SIMULATING MULTISPECTRAL BANDSETS (SENTINEL-2) FROM HYPERSPECTRAL OBSERVATIONS FOR IDENTIFYING SOYBEAN CULTIVARS

The development of remote sensing techniques is enabling the quantification and discrimination of soybeans areas, include cultivated cultivar level. This study aimed to discriminate soybean cultivars as a function of different hyperspectral bands using the sensor-system MSI-Sentinel-2 as a simulation and sample sizes using multivariate statistics. Four soybean cultivation areas cultivated with four cultivars (BMX Potência, NA5909, Don Mario, and FT Campo Mourão) were assessed. It was possible discriminate soybean cultivars by using multivariate techniques applied to multi and hyperspectral data. The bands that contributed to cultivar differentiation in order of importance were: B26, B27, A17, A21, A20 and A14. Discriminant analysis was efficient in the cultivar classification, and canonical variable analysis revealed bands associated with specific discrimination of each cultivar.