The miniJPAS survey: star-galaxy classification using machine learning^⋆,⋆⋆

¹ PPGFis & Núcleo de Astrofísica e Cosmologia (Cosmo-ufes), Universidade Federal do Espírito Santo, 29075-910 Vitória, ES, Brazil
e-mail: marra@cosmo-ufes.org
² PPGCosmo & Departamento de Física, Universidade Federal do Espírito Santo, 29075-910 Vitória, ES, Brazil
³ INAF – Osservatorio Astronomico di Trieste, Via Tiepolo 11, 34131 Trieste, Italy
⁴ IFPU – Institute for Fundamental Physics of the Universe, Via Beirut 2, 34151 Trieste, Italy
⁵ Departamento de Física, Universidade Federal de Sergipe, 49100-000 Aracaju, SE, Brazil
⁶ Donostia International Physics Center (DIPC), Manuel Lardizabal Ibilbidea, 4, San Sebastián, Spain
⁷ Ikerbasque, Basque Foundation for Science, 48013 Bilbao, Spain
⁸ Academia Sinica Institute of Astronomy & Astrophysics (ASIAA), 11F of Astronomy-Mathematics Building, AS/NTU, No. 1, Section 4, Roosevelt Road, Taipei 10617, Taiwan
⁹ Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Unidad Asociada al CSIC, Plaza San Juan, 1, 44001 Teruel, Spain
¹⁰ Instituto de Astrofísica de Canarias, C/Vía Láctea, s/n, 38205 La Laguna, Tenerife, Spain
¹¹ Departamento de Astrofísica, Universidad de La Laguna, 38206 La Laguna, Tenerife, Spain
¹² Observatório do Valongo, Universidade Federal do Rio de Janeiro, 20080-090 Rio de Janeiro, RJ, Brazil
¹³ Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Plaza San Juan 1, 44001 Teruel, Spain
¹⁴ NSF’s Optical-Infrared Astronomy Research Laboratory, Tucson, AZ 85719, USA
¹⁵ Instituto de Física, Universidade Federal do Rio de Janeiro, 21941-972 Rio de Janeiro, RJ, Brazil
¹⁶ Instituto de Física, Universidade de São Paulo, 05508-090 São Paulo, SP, Brazil
¹⁷ Physics Department, Lancaster University, Lancashire, UK
¹⁸ Departamento de Astrofísica, Centro de Astrobiología (CSIC-INTA), ESAC Campus, Camino Bajo del Castillo s/n, 28692 Villanueva de la Cañada, Madrid, Spain
¹⁹ Tartu Observatory, University of Tartu, Observatooriumi 1, 61602 Tõravere, Estonia
²⁰ Instituto de Astrofísica de Andalucía – CSIC, Apdo 3004, 18080 Granada, Spain
²¹ Observatório Nacional, Ministério da Ciencia, Tecnologia, Inovação e Comunicações, 20921-400 Rio de Janeiro, RJ, Brazil
²² Instituto de Física, Universidade Federal da Bahia, 40210-340 Salvador, BA, Brazil
²³ Departamento de Física-CFM, Universidade Federal de Santa Catarina, 88040-900 Florianópolis, SC, Brazil
²⁴ Departamento de Astronomia, Instituto de Astronomia, Geofísica e Ciências Atmosféricas, Universidade de São Paulo, 05508-090 São Paulo, SP, Brazil
²⁵ Department of Astronomy, University of Michigan, 311West Hall, 1085 South University Ave., Ann Arbor, USA
²⁶ Department of Physics and Astronomy, University of Alabama, Box 870324 Tuscaloosa, AL, USA
²⁷ Instruments4, 4121 Pembury Place, La Cañada Flintridge, CA 91011, USA

Received: 21 July 2020
Accepted: 6 November 2020

Abstract

Context. Future astrophysical surveys such as J-PAS will produce very large datasets, the so-called “big data”, which will require the deployment of accurate and efficient machine-learning (ML) methods. In this work, we analyze the miniJPAS survey, which observed about ∼1 deg² of the AEGIS field with 56 narrow-band filters and 4 ugri broad-band filters. The miniJPAS primary catalog contains approximately 64 000 objects in the r detection band (mag_AB ≲ 24), with forced-photometry in all other filters.

Aims. We discuss the classification of miniJPAS sources into extended (galaxies) and point-like (e.g., stars) objects, which is a step required for the subsequent scientific analyses. We aim at developing an ML classifier that is complementary to traditional tools that are based on explicit modeling. In particular, our goal is to release a value-added catalog with our best classification.

Methods. In order to train and test our classifiers, we cross-matched the miniJPAS dataset with SDSS and HSC-SSP data, whose classification is trustworthy within the intervals 15 ≤ r ≤ 20 and 18.5 ≤ r ≤ 23.5, respectively. We trained and tested six different ML algorithms on the two cross-matched catalogs: K-nearest neighbors, decision trees, random forest (RF), artificial neural networks, extremely randomized trees (ERT), and an ensemble classifier. This last is a hybrid algorithm that combines artificial neural networks and RF with the J-PAS stellar and galactic loci classifier. As input for the ML algorithms we used the magnitudes from the 60 filters together with their errors, with and without the morphological parameters. We also used the mean point spread function in the r detection band for each pointing.

Results. We find that the RF and ERT algorithms perform best in all scenarios. When the full magnitude range of 15 ≤ r ≤ 23.5 is analyzed, we find an area under the curve AUC = 0.957 with RF when photometric information alone is used, and AUC = 0.986 with ERT when photometric and morphological information is used together. When morphological parameters are used, the full width at half maximum is the most important feature. When photometric information is used alone, we observe that broad bands are not necessarily more important than narrow bands, and errors (the width of the distribution) are as important as the measurements (central value of the distribution). In other words, it is apparently important to fully characterize the measurement.

Conclusions. ML algorithms can compete with traditional star and galaxy classifiers; they outperform the latter at fainter magnitudes (r ≳ 21). We use our best classifiers, with and without morphology, in order to produce a value-added catalog.