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

• Main Authors: Du, Minghao, Bi, Shaolan, Zhang, Xianfei, Li, Yaguang, Li, Tanda, Shi, Ruijie
• Format: Journal Article
• Language: English
• Published: 24-12-2020
• Subjects: Physics - Solar and Stellar Astrophysics
• DOI: 10.48550/arxiv.2012.13120

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.