Generalised gravitational wave burst generation with generative adversarial networks

@article{McGinn2021GeneralisedGW,
  title={Generalised gravitational wave burst generation with generative adversarial networks},
  author={J McGinn and Chris Messenger and M J Williams and Ik Siong Heng},
  journal={Classical and Quantum Gravity},
  year={2021},
  volume={38}
}
We introduce the use of conditional generative adversarial networks (CGANs) for generalised gravitational wave (GW) burst generation in the time domain. Generative adversarial networks are generative machine learning models that produce new data based on the features of the training data set. We condition the network on five classes of time-series signals that are often used to characterise GW burst searches: sine-Gaussian, ringdown, white noise burst, Gaussian pulse and binary black hole… 

DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics

It is shown that discriminating on derivatives can stabilize the learning of GAN components on 1D continuous signals during their training phase, which results in smoother generated signals that are less distinguishable from real samples and better capture the distributions of the training data.

Generative Adversarial Networks Applied to Synthetic Financial Scenarios Generation

A GANs-based algorithm is proposed that allows the replication of multivariate data representing several properties of a set of stocks, which differs from examples in the financial literature, which are mainly focused on the reproduction of temporal asset price scenarios.

Convolutional neural network for gravitational-wave early alert: Going down in frequency

The latest development of a machine-learning pipeline for pre-merger alerts from gravitational waves coming from binary neutron stars is presented, it is shown that the network performs almost as well in non-Gaussian noise as in Gaussian noise: the method is robust w.r.t. glitches and artifacts present in real noise.

Simulating transient noise bursts in LIGO with generative adversarial networks

The noise of gravitational-wave (GW) interferometers limits their sensitivity and impacts the data quality, hindering the detection of GW signals from astrophysical sources. For transient searches,

Machine learning algorithm for minute-long burst searches

It is shown that the neural network used in this work can reach a pixel-wise detection despite trained with minimal assumptions, while being able to retrieve both astrophysical signals and noise transients originating from instrumental coupling within the detectors.

Source-agnostic gravitational-wave detection with recurrent autoencoders

An application of anomaly detection techniques based on deep recurrent autoencoders (AEs) to the problem of detecting gravitational wave signals in laser interferometers and the recurrent AE outperforms other AEs based on different architectures.

References

SHOWING 1-10 OF 76 REFERENCES

Adam: A Method for Stochastic Optimization

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

KAGRA, LIGO Scientific, VIRGO) 2018

  • Living Rev. Rel
  • 2018

coherent WaveBurst, a pipeline for unmodeled gravitational-wave data analysis

Deep Learning Based Text Classification: A Comprehensive Review

A comprehensive review of more than 150 deep learning based models for text classification developed in recent years are provided, and their technical contributions, similarities, and strengths are discussed.

Deep learning for core-collapse supernova detection

This work trained a newly developed Mini-Inception Resnet neural network using time-frequency images corresponding to injections of simulated phenomenological signals, which mimic the waveforms obtained in 3D numerical simulations of CCSNe, and computed the detection efficiency versus the source distance.

Prospects for observing and localizing gravitational-wave transients with Advanced LIGO, Advanced Virgo and KAGRA

The capability of the network to determine the sky location of the source for gravitational-wave signals from the inspiral of binary systems of compact objects, that is binary neutron star, neutron star–black hole, and binary black hole systems is studied.

Enhancing the sensitivity of transient gravitational wave searches with Gaussian mixture models

Identifying the presence of a gravitational wave transient buried in non-stationary, non-Gaussian noise which can often contain spurious noise transients (glitches) is a very challenging task. For a

Sensitivity and performance of the Advanced LIGO detectors in the third observing run

On April 1st, 2019, the Advanced Laser Interferometer Gravitational-Wave Observatory (aLIGO), joined by the Advanced Virgo detector, began the third observing run, a year-long dedicated search for

Robust machine learning algorithm to search for continuous gravitational waves

A general method, using a convolutional neural network, to reduce the impact of instrumental artifacts on searches that use the SOAP algorithm and shows that at 95% efficiency a fully automated SOAP search has a sensitivity corresponding to a coherent signal-to-noise ratio of 110.

Deep-learning continuous gravitational waves: Multiple detectors and realistic noise

The DNN performance is not adversely affected by gaps in the test data or by using a relatively undisturbed band of LigO detector data instead of Gaussian noise, but when using a more disturbed LIGO band for the tests, the DNN's detection performance is substantially degraded due to the increase in false alarms.
...