Glitch Classification and Clustering for LIGO with Deep Transfer Learning

Abstract

The detection of gravitational waves with LIGO and Virgo requires a detailed understanding of the response of these instruments in the presence of environmental and instrumental noise. Of particular interest is the study of anomalous non-Gaussian noise transients known as glitches, since their high occurrence rate in LIGO/Virgo data can obscure or even mimic true gravitational wave signals. Therefore, successfully identifying and excising glitches is of utmost importance to detect and characterize gravitational waves. In this article, we present the first application of Deep Learning combined with Transfer Learning for glitch classification, using real data from LIGO's first discovery campaign labeled by Gravity Spy, showing that knowledge from pre-trained models for real-world object recognition can be transferred for classifying spectrograms of glitches. We demonstrate that this method enables the optimal use of very deep convolutional neural networks for glitch classification given small unbalanced training datasets, significantly reduces the training time, and achieves state-of-the-art accuracy above 98.8%. Once trained via transfer learning, we show that the networks can be truncated and used as feature extractors for unsupervised clustering to automatically group together new classes of glitches and anomalies. This novel capability is of critical importance to identify and remove new types of glitches which will occur as the LIGO/Virgo detectors gradually attain design sensitivity.

Camera-ready (final) paper accepted to NIPS 2017 conference workshop on Deep Learning for Physical Sciences. Extended article: arXiv:1706.07446

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Multi-messenger Observations of a Binary Neutron Star Merger
• Advanced LIGO
• GW170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence
• Swope Supernova Survey 2017a (SSS17a), the Optical Counterpart to a Gravitational Wave Source
• BayesWave: Bayesian Inference for Gravitational Wave Bursts and Instrument Glitches
• 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
• Classification methods for noise transients in advanced gravitational-wave detectors II: performance tests on Advanced LIGO data

Cited by in corpus (93)

• An overview of deep learning in medical imaging focusing on MRI
• The Zwicky Transient Facility: Science Objectives
• Enhancing Gravitational-Wave Science with Machine Learning
• Gravitational Wave Denoising of Binary Black Hole Mergers with Deep Learning
• Reduced-order modeling with artificial neurons for gravitational-wave inference
• Deep-Learning continuous gravitational waves
• Gravitational wave signal recognition of O1 data by deep learning
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Detection and Classification of Supernova Gravitational Waves Signals: A Deep Learning Approach
• Methodology study of machine learning for the neutron star equation of state
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
• Deep Transfer Learning for Star Cluster Classification: I. Application to the PHANGS-HST Survey
• Deep learning for clustering of continuous gravitational wave candidates
• Detecting Gravitational-waves from Extreme Mass Ratio Inspirals using Convolutional Neural Networks
• Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
• Classifying the unknown: discovering novel gravitational-wave detector glitches using similarity learning
• Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
• Physics of eccentric binary black hole mergers: A numerical relativity perspective
• Some Optimizations on Detecting Gravitational Wave Using Convolutional Neural Network
• A review of unsupervised learning in astronomy
• Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Search for black hole hyperbolic encounters with gravitational wave detectors
• Using Deep Learning to Localize Gravitational Wave Sources
• Improved deep learning techniques in gravitational-wave data analysis
• Fusing numerical relativity and deep learning to detect higher-order multipole waveforms from eccentric binary black hole mergers
• A Survey on Deep Transfer Learning
• From One to Many: A Deep Learning Coincident Gravitational-Wave Search
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Binary Neutron Stars Gravitational Wave Detection Based on Wavelet Packet Analysis And Convolutional Neural Networks
• Classifying the Equation of State from Rotating Core Collapse Gravitational Waves with Deep Learning
• Gravity Spy: Lessons Learned and a Path Forward
• An autoencoder neural network integrated into gravitational-wave burst searches to improve the rejection of noise transients
• Total-variation methods for gravitational-wave denoising: performance tests on Advanced LIGO data
• Deep learning for clustering of continuous gravitational wave candidates II: identification of low-SNR candidates
• Recovering the CMB Signal with Machine Learning
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Identification of Lensed Gravitational Waves with Deep Learning
• Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Characterization of numerical relativity waveforms of eccentric binary black hole mergers
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• Utilizing Gaussian mixture models in all-sky searches for short-duration gravitational wave bursts
• A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
• Exploring gravitational-wave detection and parameter inference using Deep Learning methods
• Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-wave Detectors
• Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow
• Likelihood-free Inference with Mixture Density Network
• Star Cluster Classification using Deep Transfer Learning with PHANGS-HST
• 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
• Learning Models of Individual Behavior in Chess
• On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks
• Optimal pre-train/fine-tune strategies for accurate material property predictions
• Glitch subtraction from gravitational wave data using adaptive spline fitting
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• Transfer learning with generative models for object detection on limited datasets
• SLICK: Strong Lensing Identification of Candidates Kindred in gravitational wave data
• Application of the independent component analysis to the iKAGRA data
• New methods to assess and improve LIGO detector duty cycle
• Supporting High-Performance and High-Throughput Computing for Experimental Science
• Training Process of Unsupervised Learning Architecture for Gravity Spy Dataset
• Data-driven detection of multi-messenger transients
• Computational Techniques for Parameter Estimation of Gravitational Wave Signals
• Deep Transfer Learning for Blended Source Identification in Galaxy Survey Data
• Searching for gravitational waves from stellar-mass binary black holes early inspiral
• Employing Deep Learning for Detection of Gravitational Waves from Compact Binary Coalescences
• Astrophysics with the Laser Interferometer Space Antenna
• cDVGAN: One Flexible Model for Multi-class Gravitational Wave Signal and Glitch Generation
• Reconstruction of binary black hole harmonics in LIGO using deep learning
• No Glitch in the Matrix: Robust Reconstruction of Gravitational Wave Signals Under Noise Artifacts
• Deep Learning Approach for Very Similar Objects Recognition Application on Chihuahua and Muffin Problem
• Improving Prognostic Performance in Resectable Pancreatic Ductal Adenocarcinoma using Radiomics and Deep Learning Features Fusion in CT Images
• Deep-Learning in Search of Light Charged Higgs
• Searching for Sub-Second Stellar Variability with Wide-Field Star Trails and Deep Learning
• Time delay estimation in unresolved lensed quasars
• Real-time regression analysis with deep convolutional neural networks
• Using t-SNE for characterizing glitches in LIGO detectors
• Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
• Automatic Cross-Domain Transfer Learning for Linear Regression
• Genetic-algorithm-optimized neural networks for gravitational wave classification
• Characterization of Gravitational Waves Signals Using Neural Networks
• Machine Learning Confirms GW231123 is a "Lite" Intermediate Mass Black Hole Merger
• Glitch veto based on unphysical gravitational wave binary inspiral templates
• Multiband neural network classification of ZTF light curves as LSST proxies
• Deep Learning Techniques to make Gravitational Wave Detections from Weak Time-Series Data
• Sequence modeling of higher-order wave modes of binary black hole mergers
• Constraints on typical relic gravitational waves based on data of LIGO
• RL agents Implicitly Learning Human Preferences