Mode Angular Degree Identification in Subgiant Stars with Convolutional Neural Networks based on Power Spectrum

Abstract

Identifying the angular degrees $l$ of oscillation modes is essential for asteroseismology and depends on visual tagging before fitting power spectra in a so-called peakbagging analysis. In oscillating subgiants, radial ($l$= 0) mode frequencies distributed linearly in frequency, while non-radial ($l$ >= 1) modes are p-g mixed modes that having a complex distribution in frequency, which increased the difficulty of identifying $l$. In this study, we trained a 1D convolutional neural network to perform this task using smoothed oscillation spectra. By training simulation data and fine-tuning the pre-trained network, we achieved a 95 per cent accuracy on Kepler data.

arXiv comment9 pages, 10 figures, accepted by MNRAS

References in corpus (35)

• Modules for Experiments in Stellar Astrophysics (MESA)
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• GYRE: An open-source stellar oscillation code based on a new Magnus Multiple Shooting Scheme
• Ages and fundamental properties of Kepler exoplanet host stars from asteroseismology
• Asteroseismic fundamental properties of solar-type stars observed by the NASA Kepler Mission
• Ensemble Asteroseismology of Solar-Type Stars with the NASA Kepler Mission
• Standing on the shoulders of Dwarfs: the Kepler asteroseismic LEGACY sample II - radii, masses, and ages
• Standing on the shoulders of Dwarfs: the $Kepler$ asteroseismic LEGACY sample I - oscillation mode parameters
• Asteroseismology of red giants from the first four months of Kepler data: Fundamental parameters
• Probing the core structure and evolution of red giants using gravity-dominated mixed modes observed with Kepler
• Determining global parameters of the oscillations of solar-like stars
• Solar-like oscillations in low-luminosity red giants: first results from Kepler
• Asteroseismology of 16000 Kepler Red Giants: Global Oscillation Parameters, Masses, and Radii
• On detecting the large separation in the autocorrelation of stellar oscillation times series
• Theoretical amplitudes and lifetimes of non-radial solar-like oscillations in red giants
• Galactic archaeology: mapping and dating stellar populations with asteroseismology of red-giant stars
• Asteroseismology of red giants from the first four months of Kepler data: Global oscillation parameters for 800 stars
• Period spacings in red giants II. Automated measurement
• The Octave (Birmingham - Sheffield Hallam) automated pipeline for extracting oscillation parameters of solar-like main-sequence stars
• Impact on asteroseismic analyses of regular gaps in Kepler data
• The quest for the solar g modes
• The K2 Galactic Archaeology Program Data Release 1: Asteroseismic results from Campaign 1
• Deep Learning Classification in Asteroseismology
• Oscillation mode linewidths of main-sequence and subgiant stars observed by Kepler
• Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data
• Modelling Kepler Red Giants in Eclipsing Binaries:Calibrating the Mixing Length Parameter with Asteroseismology
• Inferring mode inertias in evolved solar-like stars
• Properties of oscillation modes in subgiant stars observed by Kepler
• Asteroseismology of 36 \emph{Kepler} subgiants -- I. Oscillation frequencies, linewidths and amplitudes
• New insights on the interior of solar-like pulsators thanks to CoRoT: the case of HD 49385
• Amplitude and lifetime of radial modes in red giant star spectra observed by Kepler
• Detecting Solar-like Oscillations in Red Giants with Deep Learning
• A synthetic sample of short-cadence solar-like oscillators for TESS
• Mode visibilities in radial velocity and photometric Sun-as-a-star helioseismic observations
• Asteroseismic analysis of two alpha-enhanced stars KIC 7976303 and KIC 8694723