The rapid and accurate identification of complex samples still remains a great challenge, especially for those with similar compositions. In this work, we report an integration strategy consisting of surface‐enhanced Raman scattering (SERS) and machine learning to discriminate complex and similar analytes, in this case green tea products with different storage times. Surface‐functionalized Ag nanoparticles (NPs) were used as a SERS substrate to reveal the changes in the sensory components of green tea with variable storage time. Principal components analysis (PCA)‐based support vector machine (SVM) classification was used to extract the key spectral features and identify green tea with different storage times. The results showed that such an integration strategy achieved high predictive accuracy on time tag discrimination for green tea. The multiclass SVM classifier successfully recognized green tea with different storage times at a prediction accuracy of 95.9%, sensitivity of 96.6%, and specificity of 98.8%. Therefore, this work illustrates that the SERS‐based PCA‐SVM platform might be a facile and reliable tool for the identification of complex matrices with subtle differentiations.

In this study, a surface-enhanced Raman scattering (SERS) substrate based on high-refractive-index reflective glass beads (HRGBs) was prepared by a facile method and successfully applied to the detection of polycyclic aromatic hydrocarbons (PAHs). The HRGB-SERS substrate was prepared by depositing silver nanoparticles (Ag NPs) onto the surface of HRGBs. The preparation procedure of the substrate was simplified by accelerating the hydrolysis of (3-Aminopropyl) trimethoxysilane (APTMS) and increasing the concentration of Ag NPs. Compared with previous methods, the HRGB-SERS substrate prepared with one round of deposition has the same detection performance, a simpler preparation process, and lower cost. Additionally, halide ions were used to modify the substrate to increase the detection sensitivity of PAHs. Adding 10 mM KBr solution to the HRGB-SERS substrate was found to achieve the best modification effect. Under the optimal modification conditions, the detection sensitivity of pyrene was improved by 3 orders of magnitude (10−7 M). Due to the HRGB-SERS substrate’s excellent performance, the rapid identification and trace detection of spiked water samples mixed with anthracene, phenanthrene, and pyrene was realized using a Raman spectrometer with only a volume of 10 μL of the water samples.

Rapid ultrasensitive detection of trace polycyclic aromatic hydrocarbons (PAHs) is essential and significant for pollution control due to their hazard, persistence, and the wide distribution in the environment. Therefore, rapid detection of PAHs is critical for controlling pollution and protecting the ecology. Considering the advantages of surface-enhanced Raman spectroscopy (SERS), a simple and reliable SERS method was proposed in this work for detecting PAHs in water. Three chemicals, namely NaCl, KBr, and KI, were chosen to modify Ag nanoparticles (NPs) for phenanthrene (Phe) detection, and Ag NPs modified with KBr (Ag-Br NPs) showed the best SERS response. The mixing sequence and the concentration of KBr were optimized. The addition order of mixing KBr and Ag NPs before Phe solution was the best sequence, and the optimal concentration of KBr was 20 mM. Under optimal conditions, the limits of quantification for Phe, pyrene (Pyr), and anthracene (Ant) were 10 À6 M, 10 À7 M, and 10 À7 M, respectively. Mixed PAHs (Phe, Pyr, and Ant) in spiked water samples were identified and quantified successfully. The proposed method has good application prospects in environmental pollution monitoring.