Information extraction and dimensionality reduction of hyperspectral datasets through spectral region analyses

Hyperspectral images present detailed spectral information of every pixel in the images where the spectral signal is sampled in hundreds of narrow and contiguous spectral channels, usually covering the 400-2500 nm spectral region where sunlight reflected by the Earth can be measured. Earth observation systems acquire spectral information by imaging spectrometers mounted in a platform flying over the Earth. Recent advances in technology make it possible to have miniaturised hyperspectral satellites in orbit. Much of the work presented in this thesis was inspired by the study of a CubeSat equipped with an imaging spectrometer and capable of onboard data processing.