Construct high performance SERS sensing platform assisted by machine learning

Abstract

Surface-Enhanced Raman Spectroscopy (SERS) is a powerful analytical technique for detecting trace analytes using noble metal nanoparticles. In this paper, we present a novel approach to construct a high-performance SERS sensing platform using self-assembled gold nanoparticles on aminated glass capillaries. The surface self-assembly technology ensures uniformity and repeatability of the SERS substrate, addressing the challenges of poor reproducibility observed in conventional methods. The 30 nm gold nanoparticles exhibit excellent plasmonic properties and biocompatibility, making them ideal candidates for SERS applications. We conducted SERS detection using Rhodamine 6G (R6G) as probe molecules, achieving a minimum detectable concentration of 0.1 nM for the AuNPs/GS substrate and 0.1 pM for the S-AuNPs/GC substrate. The S-AuNPs/GC substrate demonstrated commendable uniformity and repeatability, with a relative standard deviation of 12.1 %. Machine learning techniques, including baseline correction, normalization, and smoothing, were employed for data processing, enhancing the accuracy and reliability of the SERS analysis. By employing the K-means clustering algorithm, we identified three distinct groups of spectral characteristics. Additionally, Principal Component Analysis (PCA) allowed visualization and understanding of the clustering results in a two-dimensional space, capturing approximately 86.74 % of the data's variance. The successful construction of a high-performance SERS sensing platform with enhanced sensitivity, accuracy, and reliability, assisted by machine learning, holds great potential for various applications in chemical sensing, environmental monitoring, and biomedical diagnostics.

Keywords

• Surface-Enhanced Raman Spectroscopy (SERS)
• Self-assembled gold nanoparticles
• Machine learning
• Trace analyte detection
• Uniform SERS substrates