Predicting the stability of ternary intermetallics with density functional theory and machine learning

We use a combination of machine learning techniques and high-throughput density-functional theory calculations to explore ternary compounds with the AB(2)C(2) composition. We chose the two most common intermetallic prototypes for this composition, namely, the tI10-CeAl2Ga2 and the tP10-FeMo2B2 structures. Our results suggest that there may be similar to 10 times more stable compounds in these phases than previously known. These are mostly metallic and non-magnetic. While the use of machine learning reduces the overall calculation cost by around 75%, some limitations of its predictive power still exist, in particular, for compounds involving the second-row of the periodic table or magnetic elements. Published by AIP Publishing.