Discrimination of Gonipterini weevil genera using near infrared spectroscopy

Abstract

This proof-of-concept study aimed to investigate the potential of using near infrared (NIR) spectroscopy to discriminate between genera of Gonipterini weevil. NIR spectra (10,000–4,000 cm−1) were collected from 15 Gonipterini specimens, comprising three genera and five species. Principal component analysis (PCA) highlighted the inter-specific variation in NIR spectra, with separation observed between most species across the first two principal components. Partial least squares discriminant analysis (PLS-DA) could be used to differentiate between the genera (78% accuracy), although support vector machine (SVM) modelling gave improved accuracy (91%). The results support the prospect of NIR spectroscopy for the rapid discrimination between Gonipterini genera.