First On-Orbit Demonstration of a Geospatial Foundation Model
This work addresses the problem of enabling onboard AI for Earth observation missions by making models flight-ready, though it is incremental as it focuses on compression and adaptation of existing methods.
The paper tackled the challenge of deploying large geospatial foundation models on resource-constrained space hardware by developing compact variants that maintain performance, demonstrating reliable on-orbit inference on the International Space Station.
Geospatial foundation models (GeoFMs) promise broad generalisation capacity for Earth observation (EO) tasks, particularly under data-limited conditions. However, their large size poses a barrier to deployment on resource-constrained space hardware. To address this, we present compact variants of a Vision Transformer (ViT)-based GeoFM that preserve downstream task performance while enabling onboard execution. Evaluation across five downstream tasks and validation in two representative flight environments show that model compression and domain adaptation are critical to reducing size and resource demands while maintaining high performance under operational conditions. We further demonstrate reliable on-orbit inference with the IMAGIN-e payload aboard the International Space Station. These results establish a pathway from large GeoFMs to flight-ready, resource-efficient deployments, expanding the feasibility of onboard AI for EO missions.