Source-agnostic gravitational-wave detection with recurrent autoencoders

  title={Source-agnostic gravitational-wave detection with recurrent autoencoders},
  author={Eric Moreno and Bartłomiej Borzyszkowski and Maurizio Pierini and J. R. Vlimant and Maria Spiropulu},
  journal={Machine Learning: Science and Technology},
We present an application of anomaly detection techniques based on deep recurrent autoencoders (AEs) to the problem of detecting gravitational wave (GW) 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 AE architectures… 
2 Citations

Model-free detection of unique events in time series

This paper introduces a new anomaly concept called “unicorn” or unique event and presents a new, model-free, unsupervised detection algorithm to detect unicorns and uses the Temporal Outlier Factor (TOF) to measure the uniqueness of events in continuous data sets from dynamic systems.

Applications and Techniques for Fast Machine Learning in Science

This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions, including an abundance of pointers to source material, which can enable these breakthroughs.



Anomaly detection in gravitational waves data using convolutional autoencoders

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.

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.

Generalised gravitational wave burst generation with generative adversarial networks

The use of conditional generative adversarial networks (CGANs) for generalised gravitational wave (GW) burst generation in the time domain is introduced and it is shown that a CNN classifier trained only on the standard five signal classes has a poorer detection efficiency.

Transient Classification in LIGO data using Difference Boosting Neural Network

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

Matching Matched Filtering with Deep Networks for Gravitational-Wave Astronomy.

A deep convolutional neural network is constructed that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals and 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.

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

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

Variational autoencoders for new physics mining at the Large Hadron Collider

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.

Efficient gravitational-wave glitch identification from environmental data through machine learning

The presented method is capable of reducing the gravitational-wave detector network's false alarm rate and improving the LIGO instruments, consequently enhancing detection confidence.

Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216

This is the first ML-based search that recovers all the binary black hole mergers in the first GW transients calalog (GWTC-1), but also makes a clean detection of GW151216, which was not significant enough to be included in the catalogue.