Learning to detect continuous gravitational waves: an open data-analysis competition

Abstract

We report results of a public data-analysis challenge, hosted on the open data-science platform Kaggle, to detect simulated continuous gravitational-wave signals (CWs). These are weak signals from rapidly spinning neutron stars that remain undetected despite extensive searches. The competition dataset consisted of a population of CW signals using both simulated and real LIGO detector data matching the conditions of actual CW searches. The competition attracted more than 1,000 participants to develop realistic CW search algorithms. We describe the top 10 approaches and discuss their applicability as a pre-processing step compared to standard CW-search approaches. For the competition's dataset, we find that top approaches can reduce the computing cost by 1 to 3 orders of magnitude at a false-dismissal probability comparable to standard CW searches. Additionally, the competition drove the development of new GPU-accelerated detection pipelines, which facilitated their adoption in other areas of gravitational-wave data analysis. We release the associated dataset, which constitutes the first open standardized benchmark for CW detection, to enable reproducible method comparisons and to encourage further developments toward the first detection of these elusive signals.

34 pages, 6 + 2 figures

References in corpus (77)

• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• A simple model of complete precessing black-hole-binary gravitational waveforms
• 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
• KAGRA: 2.5 Generation Interferometric Gravitational Wave Detector
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Open data from the third observing run of LIGO, Virgo, KAGRA and GEO
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Kaggle forecasting competitions: An overlooked learning opportunity
• Real-time gravitational-wave science with neural posterior estimation
• Matching matched filtering with deep networks in gravitational-wave astronomy
• LIGO Detector Characterization in the Second and Third Observing Runs
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• The Hough transform search for continuous gravitational waves
• The generalized F-statistic: multiple detectors and multiple GW pulsars
• The BayesWave analysis pipeline in the era of gravitational wave observations
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• Searches for Continuous-Wave Gravitational Radiation
• Method for all-sky searches of continuous gravitational wave signals using the frequency-Hough transform
• Characterizing the continuous gravitational-wave signal from boson clouds around Galactic isolated black holes
• All-sky search for continuous gravitational waves from isolated neutron stars using Advanced LIGO and Advanced Virgo O3 data
• Targeted search for continuous gravitational waves: Bayesian versus maximum-likelihood statistics
• Detecting gravitational waves from mountains on neutron stars in the Advanced Detector Era
• Deep-Learning continuous gravitational waves
• Search method for long-duration gravitational-wave transients from neutron stars
• SWIGLAL: Python and Octave interfaces to the LALSuite gravitational-wave data analysis libraries
• Fast and Accurate Sensitivity Estimation for Continuous-Gravitational-Wave Searches
• Improved Stack-Slide Searches for Gravitational-Wave Pulsars
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• Searches for continuous gravitational waves from neutron stars: A twenty-year retrospective
• Exploiting Large-Scale Correlations to Detect Continuous Gravitational Waves
• How effective is machine learning to detect long transient gravitational waves from neutron stars in a real search?
• All-sky search in early O3 LIGO data for continuous gravitational-wave signals from unknown neutron stars in binary systems
• Estimating the sensitivity of wide-parameter-space searches for gravitational-wave pulsars
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Search for Continuous Gravitational Waves: Optimal StackSlide method at fixed computing cost
• Search methods for continuous gravitational-wave signals from unknown sources in the advanced-detector era
• Gravitational waves from Sco X-1: A comparison of search methods and prospects for detection with advanced detectors
• Statistical characterization of pulsar glitches and their potential impact on searches for continuous gravitational waves
• Mock LISA data challenge for the galactic white dwarf binaries
• Einstein@Home all-sky search for continuous gravitational waves in LIGO O2 public data
• Importance nested sampling with normalising flows
• Deep Einstein@Home all-sky search for continuous gravitational waves in LIGO O3 public data
• Accretion-induced spin-wandering effects on the neutron star in Scorpius X-1: Implications for continuous gravitational wave searches
• Hierarchical multi-stage MCMC follow-up of continuous gravitational wave candidates
• Parameter-space metric for all-sky semicoherent searches for gravitational-wave pulsars
• A comparison of methods for the detection of gravitational waves from unknown neutron stars
• Implementing a semicoherent search for continuous gravitational waves using optimally-constructed template banks
• F-statistic search for white-dwarf binaries in the first Mock LISA Data Challenge
• SOAP: A generalised application of the Viterbi algorithm to searches for continuous gravitational-wave signals
• Continuous gravitational waves from Galactic neutron stars: demography, detectability and prospects
• Gravity Spy: Lessons Learned and a Path Forward
• A robust machine learning algorithm to search for continuous gravitational waves
• Application of a hierarchical MCMC follow-up to Advanced LIGO continuous gravitational-wave candidates
• Empirically estimating the distribution of the loudest candidate from a gravitational-wave search
• PyFstat: a Python package for continuous gravitational-wave data analysis
• BinarySkyHough: a new method to search for continuous gravitational waves from unknown neutron stars in binary systems
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Applications of machine learning in gravitational wave research with current interferometric detectors
• GWitchHunters: Machine Learning and citizen science to improve the performance of Gravitational Wave detector
• Use of Excess Power Method and Convolutional Neural Network in All-Sky Search for Continuous Gravitational Waves
• Rapid parameter estimation for an all-sky continuous gravitational wave search using conditional varitational auto-encoders
• Deep exploration for continuous gravitational waves at 171--172 Hz in LIGO second observing run data
• Gravitational radiation from thermal mountains on accreting neutron stars: sources of temperature non-axisymmetry
• Convolutional neural network search for long-duration transient gravitational waves from glitching pulsars
• Scalable data-analysis framework for long-duration gravitational waves from compact binaries using short Fourier transforms
• Graphics processing unit implementation of the F-statistic for continuous gravitational wave searches
• Improved all-sky search method for continuous gravitational waves from unknown neutron stars in binary systems
• Toward a computationally-efficient follow-up pipeline for blind continuous gravitational-wave searches
• Population synthesis and parameter estimation of neutron stars with continuous gravitational waves and third-generation detectors
• Search for continuous gravitational waves from unknown neutron stars in binary systems with long orbital periods in O3 data
• How much spin wandering can continuous gravitational wave search algorithms handle?
• One-stop strategy to search for long-duration gravitational-wave signals

Cited by in corpus (1)

• Transformer Networks for Continuous Gravitational-wave Searches