A1 Vertaisarvioitu alkuperäisartikkeli tieteellisessä lehdessä
RADAR: Raman Spectral Analysis Using Deep Learning for Artifact Removal
Tekijät: Sjöberg, Joel; Siminea, Nicoleta; Paun, Andrei; Lita, Adrian; Larion, Mioara; Petre, Ion
Kustantaja: WILEY-V C H VERLAG GMBH
Kustannuspaikka: WEINHEIM
Julkaisuvuosi: 2025
Journal: Advanced Optical Materials
Tietokannassa oleva lehden nimi: ADVANCED OPTICAL MATERIALS
Lehden akronyymi: ADV OPT MATER
Artikkelin numero: 2500736
Sivujen määrä: 14
eISSN: 2195-1071
DOI: https://doi.org/10.1002/adom.202500736
Verkko-osoite: https://doi.org/10.1002/adom.202500736
Rinnakkaistallenteen osoite: https://research.utu.fi/converis/portal/detail/Publication/499203657
Raman spectroscopy is a non-destructive analytical technique that reveals molecular vibrations, enabling precise identification of chemical compounds and material properties. Its spatial resolution and compatibility with microscopic imaging allow for high-resolution chemical mapping of heterogeneous samples. However, spectral artifacts such as baseline drift, cosmic rays, and instrumental noise complicate data interpretation, necessitating correction. RADAR is introduced, two lightweight deep learning models for artifact removal, capable of simultaneous denoising and correction of Raman spectra, significantly accelerating high-quality data acquisition. The models help reduce the data acquisition time by 90% while preserving signal integrity, as demonstrated on noisy spectra from a diversity of samples, biological and non-biological. These models are versatile and can be readily applied to novel Raman datasets, offering an order-of-magnitude improvement in acquisition efficiency. This work advances Raman spectroscopy as a faster, more reliable tool for chemical analysis, with broad applications in materials science, biomedical research, and beyond.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
Julkaisussa olevat rahoitustiedot:
This project was partially supported by the Foundation of the University of Turku (the Niilo and Helmi Näsänen Fund and the Pentti and Tyyni Ekbom Fund), by the Swedish Cultural Foundation, and by the Core Program within the Romanian National Research, Development and Innovation Plan 2022-2027, carried out with the support of MRID (project no. 23020101(SIA-PRO), contract no. 7N/2022 and project PNRR-I8, contract CF 68), and by the Digital Europe Programme project LLMs4EU with ID. 101198470. Open access publishing facilitated by Turun yliopisto, as part of the Wiley - FinELib agreement.
