Photometric Classification of Early-time Supernova Light Curves with SCONE
Abstract
Abstract In this work, we present classification results on early supernova light curves from SCONE, a photometric classifier that uses convolutional neural networks to categorize supernovae (SNe) by type using light-curve data. SCONE is able to identify SN types from light curves at any stage, from the night of initial alert to the end of their lifetimes. Simulated LSST SNe light curves were truncated at 0, 5, 15, 25, and 50 days after the trigger date and used to train Gaussian processes in wavelength and time space to produce wavelength–time heatmaps. SCONE uses these heatmaps to perform six-way classification between SN types Ia, II, Ibc, Ia-91bg, Iax, and SLSN-I. SCONE is able to perform classification with or without redshift, but we show that incorporating redshift information improves performance at each epoch. SCONE achieved 75% overall accuracy at the date of trigger (60% without redshift), and 89% accuracy 50 days after trigger (82% without redshift). SCONE was also tested on bright subsets of SNe ( r < 20 mag) and produced 91% accuracy at the date of trigger (83% without redshift) and 95% five days after trigger (94.7% without redshift). SCONE is the first application of convolutional neural networks to themore »
- Authors:
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
- Sponsoring Org.:
- USDOE Office of Science (SC); National Aeronautics and Space Administration (NASA); National Science Foundation (NSF)
- OSTI Identifier:
- 1840079
- Alternate Identifier(s):
- OSTI ID: 1983151
- Grant/Contract Number:
- AC02-05CH11231; FOA-0002424; NNH15ZDA001N; AST-2108094
- Resource Type:
- Published Article
- Journal Name:
- The Astronomical Journal
- Additional Journal Information:
- Journal Name: The Astronomical Journal Journal Volume: 163 Journal Issue: 2; Journal ID: ISSN 0004-6256
- Publisher:
- American Astronomical Society
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; Photometry; Light curves; Supernovae; Classification; Gaussian process regression; Neural networks
Citation Formats
Qu, Helen, and Sako, Masao. Photometric Classification of Early-time Supernova Light Curves with SCONE. United States: N. p., 2022.
Web. doi:10.3847/1538-3881/ac39a1.
Qu, Helen, & Sako, Masao. Photometric Classification of Early-time Supernova Light Curves with SCONE. United States. https://doi.org/10.3847/1538-3881/ac39a1
Qu, Helen, and Sako, Masao. Tue .
"Photometric Classification of Early-time Supernova Light Curves with SCONE". United States. https://doi.org/10.3847/1538-3881/ac39a1.
@article{osti_1840079,
title = {Photometric Classification of Early-time Supernova Light Curves with SCONE},
author = {Qu, Helen and Sako, Masao},
abstractNote = {Abstract In this work, we present classification results on early supernova light curves from SCONE, a photometric classifier that uses convolutional neural networks to categorize supernovae (SNe) by type using light-curve data. SCONE is able to identify SN types from light curves at any stage, from the night of initial alert to the end of their lifetimes. Simulated LSST SNe light curves were truncated at 0, 5, 15, 25, and 50 days after the trigger date and used to train Gaussian processes in wavelength and time space to produce wavelength–time heatmaps. SCONE uses these heatmaps to perform six-way classification between SN types Ia, II, Ibc, Ia-91bg, Iax, and SLSN-I. SCONE is able to perform classification with or without redshift, but we show that incorporating redshift information improves performance at each epoch. SCONE achieved 75% overall accuracy at the date of trigger (60% without redshift), and 89% accuracy 50 days after trigger (82% without redshift). SCONE was also tested on bright subsets of SNe ( r < 20 mag) and produced 91% accuracy at the date of trigger (83% without redshift) and 95% five days after trigger (94.7% without redshift). SCONE is the first application of convolutional neural networks to the early-time photometric transient classification problem. All of the data processing and model code developed for this paper can be found in the SCONE software package 1 1 github.com/helenqu/scone located at github.com/helenqu/scone (Qu 2021).},
doi = {10.3847/1538-3881/ac39a1},
journal = {The Astronomical Journal},
number = 2,
volume = 163,
place = {United States},
year = {Tue Jan 11 00:00:00 EST 2022},
month = {Tue Jan 11 00:00:00 EST 2022}
}
https://doi.org/10.3847/1538-3881/ac39a1
Works referenced in this record:
Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
journal, February 2021
- Sánchez-Sáez, P.; Reyes, I.; Valenzuela, C.
- The Astronomical Journal, Vol. 161, Issue 3
Rapidly evolving transients in the Dark Energy Survey
journal, August 2018
- Pursiainen, M.; Childress, M.; Smith, M.
- Monthly Notices of the Royal Astronomical Society, Vol. 481, Issue 1
Photometric Selection of High-Redshift Type Ia Supernova Candidates
journal, February 2006
- Sullivan, M.; Howell, D. A.; Perrett, K.
- The Astronomical Journal, Vol. 131, Issue 2
Multilayer feedforward networks are universal approximators
journal, January 1989
- Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert
- Neural Networks, Vol. 2, Issue 5
PHOTOMETRIC TYPE Ia SUPERNOVA CANDIDATES FROM THE THREE-YEAR SDSS-II SN SURVEY DATA
journal, August 2011
- Sako, Masao; Bassett, Bruce; Connolly, Brian
- The Astrophysical Journal, Vol. 738, Issue 2
The Sloan Digital sky Survey-Ii Supernova Survey: Search Algorithm and Follow-Up Observations
journal, December 2007
- Sako, Masao; Bassett, Bruce; Becker, Andrew
- The Astronomical Journal, Vol. 135, Issue 1
Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
journal, November 2021
- Carrasco-Davis, R.; Reyes, E.; Valenzuela, C.
- The Astronomical Journal, Vol. 162, Issue 6
Extending Supernova Spectral Templates for Next-generation Space Telescope Observations
journal, October 2018
- Pierel, J. D. R.; Rodney, S.; Avelino, A.
- Publications of the Astronomical Society of the Pacific, Vol. 130, Issue 993
SN2017jgh: a high-cadence complete shock cooling light curve of a SN IIb with the Kepler telescope
journal, August 2021
- Armstrong, P.; Tucker, B. E.; Rest, A.
- Monthly Notices of the Royal Astronomical Society, Vol. 507, Issue 3
Optical Spectra of 73 Stripped-Envelope Core-Collapse Supernovae
journal, March 2014
- Modjaz, M.; Blondin, S.; Kirshner, R. P.
- The Astronomical Journal, Vol. 147, Issue 5
First cosmology results using type Ia supernovae from the Dark Energy Survey: the effect of host galaxy properties on supernova luminosity
journal, April 2020
- Smith, M.; Sullivan, M.; Wiseman, P.
- Monthly Notices of the Royal Astronomical Society, Vol. 494, Issue 3
The Supernova Legacy Survey 3-year sample: Type Ia supernovae photometric distances and cosmological constraints
journal, November 2010
- Guy, J.; Sullivan, M.; Conley, A.
- Astronomy & Astrophysics, Vol. 523
RAPID: Early Classification of Explosive Transients Using Deep Learning
journal, September 2019
- Muthukrishna, Daniel; Narayan, Gautham; Mandel, Kaisey S.
- Publications of the Astronomical Society of the Pacific, Vol. 131, Issue 1005
Supernova Light Curves Powered by Young Magnetars
journal, June 2010
- Kasen, Daniel; Bildsten, Lars
- The Astrophysical Journal, Vol. 717, Issue 1
The Magnetar Model for Type I Superluminous Supernovae. I. Bayesian Analysis of the Full Multicolor Light-curve Sample with MOSFiT
journal, November 2017
- Nicholl, Matt; Guillochon, James; Berger, Edo
- The Astrophysical Journal, Vol. 850, Issue 1
Results from the Supernova Photometric Classification Challenge
journal, December 2010
- Kessler, Richard; Bassett, Bruce; Belov, Pavel
- Publications of the Astronomical Society of the Pacific, Vol. 122, Issue 898
A faint type of supernova from a white dwarf with a helium-rich companion
journal, May 2010
- Perets, H. B.; Gal-Yam, A.; Mazzali, P. A.
- Nature, Vol. 465, Issue 7296
Constraining Dark Energy with Type Ia Supernovae and Large-Scale Structure
journal, July 1999
- Perlmutter, Saul; Turner, Michael S.; White, Martin
- Physical Review Letters, Vol. 83, Issue 4
LSST: From Science Drivers to Reference Design and Anticipated Data Products
journal, March 2019
- Ivezić, Željko; Kahn, Steven M.; Tyson, J. Anthony
- The Astrophysical Journal, Vol. 873, Issue 2
Backpropagation Applied to Handwritten Zip Code Recognition
journal, December 1989
- LeCun, Y.; Boser, B.; Denker, J. S.
- Neural Computation, Vol. 1, Issue 4
PELICAN: deeP architecturE for the LIght Curve ANalysis
journal, June 2019
- Pasquet, Johanna; Pasquet, Jérôme; Chaumont, Marc
- Astronomy & Astrophysics, Vol. 627
Bayesian Single-Epoch Photometric Classification of Supernovae
journal, July 2007
- Poznanski, Dovi; Maoz, Dan; Gal-Yam, Avishay
- The Astronomical Journal, Vol. 134, Issue 3
Deep multi-survey classification of variable stars
journal, November 2018
- Aguirre, C.; Pichara, K.; Becker, I.
- Monthly Notices of the Royal Astronomical Society, Vol. 482, Issue 4
Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
journal, December 2019
- Boone, Kyle
- The Astronomical Journal, Vol. 158, Issue 6
A simple and robust method for automated photometric classification of supernovae using neural networks
journal, December 2012
- Karpenka, N. V.; Feroz, F.; Hobson, M. P.
- Monthly Notices of the Royal Astronomical Society, Vol. 429, Issue 2
Theoretical Models of Optical Transients. I. A Broad Exploration of the Duration–Luminosity Phase Space
journal, November 2017
- Villar, V. Ashley; Berger, Edo; Metzger, Brian D.
- The Astrophysical Journal, Vol. 849, Issue 1
SNANA: A Public Software Package for Supernova Analysis
journal, September 2009
- Kessler, Richard; Bernstein, Joseph P.; Cinabro, David
- Publications of the Astronomical Society of the Pacific, Vol. 121, Issue 883
TESTING MODELS OF INTRINSIC BRIGHTNESS VARIATIONS IN TYPE Ia SUPERNOVAE AND THEIR IMPACT ON MEASURING COSMOLOGICAL PARAMETERS
journal, January 2013
- Kessler, Richard; Guy, Julien; Marriner, John
- The Astrophysical Journal, Vol. 764, Issue 1
SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification
journal, December 2019
- Möller, A.; de Boissière, T.
- Monthly Notices of the Royal Astronomical Society, Vol. 491, Issue 3
A recurrent neural network for classification of unevenly sampled variable stars
journal, November 2017
- Naul, Brett; Bloom, Joshua S.; Pérez, Fernando
- Nature Astronomy, Vol. 2, Issue 2
SuperRAENN: A Semisupervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium-Deep Survey Supernovae
journal, December 2020
- Villar, V. Ashley; Hosseinzadeh, Griffin; Berger, Edo
- The Astrophysical Journal, Vol. 905, Issue 2
The Sloan Digital sky Survey-Ii Supernova Survey: Technical Summary
journal, December 2007
- Frieman, Joshua A.; Bassett, Bruce; Becker, Andrew
- The Astronomical Journal, Vol. 135, Issue 1
Large Magellanic Cloud Cepheid Standards Provide a 1% Foundation for the Determination of the Hubble Constant and Stronger Evidence for Physics beyond ΛCDM
journal, May 2019
- Riess, Adam G.; Casertano, Stefano; Yuan, Wenlong
- The Astrophysical Journal, Vol. 876, Issue 1
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
ParSNIP: Generative Models of Transient Light Curves with Physics-enabled Deep Learning
journal, December 2021
- Boone, Kyle
- The Astronomical Journal, Vol. 162, Issue 6
Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
journal, September 1998
- Riess, Adam G.; Filippenko, Alexei V.; Challis, Peter
- The Astronomical Journal, Vol. 116, Issue 3
The Carnegie-Chicago Hubble Program. VIII. An Independent Determination of the Hubble Constant Based on the Tip of the Red Giant Branch
journal, August 2019
- Freedman, Wendy L.; Madore, Barry F.; Hatt, Dylan
- The Astrophysical Journal, Vol. 882, Issue 1
Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
journal, July 2019
- Kessler, R.; Narayan, G.; Avelino, A.
- Publications of the Astronomical Society of the Pacific, Vol. 131, Issue 1003
Long Short-Term Memory
journal, November 1997
- Hochreiter, Sepp; Schmidhuber, Jürgen
- Neural Computation, Vol. 9, Issue 8
Semi-supervised learning for photometric supernova classification★: Semi-supervised SN classification
journal, October 2011
- Richards, Joseph W.; Homrighausen, Darren; Freeman, Peter E.
- Monthly Notices of the Royal Astronomical Society, Vol. 419, Issue 2
MOSFiT: Modular Open Source Fitter for Transients
journal, May 2018
- Guillochon, James; Nicholl, Matt; Villar, V. Ashley
- The Astrophysical Journal Supplement Series, Vol. 236, Issue 1
SCONE: Supernova Classification with a Convolutional Neural Network
journal, July 2021
- Qu, Helen; Sako, Masao; Möller, Anais
- The Astronomical Journal, Vol. 162, Issue 2
Supernova 1987A in the Large Magellanic Cloud - The explosion of an approximately 20 solar mass star which has experienced mass loss?
journal, July 1987
- Woosley, S. E.; Pinto, P. A.; Martin, P. G.
- The Astrophysical Journal, Vol. 318
Deep Recurrent Neural Networks for Supernovae Classification
journal, March 2017
- Charnock, Tom; Moss, Adam
- The Astrophysical Journal, Vol. 837, Issue 2
The Type II supernova SN 2020jfo in M 61, implications for progenitor system, and explosion dynamics
journal, November 2021
- Sollerman, J.; Yang, S.; Schulze, S.
- Astronomy & Astrophysics, Vol. 655