Surface-enhanced Raman spectroscopy combined with chemometrics for quantitative analysis and carcinogenic risk estimation of polycyclic aromatic hydrocarbons in water with complex matrix

Polycyclic aromatic hydrocarbons (PAHs) as a kind of persistent organic pollutants have high teratogenic, carcinogenic, mutagenic properties, as well as high octanol/water partition coefficient and sediment/water partition coefficient, causing serious threat to human health and water environment. In this study, the feasibility of Surface-enhanced Raman spectroscopy (SERS) technology combined with chemometrics for quantitative analysis and carcinogenic risk estimation of PAHs in water with complex matrix was explored. Firstly, 36 water samples from lake, tap, and distilled water were prepared, and then nano-silver particles (Ag NPs) were mixed with samples. The integrated strategy of spectral preprocessing was adopted to remove spectral interference, and variable selection algorithm was used to extract the information effectively, thus improving the prediction performance of the random forest (RF) calibration model for PAHs quantitative analysis and carcinogenic risk. The final results indicated that RF combined with spectral preprocessing integration strategy and variable selection had better predictive performance compared with the Raw-RF model. For phenanthrene (Phe) and benzo[a]anthracene (BaA) analysis, the optimal calibration model was WT-SG-SiPLS-VIM-RF (Phe: mean relative error of prediction (MRE_p) = 0.0646, coefficient of determination of prediction (R²_p) = 0.9658; BaA: MRE_p = 0.0949, R²_p = 0.9537). SG-WT-SiPLS-VIM-RF model (MRE_p = 0.0992, R²_p = 0.9551) showed a better predictive performance for fluoranthene (Flu). WT-SG-VIM-RF model (MRE_p = 0.0902, R²_p = 0.9409) showed excellent performance for assessing the carcinogenic risk of PAHs. Therefore, the combination of SERS technology and chemometrics provides a new approach for analyzing PAHs.