← Back to NASA Technology Projects
Completed TRL 4 (started at 2, targeting 4)
The primary obstacle to the exploitation of science from optical light curve survey data is the researcher’s ability to find a light curve containing the astrophysical signal in which they are interested from among tens to hundreds of millions of light curves. This obstacle will only grow as the size of light curve data sets is augmented by improved observatories, such as the Nancy Grace Roman Space Telescope (Roman). As such, we propose to develop a universally-applicable machine learning framework for the purpose of finding any known and/or predicted astrophysical signal present in Roman light curves. This pipeline will allow a user to input a theoretical signal, which will be injected on a pre-collected set of template light curves designed to account for noise and systematics. This process will create “mock data” which will then be used to train a pre-constructed neural network, needing only minimal training due to transfer learning from pre-trained weights, to classify the astrophysical signal.
Accessibility to open data implies access to the value beneath the raw data, which can often be unobtainable to those without the capability to comb large data sets. By allowing any researcher to use AI/ML to make discoveries in Roman data, we intend to remove this obstacle. This effort will be truly community-serving. Our team is uniquely positioned to bring expertise in AI/ML combined with an extensive knowledge of various astrophysical signals in order to design and test a software package that will provide an enduring community benefit and improve the science yield of Roman.
Listed on TechPort itself — the most direct way to ask about this specific project.
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.