Related Experiment Video
Updated: Aug 5, 2026
09:57
Ultrafast Time-resolved Near-IR Stimulated Raman Measurements of Functional π-conjugate Systems
Published on: February 10, 2020
Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants
Antonio Nocera1, Michela Raimondi1, Lorenzo Luciani2
1Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche, 60131 Ancona, Italy.
Sensors (Basel, Switzerland)
|July 28, 2026
Summary
Raman spectroscopy quantification of nitrate, nitrite, and sulfate accuracy depends on feature selection. Peak-based regression is sensitive to low resolution for nitrate and sulfate, while area-based regression is more stable, except for nitrite where peak-based is better.
Area of Science:
- Analytical Chemistry
- Spectroscopy
- Machine Learning
Background:
- Raman spectroscopy is a powerful tool for chemical analysis.
- Quantifying pollutant concentrations using Raman spectroscopy requires robust methods, especially for low-resolution instruments.
- Feature selection in machine learning models impacts quantification accuracy.
Purpose of the Study:
- To investigate the influence of Raman peak features on the accuracy of pollutant concentration quantification.
- To identify optimal processing strategies for low-resolution Raman spectroscopy.
- To compare peak-based and area-based regression models for inorganic anion quantification.
Main Methods:
- A feature-based machine learning approach was applied to laboratory Raman spectroscopy data.
- Inorganic anion mixtures (nitrate, nitrite, sulfate) in water were analyzed.
- Signal downsampling simulated reduced spectral resolution to test feature robustness.
- Linear regression models were trained using peak- and area-based spectral features.
Main Results:
- Peak-based regression showed higher sensitivity to reduced resolution for nitrate and sulfate.
- Area-based regression demonstrated more stable prediction errors across varying spectral resolutions for nitrate and sulfate.
- For nitrite, peak-based regression was less affected by downsampling, outperforming area-based regression.
- Accurate quantification was achieved: MAE < 7% for nitrate (>3833 mg/L) and < 16% for sulfate (>1916 mg/L) using area-based regression; nitrite errors were within 4% using peak-based regression.
Conclusions:
- The choice between peak-based and area-based regression is crucial for accurate Raman spectroscopic quantification, depending on the analyte and spectral resolution.
- Area-based features offer more stable quantification for nitrate and sulfate under varying resolutions.
- Peak-based features are advantageous for nitrite quantification, particularly at lower resolutions.
Related Concept Videos
01:26Raman Spectroscopy Instrumentation: Overview
A conventional Raman spectrophotometer includes a laser source, a sample holding system, a wavelength selector, and a detector.
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
01:20Raman Spectroscopy: Overview
The underlying principle of Raman spectroscopy is based on the interaction between light and matter, specifically molecules' inelastic scattering of photons. When a monochromatic beam of light, typically from a laser source, interacts with a sample, most scattered light has the same frequency as the incident light. This is known as Rayleigh scattering.
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and the...
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and the...
00:58¹H NMR Signal Integration: Overview
The intensity of a signal, which can be represented by the area under the peak, depends on the number of protons contributing to that signal. The area under each peak is shown as a vertical line called an integral, with the integral value listed under it, as seen in the proton NMR spectrum of benzyl acetate. Each integral value is divided by the smallest integral value to obtain the ratio of the number of protons producing each signal. The ratio reveals the relative number of protons and not...