<i>Euclid</i> preparation

The Euclid mission is expected to image millions of galaxies at high resolution, providing an extensive dataset with which to study galaxy evolution. Because galaxy morphology is both a fundamental parameter and one that is hard to determine for large samples, we investigate the application of deep learning in predicting the detailed morphologies of galaxies in Euclid using Zoobot , a convolutional neural network pretrained with 450 000 galaxies from the Galaxy Zoo project. We adapted Zoobot for use with emulated Euclid images generated based on Hubble Space Telescope COSMOS images and with labels provided by volunteers in the Galaxy Zoo: Hubble project. We experimented with different numbers of galaxies and various magnitude cuts during the training process. We demonstrate that the trained Zoobot model successfully measures detailed galaxy morphology in emulated Euclid images. It effectively predicts whether a galaxy has features and identifies and characterises various features, such as spiral arms, clumps, bars, discs, and central bulges. When compared to volunteer classifications, Zoobot achieves mean vote fraction deviations of less than 12% and an accuracy of above 91% for the confident volunteer classifications across most morphology types. However, the performance varies depending on the specific morphological class. For the global classes, such as disc or smooth galaxies, the mean deviations are less than 10%, with only 1000 training galaxies necessary to reach this performance. On the other hand, for more detailed structures and complex tasks, such as detecting and counting spiral arms or clumps, the deviations are slightly higher, of namely around 12% with 60 000 galaxies used for training. In order to enhance the performance on complex morphologies, we anticipate that a larger pool of labelled galaxies is needed, which could be obtained using crowd sourcing. We estimate that, with our model, the detailed morphology of approximately 800 million galaxies of the Euclid Wide Survey could be reliably measured and that approximately 230 million of these galaxies would display features. Finally, our findings imply that the model can be effectively adapted to new morphological labels. We demonstrate this adaptability by applying Zoobot to peculiar galaxies. In summary, our trained Zoobot CNN can readily predict morphological catalogues for Euclid images.

Authors

Institutions

Publication Details

Journal
Astronomy and Astrophysics
Published
2024-09-01
DOI
https://doi.org/10.1051/0004-6361/202449609
Citations
12
Primary Topic
Galaxies: Formation, Evolution, Phenomena
Type
article
Field-Weighted Citation Impact
3.98

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Euclid preparation

A Hall, G. Seidel, J. Brinchmann, Will J. Percival et al.
12 citations
Astronomy and Astrophysics
Galaxies: Formation, Evolution, Phenomena
3.98
article

Euclid preparation

A Hall, G. Seidel, J. Brinchmann, Will J. Percival, M. Ballardini, R. P. Saglia, P. Tallada-Crespí, S Matthew, P. Hudelot, G. Riccio, L. Conversi, C. Sirignano, M. Brescia, E. Merlin, I. Hook, M. Kunz, I. Ferrero, M. Maturi, A. Boucaud, C. Baccigalupi, Jean‐Luc Starck, M. Bolzonella, J. H. Knapen, J. Carretero, M. Schirmer, J. Steinwagner, F. Marulli, J. García-Bellido, S. Borgani, N. Mauri, C. Giocoli, O. Marggraf, S. A. Stanford, Grant M. Stevens, J. F. Macías–Pérez, F. Courbin, Y. Copin, A. Kiessling, A. Troja, S. Paltani, Santiago Casas, A. Grazian, F. Torradeflot, A. Díaz‐Sánchez, G. Sirri, G. Gozaliasl, M. Tewes, S. Mei, S. Bardelli, G. Desprez, P. Reimberg, Harry I. Teplitz, E. Munari, E. Sefusatti, M. Martinelli, M. Magliocchetti, S. Nadathur, O. Cucciati, V. Capobianco, L. Moscardini, S.-M Niemi, L. Gabarra, S. Farrens, I. A. Zinchenko, C. J. A. P. Martins, Pierre–Alain Duc, E. Zucca, S. Andreon, S. Pires, S. V. H. Haugan, D. Vergani, R. Massey, T. Vassallo, C. Valieri, R. Toledo-Moreo, S Bruton, M. Moresco, H. Bretonnière, D. Sapone, T. Castro, Ulrike Kuchner, M. Meneghetti, Ben Aussel, J. J. E. Kajava, A. Veropalumbo, M. Poncet, G. Congedo, L. Valenziano, K. Ganga, H. Dole, H. Hildebrandt, Yoshiki Toba, E. Romelli, H. Domínguez Sánchez, C. Burigana, A. M. Di Giorgio, Christopher J. Conselice, A. Biviano, I. Tutusaus, H. Degaudenzi, O. Mansutti, G. Zamorani, Matteo Viel, G. Morgante, N. Martinet, V. Allevato, J. Väliviita, D. Karagiannis, S. Escoffier, C. Padilla Aranda, K. Pedersen, E. Maiorano, B. Gillis, M. Roncarelli, F. Dubath, M. Kümmel, R. B. Metcalf, M. Migliaccio, A. Hornstrup, S. Fotopoulou, E. Rossetti, E. Medinaceli, Sandor Kruk, A. Amara, C. Tortora, M. Pöntinen, S. Di Domizio, K. Jahnkę, B. Altieri, A. Secroun, M. Farina, Antonello Calabrò, R. Bender, F. Pasian, V. Kansal, S Anselmi, J. Weller, S. Ligori, Achille Nucita, M. Castellano, F. Grupp, R. Farinelli, F. Giacomini, A. Zacchei, S. Galeotta, F. Raison, E. Franceschi, E. A. Valentijn, Marco Baldi, ENRIQUE GAZTAÑAGA, Ariel G. Sánchez, S. Dusini, N. A. Walton, Antonio La Marca, B. Margalef-Bentabol, S. Marcin, G Cañas-Herrera, K. Markovič, R. Cabanac, Michele Delli Veneri, B. Garilli, Mike Walmsley, S. Camera, Z. Sakr, L. Legrand, E. Bozzo, Romain Teyssier, K. C. Chambers, M. Kilbinger, F. Finelli⋆, J. Dinis, V. Lindholm, R. Rébolo, Austin Peel, P.-F Rocci, M. Sereno, M. Cropper, E. Keihänen, B. Sartoris, G. Castignani, S. Cavuoti, N. Auricchio, M. Frailis, M. Fumana, A. Spurio Mancini, Petra Schneider, P. Šimon, C. Carbone, S. Kermiche, Arthur Loureiro, Sune Toft, P. B. Lilje, S. Serrano, G. Polenta, A Pezzotta, G. Mainetti, Aurel Schneider, D. Potter, C. Bodendorf, D. Guinet, E. Branchini, C. Porciani, C. S. Carvalho, Alejandro S. Borlaff, L. Pozzetti, Y. Akrami, Lingyu Wang, G. De Lucia, H. M. Courtois, Yun Wang, S. Tosi, A. Da Silva, L. Stančo, L. Maurin, G. Testera, A. Jiménez Muñoz, Y. Mellier, C. C. Kirkpatrick, V. Popa, P. Franzetti, M. Tenti, L. Popa, I. Tereno, V. Pettorino, F. R. Marleau, V. Scottez, H. Kurki‐Suonio, M. Tucci, S. Davini, M. Wiesmann, A.N Taylor, R. Laureijs, J Rhodes, S. Maurogordato, C. Neissner, F. Hormuth, Koshy George, J.A. Escartin Vigo, A. Cimatti, A Cappi, J. Zoubian, B. Kubik, D. Di Ferdinando, X Dupac, D. Bonino, W. Holmes, P Monaco, G. Meylan, J Gracia-Carpio, J. Coupon, N. Aghanim, I. Lloro, S. Ferriol, A. Gregorio, A. Renzi
article en
12 citations

Abstract

The Euclid mission is expected to image millions of galaxies at high resolution, providing an extensive dataset with which to study galaxy evolution. Because galaxy morphology is both a fundamental parameter and one that is hard to determine for large samples, we investigate the application of deep learning in predicting the detailed morphologies of galaxies in Euclid using Zoobot , a convolutional neural network pretrained with 450 000 galaxies from the Galaxy Zoo project. We adapted Zoobot for use with emulated Euclid images generated based on Hubble Space Telescope COSMOS images and with labels provided by volunteers in the Galaxy Zoo: Hubble project. We experimented with different numbers of galaxies and various magnitude cuts during the training process. We demonstrate that the trained Zoobot model successfully measures detailed galaxy morphology in emulated Euclid images. It effectively predicts whether a galaxy has features and identifies and characterises various features, such as spiral arms, clumps, bars, discs, and central bulges. When compared to volunteer classifications, Zoobot achieves mean vote fraction deviations of less than 12% and an accuracy of above 91% for the confident volunteer classifications across most morphology types. However, the performance varies depending on the specific morphological class. For the global classes, such as disc or smooth galaxies, the mean deviations are less than 10%, with only 1000 training galaxies necessary to reach this performance. On the other hand, for more detailed structures and complex tasks, such as detecting and counting spiral arms or clumps, the deviations are slightly higher, of namely around 12% with 60 000 galaxies used for training. In order to enhance the performance on complex morphologies, we anticipate that a larger pool of labelled galaxies is needed, which could be obtained using crowd sourcing. We estimate that, with our model, the detailed morphology of approximately 800 million galaxies of the Euclid Wide Survey could be reliably measured and that approximately 230 million of these galaxies would display features. Finally, our findings imply that the model can be effectively adapted to new morphological labels. We demonstrate this adaptability by applying Zoobot to peculiar galaxies. In summary, our trained Zoobot CNN can readily predict morphological catalogues for Euclid images.

Astronomy and AstrophysicsVol. 689
Université Claude Bernard Lyon 1 (FR), Institut polytechnique de Grenoble (FR), University of Geneva (CH), University of Rome Tor Vergata (IT), Leiden University (NL), California Institute of Technology (US), University of Copenhagen (DK), Ames Research Center (US), Centre National de la Recherche Scientifique (FR), University of Minnesota (US), Institute of Space Sciences (ES), University of Hawaii System (US), Jet Propulsion Laboratory (US), University of Helsinki (FI), Université Toulouse III - Paul Sabatier (FR), Consejo Superior de Investigaciones Científicas (ES), University of Bonn (DE), Scuola Internazionale Superiore di Studi Avanzati (IT), University of Padua (IT), University of Lisbon (PT), University of Nottingham (GB), University of Trieste (IT), University of Salento (IT), University of Waterloo (CA), University of Turku (FI), Universidad de La Laguna (ES), Stockholm University (SE), Délégation Paris 7 (FR), University of Groningen (NL), Université Fédérale de Toulouse Midi-Pyrénées (FR), Universidade do Porto (PT), Perimeter Institute (CA), Saint Joseph University (LB), University of Oslo (NO), University of California, Santa Cruz (US), Institute for High Energy Physics (ES), Durham University (GB), Universität Innsbruck (AT), Princeton University (US), University of Ferrara (IT), Université Côte d'Azur (FR), University of Zurich (CH), Aarhus University (DK), Université Paris Cité (FR), Aix-Marseille Université (FR), Heidelberg University (DE), University of Münster (DE), University of Cambridge (GB), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), Université Paris Sciences et Lettres (FR), Université Paris-Saclay (FR), Centre National d'Études Spatiales (FR), W.M. Keck Observatory (US), Helsinki Institute of Physics (FI), Astronomical Observatory of Rome (IT), Agenzia Spaziale Italiana (IT), Trieste Astronomical Observatory (IT), Institut d'Astrophysique de Paris (FR), Astronomical Observatory of Capodimonte (IT), European Space Agency (FR), Laboratoire AstroParticule et Cosmologie (FR), Observatoire astronomique de Strasbourg (FR), Brera Astronomical Observatory (IT), University of Manchester (GB), FHNW University of Applied Sciences and Arts Northwestern Switzerland (CH), Institute for High Performance Computing and Networking (IT), Universidad Politécnica de Cartagena (ES), University of Bristol (GB), Sorbonne Université (FR), Astrophysique, Instrumentation et Modélisation (FR), Janssen (France) (FR), Laboratoire Univers et Théories (FR), Institute of Astrophysics and Space Sciences (PT), ARC Centre of Excellence for Dark Matter Particle Physics (AU), Max Planck Institute for Extraterrestrial Physics (DE), Institut d'Estudis Espacials de Catalunya (ES), European Space Astronomy Centre (ES), Centre de physique des particules de Marseille (FR), Kavli Institute for Particle Astrophysics and Cosmology (US), Istituto Nazionale di Fisica Nucleare, Sezione di Lecce (IT), Laboratoire d’Astrophysique de Marseille (FR), Istituto Nazionale di Fisica Nucleare, Sezione di Torino (IT), Institute for Space Astrophysics and Planetology (IT), Institut d'Astrophysique Spatiale (FR), Galaxies, Etoiles, Physique et Instrumentation (FR), Laboratoire d’Etudes du Rayonnement et de la Matière en Astrophysique et Atmosphères (FR), Istituto Nazionale di Fisica Nucleare, Sezione di Padova (IT), Osservatorio Astrofisico di Torino (IT), Royal Observatory (GB), Istituto Nazionale di Fisica Nucleare, Sezione di Ferrara (IT), Istituto Nazionale di Fisica Nucleare, Sezione di Napoli (IT), Centro de Astrofísica da Universidade do Porto (PT), Max Planck Institute for Astronomy (DE), Bay Area Environmental Research Institute (US), Lagrange Laboratory (FR), Istituto di Radioastronomia di Bologna (IT), Château Gombert (FR), Federico II University Hospital (IT), Université Bourgogne Franche-Comté (FR), Centro de Estudios de Física del Cosmos de Aragón (ES), Istituto Nazionale di Fisica Nucleare, Sezione di Genova (IT), Observatoire de la Côte d’Azur (FR), CEA Paris-Saclay (FR), Instituto de Astrofísica de Canarias (ES), Institut National de Physique Nucléaire et de Physique des Particules (FR), von Hoerner & Sulger (Germany) (DE), Laboratoire de Physique Subatomique et de Cosmologie (FR), Institute of Space Science - INFLPR Subsidiary (RO), Centre de Calcul de l’Institut National de Physique Nucléaire et de Physique des Particules (FR), Istituto Nazionale di Fisica Nucleare, Sezione di Bologna (IT), Port d'Informació Científica (ES), Istituto Nazionale di Fisica Nucleare, Sezione di Trieste (IT), Institute for Fundamental Physics of the Universe (IT), Institute of Nuclear Physics of Lyon (FR), Istituto Nazionale di Fisica Nucleare, Sezione di Roma I (IT), Osservatorio Astronomico di Padova (IT), National Astronomical Observatory of Japan (JP), European Space Research Institute (IT), Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas (ES), Institut de Recherche en Astrophysique et Planétologie (FR), Infrared Processing and Analysis Center (US), Osservatorio di Astrofisica e Scienza dello Spazio, Fondazione ICSC Centro Nazionale di Ricerca in High Performance Computing, Big Data e Quantum Computing, Institut de Physique des 2 Infinis de Lyon (FR), European Space Research and Technology Centre (NL), University College London (GB), Imperial College London (GB), Space Research Organisation Netherlands (NL), École Polytechnique Fédérale de Lausanne (CH), University of Turin (IT), Swinburne University of Technology (AU), Case Western Reserve University (US), University of Portsmouth (GB), Universidad Autónoma de Madrid (ES), Saint Mary's University (CA), Lancaster University (GB), Université de Strasbourg (FR), University of Chile (CL), Heidelberg Institute for Theoretical Studies (DE), Ludwig-Maximilians-Universität München (DE), University of Genoa (IT), University of California, Davis (US), Sapienza University of Rome (IT), University of the Western Cape (ZA), National Institute for Astrophysics (IT), RWTH Aachen University (DE), Université Grenoble Alpes (FR), Ruhr University Bochum (DE), Netherlands Institute for Radio Astronomy (NL), University of Bologna (IT), Universitat Politècnica de Catalunya (ES), Technical University of Denmark (DK), Stanford University (US), University of Edinburgh (GB), Aalto University (FI)
National Aeronautics and Space Administration, Alfred P. Sloan Foundation, European Space Agency, Magyar Tudományos Akadémia, Agenzia Spaziale Italiana, National Astronomical Observatory of Japan, Agenția Spațială Română, Norsk Romsenter, Fundação para a Ciência e a Tecnologia, Staatssekretariat für Bildung, Forschung und Innovation
Openalex Percentile: Top 6%
Galaxies: Formation, Evolution, Phenomena
3.98
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.