Detection of chlorpyrifos and carbendazim residues in the cabbage using visible/near-infrared spectroscopy combined with chemometrics

Contamination of agricultural plants and food in the environment caused by pesticide residues has gained great attention of the world. Pesticide residues on vegetables constitute a potential risk to human health. A visible/near-infrared (Vis/NIR) spectroscopy combined with chemometric methods was employed to quantitatively determine chlorpyrifos and carbendazim residues in the cabbage (Brassica chinensis L.). Preprocessing methods were used for spectra denoising. Partial least squares regression (PLSR) and least squares-support vector machine (LS-SVM) were applied as the quantification models. Feature variables were selected by successive projection algorithms (SPA), random frog and regression coefficients in PLSR. As for the samples with chlorpyrifos residues, LS-SVM models based on the global spectra achieved best model performance. The best performance for carbendazim content prediction was achieved by the LS-SVM models based on the original global spectra. And modeling with SPA selected feature variables for carbendazim determination was as good as modeling with the global spectra. The results indicated that Vis/NIR spectroscopy coupled with chemometrics could be an efficient way for the assessment of the pesticide residues in vegetables, and was significant for detection of environmental pollution and ensuring food safety. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

The study successfully quantified chlorpyrifos and carbendazim residues in cabbage using visible/near-infrared spectroscopy combined with chemometric methods. Preprocessing and feature variable selection were employed, with LS-SVM models performing well on global spectra data and SPA-selected feature variables showing good performance in carbendazim detection.