Abstract:
Data acquired from the hyperspectral airborne sensor DAIS-7915 over Antequera in southern Spain was processed
to yield a quantitative soil swelling potential map based on three physicochemical soil properties currently used in
engineering as measures of soil swelling namely cation exchange capacity (CEC), coefficient of linear extensibility
(COLE), and Saturated moisture content (SP). The method adopted was the use of the statistical procedures of
cluster analysis and factor analysis to obtain spectral parameters with a potential to classify the soils into classes
based on existing classification thresholds of the three properties where laboratory, field and image extracted pixel
spectral data analysis were used. Applying this on a pixel-by-pixel basis revealed images that described spatially
and qualitatively the surface distribution of these properties and thus swell potential differences among the soils in
the area. The results gave an indication of the possible use of airborne spectral data for swell potential estimation.
