Applying linear spectral unmixing to airborne hyperspectral imagery for mapping crop yield variability

Abstract

This study evaluated linear spectral unmixing techniques for mapping the variation in crop yield. Both unconstrained and constrained linear spectral unmixing models were applied to airborne hyperspectral imagery recorded from a grain sorghum field and a cotton field. A pair of plant and soil spectra derived from each image was used as endmember spectra to generate unconstrained and constrained plant and soil cover fractions. Yield was positively related to plant fractions and negatively related to soil fractions. For comparison, all 5151 possible narrow-band normalized difference vegetation indices (NDVIs) were calculated from the 102-band images and related to yield. Plant fractions provided better correlations with yield than the majority of the NDVIs. These results indicate that plant cover fraction maps derived from hyperspectral imagery can be used as relative yield maps to characterize crop yield variability.