Near-Infrared Spectroscopy Coupled with Kernel Partial Least Squares-Discriminant Analysis for Rapid Screening Water Containing Malathion

Abstract

Near-infrared spectroscopy coupled with kernel partial\rleast squares-discriminant analysis was used to rapidly screen water containing\rmalathion. In the wavenumber of 4348 cm-1 to 9091 cm-1,\rthe overall correct classification rate of kernel partial least\rsquares-discriminant analysis was 100% for training set, and 100% for test set,\rwith the lowest concentration detected malathion residues in water being 1 μg·ml-1.\rKernel partial least\rsquares-discriminant analysis was able to have a good performance in\rclassifying data in nonlinear systems. It was inferred that Near-infrared spectroscopy coupled with the kernel partial least squares-discriminant analysis had a\rpotential in rapid screening other pesticide residues in\rwater.