Automated development of molten salt machine learning potentials: Application to LiCl

Ganesh Sivaraman, Jicheng Guo, Logan Ward, Nathaniel Hoyt, Mark Williamson, Ian Foster, Chris Benmore, Nicholas Jackson

Research output: Contribution to journalArticlepeer-review

Abstract

The in silico modeling of molten salts is critical for emerging "carbon-free"energy applications but is inhibited by the cost of quantum mechanically treating the high polarizabilities of molten salts. Here, we integrate configurational sampling using classical force fields with active learning to automate and accelerate the generation of Gaussian approximation potentials (GAP) for molten salts. This methodology reduces the number of expensive ab initio evaluations required for training set generation to O(100), enabling the facile parametrization of a molten LiCl GAP model that exhibits a 19000-fold speedup relative to AIMD. The developed molten LiCl GAP model is applied to sample extended spatiotemporal scales, permitting new physical insights into molten LiCl's coordination structure as well as experimentally validated predictions of structures, densities, self-diffusion constants, and ionic conductivities. The developed methodology significantly lowers the barrier to the in silico understanding and design of molten salts across the periodic table.

Original languageEnglish (US)
Pages (from-to)4278-4285
Number of pages8
JournalJournal of Physical Chemistry Letters
Volume12
Issue number17
DOIs
StatePublished - May 6 2021

ASJC Scopus subject areas

  • Materials Science(all)
  • Physical and Theoretical Chemistry

Fingerprint

Dive into the research topics of 'Automated development of molten salt machine learning potentials: Application to LiCl'. Together they form a unique fingerprint.

Cite this