Machine learning for rapid quantification of trace analyte molecules using SERS and flexible plasmonic paper substrates

Abstract

Given the intrinsic nature of low reproducibility and signal blinking in the surface enhanced Raman scattering (SERS) technique, especially while detecting trace/ultra-trace amounts, it remains a major challenge to quantify the analyte under study. Here we present a simple and economically viable, flexible hydrophobic plasmonic filter paper-based SERS substrate for the quantification of two trace analytes [crystal violet (CV) and picric acid (PA)] using machine learning techniques and SERS data. The wettability of the substrate was modified with an easy and low-cost technique of coating it with silicone oil. Gold nanoparticles were synthesized using a femtosecond laser ablation in water technique. The prepared nanoparticles were characterized using UV, TEM, and SEM techniques and subsequently loaded onto filter papers before using them for SERS studies. We have considered the SERS intensities of the analytes at different concentrations with over 900 spectra to train the model. Principal component analysis (PCA) was used to reduce the dimensionality and, hence, the complexity of the model. Furthermore, support vector regression was used to quantify the analyte molecules and we achieved an R² error of 0.9629 for CV and 0.9472 for PA. In conjunction with a portable Raman spectrometer and a computation time of less than <10 s, we believe that this is an affordable and rapid method for quantification of analytes using the SERS technique.