SpaceEdge

Challenges

The trend of mega satellite constellations with advanced sensors that produce enormous amounts of data is currently transforming the space industry. The proliferation of these satellite constellations will require changes to how data is analyzed, stored, processed, and delivered. It is not feasible to transfer all of the generated data to the ground in a timely and cost-efficient way.

One solution is to move the processing tasks to the edge, i.e., to relocate the data processing task onto the satellites. This is similar to what the smart and automotive industries are already implementing in their production.

Project purpose

The SpaceEdge project, in collaboration with Unibap and AI Sweden, is developing the world’s first testbed for satellite applications. Why? To enable anyone to develop their own satellite app and have it tested in orbit.

The project focuses on:

• the refinement of edge technology for terrestrial and in-orbit data handling
• utilization of earth observation data
• the development and training of AI/ML applications

The goals are:

• to shift the computing process to the edge by leveraging federated learning
• to further reduce latency
• improve the quality of training data and
• limit the need for bandwidth on the ground for satellite communication

Expected outcomes

• Create a testbed of edge devices enabled with SpaceCloud
• Multiple stakeholders will learn about and use SpaceEdge
• Establish a process to take an idea from concept to fully realized application in-orbit
• Demonstrate the development of an application from testbed to in-orbit

Contact