Identification of the Contributing Factors to the Photoelectric Conversion Efficiency for Hematite Photoanodes by Using Machine Learning.

Hematite has gained significant attention in the field of photocatalysis as one of the most promising materials for the photoanode of photoelectrochemical (PEC) water splitting due to visible light absorption and the abundance of availability. However, its performance improvement process suffers from a serious bottleneck due to "sample variation" and "inactivity". However, the physical origin of them has not yet been elucidated. To address these issues, we have developed a machine learning (ML) strategy using a combination of various analytical data of hematite photoanodes to discern "active/inactive" and identify the dominant factors. For the demonstration purpose of the ML strategy, we picked up one of the dominant factors, the interfacial resistivity between hematite and FTO, which has not generally been explored as a first candidate in the improvement of photocatalytic materials. The operational parameters for the sample preparation were optimized to modify the selected physical property. Along with the improvement of the selected resistivity, we found that the other dominant descriptors related to the properties of bulk hematite and the surface facet were also modified and help improve the PEC performance.