The miniJPAS survey quasar selection – II. Machine learning classification with photometric measurements and uncertainties

Journal Article · Fri Feb 17 00:00:00 EST 2023 · Monthly Notices of the Royal Astronomical Society

DOI:https://doi.org/10.1093/mnras/stac2836· OSTI ID:2425349

Rodrigues, Natália V N ^[1]; Abramo, L Raul ^[1]; Queiroz, Carolina ^[2]; Martínez-Solaeche, Ginés ^[3]; Pérez-Ràfols, Ignasi ^[4]; Bonoli, Silvia ^[5]; Chaves-Montero, Jonás ^[6]; Pieri, Matthew M ^[7]; González Delgado, Rosa M ^[3]; Morrison, Sean S ^[8]; Marra, Valerio ^[9]; Márquez, Isabel ^[3]; Hernán-Caballero, A ^[10]; Díaz-García, L A ^[3]; Benítez, Narciso ^[3]; Cenarro, A Javier ^[10]; Dupke, Renato A ^[11]; Ederoclite, Alessandro ^[10]; López-Sanjuan, Carlos ^[10]; Marín-Franch, Antonio ^[10] ; Mendes de Oliveira, Claudia ^[1]; Moles, Mariano ^[12]; Sodré, Laerte ^[1]; Varela, Jesús ^[10]; Ramió, Héctor Vázquez ^[10]; Taylor, Keith ^[13]

---

1. Universidade de São Paulo (Brazil)
2. Universidade de São Paulo (Brazil); Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS (Brazil)
3. Consejo Superior de Investigaciones Cientificas (CSIC), Granada (Spain). Instituto de Astrofísica de Andalucía
4. Barcelona Institute of Science and Technology (BIST), Barcelona (Spain). Institut de Física d’Altes Energies (IFAE); Sorbonne Univ., Paris (France); University Paris-Diderot (France); Centre National de la Recherche Scientifique (CNRS) (France)
5. Donostia International Physics Center (DIPC), San Sebastian (Spain); Basque Foundation for Science, Bilbao (Spain). IKERBASQUE
6. Donostia International Physics Center (DIPC), San Sebastian (Spain)
7. Aix-Marseille Univ., Marseille (France); Centre National de la Recherche Scientifique (CNRS) (France)
8. Aix-Marseille Univ., Marseille (France); Centre National de la Recherche Scientifique (CNRS) (France); Univ. of Illinois at Urbana-Champaign, IL (United States)
9. Istituto Nazionale di Astrofisica (INAF), Trieste (Italy). Osservatorio Astrofisico di Trieste; Institute for Fundamental Physics of the Universe (IFPU), Trieste (Italy)
10. Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Teruel (Spain)
11. Observatório Nacional, Rio de Janeiro (Brazil); Univ. of Michigan, Ann Arbor, MI (United States); Univ. of Alabama, Tuscaloosa, AL (United States)
12. Consejo Superior de Investigaciones Cientificas (CSIC), Granada (Spain). Instituto de Astrofísica de Andalucía; Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Teruel (Spain)
13. Instruments, La Canada Flintridge, CA (United States)

Astrophysical surveys rely heavily on the classification of sources as stars, galaxies, or quasars from multiband photometry. Surveys in narrow-band filters allow for greater discriminatory power, but the variety of different types and redshifts of the objects present a challenge to standard template-based methods. In this work, which is part of a larger effort that aims at building a catalogue of quasars from the miniJPAS survey, we present a machine learning-based method that employs convolutional neural networks (CNNs) to classify point-like sources including the information in the measurement errors. We validate our methods using data from the miniJPAS survey, a proof-of-concept project of the Javalambre Physics of the Accelerating Universe Astrophysical Survey (J-PAS) collaboration covering ∼1 deg² of the northern sky using the 56 narrow-band filters of the J-PAS survey. Due to the scarcity of real data, we trained our algorithms using mocks that were purpose-built to reproduce the distributions of different types of objects that we expect to find in the miniJPAS survey, as well as the properties of the real observations in terms of signal and noise. We compare the performance of the CNNs with other well-established machine learning classification methods based on decision trees, finding that the CNNs improve the classification when the measurement errors are provided as inputs. The predicted distribution of objects in miniJPAS is consistent with the putative luminosity functions of stars, quasars, and unresolved galaxies. Our results are a proof of concept for the idea that the J-PAS survey will be able to detect unprecedented numbers of quasars with high confidence.

• Research Organization: US Department of Energy (USDOE), Washington, DC (United States). Office of Science, Sloan Digital Sky Survey (SDSS)
• Sponsoring Organization: French National Research Agency (ANR); Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP); National Council for Scientific and Technological Development (CNPq); Spanish Ministry of Economy and Competitiveness; Spanish Ministry of Science, Innovation, and Universities
• OSTI ID: 2425349
• Journal Information: Monthly Notices of the Royal Astronomical Society, Journal Name: Monthly Notices of the Royal Astronomical Society Journal Issue: 3 Vol. 520; ISSN 1365-2966; ISSN 0035-8711
• Publisher: Oxford University Press
• Country of Publication: United States
• Language: English

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
cosmology: observations
methods: data analysis
quasars: general
techniques: photometric