Machine Learning Force Field for Thermal Oxidation of Silicon

TL;DR

This paper develops a machine learning force field trained on DFT data to accurately simulate the thermal oxidation of silicon, bridging the gap between computational efficiency and high accuracy.

Contribution

It introduces a novel ML force field for silicon oxidation, achieving ab-initio accuracy with lower computational costs and improved structural predictions over classical methods.

Findings

Structures align with ab-initio and experimental data

Outperforms classical force fields like reaxFF

Enables efficient and accurate simulation of silicon oxidation

Abstract

Looking back at seven decades of highly extensive application in the semiconductor industry, silicon and its native oxide SiO$_2$ are still at the heart of several technological developments. Recently, the fabrication of ultra-thin oxide layers has become essential for keeping up with trends in down-scaling of nanoelectronic devices and for the realization of novel device technologies. With this comes a need for better understanding of the atomic configuration at the Si/SiO$_2$ interface. Classical force fields offer flexible application and relatively low computational costs, however, suffer from limited accuracy. Ab-initio methods give much better results but are extremely costly. Machine learning force fields (MLFF) offer the possibility to combine the benefits of both worlds. We train a MLFF for the simulation of the dry thermal oxidation process of a Si substrate. The training data is generated by density functional theory calculations. The obtained structures are in line with ab-initio simulations as well as with experimental observations. Compared to a classical force field, the most recent reactive force field (reaxFF), the resulting configurations are vastly improved.