Abstract
In this work we used a convolutional neural network to determine the so called, large separation (\(\Delta \nu \)), a pattern in the oscillation frequency that is a proxy for the stellar mean density, which is key to constraint the internal structure of stars, and thereby their evolution. We trained a CNN with a grid of asteroseismic models representative of intermediate-mass stars (from 1.5 to 3 times more massive than the Sun) and validated it with a sample of observed benchmark stars. We found that the CNN was around 56% accurate finding the actual values of \(\Delta \nu \), and 94% when considering multiples and/or submultiples of \(\Delta \nu \). This method will allow us to analyse massively thousands of A-F stars observed by past, present and future space missions such as CoRoT, Kepler/K2, TESS, and the upcoming PLATO mission.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A type of intermediate-mass that pulsate with pressure modes.
References
Barceló Forteza, S., Moya, A., Barrado, D., Solano, E., Martín-Ruiz, S., Suárez, J.C., García Hernández, A.: Unveiling the power spectra of \({\delta }\) Scuti stars with TESS. The temperature, gravity, and frequency scaling relation. Astron. Astrophys. 638, A59 (2020). https://doi.org/10.1051/0004-6361/201937262
Barceló Forteza, S., Roca Cortés, T., García, R.A.: The envelope of the power spectra of over a thousand \({\delta }\) Scuti stars. The \({\bar T}_{eff}\) - \({\nu }\)\({ }_{max}\) scaling relation. Astron. Astrophys. 614, A46 (2018). https://doi.org/10.1051/0004-6361/201731803
Bedding, T.R., Murphy, S.J., Hey, D.R., Huber, D., Li, T., Smalley, B., Stello, D., White, T.R., Ball, W.H., Chaplin, W.J., Colman, I.L., Fuller, J., Gaidos, E., Harbeck, D.R., Hermes, J.J., Holdsworth, D.L., Li, G., Li, Y., Mann, A.W., Reese, D.R., Sekaran, S., Yu, J., Antoci, V., Bergmann, C., Brown, T.M., Howard, A.W., Ireland, M.J., Isaacson, H., Jenkins, J.M., Kjeldsen, H., McCully, C., Rabus, M., Rains, A.D., Ricker, G.R., Tinney, C.G., Vanderspek, R.K.: Very regular high-frequency pulsation modes in young intermediate-mass stars. Nature 581(7807), 147–151 (2020). https://doi.org/10.1038/s41586-020-2226-8
García Hernández, A., Moya, A., Michel, E., Garrido, R., Suárez, J.C., Rodríguez, E., Amado, P.J., Martín-Ruiz, S., Rolland, A., Poretti, E., Samadi, R., Baglin, A., Auvergne, M., Catala, C., Lefevre, L., Baudin, F., Rodriguez, E., Amado, P.J., Martin-Ruiz, S., Rolland, A., Poretti, E., Samadi, R., Baglin, A., Auvergne, M., Catala, C., Lefevre, L., Baudin, F.: Asteroseismic analysis of the CoRoT \(\delta \) Scuti star HD 174936. Astron. Astrophys. 506(1), 79–83 (2009)
Hernández, A.G., Suárez, J.C., Moya, A., Monteiro, M.J.P.F.G., Guo, Z., Reese, D.R., Pascual-Granado, J., Forteza, S.B., Martín-Ruiz, S., Garrido, R., Nieto, J.: Precise surface gravities of \(\delta \) Scuti stars from asteroseismology. Month. Not. R. Astron. Soc. Lett. 471(1), L140–L144 (2017). https://doi.org/10.1093/mnrasl/slx117. http://arxiv.org/abs/1707.06835
Moya, A., Suárez, J.C., García Hernández, A., Mendoza, M.A.: Semi-empirical seismic relations of A-F stars from CoRoT and Kepler legacy data. Month. Not. R. Astron. Soc. 471(2), 2491–2497 (2017). https://doi.org/10.1093/mnras/stx1717. https://arxiv.org/pdf/1707.02082.pdf
Ramón-Ballesta, A., García Hernández, A., Suárez, J.C., Rodón, J.R., Pascual-Granado, J., Garrido, R.: Study of rotational splittings in \({\delta }\) Scuti stars using pattern finding techniques. Month. Not. R. Astron. Soc. 505(4), 6217–6224 (2021). https://doi.org/10.1093/mnras/stab1719
Reese, D., Lignières, F., Rieutord, M.: Regular patterns in the acoustic spectrum of rapidly rotating stars. Astron. Astrophys. 481(2), 449–452 (2008)
Suárez, J.C., Hernández, A.G., Moya, A., Rodrigo, C., Solano, E., Garrido, R., Rodón, J.R.: Measuring mean densities of delta Scuti stars with asteroseismology. Theoretical properties of large separations using TOUCAN. Astron. Astrophys. 563(A7), 11 (2014)
Acknowledgements
JCS, AGH, RM, SBF, and GM acknowledge support by University of Granada and by Spanish public funds for research under project “Contribution of the UGR to the PLATO2.0 space mission. Phases C/D-1”, funded by MCNI/AEI/PID2019-107061GB-C64. AGH also acknowledges support from “FEDER/Junta de Andalucía-Consejería de Economía y Conocimiento” under project E-FQM-041-UGR18 by Universidad de Granada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Suárez, J.C., Hernández, A.G., Maestre, R., Forteza, S.B., Mirouh, G. (2023). A Convolutional Neural Network to Characterise the Internal Structure of Stars. In: Bufano, F., Riggi, S., Sciacca, E., Schilliro, F. (eds) Machine Learning for Astrophysics. ML4Astro 2022. Astrophysics and Space Science Proceedings, vol 60. Springer, Cham. https://doi.org/10.1007/978-3-031-34167-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-34167-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34166-3
Online ISBN: 978-3-031-34167-0
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)