Noise reduction in gravitational-wave data via deep learning

Noise reduction in gravitational-wave data via deep learning
复制标题

通过深度学习降低引力波数据的噪声

DOI:
10.1103/physrevresearch.2.033066
复制
发表时间:
2020
影响因子:
4.2
通讯作者:
Katsavounidis, Erik
Katsavounidis, Erik
中科院分区:
--
文献类型:
--
作者:
Ormiston, Rich;Nguyen, Tri;Coughlin, Michael;Adhikari, Rana X.;Katsavounidis, Erik

文献摘要

参考文献

被引文献

相似文献

随着引力波天文学的出现,人们需要扩大引力波探测器探测范围的技术。除了已经检测到的恒星质量黑洞和中子星合并之外,还有更多的黑洞和中子星合并位于噪声表面以下,如果噪声足够降低,则可以检测到。我们的方法(DeepClean)将机器学习算法应用于引力波探测器数据和来自监测仪器的现场传感器的数据,以减少由于仪器伪影和环境污染而导致的时间序列中的噪声。该框架足够通用,可以减去线性、非线性和非平稳耦合机制。它还可以提供了解当前不被理解为限制检测器灵敏度的机制的句柄。通过软件信号注入和恢复信号的参数估计,还可以解决降噪技术的鲁棒性问题,即能够有效去除噪声,而不会对引力波信号产生意外影响。结果表明,注入信号的最佳信噪比(SNR)得到增强,并且恢复的参数与注入集一致。我们展示了该算法在线性和非线性噪声源上的性能,并讨论了它对引力波探测器天体物理搜索的影响。
With the advent of gravitational-wave astronomy, techniques to extend the reach of gravitational-wave detectors are desired. In addition to the stellar-mass black hole and neutron star mergers already detected, many more are below the surface of the noise, available for detection if the noise is reduced enough. Our method (DeepClean) applies machine-learning algorithms to gravitational-wave detector data and data from on-site sensors monitoring the instrument to reduce the noise in the time series due to instrumental artifacts and environmental contamination. This framework is generic enough to subtract linear, nonlinear, and nonstationary coupling mechanisms. It may also provide handles in learning about the mechanisms which are not currently understood to be limiting detector sensitivities. The robustness of the noise-reduction technique in its ability to efficiently remove noise with no unintended effects on gravitational-wave signals is also addressed through software signal injection and parameter estimation of the recovered signal. It is shown that the optimal signal-to-noise ratio (SNR) of the injected signal is enhanced byand the recovered parameters are consistent with the injected set. We present the performance of this algorithm on linear and nonlinear noise sources and discuss its impact on astrophysical searches by gravitational-wave detectors.
LIGO 数据中环境噪声的回归
DOI: --
发表时间: 2013
期刊:
影响因子: --
作者:
V. Tiwari;M. Drago;V. Frolov;S. Klimenko;G. Mitselmakher;V. Necula;G. Prodi;V. Re;F. Salemi;G. Vedovato;I. Yakushin
通讯作者: I. Yakushin
解决引力波干涉仪中双线性和非线性耦合产生的过量噪声
DOI: 10.1088/1742-6596/716/1/012007
发表时间: 2016
期刊: Journal of Physics: Conference Series
影响因子: --
作者:
S. Bose;B. Hall;Nairwita Mazumder;S. Dhurandhar;Anuradha Gupta;A. Lundgren
通讯作者: A. Lundgren
使用差分增强神经网络对 LIGO 数据进行瞬态分类
DOI: 10.1103/physrevd.95.104059
发表时间: 2016
期刊: Physical Review D
影响因子: 5
作者:
N. Mukund;S. Abraham;S. Kandhasamy;S. Mitra;N. S. Philip
通讯作者: N. S. Philip
高级 LIGO
DOI: 10.1088/0264-9381/32/7/074001
发表时间: 2015-04-09
影响因子: 3.5
作者:
Aasi, J.;Abbott, B. P.;Zweizig, J.
通讯作者: Zweizig, J.
DOI: 10.1088/0264-9381/29/21/215008
发表时间: 2012
影响因子: 3.5
作者:
R. Derosa;J. Driggers;D. Atkinson;H. Miao;V. Frolov;M. Landry;J. Giaime;R. Adhikari
通讯作者: R. Adhikari