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

## TL;DR

This study compares machine learning and ab initio methods for predicting the stability of half-Heusler compounds, demonstrating ML's effectiveness in screening large compound spaces and highlighting discrepancies among different computational approaches.

## Contribution

It introduces a random forest classifier trained on experimental data to predict half-Heusler stability and critically analyzes its predictions against ab initio results.

## Key findings

- ML achieves high accuracy in predicting stable compounds.
- Screened 71,178 compositions, identifying 481 likely stable candidates.
- Discrepancies among ab initio studies and ML suggest additional stability factors.

## 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.