The CARMENES search for exoplanets around M dwarfs

A deep transfer learning method to determine T_eff and [M/H] of target stars^★

¹ Departamento de Construcción e Ingeniería de Fabricación, Universidad de Oviedo, c/ Pedro Puig Adam, Sede Departamental Oeste, Módulo 7, 1 a planta, 33203 Gijón, Spain
e-mail: abello@uniovi.es
² Instituto de Astrofísica de Canarias, c/ Vía Láctea s/n, 38205 La Laguna, Tenerife, Spain
³ Departamento de Astrofísica, Universidad de La Laguna, 38206 La Laguna, Tenerife, Spain
⁴ Hamburger Sternwarte, Gojenbergsweg 112, 21029 Hamburg, Germany
⁵ Homer L. Dodge Department of Physics and Astronomy, University of Oklahoma, 440 West Brooks Street, Norman, OK 73019, USA
⁶ Departamento de Ingeniería de Organización, Administración de Empresas y Estadística, Universidad Politécnica de Madrid, c/ José Gutiérrez Abascal 2, 28006 Madrid, Spain
⁷ Centro de Astrobiología (CSIC-INTA), ESAC, Camino bajo del castillo s/n, 28692 Villanueva de la Cañada, Madrid, Spain
⁸ Departamento de Ingeniería Mecánica, Universidad de la Rioja, c/ San José de Calasanz 31, 26004 Logroño, La Rioja, Spain
⁹ Institut de Ciències de l’Espai (CSIC-IEEC), Campus UAB, c/ de Can Magrans s/n, 08193 Bellaterra, Barcelona, Spain
¹⁰ Institut d’Estudis Espacials de Catalunya (IEEC), 08034 Barcelona, Spain
¹¹ Institut für Astrophysik und Geophysik, Georg-August-Universität, Friedrich-Hund-Platz 1, 37077 Göttingen, Germany
¹² Landessternwarte, Zentrum für Astronomie der Universität Heidelberg, Königstuhl 12, 69117 Heidelberg, Germany
¹³ Instituto de Astrofísica de Andalucía (IAA-CSIC), Glorieta de la Astronomía s/n, 18008 Granada, Spain
¹⁴ Max-Planck-Institut für Astronomie, Königstuhl 17, 69117 Heidelberg, Germany
¹⁵ Department of Astronomy and Astrophysics, University of Chicago, Chicago, IL 60637, USA
¹⁶ Departamento de Física de la Tierra y Astrofísica and IPARCOS-UCM (Instituto de Física de Partículas y del Cosmos de la UCM), Facultad de Ciencias Físicas, Universidad Complutense de Madrid, 28040 Madrid, Spain
¹⁷ Centro Astronómico Hispano en Andalucía (CAHA), Observatorio de Calar Alto, Sierra de los Filabres, 04550 Gérgal, Almería, Spain
¹⁸ Centro de Astrobiología (CSIC-INTA), Carretera de Ajalvir km 4, Torrejón de Ardoz, 28850 Madrid, Spain

Received: 3 May 2022
Accepted: 21 March 2023

Abstract

The large amounts of astrophysical data being provided by existing and future instrumentation require efficient and fast analysis tools. Transfer learning is a new technique promising higher accuracy in the derived data products, with information from one domain being transferred to improve the accuracy of a neural network model in another domain. In this work, we demonstrate the feasibility of applying the deep transfer learning (DTL) approach to high-resolution spectra in the framework of photospheric stellar parameter determination. To this end, we used 14 stars of the CARMENES survey sample with interferometric angular diameters to calculate the effective temperature, as well as six M dwarfs that are common proper motion companions to FGK-type primaries with known metallicity. After training a deep learning (DL) neural network model on synthetic PHOENIX-ACES spectra, we used the internal feature representations together with those 14+6 stars with independent parameter measurements as a new input for the transfer process. We compare the derived stellar parameters of a small sample of M dwarfs kept out of the training phase with results from other methods in the literature. Assuming that temperatures from bolometric luminosities and interferometric radii and metallicities from FGK+M binaries are sufficiently accurate, DTL provides a higher accuracy than our previous state-of-the-art DL method (mean absolute differences improve by 20 K for temperature and 0.2 dex for metallicity from DL to DTL when compared with reference values from interferometry and FGK+M binaries). Furthermore, the machine learning (internal) precision of DTL also improves as uncertainties are five times smaller on average. These results indicate that DTL is a robust tool for obtaining M-dwarf stellar parameters comparable to those obtained from independent estimations for well-known stars.