skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey

Abstract

ABSTRACT We present the results of a proof-of-concept experiment that demonstrates that deep learning can successfully be used for production-scale classification of compact star clusters detected in Hubble Space Telescope(HST) ultraviolet-optical imaging of nearby spiral galaxies ($$D\lesssim 20\, \textrm{Mpc}$$) in the Physics at High Angular Resolution in Nearby GalaxieS (PHANGS)–HST survey. Given the relatively small nature of existing, human-labelled star cluster samples, we transfer the knowledge of state-of-the-art neural network models for real-object recognition to classify star clusters candidates into four morphological classes. We perform a series of experiments to determine the dependence of classification performance on neural network architecture (ResNet18 and VGG19-BN), training data sets curated by either a single expert or three astronomers, and the size of the images used for training. We find that the overall classification accuracies are not significantly affected by these choices. The networks are used to classify star cluster candidates in the PHANGS–HST galaxy NGC 1559, which was not included in the training samples. The resulting prediction accuracies are 70 per cent, 40 per cent, 40–50 per cent, and 50–70 per cent for class 1, 2, 3 star clusters, and class 4 non-clusters, respectively. This performance is competitive with consistency achieved in previously published human and automated quantitative classification of star cluster candidate samples (70–80 per cent, 40–50 per cent, 40–50 per cent, and 60–70 per cent). The methods introduced herein lay the foundations to automate classification for star clusters at scale, and exhibit the need to prepare a standardized data set of human-labelled star cluster classifications, agreed upon by a full range of experts in the field, to further improve the performance of the networks introduced in this study.

Authors:
 [1];  [2];  [3];  [4]; ORCiD logo [5];  [6];  [7];  [4]; ORCiD logo [8];  [3];  [9];  [10]; ORCiD logo [10];  [11];  [12]; ORCiD logo [13]
  1. NCSA, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA, Department of Physics, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
  2. NCSA, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA, Department of Astronomy, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
  3. Space Telescope Science Institute, 3700 San Martin Drive, Baltimore, MD 21218, USA
  4. Caltech/IPAC, California Institute of Technology, Pasadena, CA 91125, USA
  5. Department of Physics and Astronomy, University of California, Riverside, CA 92507, USA
  6. Department of Physics and Astronomy, University of Toledo, Toledo, OH 43606, USA
  7. Department of Physics and Astronomy, University of Wyoming, Laramie, WY 82071, USA
  8. Department of Physics and Astronomy, The Johns Hopkins University, Baltimore, MD 21218, USA
  9. Centro de Astronomía, Universidad de Antofagasta, Avenida Angamos 601, Antofagasta 1270300, Chile
  10. Astronomisches Rechen-Institut, Zentrum für Astronomie der Universität Heidelberg, Grabengasse 1, D-69117 Heidelberg, Germany
  11. Max-Planck-Institut für extraterrestrische Physik, Giessenbachstrasse 1, D-85748 Garching, Germany
  12. Observatories of the Carnegie Institution for Science, Pasadena, CA 91101, USA, Departamento de Astronomía, Universidad de Chile, Casilla 36-D, Santiago, Chile
  13. Observatories of the Carnegie Institution for Science, Pasadena, CA 91101, USA, Las Campanas Observatory, Colina El Pino, Casilla 601, La Serena, Chile
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1604098
Grant/Contract Number:  
[AC02-06CH11357]
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: 493 Journal Issue: 3]; Journal ID: ISSN 0035-8711
Publisher:
Oxford University Press
Country of Publication:
United Kingdom
Language:
English

Citation Formats

Wei, Wei, Huerta, E. A., Whitmore, Bradley C., Lee, Janice C., Hannon, Stephen, Chandar, Rupali, Dale, Daniel A., Larson, Kirsten L., Thilker, David A., Ubeda, Leonardo, Boquien, Médéric, Chevance, Mélanie, Diederik Kruijssen, J. M., Schruba, Andreas, Blanc, Guillermo A., and Congiu, Enrico. Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey. United Kingdom: N. p., 2020. Web. doi:10.1093/mnras/staa325.
Wei, Wei, Huerta, E. A., Whitmore, Bradley C., Lee, Janice C., Hannon, Stephen, Chandar, Rupali, Dale, Daniel A., Larson, Kirsten L., Thilker, David A., Ubeda, Leonardo, Boquien, Médéric, Chevance, Mélanie, Diederik Kruijssen, J. M., Schruba, Andreas, Blanc, Guillermo A., & Congiu, Enrico. Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey. United Kingdom. doi:10.1093/mnras/staa325.
Wei, Wei, Huerta, E. A., Whitmore, Bradley C., Lee, Janice C., Hannon, Stephen, Chandar, Rupali, Dale, Daniel A., Larson, Kirsten L., Thilker, David A., Ubeda, Leonardo, Boquien, Médéric, Chevance, Mélanie, Diederik Kruijssen, J. M., Schruba, Andreas, Blanc, Guillermo A., and Congiu, Enrico. Tue . "Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey". United Kingdom. doi:10.1093/mnras/staa325.
@article{osti_1604098,
title = {Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey},
author = {Wei, Wei and Huerta, E. A. and Whitmore, Bradley C. and Lee, Janice C. and Hannon, Stephen and Chandar, Rupali and Dale, Daniel A. and Larson, Kirsten L. and Thilker, David A. and Ubeda, Leonardo and Boquien, Médéric and Chevance, Mélanie and Diederik Kruijssen, J. M. and Schruba, Andreas and Blanc, Guillermo A. and Congiu, Enrico},
abstractNote = {ABSTRACT We present the results of a proof-of-concept experiment that demonstrates that deep learning can successfully be used for production-scale classification of compact star clusters detected in Hubble Space Telescope(HST) ultraviolet-optical imaging of nearby spiral galaxies ($D\lesssim 20\, \textrm{Mpc}$) in the Physics at High Angular Resolution in Nearby GalaxieS (PHANGS)–HST survey. Given the relatively small nature of existing, human-labelled star cluster samples, we transfer the knowledge of state-of-the-art neural network models for real-object recognition to classify star clusters candidates into four morphological classes. We perform a series of experiments to determine the dependence of classification performance on neural network architecture (ResNet18 and VGG19-BN), training data sets curated by either a single expert or three astronomers, and the size of the images used for training. We find that the overall classification accuracies are not significantly affected by these choices. The networks are used to classify star cluster candidates in the PHANGS–HST galaxy NGC 1559, which was not included in the training samples. The resulting prediction accuracies are 70 per cent, 40 per cent, 40–50 per cent, and 50–70 per cent for class 1, 2, 3 star clusters, and class 4 non-clusters, respectively. This performance is competitive with consistency achieved in previously published human and automated quantitative classification of star cluster candidate samples (70–80 per cent, 40–50 per cent, 40–50 per cent, and 60–70 per cent). The methods introduced herein lay the foundations to automate classification for star clusters at scale, and exhibit the need to prepare a standardized data set of human-labelled star cluster classifications, agreed upon by a full range of experts in the field, to further improve the performance of the networks introduced in this study.},
doi = {10.1093/mnras/staa325},
journal = {Monthly Notices of the Royal Astronomical Society},
number = [3],
volume = [493],
place = {United Kingdom},
year = {2020},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: 10.1093/mnras/staa325

Save / Share:

Works referenced in this record:

Phase control of a path-entangled photon state by a deformable membrane mirror
conference, January 2011

  • Bonato, Cristian; Bonora, Stefano; Chiuri, Andrea
  • QUANTUM COMMUNICATION, MEASUREMENT AND COMPUTING (QCMC): The Tenth International Conference, AIP Conference Proceedings
  • DOI: 10.1063/1.3630139

The Luminosity Function of Star Clusters in Spiral Galaxies
journal, September 2002

  • Larsen, Søren S.
  • The Astronomical Journal, Vol. 124, Issue 3
  • DOI: 10.1086/342381

A Mathematical Theory of Communication
journal, July 1948


Alma Observations of the Antennae Galaxies. i. a new Window on a Prototypical Merger
journal, October 2014


TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests
journal, May 2013

  • Carrasco Kind, Matias; Brunner, Robert J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 432, Issue 2
  • DOI: 10.1093/mnras/stt574

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
  • DOI: 10.1093/mnras/stv632

LEGACY EXTRAGALACTIC UV SURVEY (LEGUS) WITH THE HUBBLE SPACE TELESCOPE . I. SURVEY DESCRIPTION
journal, January 2015


STAR-CLUSTER MASS AND AGE DISTRIBUTIONS OF TWO FIELDS IN M83 BASED ON HST /WFC3 OBSERVATIONS
journal, April 2014

  • Chandar, Rupali; Whitmore, Bradley C.; Calzetti, Daniela
  • The Astrophysical Journal, Vol. 787, Issue 1
  • DOI: 10.1088/0004-637X/787/1/17

The young star cluster population of M51 with LEGUS – I. A comprehensive study of cluster formation and evolution
journal, September 2017

  • Messa, M.; Adamo, A.; Östlin, G.
  • Monthly Notices of the Royal Astronomical Society, Vol. 473, Issue 1
  • DOI: 10.1093/mnras/stx2403

SExtractor: Software for source extraction
journal, June 1996

  • Bertin, E.; Arnouts, S.
  • Astronomy and Astrophysics Supplement Series, Vol. 117, Issue 2
  • DOI: 10.1051/aas:1996164

Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

Machine learning and cosmological simulations – I. Semi-analytical models
journal, November 2015

  • Kamdar, Harshil M.; Turk, Matthew J.; Brunner, Robert J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 1
  • DOI: 10.1093/mnras/stv2310

Robust Machine Learning Applied to Astronomical Data Sets. III. Probabilistic Photometric Redshifts for Galaxies and Quasars in the SDSS and GALEX
journal, August 2008

  • Ball, Nicholas M.; Brunner, Robert J.; Myers, Adam D.
  • The Astrophysical Journal, Vol. 683, Issue 1
  • DOI: 10.1086/589646

Hubble Space Telescope Observations of Candidate Young Globular Clusters and Stellar Associations in the Recent Merger Remnant NGC 3921
journal, November 1996

  • Schweizer, Francois; Miller, Bryan W.; Whitmore, Bradley C.
  • The Astronomical Journal, Vol. 112
  • DOI: 10.1086/118146

The spatial relation between young star clusters and molecular clouds in M51 with LEGUS
journal, December 2018

  • Grasha, K.; Calzetti, D.; Adamo, A.
  • Monthly Notices of the Royal Astronomical Society, Vol. 483, Issue 4
  • DOI: 10.1093/mnras/sty3424

Planetary Camera observations of NGC 1275 - Discovery of a central population of compact massive blue star clusters
journal, March 1992

  • Holtzman, J. A.; Faber, S. M.; Shaya, E. J.
  • The Astronomical Journal, Vol. 103
  • DOI: 10.1086/116094

Automated Star/Galaxy Classification for Digitized Poss-II
journal, June 1995

  • Weir, Nicholas; Fayyad, Usama M.; Djorgovski, S.
  • The Astronomical Journal, Vol. 109
  • DOI: 10.1086/117459

A Census of Object Types and Redshift Estimates in the SDSS Photometric Catalog from a Trained Decision Tree Classifier
journal, December 2005

  • Suchkov, A. A.; Hanisch, R. J.; Margon, Bruce
  • The Astronomical Journal, Vol. 130, Issue 6
  • DOI: 10.1086/497363

Galaxy Zoo: reproducing galaxy morphologies via machine learning★: Galaxy Zoo: morphology via machine learning
journal, April 2010


ImageNet Large Scale Visual Recognition Challenge
journal, April 2015

  • Russakovsky, Olga; Deng, Jia; Su, Hao
  • International Journal of Computer Vision, Vol. 115, Issue 3
  • DOI: 10.1007/s11263-015-0816-y

THE SNAPSHOT HUBBLE U -BAND CLUSTER SURVEY (SHUCS). II. THE STAR CLUSTER POPULATION OF NGC 2997
journal, July 2014


Star-Galaxy Classification in Multi-Band Optical Imaging
journal, October 2012


Stellar clusters in M83: formation, evolution, disruption and the influence of the environment: M83 stellar cluster population
journal, November 2011


The Pascal Visual Object Classes Challenge: A Retrospective
journal, June 2014

  • Everingham, Mark; Eslami, S. M. Ali; Van Gool, Luc
  • International Journal of Computer Vision, Vol. 111, Issue 1
  • DOI: 10.1007/s11263-014-0733-5

Automated novelty detection in the WISE survey with one-class support vector machines
journal, October 2017


Young massive star clusters in nearby galaxies: II. Software tools, data reductions and cluster sizes
journal, October 1999

  • Larsen, S. S.
  • Astronomy and Astrophysics Supplement Series, Vol. 139, Issue 2
  • DOI: 10.1051/aas:1999509

Effect of training characteristics on object classification: An application using Boosted Decision Trees
journal, June 2015


Unbound Young Stellar Systems: Star Formation on the Loose
journal, June 2018

  • Gouliermis, Dimitrios A.
  • Publications of the Astronomical Society of the Pacific, Vol. 130, Issue 989
  • DOI: 10.1088/1538-3873/aac1fd

Deep learning at scale for the construction of galaxy catalogs in the Dark Energy Survey
journal, August 2019


[ITAL]Hubble Space Telescope[/ITAL] Observations of Globular Clusters in M87 and an Estimate of [ITAL]H[/ITAL][TINF]0[/TINF]
journal, December 1995

  • Whitmore,, Bradley C.; Sparks, William B.; Lucas, Ray A.
  • The Astrophysical Journal, Vol. 454, Issue 2
  • DOI: 10.1086/309788

Robust Machine Learning Applied to Astronomical Data Sets. I. Star‐Galaxy Classification of the Sloan Digital Sky Survey DR3 Using Decision Trees
journal, October 2006

  • Ball, Nicholas M.; Brunner, Robert J.; Myers, Adam D.
  • The Astrophysical Journal, Vol. 650, Issue 1
  • DOI: 10.1086/507440

Effective Radii of Young, Massive Star Clusters in Two LEGUS Galaxies
journal, May 2017

  • Ryon, J. E.; Gallagher, J. S.; Smith, L. J.
  • The Astrophysical Journal, Vol. 841, Issue 2
  • DOI: 10.3847/1538-4357/aa719e

Version 1 of the Hubble Source Catalog
journal, May 2016

  • Whitmore, Bradley C.; Allam, Sahar S.; Budavári, Tamás
  • The Astronomical Journal, Vol. 151, Issue 6
  • DOI: 10.3847/0004-6256/151/6/134

Extragalactic nebulae.
journal, October 1926

  • Hubble, E. P.
  • The Astrophysical Journal, Vol. 64
  • DOI: 10.1086/143018

THE LUMINOSITY, MASS, AND AGE DISTRIBUTIONS OF COMPACT STAR CLUSTERS IN M83 BASED ON HUBBLE SPACE TELESCOPE /WIDE FIELD CAMERA 3 OBSERVATIONS
journal, July 2010


Revised Classification of 1500 Bright Galaxies.
journal, April 1963

  • de Vaucouleurs, G.
  • The Astrophysical Journal Supplement Series, Vol. 8
  • DOI: 10.1086/190084

Decision tree Classifiers for Star/Galaxy Separation
journal, May 2011


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
  • DOI: 10.1093/mnras/stt1458

The age, Mass, and size Distributions of star Clusters in m51
journal, June 2016

  • Chandar, Rupali; Whitmore, Bradley C.; Dinino, Daiana
  • The Astrophysical Journal, Vol. 824, Issue 2
  • DOI: 10.3847/0004-637X/824/2/71

Star cluster catalogues for the LEGUS dwarf galaxies
journal, February 2019

  • Cook, D. O.; Lee, J. C.; Adamo, A.
  • Monthly Notices of the Royal Astronomical Society, Vol. 484, Issue 4
  • DOI: 10.1093/mnras/stz331

Young Massive Star Clusters
journal, August 2010


The Brightest Young star Clusters in ngc 5253
journal, September 2015


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
  • DOI: 10.1093/mnras/sty1398

Star–galaxy classification using deep convolutional neural networks
journal, October 2016

  • Kim, Edward J.; Brunner, Robert J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 464, Issue 4
  • DOI: 10.1093/mnras/stw2672