The aim of this work was to obtain precise atmospheric parameters and chemical abundances automatically for solar twins, in order to find signatures of exoplanets, assess how peculiar is the Sun compared to these stars and analyze possible fine structures in the Galactic thin disk. We developed a Neural Network algorithm using python to derive atmospheric parameters and chemical abundances for a sample of 99 solar twins previously studied in the literature directly from normalized high-quality spectra from HARPS, with resolving power R~115000 and signal-to-noise ratio S/N>400. Results. We obtained precise atmospheric parameters and abundance ratios [X/Fe] of 20 chemical elements (Li, C, O, Na, Mg, Al, Si, S, Ca, Sc, Ti, V, Cr, Mn, Co, Ni, Cu, Zn, Y and Ba). The results obtained are in line with the literature, with average differences and standard deviations of (2+/-27)K for Teff , (0.00+/-0.06)dex for logg, (0.00+/-0.02)dex for [Fe/H], (-0.01+/-0.05)km/s for micro turbulence velocity (vt), (0.02+/-0.08)km/s for macro turbulence velocity (vmacro) and (-0.12+/-0.26)km/s for projected rotational velocity (vsini). Regarding the chemical abundances, most of the elements agree with the literature within 0.01-0.02dex. The abundances were corrected from the effects of the Galactic Chemical Evolution through a fitting versus the age of the stars and analyzed with the condensation temperature (Tcond ) to verify if the stars presented depletion of refractories compared to volatiles. We found that the Sun is more depleted in refractory elements compared to volatiles than 89% of the studied solar twins, with a significance of 9.5{sigma} when compared to the stars without detected exoplanets. We also found the possible presence of three subpopulations in the solar twins, one Cu-rich, one Cu-poor, and the other slightly older and poor in Na.

Cone search capability for table J/A+A/699/A46/tablea1 (Stellar parameters obtained using Neural Networks)