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

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