Denoising Raman spectra using a single layer convolutional model trained on simulated data

Raman spectroscopy is a powerful means of revealing chemical and structural information about a sample and acquiring chemically specific images. Such images often suffer from low signal to noise ratios (SNR). In this report, a novel way to improve the SNR using machine learning tools based on simula...

Full description

Saved in:
Bibliographic Details
Published in:Journal of Raman spectroscopy 2023-08, Vol.54 (8), p.814-822
Main Authors: Gil, Eddie M., Cheburkanov, Vsevolod, Yakovlev, Vladislav V.
Format: Article
Language:English
Subjects:
Image acquisition
Machine learning
noise
Noise reduction
Raman imaging
Raman spectra
Raman spectroscopy
Signal to noise ratio
Simulation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Raman spectroscopy is a powerful means of revealing chemical and structural information about a sample and acquiring chemically specific images. Such images often suffer from low signal to noise ratios (SNR). In this report, a novel way to improve the SNR using machine learning tools based on simulated data. The proposed approach offers an alternative to time consuming acquisition and labeling of large data sets and can be readily applied to unknown systems. Here, the efficacy of a single layer denoising network trained only on simulated data was evaluated, and it was found that the proposed model was able to provide a substantial improvement in SNR. The efficacy of training a single layer convolutional network on simulated data against Savitzky–Golay (SG) filtering is evaluated. For low signal to noise ratios, the network is able to outperform SG filtering. This is not the case for high SNR signals.
ISSN:0377-0486
1097-4555
DOI:10.1002/jrs.6559