Detection of wheat root and straw in soil by use of NIR hyperspectral imaging spectroscopy and Partial Least Square discriminant analysis

Monitoring of root systems development and crop residues decomposition is only possible if these constituents can be discriminated from soil and quantified. In this work, Near Infrared (NIR) combined with Hyperspectral Imaging (HSI) and Partial Least Square Discriminant Analysis (PLS-DA) is proposed as a new rapid and reliable method to discriminate soil, roots and straws. NIR-HSI provides simultaneously spectral and spatial information and PLS-DA allows discrimination between classes based on spectra of each pixel linked to chemical nature of sample constituents on the image.