A Deep Learning Approach to photospheric Parameters of CARMENES Target Stars

Passegger, Vera Maria; Ordieres-Meré, Joaquin; Bello-García, Antonio; Caballero, José Antonio; Schweitzer, Andreas; Amado, Pedro J.; González-Marcos, Ana; Ribas, Ignasi; Reiners, Ansgar; Quirrenbach, Andreas; Sarro, Luis M.; Solano, Enrique; Azzaro, Marco; Bauer, Florian F.; Béjar, Victor J. S.; Cortés-Contreras, Miriam; Dreizler, Stefan; Hatzes, Artie P.; Henning, Thomas; Jeffers, Sandra V.; Kaminski, Adrian; Kürster, Martin; Lafarga, Marina; Marfil, Emilio; Montes, David; Morales, Juan Carlos; Nagel, Evangelos; Tabernero, Hugo M.; Zechmeister, Mathias
Referencia bibliográfica

Cambridge Workshop on Cool Stars, Stellar Systems, and the Sun

Fecha de publicación:
3
2021
Número de autores
29
Número de autores del IAC
1
Número de citas
1
Número de citas referidas
1
Descripción
We construct an individual convolutional neural network architecture for each of the four stellar parameters effective temperature (Teff), surface gravity (log g), metallicity [M/H], and rotational velocity (v sin i). The networks are trained on synthetic PHOENIX-ACES spectra, showing small training and validation errors. We apply the trained networks to the observed spectra of 283 M dwarfs observed with CARMENES. Although the network models do very well on synthetic spectra, we find large deviations from literature values especially for metallicity, due to the synthetic gap.