Workflow involved in detecting gravitational wave signals and sending out alertsAbstract
Around five years ago, Gravitational Waves (GW) from the collision of a pair of black holes were detected by the Laser Interferometer Gravitational Wave Observatory (LIGO) for the first time ever. Fast forwarding to 2020, LIGO, together with the Virgo detector, has amassed a total of 50 GW detections from mergers of compact objects in three observation runs. This has allowed physicists to study GW source properties in detail, including their composition, merger rates and formation history. In this talk, I described the methods involved in the real-time detection of GW signals from raw detector data as implemented in the online GW search pipeline – SPIIR. I also described how some of the challenges involved in the estimation of GW source parameters can be alleviated by using deep learning algorithms. In particular, I showed how deep learning techniques can be used to estimate accurate sky localization of GW sources at orders of magnitude faster speeds than traditional Bayesian inference methods.
Dr. Chayan Chatterjee
AI for New Messengers Postdoctoral Fellow
Dr. Chayan Chatterjee is the A.I. for New Messengers Postdoctoral Fellow at Vanderbilt University. His research focuses on application of machine learning to study gravitational waves - tiny ripples in space-time created by colliding black holes and neutron stars.