Bringing artificial intelligence onto EO CubeSats

Combining two important paradigm shifts in recent times - Artificial Intelligence (AI) and (constellations of) space crafts with small form factor - by bringing AI on-board of CubeSats has the potential to remove limitations due to data transmission bandwidth and latency and thereby enable completely new space mission capabilities. Novel AI-enabled earth observation mission scenarios could become powerful tools to help achieve the UN’s sustainable development goals against the backdrop of the climate change and species loss crises by detecting and timely alerting the onset of environmental catastrophes such as wildfires, pollution, habitat destruction, etc.
Using the example of a planned AI remote fire detection experiment on ESA’s OPS-SAT mission, in this talk we give an introduction to the interlinked set of challenges in data concept & machine learning strategies and (FPGA) on-board hardware implementation that are to be overcome for EO applications on CubeSat missions with on-board decision making.