Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream

Abstract

The unprecedented volume and rate of transient events that will be discovered by the Large Synoptic Survey Telescope (LSST) demands that the astronomical community update its followup paradigm. Alert-brokers -- automated software system to sift through, characterize, annotate and prioritize events for followup -- will be critical tools for managing alert streams in the LSST era. The Arizona-NOAO Temporal Analysis and Response to Events System (ANTARES) is one such broker. In this work, we develop a machine learning pipeline to characterize and classify variable and transient sources only using the available multiband optical photometry. We describe three illustrative stages of the pipeline, serving the three goals of early, intermediate and retrospective classification of alerts. The first takes the form of variable vs transient categorization, the second, a multi-class typing of the combined variable and transient dataset, and the third, a purity-driven subtyping of a transient class. While several similar algorithms have proven themselves in simulations, we validate their performance on real observations for the first time. We quantitatively evaluate our pipeline on sparse, unevenly sampled, heteroskedastic data from various existing observational campaigns, and demonstrate very competitive classification performance. We describe our progress towards adapting the pipeline developed in this work into a real-time broker working on live alert streams from time-domain surveys.

arXiv comment33 pages, 14 figures, submitted to ApJS

References in corpus (55)

• The Gaia mission
• Multi-messenger Observations of a Binary Neutron Star Merger
• Swope Supernova Survey 2017a (SSS17a), the Optical Counterpart to a Gravitational Wave Source
• The Palomar Transient Factory: System Overview, Performance and First Results
• The Dark Energy Survey: more than dark energy - an overview
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Exploring the Optical Transient Sky with the Palomar Transient Factory
• The Supernova Legacy Survey 3-year sample: Type Ia Supernovae photometric distances and cosmological constraints
• SNLS3: Constraints on Dark Energy Combining the Supernova Legacy Survey Three Year Data with Other Probes
• An Open Catalog for Supernova Data
• Assessing statistical significance of periodogram peaks
• The Carnegie Supernova Project: Analysis of the First Sample of Low-Redshift Type-Ia Supernovae
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• The Carnegie Supernova Project: Second Photometry Data Release of Low-Redshift Type Ia Supernovae
• Periodograms for Multiband Astronomical Time Series
• Flash Spectroscopy: Emission Lines from the Ionized Circumstellar Material around $<10$-Day-Old Type II Supernovae
• CfA4: Light Curves for 94 Type Ia Supernovae
• Ultraviolet Light Curves of Supernovae with Swift Uvot
• The Sloan Digital Sky Survey-II: Photometry and Supernova Ia Light Curves from the 2005 data
• Automated supervised classification of variable stars I. Methodology
• Photometric Supernova Classification With Machine Learning
• Random forest automated supervised classification of Hipparcos periodic variable stars
• Results from the Supernova Photometric Classification Challenge
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• Automated Transient Identification in the Dark Energy Survey
• Energetic eruptions leading to a peculiar hydrogen-rich explosion of a massive star
• The Palomar Transient Factory photometric calibration
• Supercal: Cross-Calibration of Multiple Photometric Systems to Improve Cosmological Measurements with Type Ia Supernovae
• Finding strong lenses in CFHTLS using convolutional neural networks
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Improved Photometric Calibration of the SNLS and the SDSS Supernova Surveys
• A comparison of period finding algorithms
• The IPAC Image Subtraction and Discovery Pipeline for the intermediate Palomar Transient Factory
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• CfAIR2: Near Infrared Light Curves of 94 Type Ia Supernovae
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• Using conditional entropy to identify periodicity
• Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
• A simple and robust method for automated photometric classification of supernovae using neural networks
• Bayesian Single-Epoch Photometric Classification of Supernovae
• Automated classification of variable stars for ASAS 1-2 data
• Measuring the Properties of Dark Energy with Photometrically Classified Pan-STARRS Supernovae. I. Systematic Uncertainty from Core-Collapse Supernova Contamination
• Machine Learning Classification of SDSS Transient Survey Images
• Automated Classification of Periodic Variable Stars detected by the Wide-field Infrared Survey Explorer
• Automated supervised classification of variable stars II. Application to the OGLE database
• Classifying Supernovae Using Only Galaxy Data
• SIDRA: a blind algorithm for signal detection in photometric surveys
• Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey
• The Variable Sky of Deep Synoptic Surveys
• A Hybrid Algorithm for Period Analysis from Multi-band Data with Sparse and Irregular Sampling for Arbitrary Light Curve Shapes
• Light Curves of 213 Type Ia Supernovae from the ESSENCE Survey
• ANTARES: A Prototype Transient Broker System
• ANTARES: Progress towards building a `Broker' of time-domain alerts
• Nonparametric Transient Classification using Adaptive Wavelets

Cited by in corpus (71)

• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Zwicky Transient Facility: Data Processing, Products, and Archive
• The Zwicky Transient Facility: Science Objectives
• Design and operation of the ATLAS Transient Science Server
• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• RAPID: Early Classification of Explosive Transients using Deep Learning
• The Zwicky Transient Facility Alert Distribution System
• Machine Learning for the Zwicky Transient Facility
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Fink, a new generation of broker for the LSST community
• The Young Supernova Experiment: Survey Goals, Overview, and Operations
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• What can Machine Learning tell us about the background expansion of the Universe?
• Applications and Techniques for Fast Machine Learning in Science
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• The ANTARES Astronomical Time-Domain Event Broker
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• Anomaly detection in the Zwicky Transient Facility DR3
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Strong gravitational lensing and microlensing of supernovae
• Deep Learning for Image Sequence Classification of Astronomical Events
• GHOST: Using Only Host Galaxy Information to Accurately Associate and Distinguish Supernovae
• Imbalance Learning for Variable Star Classification
• Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
• Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
• First Data Release of the All-sky NOAO Source Catalog
• Fink: early supernovae Ia classification using active learning
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• A Machine Learning Classifier for Microlensing in Wide-Field Surveys
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Inferencing Progenitor and Explosion Properties of Evolving Core-collapse Supernovae from Zwicky Transient Facility Light Curves
• Persistent and occasional: searching for the variable population of the ZTF/4MOST sky using ZTF data release 11
• Real-Time Value-Driven Data Augmentation in the Era of LSST
• Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks
• ATAT: Astronomical Transformer for time series And Tabular data
• Reliable Identification of Binary Supermassive Black Holes from Rubin Observatory Time-Domain Monitoring
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• Linking Extragalactic Transients and their Host Galaxy Properties: Transient Sample, Multi-Wavelength Host Identification, and Database Construction
• NEOExchange -- An online portal for NEO and Solar System science
• 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 classification algorithm for time-domain novelties in preparation for LSST alerts: Application to variable stars and transients detected with DECam in the Galactic Bulge
• Classification of Multiwavelength Transients with Machine Learning
• Identification of Stellar Flares Using Differential Evolution Template Optimization
• Enabling the discovery of fast transients: A kilonova science module for the Fink broker
• Photometric classification of HSC transients using machine learning
• DELIGHT: Deep Learning Identification of Galaxy Hosts of Transients using Multi-resolution Images
• ROME/REA: A gravitational microlensing search for exo-planets beyond the snow-line on a global network of robotic telescopes
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• Photometric Data-driven Classification of Type Ia Supernovae in the Open Supernova Catalog
• Results from the Pan-STARRS Search for Kilonovae: Contamination by Massive Stellar Outbursts
• A search for gravitationally lensed supernovae within the Zwicky Transient Facility public survey
• Data challenges as a tool for time-domain astronomy
• Spectral variability studies in Active Galactic Nuclei: Exploring continuum and emission line regions in the age of LSST and JWST
• Searching for Quasi-Periodic Eruptions using Machine Learning
• Development of the Arizona Robotic Telescope Network
• Multi-scale stamps for real-time classification of alert streams
• Informative Bayesian model selection for RR Lyrae star classifiers
• El-CID: A filter for Gravitational-wave Electromagnetic Counterpart Identification
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory
• Contaminating Electromagnetic Transients in LISA Gravitational Wave Localization Volumes. I: The Intrinsic Rates
• Informative regularization for a multi-layer perceptron RR Lyrae classifier under data shift
• Searching for outliers in the Chandra Source Catalog
• PIE-ADA: Physics-Informed Ensemble with Adaptive Data Augmentation for Photometric Transient Classification
• Exploring Late Stellar Evolution in the Era of Large Surveys: Machine Learning Prospects for Hot Subdwarfs and White Dwarfs
• Finding Fast Transients in Real Time Using Novel Light Curve Analysis Algorithm