Building Scientific Machine Learning Foundation Models for LaRC SMD: showcases studies for active and passive radiative transfer simulations

We propose to build scientific Foundation Models (FMs) for satellite remote sensing application. We will first use FMs to understand passive and active remote sensing signals corresponding to different atmospheric and surface conditions. The implementation of a generative self-learning FM will provide us with opportunities to systematically invest fast self-learning retrievals algorithms with limited human interface and beyond by leveraging the benefits of tackling multiple downstream tasks over different disciplines. We will use radiative transfer model simulations as our training data because they are the core data representing remote sensing signals observed by remote sensors in space.

After completing this project; the LaRC community will gain a powerful AI tool to do science for both active satellites (i.e. GOLIGOLA mission) and passive satellites (i.e. NASA TEMPO; PACE missions etc.)

This is early/mid-stage (TRL 3) — 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.