CoChat

An automatic taxonomy of galaxy morphology using unsupervised machine learning

Open access
Hocking, Alex, Geach, James E., Sun, Yi, Davey, Neil · 2018 · Monthly Notices of the Royal Astronomical Society
Cited by 90

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Abstract

We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1−2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an ‘early’ or ‘late’ type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/mnras/stx2351

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 10 references

Research works printed but not linked: 63

  1. 2003, ApJ, 588, 218, 10.1086/373919 · DOI · Paper page
  2. 2012, MNRAS, 420, 1167, 10.1111/j.1365-2966.2011.20107.x · DOI
  3. 2010, MNRAS, 406, 342, 10.1111/j.1365-2966.2010.16713.x · DOI · Paper page
  4. 2012, MNRAS, 422, 449, 10.1111/j.1365-2966.2012.20619.x · DOI · Paper page
  5. 2016, MNRAS, 465, 4530
  6. 2013, IEEE Trans. Pattern Anal. Mach. Intell., 35, 1798, 10.1109/TPAMI.2013.50 · DOI · Paper page
  7. 2012, ASP Conf. Ser. Vol. 461, Astronomical Data Analysis Software and Systems XXI, 263
  8. 2010, MNRAS, 405, 987
  9. 2008, ApJ, 686, 1503, 10.1086/591786 · DOI · Paper page
  10. 2013, ApJ, 772, 140, 10.1088/0004-637X/772/2/140 · DOI
  11. 2014, MNRAS, 438, 3409, 10.1093/mnras/stt2456 · DOI
  12. 2012, A&A, 546, A13, 10.1051/0004-6361/201219755 · DOI · Paper page
  13. 2004, Comput. Vis. Image Underst., 93, 206, 10.1016/j.cviu.2003.09.002 · DOI
  14. 2004, PASP, 116, 345, 10.1086/383254 · DOI · Paper page
  15. 2012, ApJ, 755, 92, 10.1088/0004-637X/755/2/92 · DOI
  16. 2014, ApJ, 790, 87, 10.1088/0004-637X/790/2/87 · DOI
  17. 1996, Theor. Comput. Sci., 154, 165, 10.1016/0304-3975(94)00262-2 · doi:10.1016/0304-3975(94)00262-2
  18. 2003, MNRAS, 339, 1195, 10.1046/j.1365-8711.2003.06271.x · DOI · Paper page
  19. 2013, Neurocomputing, 72
  20. 1995, Adv. Neural Inf. Process. Syst., 7, 625
  21. 2013, A&A, A7
  22. 2012, MNRAS, 419, 2633, 10.1111/j.1365-2966.2011.19913.x · DOI · Paper page
  23. 2014, Advances in Neural Information Processing Systems 27, Curran Associates, Inc., 2672
  24. 2011, ApJS, 197, 35, 10.1088/0067-0049/197/2/35 · DOI · Paper page
  25. 2009, The Elements of Statistical Learning: Data Mining, Inference, and Prediction
  26. 2013, MNRAS, 430, 330, 10.1093/mnras/sts633 · DOI · Paper page
  27. 2008, IEEE Trans. Image Process., 17, 749, 10.1109/TIP.2008.919369 · DOI · Paper page
  28. 2016, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770
  29. 2017, International Joint Conference on Neural Networks (IJCNN). IEEE, New York, p. 4179
  30. 1976, Phys. Rev. B, 14, 3438, 10.1103/PhysRevB.14.3438 · DOI · Paper page
  31. 2008, A&A, 478, 971, 10.1051/0004-6361:20078625 · DOI · Paper page
  32. 2009, A&A, 497, 743, 10.1051/0004-6361/200811255 · DOI · Paper page
  33. 2011, A&A, 525, A157, 10.1051/0004-6361/201015735 · DOI · Paper page
  34. 2012, A&A, 547, A115, 10.1051/0004-6361/201219958 · DOI
  35. 2011, J. Parallel Distrib. Comput., 71, 615, 10.1016/j.jpdc.2010.10.012 · doi:10.1016/j.jpdc.2010.10.012
  36. 1993, A&A, 276, 309
  37. 2011, ApJS, 197, 36, 10.1088/0067-0049/197/2/36 · DOI · Paper page
  38. 2012, Advances in Neural Information Processing Systems 25 (NIPS 2012), 1097
  39. 2016, ApJS, 223, 20, 10.3847/0067-0049/223/2/20 · DOI
  40. 1995, Science, 267, 859, 10.1126/science.267.5199.859 · DOI · Paper page
  41. 2011, MNRAS, 410, 166, 10.1111/j.1365-2966.2010.17432.x · DOI · Paper page
  42. 2004, AJ, 128, 163, 10.1086/421849 · DOI · Paper page
  43. 2014, Neurocomputing, 328
  44. 2015, ApJ, 798, 122, 10.1088/0004-637X/798/2/122 · DOI
  45. 1994, American Astronomical Society Meeting Abstracts, 107.09
  46. 1995, PASP, 107, 770, 10.1086/133622 · doi:10.1086/133622
  47. 2002, AJ, 124, 266, 10.1086/340952 · DOI · Paper page
  48. 2016, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779
  49. 2016, Advances in Neural Networks, 27
  50. 2015, Astron. Comput., 12, 60, 10.1016/j.ascom.2015.05.002 · DOI · Paper page
  51. 2010, Proceedings of the 19th International Conference on World Wide Web, 1177, 10.1145/1772690.1772862 · DOI · Paper page
  52. 2011, ApJ, 736, 141, 10.1088/0004-637X/736/2/141 · DOI
  53. 2012, J. Comput. Sci., 3, 181, 10.1016/j.jocs.2012.03.004 · DOI
  54. 2014, MNRAS, 443, 3528, 10.1093/mnras/stu1429 · DOI
  55. 2013, Astron. Comput., 2, 67, 10.1016/j.ascom.2013.09.002 · DOI
  56. 1998, ASP Conf. Ser. Vol. 145, Astronomical Data Analysis Software and Systems VII, 108
  57. 2017, MNRAS, 464, 4420, 10.1093/mnras/stw2587 · DOI · Paper page
  58. 2014, ApJS, 214, 24, 10.1088/0067-0049/214/2/24 · DOI · Paper page
  59. 2012, ApJS, 203, 24, 10.1088/0067-0049/203/2/24 · DOI · Paper page
  60. 2010, J. Mach. Learn. Res., 11, 3371
  61. 2012, PASP, 124, 274, 10.1086/664796 · DOI
  62. 2015, MNRAS, 449, 451, 10.1093/mnras/stv292 · DOI · Paper page
  63. 2009, Pattern Anal. Appl., 12, 117, 10.1007/s10044-008-0109-y · DOI

Cited by

See all 90

Metadata

Authors
Hocking, A., Geach, J. E., Sun, Y., & Davey, N.
Venue
Monthly Notices of the Royal Astronomical Society
Published
2017-09-15
Volume
473
Issue
1
Pages
1108-1129
ISSN
  • 0035-8711 (ISSN-L)
  • 1365-2966
OpenAlex
W2755925698
Cited by
90
References
10
FWCI
5.04
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: An automatic taxonomy of galaxy morphology using unsupervised machine learning. https://app.cochat.ai/papers/10.1093/mnras/stx2351
The paper
Hocking, A., Geach, J. E., Sun, Y., & Davey, N. (2018). An automatic taxonomy of galaxy morphology using unsupervised machine learning. Monthly Notices of the Royal Astronomical Society. https://doi.org/10.1093/mnras/stx2351

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.