Nonlinear noise regression in gravitational-wave detectors with convolutional neural networks

Abstract

Currently, the sub-60 Hz sensitivity of gravitational-wave (GW) detectors like Advanced LIGO is limited by the control noises from auxiliary degrees of freedom, which nonlinearly couple to the main GW readout. One particularly promising way to tackle this contamination is to perform nonlinear noise mitigation using machine-learning-based convolutional neural networks (CNNs), which we examine in detail in this study. As in many cases the noise coupling is bilinear and can be viewed as a few fast channels' outputs modulated by some slow channels, we show that we can utilize this knowledge of the physical system and adopt an explicit "slow$\times$fast" structure in the design of the CNN to enhance its performance of noise subtraction. We then examine the requirement in the signal-to-noise ratio (SNR) in both the target channel (i.e., the main GW readout) and in the auxiliary sensors in order to reduce the noise by at least a factor of a few. In the case of limited SNR in the target channel, we further demonstrate that the CNN can still reach a good performance if we adopt curriculum learning techniques, which in reality can be achieved by combining data from quiet times and those from periods with active noise injections.

arXiv comment20 pages, 7 figures; contribution to "Efficient AI in Particle Physics and Astrophysics" in Frontiers in Artificial Intelligence and Frontiers in Big Data

References in corpus (48)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• 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
• The Sensitivity of the Advanced LIGO Detectors at the Beginning of Gravitational Wave Astronomy
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• 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
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Searching for Eccentricity: Signatures of Dynamical Formation in the First Gravitational-Wave Transient Catalogue of LIGO and Virgo
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• Machine-learning non-stationary noise out of gravitational wave detectors
• Rates and Characteristics of Intermediate Mass Ratio Inspirals Detectable by Advanced LIGO
• Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
• Low-Latency Gravitational Wave Alerts for Multi-Messenger Astronomy During the Second Advanced LIGO and Virgo Observing Run
• Improving astrophysical parameter estimation via offline noise subtraction for Advanced LIGO
• The Missing Link: Bayesian Detection and Measurement of Intermediate-Mass Black-Hole Binaries
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• Detection and Classification of Supernova Gravitational Waves Signals: A Deep Learning Approach
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• Prospects for detecting gravitational waves at 5 Hz with ground-based detectors
• Deep learning for multimessenger core-collapse supernova detection
• Detection and Parameter Estimation of Gravitational Waves from Binary Neutron-Star Mergers in Real LIGO Data using Deep Learning
• Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
• Deep learning for clustering of continuous gravitational wave candidates
• Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
• Deep learning for gravitational wave forecasting of neutron star mergers
• A Machine Learning Based Source Property Inference for Compact Binary Mergers
• Measuring intermediate mass black hole binaries with advanced gravitational wave detectors
• Convolutional neural networks for the detection of the early inspiral of a gravitational-wave signal
• Application of dictionary learning to denoise LIGO's blip noise transients
• Angular control of optical cavities in a radiation pressure dominated regime: the Enhanced LIGO case
• Improved deep learning techniques in gravitational-wave data analysis
• Early warning of coalescing neutron-star and neutron-star-black-hole binaries from nonstationary noise background using neural networks
• Angular instability due to radiation pressure in the LIGO gravitational wave detector
• Optimization of model independent gravitational wave search using machine learning
• Generalized Approach to Matched Filtering using Neural Networks
• A robust machine learning algorithm to search for continuous gravitational waves
• SkyMapper Optical Follow-up of Gravitational Wave Triggers: Alert Science Data Pipeline and LIGO/Virgo O3 Run
• A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources
• Density estimation with Gaussian processes for gravitational-wave posteriors
• New methods to assess and improve LIGO detector duty cycle
• The SPIIR online coherent pipeline to search for gravitational waves from compact binary coalescences
• Gravitational-wave signal-to-noise interpolation via neural networks
• Reduction of transient noise artifacts in gravitational-wave data using deep learning
• The response of the Convolutional Neural Network to the transient noise in Gravitational wave detection
• $\beta$-Annealed Variational Autoencoder for glitches

Cited by in corpus (1)

• Inference-optimized AI and high performance computing for gravitational wave detection at scale