Water bilayers on ZnO(100) surfaces: data-driven structural search

Abstract

Data science methods hold enormous promise for enhancing the efficiency of multiple aspects of theoretical materials science. Here we demonstrate an approach for the use of data science methods for a structural search for high-stability atomic structures in ab initio simulations, via the analysis of a large set of candidate structures. By partitioning a large data set of structures over an appropriate set of variables, we are able to identify a small fraction of structural space into which all low-energy structures are concentrated. Structural search methods may then be applied in the identified area. The method is demonstrated on the problem of finding stable structures of the water bilayer on the ZnO(100) surface.