Discrimination of sugarcane varieties using Landsat 7 ETM+ spectral data

This study addresses the identification of sugarcane varieties using data from an orbital-borne sensor in an attempt to reduce evaluation time and field-checking efforts. It would help institutions that breed sugarcane varieties for royalties charges for the propagation of their genetic material. The approach of this work was to apply a methodology to discriminate sugarcane varieties through Landsat 7 Enhanced Thematic Mapper Plus (ETM +) data. The hypothesis stated is that varieties have different canopies due to their particular morpho-physical characteristics, hence it might be possible to identify such differences through orbital spectral data. Thus, an image of a sugarcane-producing area in western Sao Paulo State, Brazil was obtained and first cut fields sugarcane of four varieties were evaluated. The discrimination techniques tested were: analysis of individual bands, pixel dispersion plots and discriminating equations. In single-band analysis it was found that the near-infrared (NIR) band is the most appropriate. The observation of the pixel dispersion plots between red vs NIR and NIR vs GreenNDVI also helps in the discrimination of these varieties. We concluded that it is possible to identify sugarcane varieties through the discriminating equations with 93.6% of certainty.