Spectral classification of young stars using conditional invertible neural networks

I. Introducing and validating the method

¹ Universität Heidelberg, Zentrum für Astronomie, Institut für Theoretische Astrophysik, Albert-Ueberle-Straße 2, 69120 Heidelberg, Germany
e-mail: kang@uni-heidelberg.de
² Universität Heidelberg, Interdisziplinäres Zentrum für Wissenschaftliches Rechnen, Im Neuenheimer Feld 205, 69120 Heidelberg, Germany
³ European Southern Observatory, Karl-Schwarzschild-Str. 2, 85748 Garching bei München, Germany
⁴ Universitäts-Sternwarte, Ludwig-Maximilians-Universität, Scheinerstrasse 1, 81679 München, Germany
⁵ Alma Mater Studiorum Università di Bologna, Dipartimento di Fisica e Astronomia (DIFA), Via Gobetti 93/2, 40129 Bologna, Italy
⁶ INAF – Osservatorio Astrofisico di Arcetri, Largo E. Fermi 5, 50125 Firenze, Italy
⁷ Université Paris Cité, Université Paris-Saclay, CEA, CNRS, AIM, 91191 Gif-sur-Yvette, France
⁸ INAF – Istituto di Astrofisica e Planetologia Spaziali, Via Fosso del Cavaliere 100, 00133 Roma, Italy

Received: 7 March 2023
Accepted: 10 April 2023

Abstract

Aims. We introduce a new deep-learning tool that estimates stellar parameters (e.g. effective temperature, surface gravity, and extinction) of young low-mass stars by coupling the Phoenix stellar atmosphere model with a conditional invertible neural network (cINN). Our networks allow us to infer the posterior distribution of each stellar parameter from the optical spectrum.

Methods. We discuss cINNs trained on three different Phoenix grids: Settl, NextGen, and Dusty. We evaluate the performance of these cINNs on unlearned Phoenix synthetic spectra and on the spectra of 36 class III template stars with well-characterised stellar parameters.

Results. We confirm that the cINNs estimate the considered stellar parameters almost perfectly when tested on unlearned Phoenix synthetic spectra. Applying our networks to class III stars, we find good agreement with deviations of 5–10% at most. The cINNs perform slightly better for earlier-type stars than for later-type stars such as late M-type stars, but we conclude that estimates of effective temperature and surface gravity are reliable for all spectral types within the training range of the network.

Conclusions. Our networks are time-efficient tools that are applicable to large numbers of observations. Among the three networks, we recommend using the cINN trained on the Settl library (Settl-Net) because it provides the best performance across the widest range of temperature and gravity.