Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data

Abstract

The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of speed, parameter space coverage, and search sensitivity. However, the opaque nature of DL models severely harms their reliability. In this work, we meticulously develop a DL model stage-wise and work towards improving its robustness and reliability. First, we address the problems in maintaining the purity of training data by deriving a new metric that better reflects the visual strength of the 'chirp' signal features in the data. Using a reduced, smooth representation obtained through a variational auto-encoder (VAE), we build a classifier to search for compact binary coalescence (CBC) signals. Our tests on real LIGO data show an impressive performance of the model. However, upon probing the robustness of the model through adversarial attacks, its simple failure modes were identified, underlining how such models can still be highly fragile. As a first step towards bringing robustness, we retrain the model in a novel framework involving a generative adversarial network (GAN). Over the course of training, the model learns to eliminate the primary modes of failure identified by the adversaries. Although absolute robustness is practically impossible to achieve, we demonstrate some fundamental improvements earned through such training, like sparseness and reduced degeneracy in the extracted features at different layers inside the model. We show that these gains are achieved at practically zero loss in terms of model performance on real LIGO data before and after GAN training. Through a direct search on 8.8 days of LIGO data, we recover two significant CBC events from GWTC-2.1, GW190519_153544 and GW190521_074359. We also report the search sensitivity obtained from an injection study.

arXiv comment22 pages, 22 figures

References in corpus (69)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Generative Adversarial Networks
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• Advanced LIGO
• GW151226: Observation of Gravitational Waves from a 22-Solar-Mass Binary Black Hole Coalescence
• GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• GW170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence
• GW190814: Gravitational Waves from the Coalescence of a 23 M${}_{\odot }$ Black Hole with a 2.6 M${}_{\odot }$ Compact Object
• One pixel attack for fooling deep neural networks
• GW190425: Observation of a Compact Binary Coalescence with Total Mass $\sim 3.4M_{\odot }$
• GW190521: A Binary Black Hole Merger with a Total Mass of $150M_{\odot }$
• GW170608: Observation of a 19-solar-mass Binary Black Hole Coalescence
• Binary Black Hole Mergers in the first Advanced LIGO Observing Run
• Interferometer design of the KAGRA gravitational wave detector
• Observation of gravitational waves from two neutron star-black hole coalescences
• GW190412: Observation of a Binary-Black-Hole Coalescence with Asymmetric Masses
• The PyCBC search for gravitational waves from compact binary coalescence
• Open data from the first and second observing runs of Advanced LIGO and Advanced Virgo
• GW150914: First results from the search for binary black hole coalescence with Advanced LIGO
• Matched filtering of gravitational waves from inspiraling compact binaries: Computational cost and template placement
• A chi-squared time-frequency discriminator for gravitational wave detection
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• The LIGO Open Science Center
• IndIGO and LIGO-India: Scope and Plans for Gravitational Wave Research and Precision Metrology in India
• Matching matched filtering with deep networks in gravitational-wave astronomy
• 2-OGC: Open Gravitational-wave Catalog of binary mergers from analysis of public Advanced LIGO and Virgo data
• A Highly Spinning and Aligned Binary Black Hole Merger in the Advanced LIGO First Observing Run
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• 1-OGC: The first open gravitational-wave catalog of binary mergers from analysis of public Advanced LIGO data
• 3-OGC: Catalog of gravitational waves from compact-binary mergers
• A New Search Pipeline for Compact Binary Mergers: Results for Binary Black Holes in the First Observing Run of Advanced LIGO
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Searching for Gravitational Waves from Compact Binaries with Precessing Spins
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Distinguishing short duration noise transients in LIGO data to improve the PyCBC search for gravitational waves from high mass binary black hole mergers
• Mining Gravitational-wave Catalogs To Understand Binary Stellar Evolution: A New Hierarchical Bayesian Framework
• Classification methods for noise transients in advanced gravitational-wave detectors
• Noise Reduction in Gravitational-wave Data via Deep Learning
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• Search for Eccentric Binary Neutron Star Mergers in the first and second observing runs of Advanced LIGO
• Transient Classification in LIGO data using Difference Boosting Neural Network
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• Classification methods for noise transients in advanced gravitational-wave detectors II: performance tests on Advanced LIGO data
• Deep learning and Bayesian inference of gravitational-wave populations: Hierarchical black-hole mergers
• Rapid Identification of Strongly Lensed Gravitational-Wave Events with Machine Learning
• Gravitational wave population inference with deep flow-based generative network
• Early warning of coalescing neutron-star and neutron-star-black-hole binaries from nonstationary noise background using neural networks
• Gravitational-wave selection effects using neural-network classifiers
• From One to Many: A Deep Learning Coincident Gravitational-Wave Search
• Optimization of model independent gravitational wave search using machine learning
• Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216
• Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period
• A robust machine learning algorithm to search for continuous gravitational waves
• Search for binary black hole mergers in the third observing run of Advanced LIGO-Virgo using coherent WaveBurst enhanced with machine learning
• Rapid determination of LISA sensitivity to extreme mass ratio inspirals with machine learning
• Application of Artificial Neural Network to Search for Gravitational-Wave Signals Associated with Short Gamma-Ray Bursts
• Unmodelled Clustering Methods for Gravitational Wave Populations of Compact Binary Mergers
• Generalised gravitational burst generation with Generative Adversarial Networks
• A classifier for gravitational-wave inspiral signals in non-ideal single-detector data
• Ranking Candidate Signals with Machine Learning in Low-Latency Search for Gravitational-Waves from Compact Binary Mergers
• Surrogate forward models for population inference on compact binary mergers
• Gravitational-wave signal-to-noise interpolation via neural networks
• Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study
• Chirp mass based glitch identification in long duration gravitational wave transients

Cited by in corpus (7)

• Gravity Spy: Lessons Learned and a Path Forward
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• A novel stacked hybrid autoencoder for imputing LISA data gaps
• Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning
• Novel Deep Learning Approach to Detecting Binary Black Hole Mergers