Identification of Binary Neutron Star Mergers in Gravitational-Wave Data Using YOLO One-Shot Object Detection

Abstract

We demonstrate the application of the YOLOv5 model, a general purpose convolution-based single-shot object detection model, in the task of detecting binary neutron star (BNS) coalescence events from gravitational-wave data of current generation interferometer detectors. We also present a thorough explanation of the synthetic data generation and preparation tasks based on approximant waveform models used for the model training, validation and testing steps. Using this approach, we achieve mean average precision (${\text{mAP}}_{[0.50]}$) values of 0.945 for a single class validation dataset and as high as 0.978 for test datasets. Moreover, the trained model is successful in identifying the GW170817 event in the LIGO H1 detector data. The identification of this event is also possible for the LIGO L1 detector data with an additional pre-processing step, without the need of removing the large glitch in the final stages of the inspiral. The detection of the GW190425 event is less successful, which attests to performance degradation with the signal-to-noise ratio. Our study indicates that the YOLOv5 model is an interesting approach for first-stage detection alarm pipelines and, when integrated in more complex pipelines, for real-time inference of physical source parameters.

arXiv comment11 pages, 9 figures

References in corpus (33)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• 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
• YOLOX: Exceeding YOLO Series in 2021
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• GW190425: Observation of a Compact Binary Coalescence with Total Mass $\sim 3.4M_{\odot }$
• Characterization of the LIGO detectors during their sixth science run
• Interferometer design of the KAGRA gravitational wave detector
• Matched filtering of gravitational waves from inspiraling compact binaries: Computational cost and template placement
• You Only Learn One Representation: Unified Network for Multiple Tasks
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Fast R-CNN
• Improving the NRTidal model for binary neutron star systems
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Matter imprints in waveform models for neutron star binaries: tidal and self-spin effects
• GWTC-2.1: Deep Extended Catalog of Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• Enhancing Gravitational-Wave Science with Machine Learning
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
• Improving astrophysical parameter estimation via offline noise subtraction for Advanced LIGO
• Gravitational wave signal recognition of O1 data by deep learning
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• Detection and Parameter Estimation of Gravitational Waves from Binary Neutron-Star Mergers in Real LIGO Data using Deep Learning
• Regression of Environmental Noise in LIGO Data
• Deep learning for gravitational wave forecasting of neutron star mergers
• Training Strategies for Deep Learning Gravitational-Wave Searches
• Convolutional neural networks for the detection of the early inspiral of a gravitational-wave signal
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Improved deep learning techniques in gravitational-wave data analysis
• Ensemble of Deep Convolutional Neural Networks for real-time gravitational wave signal recognition
• Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period
• Exploring gravitational-wave detection and parameter inference using Deep Learning methods

Cited by in corpus (8)

• New Gravitational Wave Discoveries Enabled by Machine Learning
• Applications of Machine Learning to Detecting Fast Neutrino Flavor Instabilities in Core-Collapse Supernova and Neutron Star Merger Models
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• Compact Binaries through a Lens: Silent vs. Detectable Microlensing for the LIGO-Virgo-KAGRA Gravitational Wave Observatories
• Comparative study of 1D and 2D convolutional neural network models with attribution analysis for gravitational wave detection from compact binary coalescences
• Searching for gravitational waves from stellar-mass binary black holes early inspiral
• Binary Neutron Star Merger Search Pipeline Powered by Deep Learning
• Neural Networks for the Analysis of Traced Particles in Kinetic Plasma Simulations