A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources

Abstract

By now, tens of gravitational-wave (GW) events have been detected by the LIGO and Virgo detectors. These GWs have all been emitted by compact binary coalescence, for which we have excellent predictive models. However, there might be other sources for which we do not have reliable models. Some are expected to exist but to be very rare (e.g., supernovae), while others may be totally unanticipated. So far, no unmodeled sources have been discovered, but the lack of models makes the search for such sources much more difficult and less sensitive. We present here a search for unmodeled GW signals using semi-supervised machine learning. We apply deep learning and outlier detection algorithms to labeled spectrograms of GW strain data, and then search for spectrograms with anomalous patterns in public LIGO data. We searched $\sim 13\%$ of the coincident data from the first two observing runs. No candidates of GW signals were detected in the data analyzed. We evaluate the sensitivity of the search using simulated signals, we show that this search can detect spectrograms containing unusual or unexpected GW patterns, and we report the waveforms and amplitudes for which a $50\%$ detection rate is achieved.

arXiv comment12 pages, 7 figures, submitted - comments welcome

References in corpus (43)

• Scikit-learn: Machine Learning in Python
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• Observation of Gravitational Waves from a Binary Black Hole Merger
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• scikit-image: Image processing in Python
• Multi-messenger Observations of a Binary Neutron Star Merger
• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Understanding Neural Networks Through Deep Visualization
• GW190412: Observation of a Binary-Black-Hole Coalescence with Asymmetric Masses
• The PyCBC search for gravitational waves from compact binary coalescence
• 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
• Coherent method for detection of gravitational wave bursts
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Multiresolution techniques for the detection of gravitational-wave bursts
• Characterizing the Gravitational Wave Signal from Core-Collapse Supernovae
• A New Search Pipeline for Compact Binary Mergers: Results for Binary Black Holes in the First Observing Run of Advanced LIGO
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• All-sky search for gravitational-wave bursts in the second joint LIGO-Virgo run
• The electromagnetic counterparts of compact binary mergers
• Machine Learning in Astronomy: a practical overview
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
• Gravitational waves from three-dimensional core-collapse supernova models: The impact of moderate progenitor rotation
• Gravitational-wave signal of a core-collapse supernova explosion of a 15 Solar mass star
• All-sky search for short gravitational-wave bursts in the first Advanced LIGO run
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Measuring the Angular Momentum Distribution in Core-Collapse Supernova Progenitors with Gravitational Waves
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Detection and Classification of Supernova Gravitational Waves Signals: A Deep Learning Approach
• A New Method to Observe Gravitational Waves emitted by Core Collapse Supernovae
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• Validating gravitational-wave detections: The Advanced LIGO hardware injection system
• Gravitational-wave Signature of a First-order Quantum Chromodynamics Phase Transition in Core-Collapse Supernovae
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection
• Detecting outliers and learning complex structures with large spectroscopic surveys - a case study with APOGEE stars
• Improving the background of gravitational-wave searches for core collapse supernovae: A machine learning approach
• Optimal matched filter in the low-number count Poisson noise regime and implications for X-ray source detection

Cited by in corpus (14)

• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Data quality up to the third observing run of Advanced LIGO: Gravity Spy glitch classifications
• Deep Residual Networks for Gravitational Wave Detection
• Gravity Spy: Lessons Learned and a Path Forward
• Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Quasar Factor Analysis -- An Unsupervised and Probabilistic Quasar Continuum Prediction Algorithm with Latent Factor Analysis
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• Classifying FRB spectrograms using nonlinear dimensionality reduction techniques
• Rapid identification of time-frequency domain gravitational wave signals from binary black holes using deep learning
• Novel Deep Learning Approach to Detecting Binary Black Hole Mergers
• Nonlinear noise regression in gravitational-wave detectors with convolutional neural networks
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift