Deep-Learning Classification and Parameter Inference of Rotational Core-Collapse Supernovae

Abstract

We test deep-learning (DL) techniques for the analysis of rotational core-collapse supernovae (CCSN) gravitational-wave (GW) signals by performing classification and parameter inference of the maximum (peak) frequency and the GW strain amplitude ($\Delta h$) multiplied by the luminosity distance ($D$) attained at core bounce, respectively, $(f_{peak})$ and $(D\cdot \Delta h)$. Our datasets are built from a catalog of numerically generated CCSN waveforms assembled by Richers et al. 2017. Those waveforms are injected into noise from the Advanced Laser Interferometer Gravitational Wave Observatory and Advanced Virgo detectors corresponding to the O2 and O3a observing runs. For a network signal-to-noise ratio (SNR) above 5, our classification network using time series detects Galactic CCSN GW signals buried in detector noise with a false positive rate of 0.10% and a 98% accuracy, being able to detect all signals with SNR>10. The inference of $f_{peak}$ is more accurate than for $D\cdot \Delta h$, particularly for our datasets with the shortest time window (0.25 s) and for a minimum SNR=15. From the calibration plots of predicted versus true values of the two parameters, the standard deviation ($\sigma$) and the slope deviation with respect to the ideal value are computed. We find ${\sigma }_{D\cdot \Delta h}=52.6$ cm and ${\sigma }_{f_{peak}}=18.3$ Hz, with respective slope deviations of 11.6% and 8.3%. Our best model is also tested on waveforms from a recent CCSN catalog built by Mitra et al. 2023, different from the one used for the training. For these new waveforms, the true values of the two parameters are mostly within the $1\sigma$ band around the network's predicted values. Our results show that DL techniques hold promise to infer physical parameters of Galactic rotational CCSN events.

References in corpus (55)

• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run
• Presupernova Evolution of Differentially Rotating Massive Stars Including Magnetic Fields
• Core-collapse supernova equations of state based on neutron star observations
• A guide to LIGO-Virgo detector noise and extraction of transient gravitational-wave signals
• Relativistic simulations of rotational core collapse. II. Collapse dynamics and gravitational radiation
• The gravitational wave burst signal from core collapse of rotating stars
• Real-time gravitational-wave science with neural posterior estimation
• An Open-Source Neutrino Radiation Hydrodynamics Code for Core-Collapse Supernovae
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• The gravitational wave signal from core-collapse supernovae
• Enhancing Gravitational-Wave Science with Machine Learning
• Gravitational-wave parameter estimation with autoregressive neural network flows
• A simple parameterization of the consequences of deleptonization for simulations of stellar core collapse
• Observing Gravitational Waves from Core-Collapse Supernovae in the Advanced Detector Era
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• Equation of State Effects on Gravitational Waves from Rotating Core Collapse
• Magnetorotational core collapse of possible GRB progenitors. I. Explosion mechanisms
• An Optically Targeted Search for Gravitational Waves emitted by Core-Collapse Supernovae during the First and Second Observing Runs of Advanced LIGO and Advanced Virgo
• "Mariage des Maillages": A new numerical approach for 3D relativistic core collapse simulations
• Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference
• Coherent WaveBurst, a pipeline for unmodeled gravitational-wave data analysis
• Correlated Gravitational Wave and Neutrino Signals from General-Relativistic Rapidly Rotating Iron Core Collapse
• Bayesian reconstruction of gravitational wave burst signals from simulations of rotating stellar core collapse and bounce
• Measuring the Angular Momentum Distribution in Core-Collapse Supernova Progenitors with Gravitational Waves
• Universal relations for gravitational-wave asteroseismology of proto-neutron stars
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Inferring the core-collapse supernova explosion mechanism with gravitational waves
• Inferring Core-Collapse Supernova Physics with Gravitational Waves
• Detection and Classification of Supernova Gravitational Waves Signals: A Deep Learning Approach
• A New Method to Observe Gravitational Waves emitted by Core Collapse Supernovae
• Equation of State Dependence of Gravitational Waves in Core-Collapse Supernovae
• Core Collapse Supernova Gravitational Wave Emission for Progenitors of 9.6, 15, and 25 Solar Masses
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Supernova Seismology: Gravitational Wave Signatures of Rapidly Rotating Core Collapse
• Deep learning for multimessenger core-collapse supernova detection
• Machine Learning Gravitational Waves from Binary Black Hole Mergers
• Inference of proto-neutron star properties from gravitational-wave data in core-collapse supernovae
• Denoising of gravitational wave signals via dictionary learning algorithms
• Universal relation for supernova gravitational waves
• Application of dictionary learning to denoise LIGO's blip noise transients
• Determining the Structure of Rotating Massive Stellar Cores with Gravitational Waves
• Inferring the core-collapse supernova explosion mechanism with three-dimensional gravitational-wave simulations
• Gravitational wave signature of proto-neutron star convection: I. MHD numerical simulations
• Classifying the Equation of State from Rotating Core Collapse Gravitational Waves with Deep Learning
• Combining effective-one-body accuracy and reduced-order-quadrature speed for binary neutron star merger parameter estimation with machine learning
• LSTM and CNN application for core-collapse supernova search in gravitational wave real data
• Deep Generative Models of Gravitational Waveforms via Conditional Autoencoder
• Exploring gravitational-wave detection and parameter inference using Deep Learning methods
• Classification of the core-collapse supernova explosion mechanism with learned dictionaries
• Rapid parameter estimation for an all-sky continuous gravitational wave search using conditional varitational auto-encoders
• Exploring Supernova Gravitational Waves with Machine Learning
• Inferring physical properties of stellar collapse by third-generation gravitational-wave detectors
• Visualizing convolutional neural network for classifying gravitational waves from core-collapse supernovae

Cited by in corpus (5)

• The Science of the Einstein Telescope
• A novel stacked hybrid autoencoder for imputing LISA data gaps
• Evaluating Machine Learning Models for Supernova Gravitational Wave Signal Classification
• Assessing the Distance for Probing the Nuclear Equation of State with Supernova Gravitational Waves
• Residual neural networks to classify the high frequency emission in core-collapse supernova gravitational waves