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

TL;DR

SpectraFormer is a transformer-based deep learning tool that accurately reconstructs and subtracts the SiC substrate Raman signal in graphene samples, enabling better analysis of weak vibrational features without needing reference measurements.

Contribution

This work introduces SpectraFormer, a novel attention-based deep learning model that reconstructs substrate signals directly from mixed Raman spectra, improving analysis of graphene on SiC.

Findings

Accurately reconstructs SiC Raman background without explicit references.

Reveals vibrational features of buffer layer graphene previously hidden.

Validated by ab initio calculations confirming physical relevance.

Abstract

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.