J-PLUS: Stellar parameters, C, N, Mg, Ca, and [α/Fe] abundances for two million stars from DR1

Context. The Javalambre Photometric Local Universe Survey (J-PLUS) has obtained precise photometry in 12 specially designed filters for large numbers of Galactic stars. Deriving their precise stellar atmospheric parameters and individual elemental abundances is crucial for studies of Galactic structure and the assembly history and chemical evolution of our Galaxy. Aims. Our goal is to estimate not only stellar parameters (effective temperature, Teff, surface gravity, log g, and metallicity, [Fe/H]), but also [α/Fe] and four elemental abundances ([C/Fe], [N/Fe], [Mg/Fe], and [Ca/Fe]) using data from the first data release (DR1) of J-PLUS. Methods. By combining recalibrated photometric data from J-PLUS DR1, Gaia DR2, and spectroscopic labels from the Large sky Area Multi-Object fiber Spectroscopic Telescope, we designed and trained a set of cost-sensitive neural networks, the CSNet, to learn the nonlinear mapping from stellar colours to their labels. Special attention was paid to the poorly populated regions of the label space by giving different weights according to their density distribution. Results. We achieved precisions of δ Teff ∼ 55 K, δlog g ∼ 0.15 dex, and δ [Fe/H] ∼ 0.07 dex, respectively, over a wide range of temperatures, surface gravities, and metallicities. The uncertainties of the abundance estimates for [α/Fe] and the four individual elements are in the 0.04–0.08 dex range. We compare our parameter and abundance estimates with those from other spectroscopic catalogs such as the Apache Point Observatory for Galactic Evolution Experiment and the Galactic Archaeology with High Efficiency and Resolution Multi-Element Spectrograph and find an overall good agreement. Conclusions. Our results demonstrate the potential of well-designed, high-quality photometric data for determinations of stellar parameters as well as individual elemental abundances. Applying the method to J-PLUS DR1, we obtained the aforementioned parameters for about two million stars, providing an outstanding dataset for chemo-dynamic analyses of the Milky Way. The catalog of the estimated parameters is publicly accessible.