Fine-tuning of universal machine-learning interatomic potentials for 2D high-entropy alloys

TL;DR

This paper explores how to adapt universal machine-learning interatomic potentials for 2D high-entropy alloys, enabling accurate and scalable simulations that are otherwise computationally prohibitive with traditional methods.

Contribution

The study develops fine-tuning strategies for universal MLIPs to accurately model 2D high-entropy alloys, bridging the gap between universal models and specific complex materials.

Findings

Universal MLIPs need fine-tuning for accurate mixing energies.

Fine-tuned models achieve near-DFT accuracy for (Mo,Ta,Nb,W,V)S₂.

Enables large-scale Monte Carlo simulations beyond DFT capabilities.

Abstract

High-entropy alloys (HEAs) and their two-dimensional counterparts (2D-HEAs) have recently attracted attention due to their tunable properties and catalytic potential, yet their chemical complexity makes direct density functional theory (DFT) calculations computationally prohibitive. The complexity also makes training of machine-learning interatomic potentials (MLIPs) challenging, but this could possibly be overcome by employing universal MLIPs as starting point. In this work, we investigate the applicability of universal MLIP models for 2D transition metal sulfide HEAs and develop effective fine-tuning strategies. Training structures are systematically generated and selected, and the performance of universal and fine-tuned models are benchmarked against DFT. We find that all universal MLIPs employed in this work yield unsatisfactory mixing energies without fine-tuning. Applied to the experimentally synthesized (Mo,Ta,Nb,W,V)S$_2$ system, fine-tuned models based on enumerated structures can achieve near-DFT accuracy in predicting mixing energies while enabling Monte-Carlo simulations and random structure sampling at scales inaccessible to DFT.