Double perovskite oxides A<sub>2</sub>BB'O<sub>6</sub> have better stability and wider bandgap range than ABO<sub>3</sub>-type oxides, which exhibit great prospects in photocatalytic overall water splitting. However, due to the diversity of crystal structures and constituents of perovskite oxides, rapid and accurate searching of A<sub>2</sub>BB'O<sub>6</sub> for photocatalyst is still a big challenge, both experimentally and theoretically. In this work, in order to screen out suitable double perovskite oxide photocatalysts, a multi-step framework combined machine learning technique and first-principles calculations is proposed. Nearly 8,000 candidates with proper bandgaps for water splitting are screened out from more than 50,000 A<sub>2</sub>BB'O<sub>6</sub>-type double perovskite oxides. Statistical analysis of the results shows that double perovskite oxides with d<sup>10</sup> metal ions at B/B' sites are more likely to have good absorption of visible light, and the structural symmetry of double perovskites also has influence on the bandgap values. Furthermore, first-principles calculations demonstrate that Sr<sub>2</sub>GaSbO<sub>6</sub>, Sr<sub>2</sub>InSbO<sub>6</sub> and K<sub>2</sub>NbTaO<sub>6</sub> are non-toxic photocatalyst candidates with proper band edges for overall water splitting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.