Materials Screening for the Discovery of New Half-Heuslers: Machine Learning versus Ab Initio Methods

Abstract

Machine learning (ML) is increasingly becoming a helpful tool in the search for novel functional compounds. Here we use classification via random forests to predict the stability of half-Heusler (HH) compounds, using only experimentally reported compounds as a training set. Cross-validation yields an excellent agreement between the fraction of compounds classified as stable and the actual fraction of truly stable compounds in the ICSD. The ML model is then employed to screen 71,178 different 1:1:1 compositions, yielding 481 likely stable candidates. The predicted stability of HH compounds from three previous high throughput ab initio studies is critically analyzed from the perspective of the alternative ML approach. The incomplete consistency among the three separate ab initio studies and between them and the ML predictions suggests that additional factors beyond those considered by ab initio phase stability calculations might be determinant to the stability of the compounds. Such factors can include configurational entropies and quasiharmonic contributions.

arXiv comment11 pages, 5 figures, 2 tables

References in corpus (5)

• AFLOW: An automatic framework for high-throughput materials discovery
• A new platform for topological quantum phenomena : Topological Insulator states in thermoelectric Heusler-related ternary compounds
• Representation of compounds for machine-learning prediction of physical properties
• Topological $R$PdBi half-Heusler semimetals: a new family of non-centrosymmetric magnetic superconductors
• Spectral descriptors for bulk metallic glasses based on the thermodynamics of competing crystalline phases