Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies
Abstract
Classification of intermediate redshift (z = 0.3-0.8) emission line galaxies as star-forming galaxies, composite galaxies, active galactic nuclei (AGNs), or low-ionization nuclear emission regions (LINERs) using optical spectra alone was impossible because the lines used for standard optical diagnostic diagrams: [N ii], Hα, and [S ii] are redshifted out of the observed wavelength range. In this work, we address this problem using four supervised machine-learning classification algorithms: k-nearest neighbors (KNN), support vector classifier (SVC), random forest (RF), and a multilayer perceptron (MLP) neural network. For input features, we use properties that can be measured from optical galaxy spectra out to z < 0.8 - [O iii]/Hβ, [O ii]/Hβ, [O iii] line width, and stellar velocity dispersion - and four colors (u - g, g - r, r - i, and i - z) corrected to z = 0.1. The labels for the low redshift emission line galaxy training set are determined using standard optical diagnostic diagrams. RF has the best area under curve score for classifying all four galaxy types, meaning the highest distinguishing power. Both the AUC scores and accuracies of the other algorithms are ordered as MLP > SVC > KNN. The classification accuracies with all eight featuresmore »
- Authors:
-
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Univ. of Pittsburgh, PA (United States)
- Consejo Superior de Investigaciones Cientificas (CSIC), Madrid (Spain); Autonomous Univ. of Madrid (Spain); Max Planck Inst. fuer Extraterrestrische Physik, Garching (Germany)
- Ecole Polytechnique Federale Lausanne (Switzerland)
- National Autonomous Univ. of Mexico, Mexico City (Mexico)
- Ecole Polytechnique Federale Lausanne (Switzerland); Aix Marseille Univ. (France)
- Univ. of Kentucky, Lexington, KY (United States)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), High Energy Physics (HEP); Alfred P. Sloan Foundation
- OSTI Identifier:
- 1650076
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- The Astrophysical Journal (Online)
- Additional Journal Information:
- Journal Name: The Astrophysical Journal (Online); Journal Volume: 883; Journal Issue: 1; Journal ID: ISSN 1538-4357
- Publisher:
- Institute of Physics (IOP)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; active galaxies; Seyfert; quasars; emission lines
Citation Formats
Zhang, Kai, Schlegel, David J., Andrews, Brett H., Comparat, Johan, Schäfer, Christoph, Vazquez Mata, Jose Antonio, Kneib, Jean-Paul, and Yan, Renbin. Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies. United States: N. p., 2019.
Web. doi:10.3847/1538-4357/ab397e.
Zhang, Kai, Schlegel, David J., Andrews, Brett H., Comparat, Johan, Schäfer, Christoph, Vazquez Mata, Jose Antonio, Kneib, Jean-Paul, & Yan, Renbin. Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies. United States. https://doi.org/10.3847/1538-4357/ab397e
Zhang, Kai, Schlegel, David J., Andrews, Brett H., Comparat, Johan, Schäfer, Christoph, Vazquez Mata, Jose Antonio, Kneib, Jean-Paul, and Yan, Renbin. Fri .
"Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies". United States. https://doi.org/10.3847/1538-4357/ab397e. https://www.osti.gov/servlets/purl/1650076.
@article{osti_1650076,
title = {Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies},
author = {Zhang, Kai and Schlegel, David J. and Andrews, Brett H. and Comparat, Johan and Schäfer, Christoph and Vazquez Mata, Jose Antonio and Kneib, Jean-Paul and Yan, Renbin},
abstractNote = {Classification of intermediate redshift (z = 0.3-0.8) emission line galaxies as star-forming galaxies, composite galaxies, active galactic nuclei (AGNs), or low-ionization nuclear emission regions (LINERs) using optical spectra alone was impossible because the lines used for standard optical diagnostic diagrams: [N ii], Hα, and [S ii] are redshifted out of the observed wavelength range. In this work, we address this problem using four supervised machine-learning classification algorithms: k-nearest neighbors (KNN), support vector classifier (SVC), random forest (RF), and a multilayer perceptron (MLP) neural network. For input features, we use properties that can be measured from optical galaxy spectra out to z < 0.8 - [O iii]/Hβ, [O ii]/Hβ, [O iii] line width, and stellar velocity dispersion - and four colors (u - g, g - r, r - i, and i - z) corrected to z = 0.1. The labels for the low redshift emission line galaxy training set are determined using standard optical diagnostic diagrams. RF has the best area under curve score for classifying all four galaxy types, meaning the highest distinguishing power. Both the AUC scores and accuracies of the other algorithms are ordered as MLP > SVC > KNN. The classification accuracies with all eight features (and the four spectroscopically determined features only) are 93.4% (92.3%) for star-forming galaxies, 69.4% (63.7%) for composite galaxies, 71.8% (67.3%) for AGNs, and 65.7% (60.8%) for LINERs. The stacked spectrum of galaxies of the same type as determined by optical diagnostic diagrams at low redshift and RF at intermediate redshift are broadly consistent. Our publicly available code (https://github.com/zkdtc/MLC_ELGs) and trained models will be instrumental for classifying emission line galaxies in upcoming wide-field spectroscopic surveys.},
doi = {10.3847/1538-4357/ab397e},
journal = {The Astrophysical Journal (Online)},
number = 1,
volume = 883,
place = {United States},
year = {Fri Sep 20 00:00:00 EDT 2019},
month = {Fri Sep 20 00:00:00 EDT 2019}
}
Web of Science
Works referenced in this record:
An experimental comparison of performance measures for classification
journal, January 2009
- Ferri, C.; Hernández-Orallo, J.; Modroiu, R.
- Pattern Recognition Letters, Vol. 30, Issue 1
Classification parameters for the emission-line spectra of extragalactic objects
journal, February 1981
- Baldwin, J. A.; Phillips, M. M.; Terlevich, R.
- Publications of the Astronomical Society of the Pacific, Vol. 93
The Sdss-Iv Extended Baryon Oscillation Spectroscopic Survey: Overview and Early data
journal, February 2016
- Dawson, Kyle S.; Kneib, Jean-Paul; Percival, Will J.
- The Astronomical Journal, Vol. 151, Issue 2
Spectral classification of emission-line galaxies from the Sloan Digital Sky Survey: II. A supplementary diagnostic for AGNs using the D n (4000) index
journal, June 2011
- Marocco, J.; Hache, E.; Lamareille, F.
- Astronomy & Astrophysics, Vol. 531
Noise estimates for measurements of weak lensing from the Ly α forest
journal, March 2018
- Metcalf, R. Benton; Croft, Rupert A. C.; Romeo, Alessandro
- Monthly Notices of the Royal Astronomical Society, Vol. 477, Issue 2
Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
journal, June 2017
- Blanton, Michael R.; Bershady, Matthew A.; Abolfathi, Bela
- The Astronomical Journal, Vol. 154, Issue 1
Prime Focus Spectrograph (PFS) for the Subaru telescope: overview, recent progress, and future perspectives
conference, August 2016
- Tamura, Naoyuki; Takato, Naruhisa; Shimono, Atsushi
- SPIE Astronomical Telescopes + Instrumentation, SPIE Proceedings
Spectral classification of emission-line galaxies
journal, February 1987
- Veilleux, Sylvain; Osterbrock, Donald E.
- The Astrophysical Journal Supplement Series, Vol. 63
The 2dF QSO Redshift Survey -- I. The optical luminosity function of quasi-stellar objects
journal, October 2000
- Boyle, B. J.; Shanks, T.; Croom, S. M.
- Monthly Notices of the Royal Astronomical Society, Vol. 317, Issue 4
Widespread and Hidden Active Galactic Nuclei in Star-Forming Galaxies at Redshift >0.3
journal, February 2013
- Juneau, Stéphanie; Dickinson, Mark; Bournaud, Frédéric
- The Astrophysical Journal, Vol. 764, Issue 2
The evolution of the [O ii], H β and [O iii] emission line luminosity functions over the last nine billions years
journal, June 2016
- Comparat, Johan; Zhu, Guangtun; Gonzalez-Perez, Violeta
- Monthly Notices of the Royal Astronomical Society, Vol. 461, Issue 1
The host galaxies of active galactic nuclei
journal, December 2003
- Kauffmann, Guinevere; Heckman, Timothy M.; Tremonti, Christy
- Monthly Notices of the Royal Astronomical Society, Vol. 346, Issue 4
Aegis: Demographics of X-Ray and Optically Selected Active Galactic Nuclei
journal, January 2011
- Yan, Renbin; Ho, Luis C.; Newman, Jeffrey A.
- The Astrophysical Journal, Vol. 728, Issue 1
TESTING DIAGNOSTICS OF NUCLEAR ACTIVITY AND STAR FORMATION IN GALAXIES AT z > 1
journal, December 2012
- Trump, Jonathan R.; Konidaris, Nicholas P.; Barro, Guillermo
- The Astrophysical Journal, Vol. 763, Issue 1
Random forest-based prediction of stroke outcome
journal, May 2021
- Fernandez-Lozano, Carlos; Hervella, Pablo; Mato-Abad, Virginia
- Scientific Reports, Vol. 11, Issue 1
An automatic taxonomy of galaxy morphology using unsupervised machine learning
journal, September 2017
- Hocking, Alex; Geach, James E.; Sun, Yi
- Monthly Notices of the Royal Astronomical Society, Vol. 473, Issue 1
THE MOSFIRE DEEP EVOLUTION FIELD (MOSDEF) SURVEY: REST-FRAME OPTICAL SPECTROSCOPY FOR ∼1500 H -SELECTED GALAXIES AT $1.37\leqslant z\leqslant 3.8$
journal, May 2015
- Kriek, Mariska; Shapley, Alice E.; Reddy, Naveen A.
- The Astrophysical Journal Supplement Series, Vol. 218, Issue 2
The optx Project. v. Identifying Distant Active Galactic Nuclei
journal, November 2011
- Trouille, L.; Barger, A. J.; Tremonti, C.
- The Astrophysical Journal, Vol. 742, Issue 1
The Mosdef Survey: agn Multi-Wavelength Identification, Selection Biases, and host Galaxy Properties
journal, January 2017
- Azadi, Mojegan; Coil, Alison L.; Aird, James
- The Astrophysical Journal, Vol. 835, Issue 1
A NEW DIAGNOSTIC OF ACTIVE GALACTIC NUCLEI: REVEALING HIGHLY ABSORBED SYSTEMS AT REDSHIFT >0.3
journal, July 2011
- Juneau, Stéphanie; Dickinson, Mark; Alexander, David M.
- The Astrophysical Journal, Vol. 736, Issue 2
Spectral classification of emission-line galaxies from the Sloan Digital Sky Survey: I. An improved classification for high-redshift galaxies
journal, January 2010
- Lamareille, F.
- Astronomy and Astrophysics, Vol. 509
Galaxy Zoo 1: data release of morphological classifications for nearly 900 000 galaxies★: Galaxy Zoo
journal, November 2010
- Lintott, Chris; Schawinski, Kevin; Bamford, Steven
- Monthly Notices of the Royal Astronomical Society, Vol. 410, Issue 1
Extragalactic science, cosmology, and Galactic archaeology with the Subaru Prime Focus Spectrograph
journal, February 2014
- Takada, Masahiro; Ellis, Richard S.; Chiba, Masashi
- Publications of the Astronomical Society of Japan, Vol. 66, Issue 1
Finding high-redshift strong lenses in DES using convolutional neural networks
journal, January 2019
- Jacobs, C.; Collett, T.; Glazebrook, K.
- Monthly Notices of the Royal Astronomical Society, Vol. 484, Issue 4
Evolution of the most massive galaxies to z= 0.6 - I. A new method for physical parameter estimation: Evolution of the most massive galaxies
journal, January 2012
- Chen, Yan-Mei; Kauffmann, Guinevere; Tremonti, Christy A.
- Monthly Notices of the Royal Astronomical Society
Basic principles of ROC analysis
journal, October 1978
- Metz, Charles E.
- Seminars in Nuclear Medicine, Vol. 8, Issue 4
The Sloan Digital Sky Survey: Technical Summary
journal, September 2000
- York, Donald G.; Adelman, J.; Anderson, Jr., John E.
- The Astronomical Journal, Vol. 120, Issue 3
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
K -Corrections and Filter Transformations in the Ultraviolet, Optical, and Near-Infrared
journal, January 2007
- Blanton, Michael R.; Roweis, Sam
- The Astronomical Journal, Vol. 133, Issue 2
Machine learning and image analysis for morphological galaxy classification
journal, March 2004
- De La Calleja, Jorge; Fuentes, Olac
- Monthly Notices of the Royal Astronomical Society, Vol. 349, Issue 1
Finding strong lenses in CFHTLS using convolutional neural networks
journal, June 2017
- Jacobs, C.; Glazebrook, K.; Collett, T.
- Monthly Notices of the Royal Astronomical Society, Vol. 471, Issue 1
THE MOSDEF SURVEY: ELECTRON DENSITY AND IONIZATION PARAMETER AT z ∼ 2.3
journal, December 2015
- Sanders, Ryan L.; Shapley, Alice E.; Kriek, Mariska
- The Astrophysical Journal, Vol. 816, Issue 1
Semi-empirical analysis of Sloan Digital Sky Survey galaxies - III. How to distinguish AGN hosts
journal, September 2006
- Stasinska, G.; Fernandes, R. C.; Mateus, A.
- Monthly Notices of the Royal Astronomical Society, Vol. 371, Issue 2
A Survey of Galaxy Kinematics to z ∼1 in the TKRS/GOODS‐N Field. I. Rotation and Dispersion Properties
journal, December 2006
- Weiner, Benjamin J.; Willmer, Christopher N. A.; Faber, S. M.
- The Astrophysical Journal, Vol. 653, Issue 2
Spectral Classification of Emission-Line Galaxies
journal, November 1986
- Osterbrock, D. E.; Veilleux, S.
- Publications of the Astronomical Society of the Pacific, Vol. 98
An introduction to ROC analysis
journal, June 2006
- Fawcett, Tom
- Pattern Recognition Letters, Vol. 27, Issue 8
The Canada-France Redshift Survey -- XII. Nature of emission-line field galaxy population up to z = 0.3
journal, August 1996
- Tresse, L.; Rola, C.; Hammer, F.
- Monthly Notices of the Royal Astronomical Society, Vol. 281, Issue 3
The Fifteenth Data Release of the Sloan Digital Sky Surveys: First Release of MaNGA-derived Quantities, Data Visualization Tools, and Stellar Library
journal, January 2019
- Aguado, D. S.; Ahumada, Romina; Almeida, Andrés
- The Astrophysical Journal Supplement Series, Vol. 240, Issue 2
The use of the area under the ROC curve in the evaluation of machine learning algorithms
journal, July 1997
- Bradley, Andrew P.
- Pattern Recognition, Vol. 30, Issue 7, p. 1145-1159
New diagnostic methods for emission-line galaxies in deep surveys
journal, August 1997
- Rola, C. S.; Terlevich, E.; Terlevich, R. J.
- Monthly Notices of the Royal Astronomical Society, Vol. 289, Issue 2
Stellar population models at high spectral resolution: High-resolution stellar population models
journal, November 2011
- Maraston, C.; Strömbäck, G.
- Monthly Notices of the Royal Astronomical Society, Vol. 418, Issue 4
The host galaxies and classification of active galactic nuclei
journal, November 2006
- Kewley, L. J.; Groves, B.; Kauffmann, G.
- Monthly Notices of the Royal Astronomical Society, Vol. 372, Issue 3
Overview of the DESI Legacy Imaging Surveys
journal, April 2019
- Dey, Arjun; Schlegel, David J.; Lang, Dustin
- The Astronomical Journal, Vol. 157, Issue 5
Finding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks
journal, August 2017
- Petrillo, C. E.; Tortora, C.; Chatterjee, S.
- Monthly Notices of the Royal Astronomical Society, Vol. 472, Issue 1
The Cosmic bpt Diagram: Confronting Theory with Observations
journal, August 2013
- Kewley, Lisa J.; Maier, Christian; Yabe, Kiyoto
- The Astrophysical Journal, Vol. 774, Issue 1
Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
text, January 2017
- Blanton, Mr; Bershady, Ma; Abolfathi, B.
- Apollo - University of Cambridge Repository
A New Diagnostic Diagram of Ionization Sources for High-redshift Emission Line Galaxies
journal, April 2018
- Zhang, Kai; Hao, Lei
- The Astrophysical Journal, Vol. 856, Issue 2
Theoretical Evolution of Optical Strong Lines Across Cosmic time
journal, August 2013
- Kewley, Lisa J.; Dopita, Michael A.; Leitherer, Claus
- The Astrophysical Journal, Vol. 774, Issue 2
LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses
journal, March 2018
- Pourrahmani, Milad; Nayyeri, Hooshang; Cooray, Asantha
- The Astrophysical Journal, Vol. 856, Issue 1
4MOST: 4-metre multi-object spectroscopic telescope
conference, October 2012
- de Jong, Roelof S.; Bellido-Tirado, Olga; Chiappini, Cristina
- SPIE Astronomical Telescopes + Instrumentation, SPIE Proceedings
Spectral classification of emission-line galaxies from the Sloan Digital Sky Survey. I. An improved classification for high redshift galaxies
text, January 2009
- Lamareille, Fabrice
- arXiv
The Cosmic BPT Diagram: Confronting Theory with Observations
text, January 2013
- Kewley, Lisa J.; Maier, Christian; Yabe, Kiyoto
- arXiv
The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
text, January 2015
- Dawson, Kyle S.; Kneib, Jean-Paul; Percival, Will J.
- arXiv
Prime Focus Spectrograph (PFS) for the Subaru Telescope: Overview, recent progress, and future perspectives
text, January 2016
- Tamura, Naoyuki; Takato, Naruhisa; Shimono, Atsushi
- arXiv
Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
text, January 2017
- Petrillo, C. E.; Tortora, C.; Chatterjee, S.
- arXiv
Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
text, January 2017
- Blanton, Michael R.; Bershady, Matthew A.; Abolfathi, Bela
- arXiv
Finding strong lenses in CFHTLS using convolutional neural networks
text, January 2017
- Jacobs, Colin; Glazebrook, Karl; Collett, Thomas
- arXiv
LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
text, January 2017
- Pourrahmani, Milad; Nayyeri, Hooshang; Cooray, Asantha
- arXiv
Overview of the DESI Legacy Imaging Surveys
text, January 2018
- Dey, Arjun; Schlegel, David J.; Lang, Dustin
- arXiv
Finding high-redshift strong lenses in DES using convolutional neural networks
text, January 2018
- Jacobs, C.; Collett, T.; Glazebrook, K.
- arXiv
Semi-empirical analysis of Sloan Digital Sky Survey galaxies III. How to distinguish AGN hosts
text, January 2006
- Stasinska, G.; Fernandes, R. Cid; Mateus, A.
- arXiv
A Survey of Galaxy Kinematics to z ~ 1 in the TKRS/GOODS-N Field. I. Rotation and Dispersion Properties
text, January 2006
- Weiner, Benjamin J.; Willmer, Christopher N. A.; Faber, S. M.
- arXiv
New diagnostic methods for emission-line galaxies in deep surveys
text, January 1997
- Rola, Claudia S.; Terlevich, Elena; Terlevich, Roberto J.
- arXiv