Abstract

Context. The APOGEE, GALAH, and LAMOST spectroscopic surveys have substantially contributed to our understanding of the Milky Way by providing a wide range of stellar parameters and chemical abundances. Complementing these efforts, photometric surveys that include narrowband and medium-band filters, such as Southern Photometric Local Universe Survey (S-PLUS), provide a unique opportunity to estimate the atmospheric parameters and elemental abundances for a much larger number of sources, compared to spectroscopic surveys. Aims. Our aim is to establish methodologies for extracting stellar atmospheric parameters and selected chemical abundances from S-PLUS photometric data, which cover approximately 3000 square degrees, by applying seven narrowband and five broadband filters. Methods. We used all 66 S-PLUS colors to estimate parameters based on three different training samples from the LAMOST, APOGEE, and GALAH surveys, applying cost-sensitive neural network (NN) and random forest (RF) algorithms. We kept the stellar abundances that lacked corresponding absorption features in the S-PLUS filters to test for spurious correlations in our method. Furthermore, we evaluated the effectiveness of the NN and RF algorithms by using estimated Teff and log g values as the input features to determine other stellar parameters and abundances. The NN approach consistently outperforms the RF technique on all parameters tested. Moreover, incorporating Teff and log g leads to an improvement in the estimation accuracy by approximately 3%. We kept only parameters with a goodness-of-fit higher than 50%. Results. Our methodology allowed us to obtain reliable estimates for fundamental stellar parameters (Teff, log g, and [Fe/H]) and elemental abundance ratios such as [α/Fe], [Al/Fe], [C/Fe], [Li/Fe], and [Mg/Fe] for approximately five million stars across the Milky Way, with a goodness-of-fit above 60%. We also obtained additional abundance ratios, including [Cu/Fe], [O/Fe], and [Si/Fe]. However, these ratios should be used cautiously due to their low accuracy or lack of a clear relationship with the S-PLUS filters. Validation of our estimations and methods was performed using star clusters, Transiting Exoplanet Survey Satellite (TESS) data and Javalambre Photometric Local Universe Survey (J-PLUS) photometry, further demonstrating the robustness and accuracy of our approach. Conclusions. By leveraging S-PLUS photometric data and advanced machine learning techniques, we have established a robust framework for extracting fundamental stellar parameters and chemical abundances from medium-band and narrowband photometric observations. This approach offers a cost-effective alternative to high-resolution spectroscopy. The estimated parameters hold significant potential for future studies, particularly when classifying objects within our Milky Way or gaining insights into its various stellar populations. © The Authors 2025.