# Source-Agnostic Gravitational-Wave Detection with Recurrent Autoencoders

@article{Moreno2021SourceAgnosticGD, title={Source-Agnostic Gravitational-Wave Detection with Recurrent Autoencoders}, author={Eric A. Moreno and J. R. Vlimant and Maria Spiropulu and Bartlomiej Borzyszkowski and Maurizio Pierini}, journal={ArXiv}, year={2021}, volume={abs/2107.12698} }

We present an application of anomaly detection techniques based on deep recurrent autoencoders to the problem of detecting gravitational wave signals in laser interferometers. Trained on noise data, this class of algorithms could detect signals using an unsupervised strategy, i.e., without targeting a specific kind of source. We develop a custom architecture to analyze the data from two interferometers. We compare the obtained performance to that obtained with other autoencoder architectures… Expand

#### References

SHOWING 1-10 OF 47 REFERENCES

Anomaly detection in gravitational waves data using convolutional autoencoders

- Computer Science, Physics
- Machine Learning: Science and Technology
- 2021

This paper proposes an alternative generic method of studying GW data based on detecting anomalies that is not limited only to GW alone, but also includes glitches occurring in the real LIGO/Virgo dataset available at the Gravitational Waves Open Science Center. Expand

Deep Neural Networks to Enable Real-time Multimessenger Astrophysics

- Computer Science, Physics
- ArXiv
- 2017

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. Expand

Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data

- Physics, Computer Science
- ArXiv
- 2017

It is demonstrated for the first time that machine learning can detect and estimate the true parameters of real events observed by LIGO, and achieves similar sensitivities and lower errors compared to matched-filtering while being far more computationally efficient and more resilient to glitches. Expand

Transient Classification in LIGO data using Difference Boosting Neural Network

- Physics
- 2017

Detection and classification of transients in data from gravitational wave detectors are crucial for efficient searches for true astrophysical events and identification of noise sources. We present a… Expand

Accelerating Recurrent Neural Networks for Gravitational Wave Experiments

- Computer Science, Physics
- 2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)
- 2021

A new architecture capable of accelerating RNN inference for analyzing time-series data from LIGO detectors is developed, based on optimizing the initiation intervals in a multi-layer LSTM (Long Short-Term Memory) network, by identifying appropriate reuse factors for each layer. Expand

Classification methods for noise transients in advanced gravitational-wave detectors

- Physics
- 2015

Noise of non-astrophysical origin will contaminate science data taken by the Advanced Laser Interferometer Gravitational-wave Observatory (aLIGO) and Advanced Virgo gravitational-wave detectors.… Expand

Classification methods for noise transients in advanced gravitational-wave detectors II: performance tests on Advanced LIGO data

- Physics
- 2016

The data taken by the advanced LIGO and Virgo gravitational-wave detectors contains short duration noise transients that limit the significance of astrophysical detections and reduce the duty cycle… Expand

Variational autoencoders for new physics mining at the Large Hadron Collider

- Computer Science, Physics
- Journal of High Energy Physics
- 2019

A one-sided threshold test to isolate previously unseen processes as outlier events is developed, which could inspire new-physics model building and new experimental searches, and be complementary to classic LHC searches. Expand

On line power spectra identification and whitening for the noise in interferometric gravitational wave detectors

- Physics
- 2001

The knowledge of the noise power spectral density of an interferometric detector of gravitational waves is fundamental for detection algorithms and for the analysis of the data. In this paper we… Expand

Method for detection and reconstruction of gravitational wave transients with networks of advanced detectors

- Physics
- 2016

We present a method for detection and reconstruction of the gravitational-wave (GW) transients with the networks of advanced detectors. Originally designed to search for transients with the initial… Expand