CaltechAUTHORS
  A Caltech Library Service

Machine Learning for the Zwicky Transient Facility

Mahabal, Ashish and Rebbapragada, U. D. and Walters, Richard and Masci, Frank J. and Blagorodnova, N. and van Roestel, Jan and Biswas, Rahul and Burdge, Kevin B. and Chang, Chan-Kao and Duev, Dmitry A. and Golkhou, V. Zach and Miller, Adam A. and Nordin, Jakob and Ward, Charlotte and Adams, Scott M. and Bellm, Eric C. and Branton, Doug and Bue, Brian D. and Cannella, C. and Connolly, Andrew and Dekany, Richard and Feindt, Ulrich and Hung, Tiara and Fortson, Lucy F. and Frederick, Sara and Fremling, C. and Gezari, Suvi and Graham, Matthew J. and Groom, Steven and Kasliwal, Mansi M. and Kulkarni, S. R. and Kupfer, Thomas and Lin, Hsing Wen and Lintott, Chris J. and Lunnan, R. and Parejko, John and Prince, Thomas A. and Riddle, Reed and Rusholme, B. and Saunders, Nicholas and Sedaghat, Nima and Shupe, David L. and Singer, Leo P. and Soumagnac, Maayane T. and Szkody, Paula and Tachibana, Yutaro and Tirumala, Kushal and van Velzen, Sjoert and Wright, Darryl (2019) Machine Learning for the Zwicky Transient Facility. Publications of the Astronomical Society of the Pacific, 131 (997). Art. No. 038002. ISSN 0004-6280. https://resolver.caltech.edu/CaltechAUTHORS:20190131-104830427

[img] PDF - Published Version
Creative Commons Attribution.

3992Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190131-104830427

Abstract

The Zwicky Transient Facility is a large optical survey in multiple filters producing hundreds of thousands of transient alerts per night. We describe here various machine learning (ML) implementations and plans to make the maximal use of the large data set by taking advantage of the temporal nature of the data, and further combining it with other data sets. We start with the initial steps of separating bogus candidates from real ones, separating stars and galaxies, and go on to the classification of real objects into various classes. Besides the usual methods (e.g., based on features extracted from light curves) we also describe early plans for alternate methods including the use of domain adaptation, and deep learning. In a similar fashion we describe efforts to detect fast moving asteroids. We also describe the use of the Zooniverse platform for helping with classifications through the creation of training samples, and active learning. Finally we mention the synergistic aspects of ZTF and LSST from the ML perspective.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1088/1538-3873/aaf3faDOIArticle
https://arxiv.org/abs/1902.01936arXivDiscussion Paper
ORCID:
AuthorORCID
Mahabal, Ashish0000-0003-2242-0244
Rebbapragada, U. D.0000-0002-2560-3495
Walters, Richard0000-0002-1835-6078
Masci, Frank J.0000-0002-8532-9395
Blagorodnova, N.0000-0003-0901-1606
van Roestel, Jan0000-0002-2626-2872
Burdge, Kevin B.0000-0002-7226-836X
Chang, Chan-Kao0000-0003-1656-4540
Duev, Dmitry A.0000-0001-5060-8733
Golkhou, V. Zach0000-0001-8205-2506
Adams, Scott M.0000-0001-5855-5939
Bellm, Eric C.0000-0001-8018-5348
Bue, Brian D.0000-0002-7856-3570
Cannella, C.0000-0003-2667-7290
Feindt, Ulrich0000-0002-9435-2167
Hung, Tiara0000-0002-9878-7889
Fortson, Lucy F.0000-0002-1067-8558
Frederick, Sara0000-0001-9676-730X
Fremling, C.0000-0002-4223-103X
Gezari, Suvi0000-0003-3703-5154
Graham, Matthew J.0000-0002-3168-0139
Groom, Steven0000-0001-5668-3507
Kasliwal, Mansi M.0000-0002-5619-4938
Kulkarni, S. R.0000-0001-5390-8563
Kupfer, Thomas0000-0002-6540-1484
Lin, Hsing Wen0000-0001-7737-6784
Lintott, Chris J.0000-0001-5578-359X
Lunnan, R.0000-0001-9454-4639
Prince, Thomas A.0000-0002-8850-3627
Riddle, Reed0000-0002-0387-370X
Rusholme, B.0000-0001-7648-4142
Saunders, Nicholas0000-0003-2657-3889
Shupe, David L.0000-0003-4401-0430
Singer, Leo P.0000-0001-9898-5597
Soumagnac, Maayane T.0000-0001-6753-1488
Tachibana, Yutaro0000-0001-6584-6945
van Velzen, Sjoert0000-0002-3859-8074
Additional Information:© 2019. The Astronomical Society of the Pacific. Original content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. Received 2018 September 4; accepted 2018 November 26; published 2019 January 31. Based on observations obtained with the Samuel Oschin Telescope 48-inch and the 60-inch Telescope at the Palomar Observatory as part of the Zwicky Transient Facility project. Major funding has been provided by the U.S. National Science Foundation under Grant No. AST-1440341 and by the ZTF partner institutions: the California Institute of Technology, the Oskar Klein Centre, the Weizmann Institute of Science, the University of Maryland, the University of Washington, Deutsches Elektronen-Synchrotron, the University of Wisconsin-Milwaukee, and the TANGO Program of the University System of Taiwan. Part of this research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration. Facilities: PO:1.2m - , PO:1.5m. -
Group:Infrared Processing and Analysis Center (IPAC), Zwicky Transient Facility
Funders:
Funding AgencyGrant Number
NSFAST-1440341
ZTF partner institutionsUNSPECIFIED
NASA/JPL/CaltechUNSPECIFIED
Issue or Number:997
Record Number:CaltechAUTHORS:20190131-104830427
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190131-104830427
Official Citation:Ashish Mahabal et al 2019 PASP 131 038002
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92541
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:31 Jan 2019 23:11
Last Modified:06 Dec 2019 21:34

Repository Staff Only: item control page