Machine learning formation enthalpies of intermetallics

TL;DR

This paper introduces a machine learning model that accurately predicts formation enthalpies of binary intermetallics using simple elemental properties, enabling rapid discovery of new intermetallic compounds for alloy design.

Contribution

The study presents a novel ML model with low MAE for predicting intermetallic formation enthalpies, extending its application to ternary systems and identifying new stable compounds.

Findings

MAE of 0.025 eV/atom in predictions

Predicted 112 new stable intermetallics

Confirmed NbV2 as a stable intermetallic via DFT

Abstract

Developing fast and accurate methods to discover intermetallic compounds is relevant for alloy design. While density-functional-theory (DFT)-based methods have accelerated design of binary and ternary alloys by providing rapid access to the energy and properties of the stable intermetallics, they are not amenable for rapidly screening the vast combinatorial space of multi-principal element alloys (MPEAs). Here, a machine-learning model is presented for predicting the formation enthalpy of binary intermetallics and used to identify new ones. The model uses easily accessible elemental properties as descriptors and has a mean absolute error (MAE) of 0.025 eV/atom in predicting the formation enthalpy of stable binary intermetallics reported in the Materials Project database. The model further predicts stable intermetallics to form in 112 binary alloy systems that do not have any stable intermetallics reported in the Materials Project database. DFT calculations confirm one such stable intermetallic identified by the model, NbV2 to be on the convex hull. The model trained with binary intermetallics can also predict ternary intermetallics with similar accuracy as DFT, which suggests that it could be extended to identify compositionally complex intermetallics that may form in MPEAs.