Abstract
We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals. The standard method for the detection of well-modeled transient gravitational-wave signals is matched filtering. We use only whitened time series of measured gravitational-wave strain as an input, and we train and test on simulated binary black hole signals in synthetic Gaussian noise representative of Advanced LIGO sensitivity. We show that our network can classify signal from noise with a performance that emulates that of match filtering applied to the same data sets when considering the sensitivity defined by receiver-operator characteristics.
Highlights
We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals
In this Letter we investigate the simplest case of establishing whether a signal is present in the data or if the data contain only detector noise
We propose a deep learning procedure requiring only the raw data time series as input with minimal signal preprocessing
Summary
We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals. We propose a deep learning procedure requiring only the raw data time series as input with minimal signal preprocessing. We compare the results of our network with the widely used matchedfiltering technique and show how a deep learning approach can be pretrained using simulated data sets and applied in low latency to achieve the same sensitivity as established matched-filtering techniques.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
