Three-dimensional spectral classification of low-metallicity stars using artificial neural networks

We explore the application of artificial neural networks (ANNs) for the est imation of atmospheric parameters (T-eff, log g, and [Fe/H]) for Galactic F - and G-type stars. The ANNs are fed with medium- resolution (Delta lambda similar to 1-2 Angstrom) non-flux-calibrated spectroscopic observations. Fr om a sample of 279 stars with previous high-resolution determinations of me tallicity and a set of (external) estimates of temperature and surface grav ity, our ANNs are able to predict T-eff with an accuracy of sigma (T-eff) = 135-150 K over the range 4250 less than or equal to T-eff less than or equ al to 6500 K, log g with an accuracy of sigma (log g) = 0.25-0.30 dex over the range 1.0 less than or equal to log g less than or equal to 5.0 dex, an d [Fe/H] with an accuracy sigma([Fe/H]) = 0.15-0.20 dex over the range -4.0 less than or equal to [Fe/H] less than or equal to 0.3. Such accuracies ar e competitive with the results obtained by fine analysis of high-resolution spectra. It is noteworthy that the ANNs are able to obtain these results w ithout consideration of photometric information for these stars. We have al so explored the impact of the signal-to-noise ratio (S/N) on the behavior o f ANNs and conclude that, when analyzed with ANNs trained on spectra of com mensurate S/N, it is possible to extract physical parameter estimates of si milar accuracy with stellar spectra having S/N as low as 13. Taken together , these results indicate that the ANN approach should be of primary importa nce for use in present and future large-scale spectroscopic surveys.