Statistical analysis of hyperspectral data from two Swedish lakes.

CASI data has been collected from two lakes in Sweden. In this paper, some statistical properties of CASI spectral data have been discussed. Principal component analysis is used for assessing the dimensionality of the data and the principal components were used for making chlorophyll maps. The quality of the reconstruction of the spectra from the principal components was demonstrated. Examples of the accuracy of the radiative transfer code 6S in atmospheric correction applications have been given. Furthermore, the widths and positions of the spectral bands based on the studied dataset were proposed for chlorophyll mapping. Robustness aspects of regression models have been discussed. Algorithms derived from one lake have been used to map water quality parameters in another lake. Algorithms based on principal components, as well as algorithms based on image bands, have been used.