Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation

Abstract

Upcoming astronomical surveys such as the Large Synoptic Survey Telescope (LSST) will rely on photometric classification to identify the majority of the transients and variables that they discover. We present a set of techniques for photometric classification that can be applied even when the training set of spectroscopically-confirmed objects is heavily biased towards bright, low-redshift objects. Using Gaussian process regression to model arbitrary light curves in all bands simultaneously, we "augment" the training set by generating new versions of the original light curves covering a range of redshifts and observing conditions. We train a boosted decision tree classifier on features extracted from the augmented light curves, and we show how such a classifier can be designed to produce classifications that are independent of the redshift distributions of objects in the training sample. Our classification algorithm was the best-performing among the 1,094 models considered in the blinded phase of the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC), scoring 0.468 on the organizers' logarithmic-loss metric with flat weights for all object classes in the training set, and achieving an AUC of 0.957 for classification of Type Ia supernovae. Our results suggest that spectroscopic campaigns used for training photometric classifiers should focus on typing large numbers of well-observed, intermediate redshift transients instead of attempting to type a sample of transients that is directly representative of the full dataset being classified. All of the algorithms described in this paper are implemented in the avocado software package.

arXiv comment24 pages, 9 figures

References in corpus (43)

• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• Astropy: A Community Python Package for Astronomy
• The NumPy array: a structure for efficient numerical computation
• Type Ia Supernova Discoveries at z>1 From the Hubble Space Telescope: Evidence for Past Deceleration and Constraints on Dark Energy Evolution
• 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
• The Supernova Legacy Survey: Measurement of Omega_M, Omega_Lambda and w from the First Year Data Set
• Improved cosmological constraints from a joint analysis of the SDSS-II and SNLS supernova samples
• The Hubble Space Telescope Cluster Supernova Survey: V. Improving the Dark Energy Constraints Above z>1 and Building an Early-Type-Hosted Supernova Sample
• Improved Cosmological Constraints from New, Old and Combined Supernova Datasets
• New Constraints on ${\Omega }_M$, ${\Omega }_{\Lambda }$, and w from an Independent Set of Eleven High-Redshift Supernovae Observed with HST
• Understanding the Lomb-Scargle Periodogram
• SALT2: using distant supernovae to improve the use of Type Ia supernovae as distance indicators
• Hubble Residuals of Nearby Type Ia Supernovae Are Correlated with Host Galaxy Masses
• SNANA: A Public Software Package for Supernova Analysis
• Evidence of Environmental Dependencies of Type Ia Supernovae from the Nearby Supernova Factory indicated by Local Hα
• Photometric Supernova Classification With Machine Learning
• Type Ia Supernova Rate Measurements to Redshift 2.5 from CANDELS : Searching for Prompt Explosions in the Early Universe
• Supernova Simulations and Strategies For the Dark Energy Survey
• The Difference Imaging Pipeline for the Transient Search in the Dark Energy Survey
• Results from the Supernova Photometric Classification Challenge
• Photometric SN Ia Candidates from the Three-Year SDSS-II SN Survey Data
• 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
• Deep Recurrent Neural Networks for Supernovae Classification
• UNITY: Confronting Supernova Cosmology's Statistical and Systematic Uncertainties in a Unified Bayesian Framework
• Bayesian Estimation Applied to Multiple Species: Towards cosmology with a million supernovae
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• How to Find More Supernovae with Less Work: Object Classification Techniques for Difference Imaging
• Kernel PCA for type Ia supernovae photometric classification
• Improving Cosmological Distance Measurements Using Twin Type Ia Supernovae
• SNEMO: Improved Empirical Models for Type Ia Supernovae
• A simple and robust method for automated photometric classification of supernovae using neural networks
• Bayesian Single-Epoch Photometric Classification of Supernovae
• Measuring the Properties of Dark Energy with Photometrically Classified Pan-STARRS Supernovae. I. Systematic Uncertainty from Core-Collapse Supernova Contamination
• Photometric Supernova Cosmology with BEAMS and SDSS-II
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Semi-supervised Learning for Photometric Supernova Classification
• Standardizing Type Ia Supernova Absolute Magnitudes Using Gaussian Process Data Regression
• STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• The Type Ia supernovae rate with Subaru/XMM-Newton Deep Survey

Cited by in corpus (68)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• The Young Supernova Experiment: Survey Goals, Overview, and Operations
• A light in the dark: searching for electromagnetic counterparts to black hole-black hole mergers in LIGO/Virgo O3 with the Zwicky Transient Facility
• SuperRAENN: A Semi-supervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium Deep Survey Supernovae
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• The Dark Energy Survey Supernova Program: Modelling selection efficiency and observed core collapse supernova contamination
• ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning
• FLEET: A Redshift-Agnostic Machine Learning Pipeline to Rapidly Identify Hydrogen-Poor Superluminous Supernovae
• Machine Learning for Observational Cosmology
• SICRET: Supernova Ia Cosmology with truncated marginal neural Ratio EsTimation
• Identifying Tidal Disruption Events with an Expansion of the FLEET Machine Learning Algorithm
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• A Fast, 2D Gaussian Process Method Based on Celerite: Applications to Transiting Exoplanet Discovery and Characterization
• Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• Real-Time Value-Driven Data Augmentation in the Era of LSST
• LSST Cadence Strategy Evaluations for AGN Time-series Data in Wide-Fast-Deep Field
• ATAT: Astronomical Transformer for time series And Tabular data
• Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys
• Classification of Multiwavelength Transients with Machine Learning
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• Sample of hydrogen-rich superluminous supernovae from the Zwicky Transient Facility
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• Classifying Astronomical Transients Using Only Host Galaxy Photometry
• Photometric classification of HSC transients using machine learning
• Transient Classifiers for Fink: Benchmarks for LSST
• Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae
• Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way
• Understanding of the properties of neural network approaches for transient light curve approximations
• SNAD Transient Miner: Finding Missed Transient Events in ZTF DR4 using k-D trees
• Impact of Rubin Observatory cadence choices on supernovae photometric classification
• SIDE-real: Supernova Ia Dust Extinction with truncated marginal neural ratio estimation applied to real data
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• What can Gaussian Processes really tell us about supernova lightcurves? Consequences for Type II(b) morphologies and genealogies
• Photometric Data-driven Classification of Type Ia Supernovae in the Open Supernova Catalog
• SNGuess: A method for the selection of young extragalactic transients
• ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
• ZTF SN Ia DR2: The secondary maximum in Type Ia supernovae
• How do wavelength correlations affect transmission spectra? Application of a new fast and flexible 2D Gaussian process framework to transiting exoplanet spectroscopy
• Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST
• Stratified Learning: A General-Purpose Statistical Method for Improved Learning under Covariate Shift
• GausSN: Bayesian Time-Delay Estimation for Strongly Lensed Supernovae
• Supernova Light Curves Approximation based on Neural Network Models
• Testing and Combining Transient Spectral Classification Tools on 4MOST-like Blended Spectra
• eROSITA-RU Tidal Disruption Events with Keck-I/LRIS: Sample Selection, Optical Properties, and Host Galaxy Demographics
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
• Real-time Light Curve Classification Framework for the Wide Field Survey Telescope Using Modified Semi-supervised Variational Auto-Encoder
• A Photometric Classifier for Tidal Disruption Events in Rubin LSST
• Supernova host galaxy association and photometric classification of over 10,000 light curves from the Zwicky Transient Facility
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory
• State Space Modelling for detecting and characterising Gravitational Waves afterglows
• STAR NRE: Solving supernova selection effects with set-based truncated auto-regressive neural ratio estimation
• ABC-SN: Attention Based Classifier for Supernova Spectra
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift
• Multivariate time series transformer embeddings for light curves of periodic variable stars
• SCONE: Supernova Classification with a Convolutional Neural Network
• LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network
• PIE-ADA: Physics-Informed Ensemble with Adaptive Data Augmentation for Photometric Transient Classification
• Progenitor and Close-In Circumstellar Medium of Type II Supernova 2020fqv from High-Cadence Photometry and Ultra-Rapid UV Spectroscopy