Machine Learning Bandgaps of Inorganic Mixed Halide Perovskites

The identification of suitable lead-free perovskites is crucial for their envisioned applications in photovoltaics. Efficient and accurate vetting of these compounds for a range of properties has recently been accomplished in high-throughput studies by use of statistical learning methods. Here we demonstrate how one such property, the fundamental bandgap, can be predicted for a family of inorganic mixed halide perovskites using fingerprints based solely on the atomic arrangement of the unit cell. Important trends and experimentally accessible factors controlling this property are thereby illuminated in a chemically intuitive manner.