Machine-Learned Interatomic Potentials for Predicting Physicochemical Properties of Molten Metal-Salt Systems for Calcium Electrolysis

TL;DR

This paper develops machine-learned interatomic potentials to accurately simulate molten metal-salt systems, enabling efficient prediction of their properties for calcium electrolysis without extensive experiments.

Contribution

It introduces a machine learning approach using Moment Tensor Potentials trained on DFT data to model molten metal-salt systems for the first time.

Findings

Simulations reproduce experimental properties within 20% deviation.

The approach accurately predicts structural, thermodynamic, and transport properties.

Framework facilitates computational exploration of metallurgical liquid systems.

Abstract

The design of efficient electrolysis devices for pure metal production requires accurate data on the properties of the melts used in the process. This work focuses on two key systems for calcium production: the molten Ca-Cu alloy and the CaCl$_2$-KCl electrolyte. High-temperature experiments are often expensive and time-consuming; however, we demonstrate that molecular dynamics (MD) simulations driven by machine-learned Moment Tensor Potentials (MTPs), trained on highly accurate density functional theory data, offer an effective and accurate alternative. Our MTP-driven MD simulations accurately reproduce the structural, thermodynamic, and transport properties across a range of temperatures and compositions relevant to electrolysis systems. We report calculated densities, radial distribution functions, heat capacities, thermal conductivities, ionic conductivities (for the electrolyte), viscosities, and diffusion coefficients, with deviations from experimental data within 20%. The strong agreement between calculations and experiments validates the proposed approach, establishing a robust framework for the computational exploration and optimization of liquid systems in metallurgical applications.