A Robust Identification Method for Hot Subdwarfs Based on Deep Learning

• Published in: The Astrophysical journal. Supplement series Vol. 259; no. 1; pp. 5 - 12
• Main Authors: Tan, Lei, Mei, Ying, Liu, Zhicun, Luo, Yangping, Deng, Hui, Wang, Feng, Deng, Linhua, Liu, Chao
• Format: Journal Article
• Language: English
• Published: Saskatoon The American Astronomical Society 01.03.2022; IOP Publishing
• Subjects: Accuracy; Artificial neural networks; Atmospheric diffusion; Atmospheric evolution; Binary stars; Classification; Convolutional neural networks; Deep learning; Diffusion processes; Identification methods; Machine learning; Model accuracy; Modelling; Neural networks; Robustness; Spectra; Stellar classification; Stellar evolution; Stellar types; Subdwarf stars
• ISSN: 0067-0049; 1538-4365
• DOI: 10.3847/1538-4365/ac4de8

Abstract Hot subdwarf stars are a particular type of star that is crucial for studying binary evolution and atmospheric diffusion processes. In recent years, identifying hot subdwarfs by machine-learning methods has become a hot topic, but there are still limitations in automation and accuracy. In this paper, we proposed a robust identification method based on a convolutional neural network. We first constructed the data set using the spectral data of LAMOST DR7-V1. We then constructed a hybrid recognition model including an eight-class classification model and a binary classification model. The model achieved an accuracy of 96.17% on the testing set. To further validate the accuracy of the model, we selected 835 hot subdwarfs that were not involved in the training process from the identified LAMOST catalog (2428, including repeated observations) as the validation set. An accuracy of 96.05% was achieved. On this basis, we used the model to filter and classify all 10,640,255 spectra of LAMOST DR7-V1, and obtained a catalog of 2393 hot subdwarf candidates, of which 2067 have been confirmed. We found 25 new hot subdwarfs among the remaining candidates by manual validation. The overall accuracy of the model is 87.42%. Overall, the model presented in this study can effectively identify specific spectra with robust results and high accuracy, and can be further applied to the classification of large-scale spectra and the search for specific targets.