Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning
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).
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).Attached Files
Published - Duev_2021_AJ_161_218.pdf
Accepted Version - 2102.13352.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:5a20bacacb6aa01f8a9b7020be10b510
|
3.3 MB | Preview Download |
|
md5:06cc425232ff90814c5b9253401a6cab
|
11.5 MB | Preview Download |
Additional details
- Eprint ID
- 108842
- Resolver ID
- CaltechAUTHORS:20210423-164903652
- Google Cloud
- Heising-Simons Foundation
- 12540303
- NSF
- AST-1440341
- ZTF partner institutions
- Created
-
2021-04-29Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field
- Caltech groups
- Infrared Processing and Analysis Center (IPAC), Astronomy Department, Zwicky Transient Facility, Division of Geological and Planetary Sciences