An AI-based framework for real time RFI detection in radio astronomy data

Transient universe focused studies have become a key aspect of modern astrophysics. Recent discoveries made at radio wavelengths, specifically “fast radio bursts” (FRBs) - highly enigmatic objects of unknown origin - represent a powerful new tool for probing the universe. However, most astronomical signals are weak compared to the background noise and confusing terrestrial radio-frequency interference (RFI). This constitutes an increasing problem for observatories at every location on earth. Post-processing operations, such as RFI identification and excision, which can currently be performed somewhat interactively, need a far higher level of automation to remain practical. Without efficient real-time RFI excision, future pulsar and transient surveys will be overwhelmed by false positives, which will become the limiting factor for survey sensitivity. Outside of the field of astrophysics, AI techniques have demonstrated exceptional signal and image processing capabilities. Thus, the goal of this proposal is to develop Artificial Intelligence (AI) based alternatives for real-time RFI detection and mitigation.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

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.