SuperRAENN: A Semi-supervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium Deep Survey Supernovae

Abstract

Automated classification of supernovae (SNe) based on optical photometric light curve information is essential in the upcoming era of wide-field time domain surveys, such as the Legacy Survey of Space and Time (LSST) conducted by the Rubin Observatory. Photometric classification can enable real-time identification of interesting events for extended multi-wavelength follow-up, as well as archival population studies. Here we present the complete sample of 5,243 "SN-like" light curves (in griz) from the Pan-STARRS1 Medium-Deep Survey (PS1-MDS). The PS1-MDS is similar to the planned LSST Wide-Fast-Deep survey in terms of cadence, filters and depth, making this a useful training set for the community. Using this dataset, we train a novel semi-supervised machine learning algorithm to photometrically classify 2,315 new SN-like light curves with host galaxy spectroscopic redshifts. Our algorithm consists of a random forest supervised classification step and a novel unsupervised step in which we introduce a recurrent autoencoder neural network (RAENN). Our final pipeline, dubbed SuperRAENN, has an accuracy of 87% across five SN classes (Type Ia, Ibc, II, IIn, SLSN-I). We find the highest accuracy rates for Type Ia SNe and SLSNe and the lowest for Type Ibc SNe. Our complete spectroscopically- and photometrically-classified samples break down into: 62.0% Type Ia (1839 objects), 19.8% Type II (553 objects), 4.8% Type IIn (136 objects), 11.7% Type Ibc (291 objects), and 1.6% Type I SLSNe (54 objects). Finally, we discuss how this algorithm can be modified for online LSST data streams.

arXiv commentSubmitted to ApJ; Companion paper to Hosseinzadeh et al.; Tables 1 and 2 available on ashleyvillar.com prior to publication

References in corpus (91)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• SMOTE: Synthetic Minority Over-sampling Technique
• Measuring Reddening with SDSS Stellar Spectra and Recalibrating SFD
• Planck 2013 results. XVI. Cosmological parameters
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• The Complete Light-curve Sample of Spectroscopically Confirmed Type Ia Supernovae from Pan-STARRS1 and Cosmological Constraints from The Combined Pantheon Sample
• Type Ia Supernova Explosion Models
• The Multi-Object, Fiber-Fed Spectrographs for SDSS and the Baryon Oscillation Spectroscopic Survey
• The 6dF Galaxy Survey: Final Redshift Release (DR3) and Southern Large-Scale Structures
• The Pan-STARRS1 Photometric System
• zCOSMOS: A Large VLT/VIMOS redshift survey covering 0 < z < 3 in the COSMOS field
• SALT2: using distant supernovae to improve the use of Type Ia supernovae as distance indicators
• The Fifth Data Release of the Sloan Digital Sky Survey
• The DEEP2 Galaxy Redshift Survey: Design, Observations, Data Reduction, and Redshifts
• The Chandra Deep Field South: Optical Spectroscopy I
• Rates and properties of type Ia supernovae as a function of mass and star-formation in their host galaxies
• The WiggleZ Dark Energy Survey: Survey Design and First Data Release
• Determining the Type, Redshift, and Age of a Supernova Spectrum
• RVSAO 2.0: Digital Redshifts and Radial Velocities
• An ultraviolet-optical flare from the tidal disruption of a helium-rich stellar core
• An Open Catalog for Supernova Data
• Hectospec, the MMT's 300 Optical Fiber-Fed Spectrograph
• Rapidly-Evolving and Luminous Transients from Pan-STARRS1
• Cosmological Constraints from Measurements of Type Ia Supernovae discovered during the first 1.5 years of the Pan-STARRS1 Survey
• Pan-STARRS Photometric and Astrometric Calibration
• The Great Observatories Origins Deep Survey - VLT/VIMOS Spectroscopy in the GOODS-South Field: Part II
• Improved redshifts for SDSS quasar spectra
• The magnetar model for Type I superluminous supernovae I: Bayesian analysis of the full multicolour light curve sample with MOSFiT
• SN 2005ap: A Most Brilliant Explosion
• Hydrogen-Poor Superluminous Supernovae and Long-Duration Gamma-Ray Bursts Have Similar Host Galaxies
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). Full spectroscopic data and auxiliary information release (PDR-2)
• Gemini Spectroscopy of Supernovae from SNLS: Improving High Redshift SN Selection and Classification
• Towards Characterization of the Type IIP Supernova Progenitor Population: a Statistical Sample of Light Curves from Pan-STARRS1
• Testing LMC Microlensing Scenarios: The Discrimination Power of the SuperMACHO Microlensing Survey
• Pan-STARRS1 Discovery of Two Ultra-Luminous Supernovae at z ~ 0.9
• The UV-bright, Slowly Declining Transient PS1-11af as a Partial Tidal Disruption Event
• Photometric Supernova Classification With Machine Learning
• Deep ATLAS radio observations of the CDFS-SWIRE field
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• The 2dF-SDSS LRG and QSO (2SLAQ) Luminous Red Galaxy Survey
• Results from the Supernova Photometric Classification Challenge
• The Pan-STARRS Data Processing System
• Pan-STARRS Pixel Processing: Detrending, Warping, Stacking
• SN 2009ip and SN 2010mc: Core-collapse Type IIn supernovae arising from blue supergiants
• Calibration of the optical mass proxy for clusters of galaxies and an update of the WHL12 cluster catalog
• 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 COSMOS AGN Spectroscopic Survey I: XMM Counterparts
• ESC Supernova spectroscopy of non-ESC targets
• A recurrent neural network for classification of unevenly sampled variable stars
• Precise Throughput Determination of the PanSTARRS Telescope and the Gigapixel Imager using a Calibrated Silicon Photodiode and a Tunable Laser: Initial Results
• The matallicities of star-forming galaxies at intermediate redshifts 0.47 < z < 0.92
• Hydrogen-Poor Superluminous Supernovae from the Pan-STARRS1 Medium Deep Survey
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Low-Redshift Ly-alpha Selected Galaxies from GALEX Spectroscopy: A Comparison with Both UV-Continuum Selected Galaxies and High-Redshift Ly-alpha Emitters
• Deep Recurrent Neural Networks for Supernovae Classification
• Detection of the Gravitational Lens Magnifying a Type Ia Supernova
• The effect of dust geometry on the Lyman-alpha output of galaxies
• Physical properties of galaxies and their evolution in the VIMOS VLT Deep Survey. I. The evolution of the mass-metallicity relation up to z~0.9
• The Foundation Supernova Survey: Measuring Cosmological Parameters with Supernovae from a Single Telescope
• SNLS Spectroscopy: Testing for Evolution in Type Ia Supernovae
• Theoretical Models of Optical Transients. I. A Broad Exploration of the Duration-Luminosity Phase Space
• PS1-10afx at z=1.388: Pan-STARRS1 Discovery of a New Type of Superluminous Supernova
• LOSS Revisited - I: Unraveling correlations between supernova rates and galaxy properties, as measured in a reanalysis of the Lick Observatory Supernova Search
• Kernel PCA for type Ia supernovae photometric classification
• Deep learning Approach for Classifying, Detecting and Predicting Photometric Redshifts of Quasars in the Sloan Digital Sky Survey Stripe 82
• Displaying the Heterogeneity of the SN 2002cx-like Subclass of Type Ia Supernovae with Observations of the Pan-STARRS-1 Discovered SN2009ku
• PS1-12sk is a Peculiar Supernova From a He-rich Progenitor System in a Brightest Cluster Galaxy Environment
• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Measuring the Properties of Dark Energy with Photometrically Classified Pan-STARRS Supernovae. I. Systematic Uncertainty from Core-Collapse Supernova Contamination
• Multiscale probability mapping: groups, clusters and an algorithmic search for filaments in SDSS
• Are There Blue, Massive E/S0s at z < 1 ?: Kinematics of Blue Spheroidal Galaxy Candidates
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Semi-supervised Learning for Photometric Supernova Classification
• The XMM large scale structure survey: optical vs. X-ray classifications of active galactic nuclei and the unified scheme
• STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
• Obscured and unobscured AGN populations in a hard-X-ray selected sample of the XMDS survey
• Classifying Supernovae Using Only Galaxy Data
• Optical identification of XMM sources in the CFHTLS
• A Plethora of AGN Among Lyman Alpha Galaxies at Low Redshift
• Luminous Red Galaxy Clustering at z~0.7 - First Results using AAOmega
• Low redshift quasars in the SDSS Stripe 82. The local environments
• Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot
• Unsupervised feature-learning for galaxy SEDs with denoising autoencoders
• Real-Time Value-Driven Data Augmentation in the Era of LSST
• Optical and infrared properties of active galactic nuclei in the Lockman Hole
• The Deep SWIRE Field III. WIYN Spectroscopy

Cited by in corpus (49)

• SALT3: An Improved Type Ia Supernova Model for Measuring Cosmic Distances
• The Young Supernova Experiment: Survey Goals, Overview, and Operations
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Cosmological Results from the RAISIN Survey: Using Type Ia Supernovae in the Near Infrared as a Novel Path to Measure the Dark Energy Equation of State
• Testing the Consistency of Dust Laws in SN Ia Host Galaxies: A BayeSN Examination of Foundation DR1
• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Superluminous supernovae: an explosive decade
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• Luminous Supernovae: Unveiling a Population Between Superluminous and Normal Core-collapse Supernovae
• A review of unsupervised learning in astronomy
• SALT3-NIR: Taking the Open-Source Type Ia Supernova Model to Longer Wavelengths for Next-Generation Cosmological Measurements
• The Dark Energy Survey 5-year photometrically identified Type Ia Supernovae
• ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning
• Translating neutron star observations to nuclear symmetry energy via artificial neural networks
• Machine Learning for Observational Cosmology
• Identifying Tidal Disruption Events with an Expansion of the FLEET Machine Learning Algorithm
• Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot
• Spectroscopic Studies of Type Ia Supernovae Using LSTM Neural Networks
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• Quasar Factor Analysis -- An Unsupervised and Probabilistic Quasar Continuum Prediction Algorithm with Latent Factor Analysis
• Machine Learning and Cosmology
• Carnegie Supernova Project-II: Near-infrared spectral diversity and template of Type Ia Supernovae
• Classifying Astronomical Transients Using Only Host Galaxy Photometry
• Using Rest-Frame Optical and NIR Data from the RAISIN Survey to Explore the Redshift Evolution of Dust Laws in SN Ia Host Galaxies
• The Simulated Catalogue of Optical Transients and Correlated Hosts (SCOTCH)
• Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• The Importance of Being Interpretable: Toward An Understandable Machine Learning Encoder for Galaxy Cluster Cosmology
• SNAD Transient Miner: Finding Missed Transient Events in ZTF DR4 using k-D trees
• Impact of Rubin Observatory cadence choices on supernovae photometric classification
• Photometric Data-driven Classification of Type Ia Supernovae in the Open Supernova Catalog
• Photometrically-Classified Superluminous Supernovae from the Pan-STARRS1 Medium Deep Survey: A Case Study for Science with Machine Learning-Based Classification
• SNGuess: A method for the selection of young extragalactic transients
• Using Gaussian Processes to detect AGN flares
• Unveiling the Universe with Emerging Cosmological Probes
• Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST
• Semi-supervised classification of stars, galaxies and quasars using K-means and random-forest approaches
• eROSITA-RU Tidal Disruption Events with Keck-I/LRIS: Sample Selection, Optical Properties, and Host Galaxy Demographics
• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
• Unsupervised learning for variability detection with Gaia DR3 photometry. The main sequence-white dwarf valley
• Real-time Light Curve Classification Framework for the Wide Field Survey Telescope Using Modified Semi-supervised Variational Auto-Encoder
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• AMPEL workflows for LSST: Modular and reproducible real-time photometric classification
• Supernova host galaxy association and photometric classification of over 10,000 light curves from the Zwicky Transient Facility
• A Photometric Classifier for Tidal Disruption Events in Rubin LSST
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory
• Multivariate time series transformer embeddings for light curves of periodic variable stars
• New Metrics for Identifying Variables and Transients in Large Astronomical Surveys