Engineering publications brought to you by Mark Allen

31 Jul 2023

Machine learning model trained on board satellite

Oxford University researchers have led a project to train a machine learning model in outer space on board a satellite.

Illustration of the data used for training the tiny cloud classification model (left), and the predictions on new scenes (right). The entire training process took about 1.5 seconds, including the time for encoding the entire training dataset, and 10 epochs of training a classification model - Image credit: Sentinel-2 data (ESA) processed by Vít Růžička

According to the University, the breakthrough could be employed on remote-sensing satellites to enable real-time monitoring and decision making for several applications.

Data collected by remote-sensing satellites allow for aerial mapping, weather prediction, and monitoring deforestation. Most satellites passively collect data, since they are not equipped to make decisions or detect changes. Instead, data is relayed to Earth to be processed, which is time consuming and limits the ability to identify and respond to rapidly emerging events, such as a natural disaster.

To overcome these restrictions, a group of researchers led by DPhil student Vít Růžička from Oxford’s Department of Computer Science took on the challenge of training the first machine learning program in outer space. During 2022, the team pitched their idea to the Dashing through the Stars mission, which had issued an open call for project proposals to be carried out on board the ION SCV004 satellite, launched in January 2022. During the autumn of 2022, the team uplinked the code for the program to the satellite already in orbit.

Register now to continue reading

Thanks for visiting The Engineer. You’ve now reached your monthly limit of news stories. Register for free to unlock unlimited access to all of our news coverage, as well as premium content including opinion, in-depth features and special reports.