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

• This research integrates deep learning technologies with traditional Raman spectroscopy to analyze two-dimensional (2D) materials, overcoming significant challenges in the field such as limited and uneven data distribution. • This research addresses the existing gaps in rapid and accurate material analysis by employing a Denoising Diffusion Probabilistic Model (DDPM) for data augmentation, followed by a Convolutional Neural Network (CNN) for the classification of these materials. • This methodology not only improves data quality and expands the training dataset but also significantly enhances the classification accuracy, achieving a groundbreaking accuracy rate of 98.8 %, and 100 % when incorporating the DDPM augmentation. 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. Illustration of the DDPM-based data augmentation for Raman Spectroscopy of 2D materials classification framework.