Kavli Affiliate: Rana X. Adhikari
| First 5 Authors: Hang Yu, Rana X. Adhikari, , ,
| Summary:
Currently, the sub-60 Hz sensitivity of gravitational-wave (GW) detectors
like Advanced LIGO is limited by the control noises from auxiliary degrees of
freedom, which nonlinearly couple to the main GW readout. One particularly
promising way to tackle this contamination is to perform nonlinear noise
mitigation using machine-learning-based convolutional neural networks (CNNs),
which we examine in detail in this study. As in many cases the noise coupling
is bilinear and can be viewed as a few fast channels’ outputs modulated by some
slow channels, we show that we can utilize this knowledge of the physical
system and adopt an explicit "slow$times$fast" structure in the design of the
CNN to enhance its performance of noise subtraction. We then examine the
requirement in the signal-to-noise ratio (SNR) in both the target channel
(i.e., the main GW readout) and in the auxiliary sensors in order to reduce the
noise by at least a factor of a few. In the case of limited SNR in the target
channel, we further demonstrate that the CNN can still reach a good performance
if we adopt curriculum learning techniques, which in reality can be achieved by
combining data from quiet times and those from periods with active noise
injections.
| Search Query: ArXiv Query: search_query=au:”Rana X. Adhikari”&id_list=&start=0&max_results=10