Machine-Learning Prediction of the Computed Band Gaps of Double Perovskite Materials

TL;DR

This study develops a machine learning model to predict the band gaps of double perovskite materials efficiently, offering a faster alternative to traditional computational methods with high accuracy.

Contribution

The paper introduces a random forest regression model using physical features to accurately predict double perovskite band gaps, demonstrating the potential for rapid materials screening.

Findings

Achieved 85.6% accuracy with 0.64 eV RMSE using top 10 features.

Identified key features like bulk modulus and cation electronegativity influencing band gaps.

Validated machine learning as a viable tool for materials discovery.

Abstract

Prediction of the electronic structure of functional materials is essential for the engineering of new devices. Conventional electronic structure prediction methods based on density functional theory (DFT) suffer from not only high computational cost, but also limited accuracy arising from the approximations of the exchange-correlation functional. Surrogate methods based on machine learning have garnered much attention as a viable alternative to bypass these limitations, especially in the prediction of solid-state band gaps, which motivated this research study. Herein, we construct a random forest regression model for band gaps of double perovskite materials, using a dataset of 1306 band gaps computed with the GLLBSC (Gritsenko, van Leeuwen, van Lenthe, and Baerends solid correlation) functional. Among the 20 physical features employed, we find that the bulk modulus, superconductivity temperature, and cation electronegativity exhibit the highest importance scores, consistent with the physics of the underlying electronic structure. Using the top 10 features, a model accuracy of 85.6% with a root mean square error of 0.64 eV is obtained, comparable to previous studies. Our results are significant in the sense that they attest to the potential of machine learning regressions for the rapid screening of promising candidate functional materials.