Deep Learning Classification in Asteroseismology

Abstract

In the power spectra of oscillating red giants, there are visually distinct features defining stars ascending the red giant branch from those that have commenced helium core burning. We train a one-dimensional convolutional neural network by supervised learning to automatically learn these visual features from images of folded oscillation spectra. By training and testing on \textit{Kepler} red giants, we achieve an accuracy of up to 99\% in separating helium-burning red giants from those ascending the red giant branch. The convolutional neural network additionally shows capability in accurately predicting the evolutionary states of 5379 previously unclassified \textit{Kepler} red giants, by which we now have greatly increased the number of classified stars.

6 pages, 7 figures. Published in the Monthly Notices of the Royal Astronomical Society. Classification tables are available as ancillary files (sidebar on the right), or in zipped form from https://academic.oup.com/mnras/article-lookup/doi/10.1093/mnras/stx1174#supplementary-data

References in corpus (15)

• Improving neural networks by preventing co-adaptation of feature detectors
• The Transiting Exoplanet Survey Satellite
• Gravity modes as a way to distinguish between hydrogen- and helium-burning red giant stars
• Calculating asteroseismic diagrams for solar-like oscillations
• Asteroseismic classification of stellar populations among 13000 red giants observed by Kepler
• Theoretical amplitudes and lifetimes of non-radial solar-like oscillations in red giants
• Mixed modes in red giants: a window on stellar evolution
• 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
• A prevalence of dynamo-generated magnetic fields in the cores of intermediate-mass stars
• Evolutionary influences on the structure of red-giant acoustic oscillation spectra from 600d of Kepler observations
• 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
• Suppression of quadrupole and octupole modes in red giants observed by Kepler
• On the asymptotic acoustic-mode phase in red-giant stars and its dependence on evolutionary state

Cited by in corpus (40)

• Asteroseismology of 16000 Kepler Red Giants: Global Oscillation Parameters, Masses, and Radii
• Confirming chemical clocks: asteroseismic age dissection of the Milky Way disk(s)
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data
• APOKASC-3: The Third Joint Spectroscopic and Asteroseismic catalog for Evolved Stars in the Kepler Fields
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• J-PLUS: Identification of low-metallicity stars with artificial neural networks using SPHINX
• Most Lithium-rich Low-mass Evolved Stars Revealed as Red Clump stars by Asteroseismology and Spectroscopy
• Mass and Age of Red Giant Branch Stars Observed with LAMOST and \emph{Kepler}
• Discovery of post-mass-transfer helium-burning red giants using asteroseismology
• The K2 Galactic Archaeology Program Data Release 3: Age-abundance patterns in C1-C8 and C10-C18
• TESS Asteroseismology of the known red-giant host stars HD 212771 and HD 203949
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Amplitude and lifetime of radial modes in red giant star spectra observed by Kepler
• Asteroseismology of 3,642 Kepler Red Giants: Correcting the Scaling Relations based on Detailed Modeling
• Nonlinear seismic scaling relations
• The CARMENES search for exoplanets around M dwarfs -- A deep learning approach to determine fundamental parameters of target stars
• A prescription for the asteroseismic surface correction
• Detecting Solar-like Oscillations in Red Giants with Deep Learning
• Deep Horizon; a machine learning network that recovers accreting black hole parameters
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• Mode Classification in Fast-Rotating Stars using a Convolutional Neural Network: Model-Based Regular Patterns in $\delta$ Scuti Stars
• Testing the intrinsic scatter of the asteroseismic scaling relations with Kepler red giants
• The K2 Galactic Archaeology Program Data Release 2: Asteroseismic results from campaigns 4, 6, & 7
• 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
• HD-TESS: An Asteroseismic Catalog of Bright Red Giants within TESS Continuous Viewing Zones
• Semi-empirical seismic relations of A-F stars from CoRoT and Kepler legacy data
• Lithium abundances and asteroseismology of red giants: understanding the evolution of lithium in giants based on asteroseismic parameters
• A Unified Exploration of the Chronology of the Galaxy
• Identifying MgII Narrow Absorption Lines with Deep Learning
• Unveiling complex magnetic field configurations in red giant stars
• Deep Transfer Learning for Classification of Variable Sources
• 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
• Uncovering the ultimate planet impostor. An eclipsing brown dwarf in a hierarchical triple with two evolved stars
• Mode Angular Degree Identification in Subgiant Stars with Convolutional Neural Networks based on Power Spectrum
• 200,000+ Deep Learning-inferred Periods of Stellar Variability from the All-Sky Automated Survey for Supernovae
• Asteroseismology of iota Draconis and Discovery of an Additional Long-Period Companion
• Physical interpretation of the oscillation spectrum on the RGB and AGB