ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning

Abstract

We present a novel method to produce empirical generative models of all kinds of astronomical transients from datasets of unlabeled light curves. Our hybrid model, that we call ParSNIP, uses a neural network to model the unknown intrinsic diversity of different transients and an explicit physics-based model of how light from the transient propagates through the universe and is observed. The ParSNIP model predicts the time-varying spectra of transients despite only being trained on photometric observations. With a three-dimensional intrinsic model, we are able to fit out-of-sample multiband light curves of many different kinds of transients with model uncertainties of 0.04-0.06 mag. The representation learned by the ParSNIP model is invariant to redshift, so it can be used to perform photometric classification of transients even with heavily biased training sets. Our classification techniques significantly outperform state-of-the-art methods on both simulated (PLAsTiCC) and real (PS1) datasets with 2.3$\times$ and 2$\times$ less contamination respectively for classification of Type~Ia supernovae. We demonstrate how our model can identify previously-unobserved kinds of transients and produce a sample that is 90% pure. The ParSNIP model can also estimate distances to Type Ia supernovae in the PS1 dataset with an RMS of 0.150 $\pm$ 0.007 mag compared to 0.155 $\pm$ 0.008 mag for the SALT2 model on the same sample. We discuss how our model could be used to produce distance estimates for supernova cosmology without the need for explicit classification.

arXiv comment27 pages, 17 figures, accepted for publication in AJ

References in corpus (50)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• emcee: The MCMC Hammer
• Measuring Reddening with SDSS Stellar Spectra and Recalibrating SFD
• 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 Complete Light-curve Sample of Spectroscopically Confirmed Type Ia Supernovae from Pan-STARRS1 and Cosmological Constraints from The Combined Pantheon Sample
• Improved cosmological constraints from a joint analysis of the SDSS-II and SNLS supernova samples
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• LSST Science Book, Version 2.0
• SALT2: using distant supernovae to improve the use of Type Ia supernovae as distance indicators
• The Pan-STARRS1 Surveys
• An Analysis of the Shapes of Interstellar Extinction Curves. V. The IR-Through-UV Curve Morphology
• An Open Catalog for Supernova Data
• PESSTO : survey description and products from the first data release by the Public ESO Spectroscopic Survey of Transient Objects
• Recent Advances in Autoencoder-Based Representation Learning
• MOSFiT: Modular Open-Source Fitter for Transients
• Photometric Supernova Classification With Machine Learning
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Measuring Dark Energy Properties with Photometrically Classified Pan-STARRS Supernovae. II. Cosmological Parameters
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
• The Core-collapse rate from the Supernova Legacy Survey
• A recurrent neural network for classification of unevenly sampled variable stars
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• The Berkeley Sample of Stripped-Envelope Supernovae
• SuperRAENN: A Semi-supervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium Deep Survey Supernovae
• A Hierarchical Bayesian SED Model for Type Ia Supernovae in the Optical to Near-Infrared
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• SNEMO: Improved Empirical Models for Type Ia Supernovae
• Superluminous Supernovae in LSST: Rates, Detection Metrics, and Light Curve Modeling
• SUGAR: An improved empirical model of Type Ia Supernovae based on spectral features
• Photometric Supernova Cosmology with BEAMS and SDSS-II
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Active Anomaly Detection for time-domain discoveries
• Anomaly Detection in the Open Supernova Catalog
• 4MOST Consortium Survey 10: The Time-Domain Extragalactic Survey (TiDES)
• The Twins Embedding of Type Ia Supernovae II: Improving Cosmological Distance Estimates
• Cosmology with Superluminous Supernovae
• Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• A method for finding anomalous astronomical light curves and their analogs
• Dalek -- a deep-learning emulator for TARDIS
• The Twins Embedding of Type Ia Supernovae I: The Diversity of Spectra at Maximum Light
• Peculiar velocity cosmology with type Ia supernovae
• Unsupervised Transient Light Curve Analysis Via Hierarchical Bayesian Inference
• Learning Spectral Templates for Photometric Redshift Estimation from Broadband Photometry
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory

Cited by in corpus (7)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• Carnegie Supernova Project-II: Near-infrared spectral diversity and template of Type Ia Supernovae
• Impact of Rubin Observatory cadence choices on supernovae photometric classification
• Deep Learning Unresolved Lensed Lightcurves
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program