D-Orbit ION satellite on orbit. Photo: D-Orbit

Over the past 10 months, Amazon Web Services (AWS) ran AWS compute and machine learning software on a satellite in orbit in a first-of-its kind experiment. AWS collaborated with D-Orbit and Unibap, and ran the experiment on D-Orbit’s ION satellite.

AWS detailed the experiment in a blog post published Tuesday. The AWS software prototype was integrated onto a payload built by Unibap, which was then integrated onto a D-Orbit ION satellite. By applying AWS compute to Earth observation imagery, D-Orbit was able to rapidly analyze large quantities of space data directly onboard its satellite. AWS said its services help reduce the size of images by up to 42% which increases processing speeds and allows real-time inferences on-orbit.

“Our customers want to securely process increasingly large amounts of satellite data with very low latency,” said Sergio Mucciarelli, vice president of commercial sales of D-Orbit. “This is something that is limited by using legacy methods, downlinking all data for processing on the ground. We believe in the drive towards edge computing, and that it can only be done with space-based infrastructure that is fit for purpose, giving customers a high degree of confidence that they can run their workloads and operations reliably in the harsh space operating environment.”

The team managed the bidirectional movement of space data over multiple ground station contacts with a TCP/IP proxy between the satellite and the AWS Cloud. This modification made it simpler for ground crews to manage the file transfers automatically, without manually processing the downlinks.

The companies are continuing to test new capabilities with the on orbit experiment, such as additional approaches for processing raw data.