London, 28 July 2023.- A project led by the University of Oxford has trained a machine learning model in outer space, on board a satellite. A group of researchers led by DPhil student Vit Růžička participated in the project. During 2022, the team successfully pitched their idea to the ‘Dashing through the Stars’ mission, which had issued a call for project proposals to be carried out on board the ION SCV004 satellite, launched in January 2022.
The researchers trained a model to detect changes in cloud cover from aerial images directly on board the satellite. The model was based on few-shot learning, which enables a model to learn the most important features to look for when it has only a few samples to train from.
The project was conducted in collaboration with the European Space Agency (ESA) Φ-lab via the Cognitive Cloud Computing in Space campaign and the Trillium Technologies initiative Networked Intelligence in Space and partners at D-Orbit and Unibap.
“Machine learning has a huge potential for improving remote sensing – the ability to push as much intelligence as possible into satellites will make space-based sensing increasingly autonomous,” said Professor Andrew Markham, who supervised Vit Růžička’s DPhil research. “This would help to overcome the issues with the inherent delays between acquisition and action by allowing the satellite to learn from data on board. Vít’s work serves as an interesting proof-of-principle.”
Machine learning in outer space could help overcome the problem of on-board satellite sensors being affected by harsh environmental conditions, requiring regular calibration. The researchers believe the model could be easily adapted to carry out different tasks such as differentiating between changes of interest e.g. flooding and fires, and natural changes.
