Identification and mapping of some soil types using field spectrometry and spectral mixture analyses: a case study of North Sinai, Egypt

This study examines linear spectral unmixing technique for mapping the surface soil types using field spectroscopy data as the reference spectra. The investigated area is located in North Sinai, Egypt. The study employed data from the Landsat 7 ETM+ satellite sensor with improved spatial and spectral resolution. Mixed remotely sensed image pixels may lead to inaccurate classification results in most conventional image classification algorithms. Spectral unmixing may solve this problem by resolving those into separate components. Four soil type end-members were identified with minimum noise fraction and pixel purity index analyses. The identified soil types are calcareous soils, dry sabkhas, wet sabkhas, and sand dunes. Soil end-member reference spectra were collected in the field using an ASD FieldSpec Pro spectrometer. Constrained sum-to-one and non-negativity linear spectral unmixing model was applied and the soil types map was produced. The results showed that linear spectral unmixing model can be a useful tool for mapping soil types from ETM+ images.