Transfer learning for galaxy morphology from one survey to another
Abstract
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 data set, 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 ~5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy (~90 percent), but small completeness and purity values. A fast domain adaptation step, consisting of a further training with a small DES sample of galaxies (~500–300), is enough for obtaining an accuracy >95 percent and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular data set, machines can quickly adapt to new instrument characteristics (e.g. PSF, seeing, depth), reducing by almost one order of magnitude the necessarymore »
- Authors:
-
more »
- Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA 19104, USA
- Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA 19104, USA, LERMA, Observatoire de Paris, PSL Research University, CNRS, Sorbonne Universités, UPMC Univ. Paris 06, F-75014 Paris, France, University of Paris Denis Diderot, University of Paris Sorbonne Cité (PSC), F-75205 Paris Cedex 13, France, Instituto de Astrofísica de Canarias, E-38200 La Laguna, Tenerife, Spain, Departamento de Astrofísica, Universidad de La Laguna, E-38206 La Laguna, Tenerife, Spain
- Centre for Astrophysics Research, University of Hertfordshire, College Lane, Hatfield, Herts AL10 9AB, UK
- Cerro Tololo Inter-American Observatory, National Optical Astronomy Observatory, Casilla 603, La Serena, Chile
- Department of Physics & Astronomy, University College London, Gower Street, London WC1E 6BT, UK, Department of Physics and Electronics, Rhodes University, PO Box 94, Grahamstown 6140, South Africa
- Fermi National Accelerator Laboratory, PO Box 500, Batavia, IL 60510, USA
- Institute of Cosmology & Gravitation, University of Portsmouth, Portsmouth PO1 3FX, UK
- Department of Physics & Astronomy, University College London, Gower Street, London WC1E 6BT, UK
- Laboratório Interinstitucional de e-Astronomia - LIneA, Rua Gal. José Cristino 77, Rio de Janeiro, RJ 20921-400, Brazil, Observatório Nacional, Rua Gal. José Cristino 77, Rio de Janeiro, RJ 20921-400, Brazil
- Department of Astronomy, University of Illinois at Urbana-Champaign, 1002 W. Green Street, Urbana, IL 61801, USA, National Center for Supercomputing Applications, 1205 West Clark St., Urbana, IL 61801, USA
- Institut de Física d’Altes Energies (IFAE), The Barcelona Institute of Science and Technology, Campus UAB, E-08193 Bellaterra (Barcelona) Spain
- Kavli Institute for Particle Astrophysics & Cosmology, PO Box 2450, Stanford University, Stanford, CA 94305, USA
- Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas (CIEMAT), Madrid, Spain
- Department of Astronomy, University of Michigan, Ann Arbor, MI 48109, USA, Department of Physics, University of Michigan, Ann Arbor, MI 48109, USA
- Institut dÉstudis Espacials de Catalunya (IEEC), E-08193 Barcelona, Spain, Institute of Space Sciences (ICE, CSIC), Campus UAB, Carrer de Can Magrans, s/n, 08193 Barcelona, Spain
- Fermi National Accelerator Laboratory, PO Box 500, Batavia, IL 60510, USA, Kavli Institute for Cosmological Physics, University of Chicago, Chicago, IL 60637, USA
- Instituto de Fisica Teorica UAM/CSIC, Universidad Autonoma de Madrid, E-28049 Madrid, Spain
- Kavli Institute for Particle Astrophysics & Cosmology, PO Box 2450, Stanford University, Stanford, CA 94305, USA, SLAC National Accelerator Laboratory, Menlo Park, CA 94025, USA
- Department of Physics & Astronomy, University College London, Gower Street, London WC1E 6BT, UK, Department of Physics, ETH Zurich, Wolfgang-Pauli-Strasse 16, CH-8093 Zurich, Switzerland
- Santa Cruz Institute for Particle Physics, Santa Cruz, CA 95064, USA
- Center for Cosmology and Astro-Particle Physics, The Ohio State University, Columbus, OH 43210, USA, Department of Physics, The Ohio State University, Columbus, OH 43210, USA
- Max Planck Institute for Extraterrestrial Physics, Giessenbachstrasse, D-85748 Garching, Germany, Universitäts-Sternwarte, Fakultät für Physik, Ludwig-Maximilians Universität München, Scheinerstr 1, D-81679 München, Germany
- Harvard-Smithsonian Center for Astrophysics, Cambridge, MA 02138, USA
- Australian Astronomical Observatory, North Ryde, NSW 2113, Australia
- Department of Astrophysical Sciences, Princeton University, Peyton Hall, Princeton, NJ 08544, USA
- Institut de Física d’Altes Energies (IFAE), The Barcelona Institute of Science and Technology, Campus UAB, E-08193 Bellaterra (Barcelona) Spain, Institució Catalana de Recerca i Estudis Avanccats, E-08010 Barcelona, Spain
- Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Dr., Pasadena, CA 91109, USA
- SLAC National Accelerator Laboratory, Menlo Park, CA 94025, USA
- Department of Physics, University of Michigan, Ann Arbor, MI 48109, USA
- School of Physics and Astronomy, University of Southampton, Southampton SO17 1BJ, UK
- Physics Department, Brandeis University, 415 South Street, Waltham MA 02453, USA
- Instituto de Física Gleb Wataghin, Universidade Estadual de Campinas, 13083-859, Campinas, SP, Brazil, Laboratório Interinstitucional de e-Astronomia - LIneA, Rua Gal. José Cristino 77, Rio de Janeiro, RJ 20921-400, Brazil
- Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
- National Center for Supercomputing Applications, 1205 West Clark St., Urbana, IL 61801, USA
- Institute for Astronomy, University of Edinburgh, Edinburgh EH9 3HJ, UK
- Publication Date:
- Research Org.:
- SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States); Univ. of Michigan, Ann Arbor, MI (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), High Energy Physics (HEP); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- OSTI Identifier:
- 1491209
- Alternate Identifier(s):
- OSTI ID: 1474426; OSTI ID: 1503971; OSTI ID: 1727378
- Report Number(s):
- arXiv:1807.00807; FERMILAB-PUB-18-106
Journal ID: ISSN 0035-8711
- Grant/Contract Number:
- AC02-07CH11359; AC05-00OR22725; SC0019193
- Resource Type:
- Published Article
- Journal Name:
- Monthly Notices of the Royal Astronomical Society
- Additional Journal Information:
- Journal Name: Monthly Notices of the Royal Astronomical Society Journal Volume: 484 Journal Issue: 1; Journal ID: ISSN 0035-8711
- Publisher:
- Royal Astronomical Society
- Country of Publication:
- United Kingdom
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; 96 KNOWLEDGE MANAGEMENT AND PRESERVATION; galaxies: structure; methods: observational-surveys
Citation Formats
Domínguez Sánchez, 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., 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., and Zuntz, J. Transfer learning for galaxy morphology from one survey to another. United Kingdom: N. p., 2018.
Web. doi:10.1093/mnras/sty3497.
Domínguez Sánchez, 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., 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. Transfer learning for galaxy morphology from one survey to another. United Kingdom. https://doi.org/10.1093/mnras/sty3497
Domínguez Sánchez, 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., 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., and Zuntz, J. Fri .
"Transfer learning for galaxy morphology from one survey to another". United Kingdom. https://doi.org/10.1093/mnras/sty3497.
@article{osti_1491209,
title = {Transfer learning for galaxy morphology from one survey to another},
author = {Domínguez Sánchez, H. and Huertas-Company, M. and Bernardi, M. and Kaviraj, S. and Fischer, J. L. and Abbott, T. M. C. and Abdalla, F. B. and Annis, J. and Avila, S. and Brooks, D. and Buckley-Geer, E. and Carnero Rosell, A. and Carrasco Kind, M. and Carretero, J. and Cunha, C. E. and D’Andrea, C. B. and da Costa, L. N. and Davis, C. and De Vicente, J. and Doel, P. and Evrard, A. E. and Fosalba, P. and Frieman, J. and García-Bellido, J. and Gaztanaga, E. and Gerdes, D. W. and Gruen, D. and Gruendl, R. A. and Gschwend, J. and Gutierrez, G. and Hartley, W. G. and Hollowood, D. L. and Honscheid, K. and Hoyle, B. and James, D. J. and Kuehn, K. and Kuropatkin, N. and Lahav, O. and Maia, M. A. G. and March, M. and Melchior, P. and Menanteau, F. and Miquel, R. and Nord, B. and Plazas, A. A. and Sanchez, E. and Scarpine, V. and Schindler, R. and Schubnell, M. and Smith, M. and Smith, R. C. and Soares-Santos, M. and Sobreira, F. and Suchyta, E. and Swanson, M. E. C. and Tarle, G. and Thomas, D. and Walker, A. R. and Zuntz, J.},
abstractNote = {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 data set, 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 ~5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy (~90 percent), but small completeness and purity values. A fast domain adaptation step, consisting of a further training with a small DES sample of galaxies (~500–300), is enough for obtaining an accuracy >95 percent and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular data set, 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.},
doi = {10.1093/mnras/sty3497},
journal = {Monthly Notices of the Royal Astronomical Society},
number = 1,
volume = 484,
place = {United Kingdom},
year = {Fri Dec 28 00:00:00 EST 2018},
month = {Fri Dec 28 00:00:00 EST 2018}
}
https://doi.org/10.1093/mnras/sty3497
Web of Science
Works referenced in this record:
The Dark Energy Survey: more than dark energy – an overview
journal, March 2016
- Abbott, T.; Abdalla, F. B.; Aleksic, J.
- Monthly Notices of the Royal Astronomical Society, Vol. 460, Issue 2, p. 1270-1299
P-MaNGA Galaxies: emission-lines properties – gas ionization and chemical abundances from prototype observations
journal, March 2015
- Belfiore, F.; Maiolino, R.; Bundy, K.
- Monthly Notices of the Royal Astronomical Society, Vol. 449, Issue 1
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
Galaxies, Human Eyes, and Artificial Neural Networks
journal, February 1995
- Lahav, O.; Naim, A.; Buta, R. J.
- Science, Vol. 267, Issue 5199
A catalogue of two-dimensional photometric decompositions in the SDSS-DR7 spectroscopic main galaxy sample: extension to g and i bands
journal, November 2015
- Meert, Alan; Vikram, Vinu; Bernardi, Mariangela
- Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 3
The Relationship between Stellar Light Distributions of Galaxies and Their Formation Histories
journal, July 2003
- Conselice, Christopher J.
- The Astrophysical Journal Supplement Series, Vol. 147, Issue 1
Sdss-Iii: Massive Spectroscopic Surveys of the Distant Universe, the Milky way, and Extra-Solar Planetary Systems
journal, August 2011
- Eisenstein, Daniel J.; Weinberg, David H.; Agol, Eric
- The Astronomical Journal, Vol. 142, Issue 3
The long Lives of Giant Clumps and the Birth of Outflows in Gas-Rich Galaxies at high Redshift
journal, December 2013
- Bournaud, Frédéric; Perret, Valentin; Renaud, Florent
- The Astrophysical Journal, Vol. 780, Issue 1
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
journal, May 2016
- Tajbakhsh, Nima; Shin, Jae Y.; Gurudu, Suryakanth R.
- IEEE Transactions on Medical Imaging, Vol. 35, Issue 5
The Cluster Lensing and Supernova Survey with Hubble: an Overview
journal, March 2012
- Postman, Marc; Coe, Dan; Benítez, Narciso
- The Astrophysical Journal Supplement Series, Vol. 199, Issue 2
A catalogue of 2D photometric decompositions in the SDSS-DR7 spectroscopic main galaxy sample: preferred models and systematics
journal, December 2014
- Meert, Alan; Vikram, Vinu; Bernardi, Mariangela
- Monthly Notices of the Royal Astronomical Society, Vol. 446, Issue 4
Galaxy Zoo: reproducing galaxy morphologies via machine learning★: Galaxy Zoo: morphology via machine learning
journal, April 2010
- Banerji, Manda; Lahav, Ofer; Lintott, Chris J.
- Monthly Notices of the Royal Astronomical Society, Vol. 406, Issue 1
The Cosmic Evolution Survey (COSMOS): Overview
journal, September 2007
- Scoville, N.; Aussel, H.; Brusa, M.
- The Astrophysical Journal Supplement Series, Vol. 172, Issue 1
The Horizon-AGN simulation: morphological diversity of galaxies promoted by AGN feedback
journal, September 2016
- Dubois, Yohan; Peirani, Sébastien; Pichon, Christophe
- Monthly Notices of the Royal Astronomical Society, Vol. 463, Issue 4
The dark Energy Camera
journal, October 2015
- Flaugher, B.; Diehl, H. T.; Honscheid, K.
- The Astronomical Journal, Vol. 150, Issue 5
Improving galaxy morphologies for SDSS with Deep Learning
journal, February 2018
- Domínguez Sánchez, H.; Huertas-Company, M.; Bernardi, M.
- Monthly Notices of the Royal Astronomical Society, Vol. 476, Issue 3
Dark Energy Survey Year 1 Results: The Photometric Data Set for Cosmology
journal, April 2018
- Drlica-Wagner, A.; Sevilla-Noarbe, I.; Rykoff, E. S.
- The Astrophysical Journal Supplement Series, Vol. 235, Issue 2
The Seventh data Release of the Sloan Digital sky Survey
journal, May 2009
- Abazajian, Kevork N.; Adelman-McCarthy, Jennifer K.; Agüeros, Marcel A.
- The Astrophysical Journal Supplement Series, Vol. 182, Issue 2
The Deep2 Galaxy Redshift Survey: Design, Observations, data Reduction, and Redshifts
journal, August 2013
- Newman, Jeffrey A.; Cooper, Michael C.; Davis, Marc
- The Astrophysical Journal Supplement Series, Vol. 208, Issue 1
A Catalog of Visual-Like Morphologies in the 5 Candels Fields Using deep Learning
journal, October 2015
- Huertas-Company, M.; Gravet, R.; Cabrera-Vives, G.
- The Astrophysical Journal Supplement Series, Vol. 221, Issue 1
The importance of minor-merger-driven star formation and black hole growth in disc galaxies
journal, April 2014
- Kaviraj, Sugata
- Monthly Notices of the Royal Astronomical Society, Vol. 440, Issue 4
A Catalog of Detailed Visual Morphological Classifications for 14,034 Galaxies in the Sloan Digital sky Survey
journal, February 2010
- Nair, Preethi B.; Abraham, Roberto G.
- The Astrophysical Journal Supplement Series, Vol. 186, Issue 2
Deep learning for galaxy surface brightness profile fitting
journal, December 2017
- Tuccillo, D.; Huertas-Company, M.; Decencière, E.
- Monthly Notices of the Royal Astronomical Society, Vol. 475, Issue 1
Detailed Structural Decomposition of Galaxy Images
journal, July 2002
- Peng, Chien Y.; Ho, Luis C.; Impey, Chris D.
- The Astronomical Journal, Vol. 124, Issue 1
Candels: the Cosmic Assembly Near-Infrared deep Extragalactic Legacy Survey
journal, December 2011
- Grogin, Norman A.; Kocevski, Dale D.; Faber, S. M.
- The Astrophysical Journal Supplement Series, Vol. 197, Issue 2
Neural computation as a tool for galaxy classification: methods and examples
journal, October 1996
- Lahav, O.; Nairn, A.; Sodre, L.
- Monthly Notices of the Royal Astronomical Society, Vol. 283, Issue 1
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
Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey
journal, September 2013
- Willett, Kyle W.; Lintott, Chris J.; Bamford, Steven P.
- Monthly Notices of the Royal Astronomical Society, Vol. 435, Issue 4
Using transfer learning to detect galaxy mergers
journal, May 2018
- Ackermann, Sandro; Schawinski, Kevin; Zhang, Ce
- Monthly Notices of the Royal Astronomical Society, Vol. 479, Issue 1