Ultra-High-Energy Neutrino Astronomy through Radio Detection and Deep Learning

Detecting neutrinos at ultra-high energies (UHE, _E_ > 10¹⁷ eV) would mark one of the major breakthroughs in astroparticle physics of the 21st century, opening a new observational window to the most violent processes in our universe. However, the extremely small flux and cross-section of cosmic neutrinos make their detection extraordinarily challenging and demand the instrumentation of enormous target volumes.

In this colloquium, I will discuss how sparse arrays of radio detector stations, deployed in the polar ice sheets, can achieve unprecedented sensitivity to UHE cosmic neutrinos. I will explain the detection
principle and will introduce the Radio Neutrino Observatory Greenland (RNO-G)—currently under construction—and outline the plans for the next-generation IceCube-Gen2 observatory at the South Pole.

I will also present how my new research group at TU Dortmund aims to make significant contributions to this international effort. A particular focus will be on leveraging recent advances in deep learning and differentiable programming to enhance the performance of future radio detectors. In particular, real-time AI-based triggering may double the neutrino detection rate, while end-to-end detector optimization
through differentiable programming promises substantial improvements in reconstruction accuracy and overall sensitivity.