Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images

Euclid Collaboration; Bisigello, L; Conselice, C J; Baes, M; Bolzonella, M; Brescia, M; Cavuoti, S; Cucciati, O; Humphrey, A; Hunt, L K; Maraston, C; Pozzetti, L; Tortora, C; van Mierlo, S E; Aghanim, N; Auricchio, N; Baldi, M; Bender, R; Bodendorf, C; Bonino, D; Branchini, E; Brinchmann, J; Camera, S; Capobianco, V; Carbone, C; Carretero, J; Castander, F J; Castellano, M; Cimatti, A; Congedo, G; Conversi, L; Copin, Y; Corcione, L; Courbin, F; Cropper, M; Da Silva, A; Degaudenzi, H; Douspis, M; Dubath, F; Duncan, C A J; Dupac, X; Dusini, S; Farrens, S; Ferriol, S; Frailis, M; Franceschi, E; Franzetti, P; Fumana, M; Garilli, B; Gillard, W; Gillis, B; Giocoli, C; Grazian, A; Grupp, F; Guzzo, L; Haugan, S V H; Holmes, W; Hormuth, F; Hornstrup, A; Jahnke, K; Kümmel, M; Kermiche, S; Kiessling, A; Kilbinger, M; Kohley, R; Kunz, M; Kurki-Suonio, H; Ligori, S; Lilje, P B; Lloro, I; Maiorano, E; Mansutti, O; Marggraf, O; Markovic, K; Marulli, F; Massey, R; Maurogordato, S; Medinaceli, E; Meneghetti, M; Merlin, E; Meylan, G; Moresco, M; Moscardini, L; Munari, E; Niemi, S M; Padilla, C; Paltani, S; Pasian, F; Pedersen, K; Pettorino, V; Polenta, G; Poncet, M; Popa, L; Raison, F; Renzi, A; Rhodes, J; Riccio, G; Rix, H -W; Romelli, E; Roncarelli, M; Rosset, C; Rossetti, E; Saglia, R; Sapone, D; Sartoris, B; Schneider, P; Scodeggio, M; Secroun, A; Seidel, G; Sirignano, C; Sirri, G; Stanco, L; Tallada-Crespí, P; Tavagnacco, D; Taylor, A N; Tereno, I; Toledo-Moreo, R; Torradeflot, F; Tutusaus, I; Valentijn, E A; Valenziano, L; Vassallo, T; Wang, Y; Zacchei, A; Zamorani, G; Zoubian, J; Andreon, S; Bardelli, S; Boucaud, A; Colodro-Conde, C; Ferdinando, D Di; Graciá-Carpio, J; Lindholm, V; Maino, D; Mei, S; Scottez, V; Sureau, F; Tenti, M; Zucca, E; Borlaff, A S; Ballardini, M; Biviano, A; Bozzo, E; Burigana, C; Cabanac, R; Cappi, A; Carvalho, C S; Casas, S; Castignani, G; Cooray, A; Coupon, J; Courtois, H M; Cuby, J; Davini, S; De Lucia, G; Desprez, G; Dole, H; Escartin, J A; Escoffier, S; Farina, M; Fotopoulou, S; Ganga, K; Garcia-Bellido, J; George, K; Giacomini, F; Gozaliasl, G; Hildebrandt, H; Hook, I; Huertas-Company, M; Kansal, V; Keihanen, E; Kirkpatrick, C C; Loureiro, A; Macías-Pérez, J F; Magliocchetti, M; Mainetti, G; Marcin, S; Martinelli, M; Martinet, N; Metcalf, R B; Monaco, P; Morgante, G; Nadathur, S; Nucita, A A; Patrizii, L; Peel, A; Potter, D; Pourtsidou, A; Pöntinen, M; Reimberg, P; Sánchez, A G; Sakr, Z; Schirmer, M; Sefusatti, E; Sereno, M; Stadel, J; Teyssier, R; Valieri, C; Valiviita, J; Viel, M

doi:10.1093/mnras/stac3810

Published April 2023 | Version Published

Journal Article Open

Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images

1. University of Padua
2. INAF-Osservatorio di Astrofisica e Scienza dello Spazio di Bologna, Via Piero Gobetti 93/3, I-40129 Bologna, Italy
3. University of Nottingham
4. University of Manchester
5. Ghent University
6. INFN Sezione di Napoli
7. Astronomical Observatory of Capodimonte
8. University of Naples Federico II
9. University of Porto
10. Arcetri Astrophysical Observatory
11. University of Portsmouth
12. National Institute for Astrophysics
13. University of Groningen
14. Institut d'Astrophysique Spatiale
15. University of Bologna
16. INFN Sezione di Bologna
17. Ludwig-Maximilians-Universität München
18. Max Planck Institute for Extraterrestrial Physics
19. Osservatorio Astrofisico di Torino
20. INFN Sezione di Genova
21. INFN Sezione di Roma III
22. University of Turin
23. INFN Sezione di Torino
24. Istituto di Astrofisica Spaziale e Fisica Cosmica di Milano
25. Institute for High Energy Physics
26. Institut d'Estudis Espacials de Catalunya
27. Institute of Space Sciences
28. INAF-Osservatorio Astronomico di Roma, Via Frascati 33, I-00078 Monteporzio Catone, Italy
29. University of Edinburgh
30. European Space Astronomy Centre
31. European Space Research Institute
32. University of Lyon System
33. École Polytechnique Fédérale de Lausanne
34. University College London
35. University of Lisbon
36. University of Geneva
37. University of Oxford
38. INFN Sezione di Padova
39. University of Paris
40. Trieste Astronomical Observatory
41. Center for Particle Physics of Marseilles
42. Osservatorio Astronomico di Padova
43. University of Milan
44. Brera Astronomical Observatory
45. INFN Sezione di Milano
46. University of Oslo
47. Jet Propulsion Lab
48. Technical University of Denmark
49. Max Planck Institute for Astronomy
50. University of Helsinki
51. NOVA Optical Infrared Instrumentation Group at ASTRON, Oude Hoogeveensedijk 4, NL-7991 PD Dwingeloo, The Netherlands
52. University of Bonn
53. Durham University
54. Lagrange Laboratory
55. European Space Research and Technology Centre
56. Aarhus University
57. Agenzia Spaziale Italiana
58. Centre National d'Études Spatiales
59. Institute of Space Science
60. Astroparticle and Cosmology Laboratory
61. University of Chile
62. Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas
63. Polytechnic University of Cartagena
64. Infrared Processing and Analysis Center
65. California Institute of Technology
66. Instituto de Astrofísica de Canarias
67. Sorbonne University
68. Institut d'Astrophysique de Paris
69. Astrophysique, Instrumentation et Modélisation
70. Ames Research Center
71. Institute for Fundamental Physics of the Universe
72. University of Ferrara
73. Research Institute in Astrophysics and Planetology
74. RWTH Aachen University
75. University of California, Irvine
76. Aix-Marseille Université, CNRS, CNES, LAM, F-13013 Marseille, France
77. Institute for Space Astrophysics and Planetology
78. University of Bristol
79. Institute for Theoretical Physics
80. Ruhr University Bochum
81. Lancaster University
82. Imperial College London
83. Grenoble Institute of Technology
84. University of Applied Sciences and Arts Northwestern Switzerland
85. University of Salento
86. INFN Sezione di Lecce
87. University of Zurich
88. Heidelberg University
89. Faculty of Science, Université St Joseph, Beirut, Lebanon
90. INFN Sezione di Trieste
91. Princeton University
92. Helsinki Institute of Physics

Next-generation telescopes, like Euclid, Rubin/LSST, and Roman, will open new windows on the Universe, allowing us to infer physical properties for tens of millions of galaxies. Machine-learning methods are increasingly becoming the most efficient tools to handle this enormous amount of data, because they are often faster and more accurate than traditional methods. We investigate how well redshifts, stellar masses, and star-formation rates (SFRs) can be measured with deep-learning algorithms for observed galaxies within data mimicking the Euclid and Rubin/LSST surveys. We find that deep-learning neural networks and convolutional neural networks (CNNs), which are dependent on the parameter space of the training sample, perform well in measuring the properties of these galaxies and have a better accuracy than methods based on spectral energy distribution fitting. CNNs allow the processing of multiband magnitudes together with H_E-band images. We find that the estimates of stellar masses improve with the use of an image, but those of redshift and SFR do not. Our best results are deriving (i) the redshift within a normalized error of <0.15 for 99.9 per cent of the galaxies with signal-to-noise ratio >3 in the H_E band; (ii) the stellar mass within a factor of two (⁠∼0.3 dex⁠) for 99.5 per cent of the considered galaxies; and (iii) the SFR within a factor of two (⁠∼0.3 dex⁠) for ∼70 per cent of the sample. We discuss the implications of our work for application to surveys as well as how measurements of these galaxy parameters can be improved with deep learning.

Copyright and License

This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model).

Acknowledgement

LB and CC acknowledge the support of the STFC Cosmic Vision funding. LB acknowledges the financial support of Agenzia Spaziale Italiana (ASI) under the research contract 2018-31-HH.0. SvM acknowledges funding from the European Research Council through the award of the Consolidator Grant ID 681627-BUILDUP. HH is supported by a Heisenberg grant of the Deutsche Forschungsgemeinschaft (Hi 1495/5-1) as well as an ERC Consolidator Grant (No. 770935). MB acknowledges financial contributions from the agreement ASI/INAF 2018-23-HH.0, Euclid ESA mission - Phase D. The Euclid Consortium acknowledges the European Space Agency and a number of agencies and institutes that have supported the development of Euclid, in particular the Academy of Finland, the Agenzia Spaziale Italiana, the Belgian Science Policy, the Canadian Euclid Consortium, the French Centre National d’Etudes Spatiales, the Deutsches Zentrum für Luft- und Raumfahrt, the Danish Space Research Institute, the Fundação para a Ciência e a Tecnologia, the Ministerio de Ciencia e Innovación, the National Aeronautics and Space Administration, the National Astronomical Observatory of Japan, the Netherlandse Onderzoekschool Voor Astronomie, the Norwegian Space Agency, the Romanian Space Agency, the State Secretariat for Education, Research and Innovation (SERI) at the Swiss Space Office (SSO), and the United Kingdom Space Agency. A complete and detailed list is available on the Euclid web site (http://www.euclid-ec.org). In this work, we made use of the numpy (Harris et al. 2020) package for Python.

Funding

LB and CC acknowledge the support of the STFC Cosmic Vision funding. LB acknowledges the financial support of Agenzia Spaziale Italiana (ASI) under the research contract 2018-31-HH.0. SvM acknowledges funding from the European Research Council through the award of the Consolidator Grant ID 681627-BUILDUP. HH is supported by a Heisenberg grant of the Deutsche Forschungsgemeinschaft (Hi 1495/5-1) as well as an ERC Consolidator Grant (No. 770935). MB acknowledges financial contributions from the agreement ASI/INAF 2018-23-HH.0, Euclid ESA mission - Phase D.

Data Availability

Data included in this paper will be available on request.

Supplemental Material

Supplementary data (PDF).

Files

stac3810.pdf

Files (7.6 MB)

Name	Size	Download all
stac3810.pdf md5:962aeb95acd7e68b852c2a7b8e7932c4	6.4 MB	Preview Download
stac3810_supplemental_file.pdf md5:7543e481096a49ad365973c13d5e6518	1.2 MB	Preview Download

Additional details

Is new version of: Discussion Paper: arXiv:2206.14944 (arXiv)

Science and Technology Facilities Council
Cosmic Vision
Agenzia Spaziale Italiana
2018-31-HH.0
European Research Council
681627-BUILDUP
Deutsche Forschungsgemeinschaft
Hi 1495/5-1
European Research Council
770935
Agenzia Spaziale Italiana
2018-23-HH.0
European Space Agency

Accepted: 2022-12-22

Accepted
Available: 2023-01-09

Published
Available: 2023-02-17

Corrected and typeset

Caltech groups: Infrared Processing and Analysis Center (IPAC)
Publication Status: Published

	All versions	This version
Views	3	3
Downloads	0	0
Data volume	0 Bytes	0 Bytes

Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images

Copyright and License

Acknowledgement

Funding

Data Availability

Supplemental Material

Files

stac3810.pdf

Files (7.6 MB)

Additional details

Related works

Funding

Dates

Caltech Custom Metadata

Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images

Creators

Abstract

Copyright and License

Acknowledgement

Funding

Data Availability

Supplemental Material

Files

stac3810.pdf

Files (7.6 MB)

Additional details

Related works

Funding

Dates

Caltech Custom Metadata