Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations

TL;DR

This paper introduces an unsupervised machine learning approach using TS-LPP to analyze local atomic structures in large-scale atomistic simulations, helping to understand complex material phenomena.

Contribution

It presents a novel two-step locality preserving projection method for low-dimensional analysis of local atomic structures in MD simulations.

Findings

Effective in analyzing crystalline, liquid, and amorphous states

Captures local structural distributions accurately

Applicable to various material systems

Abstract

Owing to the advances in computational techniques and the increase in computational power, atomistic simulations of materials can simulate large systems with higher accuracy. Complex phenomena can be observed in such state-of-the-art atomistic simulations. However, it has become increasingly difficult to understand what is actually happening and mechanisms, for example, in molecular dynamics (MD) simulations. We propose an unsupervised machine learning method to analyze the local structure around a target atom. The proposed method, which uses the two-step locality preserving projections (TS-LPP), can find a low-dimensional space wherein the distributions of datapoints for each atom or groups of atoms can be properly captured. We demonstrate that the method is effective for analyzing the MD simulations of crystalline, liquid, and amorphous states and the melt-quench process from the perspective of local structures. The proposed method is demonstrated on a silicon single-component system, a silicon-germanium binary system, and a copper single-component system.