DOI: https://doi.org/10.18524/1810-4215.2019.32.182092

DEEP LEARNING FOR MORPHOLOGICAL CLASSIFICATION OF GALAXIES FROM SDSS

V. Khramtsov, D. V. Dobrycheva, M. Yu. Vasylenko, V. S. Akhmetov

Анотація


We present the results of applying
deep convolutional neural network to the images of
redshift-limited ( z < 0 . 1) sample of ∼ 300000 galaxies
from the SDSS DR9. We aimed to classify galaxies into
the two classes: Elliptical and Spiral. To create the
training sample, we used a set of ∼ 6000 galaxies from
our previous work with visually inspected morphologi-
cal types, and also added 80000 well-confirmed galaxies
from Galaxy Zoo 2 dataset, that were also classified
visually. With a given sample of ∼ 86000 galaxies, we
used the deep neural network, namely Xception, to
provide a classification of g-r-i composite images (25
arcsec in each axis in size) of galaxies. Keeping in the
mind a relatively small training dataset, we provided
the data augmentation (horizontal and vertical flips,
random shifts on ± 10 pixels , and rotations within 180
degrees), that was randomly applied to the images
during learning. The data augmentation is a key
technique within our algorithm to display the variative
nature of the observed galaxies, and avoid overfitting
problem. We compared our classification result with
the Support Vector Machine (SVM) classification
performed on the SDSS photometric data (absolute
magnitudes, colour indices, inverse concentration index,
ratios of semiaxes, etc.), and proposed a method
to learn the benefits from both approaches (Deep
Learning and photometric classification). We show the
common mistakes of both algorithms, and propose to
stack these two approaches to block these mistakes,
with a main goal to increase the overall classification
quality of SDSS galaxies.

 


Ключові слова


galaxies; morphological classification; machine learning

Повний текст:

PDF (English)

Посилання


Ahn C.P., Alexandroff R., Allende P.C. et al.: 2012, ApJS, 203, 21.

Blanton M.R., Bershady M.A., Abolfathi B. et al.: 2017, Astron. J., 154, 35.

Chollet F.: 2016, arXiv:1610.02357.

Dalya G., Galgoczi G. et al.: 2018, MNRAS, 479 , 2374.

Dobrycheva D.V.: 2013, OAP, 26, 187.

Dobrycheva D.V., Melnyk O.V., Vavilova I.B. et al.: 2015, Astrophysics, 58, 168.

Dobrycheva D.V. et al.: 2017, arXiv:1712.08955.

Dobrycheva D.V., Vavilova I.B., Melnyk O.V. et al.: 2018, Kinemat. Phys. Celest. Bodies, 34, 290.

Khramtsov V., Sergeyev A., Spiniello C. et al.: 2019, arXiv:1906.01638.

Sergeyev A., Spiniello C., Khramtsov V. et al.: 2018, AAS, 2, 189.

Vapnik V.: 1979, Estimation of Dependences Based on Empirical Data [in Russian].

Vavilova I.B., Elyiv A.A., Vasylenko M.Yu.: 2018, Radio Phys. Radio Astron., 23, 244.

Vasylenko M.Yu., Dobrycheva D.V., Vavilova I.B. et al.: 2019, OAP, this issue.

Willett K.W., Lintott C.J., Bamford S.P. et al.: 2013, MNRAS, 435, 2835




Copyright (c) 2019 Odessa Astronomical Publications

Creative Commons License
Ця робота ліцензована Creative Commons Attribution-NonCommercial 4.0 International License.