Artificial Intelligence for Earth observation
ɸ-sat-1, pronounced phisat-1, is artificial intelligence technology carried on one of the two CubeSats that make up the Federated Satellite Systems mission (FSSCat). Proposed by a team from Spain’s Polytechnic University of Catalonia, FSSCat won ESA’s Small Satellite Challenge as well as taking top prize at the Copernicus Masters competition in 2017.
The FSSCat mission is based on two CubeSats, each about the size of a shoebox, that use state-of-the-art dual microwave and multispectral optical sensors to measure, for example, soil moisture, ice extent, ice thickness, urban heat islands and to monitor changes in vegetation and water quality.
To take FSSCat to the next level, ESA worked with partners to develop ɸ-sat-1 to not only give FSSCat more spectral capabilities, but also to improve the efficiency of sending vast quantities of data back to Earth.
As a result, ɸ-sat-1 is the first artificial intelligence to be carried on a European Earth observation mission. Its hyperspectral camera images in the visible, near-infrared and thermal-infrared parts of the electromagnetic spectrum and acquires an enormous number of images of Earth.
However, some images will not be suitable for use because of cloud cover. To avoid downlinking these less than perfect images back to Earth, the ɸ-sat-1 artificial intelligence chip filters them out so that only usable data are returned. This will make the process of handling all these data more efficient, allowing users access to more timely information, ultimately benefiting society at large.
The FSSCat/ɸ-sat-1 CubeSats will be launched along with more than 50 other small satellites on Vega rocket from Europe’s spaceport in French Guiana in mid-June 2020.
As part of the initiative to promote the development of artificial intelligence technologies for Earth-observing satellites, ESA is assessing concepts for a ɸ-sat-2 mission.
