Deep Learning for Raman Spectroscopy: A Review

Abstract

Raman spectroscopy (RS) is a spectroscopic method which indirectly measures the vibrational states within samples. This information on vibrational states can be utilized as spectroscopic fingerprints of the sample, which, subsequently, can be used in a wide range of application scenarios to determine the chemical composition of the sample without altering it, or to predict a sample property, such as the disease state of patients. These two examples are only a small portion of the application scenarios, which range from biomedical diagnostics to material science questions. However, the Raman signal is weak and due to the label-free character of RS, the Raman data is untargeted. Therefore, the analysis of Raman spectra is challenging and machine learning based chemometric models are needed. As a subset of representation learning algorithms, deep learning (DL) has had great success in data science for the analysis of Raman spectra and photonic data in general. In this review, recent developments of DL algorithms for Raman spectroscopy and the current challenges in the application of these algorithms will be discussed.

Optical photothermal infrared spectroscopy with simultaneously acquired Raman spectroscopy for two-dimensional microplastic identification

“…With advances in analytical techniques and a growing interest in MP research, the need for reliable detection methods and the need for standardization have been rising 12 – 16 . Modern analysis methods such as machine learning were applied to spectral data of MPs 17 and demonstrated to minimize identification errors and improve the accuracy of the data analysis 18 , 19 . The international organization of standards summarizes the state of knowledge and methodology of MP detection and methods for analysis 20 .…”

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

“…With the ease of data collection and availability of open source Raman spectroscopy data, SERS has also seen a surge in machine learning models [ 49 , 351 , 352 ]. The trend is welcoming and desirable as the nature of existing challenges in SERS involving trace detection, signal fluctuations, quantification and identification are complex with many variables calling for an analytical tool that has the ability to capture the patterns devoid of experts [ 353 ].…”

Recurrent neural networks for time domain modelling of FTIR spectra: application to brain tumour detection

“…Deep learning techniques have been employed for various types of spectral analysis including Raman spectroscopy, 11 spectral imaging 12 and FTIR vibrational spectroscopy. 13 Convolutional Neural Networks (CNNs) in particular (see Schmidhuber 14 and references therein), which have emerged in computer vision, can provide a powerful alternative to traditional machine learning algorithms for these tasks mainly for their ability to extract spectral and local spatial patterns.…”