Deep learning assisted Raman spectroscopy for rapid identification of 2D materials

Abstract

Two-dimensional (2D) materials have attracted extensive attention due to their unique characteristics and potential applications. Raman spectroscopy, as a rapid and non-destructive probe, exhibits distinct features and holds notable advantages in the characterization of 2D materials. However, traditional data analysis of Raman spectra relies on manual interpretation and feature extraction, which are both time-consuming and subjective. In this work, we employ deep learning techniques, including classificatory and generative deep learning, to assist the analysis of Raman spectra of representative 2D materials. For the limited and unevenly distributed Raman spectral data, we propose a data augmentation approach based on Denoising Diffusion Probabilistic Models (DDPM) to augment the training dataset and construct a four-layer Convolutional Neural Network (CNN) for 2D material classification. The proposed CNN model achieves an impressive accuracy of 98.8 % on the original dataset. Experiments illustrate the effectiveness of DDPM in addressing data limitations and significantly improving the performance of the classification model. Notably, when enhanced with DDPM-augmented data, the DDPM-CNN method shows high reliability, with 100 % classification accuracy. Our work demonstrates the practicality of deep learning-assisted Raman spectral analysis for high-precision recognition and classification of 2D materials, presenting a promising avenue for rapid and automated materials analysis via spectroscopy.