The aim of this study was to investigate the potential use of leaf level spectrometric data to predict the incidence of sugarcane thrips Fulmekiola serrata (Kobus). A hand-held FieldSpec® 3 spectroradiometer (ASD) was employed to collect the spectral measurements. The analysis was conducted using spindle leaves from 4-5 month old sugarcane crops of one variety (N19), sampled from commercial fields. A random forest algorithm followed by partial least squares regression were used for the analysis. Models developed were deemed adequate to predict December nymph numbers and March adult numbers, but different models needed to be developed according to thrips life stage assessed and the season at which the estimation takes place.