Sökning: onr:"swepub:oai:gup.ub.gu.se/313497" >
Deep Learning for R...
Deep Learning for Reconstructing Low-Quality FTIR and Raman Spectra─A Case Study in Microplastic Analyses
-
- Brandt, Josef (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för marina vetenskaper,Department of marine sciences
-
- Mattsson, Karin (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för marina vetenskaper,Department of marine sciences
-
- Hassellöv, Martin, 1970 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för marina vetenskaper,Department of marine sciences
-
(creator_code:org_t)
- 2021-11-22
- 2021
- Engelska.
-
Ingår i: Analytical Chemistry. - : American Chemical Society (ACS). - 0003-2700 .- 1520-6882. ; 93:49, s. 16360-16368
- Relaterad länk:
-
https://pubs.acs.org...
-
visa fler...
-
https://gup.ub.gu.se...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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. © 2021 The Authors. Published by American Chemical Society.
Ämnesord
- NATURVETENSKAP -- Geovetenskap och miljövetenskap -- Oceanografi, hydrologi och vattenresurser (hsv//swe)
- NATURAL SCIENCES -- Earth and Related Environmental Sciences -- Oceanography, Hydrology and Water Resources (hsv//eng)
Nyckelord
- Automation
- Deep learning
- Fourier transform infrared spectroscopy
- Parameter estimation
- Raman scattering
- Signal to noise ratio
- Case-studies
- Fourier transform infrared
- Fourier transform Raman
- Infrared and Raman spectra
- Instrumental noise
- Learning methods
- Low qualities
- Microplastics
- Spectra's
- Spectral artifacts
- Computational efficiency
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas