Alert Classification for the ALeRCE Broker System: The Light Curve Classifier

Abstract

We present the first version of the ALeRCE (Automatic Learning for the Rapid Classification of Events) broker light curve classifier. ALeRCE is currently processing the Zwicky Transient Facility (ZTF) alert stream, in preparation for the Vera C. Rubin Observatory. The ALeRCE light curve classifier uses variability features computed from the ZTF alert stream, and colors obtained from AllWISE and ZTF photometry. We apply a Balanced Random Forest algorithm with a two-level scheme, where the top level classifies each source as periodic, stochastic, or transient, and the bottom level further resolves each of these hierarchical classes, amongst 15 total classes. This classifier corresponds to the first attempt to classify multiple classes of stochastic variables (including core- and host-dominated active galactic nuclei, blazars, young stellar objects, and cataclysmic variables) in addition to different classes of periodic and transient sources, using real data. We created a labeled set using various public catalogs (such as the Catalina Surveys and {\em Gaia} DR2 variable stars catalogs, and the Million Quasars catalog), and we classify all objects with $\ge 6$ $g$-band or $\ge 6$ $r$-band detections in ZTF (868,371 sources as of 2020/06/09), providing updated classifications for sources with new alerts every day. For the top level we obtain macro-averaged precision and recall scores of 0.96 and 0.99, respectively, and for the bottom level we obtain macro-averaged precision and recall scores of 0.57 and 0.76, respectively. Updated classifications from the light curve classifier can be found at the \href{http://alerce.online}{ALeRCE Explorer website}.

arXiv comment39 pages, 24 figures, 5 tables, 4 apendices. Accepted for publication in the Astronomical Journal (AJ)

References in corpus (82)

• XGBoost: A Scalable Tree Boosting System
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Astropy: A Community Python Package for Astronomy
• The NumPy array: a structure for efficient numerical computation
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• The Dust Content and Opacity of Actively Star-Forming Galaxies
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The SIMBAD astronomical database
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• First Results from the Catalina Real-time Transient Survey
• Understanding the Lomb-Scargle Periodogram
• The Zwicky Transient Facility: Data Processing, Products, and Archive
• Electromagnetic Counterparts of Compact Object Mergers Powered by the Radioactive Decay of R-process Nuclei
• A box-fitting algorithm in the search for periodic transits
• Preliminary Results from NEOWISE: An Enhancement to the Wide-field Infrared Survey Explorer for Solar System Science
• Are the Variations in Quasar Optical Flux Driven by Thermal Fluctuations?
• Modeling the Time Variability of SDSS Stripe 82 Quasars as a Damped Random Walk
• Catalogue of cataclysmic binaries, low-mass X-ray binaries and related objects (Seventh edition)
• Active Galactic Nuclei: what's in a name?
• The Catalina Surveys Periodic Variable Star Catalog
• The ASAS-SN Catalog of Variable Stars I: The Serendipitous Survey
• An Open Catalog for Supernova Data
• Efficient Photometric Selection of Quasars from the Sloan Digital Sky Survey: II. ~1,000,000 Quasars from Data Release Six
• The 5th edition of the Roma-BZCAT. A short presentation
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Spectral properties of quasars from Sloan Digital Sky Survey data release 14: The catalog
• Automated supervised classification of variable stars I. Methodology
• The ASAS-SN Catalog of Variable Stars II: Uniform Classification of 412,000 Known Variables
• The Half Million Quasars (HMQ) Catalogue
• The ASAS-SN Catalog of Variable Stars III: Variables in the Southern TESS Continuous Viewing Zone
• The delay of shock breakout due to circumstellar material seen in most Type II Supernovae
• Selecting Quasars by their Intrinsic Variability
• Optimal Time-Series Selection of Quasars
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Exploring the Variable Sky with LINEAR. III. Classification of Periodic Light Curves
• A recurrent neural network for classification of unevenly sampled variable stars
• A New Catalogue of Type 1 AGN and its Implication on the AGN Unified Model
• Understanding extreme quasar optical variability with CRTS: I. Major AGN flares
• Optical variability of AGN in the PTF/iPTF survey
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• The Extended Baryon Oscillation Spectroscopic Survey: Variability Selection and Quasar Luminosity Function
• Prevalence of X-ray variability in the Chandra Deep Field South
• A Morphological Classification Model to Identify Unresolved PanSTARRS1 Sources: Application in the ZTF Real-Time Pipeline
• A comparison of period finding algorithms
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• Construction of a Calibrated Probabilistic Classification Catalog: Application to 50k Variable Sources in the All-Sky Automated Survey
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• Gaia Data Release 2: The first Gaia catalogue of long-period variable candidates
• The ASAS-SN Catalog of Variable Stars V: Variables in the Southern Hemisphere
• A Package for the Automated Classification of Periodic Variable Stars
• A Mexican Hat with holes: calculating low resolution power spectra from data with gaps
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• The QUEST-La Silla AGN variability survey: connection between AGN variability and black hole physical properties
• Measuring X-ray variability in faint/sparsely-sampled AGN
• The High Cadence Transient Survey (HiTS) - I. Survey design and supernova shock breakout constraints
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• An analysis of feature relevance in the classification of astronomical transients with machine learning methods
• The ASAS-SN Bright Supernova Catalog -- IV. 2017
• Deep multi-survey classification of variable stars
• Near Infrared Variability of obscured and unobscured X-ray selected AGN in the COSMOS field
• Deep Learning for Image Sequence Classification of Astronomical Events
• A machine learned classifier for RR Lyrae in the VVV survey
• Gaia Data Release 2: All-sky classification of high-amplitude pulsating stars
• Automated supervised classification of variable stars II. Application to the OGLE database
• Classifying Supernovae Using Only Galaxy Data
• Imbalance Learning for Variable Star Classification
• Robust period estimation using mutual information for multi-band light curves in the synoptic survey era
• Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
• Optically variable active galactic nuclei in the 3 yr VST survey of the COSMOS field
• The QUEST-La Silla AGN Variability Survey: selection of AGN candidates through optical variability
• A forward modelling approach to AGN variability -- Method description and early applications
• An irregular discrete time series model to identify residuals with autocorrelation in astronomical light curves
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• Period Error Estimation for the Kepler Eclipsing Binary Catalog
• Uncertain classification of Variable Stars: handling observational GAPS and noise
• Star formation and morphological properties of galaxies in the Pan-STARRS $3\pi$ survey- I. A machine learning approach to galaxy and supernova classification
• A Multiband Generalization of the Analysis of Variance Period Estimation Algorithm and the Effect of Inter-band Observing Cadence on Period Recovery Rate
• Streaming Classification of Variable Stars
• GRAPE: Genetic Routine for Astronomical Period Estimation
• A "Crib Sheet" for Supernova Events

Cited by in corpus (74)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• 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
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• Confirming new changing--look AGNs discovered through optical variability using a random-forest based light curve classifier
• SN 2020jfo: A short plateau Type II supernova from a low mass progenitor
• ASTROMER: A transformer-based embedding for the representation of light curves
• Velocity-resolved Reverberation Mapping of Changing-look Active Galactic Nucleus NGC~4151 During Outburst Stage: Evidence for Kinematics Evolution of Broad-line Region
• Machine Learning for Observational Cosmology
• The ZTF Source Classification Project: I. Methods and Infrastructure
• Identifying Tidal Disruption Events with an Expansion of the FLEET Machine Learning Algorithm
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Improving the selection of changing-look AGNs through multi-wavelength photometric variability
• Inferencing Progenitor and Explosion Properties of Evolving Core-collapse Supernovae from Zwicky Transient Facility Light Curves
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• The Type 1 and Type 2 AGN dichotomy according to their ZTF optical variability
• Persistent and occasional: searching for the variable population of the ZTF/4MOST sky using ZTF data release 11
• SDSS1335+0728: The awakening of a $\sim 10^6{M}_{\odot }$ black hole
• ATAT: Astronomical Transformer for time series And Tabular data
• Velocity-resolved Reverberation Mapping of Changing-look Active Galactic Nucleus NGC 4151 during Outburst Stage. II. Four Season Observation Results
• Detection of periodic signals in AGN red noise light curves: empirical tests on the Auto-Correlation Function and Phase Dispersion Minimization
• Identification of 3 cataclysmic variables detected by the ART-XC and eROSITA telescopes aboard SRG during the all-sky X-ray survey
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• Continuum optical-UV and X-ray variability of AGN: current results and future challenges
• Inferring CSM Properties of Type II SNe Using a Magnitude-Limited ZTF Sample
• Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
• Post maximum light and late time optical imaging polarimetry of type I superluminous supernova 2020znr
• Novel bivariate autoregressive model for predicting and forecasting irregularly observed time series
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Understanding of the properties of neural network approaches for transient light curve approximations
• Multiwavelength monitoring of the nucleus in PBC J2333.9-2343: the giant radio galaxy with a blazar-like core
• Selection of optically variable active galactic nuclei via a random forest algorithm
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• Machine Learning based search for Cataclysmic Variables within Gaia Science Alerts
• Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves
• 60 Microlensing Events from the Three Years of Zwicky Transient Facility Phase One
• Early Light Curve Excess in Type IIb Supernovae Observed by the ATLAS Survey: Qualitative Constraints on Progenitor Systems
• Selection of powerful radio galaxies with machine learning
• Three Cases of Optical Periodic Modulation in Active Galactic Nuclei
• SNGuess: A method for the selection of young extragalactic transients
• A Newborn AGN in a Starforming Galaxy
• ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
• The Success of Optical Variability in Uncovering AGNs in Low-stellar Mass Galaxies
• A search for gravitationally lensed supernovae within the Zwicky Transient Facility public survey
• AT2021acak: a candidate tidal disruption event found in the Zwicky Transient Facility survey
• A Systematic Search for Active Galactic Nucleus Flares in ZTF Data Release 23
• Early Identification of Optical Tidal Disruption Events: A science module for the Fink broker
• Light Curve Classification with DistClassiPy: a new distance-based classifier
• Multi-scale stamps for real-time classification of alert streams
• A statistical study of lopsided galaxies using random forest
• Scalable and Robust Multiband Modeling of AGN Light Curves in Rubin-LSST
• FALCO: a Foundation model of Astronomical Light Curves for time dOmain astronomy
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• Kilonova-Targeting Lightcurve Classification for Wide Field Survey Telescope
• A Broker Integrated Algorithm for Gravitational Wave - Electromagnetic Counterpart Searches in O4a and O4b Runs
• A New Period Determination Method for Periodic Variable Stars
• Real-time Light Curve Classification Framework for the Wide Field Survey Telescope Using Modified Semi-supervised Variational Auto-Encoder
• Improving Astronomical Time-series Classification via Data Augmentation with Generative Adversarial Networks
• Multiband analysis of the O'Connell effect in 14 eclipsing binaries
• Unlocking AGN Variability with Custom ZTF Photometry for High-Fidelity Light Curves and Robust Selection
• High-cadence stellar variability studies of RR Lyrae stars with DECam: New multi-band templates
• Supernova host galaxy association and photometric classification of over 10,000 light curves from the Zwicky Transient Facility
• AMPEL workflows for LSST: Modular and reproducible real-time photometric classification
• Navigating AGN variability with self-organizing maps
• Multivariate time series transformer embeddings for light curves of periodic variable stars
• AT 2021hdr: A candidate tidal disruption of a gas cloud by a binary super massive black hole system
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• Anomaly Detection for Multivariate Time Series of Exotic Supernovae
• Seeing through the dust: Unraveling near-infrared variability in type 2 active galactic nuclei
• Electron-capture Supernova Candidates from Light Curves: Implications for Their Progenitors and Explosion Properties
• Astrophotometric search for massive stars in the Milky way. Confronting Random Forest predictions with available spectroscopy
• Semi-Supervised Learning for Lensed Quasar Detection
• The Solar System Notification Alert Processing System (SNAPS): Asteroid Population Outlier Detection