Noise subtraction from KAGRA O3GK data using Independent Component Analysis

Abstract

During April 7-21 2020, KAGRA conducted its first scientific observation in conjunction with the GEO600 detector.
The dominant noise sources during this run were found to be suspension control noise in the low-frequency range and acoustic noise in the mid-frequency range.
In this study, we show that their contributions in the observational data can be reduced by a signal processing method called independent component analysis (ICA). The model of ICA is extended from that studied in the iKAGRA data analysis to account for frequency dependence, while the linearity and stationarity of the coupling between the interferometer and the noise sources are still assumed. 
We identify optimal witness sensors in the application of ICA, leading to successful mitigation of these two dominant contributions.
We also analyze the stability of the transfer functions for the entire two weeks of data to investigate the applicability of the proposed subtraction method in gravitational wave searches.

Status of KAGRA

“…We plan to join the O4b run in spring 2024 with improved sensitivity of the BNS range of 3∼10 Mpc hopefully. In the meantime, investigation of the effects of the environmental disturbances on the detector performance and post-data-taking noise reduction techniques have been studied [22][23][24][25].…”

Developing a New Nonlinear Independent Component Analysis Scheme

“…The linear ICA has been applied to both iKAGRA data [9] and O3GK data [10] and proven to be effective for gravitational wave data analysis. The application of the nonlinear ICA proposed here is now underway.…”

“…In order to satisfy (10) the above expectation value should vanish for each index. Multiplying to the argument of the expectation value, we find it equivalent to…”