Generalised gravitational burst generation with Generative Adversarial Networks

Abstract

We introduce the use of conditional generative adversarial networks forgeneralised gravitational wave burst generation in the time domain.Generativeadversarial networks are generative machine learning models that produce new databased on the features of the training data set. We condition the network on fiveclasses of time-series signals that are often used to characterise gravitational waveburst searches: sine-Gaussian, ringdown, white noise burst, Gaussian pulse and binaryblack hole merger. We show that the model can replicate the features of these standardsignal classes and, in addition, produce generalised burst signals through interpolationand class mixing. We also present an example application where a convolutional neuralnetwork classifier is trained on burst signals generated by our conditional generativeadversarial network. We show that a convolutional neural network classifier trainedonly on the standard five signal classes has a poorer detection efficiency than aconvolutional neural network classifier trained on a population of generalised burstsignals drawn from the combined signal class space.

References in corpus (53)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Observation of Gravitational Waves from a Binary Black Hole Merger
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• An overview of gradient descent optimization algorithms
• Generative Adversarial Networks
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• GW151226: Observation of Gravitational Waves from a 22-Solar-Mass Binary Black Hole Coalescence
• Deep learning for time series classification: a review
• GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2
• Generative Adversarial Text to Image Synthesis
• GW170608: Observation of a 19-solar-mass Binary Black Hole Coalescence
• A guide to convolution arithmetic for deep learning
• Frequency-domain gravitational waves from non-precessing black-hole binaries. II. A phenomenological model for the advanced detector era
• Binary Black Hole Population Properties Inferred from the First and Second Observing Runs of Advanced LIGO and Advanced Virgo
• Searching for Activation Functions
• The PyCBC search for gravitational waves from compact binary coalescence
• Matched filtering of gravitational waves from inspiraling compact binaries: Computational cost and template placement
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• Deep Learning Based Text Classification: A Comprehensive Review
• A guide to LIGO-Virgo detector noise and extraction of transient gravitational-wave signals
• Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Coherent method for detection of gravitational wave bursts
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• Searching for gravitational waves from binary coalescence
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Gravitational-wave parameter estimation with autoregressive neural network flows
• All-sky search for gravitational-wave bursts in the second joint LIGO-Virgo run
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• Gravitational Waves from Gravitational Collapse
• Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
• Coherent WaveBurst, a pipeline for unmodeled gravitational-wave data analysis
• All-sky search for short gravitational-wave bursts in the second Advanced LIGO and Advanced Virgo run
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• On the gravitational radiation from the collapse of neutron stars to rotating black holes
• Probing neutron star superfluidity with gravitational-wave data
• Deep-Learning continuous gravitational waves
• Deep learning for multimessenger core-collapse supernova detection
• Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
• The GstLAL Search Analysis Methods for Compact Binary Mergers in Advanced LIGO's Second and Advanced Virgo's First Observing Runs
• Search method for coincident events from LIGO and IceCube detectors
• A robust machine learning algorithm to search for continuous gravitational waves
• Efficient Object Localization Using Convolutional Networks
• Enhancing the sensitivity of transient gravitational wave searches with Gaussian Mixture Models

Cited by in corpus (11)

• Simulating Transient Noise Bursts in LIGO with Generative Adversarial Networks
• Generative Adversarial Networks Applied to Synthetic Financial Scenarios Generation
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks
• Convolutional neural network for gravitational-wave early alert: Going down in frequency
• Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
• cDVGAN: One Flexible Model for Multi-class Gravitational Wave Signal and Glitch Generation
• Generative adversarial network for stellar core-collapse gravitational waves
• Extracting overlapping gravitational-wave signals of galactic compact binaries: a mini review
• A machine learning algorithm for minute-long Burst searches