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.

12 pages, 4 figures, 2 tables, submitted to ApJL

References in corpus (15)

• 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
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• A recurrent neural network for classification of unevenly sampled variable stars
• Two-Dimensional Core-Collapse Supernova Models with Multi-Dimensional Transport
• Anomaly detection in the Zwicky Transient Facility DR3
• 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
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• The Three-Dimensional Collapse of a Rapidly Rotating 16 $M_{\odot }$ Star
• Characterization of Supernovae Based on the Spectral-Temporal Energy Distribution: Possible two SN Ib Subtypes

Cited by in corpus (1)

• From Galactic Chemical Evolution to Cosmic Supernova Rates Synchronized with Core-Collapse Supernovae Limited to the Narrow Progenitor Mass Range