Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data

Abstract

Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS and PLATO, we train classifiers that are able to classify the evolutionary states of lower frequency resolution spectra expected from these missions. Additionally, we provide new classifications for 8633 Kepler red giants, out of which 426 have previously not been classified using asteroseismology. This brings the total to 14983 Kepler red giants classified with our new neural network. We also verify that our classifiers are remarkably robust to suboptimal data, including low signal-to-noise and incorrect training truth labels.

12 pages, 14 figures, 4 tables. Accepted for publication in the Main Journal of MNRAS. The catalogue containing updated evolutionary state classifications of ~16000 Kepler red giants is available as an ancillary file

References in corpus (12)

• The Transiting Exoplanet Survey Satellite
• The K2 Mission: Characterization and Early results
• The APOKASC Catalog: An Asteroseismic and Spectroscopic Joint Survey of Targets in the Kepler Fields
• EVEREST: Pixel Level Decorrelation of K2 Light curves
• Mixed modes in red giants: a window on stellar evolution
• The asteroseismic potential of TESS: exoplanet-host stars
• PLATO as it is: a legacy mission for Galactic archaeology
• The K2 Galactic Archaeology Program Data Release 1: Asteroseismic results from Campaign 1
• The K2 M67 Study: Revisiting old friends with K2 reveals oscillating red giants in the open cluster M67
• Deep Learning Classification in Asteroseismology
• Theoretical power spectra of mixed modes in low mass red giant stars
• A New Method for the Asteroseismic Determination of the Evolutionary State of Red-Giant Stars

Cited by in corpus (48)

• Surface rotation and photometric activity for Kepler targets I. M and K main-sequence stars
• The K2-HERMES Survey: Age and Metallicity of the Thick Disc
• J-PLUS: Identification of low-metallicity stars with artificial neural networks using SPHINX
• Gaia Data Release 3: Pulsations in main sequence OBAF-type stars
• Giant planet occurrence within 0.2 AU of low-luminosity red giant branch stars with K2
• Detection and characterisation of oscillating red giants: first results from the TESS satellite
• The GALAH survey: A census of lithium-rich giant stars
• Prospects for Galactic and stellar astrophysics with asteroseismology of giant stars in the $TESS$ Continuous Viewing Zones and beyond
• The K2 Galactic Archaeology Program Data Release 3: Age-abundance patterns in C1-C8 and C10-C18
• Benchmark ages for the Gaia benchmark stars
• TESS Asteroseismology of the known red-giant host stars HD 212771 and HD 203949
• Asteroseismology of 36 \emph{Kepler} subgiants -- I. Oscillation frequencies, linewidths and amplitudes
• TESS asteroseismology of the Kepler red giants
• Insights from the APOKASC Determination of the Evolutionary State of Red-Giant Stars by consolidation of different methods
• Detecting Solar-like Oscillations in Red Giants with Deep Learning
• FliPer: A global measure of power density to estimate surface gravities of main-sequence Solar-like stars and red giants
• Age-Dating Red Giant Stars Associated with Galactic Disk and Halo Substructures
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• The K2 Galactic Archaeology Program Data Release 2: Asteroseismic results from campaigns 4, 6, & 7
• Age Determination of Galaxy Merger Remnant Stars using Asteroseismology
• Asteroseismology of the Hyades red giant and planet host epsilon Tauri
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Hierarchically modelling Kepler dwarfs and subgiants to improve inference of stellar properties with asteroseismology
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• The APO-K2 Catalog. II. Accurate Stellar Ages for Red Giant Branch Stars across the Milky Way
• HD-TESS: An Asteroseismic Catalog of Bright Red Giants within TESS Continuous Viewing Zones
• Lithium Evolution of Giant Stars Observed by LAMOST and Kepler
• Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
• Clumpiness: Time-domain classification of red-giant evolutionary states
• Neural network for determining an asteroid mineral composition from reflectance spectra
• Unveiling the Structure and Dynamics of Red Giants with Asteroseismology
• Multiscale entropy analysis of astronomical time series. Discovering subclusters of hybrid pulsators
• Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
• Modeling Asteroseismic Yields for the Roman Galactic Bulge Time-Domain Survey
• Revisiting the Red-giant Branch Hosts KOI-3886 and $\iota$ Draconis. Detailed Asteroseismic Modeling and Consolidated Stellar Parameters
• Red giants evolutionary status determination: the complete Kepler catalog
• Vetting Asteroseismic $\Delta \nu$ Measurements using Neural Networks
• K2-HERMES II. Planet-candidate properties from K2 Campaigns 1-13
• FliPer${}_{Class}$: In search of solar-like pulsators among TESS targets
• Modelling stars with Gaussian Process Regression: Augmenting Stellar Model Grid
• Mode Angular Degree Identification in Subgiant Stars with Convolutional Neural Networks based on Power Spectrum
• CN and CO Features: Key Indicators of Red Giant Evolutionary Phase in Moderate-Resolution X-Shooter Spectra
• Asteroseismically Inferred Ages of 132,000 Red Giants with TESS
• The K2 Galactic Archaeology Program: Overview, target selection and survey properties
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• A 'Quick Look' at All-Sky Galactic Archeology with TESS: 158,000 Oscillating Red Giants from the MIT Quick-Look Pipeline
• Asteroseismology of iota Draconis and Discovery of an Additional Long-Period Companion
• Physical interpretation of the oscillation spectrum on the RGB and AGB