Cloud-Based Machine Learning Service for Astronomical Sub-Object Classification - Case Study On the First Byurakan Survey Spectra - Research Paper

Aug 6, 2026

Upload by Patrick

The classification of astronomical objects in the Digitized First Byurakan Survey (DFBS), covering roughly twenty million sources with low-dispersion spectra, highlights major constraints in accuracy, performance, and computational resources. Because spectral patterns vary across subgroups, sub-object classification is essential to interpret the dataset at higher granularity. The work presents a cloud-based machine learning service that assigns spectral classes and subtypes, emphasizing carbon stars, white dwarfs/subdwarfs, and Markarian (UV-excess) galaxies. Trained on labeled data and provided through a user-friendly interface, the service leverages cloud computing to meet the demands of DFBS-scale analysis.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Virtual observatories and survey challenges

The Digitized First Byurakan Survey (DFBS)

Need for sub-object spectral classification

Proposed cloud-based service

Cloud-Based Machine Learning Service for Astronomical Sub-Object Classification: Case Study On the First Byurakan Survey Spectra HRACHYA ASTSATRYAN STEPAN BABAYAN AREG MICKAELIAN GOR MIKAYELYAN MARTIN ASTSATRYAN *Author affiliations can be found in the back matter of this article ABSTRACT The classification of astronomical objects in the Digitized First Byurakan Survey (DFBS), comprising low-dispersion spectra for approximately twenty million objects, presents challenges regarding performance and computational resources. However, considering the distinct spectral characteristics within subgroups, sub-object classification becomes crucial for a more detailed understanding of the dataset. The article addresses these challenges by proposing a comprehensive cloud-based service for classifying objects into spectral classes and subtypes, with a focus on carbon stars, white dwarfs / subdwarfs, and Markarian (UV-excess) galaxies, which are the primary objects in DFBS. By leveraging the power of cloud computing, it effectively handles the computational requirements associated with analyzing the extensive DFBS dataset. The service employs advanced machine learning algorithms trained on labeled data to classify objects into their respective spectral types and subtypes. The service can be accessed and utilized through a user-friendly interface, making it accessible to a wide range of users in the astronomical community. RESEARCH PAPER CORRESPONDING AUTHOR: Hrachya Astsatryan Institute for Informatics and Automation Problems (IIAP), P. Sevak 1, 0014 Yerevan, Armenia [hrach@sci.am](hrach@sci.am) KEYWORDS: Telescopes; Surveys; Catalogs; Byurakan Plate Archive; Databases; Big Data; Data Mining; Machine Learning; Virtual Observatories TO CITE THIS ARTICLE: Astsatryan, H, Babayan, S, Mickaelian, A, Mikayelyan, G and Astsatryan, M. 2024. Cloud-Based Machine Learning Service for Astronomical Sub-Object Classification: Case Study On the First Byurakan Survey Spectra. Data Science Journal, 23: 6, pp. 1–14. DOI: [https://doi.org/10.5334/dsj-](https://doi.org/10.5334/dsj-)[ ](https://doi.org/10.5334/dsj-)[2024-006](2024-006) 1 INTRODUCTION Astronomical research has produced vast datasets that challenge conventional data management and analysis techniques in recent decades, necessitating innovative approaches due to their sheer volume. Astronomical surveys systematically capture and catalog celestial entities and phenomena across the sky, serving as principal sources for new astronomical revelations. Nevertheless, their utilization remains limited, with only a handful of observatories and a fraction of astronomers depending on them, as pointed observations constitute the norm for most telescopes. A pioneering concept known as Virtual Observatories (VO) has emerged to address these challenges, offering astronomers enhanced efficiency in accessing, processing, and collaborating on astronomical data (Cui and Zhao 2007). VOs encompass interconnected networks of telescopes, data centers, and computational systems designed to support astronomers with interfaces for seamless data access and utilization of advanced computing resources. The International Virtual Observatory Alliance (IVOA) was founded in 2002 to foster the coordinated and structured advancement of VOs (Quinn et al. 2004; Hanisch et al. 2015) . IVOA, encompassing VO initiatives from 22 nations and 2 European projects, orchestrates the integration of astronomical resources and datasets by establishing technical standards for creating VOs and the seamless exchange of information between these platforms. Among these efforts, the Armenian Virtual Observatory (ArVO) has participated actively since 2005 (Mickaelian et al. 2016; Mickaelian et al. 2023) . ArVO is a project of the Byurakan Astrophysical Observatory (BAO) and the Institute for Informatics and Automation Problems, created to provide an advanced platform for astronomers to access and analyze a

FAQs

Why is sub-object classification important for the DFBS dataset?

Sub-object classification is crucial because distinct spectral characteristics appear within subgroups, enabling more detailed understanding beyond broad object categories.

What does the proposed cloud-based service classify?

It classifies astronomical objects into spectral classes and spectral subtypes, with focus on carbon stars, white dwarfs/subdwarfs, and Markarian (UV-excess) galaxies.

How does the service address the computational demands of DFBS?

It leverages cloud computing to handle the computational requirements of analyzing the very large DFBS dataset and runs advanced machine learning algorithms trained on labeled data.

Aug 6, 2026

Upload by Patrick