Parameter Prioritization for Efficient Transmission of Neural Networks in Small Satellite Applications

Low-earth-orbit (LEO) satellites can be used to launch cost-effective Earth observation missions. Onboard processing, in particular using machine learning (ML) approaches, is often discussed as a way to reduce the amount of data transmitted back to Earth. However, the combination of LEO satellites and ML brings unique communication challenges, as requirements - and therefore ML models - often change throughout the lifetime of a satellite mission. In this paper, we propose a novel communication protocol that deals with model updates efficiently by providing incremental updates with low communication overhead and quick improvements in onboard classification accuracy. Our initial evaluation shows that the proposed, priority-based approach significantly outperforms the baseline of transmitting updated models without considering prioritization.