J-PLUS: Bayesian object classification with a strum of BANNJOS

¹ Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Unidad Asociada al CSIC, Plaza San Juan 1, 44001 Teruel, Spain
² Instituto de Astrofísica de Andalucía, IAA-CSIC, Glorieta de la Astronomía s/n, 18008 Granada, Spain
³ Instituto de Física, Universidade Federal da Bahia, 40170-155, Salvador, BA, Brazil
⁴ PPGCosmo, Universidade Federal do Espírito Santo, 29075-910 Vitória, ES, Brazil
⁵ Instituto de Astronomia, Geofísica e Ciências Atmosféricas, Universidade de São Paulo, 05508-090 São Paulo, Brazil
⁶ Centro de Astrobiología, CSIC-INTA, Camino bajo del castillo s/n, 28692 Villanueva de la Canãda, Madrid, Spain
⁷ Departamento de Física, Universidade Federal do Espírito Santo, 29075-910 Vitória, ES, Brazil
⁸ INAF, Osservatorio Astronomico di Trieste, via Tiepolo 11, 34131 Trieste, Italy
⁹ IFPU, Institute for Fundamental Physics of the Universe, via Beirut 2, 34151 Trieste, Italy
¹⁰ Instituto de Física, Universidade Federal do Rio de Janeiro, 21941-972, Rio de Janeiro, RJ, Brazil
¹¹ Observatório do Valongo, Universidade Federal do Rio de Janeiro, 20080-090, Rio de Janeiro, RJ, Brazil
¹² Observatório Nacional – MCTI (ON), Rua Gal. José Cristino 77, São Cristóvão, 20921-400 Rio de Janeiro, Brazil
¹³ Donostia International Physics Centre (DIPC), Paseo Manuel de Lardizabal 4, 20018 Donostia-San Sebastián, Spain
¹⁴ IKERBASQUE, Basque Foundation for Science, 48013, Bilbao, Spain
¹⁵ University of Michigan, Department of Astronomy, 1085 South University Ave., Ann Arbor, MI 48109, USA
¹⁶ University of Alabama, Department of Physics and Astronomy, Gallalee Hall, Tuscaloosa, AL 35401, USA
¹⁷ Instituto de Astrofísica de Canarias, La Laguna, 38205 Tenerife, Spain
¹⁸ Departamento de Astrofísica, Universidad de La Laguna, 38206 Tenerife, Spain
¹⁹ Centro de Estudios de Física del Cosmos de Aragón (CEFCA), Plaza San Juan 1, 44001 Teruel, Spain

^★ Corresponding author; andresdelpinomolina@gmail.com

Received: 25 April 2024
Accepted: 23 September 2024

Abstract

Context. With its 12 optical filters, the Javalambre-Photometric Local Universe Survey (J-PLUS) provides an unprecedented multicolor view of the local Universe. The third data release (DR3) covers 3192 deg² and contains 47.4 million objects. However, the classification algorithms currently implemented in the J-PLUS pipeline are deterministic and based solely on the morphology of the sources.

Aims. Our goal is to classify the sources identified in the J-PLUS DR3 images as stars, quasi-stellar objects (QSOs), or galaxies. For this task, we present BANNJOS, a machine learning pipeline that utilizes Bayesian neural networks to provide the full probability distribution function (PDF) of the classification.

Methods. BANNJOS has been trained on photometric, astrometric, and morphological data from J-PLUS DR3, Gaia DR3, and CatWISE2020, using over 1.2 million objects with spectroscopic classification from SDSS DR18, LAMOST DR9, the DESI Early Data Release, and Gaia DR3. Results were validated on a test set of about 1.4 × 10⁵ objects and cross-checked against theoretical model predictions.

Results. BANNJOS outperforms all previous classifiers in terms of accuracy, precision, and completeness across the entire magnitude range. It delivers over 95% accuracy for objects brighter than r = 21.5 mag and ~ 90% accuracy for those up to r = 22 mag, where J-PLUS completeness is ≲ 25%. BANNJOS is also the first object classifier to provide the full PDF of the classification, enabling precise object selection for high purity or completeness, and for identifying objects with complex features, such as active galactic nuclei with resolved host galaxies.

Conclusions. BANNJOS effectively classified J-PLUS sources into around 20 million galaxies, one million QSOs, and 26 million stars, with full PDFs for each, which allow for later refinement of the sample. The upcoming J-PAS survey, with its 56 color bands, will further enhance BANNJOS’s ability to detail the nature of each source.