Estimating baselines of Raman spectra based on transformer and manually annotated data
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2025-04 · 330 · 125679
DOI: 10.1016/j.saa.2024.125679 ↗Kurz gefasst
Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2025-04. Verfasst von Jiangsan Zhao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Agricultural Technology, Center for Precision Agriculture, Norwegian Institute of Bioeconomy Research (NIBIO), Nylinna 226 2849, Kapp, …. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Norway, Foundation for Research Levy on Agricultural Products, Norsk institutt for Bioøkonomi.
Abstract (Originalsprache)
Raman spectroscopy is a powerful and non-invasive analytical method for determining the chemical composition and molecular structure of a wide range of materials, including complex biological tissues. However, the captured signals typically suffer from interferences manifested as noise and baseline, which need to be removed for successful data analysis. Effective baseline correction is critical in quantitative analysis, as it may impact peak signature derivation. Current baseline correction methods can be labor-intensive and may require extensive parameter adjustment depending on the input spectrum characteristics. In contrast, deep learning-based baseline correction models trained across various materials, offer a promising and more versatile alternative. This study reports an approach to manually identify the ground-truth baselines for eight different biological materials through extensively tuning the parameters of three classical baseline correction methods, Modified Multi-Polynomial Fit (Modpoly), Improved Modified Multi-Polynomial Fitting (IModpoly), and Adaptive Iteratively Reweighted Penalized Least Squares (airPLS), and combining the outputs to best fit the training data. We designed a one-dimensional Transformer (1dTrans) tailored to fit Raman spectral data for estimating their baselines, and evaluated its performance against convolutional neural network (CNN), ResUNet, and three aforementioned parametric methods. The 1dTrans model achieved lower mean absolute error (MAE) and spectral angle mapper (SAM) scores when compared to the other methods in both development and evaluation of the manually labeled original raw Raman spectra, highlighting the effectiveness of the method in Raman spectra pre-processing.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Agricultural Technology, Center for Precision Agriculture, Norwegian Institute of Bioeconomy Research (NIBIO), Nylinna 226 2849, Kapp, Norway. Electronic address: jiangsan.zhao@nibio.no.
- Department of Horticulture, Norwegian Institute of Bioeconomy Research (NIBIO), Nylinna 226 2849, Kapp, Norway.
- Department of Agricultural Technology, Center for Precision Agriculture, Norwegian Institute of Bioeconomy Research (NIBIO), Nylinna 226 2849, Kapp, Norway.
Förderung
- Research Council of Norway
- Foundation for Research Levy on Agricultural Products
- Norsk institutt for Bioøkonomi
Zitieren
APA
Zhao, J., Woznicki, T., & Kusnierek, K. (2025). Estimating baselines of Raman spectra based on transformer and manually annotated data. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 330, 125679. https://doi.org/10.1016/j.saa.2024.125679
Vancouver
Zhao J, Woznicki T, Kusnierek K. Estimating baselines of Raman spectra based on transformer and manually annotated data. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2025;330:125679. doi:10.1016/j.saa.2024.125679
BibTeX
@article{Zhao2025,
author = {Zhao, Jiangsan and Woznicki, Tomasz and Kusnierek, Krzysztof},
title = {Estimating baselines of Raman spectra based on transformer and manually annotated data},
journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
year = {2025},
volume = {330},
pages = {125679},
doi = {10.1016/j.saa.2024.125679}
}
EUVIMED