Accurate prediction of structural and mechanical properties on amorphous materials enabled through machine-learning potentials: a case study of silicon nitride

Abstract

Amorphous silicon nitride (a-SiN) is a material which has found wide application due to its excellent mechanical and electrical properties. Despite the significant effort devoted in understanding how the microscopic structure influences the material performance, many aspects still remain elusive. If on the one hand \textit{ab initio} calculations respresent the technique of election to study such a system, they present severe limitations in terms of the size of the system that can be simulated. Such an aspect plays a determinant role, particularly when amorphous structure are to be investigated, as often results depend dramatically on the size of the system. Here, we overcome this limitation by training a machine-learning (ML) interatomic model to \textit{ab initio} data. We show that molecular dynamics simulations using the ML model on much larger systems can reproduce experimental measurements of elastic properties, including elastic isotropy. Our study demonstrates the broader impact of machine-learning potentials for predicting structural and mechanical properties, even for complex amorphous structures.