Deep Learning for space based hyperspectral remote sensing

The main objective of this work is to improve the utility of new small satellites for Earth Observation (EO), by researching machine learning techniques to obtain improved and useful detection, classification, and identification capabilities from space.

Special emphasize will be on hyperspectral sensors for land cover classification. A target EO system is the planned Norwegian In-Orbit-Demonstrator (IOD) with a Short-Wave Infrared (SWIR) hyperspectral imager (HyperNor), funded by the European Space Agency (ESA) and the Norwegian Space Agency (NOSA).