Semi-blind source separation for estimation of clay content over semi-vegetated areas, from vnir/swir hyperspectral airborne data

The applicability of Visible, Near-Infrared and Short Wave Infrared (VNIR/SWIR) hyperspectral imagery for soil property mapping decreases when surfaces are partially covered by vegetation. The objective of this research was to develop and evaluate the performance of a “double-extraction” technique for clay content estimation over semi-vegetated surfaces using VNIR/SWIR hyperspectral imagery. The “double-extraction” technique consists of 1) an extraction of a soil reflectance spectrum ŝ
_soil
, using a Semi-Blind Source Separation (SBSS) technique applied to couples of semi-vegetated spectra, and 2) an extraction of clay content from the soil reflectance spectrum ŝ
_soil
, by a classical multivariate regression method. Semi-Blind source separation approach profited by known information about our context (presence of soil and green vegetation).