Related Experiment Video
Updated: Feb 21, 2026
Author Spotlight: Development and Application of SERS Flexible Substrates Using Synthesized AgNPs
Published on: November 17, 2023
Machine learning assisted SERS detection of selenium species using a sodium alginate/silver hydrogel substrate
Ziqi Zhang1, Zhixi Zhao1, Huaqing Ling1
1College of Chemistry and Chemical Engineering, Xinjiang Normal University, Urumqi 830054, China; Xinjiang Key Laboratory of Energy Storage and Photoelectroctalytic Materials, Urumqi 830054, China; Technical Research Center for Environmental Geotechnical Engineering Restoration and Resource Utilization, Xinjiang Normal University, Urumqi 830054, China.
Researchers developed a novel hydrogel-based sensing platform for fast and accurate selenium speciation analysis in environmental samples. This method integrates surface-enhanced Raman scattering (SERS) with machine learning for reliable detection of selenium(IV) and selenium(VI).
Area of Science:
- Environmental Science
- Analytical Chemistry
- Materials Science
Background:
- Selenium (Se) is an essential trace element with a narrow window between nutritional needs and toxicity.
- Accurate and rapid detection of selenium speciation in environmental matrices is crucial for risk assessment.
- Existing methods for selenium speciation can be time-consuming and lack portability.
Purpose of the Study:
- To develop a portable, stable, and highly sensitive sensing platform for rapid qualitative and quantitative analysis of selenium speciation.
- To synthesize and characterize sodium alginate/silver nanoparticles (SA/Ag NPs) hydrogel substrates for surface-enhanced Raman scattering (SERS).
- To evaluate the performance of machine learning algorithms for identifying and quantifying selenium species in real samples.
Main Methods:
- Synthesis of SA/Ag NPs hydrogel substrates via Ca2+ ion crosslinking.
- Characterization of hydrogel properties, including uniformity, reproducibility, stability, and enhancement factor (EF).
- Application of SERS for detecting Se(IV) and Se(VI) with subsequent analysis using machine learning models (PLS-DA, PCA-DA, KNN, SVM, PLSR, SVR).
Main Results:
- The SA/Ag NPs hydrogel substrate demonstrated excellent uniformity, reproducibility, and stability with an EF of 109.
- Achieved low detection limits for Se(IV) (3.35 μg/L) and Se(VI) (3.37 μg/L).
- The Support Vector Machine (SVM) model showed 90.0% accuracy for classification, and the Support Vector Regression (SVR) model achieved R2 > 0.8958 for quantification.
Conclusions:
- A reliable framework integrating a hydrogel SERS substrate and machine learning algorithms was established for selenium speciation analysis.
- The developed sensing platform offers a promising solution for rapid and accurate on-site monitoring of selenium in complex environmental samples.
- The study highlights the potential of SERS-based hydrogel substrates combined with chemometrics for environmental trace element analysis.
