Study on outliers in the big stellar spectral dataset of the fifth data release (DR5) of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST)

Yan, Lu; Luo, A-Li; Wang, L.-L.; Qin, Li; Wang, R.; Chen, X.-L.; Du, Bing; Zuo, Fang; Hou, Wen; Chen, J.-J.; Tang, Yanke; Han, Jianmin; Zhao, Yi

doi:10.1016/j.ascom.2021.100485

Cited by 1 publication

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been an exponential growth in astronomical data due to the advancements in large-scale sky surveys such as the Sloan Digital Sky Survey (Lyke et al 2020), the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) (Lu et al 2021), the Five-hundred-meter Aperture Spherical radio Telescope (Ching et al 2022), and the Dark Energy Survey (Lahav et al 2020). Among the fundamental tasks in astronomical data analysis, stellar spectral classification is always an important task.…”

Section: Introductionmentioning

confidence: 99%

DRC-Net Method for Two-dimensional Spectral Classification

Zhang¹,

Gao²,

Qiu

et al. 2023

Res. Astron. Astrophys.

View full text Add to dashboard Cite

Spectral classification plays a crucial role in the analysis of astronomical data.Currently, stellar spectral classification primarily relies on one-dimensional (1D) spectra andnecessitates a sufficient signal-to-noise ratio (SNR). However, in cases where the SNR is low,obtaining valuable information becomes impractical. In this paper, we propose a novel modelcalled DRC-Net (Double-branch celestial spectra classification network based on residualmechanisms) for stellar classification, which operates solely on two-dimensional(2D) spec tra. The model consists of two branches that use 1D convolutions to reduce the dimensionalityof the 2D spectral composed of both blue and red arms. In the following the features extractedfrom both branches are fused, and the fused result undergoes further feature extraction beforebeing fed into the classifier for final output generation. The dataset is from the Large Sky AreaMulti-Object Fiber Spectroscopic Telescope (LAMOST), comprising 15,680 spectra of F, G,and K type. The prepocessing process includes normalization and early stopping mechanism.The experimental results demonstrate that the proposed DRC-Net achieved remarkable clas sification precision of 93.0%, 83.5%, and 86.9% for F, G, and K type, respectively, surpassingthe performance of 1D spectral classification methods. Furthermore, different SNR intervalsare tested to judge the classification ability of DRC-Net. The results reveal that DRC-Net, asa 2D spectral classification model, can deliver superior classification outcomes for the spectrawith low SNRs. These experimental findings not only validate the efficiency of DRC-Net butalso confirm the enhanced noise resistance ability exhibited by 2D spectra.

show abstract