SpectraFormer: an Attention-Based Raman Unmixing Tool for Accessing the Graphene Buffer-Layer Signature on SiC

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Poteryayev, Dmitriy, Novelli, Pietro, Coriolano, Annalisa, Dettori, Riccardo, Tozzini, Valentina, Beltram, Fabio, Pontil, Massimiliano, Rossi, Antonio, Forti, Stiven, Coletti, Camilla
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908752912842752
author Poteryayev, Dmitriy
Novelli, Pietro
Coriolano, Annalisa
Dettori, Riccardo
Tozzini, Valentina
Beltram, Fabio
Pontil, Massimiliano
Rossi, Antonio
Forti, Stiven
Coletti, Camilla
author_facet Poteryayev, Dmitriy
Novelli, Pietro
Coriolano, Annalisa
Dettori, Riccardo
Tozzini, Valentina
Beltram, Fabio
Pontil, Massimiliano
Rossi, Antonio
Forti, Stiven
Coletti, Camilla
contents Raman spectroscopy is a key tool for graphene characterization, yet its application to graphene grown on silicon carbide (SiC) is strongly limited by the intense and variable second-order Raman response of the substrate. This limitation is critical for buffer layer graphene, a semiconducting interfacial phase, whose vibrational signatures are overlapped with the SiC background and challenging to be reliably accessed using conventional reference-based subtraction, due to strong spatial and experimental variability of the substrate signal. Here we present SpectraFormer, a transformer-based deep learning model that reconstructs the SiC Raman substrate contribution directly from post-growth partially masked spectroscopic data without relying on explicit reference measurements. By learning global correlations across the entire Raman shift range, the model captures the statistical structure of the SiC background and enables accurate reconstruction of its contribution in mixed spectra. Subtraction of the reconstructed substrate signal reveals weak vibrational features associated with ZLG that are inaccessible through conventional analysis methods. The extracted spectra are validated by ab initio vibrational calculations, allowing assignment of the resolved features to specific modes and confirming their physical consistency. By leveraging a state-of-the-art attention-based deep learning architecture, this approach establishes a robust, reference-free framework for Raman analysis of graphene on SiC and provides a foundation, compatible with real-time data acquisition, to its integration into automated, closed-loop AI-assisted growth optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04445
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SpectraFormer: an Attention-Based Raman Unmixing Tool for Accessing the Graphene Buffer-Layer Signature on SiC
Poteryayev, Dmitriy
Novelli, Pietro
Coriolano, Annalisa
Dettori, Riccardo
Tozzini, Valentina
Beltram, Fabio
Pontil, Massimiliano
Rossi, Antonio
Forti, Stiven
Coletti, Camilla
Materials Science
Artificial Intelligence
Machine Learning
Raman spectroscopy is a key tool for graphene characterization, yet its application to graphene grown on silicon carbide (SiC) is strongly limited by the intense and variable second-order Raman response of the substrate. This limitation is critical for buffer layer graphene, a semiconducting interfacial phase, whose vibrational signatures are overlapped with the SiC background and challenging to be reliably accessed using conventional reference-based subtraction, due to strong spatial and experimental variability of the substrate signal. Here we present SpectraFormer, a transformer-based deep learning model that reconstructs the SiC Raman substrate contribution directly from post-growth partially masked spectroscopic data without relying on explicit reference measurements. By learning global correlations across the entire Raman shift range, the model captures the statistical structure of the SiC background and enables accurate reconstruction of its contribution in mixed spectra. Subtraction of the reconstructed substrate signal reveals weak vibrational features associated with ZLG that are inaccessible through conventional analysis methods. The extracted spectra are validated by ab initio vibrational calculations, allowing assignment of the resolved features to specific modes and confirming their physical consistency. By leveraging a state-of-the-art attention-based deep learning architecture, this approach establishes a robust, reference-free framework for Raman analysis of graphene on SiC and provides a foundation, compatible with real-time data acquisition, to its integration into automated, closed-loop AI-assisted growth optimization.
title SpectraFormer: an Attention-Based Raman Unmixing Tool for Accessing the Graphene Buffer-Layer Signature on SiC
topic Materials Science
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.04445