Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution

TL;DR

This paper presents a deep convolutional neural network that automatically identifies chemical species from Raman spectra without preprocessing, achieving superior accuracy over traditional machine learning methods on mineral data.

Contribution

The authors introduce a unified CNN-based approach for Raman spectrum classification that eliminates the need for preprocessing steps like baseline correction or PCA.

Findings

Outperforms support vector machine in classification accuracy

Successfully classifies mineral spectra from the RRUFF database

Simplifies Raman spectrum analysis with an end-to-end deep learning model

Abstract

Machine learning methods have found many applications in Raman spectroscopy, especially for the identification of chemical species. However, almost all of these methods require non-trivial preprocessing such as baseline correction and/or PCA as an essential step. Here we describe our unified solution for the identification of chemical species in which a convolutional neural network is trained to automatically identify substances according to their Raman spectrum without the need of ad-hoc preprocessing steps. We evaluated our approach using the RRUFF spectral database, comprising mineral sample data. Superior classification performance is demonstrated compared with other frequently used machine learning algorithms including the popular support vector machine.