SuperSalt: Equivariant Neural Network Force Fields for Multicomponent Molten Salts System

TL;DR

SuperSalt is a machine learning interatomic potential that accurately models multicomponent molten salts, enabling efficient property prediction and accelerated discovery for clean energy applications.

Contribution

We developed SuperSalt, a transferable MLIP for multicomponent molten salts, combining physics-based accuracy with efficient workflows and Bayesian optimization.

Findings

SuperSalt achieves near-DFT accuracy in property predictions.

The model demonstrates excellent transferability across diverse chemical spaces.

Bayesian optimization with SuperSalt accelerates salt composition discovery.

Abstract

Molten salts are crucial for clean energy applications, yet exploring their thermophysical properties across diverse chemical space remains challenging. We present the development of a machine learning interatomic potential (MLIP) called SuperSalt, which targets 11-cation chloride melts and captures the essential physics of molten salts with near-DFT accuracy. Using an efficient workflow that integrates systems of one, two, and 11 components, the SuperSalt potential can accurately predict thermophysical properties such as density, bulk modulus, thermal expansion, and heat capacity. Our model is validated across a broad chemical space, demonstrating excellent transferability. We further illustrate how Bayesian optimization combined with SuperSalt can accelerate the discovery of optimal salt compositions with desired properties. This work provides a foundation for future studies that allows easy extensions to more complex systems, such as those containing additional elements. SuperSalt represents a shift towards a more universal, efficient, and accurate modeling of molten salts for advanced energy applications.