Machine-Learning-Assisted Construction of Ternary Convex Hull Diagrams

TL;DR

This paper presents a machine-learning workflow that accelerates the construction of accurate ternary convex hull diagrams, reducing reliance on extensive DFT calculations and enabling efficient materials discovery in alloy systems.

Contribution

The authors introduce a novel workflow integrating machine-learning spectral neighbor-analysis potentials with DFT to efficiently generate ternary convex hull diagrams without additional first-principles data.

Findings

Workflow achieves DFT-level accuracy in convex hull construction.

Successfully applied to Cu-Ag-Au and Mo-Ta-W systems.

Reduces computational cost compared to traditional methods.

Abstract

In the search for novel intermetallic ternary alloys, much of the effort goes into performing a large number of ab-initio calculations covering a wide range of compositions and structures. These are essential to build a reliable convex hull diagram. While density functional theory (DFT) provides accurate predictions for many systems, its computational overheads set a throughput limit on the number of hypothetical phases that can be probed. Here, we demonstrate how an ensemble of machine-learning spectral neighbor-analysis potentials (SNAPs) can be integrated into a workflow for the construction of accurate ternary convex hull diagrams, highlighting regions fertile for materials discovery. Our workflow relies on using available binary-alloy data both to train the SNAP models and to create prototypes for ternary phases. From the prototype structures, all unique ternary decorations are created and used to form a pool of candidate compounds. The SNAPs are then used to pre-relax the structures and screen the most favourable prototypes, before using DFT to build the final phase diagram. As constructed, the proposed workflow relies on no extra first-principles data to train the machine-learning surrogate model and yields a DFT-level accurate convex hull. We demonstrate its efficacy by investigating the Cu-Ag-Au and Mo-Ta-W ternary systems.