Machine learning technique for morphological classification of galaxies from the SDSS. III. The CNN image-based inference of detailed features
Рубрика:
| 1Khramtsov, V, 2Vavilova, IB, 2Dobrycheva, DV, 2Vasylenko, MYu., 2Melnyk, OV, 2Elyiv, AA, 3Akhmetov, VS, 3Dmytrenko, AM 1V.N. Karazin Kharkiv National University, Kharkiv, Ukraine 2Main Astronomical Observatory of the National Academy of Sciences of Ukraine, Kyiv, Ukraine 3Institute of Astronomy of Kharkiv National University, Kharkiv, Ukraine |
| Space Sci. & Technol. 2022, 28 ;(5):27-55 |
| https://doi.org/10.15407/knit2022.05.027 |
| Язык публикации: English |
Аннотация: This paper follows a series of our works on the applicability of various machine learning methods to morphological galaxy classification (Vavilova et al., 2021, 2022). We exploited the sample of ∼315800 low-redshift SDSS DR9 galaxies with absolute stellar magnitudes of −24m < Mr< −19.4m at 0.003 < z < 0.1 redshifts as a target data set for the CNN classifier. Because it is tightly overlapped with the Galaxy Zoo 2 (GZ2) sample, we use these annotated data as the training data set to classify galaxies into 34 detailed features.
In the presence of a pronounced difference in visual parameters between galaxies from the GZ2 training data set and galaxies without known morphological parameters, we applied novel procedures, which allowed us for the first time to get rid of this difference for smaller and fainter SDSS galaxies with mr< 17.7. We describe in detail the adversarial validation technique as well as how we managed the optimal train-test split of galaxies from the training data set to verify our CNN model based on the DenseNet-201 realistically. We have also found optimal galaxy image transformations, which help increase the classifier’s generalization ability.
We demonstrate for the first time that implication of the CNN model with a train-test split of data sets and size-changing function simulating a decrease in magnitude and size (data augmentation) significantly improves the classification of smaller and fainter SDSS galaxies. It can be considered as another way to improve the human bias for those galaxy images that had a poor vote classification in the GZ project. Such an approach, like autoimmunization, when the CNN classifier, trained on very good galaxy images, is able to retrain bad images from the same homogeneous sample, can be considered co-planar to other methods of combating such a human bias.
The most promising result is related to the CNN prediction probability in the classification of detailed features. The accuracy of the CNN classifier is in the range of 83.3–99.4 % depending on 32 features (exception is for “disturbed” (68.55 %) and “arms winding medium” (77.39 %) features). As a result, for the first time, we assigned the detailed morphological classification for more than 140000 low-redshift galaxies, especially at the fainter end. A visual inspection of the samples of galaxies with certain morphological features allowed us to reveal typical problem points of galaxy image classification by shape and features from the astronomical point of view.
The morphological catalogs of low-redshift SDSS galaxies with the most interesting features are available through the UkrVO website (http://ukr-vo.org/starcats/galaxies/) and VizieR.
|
| Ключевые слова: Convolutional Neural Network, data analysis, galaxies, image processing, morphological classification |
References:
1. Agnello A., Kelly B. C., Treu T., Marshall P. J. (2015). Data mining for gravitationally lensed quasars, Mon. Not. R. Astron. Soc., 448 (2), 1446-1462.
https://doi.org/10.1093/mnras/stv037
doi:10.1093/mnras/stv037.
https://doi.org/10.1093/mnras/stv037
2. Ostrovski F., McMahon R. G., Connolly A. J. et al. (2017). VDES J2325-5229 a z = 2.7 gravitationally lensed quasar discovered using morphology-independent supervised machine learning. Mon. Not. R. Astron. Soc., 465 (4), 4325-4334.
https://doi.org/10.1093/mnras/stw2958
doi:10.1093/mnras/stw2958.
https://doi.org/10.1093/mnras/stw2958
3. Lanusse F., Ma Q., Li N. et al. (2018). CMU DeepLens: deep learning for automatic image based galaxy-galaxy strong lens finding. Mon. Not. R. Astron. Soc., 473 (3), 3895-3906.
https://doi.org/10.1093/mnras/stx1665
doi:10.1093/mnras/stx1665.
https://doi.org/10.1093/mnras/stx1665
4. Jacobs C., Collett T., Glazebrook K. et al. (2019). Finding highredshift strong lenses in DES using convolutional neural networks. Mon. Not. R. Astron. Soc. 484 (4), 5330-5349.
https://doi.org/10.1093/mnras/stz272
doi:10.1093/mnras/stz272.
https://doi.org/10.1093/mnras/stz272
5. Khramtsov V., Sergeyev A., Spiniello C. et al. (2019). Kids-squad - ii. machine learning selection of bright extragalactic objects to search for new gravitationally lensed quasars. Astron. Astrophys., A632, A56.
https://doi.org/10.1051/0004-6361/201936006
doi:10.1051/0004-6361/201936006.
https://doi.org/10.1051/0004-6361/201936006
6. Petrillo C. E., Tortora C., Chatterjee S. et al. (2019). Testing convolutional neural networks for finding strong gravitational lenses in KiDS. Mon. Not. R. Astron. Soc., 482 (1), 807-820.
doi:10.1093/mnras/sty2683.
https://doi.org/10.1093/mnras/sty2683
7. Ribli D., Pataki B. A., Zorrilla Matilla J. M. et al. (2019). Weak lensing cosmology with convolutional neural networks on noisy data. Mon. Not. R. Astron. Soc., 490 (2), 1843-1860.
https://doi.org/10.1093/mnras/stz2610
doi:10.1093/mnras/stz2610.
https://doi.org/10.1093/mnras/stz2610
8. Pourrahmani M., Nayyeri H., Cooray A. (2018). LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses. Astrophys. J. , 856 (1), 68.
https://doi.org/10.3847/1538-4357/aaae6a
doi:10.3847/1538-4357/aaae6a.
https://doi.org/10.3847/1538-4357/aaae6a
9. Pasquet J., Bertin E., Treyer M. et al. (2019). Photometric redshifts from SDSS images using a convolutional neural network. Astron. Astrophys., 621, A26.
https://doi.org/10.1051/0004-6361/201833617
doi:10.1051/0004-6361/201833617.
https://doi.org/10.1051/0004-6361/201833617
10. Fussell L., Moews B. (2019). Forging new worlds: high-resolution synthetic galaxies with chained generative a dversarial networks. Mon. Not. R. Astron. Soc., 485 (3), 3203-3214.
https://doi.org/10.1093/mnras/stz602
doi:10.1093/mnras/stz602.
https://doi.org/10.1093/mnras/stz602
11. Salvato M., Ilbert O., Hoyle B. (2019). The many flavours of photometric redshifts. Nature Astronomy, 3, 212-222.
https://doi.org/10.1038/s41550-018-0478-0
doi:10.1038/s41550-018-0478-0.
https://doi.org/10.1038/s41550-018-0478-0
12. Bonnett C., Troxel M. A., Hartley W. et al. (2016). Redshift distributions of galaxies in the Dark Energy Survey Science Verification shear catalogue and implications for weak lensing, Phys. Rev. D, 94 (4), 042005.
doi:10.1103/PhysRevD.94.042005.
https://doi.org/10.1103/PhysRevD.94.042005
13. Amaro V., Cavuoti S., Brescia M. et al. (2019). Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies. Mon. Not. R. Astron. Soc., 482 (3), 3116-3134.
https://doi.org/10.1093/mnras/sty2922
doi:10.1093/mnras/sty2922.
https://doi.org/10.1093/mnras/sty2922
14. Sadeh I., Abdalla F. B., Lahav O. (2016). ANNz2: Photometric Redshift and Probability Distribution Function Estimation using Machine Learning. Publ. ASP, 128 (968), 104502.
https://doi.org/10.1088/1538-3873/128/968/104502
doi:10.1088/1538-3873/128/968/104502.
https://doi.org/10.1088/1538-3873/128/968/104502
15. Pasquet-Itam J., Pasquet J. (2018). Deep learning approach for classifying, detecting and predicting photometric redshifts of quasars in the Sloan Digital Sky Survey stripe 82. Astron. Astrophys., 611, A97.
https://doi.org/10.1051/0004-6361/201731106
doi:10.1051/0004-6361/201731106.
https://doi.org/10.1051/0004-6361/201731106
16. K¨ugler S. D., Gianniotis N. (2016). Modelling multimodal photometric redshift regression with noisy observations. arXiv:1607.06059.
17. Speagle J. S., Eisenstein D. J. (2017). Deriving photometric redshifts using fuzzy archetypes and self-organizing maps - II. Implementation. Mon. Not. R. Astron. Soc., 469 (1), 1205-1224.
https://doi.org/10.1093/mnras/stx510
doi:10.1093/mnras/stx510.
https://doi.org/10.1093/mnras/stx510
18. D'Isanto A., Cavuoti S., Gieseke F., Polsterer K. L. (2018). Return of the features. Efficient feature selection and interpretation for photometric redshifts. Astron. Astrophys., 616, A97.
https://doi.org/10.1051/0004-6361/201833103
doi:10.1051/0004-6361/201833103.
https://doi.org/10.1051/0004-6361/201833103
19. Elyiv A. A., Melnyk O. V., Vavilova I. B. et al. (2020). Machine-learning computation of distance modulus for local Galaxies. Astron. Astrophys., 635 (2020) A124.
https://doi.org/10.1051/0004-6361/201936883
doi:10.1051/0004-6361/201936883.
https://doi.org/10.1051/0004-6361/201936883
20. Rastegarnia F., Mirtorabi M. T., Moradi R. et al. (2022). Deep learning in searching the spectroscopic redshift of quasars. Mon. Not. R. Astron. Soc., 511 (3), 4490-4499.
https://doi.org/10.1093/mnras/stac076
doi:10.1093/mnras/stac076.
https://doi.org/10.1093/mnras/stac076
21. Elyiv A. A., Karachentsev I. D., Karachentseva V. E. et al. (2013). Low-density structures in the Local Universe. II. Nearby cosmic voids. Astrophys. Bull., 68 (1), 1-13.
https://doi.org/10.1134/S199034131301001X
doi:10.1134/S199034131301001X.
https://doi.org/10.1134/S199034131301001X
22. Koulouridis E., Plionis M., Melnyk O., Elyiv A. et al. (2014). X-ray AGN in the XMMLSS galaxy clusters: no evidence of AGN suppression. Astron. Astrophys., 567, A83.
https://doi.org/10.1051/0004-6361/201423601
doi:10.1051/0004-6361/201423601.
https://doi.org/10.1051/0004-6361/201423601
23. Elyiv A., Marulli F., Pollina G. et al. (2015). Cosmic voids detection without density measurements. Mon. Not. R. Astron. Soc., 448 (1), 642-653.
https://doi.org/10.1093/mnras/stv043
doi:10.1093/mnras/stv043.
https://doi.org/10.1093/mnras/stv043
24. Schawinski K., Zhang C., Zhang H. et al. (2017). Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit. Mon. Not. R. Astron. Soc., 467 (1), L110-L114.
https://doi.org/10.1093/mnrasl/slx008
doi:10.1093/mnrasl/slx008.
https://doi.org/10.1093/mnrasl/slx008
25. Vavilova I. B., Elyiv A. A., Vasylenko M. Y. (2018). Behind the Zone of Avoidance of the Milky Way: what can we Restore by Direct and Indirect Methods? Russian Radio Physics and Radio Astronomy, 23 (4), 244-257.
https://doi.org/10.15407/rpra23.04.244
doi:10.15407/rpra23.04.244.
https://doi.org/10.15407/rpra23.04.244
26. Rodr'ıguez A. C., Kacprzak T., Lucchi A. et al. (2018). Fast cosmic web simulations with generative adversarial networks. Comput. Astrophys. Cosmol., 5 (1), 4.
https://doi.org/10.1186/s40668-018-0026-4
doi:10.1186/s40668-018-0026-4.
https://doi.org/10.1186/s40668-018-0026-4
27. Khramtsov V., Akhmetov V., Fedorov P. (2020). The Northern Extragalactic WISE Ч Pan-STARRS (NEWS) catalogue. Machine-learning identification of 40 million extragalactic objects. Astron. Astrophys., 644, A69.
https://doi.org/10.1051/0004-6361/201834122
doi: 10.1051/0004-6361/201834122.
https://doi.org/10.1051/0004-6361/201834122
28. Hong S. E., Jeong D., Hwang H. S., Kim J (2021). Revealing the Local Cosmic Web from Galaxies by Deep Learning, Astrophys. J., 913 (1), 76.
https://doi.org/10.3847/1538-4357/abf040
doi:10.3847/1538-4357/abf040.
https://doi.org/10.3847/1538-4357/abf040
29. Khramtsov V., Spiniello C., Agnello A., Sergeyev A. (2021). VEXAS: VISTA EXtension to Auxiliary Surveys. Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere. Astron. Astrophys., 651, A69.
https://doi.org/10.1051/0004-6361/202040131
doi:10.1051/0004-6361/202040131.
https://doi.org/10.1051/0004-6361/202040131
30. Diakogiannis F. I., Lewis G. F., Ibata R. A. et al. (2019). Reliable mass calculation in spherical gravitating Systems. Mon. Not. R. Astron. Soc., 482 (3), 3356-3372.
https://doi.org/10.1093/mnras/sty2931
doi:10.1093/mnras/sty2931.
https://doi.org/10.1093/mnras/sty2931
31. Tsizh M., Novosyadlyj B., Holovatch Y., Libeskind N. I. (2020). Large-scale structures in the ΛCDM Universe: network analysis and machine learning. Mon. Not. R. Astron. Soc., 495 (1), 1311-1320.
https://doi.org/10.1093/mnras/staa1030
doi:10.1093/mnras/staa1030.
https://doi.org/10.1093/mnras/staa1030
32. Chen Y., Mo H. J., Li C. et al. (2020). Relating the Structure of Dark Matter Halos to Their Assembly and Environment. Astrophys. J., 899 (1), 81.
https://doi.org/10.3847/1538-4357/aba597
doi:10.3847/1538-4357/aba597.
https://doi.org/10.3847/1538-4357/aba597
33. Moriwaki K., Shirasaki M., Yoshida N. (2021). Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps, Astrophys. J. Let., 906 (1), L1.
https://doi.org/10.3847/2041-8213/abd17f
doi:10.3847/2041-8213/abd17f.
https://doi.org/10.3847/2041-8213/abd17f
34. Flamary R. (2016). Astronomical image reconstruction with convolutional neural networks. arXiv:1612.04526.
https://doi.org/10.23919/EUSIPCO.2017.8081654
35. Kremer J., Stensbo-Smidt K., Gieseke F. et al. (2017). Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy. arXiv:1704.04650.
https://doi.org/10.1109/MIS.2017.40
36. Savanevych V. E., Khlamov S. V., Vavilova I. B. et al. (2018). A method of immediate detection of objects with a near-zero apparent motion in series of CCD-frames. Astron. Astrophys., 609, A54.
https://doi.org/10.1051/0004-6361/201630323
doi:10.1051/0004-6361/201630323.
https://doi.org/10.1051/0004-6361/201630323
37. Villarroel B., Soodla J., Comer'on S. et al. (2020). The Vanishing and Appearing Sources during a Century of Observations Project. I. USNO Objects Missing in Modern Sky Surveys and Follow-up Observations of a "Missing Star", 159 (1), 8.
https://doi.org/10.3847/1538-3881/ab570f
doi:10.3847/1538-3881/ab570f.
https://doi.org/10.3847/1538-3881/ab570f
38. Pavlenko Y., Kulyk I., Shubina O. et al. (2022). New exocomets of β Pic, 660, A49.
https://doi.org/10.1051/0004-6361/202142111
doi:10.1051/0004-6361/202142111.
https://doi.org/10.1051/0004-6361/202142111
39. Reiman D. M., G¨ohre B. E. (2019). Deblending galaxy superpositions with branched generative adversarial networks. Mon. Not. R. Astron. Soc.. 485 (2), 2617-2627.
https://doi.org/10.1093/mnras/stz575
doi:10.1093/mnras/stz575.
https://doi.org/10.1093/mnras/stz575
40. Buchanan J. J., Schneider M. D., Armstrong R. E. et al. (2021). Gaussian Process Classification for Galaxy Blend Identification in LSST. arXiv: 2107.09246.
41. El Bouchefry K., de Souza R. S. (2020). Learning in Big Data: Introduction to Machine Learning, in: P. ˇSkoda, F. Adam (Eds.), Knowledge Discovery in Big Data from Astronomy and Earth Observation, 2020, pp. 225-249.
https://doi.org/10.1016/B978-0-12-819154-5.00023-0
doi:10.1016/B978-0-12-819154-5.00023-0.
https://doi.org/10.1016/B978-0-12-819154-5.00023-0
42. Burgazli A., Sergijenko O., Vavilova I. (2022). Machine learning in cosmology and gravitational wave astronomy: recent trends. In: Horizons in Computer Science Research. Ed. T.S. Clary, Vol. 22., Chapter 7, p. 193-240. New York, Nova Science Publisher Inc.
43. Kang S.-J., Fan J.H., Mao W. et al. (2019). Evaluating the Optical Classification of Fermi BCUs Using Machine Learning. Astrophys. J., 872 (2), 189. arXiv:1902.07717.
https://doi.org/10.3847/1538-4357/ab0383
doi:10.3847/1538-4357/ab0383.
https://doi.org/10.3847/1538-4357/ab0383
44. Krause M., Pueschel E., Maier G. (2017). Improved γ/hadron separation for the detection of faint γ-ray sources using boosted decision trees. Astroparticle Phys., 89, 1-9. doi:10.1016/j.astropartphys.2017.01.004.
https://doi.org/10.1016/j.astropartphys.2017.01.004
45. Ruhe T. (2020). Application of machine learning algorithms in imaging Cherenkov and neutrino astronomy, Int. J. Mod. Phys. A, 35 (33), 2043004-778.
https://doi.org/10.1142/S0217751X20430046
doi:10.1142/S0217751X20430046.
https://doi.org/10.1142/S0217751X20430046
46. Morello G., Morris P. W., Van Dyk S. D. et al. (2018). Applications of machine-learning algorithms for infrared colour selection of Galactic Wolf-Rayet stars. Mon. Not. R. Astron. Soc., 473 (2), 2565-2574.
https://doi.org/10.1093/mnras/stx2474
doi:10.1093/mnras/stx2474.
https://doi.org/10.1093/mnras/stx2474
47. Ciuca R., Hern'andez O. F. (2017). A Bayesian framework for cosmic string searches in CMB maps, J. Cosm. Astropart. Phys., 2017 (8), 028.
https://doi.org/10.1088/1475-7516/2017/08/028
doi:10.1088/1475-7516/2017/08/028.
https://doi.org/10.1088/1475-7516/2017/08/028
48. Aniyan A. K., Thorat K. (2017). Classifying Radio Galaxies with the Convolutional Neural Network, Astrophys. J. Supl., 230 (2), 20.
https://doi.org/10.3847/1538-4365/aa7333
doi:10.3847/1538-4365/aa7333.
https://doi.org/10.3847/1538-4365/aa7333
49. Lukic V., Br¨uggen M., Banfield J. K. et al. (2018). Radio Galaxy Zoo: compact and extended radio source classification with deep learning. Mon. Not. R. Astron. Soc., 476 (1), 246-260.
https://doi.org/10.1093/mnras/sty163
doi:10.1093/mnras/sty163.
https://doi.org/10.1093/mnras/sty163
50. Ma Z., Xu H., Zhu J. et al. (2019). A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best-Heckman Sample. Astrophys. J. Suppl., 240 (2), 34.
https://doi.org/10.3847/1538-4365/aaf9a2
doi:10.3847/1538-4365/aaf9a2.
https://doi.org/10.3847/1538-4365/aaf9a2
51. Scaife A. M. M., Porter F. (2021). Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks. Mon. Not. R. Astron. Soc., 503 (2), 2369-2379.
https://doi.org/10.1093/mnras/stab530
doi:10.1093/mnras/stab530.
https://doi.org/10.1093/mnras/stab530
52. Ciprijanovi'c A., Kafkes D., Downey K. et al. (2021). DeepMerge - II. Building robust deep learning algorithms for merging galaxy identification across domains. Mon. Not. R. Astron. Soc., 506 (1), 677-691.
https://doi.org/10.1093/mnras/stab1677
doi:10.1093/mnras/stab1677.
https://doi.org/10.1093/mnras/stab1677
53. Shamir L. (2021). Automatic identification of outliers in Hubble Space Telescope galaxy images. Mon. Not. R. Astron. Soc., 501 (4), 5229-5238.
https://doi.org/10.1093/mnras/staa4036
doi:10.1093/mnras/staa4036.
https://doi.org/10.1093/mnras/staa4036
54. Vavilova I. B., Dobrycheva D. V., Vasylenko M. Y. et al. (2021). Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach. Astron. Astrophys., 648, A122.
https://doi.org/10.1051/0004-6361/202038981
doi:10.1051/0004-6361/202038981.
https://doi.org/10.1051/0004-6361/202038981
55. Vavilova I. B., Khramtsov V., Dobrycheva D. V. et al. (2022). Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02 56. Walmsley M., Smith L., Lintott C. et al. (2020). Galaxy Zoo: probabilistic morphology through Bayesian CNNs and active learning. Mon. Not. R. Astron. Soc., 491 (2), 1554-1574. doi:10.1093/mnras/stz2816. 57. Muller A., Guido S. (2016). Introduction to Machine Learning with Python, O'Reilly Media. 58. Melnyk O. V., Dobrycheva D. V., Vavilova I. B. (2012). Morphology and color indices of galaxies in Pairs: Criteria for the classification of galaxies, Astrophysics, 55 (3), 293-305. doi:10.1007/s10511-012-9236-7. 59. Dobrycheva D. V., Melnyk O. V., Vavilova I. B., Elyiv A. A. (2014). Environmental Properties of Galaxies at z ! 0.1 from the SDSS via the Voronoi Tessellation. Odessa Astron. Publ., 27, 26. 60. Dobrycheva D. V., Melnyk O. V., Vavilova I. B., Elyiv A. A. (2015). Environmental Density vs. Colour Indices of the Low Redshifts Galaxies. Astrophysics, 58 (2), 168-180. doi:10.1007/s10511-015-9373-x. 61. Dobrycheva D. V., Vavilova I. B., Melnyk O. V., Elyiv A. A. (2017). Machine learning technique for morphological classification of galaxies at z 0.1 from the SDSS. arXiv:1712.08955. 62. Dobrycheva D. V. (2017). Morphological content and color indices bimodality of a new galaxy sample at the redshifts z
63. Dobrycheva D. V., Vavilova I. B., Melnyk O. V., Elyiv A. A. (2018). Morphological Type and Color Indices of the SDSS DR9 Galaxies at 0.02
https://doi.org/10.3103/S0884591318060028 doi:10.3103/S0884591318060028. 64. Vasylenko M. Y., Dobrycheva D. V., Vavilova I. B. et al. (2019). Verification of Machine Learning Methods for Binary Morphological Classification of Galaxies from SDSS. Odessa Astron. Publ., 32, 46. doi:10.18524/1810-4215.2019.32.182538. 65. Khramtsov V., Dobrycheva D. V., Vasylenko M. Y., Akhmetov V. S. (2019). Deep learning for morphological classification of galaxies from SDSS, Odessa Astron. Publ., 32, 21. doi:10.18524/1810-4215.2019.32.182092. 66. Vasylenko M., Dobrycheva D., Khramtsov V., Vavilova I. (2020). Deep Convolutional Neural Networks models for the binary morphological classification of SDSS-galaxies. Commun. BAO, 67, 354. doi:10.52526/25792776-2020.67.2-354. 67. Vavilova I., Dobrycheva D., Vasylenko M. et al. (2020). Multiwavelength Extragalactic Surveys: Examples of Data Mining, In: Knowledge Discovery in Big Data from Astronomy and Earth Observation, Eds. P. Skoda and F. Adam, Elsevier, Ch. 16, pp. 307-323. doi:10.1016/B978-0-12-819154-5.00028-X. 68. Vavilova I., Elyiv A., Dobrycheva D., Melnyk O. (2021). The Voronoi tessellation method in astronomy, In: Intelligent Astrophysics, Eds. I. Zelinka, M. Brescia, D. Baron, Springer, Cham, Vol. 39, Ch. 3, pp. 57-79. doi:10.1007/978-3-030-65867-0\_3. 69. Vavilova I. B., Dobrycheva D. V., Vasylenko M. Y. et al. (2021). VizieR Online Data Catalog: SDSS galaxies morphological classification (Vavilova+, 2021), VizieR Online Data Catalog (2021) J/A+A/648/A122. 70. Vavilova I. B., Khramtsov V., Dobrycheva D. V. et al. VizieR Online Data Catalog: Galaxies at 0.02 71. Willett K. W., Lintott C. J., Bamford S. P. et al. (2013). Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey. Mon. Not. R. Astron. Soc., 435 (4), 2835-2860. doi:10.1093/mnras/stt1458. 72. Blanton M. R., Dalcanton J., Eisenstein D. et al. (2001). The Luminosity Function of Galaxies in SDSS Commissioning Data. Astron. J., 121 (5), 2358-2380. doi:10.1086/320405. 73. Yasuda N., Fukugita M.,. Narayanan V. K. et al. (2001). Galaxy Number Counts from the Sloan Digital Sky Survey Commissioning Data. Astron. J., 122 (3), 1104-1124. doi:10.1086/322093. 74. Walmsley M., Lintott C., Geron T. et al. (2021). Galaxy ZOO DECaLSs: Detailed visual morphology measurements from volunteers and deep learning for 314000 galaxies. arXiv:2102.08414. 75. Lupton R., Blanton M. R., Fekete G. et al. (2004). Preparing Red-Green-Blue Images from CCD Data. Publ. ASP, 116 (816), 133-137. doi:10.1086/382245. 76. Wang N., Choi J., Brand D. et al. (2018). Training Deep Neural Networks with 8-bit Floating Point Numbers, arXiv e-prints. arXiv:1812.08011. 77. Ren W., Yu Y., Zhang J., Huang K. (2014). Learning convolutional nonlinear features for k nearest neighbor image classification, in: 22nd Int. Conf. on Pattern Recognition, 4358-4363. 78. Honghui S. (2016). Galaxy Classification with deep convolutional neural networks. Ph.D. thesis, University of Illinois at Urbana-Champaign. 79. Meyer B. J., Harwood B., Drummond T. (2018). Deep metric learning and image classification with nearest neighbour gaussian kernels, in: 25th IEEE Int. Conf. on Image Processing (ICIP), 151-155. 80. Pan J., Pham V., Dorairaj M. et al. (2020). Adversarial validation approach to concept drift problem in user targeting automation systems at uber. arXiv:2004.03045. 81. Bishop C. (1995). Neural networks for pattern recognition, Oxford University Press, USA. 82. Dieleman S., Willett K. W., Dambre J. (2015). Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon. Not. R. Astron. Soc., 450 (2), 1441-1459. doi:10.1093/mnras/stv632. 83. He K., Zhang X., Ren S., Sun J. (2015). Deep residual learning for image recognition. arXiv:1512.03385. 84. Vega-Ferrero J., Dominguez Sanchez H., Bernardi M. et al. (2021). Huertas-Company, Pushing automated morphological classifications to their limits with the Dark Energy Survey. Mon. Not. R. Astron. Soc., 506 (2), 1927-1943. doi:10.1093/mnras/stab594. 85. Bhambra P., Joachimi B., Lahav O. (2022). Explaining deep learning of galaxy morphology with saliency mapping, Mon. Not. R. Astron. Soc., 511 (4), 5032-5041. doi:10.1093/mnras/stac368. 86. Gupta R., Srijith P. K., Desai S. (2022)., Galaxy morphology classification using neural ordinary differential equations. Astron. Comp., 38, 100543. doi:10.1016/j.ascom.2021.100543. 87. Huang G., Liu Z., van der Maaten L., Weinberger K. Q. (2018). Densely connected convolutional networks. arXiv:1608.06993. 88. Szegedy C., Vanhoucke V., Ioffe S. et al. (2015). Rethinking the inception architecture for computer vision (2015). arXiv:1512.00567. 89. Szegedy C., Ioffe S., Vanhoucke V., Alemi A. (2016). Inception-v4, inception resnet and the impact of residual connections on learning. arXiv:1602.07261. 90. Zoph B., Vasudevan V., Shlens J. (2017). Learning Transferable Architectures for Scalable Image Recognition. arXiv:1707.07012. 91. Simonyan K., Zisserman A. (2015). Very deep convolutional networks for largescale image recognition. arXiv:1409.1556. 92. Chollet F. (2017). Xception: Deep learning with depthwise separable convolutions. arXiv:1610.02357. 93. Bradley A. P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms, Pattern Recognition, 30 (7), 1145-1159. doi:10.1016/S0031-3203(96)00142-2. 94. Rahmani S., Teimoorinia H., Barmby P. (2018). Classifying galaxy spectra at 0.5 doi:10.1093/mnras/sty1291. 95. Curti M., Hayden-Pawson C., Maiolino R. et al. (2022). What drives the scatter of local star-forming galaxies in the BPT diagrams? A Machine Learning based analysis. Mon. Not. R. Astron. Soc., 512 (3), 4136-4163. doi:10.1093/mnras/stac544. 96. Shi F., Liu Y-Y., Sun G.L. et al. A support vector machine for spectral classification of emission-line galaxies from the Sloan Digital Sky Survey. Mon. Not. R. Astron. Soc., 453 (1), 122-127. doi:10.1093/mnras/stv1617. 97. Tempel E., Saar E., Liivam¨agi L. J. et al. (2011). Galaxy morphology, luminosity, and environment in the SDSS DR7. Astron. Astrophys., 529 (2011) A53. doi:10.1051/0004-6361/201016196. 98. Tojeiro R., Masters K. L., Richards J. et al. (2013). The different star formation histories of blue and red spiral and elliptical galaxies. Mon. Not. R. Astron. Soc., 432 (1), 359-373. doi:10.1093/mnras/stt484. 99. Vavilova I. B., Ivashchenko G. Y., Babyk I. V. et al. (2015). The astrocosmic databases for multi-wavelength and cosmological properties of extragalactic sources, Kosm. Nauka Tekhnol., 21 (3), 94-107. doi:10.15407/knit2015.05.094. 100. Guo R., Hao C.-N., Xia X. et al. (2020). Toward an Understanding of the Massive Red Spiral Galaxy Formation. Astrophys. J., 897 (2), 162. doi:10.3847/1538-4357/ab9b75. 101. Mezcua M., Lobanov A. P., Mediavilla E., Karouzos M. (2014). Photometric Decomposition of Mergers in Disk Galaxies. Astrophys. J., 784 (1), 16. doi:10.1088/0004-637X/784/1/16. 102. Simmons B. D., Lintott C., Willett K. W. et al. (2017). Galaxy Zoo: quantitative visual morphological classifications for 48 000 galaxies from CANDELS. Mon. Not. R. Astron. Soc., 464 (4), 4420-4447. doi:10.1093/mnras/stw2587. 103. Bottrell C., Hani M. H., Teimoorinia H. et al. (2019). Deep learning predictions of galaxy merger stage and the importance of observational realism. Mon. Not. R. Astron. Soc., 490 (4), 5390-5413. doi:10.1093/mnras/stz2934. 104. Pearson W. J., Wang L., Trayford J. W. Petrillo E., van der Tak F.F.S. (2019). Identifying galaxy mergers in observations and simulations with deep learning. Astron. Astrophys., 626, A49. doi:10.1051/0004-6361/201935355. 105. Cabrera-Vives G., Miller C. J., Schneider J. Systematic Labeling Bias in Galaxy Morphologies. Astron. J., 156 (6), 284. doi:10.3847/1538-3881/aae9f4. 106. Hart R. E., Bamford S. P., Willett K. W. et al. (2016). Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias. Mon. Not. R. Astron. Soc., 461 (4), 3663-3682. doi:10.1093/mnras/stw1588. 107. Tarsitano F., Bruderer C., Schawinski K., Hartley W. G. (2022). Image feature extraction and galaxy classification: a novel and efficient approach with automated machine learning. Mon. Not. R. Astron. Soc., 511 (3), 3330-3338. doi:10.1093/mnras/stac233. 108. Gauthier A., Jain A., Noordeh E. (2016). Galaxy Morphology Classification. e-proceedings, 1-6. URL http://cs229.stanford.edu/proj2016/report/GauthierJainNoordeh-GalaxyMorp... 109. Barchi P. H., de Carvalho R. R., Rosa R. R. et al. (2020). Machine and Deep Learning applied to galaxy morphology - A comparative study. Astron. Comp., 30, 100334. doi:10.1016/j.ascom.2019.100334. 110. Mittal A., Soorya A., Nagrath P., Hemanth D. J. (2020). Data augmentation based morphological classification of galaxies using deep convolutional neural network. Earth Sci. Inform., 13, 601-617. doi:10.1007/s12145-019-00434-8. 111. Sreejith S., Pereverzyev J., Kelvin L. S. et al. (2018). Galaxy And Mass Assembly: automatic morphological classification of galaxies using statistical learning. Mon. Not. R. Astron. Soc., 474 (4), 5232-5258. doi:10.1093/mnras/stx2976. 112. Ghosh A., Urry C. M., Wang Z. et al. (2020). Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in ∼100,000 SDSS and ∼20,000 CANDELS Galaxies. Astrophys. J., 895 (2), 112. doi:10.3847/1538-4357/ab8a47. 113. Walmsley M., Scaife A. M. M., Lintott C. et al. (2022). Practical galaxy morphology tools from deep supervised representation learning. Mpn. Not. R. Astron. Soc., 513 (2) (2022) 1581-1599. doi:10.1093/mnras/stac525. 114. Gauci A., Zarb Adami K., Abela J. (2010). Machine Learning for Galaxy Morphology Classification. arXiv:1005.0390. 115. Dom'ınguez S'anchez H., Huertas-Company M., Bernardi M. et al. (2018). Improving galaxy morphologies for SDSS with Deep Learning. Mon. Not. R. Astron. Soc., 476 (3), 3661-3676. doi:10.1093/mnras/sty338. 116. Yao-Yu Lin J., S.-M. Liao, Huang H.-J. et al. (2021). Galaxy Morphological Classification with Efficient Vision Transformer. arXiv:2110.01024. 117. Karachentseva V. E., Vavilova I. B. (1994). Clustering of low surface brightness dwarf galaxies. I. General properties., Bull. SAO, 37, 98-118. 118. Karachentseva V. E., Vavilova I. B. (1995). Clustering of dwarf galaxies with low surface brightness. II. The Virgo cluster. Kinemat. Phys. Celest. Bodies, 11 (5), 38-48. 119. Sabatini S., Roberts S., Davies J. (2003). Dwarf LSB galaxies and their environment: The Virgo Cluster, the Ursa Major Cluster, isolated galaxies and voids. Astrophys. J. Supl. Ser., 285 (1), 97-106. doi:10.1023/A:1024609809391. 120. Du W., Cheng C., Wu H. et al. (2019). Low Surface Brightness Galaxy catalogue selected from the α.40-SDSS DR7 Survey and Tully-Fisher relation. Mon. Not. R. Astron. Soc., 483 (2), 1754-1795. doi:10.1093/mnras/sty2976. 121. Zhu X.-P., Dai J.-M., Bian C.J. et al. (2019). Galaxy morphology classification with deep convolutional neural networks. Astrophys. Space Sci., 364 (4), 55. doi:10.1007/s10509-019-3540-1. 122. Dhar S., Shamir L. (202). Systematic biases when using deep neural networks for annotating large catalogs of astronomical images. Astron. Comp., 38, 100545. doi:10.1016/j.ascom.2022.100545. 123. Smethurst R. J., Masters K. L., Simmons B. D. et al. (2022). Quantifying the poor purity and completeness of morphological samples selected by galaxy colour. Mon. Not. R. Astron. Soc., 510 (3), 4126-4133. doi:10.1093/mnras/stab3607. 124. Kautsch S. J., Grebel E. K., Barazza F. D. et al. (2006). A catalog of edge-on disk galaxies. From galaxies with a bulge to superthin galaxies. Astron. Astrophys., 445 (2), 765-778. doi:10.1051/0004-6361:20053981. 125. Bizyaev D. V., Kautsch S. J., Mosenkov A. V. et al. (2014). The Catalog of Edge-on Disk Galaxies from SDSS. I. The Catalog and the Structural Parameters of Stellar Disks. Astrophys. J., 787 (1), 24. doi:10.1088/0004-637X/787/1/24. 126. Lima-Dias C., Monachesi A., Torres-Flores, S. et al. (2021). An environmental dependence of the physical and structural properties in the Hydra cluster galaxies. Mon. Not. R. Astron. Soc., 500 (1), 1323-1339. doi:10.1093/mnras/staa3326. 127. Dom'ınguez-S'anchez H., Huertas-Company M., Bernardi M. et al. (2019). Transfer learning for galaxy morphology from one survey to another. Mon. Not. R. Astron. Soc., 484 (1), 93-100. doi:10.1093/mnras/sty3497. 128. Lingard T. K., Masters K. L., Krawczyk C. et al. (2020). Galaxy Zoo Builder: Four-component Photometric Decomposition of Spiral Galaxies Guided by Citizen Science. Astrophys. J., 900 (2), 178. doi:10.3847/1538-4357/ab9d83. 129. Schawinski K., Urry C. M., Simmons B. D., et al. (2014). The green valley is a red herring: Galaxy Zoo reveals two evolutionary pathways towards quenching of star formation in early- and late-type galaxies. Mon. Not. R. Astron. Soc., 440 (1), 889-907. doi:10.1093/mnras/stu327. 130. Madore B. F., Nelson E., Petrillo K. (2009). VizieR Online Data Catalog: Collisional ring galaxies atlas (Madore+, 2009), VizieR Online Data Catalog (2009) J/ApJS/181/572. 131. Smirnov D. V., Reshetnikov V. P. (2022). The luminosity function of ringed galaxies. arXiv:2209.06875. 132. Hoyle B., Masters K. L., Nichol R. C. et al. (2011). Galaxy Zoo: bar lengths in local disc galaxies. Mon. Not. R. Astron. Soc., 415 (4), 3627-3640. doi:10.1111/j.1365-2966.2011.18979.x. 133. Reza M. (2021). Galaxy morphology classification using automated machine learning. Astron. Comp., 37, 100492. doi:10.1016/j.ascom.2021.100492. 134. Vavilova I. B., Karachentseva V. E., Makarov D. I., Melnyk O. V. (2005). Triplets of Galaxies in the Local Supercluster. I. Kinematic and Virial Parameters. Kinemat. Fiz. Neb. Tel, 21 (1), 3-20. 135. Darg D. W., Kaviraj S., Lintott C. J. et al. (2010). Galaxy Zoo: the fraction of merging galaxies in the SDSS and their morphologies. Mon. Not. R. Astron. Soc., 401 (2), 1043-1056. doi:10.1111/j.1365-2966.2009.15686.x. 136. Weston M. E., McIntosh D. H., Brodwin M. et al. Incidence of WISE -selected obscured AGNs in major mergers and interactions from the SDSS. Mon. Not. R. Astron. Soc., 464 (4), 3882-3906. doi:10.1093/mnras/stw2620. 137. Pearson W. J., Suelves L. E., Ho S. C. C. et al. (2022). North Ecliptic Pole merging galaxy catalogue. Astron. Astrophys., 661, A52. doi:10.1051/0004-6361/202141013. 138. Ahn C. P., Alexandroff R., Allende Prieto C. et al. (2012). The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey. Astrophys. J. Supl., 203 (2), 21. doi:10.1088/0067-0049/203/2/21. 139. Blanton M. R., Bershady M. A., Abolfathi B. et al. (2017). SDSS IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe. Astron. J., 154, 28. doi:10.3847/1538-3881/aa7567. 140. Wenger M., Ochsenbein F., Egret D. et al. The SIMBAD astronomical database. The CDS reference database for astronomical objects. Astron. Astrophys. Supl., 143 (2000) 9-22. doi:10.1051/aas:2000332.
https://doi.org/10.1093/mnras/stz2816
https://doi.org/10.1007/s10511-012-9236-7
https://doi.org/10.1007/s10511-015-9373-x
https://doi.org/10.3103/S0884591318060028
https://doi.org/10.18524/1810-4215.2019.32.182538
https://doi.org/10.18524/1810-4215.2019.32.182538
https://doi.org/10.18524/1810-4215.2019.32.182092
https://doi.org/10.18524/1810-4215.2019.32.182092
https://doi.org/10.52526/25792776-2020.67.2-354
https://doi.org/10.52526/25792776-2020.67.2-354
https://doi.org/10.1016/B978-0-12-819154-5.00028-X
https://doi.org/10.1016/B978-0-12-819154-5.00028-X
https://doi.org/10.1007/978-3-030-65867-0_3
https://doi.org/10.1007/978-3-030-65867-0
https://doi.org/10.1051/0004-6361/202038981
https://doi.org/10.1093/mnras/stt1458
https://doi.org/10.1093/mnras/stt1458
https://doi.org/10.1086/320405
https://doi.org/10.1086/320405
https://doi.org/10.1086/322093
https://doi.org/10.1086/322093
https://doi.org/10.1086/382245
https://doi.org/10.1086/382245
https://doi.org/10.1109/ICPR.2014.746
https://doi.org/10.1109/ICIP.2018.8451297
https://doi.org/10.1201/9781420050646.ptb6
https://doi.org/10.1093/mnras/stv632
https://doi.org/10.1093/mnras/stv632
https://doi.org/10.1109/CVPR.2016.90
https://doi.org/10.1093/mnras/stab594
https://doi.org/10.1093/mnras/stab594
https://doi.org/10.1093/mnras/stac368
https://doi.org/10.1093/mnras/stac368
https://doi.org/10.1016/j.ascom.2021.100543
https://doi.org/10.1109/CVPR.2017.243
https://doi.org/10.1109/CVPR.2016.308
https://doi.org/10.1609/aaai.v31i1.11231
https://doi.org/10.1109/CVPR.2018.00907
https://doi.org/10.1109/CVPR.2017.195
https://doi.org/10.1016/S0031-3203(96)00142-2
https://doi.org/10.1016/S0031-3203(96)00142-2
https://doi.org/10.1093/mnras/sty1291
https://doi.org/10.1093/mnras/stac544
https://doi.org/10.1093/mnras/stac544
https://doi.org/10.1093/mnras/stv1617
https://doi.org/10.1093/mnras/stv1617
https://doi.org/10.1051/0004-6361/201016196
https://doi.org/10.1051/0004-6361/201016196
https://doi.org/10.1093/mnras/stt484
https://doi.org/10.1093/mnras/stt484
https://doi.org/10.15407/knit2015.05.094
https://doi.org/10.15407/knit2015.05.094
https://doi.org/10.3847/1538-4357/ab9b75
https://doi.org/10.3847/1538-4357/ab9b75
https://doi.org/10.1088/0004-637X/784/1/16
https://doi.org/10.1088/0004-637X/784/1/16
https://doi.org/10.1093/mnras/stw2587
https://doi.org/10.1093/mnras/stw2587
https://doi.org/10.1093/mnras/stz2934
https://doi.org/10.1093/mnras/stz2934
https://doi.org/10.1051/0004-6361/201935355
https://doi.org/10.1051/0004-6361/201935355
https://doi.org/10.3847/1538-3881/aae9f4
https://doi.org/10.3847/1538-3881/aae9f4
https://doi.org/10.1093/mnras/stw1588
https://doi.org/10.1093/mnras/stw1588
https://doi.org/10.1093/mnras/stac233
https://doi.org/10.1093/mnras/stac233
https://doi.org/10.1016/j.ascom.2019.100334
https://doi.org/10.1016/j.ascom.2019.100334
https://doi.org/10.1007/s12145-019-00434-8
https://doi.org/10.1007/s12145-019-00434-8
https://doi.org/10.1093/mnras/stx2976
https://doi.org/10.1093/mnras/stx2976
https://doi.org/10.3847/1538-4357/ab8a47
https://doi.org/10.3847/1538-4357/ab8a47
https://doi.org/10.1093/mnras/stac525
https://doi.org/10.1093/mnras/stac525
https://doi.org/10.1093/mnras/sty338
https://doi.org/10.1093/mnras/sty338
https://doi.org/10.1007/978-94-010-0107-6_13
https://doi.org/10.1023/A:1024609809391
https://doi.org/10.1093/mnras/sty2976
https://doi.org/10.1093/mnras/sty2976
https://doi.org/10.1007/s10509-019-3540-1
https://doi.org/10.1007/s10509-019-3540-1
https://doi.org/10.1016/j.ascom.2022.100545
https://doi.org/10.1016/j.ascom.2022.100545
https://doi.org/10.1093/mnras/stab3607
https://doi.org/10.1093/mnras/stab3607
https://doi.org/10.1051/0004-6361:20053981
https://doi.org/10.1051/0004-6361:20053981
https://doi.org/10.1088/0004-637X/787/1/24
https://doi.org/10.1088/0004-637X/787/1/24
https://doi.org/10.1093/mnras/staa3326
https://doi.org/10.1093/mnras/staa3326
https://doi.org/10.1093/mnras/sty3497
https://doi.org/10.1093/mnras/sty3497
https://doi.org/10.3847/1538-4357/ab9d83
https://doi.org/10.3847/1538-4357/ab9d83
https://doi.org/10.1093/mnras/stu327
https://doi.org/10.1093/mnras/stu327
https://doi.org/10.1088/0067-0049/181/2/572
https://doi.org/10.1093/mnras/stac2549
https://doi.org/10.1111/j.1365-2966.2011.18979.x
https://doi.org/10.1111/j.1365-2966.2011.18979.x
https://doi.org/10.1016/j.ascom.2021.100492
https://doi.org/10.1111/j.1365-2966.2009.15686.x
https://doi.org/10.1111/j.1365-2966.2009.15686.x
https://doi.org/10.1093/mnras/stw2620
https://doi.org/10.1093/mnras/stw2620
https://doi.org/10.1051/0004-6361/202141013
https://doi.org/10.1051/0004-6361/202141013
https://doi.org/10.1088/0067-0049/203/2/21
https://doi.org/10.1088/0067-0049/203/2/21
https://doi.org/10.3847/1538-3881/aa7567
https://doi.org/10.3847/1538-3881/aa7567
https://doi.org/10.1051/aas:2000332
https://doi.org/10.1051/aas:2000332