Pushing automated morphological classifications to their limits with the Dark Energy Survey

J. Vega-Ferrero; H. Domínguez Sánchez; M. Bernardi; M. Huertas-Company; R. Morgan; B. Margalef; M. Aguena; S. Allam; J. Annis; S. Avila; D. Bacon; E. Bertin; D. Brooks; A. Carnero Rosell; M. Carrasco Kind; J. Carretero; A. Choi; C. Conselice; M. Costanzi; L. N. Da Costa; M. E.S. Pereira; J. De Vicente; S. Desai; I. Ferrero; P. Fosalba; J. Frieman; J. García-Bellido; D. Gruen; R. A. Gruendl; J. Gschwend; G. Gutierrez; W. G. Hartley; S. R. Hinton; D. L. Hollowood; K. Honscheid; B. Hoyle; M. Jarvis; A. G. Kim; K. Kuehn; N. Kuropatkin; M. Lima; M. A.G. Maia; F. Menanteau; R. Miquel; R. L.C. Ogando; A. Palmese; F. Paz-Chinchón; A. A. Plazas; A. K. Romer; E. Sanchez; V. Scarpine; M. Schubnell; S. Serrano; I. Sevilla-Noarbe; M. Smith; E. Suchyta; M. E.C. Swanson; G. Tarle; F. Tarsitano; C. To; D. L. Tucker; T. N. Varga; R. D. Wilkinson

doi:10.1093/mnras/stab594

Pushing automated morphological classifications to their limits with the Dark Energy Survey

J. Vega-Ferrero, H. Domínguez Sánchez, M. Bernardi, M. Huertas-Company, R. Morgan, B. Margalef, M. Aguena, S. Allam, J. Annis, S. Avila, D. Bacon, E. Bertin, D. Brooks, A. Carnero Rosell, M. Carrasco Kind, J. Carretero, A. Choi, C. Conselice, M. Costanzi, L. N. Da CostaM. E.S. Pereira, J. De Vicente, S. Desai, I. Ferrero, P. Fosalba, J. Frieman, J. García-Bellido, D. Gruen, R. A. Gruendl, J. Gschwend, G. Gutierrez, W. G. Hartley, S. R. Hinton, D. L. Hollowood, K. Honscheid, B. Hoyle, M. Jarvis, A. G. Kim, K. Kuehn, N. Kuropatkin, M. Lima, M. A.G. Maia, F. Menanteau, R. Miquel, R. L.C. Ogando, A. Palmese, F. Paz-Chinchón, A. A. Plazas, A. K. Romer, E. Sanchez, V. Scarpine, M. Schubnell, S. Serrano, I. Sevilla-Noarbe, M. Smith, E. Suchyta, M. E.C. Swanson, G. Tarle, F. Tarsitano, C. To, D. L. Tucker, T. N. Varga, R. D. Wilkinson

Workflow Systems

Research output: Contribution to journal › Review article › peer-review

37 Scopus citations

Abstract

We present morphological classifications of ~27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have mr ≤17.7 mag; we model fainter objects to mr < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 per cent accuracy to mr < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for ~87 per cent and 73 per cent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with Sérsic index (n), ellipticity (ϵ), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.

Original language	English
Pages (from-to)	1927-1943
Number of pages	17
Journal	Monthly Notices of the Royal Astronomical Society
Volume	506
Issue number	2
DOIs	https://doi.org/10.1093/mnras/stab594
State	Published - Sep 1 2021

Funding

This work was supported in part by National Science Foundation (NSF) grant AST-1816330. HDS acknowledges support from the Centro Superior de Investigaciones Cientificas PIE2018-50E099.We are grateful to R. Sheth for a careful reading of the manuscript. Funding for the DES Projects has been provided by the U.S. Department of Energy, the U.S. National Science Foundation, the Ministry of Science and Education of Spain, the Science and Technology Facilities Council of the United Kingdom, the Higher Education Funding Council for England, the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign, the Kavli Institute of Cosmological Physics at the University of Chicago, the Center for Cosmology and Astro-Particle Physics at the Ohio StateUniversity, the Mitchell Institute for Fundamental Physics and Astronomy at Texas A&M University, Financiadora de Estudos e Projetos, Fundação Carlos Chagas Filho de Amparoa Pesquisa do Estado do Rio de Janeiro, Conselho Nacional de Desenvolvimento Cientifico e Tecnologico and the Ministerio da Ciencia, Tecnologia e Inovacao, the Deutsche Forschungsgemeinschaft, and the Collaborating Institutions in the Dark Energy Survey. The Collaborating Institutions are Argonne National Laboratory, the University of California at Santa Cruz, the University of Cambridge, Centro de Investigaciones Energeticas, Medioambientales y Tecnologicas - Madrid, the University of Chicago, University College London, the DES-Brazil Consortium, the University of Edinburgh, the Eidgenossische Technische Hochschule (ETH) Zurich, Fermi National Accelerator Laboratory, the University of Illinois at Urbana-Champaign, the Institut de Ciencies de l'Espai (IEEC/CSIC), the Institut de Fisica d'Altes Energies, Lawrence Berkeley National Laboratory, the Ludwig-Maximilians Universitat Munchen and the associated Excellence Cluster Universe, the University of Michigan, NFS's NOIRLab, the University of Nottingham, The Ohio State University, the University of Pennsylvania, the University of Portsmouth, SLAC National Accelerator Laboratory, Stanford University, the University of Sussex, Texas A&M University, and the OzDES Membership Consortium. Based in part on observations at Cerro Tololo Inter-American Observatory at NSF's NOIRLab (NOIRLab Prop. ID 2012B-0001; PI: J. Frieman), which is managed by the Association of Universities for Research in Astronomy (AURA) under a cooperative agreement with the National Science Foundation. The DES data management system is supported by the National Science Foundation under grant numbers AST-1138766 and AST-1536171. The DES participants from Spanish institutions are partially supported by MICINN under grants ESP2017-89838, PGC2018-094773, PGC2018-102021, SEV-2016-0588, SEV-2016- 0597, and MDM-2015-0509, some of which include ERDF funds from the European Union. IFAE is partially funded by the CERCA program of the Generalitat de Catalunya. Research leading to these results has received funding from the European Research Council under the European Union's Seventh Framework Program (FP7/2007-2013) including ERC grant agreements 240672, 291329, and 306478. We acknowledge support from the Brazilian Instituto Nacional de Ciencia e Tecnologia (INCT) do e-Universo (CNPq grant 465376/2014-2). This manuscript has been authored by Fermi Research Alliance, LLC under Contract no. DE-AC02-07CH11359 with the U.S. Department of Energy, Office of Science, Office of High Energy Physics.

Funders	Funder number
Brazilian Instituto Nacional de Ciencia e Tecnologia
Center for Cosmology and Astro-Particle Physics at the Ohio StateUniversity
Centro Superior de Investigaciones Cientificas	PIE2018-50E099
Collaborating Institutions are Argonne National Laboratory
Collaborating Institutions in the Dark Energy Survey
Fermi Research Alliance, LLC	DE-AC02-07CH11359
Institut de Ciencies de l'Espai
Mitchell Institute for Fundamental Physics and Astronomy at Texas A&M University
Science and Technology Facilities Council of the United Kingdom
Zurich
National Science Foundation	AST-1816330
U.S. Department of Energy
University of Illinois at Urbana-Champaign
Stanford University
Office of Science
High Energy Physics
Fermilab
Lawrence Berkeley National Laboratory
University of California, Santa Cruz
University of Pennsylvania
Ohio State University
University of Chicago
University of Michigan
Texas A and M University	2012B-0001, AST-1138766, AST-1536171
University of Portsmouth
National Centre for Supercomputing Applications
Seventh Framework Programme	1138766, 240672, 1816330, 306478, 291329
SLAC National Accelerator Laboratory
Higher Education Funding Council for England
Engineering Research Centers
University of Cambridge
University College London
European Commission
European Research Council
University of Nottingham
University of Sussex
University of Edinburgh
Deutsche Forschungsgemeinschaft
Generalitat de Catalunya
Eidgenössische Technische Hochschule Zürich
Ministério da Ciência, Tecnologia e Inovação
Conselho Nacional de Desenvolvimento Científico e Tecnológico	465376/2014-2
Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro
Financiadora de Estudos e Projetos
Ministerio de Ciencia e Innovación	SEV-2016-0588, MDM-2015-0509, SEV-2016- 0597, PGC2018-094773, PGC2018-102021, ESP2017-89838
Seventh Framework Programme
Ludwig-Maximilians-Universität München
Instituto Nacional de Ciência e Tecnologia para Excitotoxicidade e Neuroproteção
Ministry of Education and Science of Ukraine
European Regional Development Fund
Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas
Institut de Física d'Altes Energies

Keywords

Catalogues
Galaxies: structure
Methods: observational

Access to Document

10.1093/mnras/stab594

Cite this

Vega-Ferrero, J., Domínguez Sánchez, H., Bernardi, M., Huertas-Company, M., Morgan, R., Margalef, B., Aguena, M., Allam, S., Annis, J., Avila, S., Bacon, D., Bertin, E., Brooks, D., Carnero Rosell, A., Carrasco Kind, M., Carretero, J., Choi, A., Conselice, C., Costanzi, M., ... Wilkinson, R. D. (2021). Pushing automated morphological classifications to their limits with the Dark Energy Survey. Monthly Notices of the Royal Astronomical Society, 506(2), 1927-1943. https://doi.org/10.1093/mnras/stab594

@article{e5dd4f84c8e14ca5a4ae68ddfefd3b61,

title = "Pushing automated morphological classifications to their limits with the Dark Energy Survey",

abstract = "We present morphological classifications of ~27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have mr ≤17.7 mag; we model fainter objects to mr < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 per cent accuracy to mr < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for ~87 per cent and 73 per cent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with S{\'e}rsic index (n), ellipticity (ϵ), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.",

keywords = "Catalogues, Galaxies: structure, Methods: observational",

author = "J. Vega-Ferrero and {Dom{\'i}nguez S{\'a}nchez}, H. and M. Bernardi and M. Huertas-Company and R. Morgan and B. Margalef and M. Aguena and S. Allam and J. Annis and S. Avila and D. Bacon and E. Bertin and D. Brooks and {Carnero Rosell}, A. and {Carrasco Kind}, M. and J. Carretero and A. Choi and C. Conselice and M. Costanzi and {Da Costa}, {L. N.} and Pereira, {M. E.S.} and {De Vicente}, J. and S. Desai and I. Ferrero and P. Fosalba and J. Frieman and J. Garc{\'i}a-Bellido and D. Gruen and Gruendl, {R. A.} and J. Gschwend and G. Gutierrez and Hartley, {W. G.} and Hinton, {S. R.} and Hollowood, {D. L.} and K. Honscheid and B. Hoyle and M. Jarvis and Kim, {A. G.} and K. Kuehn and N. Kuropatkin and M. Lima and Maia, {M. A.G.} and F. Menanteau and R. Miquel and Ogando, {R. L.C.} and A. Palmese and F. Paz-Chinch{\'o}n and Plazas, {A. A.} and Romer, {A. K.} and E. Sanchez and V. Scarpine and M. Schubnell and S. Serrano and I. Sevilla-Noarbe and M. Smith and E. Suchyta and Swanson, {M. E.C.} and G. Tarle and F. Tarsitano and C. To and Tucker, {D. L.} and Varga, {T. N.} and Wilkinson, {R. D.}",

note = "Publisher Copyright: {\textcopyright} 2021 The Author(s) Published by Oxford University Press on behalf of Royal Astronomical Society.",

year = "2021",

month = sep,

day = "1",

doi = "10.1093/mnras/stab594",

language = "English",

volume = "506",

pages = "1927--1943",

journal = "Monthly Notices of the Royal Astronomical Society",

issn = "0035-8711",

publisher = "Oxford University Press",

number = "2",

}

Vega-Ferrero, J, Domínguez Sánchez, H, Bernardi, M, Huertas-Company, M, Morgan, R, Margalef, B, Aguena, M, Allam, S, Annis, J, Avila, S, Bacon, D, Bertin, E, Brooks, D, Carnero Rosell, A, Carrasco Kind, M, Carretero, J, Choi, A, Conselice, C, Costanzi, M, Da Costa, LN, Pereira, MES, De Vicente, J, Desai, S, Ferrero, I, Fosalba, P, Frieman, J, García-Bellido, J, Gruen, D, Gruendl, RA, Gschwend, J, Gutierrez, G, Hartley, WG, Hinton, SR, Hollowood, DL, Honscheid, K, Hoyle, B, Jarvis, M, Kim, AG, Kuehn, K, Kuropatkin, N, Lima, M, Maia, MAG, Menanteau, F, Miquel, R, Ogando, RLC, Palmese, A, Paz-Chinchón, F, Plazas, AA, Romer, AK, Sanchez, E, Scarpine, V, Schubnell, M, Serrano, S, Sevilla-Noarbe, I, Smith, M, Suchyta, E, Swanson, MEC, Tarle, G, Tarsitano, F, To, C, Tucker, DL, Varga, TN & Wilkinson, RD 2021, 'Pushing automated morphological classifications to their limits with the Dark Energy Survey', Monthly Notices of the Royal Astronomical Society, vol. 506, no. 2, pp. 1927-1943. https://doi.org/10.1093/mnras/stab594

TY - JOUR

T1 - Pushing automated morphological classifications to their limits with the Dark Energy Survey

AU - Vega-Ferrero, J.

AU - Domínguez Sánchez, H.

AU - Bernardi, M.

AU - Huertas-Company, M.

AU - Morgan, R.

AU - Margalef, B.

AU - Aguena, M.

AU - Allam, S.

AU - Annis, J.

AU - Avila, S.

AU - Bacon, D.

AU - Bertin, E.

AU - Brooks, D.

AU - Carnero Rosell, A.

AU - Carrasco Kind, M.

AU - Carretero, J.

AU - Choi, A.

AU - Conselice, C.

AU - Costanzi, M.

AU - Da Costa, L. N.

AU - Pereira, M. E.S.

AU - De Vicente, J.

AU - Desai, S.

AU - Ferrero, I.

AU - Fosalba, P.

AU - Frieman, J.

AU - García-Bellido, J.

AU - Gruen, D.

AU - Gruendl, R. A.

AU - Gschwend, J.

AU - Gutierrez, G.

AU - Hartley, W. G.

AU - Hinton, S. R.

AU - Hollowood, D. L.

AU - Honscheid, K.

AU - Hoyle, B.

AU - Jarvis, M.

AU - Kim, A. G.

AU - Kuehn, K.

AU - Kuropatkin, N.

AU - Lima, M.

AU - Maia, M. A.G.

AU - Menanteau, F.

AU - Miquel, R.

AU - Ogando, R. L.C.

AU - Palmese, A.

AU - Paz-Chinchón, F.

AU - Plazas, A. A.

AU - Romer, A. K.

AU - Sanchez, E.

AU - Scarpine, V.

AU - Schubnell, M.

AU - Serrano, S.

AU - Sevilla-Noarbe, I.

AU - Smith, M.

AU - Suchyta, E.

AU - Swanson, M. E.C.

AU - Tarle, G.

AU - Tarsitano, F.

AU - To, C.

AU - Tucker, D. L.

AU - Varga, T. N.

AU - Wilkinson, R. D.

PY - 2021/9/1

Y1 - 2021/9/1

N2 - We present morphological classifications of ~27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have mr ≤17.7 mag; we model fainter objects to mr < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 per cent accuracy to mr < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for ~87 per cent and 73 per cent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with Sérsic index (n), ellipticity (ϵ), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.

AB - We present morphological classifications of ~27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have mr ≤17.7 mag; we model fainter objects to mr < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 per cent accuracy to mr < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for ~87 per cent and 73 per cent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with Sérsic index (n), ellipticity (ϵ), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.

KW - Catalogues

KW - Galaxies: structure

KW - Methods: observational

UR - http://www.scopus.com/inward/record.url?scp=85106122349&partnerID=8YFLogxK

U2 - 10.1093/mnras/stab594

DO - 10.1093/mnras/stab594

M3 - Review article

AN - SCOPUS:85106122349

SN - 0035-8711

VL - 506

SP - 1927

EP - 1943

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

IS - 2

ER -

Pushing automated morphological classifications to their limits with the Dark Energy Survey

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this