Differentiation of Cotton from Other Crops at Different Growth Stages Using Spectral Properties and Discriminant Analysis

Abstract

The spectral reflectance properties of cotton (Gossypium hirsutum L.), corn (Zea mays L.), soybean [Glycine max (L.)], and sorghum [Sorghum bicolor (L.)] crops during their different growth stages were examined, and spectral data were used to distinguish cotton from other crops. Two field blocks with two different soil types, Belk clay (BaA) and Ships clay (ShA), were set up with cotton, corn, soybean, and sorghum in each block and grown using conventional production practices for the area. Spectral information was collected from all crops at different growth stages from May to July 2009. Reflectance spectra and the first derivative of the spectra were analyzed to characterize the spectral properties of crop types and compare the crops grown in different soil types. The red-edge points of cotton, soybean, and sorghum shifted with the growth stage. Principal component analyses were successful in reducing the dimensionality of the hyperspectral data and identifying significant features from the original data. Most significant wavelengths selected were in the 548-556 nm, 679-682 nm, 756-764 nm, and 928-940 nm regions of the spectrum. Discriminant analysis was able to differentiate cotton from other crop types at four critical growth stages with 100% accuracy of classification for all four observation dates.