The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals
Abstract
Classification of transient and variable light curves is an essential step in using astronomical observations to develop an understanding of the underlying physical processes from which they arise. However, upcoming deep photometric surveys, including the Large Synoptic Survey Telescope (LSST), will produce a deluge of low signal-to-noise data for which traditional type estimation procedures are inappropriate. Probabilistic classification is more appropriate for such data but is incompatible with the traditional metrics used on deterministic classifications. Furthermore, large survey collaborations like LSST intend to use the resulting classification probabilities for diverse science objectives, indicating a need for a metric that balances a variety of goals. We describe the process used to develop an optimal performance metric for an open classification challenge that seeks to identify probabilistic classifiers that can serve many scientific interests. The Photometric LSST Astronomical Time-series Classification Challenge (PLASTICC) aims to identify promising techniques for obtaining classification probabilities of transient and variable objects by engaging a broader community beyond astronomy. Using mock classification probability submissions emulating realistically complex archetypes of those anticipated of PLASTICC, we compare the sensitivity of two metrics of classification probabilities under various weighting schemes, finding that both yield results that are qualitatively consistent with intuitivemore »
- Authors:
-
more »
- German Centre of Cosmological Lensing, Ruhr-Universität Bochum, Universitätsstraße 150, Bochum, Germany; New York Univ., New York, NY (United States). Center for Cosmology and Particle Physics; New York Univ., New York, NY (United States). Dept. of Physics
- Univ. of Toronto, Toronto, ON, Canada. Dept. of Astronomy and Astrophysics; Univ. of Toronto, Toronto, ON, Canada. Dunlap Institute for Astronomy and Astrophysics
- University College London, Dorking, United Kingdom. Mullard Space Science Lab, Dept. of Space and Climate Physics
- Univ. of Toronto, Toronto, ON, Canada. Dunlap Institute for Astronomy and Astrophysics
- Stockholm University, AlbaNova, Stockholm, Sweden. The Oskar Klein Centre for Cosmoparticle Physics, Dept. of Physics
- Rutgers, the State University of New Jersey, Piscataway, NJ (United States)
- Univ. of Pittsburgh, Pittsburgh, PA (United States); Departamento de Física Teórica y del Cosmos, Universidad de Granada, Granada, Spain
- Université Clermont Auvergne, CNRS/IN2P3, LPC, F-63000 Clermont-Ferrand, France
- Univ. of California, Santa Cruz, Santa Cruz, CA (United States)
- KICP, Chicago, IL (United States)
- African Institute for Mathematical Sciences, 6 Melrose Road, Muizenberg, 7945, South Africa; South African Radio Astronomy Observatory, The Park, Park Road, Pinelands, Cape Town 7405, South Africa
- California Institute of Technology, Pasadena, CA (United States). Div. of Physics, Mathematics, and Astronomy; California Institute of Technology, Pasadena, CA (United States). Center for Data Driven Discovery
- Institute of Astronomy and Kavli Institute for Cosmology, Madingley Road, Cambridge, United Kingdom; Univ. of Cambridge, Wilberforce Road, Cambridge, United Kingdom. Statistical Laboratory, DPMMS
- Harvard-Smithsonian Center for Astrophysics, Cambridge, MA (United States)
- Institute of Astronomy and Kavli Institute for Cosmology, Madingley Road, Cambridge, United Kingdom
- Space Telescope Science Institute, Baltimore, MD (United States)
- Stockholm University, AlbaNova, Stockholm, Sweden. The Oskar Klein Centre for Cosmoparticle Physics, Dept. of Physics; Department of Physics and Astronomy, University College London, Gower Street, London, United Kingdom
- Univ. of California Berkeley, Berkeley, CA (United States). Berkeley Center for Cosmological Physics
- Publication Date:
- Research Org.:
- Rutgers Univ., Piscataway, NJ (United States); Univ. of California, Oakland, CA (United States); Stanford Univ., CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC); National Science Foundation (NSF); Swedish Research Council (SRC); Ajax Foundation; Marie Sklodowska-Curie; ERC
- Contributing Org.:
- LSST Dark Energy Science Collaboration; LSST Transients and Variable Stars Science Collaboration
- OSTI Identifier:
- 1802229
- Grant/Contract Number:
- SC0011636; AC02-05CH11231; AC02-76SF00515; AST-1517237; Dnr 2016-06012; AST-0909182; AST-1313422; AST-1413600; AST-1518308; 839090; 306478-CosmicDawn
- Resource Type:
- Accepted Manuscript
- Journal Name:
- The Astronomical Journal (Online)
- Additional Journal Information:
- Journal Name: The Astronomical Journal (Online); Journal Volume: 158; Journal Issue: 5; Journal ID: ISSN 1538-3881
- Publisher:
- IOP Publishing
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; astronomy & astrophysics; data analysis; statistical methods; variables; supernovae; surveys; photometric
Citation Formats
Malz, A. I., Hložek, R., Allam, T., Bahmanyar, A., Biswas, R., Dai, M., Galbany, L., Ishida, E. E. O., Jha, S. W., Jones, D. O., Kessler, R., Lochner, M., Mahabal, A. A., Mandel, K. S., Martínez-Galarza, J. R., McEwen, J. D., Muthukrishna, D., Narayan, G., Peiris, H., Peters, C. M., Ponder, K., and Setzer, C. N. The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals. United States: N. p., 2019.
Web. doi:10.3847/1538-3881/ab3a2f.
Malz, A. I., Hložek, R., Allam, T., Bahmanyar, A., Biswas, R., Dai, M., Galbany, L., Ishida, E. E. O., Jha, S. W., Jones, D. O., Kessler, R., Lochner, M., Mahabal, A. A., Mandel, K. S., Martínez-Galarza, J. R., McEwen, J. D., Muthukrishna, D., Narayan, G., Peiris, H., Peters, C. M., Ponder, K., & Setzer, C. N. The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals. United States. https://doi.org/10.3847/1538-3881/ab3a2f
Malz, A. I., Hložek, R., Allam, T., Bahmanyar, A., Biswas, R., Dai, M., Galbany, L., Ishida, E. E. O., Jha, S. W., Jones, D. O., Kessler, R., Lochner, M., Mahabal, A. A., Mandel, K. S., Martínez-Galarza, J. R., McEwen, J. D., Muthukrishna, D., Narayan, G., Peiris, H., Peters, C. M., Ponder, K., and Setzer, C. N. Thu .
"The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals". United States. https://doi.org/10.3847/1538-3881/ab3a2f. https://www.osti.gov/servlets/purl/1802229.
@article{osti_1802229,
title = {The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals},
author = {Malz, A. I. and Hložek, R. and Allam, T. and Bahmanyar, A. and Biswas, R. and Dai, M. and Galbany, L. and Ishida, E. E. O. and Jha, S. W. and Jones, D. O. and Kessler, R. and Lochner, M. and Mahabal, A. A. and Mandel, K. S. and Martínez-Galarza, J. R. and McEwen, J. D. and Muthukrishna, D. and Narayan, G. and Peiris, H. and Peters, C. M. and Ponder, K. and Setzer, C. N.},
abstractNote = {Classification of transient and variable light curves is an essential step in using astronomical observations to develop an understanding of the underlying physical processes from which they arise. However, upcoming deep photometric surveys, including the Large Synoptic Survey Telescope (LSST), will produce a deluge of low signal-to-noise data for which traditional type estimation procedures are inappropriate. Probabilistic classification is more appropriate for such data but is incompatible with the traditional metrics used on deterministic classifications. Furthermore, large survey collaborations like LSST intend to use the resulting classification probabilities for diverse science objectives, indicating a need for a metric that balances a variety of goals. We describe the process used to develop an optimal performance metric for an open classification challenge that seeks to identify probabilistic classifiers that can serve many scientific interests. The Photometric LSST Astronomical Time-series Classification Challenge (PLASTICC) aims to identify promising techniques for obtaining classification probabilities of transient and variable objects by engaging a broader community beyond astronomy. Using mock classification probability submissions emulating realistically complex archetypes of those anticipated of PLASTICC, we compare the sensitivity of two metrics of classification probabilities under various weighting schemes, finding that both yield results that are qualitatively consistent with intuitive notions of classification performance. We thus choose as a metric for PLASTICC a weighted modification of the cross-entropy because it can be meaningfully interpreted in terms of information content. Finally, we propose extensions of our methodology to ever more complex challenge goals and suggest some guiding principles for approaching the choice of a metric of probabilistic data products.},
doi = {10.3847/1538-3881/ab3a2f},
journal = {The Astronomical Journal (Online)},
number = 5,
volume = 158,
place = {United States},
year = {Thu Oct 10 00:00:00 EDT 2019},
month = {Thu Oct 10 00:00:00 EDT 2019}
}
Works referenced in this record:
K2 variable catalogue – II. Machine learning classification of variable stars and eclipsing binaries in K2 fields 0–4
journal, December 2015
- Armstrong, D. J.; Kirk, J.; Lam, K. W. F.
- Monthly Notices of the Royal Astronomical Society, Vol. 456, Issue 2
The Third Gravitational Lensing Accuracy Testing (GREAT3) Challenge Handbook
text, January 2013
- Mandelbaum, Rachel; Rowe, Barnaby; Bosch, James
- arXiv
Separation of pulsar signals from noise using supervised machine learning algorithms
journal, April 2018
- Bethapudi, S.; Desai, S.
- Astronomy and Computing, Vol. 23
Statistical classification techniques for photometric supernova typing: Statistical methods for photometric typing
journal, April 2011
- Newling, J.; Varughese, M.; Bassett, B.
- Monthly Notices of the Royal Astronomical Society, Vol. 414, Issue 3
Detecting Solar-like Oscillations in Red Giants with Deep Learning
journal, May 2018
- Hon, Marc; Stello, Dennis; Zinn, Joel C.
- The Astrophysical Journal, Vol. 859, Issue 1
Kernel PCA for type Ia supernovae photometric classification
text, January 2012
- Ishida, Emille E. O.; de Souza, Rafael S.
- arXiv
Detecting Solar-like Oscillations in Red Giants with Deep Learning
text, January 2018
- Hon, Marc; Stello, Dennis; Zinn, Joel C.
- arXiv
Photometric Supernova Classification With Machine Learning
text, January 2016
- Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.
- arXiv
Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
journal, December 2016
- Möller, A.; Ruhlmann-Kleider, V.; Leloup, C.
- Journal of Cosmology and Astroparticle Physics, Vol. 2016, Issue 12
K ‐Corrections and Extinction Corrections for Type Ia Supernovae
journal, August 2002
- Nugent, Peter; Kim, Alex; Perlmutter, Saul
- Publications of the Astronomical Society of the Pacific, Vol. 114, Issue 798
Observing Dark Worlds: A crowdsourcing experiment for dark matter mapping
journal, July 2014
- Harvey, D.; Kitching, T. D.; Noah-Vanhoucke, J.
- Astronomy and Computing, Vol. 5
Validation of the NOAA Space Weather Prediction Center's solar flare forecasting look-up table and forecaster-issued probabilities: VALIDATION OF SWPC FLARE PROBABILITIES
journal, June 2012
- Crown, Misty D.
- Space Weather, Vol. 10, Issue 6
Observation of a Rapidly Pulsating Radio Source
journal, February 1968
- Hewish, A.; Bell, S. J.; Pilkington, J. D. H.
- Nature, Vol. 217, Issue 5130
Measuring photometric redshifts using galaxy images and Deep Neural Networks
journal, July 2016
- Hoyle, B.
- Astronomy and Computing, Vol. 16
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
UNITY: Confronting Supernova Cosmology's Statistical and Systematic Uncertainties in a Unified Bayesian Framework
text, January 2015
- Rubin, David; Aldering, Greg; Barbary, Kyle
- arXiv
Gravitational Lensing Accuracy Testing 2010 (GREAT10) Challenge Handbook
journal, September 2011
- Kitching, Thomas; Amara, Adam; Gill, Mandeep
- The Annals of Applied Statistics, Vol. 5, Issue 3
zBEAMS: a unified solution for supernova cosmology with redshift uncertainties
journal, October 2017
- Roberts, Ethan; Lochner, Michelle; Fonseca, José
- Journal of Cosmology and Astroparticle Physics, Vol. 2017, Issue 10
A Hybrid Ensemble Learning Approach to Star-Galaxy Classification
text, January 2015
- Kim, Edward J.; Brunner, Robert J.; Kind, Matias Carrasco
- arXiv
Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
text, January 2016
- Zevin, Michael; Coughlin, Scott; Bahaadini, Sara
- arXiv
K-corrections and Extinction Corrections for Type Ia Supernovae
text, January 2002
- Nugent, Peter; Kim, Alex; Perlmutter, Saul
- arXiv
Classification and unsupervised clustering of LIGO data with Deep Transfer Learning
journal, May 2018
- George, Daniel; Shen, Hongyu; Huerta, E. A.
- Physical Review D, Vol. 97, Issue 10
Bayesian High-Redshift Quasar Classification from Optical and Mid-Ir Photometry
journal, August 2015
- Richards, Gordon T.; Myers, Adam D.; Peters, Christina M.
- The Astrophysical Journal Supplement Series, Vol. 219, Issue 2
Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning
text, January 2018
- Florios, Kostas; Kontogiannis, Ioannis; Park, Sung-Hong
- arXiv
Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
text, January 2016
- Möller, A.; Ruhlmann-Kleider, V.; Leloup, C.
- arXiv
Automated probabilistic classification of transients and variables
journal, March 2008
- Mahabal, A.; Djorgovski, S. G.; Turmon, M.
- Astronomische Nachrichten, Vol. 329, Issue 3
Ensemble modeling of CMEs using the WSA-ENLIL+Cone model
text, January 2015
- Mays, M. L.; Taktakishvili, A.; Pulkkinen, A. A.
- arXiv
Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
journal, November 2012
- Bloom, J. S.; Richards, J. W.; Nugent, P. E.
- Publications of the Astronomical Society of the Pacific, Vol. 124, Issue 921
Star–galaxy classification using deep convolutional neural networks
journal, October 2016
- Kim, Edward J.; Brunner, Robert J.
- Monthly Notices of the Royal Astronomical Society, Vol. 464, Issue 4
The Third Gravitational Lensing Accuracy Testing (Great3) Challenge Handbook
journal, April 2014
- Mandelbaum, Rachel; Rowe, Barnaby; Bosch, James
- The Astrophysical Journal Supplement Series, Vol. 212, Issue 1
Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
text, January 2018
- Narayan, Gautham; Zaidi, Tayeb; Soraisam, Monika D.
- arXiv
Detecting Quasars in Large-Scale Astronomical Surveys
conference, December 2010
- Gieseke, Fabian; Polsterer, Kai Lars; Thom, Andreas
- 2010 International Conference on Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on Machine Learning and Applications
Machine-learning selection of optical transients in the Subaru/Hyper Suprime-Cam survey
journal, October 2016
- Morii, Mikio; Ikeda, Shiro; Tominaga, Nozomu
- Publications of the Astronomical Society of Japan, Vol. 68, Issue 6
Rotation-invariant convolutional neural networks for galaxy morphology prediction
journal, April 2015
- Dieleman, Sander; Willett, Kyle W.; Dambre, Joni
- Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2
Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning
journal, January 2018
- Florios, Kostas; Kontogiannis, Ioannis; Park, Sung-Hong
- Solar Physics, Vol. 293, Issue 2
Photometric Supernova Classification with Machine Learning
journal, August 2016
- Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.
- The Astrophysical Journal Supplement Series, Vol. 225, Issue 2
SiFTO: An Empirical Method for Fitting SN Ia Light Curves
journal, July 2008
- Conley, A.; Sullivan, M.; Hsiao, E. Y.
- The Astrophysical Journal, Vol. 681, Issue 1
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
Detection of bars in galaxies using a deep convolutional neural network
journal, March 2018
- Abraham, Sheelu; Aniyan, A. K.; Kembhavi, Ajit K.
- Monthly Notices of the Royal Astronomical Society, Vol. 477, Issue 1
Deep learning classification in asteroseismology
journal, May 2017
- Hon, Marc; Stello, Dennis; Yu, Jie
- Monthly Notices of the Royal Astronomical Society, Vol. 469, Issue 4
Approximating Photo- z PDFs for Large Surveys
journal, June 2018
- Malz, A. I.; Marshall, P. J.; DeRose, J.
- The Astronomical Journal, Vol. 156, Issue 1
K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
text, January 2015
- Armstrong, D. J.; Kirk, J.; Lam, K. W. F.
- arXiv
CONSTRUCTION OF A CALIBRATED PROBABILISTIC CLASSIFICATION CATALOG: APPLICATION TO 50k VARIABLE SOURCES IN THE ALL-SKY AUTOMATED SURVEY
journal, December 2012
- Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.
- The Astrophysical Journal Supplement Series, Vol. 203, Issue 2
Ensemble Modeling of CMEs Using the WSA–ENLIL+Cone Model
journal, May 2015
- Mays, M. L.; Taktakishvili, A.; Pulkkinen, A.
- Solar Physics, Vol. 290, Issue 6
Unity: Confronting Supernova Cosmology’S Statistical and Systematic Uncertainties in a Unified Bayesian Framework
journal, November 2015
- Rubin, D.; Aldering, G.; Barbary, K.
- The Astrophysical Journal, Vol. 813, Issue 2
Kernel PCA for Type Ia supernovae photometric classification
journal, January 2013
- Ishida, E. E. O.; de Souza, R. S.
- Monthly Notices of the Royal Astronomical Society, Vol. 430, Issue 1
Gravity Spy: integrating advanced LIGO detector characterization, machine learning, and citizen science
journal, February 2017
- Zevin, M.; Coughlin, S.; Bahaadini, S.
- Classical and Quantum Gravity, Vol. 34, Issue 6
Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
text, January 2011
- Bloom, J. S.; Richards, J. W.; Nugent, P. E.
- arXiv
Measuring Dark Energy Properties with Photometrically Classified Pan-STARRS Supernovae. II. Cosmological Parameters
journal, April 2018
- Jones, D. O.; Scolnic, D. M.; Riess, A. G.
- The Astrophysical Journal, Vol. 857, Issue 1
Results from the Supernova Photometric Classification Challenge
text, January 2010
- Kessler, Richard; Bassett, Bruce; Belov, Pavel
- arXiv
Matplotlib: A 2D Graphics Environment
journal, January 2007
- Hunter, John D.
- Computing in Science & Engineering, Vol. 9, Issue 3
Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
journal, February 2017
- Cabrera-Vives, Guillermo; Reyes, Ignacio; Förster, Francisco
- The Astrophysical Journal, Vol. 836, Issue 1
Python for Scientific Computing
journal, January 2007
- Oliphant, Travis E.
- Computing in Science & Engineering, Vol. 9, Issue 3
Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey
text, January 2016
- Morii, Mikio; Ikeda, Shiro; Tominaga, Nozomu
- arXiv
The NumPy Array: A Structure for Efficient Numerical Computation
journal, March 2011
- van der Walt, Stéfan; Colbert, S. Chris; Varoquaux, Gaël
- Computing in Science & Engineering, Vol. 13, Issue 2
Deep learning classification in asteroseismology using an improved neural network: results on 15 000 Kepler red giants and applications to K2 and TESS data
journal, February 2018
- Hon, Marc; Stello, Dennis; Yu, Jie
- Monthly Notices of the Royal Astronomical Society, Vol. 476, Issue 3
Machine-learning-based Brokers for Real-time Classification of the LSST Alert Stream
journal, May 2018
- Narayan, Gautham; Zaidi, Tayeb; Soraisam, Monika D.
- The Astrophysical Journal Supplement Series, Vol. 236, Issue 1
Radio Galaxy Zoo: Claran – a deep learning classifier for radio morphologies
journal, October 2018
- Wu, Chen; Wong, Oiwei Ivy; Rudnick, Lawrence
- Monthly Notices of the Royal Astronomical Society, Vol. 482, Issue 1
Measuring photometric redshifts using galaxy images and Deep Neural Networks
preprint, January 2015
- Hoyle, Ben
- arXiv
A hybrid ensemble learning approach to star–galaxy classification
journal, August 2015
- Kim, Edward J.; Brunner, Robert J.; Carrasco Kind, Matias
- Monthly Notices of the Royal Astronomical Society, Vol. 453, Issue 1
Works referencing / citing this record:
Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
text, January 2019
- Boone, Kyle
- arXiv
Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
journal, December 2019
- Boone, Kyle
- The Astronomical Journal, Vol. 158, Issue 6