Erlangen 2026 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 50: Data, AI, Computing, Electronics V

T 50.5: Talk

Wednesday, March 18, 2026, 17:15–17:30, KH 00.024

Binary Black Hole Parameter Estimation using a Conditioned Normalizing Flow — •Markus Bachlechner and Achim Stahl — III. Physikalisches Institut B, RWTH Aachen

The proposed Einstein Telescope is the first of the third-generation gravitational wave detectors. It is expected to reach a noise level at least one order of magnitude lower than current interferometers like LIGO and Virgo. Thus, the improved sensitivity increases the observable volume and extends the time window in which the inspiral phase of binary systems is measurable. To analyze the resulting vast amounts of data efficiently, Neural Networks (NNs) can be utilized. This talk presents a fast Binary Black Hole parameter reconstruction using a conventional convolutional NN, which conditions a subsequent Normalizing Flow (NF). Using the NF, an approximate posterior parameter distribution is obtained on an event-by-event basis, allowing for the estimation of uncertainties.

Keywords: Normalizing Flow; Gravitational Waves