We show that the masses of red giant stars can be well predicted from their photospheric carbon and nitrogen abundances , in conjunction with their spectroscopic stellar labels log g , T _ { \mathrm { eff } } , and [ Fe/H ] .
This is qualitatively expected from mass-dependent post main sequence evolution .
We here establish an empirical relation between these quantities by drawing on 1,475 red giants with asteroseismic mass estimates from Kepler that also have spectroscopic labels from APOGEE DR12 .
We assess the accuracy of our model , and find that it predicts stellar masses with fractional r.m.s .
errors of about 14 % ( typically 0.2 M _ { \odot } ) .
From these masses , we derive ages with r.m.s errors of 40 % .
This empirical model allows us for the first time to make age determinations ( in the range 1–13 Gyr ) for vast numbers of giant stars across the Galaxy .
We apply our model to \sim 52,000 stars in APOGEE DR12 , for which no direct mass and age information was previously available .
We find that these estimates highlight the vertical age structure of the Milky Way disk , and that the relation of age with [ \alpha /M ] and metallicity is broadly consistent with established expectations based on detailed studies of the solar neighbourhood .