2D Janus Halogenated Silicene database

Recent advances in theoretical computing and machine learning (ML) have facilitated the in-depth exploration of two-dimensional (2D) materials. We combines ML with 2D materials screening with the aim of exploring novel halogenated silicene-based materials for applications in photocatalysis and solar cells. We construct a data-driven framework that combines first-principles computation and self-contained databases for supervised learning to develop highly accurate predictive models. This dataset containing 286 halogenated silicene structures, which is 11.5% of the total database, is obtained after Density-functional theory (DFT) calculations.