Identification of Galaxy Shreds in Large Photometric Catalogs Using Convolutional Neural Networks

Di Teodoro, Enrico M.; Peek, J. G.; Wu, John F.

doi:10.3847/1538-3881/acb53a

Identification of Galaxy Shreds in Large Photometric Catalogs Using Convolutional Neural Networks

Journal Article · Wed Feb 22 00:00:00 EST 2023 · The Astronomical Journal

DOI:https://doi.org/10.3847/1538-3881/acb53a· OSTI ID:2425196

^[1]; ^[2]; ^[2]

Johns Hopkins Univ., Baltimore, MD (United States); Space Telescope Science Institute, Baltimore, MD (United States); Università degli Studi di Firenze, Fiorentino (Italy)
Johns Hopkins Univ., Baltimore, MD (United States); Space Telescope Science Institute, Baltimore, MD (United States)

Contamination from galaxy fragments, identified as sources, is a major issue in large photometric galaxy catalogs. In this paper, we prove that this problem can be easily addressed with computer vision techniques. We use image cutouts to train a convolutional neural network (CNN) to identify cataloged sources that are in reality just star-formation regions and/or shreds of larger galaxies. The CNN reaches an accuracy ~98% on our testing data sets. We apply this CNN to galaxy catalogs from three among the largest surveys available today: the Sloan Digital Sky Survey, the DESI Legacy Imaging Surveys, and the Panoramic Survey Telescope and Rapid Response System Survey. We find that, even when strict selection criteria are used, all catalogs still show a ~5% level of contamination from galaxy shreds. Our CNN gives a simple yet effective solution to clean galaxy catalogs from these contaminants.

View Accepted Manuscript (DOE)

Research Organization:: US Department of Energy (USDOE), Washington, DC (United States). Office of Science, Sloan Digital Sky Survey (SDSS)

Sponsoring Organization:: European Research Council (ERC); National Science Foundation (NSF); USDOE Office of Science (SC)

OSTI ID:: 2425196

Journal Information:: The Astronomical Journal, Journal Name: The Astronomical Journal Journal Issue: 3 Vol. 165; ISSN 0004-6256

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: United States

Language:: English

References (16)

A quantitative analysis of source detection approaches in optical, infrared, and radio astronomical images Masias, M.; Peracaula, M.; Freixenet, J. Experimental Astronomy, Vol. 36, Issue 3 https://doi.org/10.1007/s10686-013-9346-1	journal	September 2013
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/Nature14539	journal	May 2015
Astropy: A community Python package for astronomy Robitaille, Thomas P.; Tollerud, Erik J.; Greenfield, Perry Astronomy & Astrophysics, Vol. 558 https://doi.org/10.1051/0004-6361/201322068	journal	September 2013
SExtractor: Software for source extraction Bertin, E.; Arnouts, S. Astronomy and Astrophysics Supplement Series, Vol. 117, Issue 2 https://doi.org/10.1051/aas:1996164	journal	June 1996
Improved Background Subtraction for the Sloan Digital sky Survey Images Blanton, Michael R.; Kazin, Eyal; Muna, Demitri The Astronomical Journal, Vol. 142, Issue 1 https://doi.org/10.1088/0004-6256/142/1/31	journal	June 2011
Sdss-Iii: Massive Spectroscopic Surveys of the Distant Universe, the Milky way, and Extra-Solar Planetary Systems Eisenstein, Daniel J.; Weinberg, David H.; Agol, Eric The Astronomical Journal, Vol. 142, Issue 3 https://doi.org/10.1088/0004-6256/142/3/72	journal	August 2011
Project Overview of the Beijing–Arizona Sky Survey Zou, Hu; Zhou, Xu; Fan, Xiaohui Publications of the Astronomical Society of the Pacific, Vol. 129, Issue 976 https://doi.org/10.1088/1538-3873/aa65ba	journal	April 2017
Rotation-invariant convolutional neural networks for galaxy morphology prediction Dieleman, Sander; Willett, Kyle W.; Dambre, Joni Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2 https://doi.org/10.1093/MNRAS/stv632	journal	April 2015
Deblending galaxies with variational autoencoders: A joint multiband, multi-instrument approach Arcelin, Bastien; Doux, Cyrille; Aubourg, Eric Monthly Notices of the Royal Astronomical Society, Vol. 500, Issue 1 https://doi.org/10.1093/mnras/staa3062	journal	October 2020
Gradient-based learning applied to document recognition Lecun, Y.; Bottou, L.; Bengio, Y. Proceedings of the IEEE, Vol. 86, Issue 11 https://doi.org/10.1109/5.726791	journal	January 1998
A review of source detection approaches in astronomical images: Source detection in astronomical images Masias, M.; Freixenet, J.; Lladó, X. Monthly Notices of the Royal Astronomical Society, Vol. 422, Issue 2 https://doi.org/10.1111/j.1365-2966.2012.20742.x	journal	March 2012
The Astropy Project: Building an Open-science Project and Status of the v2.0 Core Package Price-Whelan, A. M.; Sipőcz, B. M.; Günther, H. M. The Astronomical Journal, Vol. 156, Issue 3 https://doi.org/10.3847/1538-3881/aabc4f	journal	August 2018
Overview of the DESI Legacy Imaging Surveys Dey, Arjun; Schlegel, David J.; Lang, Dustin The Astronomical Journal, Vol. 157, Issue 5 https://doi.org/10.3847/1538-3881/ab089d	journal	April 2019
The SAGA Survey. I. Satellite Galaxy Populations around Eight Milky Way Analogs Geha, Marla; Wechsler, Risa H.; Mao, Yao-Yuan The Astrophysical Journal, Vol. 847, Issue 1 https://doi.org/10.3847/1538-4357/aa8626	journal	September 2017
The SAGA Survey. II. Building a Statistical Sample of Satellite Systems around Milky Way–like Galaxies Mao, Yao-Yuan; Geha, Marla; Wechsler, Risa H. The Astrophysical Journal, Vol. 907, Issue 2 https://doi.org/10.3847/1538-4357/abce58	journal	February 2021
Extending the SAGA Survey (xSAGA). I. Satellite Radial Profiles as a Function of Host-galaxy Properties Wu, John F.; Peek, J. E. G.; Tollerud, Erik J. The Astrophysical Journal, Vol. 927, Issue 1 https://doi.org/10.3847/1538-4357/ac4eea	journal	March 2022

Similar Records

Extending the SAGA Survey (xSAGA). I. Satellite Radial Profiles as a Function of Host-galaxy Properties

Journal Article · Tue Mar 08 19:00:00 EST 2022 · The Astrophysical Journal · OSTI ID:1867010

AutoSourceID-Classifier: Star-galaxy classification using a convolutional neural network with spatial information

Journal Article · Thu Nov 30 19:00:00 EST 2023 · Astronomy and Astrophysics · OSTI ID:2582047

Search of strong lens systems in the Dark Energy Survey using convolutional neural networks

Journal Article · Mon Dec 05 19:00:00 EST 2022 · Astronomy and Astrophysics · OSTI ID:2423872

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS

Identification of Galaxy Shreds in Large Photometric Catalogs Using Convolutional Neural Networks

Citation Formats

References (16)

Similar Records

Related Subjects