Applications of Machine Learning to Predicting Core-collapse Supernova Explosion Outcomes

Abstract

Most existing criteria derived from progenitor properties of core-collapse supernovae are not very accurate in predicting explosion outcomes. We present a novel look at identifying the explosion outcome of core-collapse supernovae using a machine learning approach. Informed by a sample of 100 2D axisymmetric supernova simulations evolved with Fornax, we train and evaluate a random forest classifier as an explosion predictor. Furthermore, we examine physics-based feature sets including the compactness parameter, the Ertl condition, and a newly developed set that characterizes the silicon/oxygen interface. With over 1500 supernovae progenitors from 9$-$27 M${}_{\odot }$, we additionally train an auto-encoder to extract physics-agnostic features directly from the progenitor density profiles. We find that the density profiles alone contain meaningful information regarding their explodability. Both the silicon/oxygen and auto-encoder features predict explosion outcome with $\approx$90\% accuracy. In anticipation of much larger multi-dimensional simulation sets, we identify future directions in which machine learning applications will be useful beyond explosion outcome prediction.

arXiv comment12 pages, 4 figures, 2 tables, submitted to ApJL

References in corpus (63)

• Core-Collapse Supernovae from 9 to 120 Solar Masses Based on Neutrino-powered Explosions
• Black Hole Formation in Failing Core-Collapse Supernovae
• Mass Limits For Black Hole Formation
• Progenitor-Explosion Connection and Remnant Birth Masses for Neutrino-Driven Supernovae of Iron-Core Progenitors
• A two-parameter criterion for classifying the explodability of massive stars by the neutrino-driven mechanism
• Data Mining and Machine Learning in Astronomy
• The Overarching Framework of Core-Collapse Supernova Explosions as Revealed by 3D Fornax Simulations
• Exploring the relativistic regime with Newtonian hydrodynamics: An improved effective gravitational potential for supernova simulations
• High Resolution Study of Presupernova Compactness
• A Simple Approach to the Supernova Progenitor-Explosion Connection
• Exploring Fundamentally Three-dimensional Phenomena in High-fidelity Simulations of Core-collapse Supernovae
• Three-Dimensional Simulations of Neutrino-Driven Core-Collapse Supernovae from Low-Mass Single and Binary Star Progenitors
• A Successful 3D Core-Collapse Supernova Explosion Model
• Fornax: a Flexible Code for Multiphysics Astrophysical Simulations
• Different to the core: the pre-supernova structures of massive single and binary-stripped stars
• The Progenitor Dependence of the Preexplosion Neutrino Emission in Core-Collapse Supernovae
• Three-Dimensional Supernova Explosion Simulations of 9-, 10-, 11-, 12-, and 13-M${}_{\odot }$ Stars
• Rotation-supported Neutrino-driven Supernova Explosions in Three Dimensions and the Critical Luminosity Condition
• Classifying Radio Galaxies with Convolutional Neural Network
• The Progenitor Dependence of Three-Dimensional Core-Collapse Supernovae
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• A recurrent neural network for classification of unevenly sampled variable stars
• The Last Minutes of Oxygen Shell Burning in a Massive Star
• Progenitor-dependent Explosion Dynamics in Self-consistent, Axisymmetric Simulations of Neutrino-driven Core-collapse Supernovae
• Electron-Capture and Low-Mass Iron-Core-Collapse Supernovae: New Neutrino-Radiation-Hydrodynamics Simulations
• Crucial Physical Dependencies of the Core-Collapse Supernova Mechanism
• Pushing 1D CCSNe to explosions: model and SN 1987A
• Two Dimensional Core-Collapse Supernova Explosions Aided by General Relativity with Multidimensional Neutrino Transport
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Magnetorotational Explosion of A Massive Star Supported by Neutrino Heating in General Relativistic Three Dimensional Simulations
• Two-Dimensional Core-Collapse Supernova Models with Multi-Dimensional Transport
• Simulating Turbulence-aided Neutrino-driven Core-collapse Supernova Explosions in One Dimension
• Magnetorotational core collapse of possible GRB progenitors. III. Three-dimensional models
• Revival of the Fittest: Exploding Core-Collapse Supernovae from 12 to 25 M${}_{\odot }$
• Three-Dimensional Core-Collapse Supernova Simulations with Multi-Dimensional Neutrino Transport Compared to the Ray-by-Ray-plus Approximation
• One-, Two-, and Three-dimensional Simulations of Oxygen Shell Burning Just Before the Core-Collapse of Massive Stars
• The Physics of the Neutrino Mechanism of Core-Collapse Supernovae
• Multi-D Simulations of Ultra-Stripped Supernovae to Shock Breakout
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• A numerical model for multigroup radiation hydrodynamics
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• The Collapse and Three-Dimensional Explosion of Three-Dimensional, vis à vis One-Dimensional, Massive-star Supernova Progenitor Models
• Core-collapse supernova simulations and the formation of neutron stars, hybrid stars, and black holes
• Towards an Understanding of the Resolution Dependence of Core-Collapse Supernova Simulations
• Evolution of ONeMg Core in Super-AGB Stars towards Electron-Capture Supernovae: Effects of Updated Electron-Capture Rate
• Anomaly detection in the Zwicky Transient Facility DR3
• Binary-Stripped Stars as Core-Collapse Supernovae Progenitors
• Active Anomaly Detection for time-domain discoveries
• Optimal Classification and Outlier Detection for Stripped-Envelope Core-Collapse Supernovae
• Three-Dimensional Hydrodynamic Simulations of Convective Nuclear Burning In Massive Stars Near Iron Core Collapse
• Spectral modeling of type II supernovae II. A machine learning approach to quantitative spectroscopic analysis
• Translating neutron star observations to nuclear symmetry energy via artificial neural networks
• On The Development of Multidimensional Progenitor Models For Core-collapse Supernovae
• The ZTF Source Classification Project: I. Methods and Infrastructure
• Stellar Parameter Determination from Photometry using Invertible Neural Networks
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Convection-Aided Explosions in One-Dimensional Core-Collapse Supernova Simulations I: Technique and Validation
• Hydrodynamic Simulations of Electron-capture Supernovae: Progenitor and Dimension Dependence
• The Three-Dimensional Collapse of a Rapidly Rotating 16 $M_{\odot }$ Star
• The Antesonic Condition for the Explosion of Core-Collapse Supernovae I: Spherically Symmetric Polytropic Models: Stability & Wind Emergence
• A Force Explosion Condition for Spherically Symmetric Core-collapse Supernovae
• Characterization of Supernovae Based on the Spectral-Temporal Energy Distribution: Possible two SN Ib Subtypes

Cited by in corpus (13)

• The physics of Core-Collapse Supernovae: explosion mechanism and explosive nucleosynthesis
• It's written in the massive stars: The role of stellar physics in the formation of black holes
• A 3D Simulation of a Type II-P Supernova: from Core Bounce to Beyond Shock Breakout
• Explodability criteria for the neutrino-driven supernova mechanism
• Applications of Machine Learning to Detecting Fast Neutrino Flavor Instabilities in Core-Collapse Supernova and Neutron Star Merger Models
• Exploring Supernova Gravitational Waves with Machine Learning
• Diffuse neutrino background from past core-collapse supernovae
• From Galactic Chemical Evolution to Cosmic Supernova Rates Synchronized with Core-Collapse Supernovae Limited to the Narrow Progenitor Mass Range
• Earth tomography with supernova neutrinos at future neutrino detectors
• Light Curves of Type IIP Supernovae from Neutrino-driven Explosions of Red Supergiants Obtained by a Semi-analytic Approach
• R-process heating implementation in hydrodynamic simulations with neural networks
• Carbon from massive binary-stripped stars over cosmic time: effect of metallicity
• Shedding light on the $\Delta m_{21}^2$ tension with supernova neutrinos