Deep-Learning continuous gravitational waves

Abstract

We present a first proof-of-principle study for using deep neural networks (DNNs) as a novel search method for continuous gravitational waves (CWs) from unknown spinning neutron stars. The sensitivity of current wide-parameter-space CW searches is limited by the available computing power, which makes neural networks an interesting alternative to investigate, as they are extremely fast once trained and have recently been shown to rival the sensitivity of matched filtering for black-hole merger signals. We train a convolutional neural network with residual (short-cut) connections and compare its detection power to that of a fully-coherent matched-filtering search using the WEAVE pipeline. As test benchmarks we consider two types of all-sky searches over the frequency range from $20\mathrm{Hz}$ to $1000\mathrm{Hz}$: an `easy' search using $T=10^5\mathrm{s}$ of data, and a `harder' search using $T=10^6\mathrm{s}$. Detection probability $p_{\det }$ is measured on a signal population for which matched filtering achieves $p_{\det }=90\%$ in Gaussian noise. In the easiest test case ($T=10^5\mathrm{s}$ at $20\mathrm{Hz}$) the DNN achieves $p_{\det }\sim 88\%$, corresponding to a loss in sensitivity depth of $\sim 5\%$ versus coherent matched filtering. However, at higher-frequencies and longer observation time the DNN detection power decreases, until $p_{\det }\sim 13\%$ and a loss of $\sim 66\%$ in sensitivity depth in the hardest case ($T=10^6\mathrm{s}$ at $1000\mathrm{Hz}$). We study the DNN generalization ability by testing on signals of different frequencies, spindowns and signal strengths than they were trained on. We observe excellent generalization: only five networks, each trained at a different frequency, would be able to cover the whole frequency range of the search.

arXiv comment11 pages, 8 figures, 7 tables; changed author list, refereed version

References in corpus (32)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• Data analysis of gravitational-wave signals from spinning neutron stars. I. The signal and its detection
• Method for detection and reconstruction of gravitational wave transients with networks of advanced detectors
• 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
• Searching for periodic sources with LIGO
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Searching for periodic sources with LIGO. II: Hierarchical searches
• 1-OGC: The first open gravitational-wave catalog of binary mergers from analysis of public Advanced LIGO data
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Gravitational Waves from Neutron Stars: A Review
• Recent searches for continuous gravitational waves
• Targeted search for continuous gravitational waves: Bayesian versus maximum-likelihood statistics
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Postprocessing methods used in the search for continuous gravitational-wave signals from the Galactic Center
• Template-based searches for gravitational waves: efficient lattice covering of flat parameter spaces
• Fast and Accurate Sensitivity Estimation for Continuous-Gravitational-Wave Searches
• Transient Classification in LIGO data using Difference Boosting Neural Network
• A New Method to Observe Gravitational Waves emitted by Core Collapse Supernovae
• Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors
• Search for Continuous Gravitational Waves: Optimal StackSlide method at fixed computing cost
• Lattice template placement for coherent all-sky searches for gravitational-wave pulsars
• Implementing a semicoherent search for continuous gravitational waves using optimally-constructed template banks
• Optimally setting up directed searches for continuous gravitational waves in Advanced LIGO O1 data
• Optimising the choice of analysis method for all-sky searches for continuous gravitational waves with Einstein@Home
• OctApps: a library of Octave functions for continuous gravitational-wave data analysis
• Enhancing the significance of gravitational wave bursts through signal classification

Cited by in corpus (58)

• Enhancing Gravitational-Wave Science with Machine Learning
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• Searches for Continuous-Wave Gravitational Radiation
• Parameter estimation with gravitational waves
• Gravitational wave signal recognition of O1 data by deep learning
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Applications and Techniques for Fast Machine Learning in Science
• Searches for continuous gravitational waves from neutron stars: A twenty-year retrospective
• Learning physical properties of liquid crystals with deep convolutional neural networks
• How effective is machine learning to detect long transient gravitational waves from neutron stars in a real search?
• Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Search methods for continuous gravitational-wave signals from unknown sources in the advanced-detector era
• Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation
• Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
• Deep learning for clustering of continuous gravitational wave candidates
• Status and perspectives of Continuous Gravitational Wave searches
• Deep Learning Ensemble for Real-time Gravitational Wave Detection of Spinning Binary Black Hole Mergers
• Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
• Training Strategies for Deep Learning Gravitational-Wave Searches
• Gravitational wave population inference with deep flow-based generative network
• Determining liquid crystal properties with ordinal networks and machine learning
• Improved deep learning techniques in gravitational-wave data analysis
• Machine learning forecasts of the cosmic distance duality relation with strongly lensed gravitational wave events
• Anomaly Detection in Gravitational Waves data using Convolutional AutoEncoders
• Generalized Approach to Matched Filtering using Neural Networks
• Classifying the Equation of State from Rotating Core Collapse Gravitational Waves with Deep Learning
• Inference-optimized AI and high performance computing for gravitational wave detection at scale
• Quasinormal modes of dS and AdS Black Holes: Feedforward neural network method
• A robust machine learning algorithm to search for continuous gravitational waves
• Deep learning for clustering of continuous gravitational wave candidates II: identification of low-SNR candidates
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Cosmic Velocity Field Reconstruction Using AI
• Generalised gravitational burst generation with Generative Adversarial Networks
• Use of Excess Power Method and Convolutional Neural Network in All-Sky Search for Continuous Gravitational Waves
• Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• Convolutional neural network search for long-duration transient gravitational waves from glitching pulsars
• Premerger detection of massive black hole binaries using deep learning
• Matched filtering for gravitational wave detection without template bank driven by deep learning template prediction model bank
• Localization of gravitational waves using machine learning
• Deep learning for intermittent gravitational wave signals
• Assessing the impact of non-Gaussian noise on convolutional neural networks that search for continuous gravitational waves
• Computational Techniques for Parameter Estimation of Gravitational Wave Signals
• Graphics processing unit implementation of the F-statistic for continuous gravitational wave searches
• Novel neural-network architecture for continuous gravitational waves
• AI and extreme scale computing to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers
• Gravitational-wave searches in the era of Advanced LIGO and Virgo
• Method to search for inspiraling planetary-mass ultra-compact binaries using the generalized frequency-Hough transform in LIGO O3a data
• Large-kernel Convolutional Neural Networks for Wide Parameter-Space Searches of Continuous Gravitational Waves
• Transformer Networks for Continuous Gravitational-wave Searches
• Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
• Map Reconstruction of radio observations with Conditional Invertible Neural Networks
• Statistically-informed deep learning for gravitational wave parameter estimation
• Learning to detect continuous gravitational waves: an open data-analysis competition
• Interpretable liquid crystal phase classification via two-by-two ordinal patterns
• Constraints on typical relic gravitational waves based on data of LIGO