Using machine learning to autotune chi-squared tests for gravitational wave searches

  title={Using machine learning to autotune chi-squared tests for gravitational wave searches},
  author={Connor McIsaac and Ian Harry},
  journal={Physical Review D},
The sensitivity of gravitational wave searches is reduced by the presence of non-Gaussian noise in the detector data. These non-Gaussianities often match well with the template waveforms used in matched filter searches, and require signal-consistency tests to distinguish them from astrophysical signals. However, empirically tuning these tests for maximum efficacy is time consuming and limits the complexity of these tests. In this work we demonstrate a framework to use machine-learning techniques… 

Figures and Tables from this paper


From One to Many: A Deep Learning Coincident Gravitational-Wave Search
This work constructs a two-detector search for gravitational waves from binary black hole mergers using neural networks trained on non-spinning binaryBlack hole data from a single detector and constructs a set of simple networks that operate directly on data from both detectors.
Detection of gravitational-wave signals from binary neutron star mergers using machine learning
A novel neural-network based machine learning algorithm that uses time series strain data from gravitational-wave detectors to detect signals from non-spinning binary neutron star mergers and improves the ability to compare machine learning and classical searches.
Convolutional neural networks: a magic bullet for gravitational-wave detection?
This work explains in detail why convolutional neural networks alone cannot be used to claim a statistically significant gravitational-wave detection, and demonstrates how they can still be use to rapidly flag the times of potential signals in the data for a more detailed follow-up.
Searching for gravitational waves from binary coalescence
The implementation of a search for gravitational waves from compact binary coalescences in LIGO and Virgo data is described and it is demonstrated that the signal consistency tests are capable of mitigating the effect of non-Gaussian noise and providing a sensitivity comparable to that achieved in Gaussian noise.
Targeted coherent search for gravitational waves from compact binary coalescences
A method for conducting a targeted, coherent search for compact binary coalescences is introduced and it is verified that the signal consistency tests are capable of removing the majority of noise transients, giving the search an efficiency comparable to that achieved in Gaussian noise.
Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
Deep Filtering is introduced, a new highly scalable method for end-to-end time-series signal processing, based on a system of two deep convolutional neural networks, which is designed for classification and regression to rapidly detect and estimate parameters of signals in highly noisy time- series data streams.
χ2 time-frequency discriminator for gravitational wave detection
Searches for known waveforms in gravitational wave detector data are often done using matched filtering. When used on real instrumental data, matched filtering often does not perform as well as might
Improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
We improve the accuracy of the effective-one-body (EOB) waveforms that were employed during the first observing run of Advanced LIGO for binaries of spinning, nonprecessing black holes by calibrating