Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy

TL;DR

This paper introduces PhaseForge, a workflow integrating machine-learning interatomic potentials into phase diagram calculations for alloys, enabling efficient exploration and benchmarking of MLIP accuracy in high-entropy alloys.

Contribution

The paper presents a novel workflow that combines MLIPs with the ATAT framework for efficient phase diagram prediction and benchmarking in alloy research.

Findings

Efficient phase diagram calculations using MLIPs.

Benchmarking MLIP accuracy for alloy thermodynamics.

Application to high-entropy alloys.

Abstract

High-entropy alloys (HEAs) have attracted increasing attention due to their unique structural and functional properties. In the study of HEAs, thermodynamic properties and phase stability play a crucial role, making phase diagram calculations significantly important. However, phase diagram calculations with conventional CALPHAD assessments based on experimental or ab-initio data can be expensive. With the emergence of machine-learning interatomic potentials (MLIPs), we have developed a program named PhaseForge, which integrates MLIPs into the Alloy Theoretic Automated Toolkit (ATAT) framework using our MLIP calculation library, MaterialsFramework, to enable efficient exploration of alloy phase diagrams. Moreover, our workflow can also serve as a benchmarking tool for evaluating the quality of different MLIPs.