Room 02-02
BiCoQ Seminar: Artificial Intelligence for the Design and Control of Gravitational Wave Detectors
Jan Harms (GSSI)
Abstract: Artificial intelligence (AI) is playing an increasingly important role in gravitational-wave (GW) detection. It is being developed as a tool to overcome limitations of the computationally expensive Bayesian inference methods. More recently, AI utilization has been explored to improve the performance of GW detectors by optimizing their designs and their control. In this talk, we will present two important examples, namely the optimized design of environmental monitoring systems for the subtraction of noise in the GW data, and the optimized detector control through a technique called Deep Loop Shaping, where a noise reduction by up to two orders of magnitude was recently demonstrated. These examples show the enormous potential of AI to improve detector performance and to enable the ambitious sensitivity goals of future detectors like the Einstein Telescope. Host: Tommaso Tabarelli de Fatis