Composition-transferable machine learning potential for LiCl-KCl molten salts validated by high-energy x-ray diffraction

Abstract

Unraveling the liquid structure of multicomponent molten salts is challenging due to the difficulty in conducting and interpreting high-temperature diffraction experiments. Motivated by this challenge, we developed composition-transferable Gaussian approximation potential (GAP) for molten LiCl-KCl. A DFT-SCAN accurate GAP is active-learned from only $\ensuremath{\sim}$1100 training configurations drawn from 10 unique mixture compositions enriched with metadynamics. The GAP-computed structures show strong agreement across high-energy x-ray diffraction experiments, including for a eutectic not explicitly included in model training, thereby opening the possibility of composition discovery.