Data-driven Discovery of Photoactive Quaternary Oxides using First-principles Machine Learning
Published in Chemistry of Materials, 2019
Recommended citation: D W Davies, K T Butler and A Walsh. "Data-driven Discovery of Photoactive Quaternary Oxides using First-principles Machine Learning" Chem. Mater., 31 (2019).
In this work we use a series of cheap, data-driven filters to screen through a million possible quaternary oxides to identify new photoactive semiconductors. This includes a supervised learning model to predict band gap, trained on a pre-existing database of accurately calculated values.
