Heavy Metal Detection in Fritillaria thunbergii Using Laser-Induced Breakdown Spectroscopy Coupled with Variable Selection Algorithm and Chemometrics.

Abstract

Environmental and health risks associated with heavy metal pollution are serious. Human health can be adversely affected by the smallest amount of heavy metals. Modeling spectrum requires the careful selection of variables. Hence, simple variables that have a low level of interference and a high degree of precision are required for fast analysis and online detection. This study used laser-induced breakdown spectroscopy coupled with variable selection and chemometrics to simultaneously analyze heavy metals (Cd, Cu and Pb) in Fritillaria thunbergii. A total of three machine learning algorithms were utilized, including a gradient boosting machine (GBM), partial least squares regression (PLSR) and support vector regression (SVR). Three promising wavelength selection methods were evaluated for comparison, namely, a competitive adaptive reweighted sampling method (CARS), a random frog method (RF), and an uninformative variable elimination method (UVE). Compared to full wavelengths, the selected wavelengths produced excellent results. Overall, RC2, RV2, RP2, RSMEC, RSMEV and RSMEP for the selected variables are as follows: 0.9967, 0.8899, 0.9403, 1.9853 mg kg-1, 11.3934 mg kg-1, 8.5354 mg kg-1; 0.9933, 0.9316, 0.9665, 5.9332 mg kg-1, 18.3779 mg kg-1, 11.9356 mg kg-1; 0.9992, 0.9736, 0.9686, 1.6707 mg kg-1, 10.2323 mg kg-1, 10.1224 mg kg-1 were obtained for Cd Cu and Pb, respectively. Experimental results showed that all three methods could perform variable selection effectively, with GBM-UVE for Cd, SVR-RF for Pb, and GBM-CARS for Cu providing the best results. The results of the study suggest that LIBS coupled with wavelength selection can be used to detect heavy metals rapidly and accurately in Fritillaria by extracting only a few variables that contain useful information and eliminating non-informative variables.