Physics

Friday 16 Jan 2026, 14:15 → 15:45 Europe/Berlin

DO: JvF25/3-303 | BN: b-it/1.047

Prof. Christian Glaser

AI in Physics: How AI is enabling new breakthroughs in fundamental physics

---

The integration of AI into physics is sparking a data-analysis revolution, unlocking unprecedented insights and driving new discoveries. In this lecture, I will show how deep learning enables new insights into high-energy astroparticle phenomena through simulation-based inference and uncertainty quantification using Neural Posterior Estimation. We will explore methods that combine neural networks with conditional normalizing flows to predict full posteriors for physical quantities. Real-world examples include precise cosmic-ray mass measurements at the Pierre Auger Observatory and the AI-assisted discovery of neutrino emission from our Galaxy by the IceCube Neutrino Observatory at the South Pole. Finally, I will highlight prospects for deploying neural networks on low-power hardware (FPGAs) for real-time data analysis at the Radio Neutrino Observatory in Greenland.