CaltechAUTHORS
  A Caltech Library Service

Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning

Duev, Dmitry A. and Bolin, Bryce T. and Graham, Matthew J. and Kelley, Michael S. P. and Mahabal, Ashish and Bellm, Eric C. and Coughlin, Michael W. and Dekany, Richard and Helou, George and Kulkarni, Shrinivas R. and Masci, Frank J. and Prince, Thomas A. and Riddle, Reed and Soumagnac, Maayane T. and van der Walt, Stéfan J. (2021) Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning. Astronomical Journal, 161 (5). Art. No. 218. ISSN 0004-6256. https://resolver.caltech.edu/CaltechAUTHORS:20210423-164903652

[img] PDF - Published Version
See Usage Policy.

3MB
[img] PDF - Accepted Version
Creative Commons Attribution.

11MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210423-164903652

Abstract

We present Tails, an open-source deep-learning framework for the identification and localization of comets in the image data of the Zwicky Transient Facility (ZTF), a robotic optical time-domain survey currently in operation at the Palomar Observatory in California, USA. Tails employs a custom EfficientDet-based architecture and is capable of finding comets in single images in near real time, rather than requiring multiple epochs as with traditional methods. The system achieves state-of-the-art performance with 99% recall, a 0.01% false-positive rate, and a 1–2 pixel rms error in the predicted position. We report the initial results of the Tails efficiency evaluation in a production setting on the data of the ZTF Twilight survey, including the first AI-assisted discovery of a comet (C/2020 T2) and the recovery of a comet (P/2016 J3 = P/2021 A3).


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.3847/1538-3881/abea7bDOIArticle
https://arxiv.org/abs/2102.13352arXivDiscussion Paper
ORCID:
AuthorORCID
Duev, Dmitry A.0000-0001-5060-8733
Bolin, Bryce T.0000-0002-4950-6323
Graham, Matthew J.0000-0002-3168-0139
Kelley, Michael S. P.0000-0002-6702-7676
Mahabal, Ashish0000-0003-2242-0244
Bellm, Eric C.0000-0001-8018-5348
Coughlin, Michael W.0000-0002-8262-2924
Dekany, Richard0000-0002-5884-7867
Helou, George0000-0003-3367-3415
Kulkarni, Shrinivas R.0000-0001-5390-8563
Masci, Frank J.0000-0002-8532-9395
Prince, Thomas A.0000-0002-8850-3627
Riddle, Reed0000-0002-0387-370X
Soumagnac, Maayane T.0000-0001-6753-1488
van der Walt, Stéfan J.0000-0001-9276-1891
Additional Information:© 2021. The American Astronomical Society. Received 2021 January 11; revised 2021 February 23; accepted 2021 February 25; published 2021 April 8. D.A. Duev would like to thank Ivan Duev for assistance with data labeling. D.A. Duev acknowledges support from Google Cloud and from the Heising-Simons Foundation under grant No. 12540303. 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. ZTF is supported by the National Science Foundation under grant No. AST-1440341 and a collaboration including Caltech, IPAC, the Weizmann Institute for Science, the Oskar Klein Center at Stockholm University, the University of Maryland, the University of Washington, Deutsches Elektronen-Synchrotron and Humboldt University, Los Alamos National Laboratories, the TANGO Consortium of Taiwan, the University of Wisconsin at Milwaukee, and Lawrence Berkeley National Laboratories. Operations are conducted by COO, IPAC, and UW. This research has made use of data and/or services provided by the International Astronomical Union's Minor Planet Center. The authors would like to express gratitude to the anonymous referee. Facilities: PO:1.2 m - , ZTF - . Software: astropy (Astropy Collaboration et al. 2018), Fritz (https://github.com/fritz-marshal/fritz), Kowalski (Duev et al. 2019), matplotlib (Hunter 2007), numpy (Harris et al. 2020), pandas (Pandas Development Team 2020), pypride (Duev et al. 2016), SEP (Barbary 2016), sbpy (Mommert et al. 2019), TensorFlow (Abadi et al. 2016), ZChecker (Kelley et al. 2019).
Group:Infrared Processing and Analysis Center (IPAC), Astronomy Department, Zwicky Transient Facility
Funders:
Funding AgencyGrant Number
Google CloudUNSPECIFIED
Heising-Simons Foundation12540303
NSFAST-1440341
ZTF partner institutionsUNSPECIFIED
Subject Keywords:Astroinformatics; Astronomy data analysis; Convolutional neural networks; Comets
Issue or Number:5
Classification Code:Unified Astronomy Thesaurus concepts: Astroinformatics (78); Astronomy data analysis (1858); Convolutional neural networks (1938); Comets (280)
Record Number:CaltechAUTHORS:20210423-164903652
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210423-164903652
Official Citation:Dmitry A. Duev et al 2021 AJ 161 218
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108842
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:29 Apr 2021 14:54
Last Modified:29 Apr 2021 14:54

Repository Staff Only: item control page