Using deep learning to characterize single-exposure double-line spectroscopic binaries

TL;DR

This paper introduces a deep learning method to analyze single-exposure spectra of double-line spectroscopic binaries, enabling extraction of stellar parameters without traditional spectral disentangling, thus aiding large survey data analysis.

Contribution

The paper presents a novel deep neural network approach for characterizing SB2 components from single spectra, bypassing the need for multiple observations or spectral disentangling.

Findings

Neural network accurately predicts stellar parameters from simulated Gaia-like spectra.

Method performs well without explicit spectral disentangling or radial velocity extraction.

Tool is expected to facilitate analysis of large spectroscopic survey data.

Abstract

Distinguishing the component spectra of double-line spectroscopic binaries (SB2s) and extracting their stellar parameters is a complex and computationally intensive task that usually requires observations spanning several epochs that represent various orbital phases. This poses an especially significant challenge for large surveys such as Gaia or LAMOST, where the number of available spectra per target is often not enough for a proper spectral disentangling. We present a new approach for characterizing SB2 components from single-exposure spectroscopic observations. The proposed tool uses deep neural networks to extract the stellar parameters of the individual component spectra that comprise the single exposure, without explicitly disentangling them or extracting their radial velocities. The neural networks were trained, tested, and validated using simulated data resembling Gaia RVS spectra, which will be made available to the community in the coming Gaia data releases. We expect our tool to be useful in their analysis.