Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Galaxy morphology is a fundamental quantity, which is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology (e.g. as a prior for photometric-redshift measurements and as contextual data for transient light-curve classifications). While a rich literature exists on morphological-classification techniques, the unprecedented data volumes, coupled, in some cases, with the short cadences of forthcoming ‘Big-Data’ surveys (e.g. from the LSST), present novel challenges for this field. Large data volumes make such data sets intractable for visual inspection (even via massively distributed platforms like Galaxy Zoo), while short cadences make it difficult to employ techniques like supervised machine learning, since it may be impractical to repeatedly produce training sets on short time-scales. Unsupervised machine learning, which does not require training sets, is ideally suited to the morphological analysis of new and forthcoming surveys. Here, we employ an algorithm that performs clustering of graph representations, in order to group image patches with similar visual properties and objects constructed from those patches, like galaxies. We implement the algorithm on the Hyper-Suprime-Cam Subaru-Strategic-Program Ultra-Deep survey, to autonomously reduce the galaxy population to a small number (160) of ‘morphological clusters’, populated by galaxies with similar morphologies, which are then benchmarked using visual inspection. The morphological classifications (which we release publicly) exhibit a high level of purity, and reproduce known trends in key galaxy properties as a function of morphological type at z < 1 (e.g. stellar-mass functions, rest-frame colours, and the position of galaxies on the star-formation main sequence). Our study demonstrates the power of unsupervised machine learning in performing accurate morphological analysis, which will become indispensable in this new era of deep-wide surveys.
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.
Integrity signals
Registry
Cites
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.
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
The Hyper Suprime-Cam SSP Survey: Overview and survey design
Aihara, H., Arimoto, N., Armstrong, R., Arnouts, S., Bahcall, N. A., Bickerton, S., Bosch, J., Bundy, K., Capak, P. L., Chan, J. H. H., et al. (2018) · Publications of the Astronomical Society of Japan · doi:10.1093/pasj/psx066 · Cited by 1,087 · cited 19×
“In Section 3, we outline the properties of the HSC-SSP and the ancillary data used in this study.”
BackgroundMethodInfluentialThe Relationship between Stellar Light Distributions of Galaxies and Their Formation Histories
Conselice, C. J. (2003) · The Astrophysical Journal Supplement Series · doi:10.1086/375001 · Cited by 875 · cited 1×
“…& Gunn 2012), to non-parametric methods that reduce these light distributions to single values such as in the ‘CAS’ system (e.g. Abraham et al. 1994; Conselice 2003; Menanteau et al. 2006), the Gini-M20 coefficients (e.g. Lotz et al. 2004; Scarlata et al. 2007; Peth et al. 2016) or other…”
MethodRotation-invariant convolutional neural networks for galaxy morphology prediction
Dieleman, S., Willett, K. W., & Dambre, J. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv632 · Cited by 781
A CATALOG OF VISUAL-LIKE MORPHOLOGIES IN THE 5 CANDELS FIELDS USING DEEP LEARNING
Huertas-Company, M., Gravet, R., Cabrera-Vives, G., Pérez-González, P. G., Kartaltepe, J. S., Barro, G., Bernardi, M., Mei, S., Shankar, F., Dimauro, P., et al. (2015) · The Astrophysical Journal Supplement Series · doi:10.1088/0067-0049/221/1/8 · Cited by 285
Schawinski, K., Zhang, C., Zhang, H., Fowler, L., & Santhanam, G. K. (2017) · Monthly Notices of the Royal Astronomical Society: Letters · doi:10.1093/mnrasl/slx008 · Cited by 246 · cited 1×
“…in the use of such techniques applied to a wide variety of problems in astrophysics (e.g. Huertas-Company et al. 2015a; Ostrovski et al. 2017; Schawinski et al. 2017; Hocking et al. 2018; Goulding et al. 2018; D’Isanto & Polsterer 2018; Siudek et al. 2018; An et al. 2018; Cheng et al. 2019;…”
MethodWalmsley, M., Ferguson, A. M. N., Mann, R. G., & Lintott, C. J. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty3232 · Cited by 66 · cited 1×
“…those that exploit machine-learning, have been routinely benchmarked against visual classifications from databases like GZ, and are now commonly deployed on large-scale survey data (e.g. Huertas-Company et al. 2015a; Dieleman et al. 2015; Beck et al. 2018; Walmsley et al. 2019; Ma et al. 2019).”
Method
Research works printed but not linked: 108
- Abraham, 1994, ApJ, 432, 75, 10.1086/174550 · DOI · Paper page
- Aihara, 2018, PASJ, 70, S8, 10.1093/pasj/psx081 · DOI · Paper page
- An, 2018, ApJ, 862, 101, 10.3847/1538-4357/aacdaa · DOI
- Ballard, 1982, Computer Vision
- Baum, 1959, PASJ, 71, 106, 10.1086/127346 · doi:10.1086/127346
- Beck, 2018, MNRAS, 476, 5516, 10.1093/mnras/sty503 · DOI · Paper page
- Bertin, 1996, A&AS, 117, 393, 10.1051/aas:1996164 · DOI · Paper page
- Birk, 1979, IEEE Trans. Pattern Anal. Mach. Intell., 235
- Bluck, 2014, MNRAS, 441, 599, 10.1093/mnras/stu594 · DOI · Paper page
- Bruzual, 2003, MNRAS, 344, 1000, 10.1046/j.1365-8711.2003.06897.x · DOI · Paper page
- Bundy, 2005, ApJ, 625, 621, 10.1086/429549 · DOI · Paper page
- Cerulo, 2017, MNRAS, 472, 254, 10.1093/mnras/stx1687 · doi:10.1093/mnras/stx1687
- Cheriyadat, 2013, IEEE Trans. Geosci. Remote Sens., 52, 439, 10.1109/TGRS.2013.2241444 · DOI · Paper page
- Coates, 2011, Proceedings of the fourteenth international conference on artificial intelligence and statistics, 215
- Codis, 2012, MNRAS, 427, 3320, 10.1111/j.1365-2966.2012.21636.x · DOI
- Conselice, 2006, MNRAS, 373, 1389, 10.1111/j.1365-2966.2006.11114.x · DOI · Paper page
- Conselice, 2008, MNRAS, 386, 909, 10.1111/j.1365-2966.2008.13069.x · DOI · Paper page
- Conselice, 2014, MNRAS, 444, 1125, 10.1093/mnras/stu1385 · DOI
- D'Isanto, 2018, A&A, 609, A111, 10.1051/0004-6361/201731326 · DOI · Paper page
- D'Isanto, 2018, A&A, 616, A97, 10.1051/0004-6361/201833103 · doi:10.1051/0004-6361/201833103
- Djorgovski, 2012, Proc. 2012 IEEE 8th International Conference on E-Science
- Dressler, 1980, ApJ, 236, 351, 10.1086/157753 · DOI · Paper page
- Dressler, 1997, ApJ, 490, 577, 10.1086/304890 · DOI · Paper page
- Edgeworth, 1888, J. R. Stat. Soc., 51, 346
- Eisenstein, 2001, AJ, 122, 2267, 10.1086/323717 · DOI · Paper page
- Eisenstein, 2011, AJ, 142, 72, 10.1088/0004-6256/142/3/72 · DOI · Paper page
- Fadely, 2012, ApJ, 760, 15, 10.1088/0004-637X/760/1/15 · DOI
- Freeman, 2013, MNRAS, 434, 282, 10.1093/mnras/stt1016 · DOI · Paper page
- Fritzke, 1995, Advances in Neural Information Processing Systems, 625
- Galler, 1964, Commun. ACM, 7, 301, 10.1145/364099.364331 · DOI
- Goulding, 2018, PASJ, 70, S37, 10.1093/pasj/psx135 · DOI · Paper page
- Hatton, 2003, MNRAS, 343, 75, 10.1046/j.1365-8711.2003.05589.x · DOI · Paper page
- Hendel, 2019, MNRAS, 486, 3604, 10.1093/mnras/stz1107 · DOI
- Henrion, 2011, MNRAS, 412, 2286, 10.1111/j.1365-2966.2010.18055.x · DOI
- Herlihy, 2011, Art of Multiprocessor Programming
- Hocking, 2017, 2017 International Joint Conference on Neural Networks (IJCNN), 4179, 10.1109/IJCNN.2017.7966384 · DOI
- Hocking, 2018, MNRAS, 473, 1108, 10.1093/mnras/stx2351 · DOI · Paper page
- Hubble, 1936, Realm of the Nebulae
- Huertas-Company, 2015, ApJ, 809, 95, 10.1088/0004-637X/809/1/95 · DOI
- Ilbert, 2010, ApJ, 709, 644, 10.1088/0004-637X/709/2/644 · DOI · Paper page
- Jaffé, 2011, MNRAS, 410, 280, 10.1111/j.1365-2966.2010.17445.x · DOI
- Jansen, 2001, A&A, 365, L1, 10.1051/0004-6361:20000036 · DOI · Paper page
- Jarvis, 2013, MNRAS, 428, 1281, 10.1093/mnras/sts118 · DOI · Paper page
- Johnson, 1967, Psychometrika, 32, 241, 10.1007/BF02289588 · DOI · Paper page
- Kaviraj, 2010, MNRAS, 406, 382, 10.1111/j.1365-2966.2010.16714.x · DOI
- Kaviraj, 2014, MNRAS, 437, L41, 10.1093/mnrasl/slt136 · DOI
- Kaviraj, 2014, MNRAS, 440, 2944, 10.1093/mnras/stu338 · DOI
- Kaviraj, 2019, MNRAS, 489, L12, 10.1093/mnrasl/slz102 · DOI · Paper page
- Kelvin, 2014, MNRAS, 444, 1647, 10.1093/mnras/stu1507 · DOI
- Khim, 2015, ApJS, 220, 3, 10.1088/0067-0049/220/1/3 · DOI
- Klein, 2006, Survival Analysis: Techniques for Censored and Truncated Data.
- Koekemoer, 2011, ApJS, 197, 36, 10.1088/0067-0049/197/2/36 · DOI · Paper page
- Kron, 1980, ApJS, 43, 305, 10.1086/190669 · DOI · Paper page
- Lackner, 2012, MNRAS, 421, 2277, 10.1111/j.1365-2966.2012.20450.x · DOI
- Lahav, 1995, Science, 267, 859, 10.1126/science.267.5199.859 · DOI · Paper page
- Lange, 2015, MNRAS, 447, 2603, 10.1093/mnras/stu2467 · DOI · Paper page
- Lawrence, 2007, MNRAS, 379, 1599, 10.1111/j.1365-2966.2007.12040.x · DOI · Paper page
- Lazebnik, 2005, IEEE Trans. Pattern Anal. Mach. Intell., 27, 1265, 10.1109/TPAMI.2005.151 · DOI · Paper page
- Lintott, 2011, MNRAS, 410, 166, 10.1111/j.1365-2966.2010.17432.x · DOI · Paper page
- López Fernández, 2018, A&A, 615, A27, 10.1051/0004-6361/201732358 · DOI
- Lotz, 2004, AJ, 128, 163, 10.1086/421849 · DOI · Paper page
- Ma, 2019, ApJS, 240, 34, 10.3847/1538-4365/aaf9a2 · DOI · Paper page
- MacQueen, 1967, Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, 281
- Malmquist, 1922, Meddelanden fran Lunds Astronomiska Observatorium Serie I, 100, 1
- Martin, 2018, MNRAS, 474, 3140, 10.1093/mnras/stx3057 · DOI
- Martin, 2018, MNRAS, 476, 2801, 10.1093/mnras/sty324 · DOI
- Martin, 2019, MNRAS, 485, 796, 10.1093/mnras/stz356 · DOI
- Menanteau, 2006, AJ, 131, 208, 10.1086/498344 · DOI
- Menou, 2019, MNRAS, 489, 4802, 10.1093/mnras/stz2477 · DOI
- Miyazaki, 2012, Proc. SPIE Conf. Ser., 84460Z, 10.1117/12.926844 · DOI · Paper page
- Moore, 1999, MNRAS, 304, 465, 10.1046/j.1365-8711.1999.02345.x · doi:10.1046/j.1365-8711.1999.02345.x
- Odewahn, 2002, ApJ, 568, 539, 10.1086/339036 · DOI
- Oh, 2019, MNRAS, 488, 4169, 10.1093/mnras/stz1920 · DOI
- Okabe, 2009, Spatial Tessellations: Concepts and Applications of Voronoi Diagrams, vol. 501
- Ostrovski, 2017, MNRAS, 465, 4325, 10.1093/mnras/stw2958 · DOI · Paper page
- Peirani, 2010, MNRAS, 405, 2327, 10.1111/j.1365-2966.2010.16666.x · DOI
- Peth, 2016, MNRAS, 458, 963, 10.1093/mnras/stw252 · DOI · Paper page
- Pogge, 1993, AJ, 106, 1405, 10.1086/116735 · DOI
- Postman, 2005, ApJ, 623, 721, 10.1086/428881 · DOI · Paper page
- Rajaraman, 2011, Mining of Massive Data sets, 10.1017/CBO9781139058452 · DOI · Paper page
- Robitaille, 2013, A&A, 558, A33, 10.1051/0004-6361/201322068 · DOI · Paper page
- Rousseeuw, 1987, J. Comput. Appl. Math., 20, 53, 10.1016/0377-0427(87)90125-7 · DOI · Paper page
- Scarlata, 2007, ApJS, 172, 406, 10.1086/516582 · DOI · Paper page
- Schawinski, 2014, MNRAS, 440, 889, 10.1093/mnras/stu327 · DOI · Paper page
- Schmidt, 1968, ApJ, 151, 393, 10.1086/149446 · DOI · Paper page
- Sérsic, 1963, Boletin de la Asociacion Argentina de Astronomia La Plata Argentina, 6, 41
- Simard, 2002, ApJS, 142, 1, 10.1086/341399 · DOI · Paper page
- Simmons, 2017, MNRAS, 464, 4420, 10.1093/mnras/stw2587 · DOI · Paper page
- Siudek, 2018, A&A, 617, A70, 10.1051/0004-6361/201832784 · DOI
- Skibba, 2009, MNRAS, 399, 966, 10.1111/j.1365-2966.2009.15334.x · DOI · Paper page
- Smethurst, 2015, MNRAS, 450, 435, 10.1093/mnras/stv161 · DOI
- Soo, 2018, MNRAS, 475, 3613, 10.1093/mnras/stx3201 · DOI
- Soumagnac, 2015, MNRAS, 450, 666, 10.1093/mnras/stu1410 · DOI
- Stoughton, 2002, AJ, 123, 485, 10.1086/324741 · DOI · Paper page
- Strateva, 2001, AJ, 122, 1861, 10.1086/323301 · DOI · Paper page
- Tanaka, 2015, ApJ, 801, 20, 10.1088/0004-637X/801/1/20 · DOI · Paper page
- Tanaka, 2018, PASJ, 70, S9, 10.1093/pasj/psx077 · DOI · Paper page
- Tao, 2015, IEEE Geosci. Remote Sens. Lett., 12, 2438, 10.1109/LGRS.2015.2482520 · DOI · Paper page
- Thronson, 1989, AJ, 97, 363, 10.1086/114987 · DOI
- Tomczak, 2014, ApJ, 783, 85, 10.1088/0004-637X/783/2/85 · DOI · Paper page
- Vika, 2015, A&A, 577, A97, 10.1051/0004-6361/201425174 · DOI
- Visvanathan, 1981, A&A, 100, L20
- Vulcani, 2011, MNRAS, 412, 246, 10.1111/j.1365-2966.2010.17904.x · DOI
- Weigel, 2016, MNRAS, 459, 2150, 10.1093/mnras/stw756 · DOI
- Weisz, 2011, ApJ, 739, 5, 10.1088/0004-637X/739/1/5 · DOI · Paper page
- Willett, 2017, MNRAS, 464, 4176, 10.1093/mnras/stw2568 · DOI · Paper page
- Wilman, 2012, ApJ, 746, 160, 10.1088/0004-637X/746/2/160 · DOI
- Wollaeger, 2018, MNRAS, 478, 3298, 10.1093/mnras/sty1018 · DOI
Cited by
The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys
Huertas-Company, M., & Lanusse, F. (2023) · Publications of the Astronomical Society of Australia · doi:10.1017/pasa.2022.55 · Cited by 102
Ferreira, L., Conselice, C. J., Duncan, K., Cheng, T.-Y., Griffiths, A., & Whitney, A. (2020) · The Astrophysical Journal · doi:10.3847/1538-4357/ab8f9b · Cited by 92
“For instance, CNNs are widely used in astronomy to tackle several problems, like galaxy morphological classification, segmentation and deblending (e.g. Huertas-Company et al. 2018; Reiman & Göhre 2019; Huertas-Company et al. 2019; Cheng et al. 2019; Martin et al. 2019).”
MethodSelf-supervised Representation Learning for Astronomical Images
Hayat, M. A., Stein, G., Harrington, P., Lukić, Z., & Mustafa, M. (2021) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/abf2c7 · Cited by 79
Martin, G., Bazkiaei, A. E., Spavone, M., Iodice, E., Mihos, J. C., Montes, M., Benavides, J. A., Brough, S., Carlin, J. L., Collins, C. A., et al. (2022) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stac1003 · Cited by 76
Self-citationCañameras, R., Schuldt, S., Shu, Y., Suyu, S. H., Taubenberger, S., Andika, I. T., Bag, S., Inoue, K. T., Jaelani, A. T., Leal-Taixé, L., et al. (2024) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202347072 · Cited by 19
Metadata
- Authors
- Martin, G., Kaviraj, S., Hocking, A., Read, S. C., & Geach, J. E.
- Venue
- Monthly Notices of the Royal Astronomical Society
- Publisher
- Oxford University Press (OUP)
- Published
- 2019-10-26
- Volume
- 491
- Issue
- 1
- Pages
- 1408-1426
- ISSN
- 0035-8711 (ISSN-L)
- 1365-2966
- OpenAlex
- W2977076818
- Cited by
- 87
- References
- 6
- FWCI
- 5.47
- Type
- journal article
- Language
- en
- Open access
- bronze
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Funders
- Science and Technology Facilities Council (ST/N504105/1)
- National Astronomical Observatory of Japan
- National Aeronautics and Space Administration (NNX08AR22G)
- National Science Foundation (AST-1238877)
- University of Maryland
- Eotvos Lorand University
- Los Alamos National Laboratory
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: Galaxy morphological classification in deep-wide surveys via unsupervised machine learning. https://app.cochat.ai/papers/10.1093/mnras/stz3006
- The paper
- Martin, G., Kaviraj, S., Hocking, A., Read, S. C., & Geach, J. E. (2020). Galaxy morphological classification in deep-wide surveys via unsupervised machine learning. Monthly Notices of the Royal Astronomical Society. https://doi.org/10.1093/mnras/stz3006
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.