Deep Learning for Communication Limited Spacecraft (CLDL)

The objective of this project is to investigate the feasibility of applying deep-learning algorithms to communication-limited spacecraft, an operational domain where a slow, restricted, or intermittent downlink bottleneck inhibits the generation of large training datasets on the ground. With novel complex sensors generating ever-increasing amounts of data, it is imperative to be able to autonomously and robustly classify scientifically useful data to maximize scientific utility per bit transmitted to the ground. This project studies two classification approaches, including supervised transfer learning and unsupervised feature extraction followed by clustering, to optimize selection of data products for download. Additionally, this project establishes metrics and requirements criteria to allow missions to identify which approach is more viable for them, and finally validates the feasibility of both approaches by testing on flight-like hardware.

Due to limitations in satellite transmission bandwidth, numerous missions spanning planetary science, Earth science, and other domains suffer from downlink restrictions. For example, the four Magnetosphere Multiscale (MMS) spacecraft generates approximately 100 GB/day of science data, but only 4% of this data can be transmitted to the ground on average. As a result, the Science Operations Center in Boulder, CO was established to handle selection of the data to be downlinked. However, this effort is both time-consuming and costly, as trained scientists must manually hand-select which data is scientifically valuable. Furthermore, this method can suffer from analyst bias as scientists can often disagree on what data is scientifically interesting. By applying deep learning models to this classification problem, this project aims to accelerate classification times, reduce costs, and remove analyst bias for communication-limited spacecraft.

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.