Nonsequential neural network for simultaneous, consistent classification, and photometric redshifts of OTELO galaxies

¹ Instituto de Astronomía, Universidad Nacional Autónoma de México, Apdo. Postal 70-264, 04510 Ciudad de México, MX, USA
e-mail: jdo@astro.unam.mx
² Instituto de Astrofísica de Canarias (IAC), 38200 La Laguna, Tenerife, Spain
³ Departamento de Astrofísica, Universidad de La Laguna (ULL), 38205 La Laguna, Tenerife, Spain
⁴ Institut de Radioastronomie Millimétrique (IRAM), Av. Divina Pastora 7, Local 20, 18012 Granada, España
⁵ Asociación Astrofísica para la Promoción de la Investigación, Instrumentación y su Desarrollo, ASPID, 38205 La Laguna, Tenerife, Spain
⁶ Armagh Observatory and Planetarium, College Hill, Armagh BT61 DG, UK
⁷ Departamento de Física de la Tierra y Astrofísica, Instituto de Física de Partículas y del Cosmos (IPARCOS), Universidad Complutense de Madrid, 28040 Madrid, Spain
⁸ Depto. Astrofísica, Centro de Astrobiología (INTA-CSIC), ESAC Campus, Camino Bajo del Castillo s/n, 28692 Villanueva de la Cañada, Spain
⁹ Instituto de Física de Cantabria (CSIC-Universidad de Cantabria), 39005 Santander, Spain
¹⁰ Instituto de Astrofísica de Andalucía, CSIC, Glorieta de la Astronomía, s/n, 18008 Granada, Spain
¹¹ Ethiopian Space Science and Technology Institute (ESSTI), Entoto Observatory and Research Center (EORC), Astronomy and Astrophysics Research and Development Department, PO Box 33679, Addis Ababa, Ethiopia
¹² ISDEFE for European Space Astronomy Centre (ESAC)/ESA, PO Box 78, 28690 Villanueva de la Cañada, Madrid, Spain
¹³ Fundación Galileo Galilei, Telescopio Nazionale Galileo, Rambla José Ana Fernández Pérez, 7, 38712 Breña Baja, Santa Cruz de la Palma, Spain
¹⁴ Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Plaza San Juan, 1, 44001 Teruel, Spain
¹⁵ Department of Astronomy & Astrophysics, University of Toronto, Toronto, ON, Canada

Received: 20 May 2021
Accepted: 20 August 2021

Abstract

Context. Computational techniques are essential for mining large databases produced in modern surveys with value-added products.

Aims. This paper presents a machine learning procedure to carry out a galaxy morphological classification and photometric redshift estimates simultaneously. Currently, only a spectral energy distribution (SED) fitting has been used to obtain these results all at once.

Methods. We used the ancillary data gathered in the OTELO catalog and designed a nonsequential neural network that accepts optical and near-infrared photometry as input. The network transfers the results of the morphological classification task to the redshift fitting process to ensure consistency between both procedures.

Results. The results successfully recover the morphological classification and the redshifts of the test sample, reducing catastrophic redshift outliers produced by an SED fitting and avoiding possible discrepancies between independent classification and redshift estimates. Our technique may be adapted to include galaxy images to improve the classification.