Deep Learning for Reconstructing Low-Quality FTIR and Raman SpectraA Case Study in Microplastic Analyses

• Published in: Analytical chemistry (Washington) 2021-12, Vol.93 (49), p.16360-16368
• Main Authors: Brandt, Josef, Mattsson, Karin, Hassellöv, Martin
• Format: Article
• Language: English
• Subjects: Automation; Case-studies; Chemistry; Computational efficiency; Computer applications; Deep Learning; Fourier Analysis; Fourier transform infrared; Fourier transform infrared spectroscopy; Fourier transform Raman; Fourier transforms; Infrared and Raman spectra; Infrared spectra; Infrared spectroscopy; Instrumental noise; Learning methods; Low qualities; Microplastics; Noise; Noise levels; Oceanografi, hydrologi, vattenresurser; Oceanography, Hydrology, Water Resources; Parameter estimation; Parameters; Plastic pollution; Plastics; Raman scattering; Raman spectra; Raman spectroscopy; Signal processing; Signal to noise ratio; Spectra's; Spectral artifacts; Spectroscopy, Fourier Transform Infrared
• ISSN: 0003-2700; 1520-6882
• DOI: 10.1021/acs.analchem.1c02618

Herein we report on a deep-learning method for the removal of instrumental noise and unwanted spectral artifacts in Fourier transform infrared (FTIR) or Raman spectra, especially in automated applications in which a large number of spectra have to be acquired within limited time. Automated batch workflows allowing only a few seconds per measurement, without the possibility of manually optimizing measurement parameters, often result in challenging and heterogeneous datasets. A prominent example of this problem is the automated spectroscopic measurement of particles in environmental samples regarding their content of microplastic (MP) particles. Effective spectral identification is hampered by low signal-to-noise ratios and baseline artifacts as, again, spectral post-processing and analysis must be performed in automated measurements, without adjusting specific parameters for each spectrum. We demonstrate the application of a simple autoencoding neural net for reconstruction of complex spectral distortions, such as high levels of noise, baseline bending, interferences, or distorted bands. Once trained on appropriate data, the network is able to remove all unwanted artifacts in a single pass without the need for tuning spectra-specific parameters and with high computational efficiency. Thus, it offers great potential for monitoring applications with a large number of spectra and limited analysis time with availability of representative data from already completed experiments.