Molecular Dynamics simulations of Al-Ti metallic alloy melts using a transferable machine-learning potential

TL;DR

This study uses machine-learning-enhanced molecular dynamics to accurately simulate the structural and dynamical properties of Al-Ti liquid alloys, aligning well with experimental data despite the potential being trained on solid properties.

Contribution

It demonstrates the effectiveness of a transferable machine-learning potential in modeling liquid metallic alloys, extending its applicability beyond solid-state properties.

Findings

Good agreement with experimental data for liquid properties

Weak chemical-ordering effects in Al-Ti alloys

Successful disentangling of local packing and chemical ordering

Abstract

We investigate the structural and dynamical properties of binary aluminum-titanium liquid metallic alloys, as a function of temperature and composition. We make use of MD-simulations, using a transferable machine-learning potential developed by Song et al. [Nature Communications 15, 10208 (2024)], and compare our results to experimental data. Although this potential was initially trained on solid properties, we find good agreement between the experimental data and the simulation results for the liquid state. The excess volume and compositional changes of the structure are captured well by the machine-learned potential. The simulation allows to disentangle local packing from chemical-ordering effects; the latter are found to be weak in Al-Ti. Dynamical quantities like the viscosity and the diffusion coefficients are also discussed.