ML-aided computational screening of 2D materials for photocatalytic water splitting

The exploration of two-dimensional (2D) materials with exceptional physical and chemical properties is essent ial for the advancement of solar water-splitting technologies. However, the discovery of 2D materials is currently heavily reliant on fragmented studies with limited opportunities for fine-tuning the chemical composition and electronic features of compounds. Here, we apply a combination of machine learning (ML) and physics-based computation to evaluate the V2DB digital library, which contains an extensive collection of 2D materials for their potential use in photocatalytic water splitting. To examine the structural and electronic properties of the potential 2D photocatalysts, we utilize a computational funnel approach that integrates ML modeling, as well as DFT, hybrid-DFT, and GW calculations. Our screening process yields a selection of 11 promising 2D photocatalysts. Consequently, our study not only unearths previously unexplored 2D potential photocatalysts but also introduces an effective screening methodology that may serve as a model for accelerating 2D materials discovery within a large chemical space.