EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants

Antonio Nocera iD, Michela Raimondi, Lorenzo Luciani iD, Laura Burattini iD, Laura Falaschetti iD, Rossana Galassi iD

Sensors · 17.07.2026 · 26 (14) · 4552

DOI: 10.3390/s26144552 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.07.2026. Verfasst von Antonio Nocera und 5 weiteren Autor:innen. Beteiligte Einrichtung: Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche, 60131 Ancona, Italy. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Italian Ministry for Enterprise and Made in Italy 404 - DM 31/12/2021 and Agreements for Innovation 16/11/2023.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates how Raman peak features influence the accuracy of pollutant concentration quantification in Raman spectroscopy using feature-based machine learning. A Raman peak feature-based approach is applied to data acquired from laboratory Raman equipment for inorganic anion mixtures, with the objective of identifying processing strategies suitable for low-resolution Raman instruments. A dataset comprising nitrate, nitrite, and sulphate dissolved in water at varying concentrations was used to develop a pre-processing pipeline, train and validate models, and perform linear regression using peak- and area-based features extracted from analyte-specific spectral fingerprint regions. Signal downsampling was employed to simulate reduced spectral resolution and evaluate feature robustness under peak broadening conditions. Results indicate that peak-based regression is more sensitive to reduced peak resolution for nitrate and sulphate, whereas area-based regression produces more stable prediction errors across downsampling factors. Conversely, for nitrite, peak-based regression is less affected by downsampling, while area-based regression exhibits degraded performance. Area-based regression achieved mean absolute percentage errors below 7% and 16% for nitrate concentrations above 3833 mg/L and 1916 mg/L, respectively, and generally below 16% for sulphate concentrations above 1916 mg/L. For nitrite, peak-based regression yielded errors within 4%.

Schlagwörter

Stichwörter der Autor:innen

Raman spectroscopymachine learningnitratenitritequantificationsulphatewater analysis

Autor:innen und Institutionen

  • Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche, 60131 Ancona, Italy.
  • Scuola di Scienze e Tecnologie, Chemistry Division, Università di Camerino, 62032 Camerino, Italy.

ORCID-Profile: Antonio Nocera, Lorenzo Luciani, Laura Burattini, Laura Falaschetti, Rossana Galassi

Förderung

  • Italian Ministry for Enterprise and Made in Italy 404 - DM 31/12/2021 and Agreements for Innovation 16/11/2023

Zitieren

APA

Nocera, A., Raimondi, M., Luciani, L., Burattini, L., Falaschetti, L., & Galassi, R. (2026). Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants. Sensors, 26(14), 4552. https://doi.org/10.3390/s26144552

Vancouver

Nocera A, Raimondi M, Luciani L, Burattini L, Falaschetti L, Galassi R. Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants. Sensors. 2026;26(14):4552. doi:10.3390/s26144552

BibTeX
@article{Nocera2026,
  author = {Nocera, Antonio and Raimondi, Michela and Luciani, Lorenzo and Burattini, Laura and Falaschetti, Laura and Galassi, Rossana},
  title = {Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4552},
  doi = {10.3390/s26144552}
}
Kostenlos starten →