Astronomical objects classification based on the Digitized First Byurakan Survey low-dispersion spectra


Astsatryan Hrachya ; Mickaelian A.



Co-author(s) :

Gevorgyan G. ; Knyazyan Aram ; Mikayelyan G.A.

Uncontrolled Keywords:

Astronomical data ; DFBS ; Machine Learning ; Data classification ; Virtual Observatories ; ArVO


The Digitized First Byurakan Survey is the largest and the first systematic objective-prism survey of the extragalactic sky. The detection, extraction, and classification of about 40 million spectra of about 20 million astronomical objects available in the survey require distinguishing the pixels containing photons from the source and the noise pixels per object. This paper aims at developing a service to classify the spectra of UV-excess galaxies, quasars, compact galaxies, and other objects in the survey. Supervised and unsupervised convolutional neural network deep learning algorithms have been developed and studied.



Date submitted:

29 July 2020

Date accepted:

4 December 2020





Journal or Publication Title:

Astronomy and Computing




Additional Information:

The paper is supported by the European Union’s Horizon 2020research infrastructures programme under grant agreement No857645, project NI4OS Europe (National Initiatives for Open Sciencein Europe).


Institute for Informatics and Automation Problems of the National Academy of Sciences of the Republic of Armenia ; V. Ambartsumian Byurakan Astrophysical Observatory of the National Academy of Sciences of the Republic of Armenia




Astsatryan, H., Knyazyan, A., Mickaelian, A., Sargsyan, L., 2010. Web portal for thearmenian virtual observatory based on armenian national grid infrastructure.Parallel Comput. Control Probl. 109–114. ; Astsatryan, H., Sahakyan, V., Shoukourian, Y., Dongarra, J., Cros, P.-H., Dayde, M.,Oster, P., 2015. Strengthening compute and data intensive capacities of armenia.In: 14th RoEduNet International Conference-Networking in Educationand Research (RoEduNet NER). IEEE, pp. 28–33. ; Buades, A., Coll, B., Morel, J.-M., 2005. A review of image denoising algorithms,with a new one. Multiscale Model. Simul. 4 (2), 490–530. ; Demleitner, M., Gufler, B., Kim, J., Lemson, G., Nickelt-Czycykowski, I., Rauch, T.,Stampa, U., Steinmetz, M., Voges, W., Wambsganss, J., 2007. The germanastrophysical virtual observatory (gavo): archives and applications, statusand services. Astron. Nachr. 328 (7), 713. ; Genova, F., Allen, M.G., Arviset, C., Lawrence, A., Pasian, F., Solano, E., Wambsganss,J., 2015. Euro-vo—Coordination of virtual observatory activities ineurope. Astron. Comput. 11, 181–189. ; Hajian, A., Alvarez, M.A., Bond, J.R., 2015. Machine learning etudes in astrophysics:selection functions for mock cluster catalogs. J. Cosmol. Astropart.Phys. 2015 (01), 038. ; Hanisch, R.J., 2012. Science initiatives of the US virtual astronomical observatory.Open Astron. 21 (3), 301–308. ; Hanisch, R.J., 2014. The virtual observatory: I. Astron. Comput. 7, 1–2. ; Hanisch, R.J., Farris, A., Greisen, E.W., Pence, W.D., Schlesinger, B.M., Teuben, P.J.,Thompson, R.W., Warnock, A., 2001. Definition of the flexible image transportsystem (fits). Astron. Astrophys. 376 (1), 359–380. ; Huchra, J.P., 1977. The nature of markarian galaxies. Astrophys. J. Suppl. Ser. 35,171–195. ; Indolia, S., Goswami, A.K., Mishra, S., Asopa, P., 2018. Conceptual understandingof convolutional neural network-a deep learning approach. Procedia Comput.Sci. 132, 679–688. ; Kohonen, T., 1982. Analysis of a simple self-organizing process. Biol. Cybern. 44(2), 135–140. ; MacQueen, J., et al., 1967. Some methods for classification and analysisof multivariate observations. In: Proceedings of the Fifth Berkeley Symposiumon Mathematical Statistics and Probability. Oakland, CA, USA,pp. 281–297. ; Massaro, E., Mickaelian, A., Nesci, R., Weedman, D., 2008. The digitized firstbyurakan survey. In: Aracne. p. 78. ; Mickaelian, A., Astsatryan, H., Knyazyan, A., Magakian, T.Y., Mikayelyan, G.,Erastova, L., Hovhannisyan, L., Sargsyan, L., Sinamyan, P., 2016. Ten yearsof the armenian virtual observatory. Astron. Soc. Pac. Conf. Ser. 505,16–23. ; Mickaelian, A., Nesci, R., Rossi, C., Weedman, D., Cirimele, G., Sargsyan, L.,Gaudenzi, S., 2007. The digitized first byurakan survey — Dfbs. Astron.Astrophys. 464 (3), 1177–1180. ; Mickaelian, A.M., Sargsyan, L.A., Astsatryan, H.V., Cirimele, G., Nesci, R., 2009.The dfbs spectroscopic database and the armenian virtual observatory. DataSci. J. 0905280112. ; Nair, V., Hinton, G.E., 2010. Rectified linear units improve restricted boltzmannmachines. ICML. ; Pavlidis, T., 2012. Algorithms for graphics and image processing. Springer Science& Business Media. ; Quinn, P.J., Barnes, D.G., Csabai, I., Cui, C., Genova, F., Hanisch, B., Kembhavi,A., Kim, S.C., Lawrence, A., Malkov, O., et al., 2004. The internationalvirtual observatory alliance: recent technical developments and the roadahead. In: Optimizing Scientific Return for Astronomy Through InformationTechnologies, Vol. 5493. International Society for Optics and Photonicspp. 137–145. ; Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. Learning representations byback-propagating errors. Nature 323 (6088), 533–536. ; Scaife, A., 2020. Big telescope, big data: towards exascale with the squarekilometre array. Phil. Trans. R. Soc. A 378 (2166), 20190060. ; Zhang, M., 2019. Use density-based spatial clustering of applications with noise(dbscan) algorithm to identify galaxy cluster members. IOP Conf. Ser.: EarthEnviron. Sci. 242 (4), 042033.


Arts and Humanities Citation Index ; Astrophysics Data System ; INSPEC ; Science Citation Index Expanded ; Scopus ; Web of Science