Application of Machine Learning on the noise subtraction of the gravitaional wave data in KAGRA

Chia-Jui Chou^1*

¹Department of Electrophysics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan

* Presenter:Chia-Jui Chou, email:chiajuichou@nycu.edu.tw

Real-time noise regression algorithms are crucial for maximizing the science outcomes of the LIGO, Virgo, and KAGRA gravitational-wave detectors. This includes improvements in the detectability, source localization and pre-merger detectability of signals thereby enabling rapid multi-messenger follow-up. In the talk, I will introduce the demonstration of DeepClean, a convolutional neural network architecture that uses witness sensors to estimate and subtract non-linear and non-stationary noise from gravitational-wave strain data, on the gravitaional wave data from Observation run O3 and O4. The current status of the low-latency noise subtraction using DeepClean on the data from the LIGO's and KAGRA's detectors will also be covered.

Keywords: Gravitational Wave, Machine Learning