Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data
arXiv:1303.6984 · doi:10.1103/PhysRevD.88.062003
Abstract
The sensitivity of searches for astrophysical transients in data from the LIGO is generally limited by the presence of transient, non-Gaussian noise artifacts, which occur at a high-enough rate such that accidental coincidence across multiple detectors is non-negligible. Furthermore, non-Gaussian noise artifacts typically dominate over the background contributed from stationary noise. These "glitches" can easily be confused for transient gravitational-wave signals, and their robust identification and removal will help any search for astrophysical gravitational-waves. We apply Machine Learning Algorithms (MLAs) to the problem, using data from auxiliary channels within the LIGO detectors that monitor degrees of freedom unaffected by astrophysical signals. The number of auxiliary-channel parameters describing these disturbances may also be extremely large; an area where MLAs are particularly well-suited. We demonstrate the feasibility and applicability of three very different MLAs: Artificial Neural Networks, Support Vector Machines, and Random Forests. These classifiers identify and remove a substantial fraction of the glitches present in two very different data sets: four weeks of LIGO's fourth science run and one week of LIGO's sixth science run. We observe that all three algorithms agree on which events are glitches to within 10% for the sixth science run data, and support this by showing that the different optimization criteria used by each classifier generate the same decision surface, based on a likelihood-ratio statistic. Furthermore, we find that all classifiers obtain similar limiting performance, suggesting that most of the useful information currently contained in the auxiliary channel parameters we extract is already being used.
arXiv comment21 pages, 8 figures
References in corpus (14)
- LIGO: The Laser Interferometer Gravitational-Wave Observatory
- Predictions for the Rates of Compact Binary Coalescences Observable by Ground-based Gravitational-wave Detectors
- An excess power statistic for detection of burst sources of gravitational radiation
- Multiresolution techniques for the detection of gravitational-wave bursts
- Searching for gravitational waves from binary coalescence
- The LSC Glitch Group : Monitoring Noise Transients during the fifth LIGO Science Run
- The characterization of Virgo data and its impact on gravitational-wave searches
- A hierarchical method for vetoing noise transients in gravitational-wave detectors
- Methods for Reducing False Alarms in Searches for Compact Binary Coalescences in LIGO Data
- Optimizing Vetoes for Gravitational-wave Transient Searches
- Gravitational wave burst vetoes in the LIGO S2 and S3 data analyses
- Likelihood-ratio ranking of gravitational-wave candidates in a non-Gaussian background
- Physical instrumental vetoes for gravitational-wave burst triggers
- Detecting transient gravitational waves in non-Gaussian noise with partially redundant analysis methods
Cited by in corpus (72)
- Characterization of the LIGO detectors during their sixth science run
- Analysis Framework for the Prompt Discovery of Compact Binary Mergers in Gravitational-wave Data
- Quantum Entanglement in Neural Network States
- Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914
- Machine Learning Topological States
- Enhancing Gravitational-Wave Science with Machine Learning
- Observing Gravitational Waves from Core-Collapse Supernovae in the Advanced Detector Era
- Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
- Mitigation of the instrumental noise transient in gravitational-wave data surrounding GW170817
- Low-Latency Gravitational Wave Alerts for Multi-Messenger Astronomy During the Second Advanced LIGO and Virgo Observing Run
- Neural Networks for Modeling and Control of Particle Accelerators
- Solving frustrated quantum many-particle models with convolutional neural networks
- Unveiling phase transitions with machine learning
- Classification methods for noise transients in advanced gravitational-wave detectors
- Searching for the full symphony of black hole binary mergers
- Quenches near Ising quantum criticality as a challenge for artificial neural networks
- Noise Reduction in Gravitational-wave Data via Deep Learning
- Applications and Techniques for Fast Machine Learning in Science
- Transient Classification in LIGO data using Difference Boosting Neural Network
- Machine Learning Bell Nonlocality in Quantum Many-body Systems
- Accuracy of Estimating Highly Eccentric Binary Black Hole Parameters with Gravitational-Wave Detections
- Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors
- Machine Learning meets Quantum Foundations: A Brief Survey
- Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
- Data quality up to the third observing run of Advanced LIGO: Gravity Spy glitch classifications
- The miniJPAS survey: star-galaxy classification using machine learning
- The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
- Classifying the unknown: discovering novel gravitational-wave detector glitches using similarity learning
- Unsupervised Learning of Non-Hermitian Topological Phases
- Neural-network-designed pulse sequences for robust control of singlet-triplet qubits
- Machine learning topological invariants of non-Hermitian systems
- Generalized Approach to Matched Filtering using Neural Networks
- Investigation of the effects of non-Gaussian noise transients and their mitigation in parameterized gravitational-wave tests of general relativity
- Multivariate Classification with Random Forests for Gravitational Wave Searches of Black Hole Binary Coalescence
- Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period
- Limiting the effects of earthquakes on gravitational-wave interferometers
- Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
- Utilizing Gaussian mixture models in all-sky searches for short-duration gravitational wave bursts
- Applications of machine learning in gravitational wave research with current interferometric detectors
- Inferring galaxy dark halo properties from visible matter with Machine Learning
- Application of Artificial Neural Network to Search for Gravitational-Wave Signals Associated with Short Gamma-Ray Bursts
- Exploring gravitational-wave detection and parameter inference using Deep Learning methods
- Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
- Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow
- A classifier for gravitational-wave inspiral signals in non-ideal single-detector data
- Glitch subtraction from gravitational wave data using adaptive spline fitting
- Using supervised learning algorithms as a follow-up method in the search of gravitational waves from core-collapse supernovae
- Sensitivity study using machine learning algorithms on simulated r-mode gravitational wave signals from newborn neutron stars
- Machine Learning enables Design of On-chip Integrated Silicon T-junctions with footprint of 1.2 m x 1.2 m
- Searches for Mass-Asymmetric Compact Binary Coalescence Events using Neural Networks in the LIGO/Virgo Third Observation Period
- Ranking Candidate Signals with Machine Learning in Low-Latency Search for Gravitational-Waves from Compact Binary Mergers
- Bilinear noise subtraction at the GEO 600 observatory
- New methods to assess and improve LIGO detector duty cycle
- A genetic-algorithm-based method to find the unitary transformations for any de- sired quantum computation and application to a one-bit oracle decision problem
- Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
- Parameter estimates in binary black hole collisions using neural networks
- A Coincidence Null Test for Poisson-Distributed Events
- Event reconstruction of Compton telescopes using a multi-task neural network
- Robust inference of gravitational wave source parameters in the presence of noise transients using normalizing flows
- Training Process of Unsupervised Learning Architecture for Gravity Spy Dataset
- Machine learning of mirror skin effects in the presence of disorder
- Spin-qubit noise spectroscopy from randomized benchmarking by supervised learning
- Novel Deep Learning Approach to Detecting Binary Black Hole Mergers
- Machine Learning for Quantum-Enhanced Gravitational-Wave Observatories
- Clusternets: A deep learning approach to probe clustering dark energy
- Detecting and Diagnosing Terrestrial Gravitational-Wave Mimics Through Feature Learning
- Sensing and vetoing loud transient noises for the gravitational-wave detection
- Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
- Glitch veto based on unphysical gravitational wave binary inspiral templates
- Architectural Optimization and Feature Learning for High-Dimensional Time Series Datasets
- Unveiling gravitational waves from core-collapse supernovae with MUSE
- Searches for Compact Binary Coalescence Events Using Neural Networks in LIGO/Virgo Third Observation Period