Google Tests AI Processors in Low Earth Orbit

Google is pushing the boundaries of artificial intelligence computing by preparing to send AI processors into low Earth orbit. The research, part of Project Suncatcher announced in 2025, will examine whether machine-learning computing can occur in space and hardware can operate reliably in orbit.

The first test is scheduled as part of SpaceX's Transporter-18 rideshare mission, which involves satellite company Planet. Google Tensor Processing Units (TPUs) will be placed in orbit to collect data on how the processors perform under the vibration, radiation, and temperature conditions of space.

Google has already tested its Trillium TPUs using a proton beam at the University of California, Davis' Crocker Nuclear Laboratory while running AI workloads. Researchers monitored the systems for errors caused by radiation, finding that the TPUs could withstand a total ionizing dose greater than expected during a five-year space mission.

The orbital test will provide data that cannot be reproduced fully in ground-based facilities and will guide the design of later missions as Google investigates whether orbital infrastructure can support larger AI workloads.