Determining the Twist Angle of Bilayer Graphene by Machine Learning Analysis of its Raman Spectrum

TL;DR

This paper introduces a machine learning approach to accurately and efficiently determine the twist angle of bilayer graphene from Raman spectra, enabling non-destructive analysis in graphene research.

Contribution

It presents a low-computational ML classification method that automates twist angle determination from Raman spectra with high accuracy, improving speed and reliability.

Findings

Achieved ~99% agreement with manual labeling

Provided a fast, non-invasive classification method

Demonstrated the use of open-source tools for ML integration

Abstract

With the increasing interest in twisted bilayer graphene (tBLG) of the past years, fast, reliable, and non-destructive methods to precisely determine the twist angle are required. Raman spectroscopy potentially provides such method, given the large amount of information about the state of the graphene that is encoded in its Raman spectrum. However, changes in the Raman spectra induced by the stacking order can be very subtle, thus making the angle identification tedious. In this work, we propose the use of machine learning (ML) analysis techniques for the automated classification of the Raman spectrum of tBLG into a selected range of twist angles. The ML classification proposed here is low computationally demanding, providing fast and accurate results with ~99 % of agreement with the manual labelling of the spectra. The flexibility and non-invasive nature of the Raman measurements, paired with the predictive accuracy of the ML, is expected to facilitate the exploration of the nascent research of tBLG. Moreover, the present work showcases how the currently available open-source tools facilitate the study and integration of ML-based techniques.