An Accurate and Transferable Machine-Learning Interatomic Potential for Silicon

TL;DR

This paper presents a machine-learning neural network potential for silicon that accurately predicts complex surface reconstructions and reproduces DFT results, offering a transferable and efficient alternative to traditional methods.

Contribution

The authors develop a generalized neural network potential for silicon that achieves high accuracy and transferability, including predicting the Si(111)-(7x7) surface reconstruction.

Findings

Successfully predicts Si(111)-(7x7) surface reconstruction

Accurately reproduces DFT results across various Si structures

Demonstrates transferability to complex silicon systems

Abstract

The development of modern ab initio methods has rapidly increased our understanding of physics, chemistry and materials science. Unfortunately, intensive ab initio calculations are intractable for large and complex systems. On the other hand, empirical force fields are less accurate with poor transferability even though they are efficient to handle large and complex systems. The recent development of machine-learning based neural-network (NN) for local atomic environment representation of density functional theory (DFT) has offered a promising solution to this long-standing challenge. Si is one of the most important elements in science and technology, however, an accurate and transferable interatomic potential for Si is still lacking. Here, we develop a generalized NN potential for Si, which correctly predicts the Si(111)-(7x7) ground-state surface reconstruction for the first time and accurately reproduces the DFT results in a wide range of complex Si structures. We envision similar developments will be made for a wide range of materials systems in the near future.