Data cluster analysis and machine learning for classification of twisted bilayer graphene

TL;DR

This paper introduces a machine learning approach combining Raman spectroscopy and Gaussian mixture models to efficiently identify and classify twist angles in bilayer graphene, facilitating high-throughput fabrication.

Contribution

It presents two novel methods using GMM and PCA for cluster analysis of Raman data to determine twist angles in TBLG, enabling automated and scalable identification.

Findings

GMM can distinguish regions with different twist angles from Raman data.

The approach allows for reapplication to new scans for similarity assessment.

Methods enable automated, high-throughput TBLG characterization.

Abstract

Twisted bilayer graphene (TBLG) has emerged as an exciting new material with tunable electronic properties ranging from superconductivity to correlated insulating phases. But current methods of fabrication and identification of TBLG are painstaking and laborious. In this work, we combine Raman spectroscopy with the Gaussian mixture model (GMM) data clustering algorithm to identify areas with particular twist angles, from a TBLG sample with a mixture of orientations. We present two approaches to this cluster analysis: training the GMM on Raman parameters returned by peak fits, and on full Raman spectra with dimensionality reduced by principal component analysis. In both cases we demonstrate that GMM can identify regions of distinct twist angle from within Raman datacubes. We also show that once a model has been trained, and the identified clusters labelled, the model can be reapplied to new Raman scans to assess the similarity between the materials in the new region and the testing region. This could enable high-throughput fabrication of TBLG, by allowing computerised detection of particular twist angles from automated large-area scans.