J-PAS: A neural network approach to single stellar population characterisation

¹ Instituto de Física de Cantabria Av. de los Castros 39005 Santander Cantabria, Spain
² Centro de Estudios de Física del Cosmos de Aragón, Plaza de San Juan, 1 E-44001 Teruel, Spain
³ Unidad Asociada CEFCA-IAA, CEFCA, Unidad Asociada al CSIC por el IAA y el IFCA Plaza San Juan 1 44001 Teruel, Spain
⁴ Universidade de São Paulo, Instituto de Astronomia, Geofisica e Ciências Atmosféricas, Rua do Matão 1226 05508-090 São Paulo SP, Brazil
⁵ Instituto de Radioastronomía y Astrofísica, Universidad Nacional Autónoma de México, Morelia Michoacán 58089, Mexico
⁶ Instituto de Astrofísica de Andalucía (CSIC) PO Box 3004 18080 Granada, Spain
⁷ Tartu Observatory, University of Tartu Observatooriumi 1 Tõravere 61602, Estonia
⁸ Observatori Astronòmic de la Universitat de València, Ed. Instituts d’Investigació, Parc Científic. C/ Catedrático José Beltrán, n2 46980 Paterna Valencia, Spain
⁹ Departament d’Astronomia i Astrofísica, Universitat de València 46100 Burjassot, Spain
¹⁰ NSF NOIRLab Tucson AZ 85719, USA
¹¹ Departamento de Astronomia, Instituto de Astronomia, Geofísica e Ciências Atmosféricas, Universidade de São Paulo São Paulo, Brazil
¹² Observatório Nacional, Rua General José Cristino, 77 São Cristóvão 20921-400 Rio de Janeiro RJ, Brazil
¹³ Donostia International Physics Center (DIPC), Manuel Lardizabal Ibilbidea, 4 San Sebastián, Spain
¹⁴ Instituto de Astrofísica de Canarias C/ Vía Láctea s/n E-38205 La Laguna Tenerife, Spain
¹⁵ Universidad de La Laguna, Avda Francisco Sánchez E-38206 San Cristóbal de La Laguna Tenerife, Spain
¹⁶ Instruments4 4121 Pembury Place La Canada Flintridge CA 91011, USA

^★ Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Received: 4 July 2025
Accepted: 10 November 2025

Abstract

J-PAS (Javalambre Physics of the Accelerating Universe Astrophysical Survey) will present a groundbreaking photometric survey covering 8500 deg² of the visible sky from Javalambre, capturing data in 56 narrow-band filters. This survey promises to revolutionise galaxy evolution studies by observing ∼10⁸ galaxies with low spectral resolution. A crucial aspect of this analysis involves predicting stellar population parameters from the observed galaxy photometry. In this study, we combined the exquisite J-PAS photometry with state-of-the-art single stellar population (SSP) libraries to accurately predict stellar age, metallicity, and dust attenuation with a neural network (NN) model. The NN was trained on synthetic J-PAS photometry from different SSP libraries (E-MILES, Charlot & Bruzual, and XSL) to enhance the robustness of our predictions against individual SSP model variations and limitations. To create mock samples with varying observed magnitudes, we added artificial noise in the form of random Gaussian variations within typical observational uncertainties in each band. Our results indicate that the NN was able to accurately estimate stellar parameters for SSP models without any evident degeneracies, surpassing a Bayesian SED-fitting method on the same test set. We obtained the median bias, scatter, and the percentage of outliers: μ= (0.01 dex, 0.00 dex, 0.00 mag), σ_NMAD= (0.23 dex, 0.29 dex, 0.04 mag), f_o= (17%, 24%, 1%) at i ∼ 17 mag for the age, metallicity and dust attenuation, respectively. The accuracy of the predictions is highly dependent on the signal-to-noise ratio (S/N) of the photometry, achieving robust predictions up to i ∼ 20 mag.