gradient approximation for general chemical applications
• Workhorse minimally-empirical dispersion-corrected density functional, with tests for weakly-bound systems: r${}^2$SCAN+rVV10
• Thermophysical properties of FLiBe using moment tensor potentials
• Studies of Ni-Cr complexation in FLiBe molten salt using machine learning interatomic potentials

Cited by in corpus (2)

• A practical guide to machine learning interatomic potentials -- Status and future
• Machine-Learned Interatomic Potentials for Predicting Physicochemical Properties of Molten Metal-Salt Systems for Calcium Electrolysis