AI in Space
Edge learning has the potential to revolutionize the development of AI for space applications, and AI Sweden’s focus in this area is exploring technologies that can be used for high-impact use cases.
Recent activities
Watch as Chiara Ceccobello talks about 'AI in Space' during the event 'The Latest Advancements in Decentralized Learning' in Gothenburg on April 23, 2024.
Why edge learning in space?
Today, AI models are trained by transferring as much data as possible from sensors to a central storage and compute location. In general, the more data, the better the quality of the resulting model. However, as the number of satellites increases, the available bandwidth to transfer data will become less and less. Thus, data transfer costs are expected to rise, it will take longer to transfer enough data to Earth to train models, and the models will be less accurate if less data is transferred.
Edge learning (also known as decentralized learning, federated learning, or swarm learning) is a technology that has the potential to revolutionize the development of AI for space applications by solving these challenges. This would save both money and resources since there is no need to send large amounts of data to the Earth.
ONGOING PROJECT
Swedish Space Data Lab 3.0
Space data can be used for weather forecasting, climate monitoring, forestry, and agriculture. The need to analyze, make available, and coordinate data is steadily increasing. The Swedish Space Data Lab 3.0 is an initiative to promote innovation based on space data, lower the threshold for utilization, and contribute to societal benefits.
NEW PILOT
Interactive simulation tool for earth observation satellites
Under the Space Data Lab 3 initiative, we are currently working on a new demonstration tool, developed using the PASEOS Python package, designed to make the science of Earth observations more comprehensible and engaging for a broad audience. This tool will soon be available for hands-on exploration at AI Sweden's offices (in Stockholm and Gothenburg), providing an opportunity to engage directly with the principles of satellite-based Earth observation.
Past projects
Space Data Hackathon
SpaceEdge
SpaceEdge 2
Swedish Space Data Lab 1.0
Research
PAseos Simulates the Environment for Operating multiple Spacecraft
PASEOS is an open-source Python module that is capable of modeling operational scenarios involving one or multiple spacecraft. It considers several physical phenomena including thermal, power, bandwidth, and communications constraints as well as the impact of radiation on spacecraft. PASEOS can be run both as a high-performance-oriented numerical simulation and/or in a real-time mode directly on edge hardware. Find the code here and the accompanying paper here.
If you are interested in becoming a partner of AI Sweden, and getting access to the partner benefits, including the Labs, please feel free to reach out.