Assessing the impact of non-Gaussian noise on convolutional neural networks that search for continuous gravitational waves

Abstract

We present a convolutional neural network that is capable of searching for continuous gravitational waves, quasi-monochromatic, persistent signals arising from asymmetrically rotating neutron stars, in $\sim 1$ year of simulated data that is plagued by non-stationary, narrow-band disturbances, i.e., lines. Our network has learned to classify the input strain data into four categories: (1) only Gaussian noise, (2) an astrophysical signal injected into Gaussian noise, (3) a line embedded in Gaussian noise, and (4) an astrophysical signal contaminated by both Gaussian noise and line noise. In our algorithm, different frequencies are treated independently; therefore, our network is robust against sets of evenly-spaced lines, i.e., combs, and we only need to consider perfectly sinusoidal line in this work. We find that our neural network can distinguish between astrophysical signals and lines with high accuracy. In a frequency band without line noise, the sensitivity depth of our network is about ${\mathcal{D}}^{95\%}\simeq 43.9$ with a false alarm probability of $\sim 0.5\%$, while in the presence of line noise, we can maintain a false alarm probability of $\sim 10\%$ and achieve ${\mathcal{D}}^{95\%}\simeq 3.62$ when the line noise amplitude is $h_0^{\mathrm{line}}/\sqrt{S_{\mathrm{n}}(f_k)}=1.0$. We evaluate the computational cost of our method to be $O(10^{19})$ floating point operations, and compare it to those from standard all-sky searches, putting aside differences between covered parameter spaces. Our results show that our method is more efficient by one or two orders of magnitude than standard searches. Although our neural network takes about $O(10^8)$ sec to employ using our current facilities (a single GPU of GTX1080Ti), we expect that it can be reduced to an acceptable level by utilizing a larger number of improved GPUs.

arXiv comment17 pages, 11 figures; v2: Virgo's contribution appropriately mentioned, typos fixed

References in corpus (50)

• Advanced LIGO
• The ATNF Pulsar Catalogue
• String Axiverse
• Data analysis of gravitational-wave signals from spinning neutron stars. I. The signal and its detection
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Real-time gravitational-wave science with neural posterior estimation
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• Gravitational Waves from Neutron Stars: A Review
• The Hough transform search for continuous gravitational waves
• Enhancing Gravitational-Wave Science with Machine Learning
• Gravitational-wave parameter estimation with autoregressive neural network flows
• All-sky search for continuous gravitational waves from isolated neutron stars using Advanced LIGO O2 data
• Identification and mitigation of narrow spectral artifacts that degrade searches for persistent gravitational waves in the first two observing runs of Advanced LIGO
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• Direct constraints on ultra-light boson mass from searches for continuous gravitational waves
• Method for all-sky searches of continuous gravitational wave signals using the frequency-Hough transform
• Recent searches for continuous gravitational waves
• Directed searches for gravitational waves from ultralight bosons
• First low-frequency Einstein@Home all-sky search for continuous gravitational waves in Advanced LIGO data
• Continuous gravitational waves from neutron stars: current status and prospects
• All-sky search for gravitational wave emission from scalar boson clouds around spinning black holes in LIGO O3 data
• Deep-Learning continuous gravitational waves
• Full Band All-sky Search for Periodic Gravitational Waves in the O1 LIGO Data
• Narrowband searches for continuous and long-duration transient gravitational waves from known pulsars in the LIGO-Virgo third observing run
• 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
• Prospects for probing gravitational waves from primordial black hole binaries
• Search methods for continuous gravitational-wave signals from unknown sources in the advanced-detector era
• Probing planetary-mass primordial black holes with continuous gravitational waves
• Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
• Machine Learning Gravitational Waves from Binary Black Hole Mergers
• Deep learning for clustering of continuous gravitational wave candidates
• A semi-coherent analysis method to search for continuous gravitational waves emitted by ultra-light boson clouds around spinning black holes
• A Machine Learning Based Source Property Inference for Compact Binary Mergers
• A method to search for long duration gravitational wave transients from isolated neutron stars using the generalized FrequencyHough
• Constraints on planetary and asteroid-mass primordial black holes from continuous gravitational-wave searches
• Search for black hole hyperbolic encounters with gravitational wave detectors
• Search of the Early O3 LIGO Data for Continuous Gravitational Waves from the Cassiopeia A and Vela Jr. Supernova Remnants
• Comparison of various methods to extract ringdown frequency from gravitational wave data
• A comparison of methods for the detection of gravitational waves from unknown neutron stars
• SOAP: A generalised application of the Viterbi algorithm to searches for continuous gravitational-wave signals
• An Effective Search Method for Gravitational Ringing of Black Holes
• A robust machine learning algorithm to search for continuous gravitational waves
• Merger-Ringdown Consistency: A New Test of Strong Gravity using Deep Learning
• Use of Excess Power Method and Convolutional Neural Network in All-Sky Search for Continuous Gravitational Waves
• Sensitivity study using machine learning algorithms on simulated r-mode gravitational wave signals from newborn neutron stars
• Conditional Noise Deep Learning for Parameter Estimation of Gravitational Wave Events
• Searching for Mini Extreme Mass Ratio Inspirals with Gravitational-Wave Detectors
• Use of conditional variational auto encoder to analyze ringdown gravitational waves

Cited by in corpus (6)

• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Convolutional neural network search for long-duration transient gravitational waves from glitching pulsars
• Deep learning for intermittent gravitational wave signals
• Method to search for inspiraling planetary-mass ultra-compact binaries using the generalized frequency-Hough transform in LIGO O3a data
• Transformer Networks for Continuous Gravitational-wave Searches