Photometric classification of HSC transients using machine learning

Abstract

The advancement of technology has resulted in a rapid increase in supernova (SN) discoveries. The Subaru/Hyper Suprime-Cam (HSC) transient survey, conducted from fall 2016 through spring 2017, yielded 1824 SN candidates. This gave rise to the need for fast type classification for spectroscopic follow-up and prompted us to develop a machine learning algorithm using a deep neural network (DNN) with highway layers. This machine is trained by actual observed cadence and filter combinations such that we can directly input the observed data array into the machine without any interpretation. We tested our model with a dataset from the LSST classification challenge (Deep Drilling Field). Our classifier scores an area under the curve (AUC) of 0.996 for binary classification (SN Ia or non-SN Ia) and 95.3% accuracy for three-class classification (SN Ia, SN Ibc, or SN II). Application of our binary classification to HSC transient data yields an AUC score of 0.925. With two weeks of HSC data since the first detection, this classifier achieves 78.1% accuracy for binary classification, and the accuracy increases to 84.2% with the full dataset. This paper discusses the potential use of machine learning for SN type classification purposes.

23 pages, 18 figures, accepted for publication in PASJ

References in corpus (76)

• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Complete Light-curve Sample of Spectroscopically Confirmed Type Ia Supernovae from Pan-STARRS1 and Cosmological Constraints from The Combined Pantheon Sample
• Exploring the Expansion History of the Universe
• The Cosmic Evolution Survey (COSMOS) -- Overview
• Evolutionary population synthesis: models, analysis of the ingredients and application to high-z galaxies
• Improved cosmological constraints from a joint analysis of the SDSS-II and SNLS supernova samples
• The COSMOS2015 Catalog: Exploring the 1<z<6 Universe with half a million galaxies
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• SALT2: using distant supernovae to improve the use of Type Ia supernovae as distance indicators
• Nearby Supernova Rates from the Lick Observatory Supernova Search. II. The Observed Luminosity Functions and Fractions of Supernovae in a Complete Sample
• First Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• Luminous Supernovae
• The Supernova Legacy Survey 3-year sample: Type Ia Supernovae photometric distances and cosmological constraints
• The type Ia supernova SNLS-03D3bb from a super-Chandrasekhar-mass white dwarf star
• The Cosmic Energy Inventory
• Hydrogen-poor superluminous stellar explosions
• ANNz: estimating photometric redshifts using artificial neural networks
• A Modified Magnitude System that Produces Well-Behaved Magnitudes, Colors, and Errors Even for Low Signal-to-Noise Ratio Measurements
• Photometric redshift and classification for the XMM-COSMOS sources
• Photometric Redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1
• Shock Breakout in Core-Collapse Supernovae and its Neutrino Signature
• The PRIsm MUlti-Object Survey (PRIMUS) I: Survey Overview and Characteristics
• SN 2005ap: A Most Brilliant Explosion
• Chemodynamical Simulations of the Milky Way Galaxy
• The DEIMOS 10k spectroscopic survey catalog of the COSMOS field
• The Peculiar SN 2005hk: Do Some Type Ia Supernovae Explode as Deflagrations?
• On the Evolution of the Cosmic Supernova Rates
• Strong Ultraviolet Pulse From a Newborn Type Ia Supernova
• Photometric Supernova Classification With Machine Learning
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• Simulations of the WFIRST Supernova Survey and Forecasts of Cosmological Constraints
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Super-luminous supernovae at redshifts of 2.05 and 3.90
• Type-Ia Supernova Rates to Redshift 2.4 from CLASH: the Cluster Lensing And Supernova survey with Hubble
• Systematic Uncertainties Associated with the Cosmological Analysis of the First Pan-STARRS1 Type Ia Supernova Sample
• The delay of shock breakout due to circumstellar material seen in most Type II Supernovae
• The History of the Comic Supernova Rate Derived from the Evolution of the Host Galaxies
• The FMOS-COSMOS survey of star-forming galaxies at z~1.6 III. Survey design, performance, and sample characteristics
• Automated Transient Identification in the Dark Energy Survey
• Superluminous supernovae
• Measuring Dark Energy Properties with Photometrically Classified Pan-STARRS Supernovae. II. Cosmological Parameters
• Photometric SN Ia Candidates from the Three-Year SDSS-II SN Survey Data
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
• The Rate of Core Collapse Supernovae to Redshift 2.5 From The CANDELS and CLASH Supernova Surveys
• A hybrid type Ia supernova with an early flash triggered by helium-shell detonation
• The Complete Calibration of the Color-Redshift Relation (C3R2) Survey: Survey Overview and Data Release 1
• First Cosmology Results Using Type Ia Supernovae From the Dark Energy Survey: Analysis, Systematic Uncertainties, and Validation
• A Measurement of the Rate of type-Ia Supernovae at Redshift $z\approx$ 0.1 from the First Season of the SDSS-II Supernova Survey
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Measuring Type Ia Supernova Populations of Stretch and Color and Predicting Distance Biases
• Deep Recurrent Neural Networks for Supernovae Classification
• The Rise Time of Type Ia Supernovae from the Supernova Legacy Survey
• UNITY: Confronting Supernova Cosmology's Statistical and Systematic Uncertainties in a Unified Bayesian Framework
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Application of Convolutional Neural Networks for Stellar Spectral Classification
• Enrichment of the hot intracluster medium: observations
• Shock Breakout in Type II Plateau Supernovae: Prospects for High Redshift Supernova Surveys
• Cosmological Parameter Uncertainties from SALT-II Type Ia Supernova Light Curve Models
• Type Ia Supernovae in the First Few Days: Signatures of Helium Detonation versus Interaction
• The volumetric rate of normal type Ia supernovae in the local universe discovered by the Palomar Transient Factory
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• First release of high-redshift superluminous supernovae from the Subaru HIgh-Z sUpernova CAmpaign (SHIZUCA). I. Photometric properties
• The Relative Specific Type Ia Supernovae Rate From Three Years of ASAS-SN
• SN 2016jhj at redshift 0.34: extending the Type II supernova Hubble diagram using the standard candle method
• The Hyper Suprime-Cam SSP Transient Survey in COSMOS: Overview
• Rapidly Evolving Transients from the Hyper Suprime-Cam SSP Transient Survey
• First release of high-redshift superluminous supernovae from the Subaru HIgh-Z sUpernova CAmpaign (SHIZUCA). II. Spectroscopic properties
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Search for Soft X-ray Flashes at Fireball Phase of Classical/Recurrent Novae using MAXI/GSC data
• Machine learning in APOGEE: Unsupervised spectral classification with $K$-means
• R-band light-curve properties of Type Ia supernovae from the (intermediate) Palomar Transient Factory
• The HSC-SSP Transient Survey: Implications from Early Photometry and Rise Time of Normal Type Ia Supernovae

Cited by in corpus (9)

• Machine Learning for Observational Cosmology
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Spectroscopic Studies of Type Ia Supernovae Using LSTM Neural Networks
• Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys
• Photometric Data-driven Classification of Type Ia Supernovae in the Open Supernova Catalog
• Deep Learning of the Eddington Tensor in the Core-collapse Supernova Simulation
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory