Liquid–Crystal Structure Inheritance in Machine Learning Potentials for Network-Forming Systems

Abstract

It has been studied whether machine learning interatomic potentials parameterized with only disordered configurations corresponding to liquid can describe the properties of crystalline phases and predict their structure. The study has been performed for a network-forming system SiO2, which has numerous polymorphic phases significantly different in structure and density. Using only high-temperature disordered configurations, a machine learning interatomic potential based on artificial neural networks (DeePMD model) has been parameterized. The potential reproduces well ab initio dependences of the energy on the volume and the vibrational density of states for all considered tetra- and octahedral crystalline phases of SiO2. Furthermore, the combination of the evolutionary algorithm and the developed DeePMD potential has made it possible to reproduce the really observed crystalline structures of SiO2. Such a good liquid–crystal portability of the machine learning interatomic potential opens prospects for the simulation of the structure and properties of new systems for which experimental information on crystalline phases is absent.