Deep learning applications for stellar parameter determination: II-application to the observed spectra of AFGK stars

• Published in: Open astronomy Vol. 32; no. 1; pp. 1031 - 1037
• Main Authors: Gebran, Marwan, Paletou, Frederic, Bentley, Ian, Brienza, Rose, Connick, Kathleen
• Format: Journal Article
• Language: English
• Published: De Gruyter 23.01.2023
• Subjects: Astrophysics; Data Analysis, Statistics and Probability; data analyzis methods; deep learning methods; fundamental parameter stars; Instrumentation and Methods for Astrophysic; methods; Physics; Sciences of the Universe; Solar and Stellar Astrophysics; spectroscopic techniques; statistical; statistical; data analyzis methods; deep learning methods; fundamental parameter stars; methods; spectroscopic techniques
• ISSN: 2543-6376; 2543-6376
• DOI: 10.1515/astro-2022-0209

In this follow-up article, we investigate the use of convolutional neural network for deriving stellar parameters from observed spectra. Using hyperparameters determined previously, we have constructed a Neural Network architecture suitable for the derivation of , , , and . The network was constrained by applying it to databases of AFGK synthetic spectra at different resolutions. Then, parameters of A stars from Polarbase, SOPHIE, and ELODIE databases are derived, as well as those of FGK stars from the spectroscopic survey of stars in the solar neighbourhood. The network model’s average accuracy on the stellar parameters is found to be as low as 80 K for , 0.06 dex for , 0.08 dex for , and 3 km/s for for AFGK stars.