Transfer learning for galaxy morphology from one survey to another

Autor: V. Scarpine, Michael Schubnell, Mariangela Bernardi, E. Suchyta, August E. Evrard, T. M. C. Abbott, N. Kuropatkin, L. N. da Costa, A. Carnero Rosell, M. E. C. Swanson, E. J. Sanchez, Peter Doel, Kyler Kuehn, R. H. Schindler, Ben Hoyle, Santiago Avila, Sugata Kaviraj, Carlos E. Cunha, K. Honscheid, Ofer Lahav, Joshua A. Frieman, G. Tarle, Joe Zuntz, J. Annis, Peter Melchior, Brian Nord, David J. Brooks, David J. James, Felipe Menanteau, Pablo Fosalba, Marc Huertas-Company, M. Carrasco Kind, Alistair R. Walker, H. Doḿinguez Sanchez, Marcelle Soares-Santos, Filipe B. Abdalla, Ramon Miquel, M. A. G. Maia, A. A. Plazas, G. Gutierrez, D. L. Hollowood, C. Davis, C. B. D'Andrea, J. Gschwend, Enrique Gaztanaga, W. G. Hartley, Flavia Sobreira, Robert A. Gruendl, M. Smith, D. W. Gerdes, J. L. Fischer, Daniel Gruen, M. March, Daniel Thomas, E. Buckley-Geer, J. De Vicente, Juan Garcia-Bellido, J. Carretero, R. C. Smith
Přispěvatelé: Laboratoire d'Etude du Rayonnement et de la Matière en Astrophysique (LERMA (UMR_8112)), Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire de Paris, PSL Research University (PSL)-PSL Research University (PSL)-Université de Cergy Pontoise (UCP), Université Paris-Seine-Université Paris-Seine-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Université Paris Diderot - Paris 7 (UPD7), DES, Observatoire de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Sorbonne Université (SU)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Zdroj: Mon.Not.Roy.Astron.Soc.
Mon.Not.Roy.Astron.Soc., 2019, 484 (1), pp.93-100. ⟨10.1093/mnras/sty3497⟩
Sánchez, H D, Huertas-Company, M, Bernardi, M, Kaviraj, S, Fischer, J L, Abbott, T M C, Abdalla, F B, Annis, J, Avila, S, Brooks, D, Buckley-Geer, E, Rosell, A C, Kind, M C, Carretero, J, Cunha, C E, D'Andrea, C B, Costa, L N D, Davis, C, Vicente, J D, Doel, P, Evrard, A E, Fosalba, P, Frieman, J, García-Bellido, J, Gaztanaga, E, Gerdes, D W, Gruen, D, Gruendl, R A, Gschwend, J, Gutierrez, G, Hartley, W G, Hollowood, D L, Honscheid, K, Hoyle, B, James, D J, Kuehn, K, Kuropatkin, N, Lahav, O, Maia, M A G, March, M, Melchior, P, Menanteau, F, Miquel, R, Nord, B, Plazas, A A, Sanchez, E, Scarpine, V, Schindler, R, Schubnell, M, Smith, M, Smith, R C, Soares-Santos, M, Sobreira, F, Suchyta, E, Swanson, M E C, Tarle, G, Thomas, D, Walker, A R & Zuntz, J 2018, ' Transfer learning for galaxy morphology from one survey to another ', Monthly Notices of the Royal Astronomical Society . https://doi.org/10.1093/mnras/sty3497
Doḿinguez Sanchez, H, Huertas-Company, M, Bernardi, M, Kaviraj, S, Fischer, J L, Abbott, T M C, Abdalla, F B, Annis, J, Avila, S, Brooks, D, Buckley-Geer, E, Carnero Rosell, A, Carrasco Kind, M, Carretero, J, Cunha, C E, D'Andrea, C B, Da Costa, L N, Davis, C, De Vicente, J, Doel, P, Evrard, A E, Fosalba, P, Frieman, J, Garćia-Bellido, J, Gaztanaga, E, Gerdes, D W, Gruen, D, Gruendl, R A, Gschwend, J, Gutierrez, G, Hartley, W G, Hollowood, D L, Honscheid, K, Hoyle, B, James, D J, Kuehn, K, Kuropatkin, N, Lahav, O, Maia, M A G, March, M, Melchior, P, Menanteau, F, Miquel, R, Nord, B, Plazas, A A, Sanchez, E, Scarpine, V, Schindler, R, Schubnell, M, Smith, M, Smith, R C, Soares-Santos, M, Sobreira, F, Suchyta, E, Swanson, M E C, Tarle, G, Thomas, D, Walker, A R & Zuntz, J 2019, ' Transfer learning for galaxy morphology from one survey to another ', Monthly Notices of the Royal Astronomical Society, vol. 484, no. 1, pp. 93-100 . https://doi.org/10.1093/mnras/sty3497
Monthly Notices of the Royal Astronomical Society
Monthly Notices of the Royal Astronomical Society, Oxford University Press (OUP): Policy P-Oxford Open Option A, 2019, 484 (1), pp.93-100. ⟨10.1093/mnras/sty3497⟩
ISSN: 0035-8711
1365-2966
DOI: 10.1093/mnras/sty3497⟩
Popis: Deep Learning (DL) algorithms for morphological classification of galaxies have proven very successful, mimicking (or even improving) visual classifications. However, these algorithms rely on large training samples of labelled galaxies (typically thousands of them). A key question for using DL classifications in future Big Data surveys is how much of the knowledge acquired from an existing survey can be exported to a new dataset, i.e. if the features learned by the machines are meaningful for different data. We test the performance of DL models, trained with Sloan Digital Sky Survey (SDSS) data, on Dark Energy survey (DES) using images for a sample of $\sim$5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy ($\sim$ 90%), but small completeness and purity values. A fast domain adaptation step, consisting in a further training with a small DES sample of galaxies ($\sim$500-300), is enough for obtaining an accuracy > 95% and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular dataset, machines can quickly adapt to new instrument characteristics (e.g., PSF, seeing, depth), reducing by almost one order of magnitude the necessary training sample for morphological classification. Redshift evolution effects or significant depth differences are not taken into account in this study.
Accepted for publication in MNRAS
Databáze: OpenAIRE
Externí odkaz: