The utility of composition-based machine learning models for band gap prediction

Given the importance of band gaps in electronic and optoelectronics applications, methods that can reliably predict the band gap of any material are in demand. Here, we show that the rule-based ensemble Cubist model that uses descriptors derived from elemental compositions, provides rapid and accurate estimates of experimental band gaps. The generalizability of the model was tested using two independent test sets, both of which yielded squared correlations > 0.85. The model was also found to yield lower errors compared with most density functionals specifically crafted for the determination of band gaps. Furthermore, the inclusion of a distance based model domain applicability metric facilitates the assessment of the reliability of the model predictions, thereby improving prospective screening performance.

Automated summary

The study demonstrated the successful prediction of experimental band gaps using a rule-based ensemble Cubist model with descriptors derived from elemental compositions, showing rapid and accurate predictive capabilities. The model exhibited good generalizability, low errors, and better prediction performance compared to most density functionals specifically designed for band gap determination. Additionally, the inclusion of a distance-based model domain applicability metric improved the assessment of model predictions, enhancing prospective screening performance.