Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine learning

TL;DR

This paper demonstrates that a unified atomistic machine learning approach, combined with active learning, can accurately model the complex nanoscale structures of silicon-oxygen compounds across various phases and morphologies.

Contribution

The study introduces a novel active machine learning framework that captures nanoscale heterogeneity in the Si-O system, extending modeling capabilities beyond atomic scales.

Findings

Successfully modeled high-pressure silica structures

Analyzed surfaces and aerogels with the approach

Captured amorphous silicon monoxide structure

Abstract

Silicon-oxygen compounds are among the most important ones in the natural sciences, occurring as building blocks in minerals and being used in semiconductors and catalysis. Beyond the well known silicon dioxide, there are phases with different stoichiometric composition and nanostructured composites. One of the key challenges in understanding the Si-O system is therefore to accurately account for its nanoscale heterogeneity beyond the length scale of individual atoms. Here we show that a unified computational description of the full Si-O system is indeed possible, based on atomistic machine learning coupled to an active-learning workflow. We showcase applications to very-high-pressure silica, to surfaces and aerogels, and to the structure of amorphous silicon monoxide. In a wider context, our work illustrates how structural complexity in functional materials beyond the atomic and few-nanometre length scales can be captured with active machine learning.