Fast and Accurate Detection of Cosmic Ray Contamination in JWST Data

Technical Approach: Develop a convolutional neural network (U-Net) for the detection of cosmic ray hits. This model requires a labeled data set, which we will create using labels provided by the current method and accurate labels provided by an active learning strategy. We will create a data labeling tool for human labelers to provide high-quality labels in an efficient way. As an alternative method that does not require labeled data, we will design a convolutional autoencoder that learns to detect cosmic ray hits as anomalous events. To demonstrate our methodology and permit a future generalization of the tool, we will conduct the analysis of the prototype using mid-infrared low-resolution spectroscopy data for exoplanet WASP80b from the Guaranteed Time Observations Program JWST-GTO-1177.

Accurate and fast detection and amelioration of cosmic ray contamination in James Webb Space Telescope (JWST) data.

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.