Atmospheric parameter measurement of Low-S/N stellar spectra based on deep learning

Abstract Deriving accurate atmospheric parameters from stellar spectra is of fundamental importance for stellar research. At present, machine learning, such as multiple linear regression, artificial neural networks (ANN), and support vector machines, have been widely used to derive atmospheric parameters. However, these methods are generally only applicable to estimate the atmospheric parameters of high signal-to-noise ratio (high-S/N) stellar spectra. For low signal-to-noise ratio (low-S/N) stellar spectra, these methods tend to perform poorly. In order to address the problem, we propose a one-dimensional convolutional neural network StarNet. The proposed method includes the following three steps: firstly, select the spectra with S/N

[1]  Carlos Bacigalupo,et al.  The GALAH survey: observational overview and Gaia DR1 companion , 2016, 1609.02822.

[2]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Sergey E. Koposov,et al.  The RAVE-on Catalog of Stellar Atmospheric Parameters and Chemical Abundances for Chemo-dynamic Studies in the Gaia Era , 2016, 1609.02914.

[4]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[5]  Jingchang Pan,et al.  Stellar atmospheric parameter estimation using Gaussian process regression , 2015 .

[6]  Bingqiu Chen,et al.  LAMOST Spectroscopic Survey of the Galactic Anticentre (LSS-GAC): the second release of value-added catalogues , 2017, 1701.05409.

[7]  Sebastien Fabbro,et al.  An application of deep learning in the analysis of stellar spectra , 2017, 1709.09182.

[8]  Wu Hao,et al.  Optimized CNN Based Image Recognition Through Target Region Selection , 2018 .

[9]  U. Munari,et al.  The radial velocity experiment (RAVE): First data release , 2006 .

[10]  Bingqiu Chen,et al.  LAMOST Spectroscopic Survey of the Galactic Anticentre (LSS-GAC): target selection and the first release of value-added catalogues , 2014, 1412.6628.

[11]  Application of Multi-task Sparse Lasso Feature Extraction and Support Vector Machine Regression in the Stellar Atmospheric Parameterization☆☆☆ , 2017 .

[12]  Xiangru Li,et al.  Estimating stellar atmospheric parameters based on LASSO and support-vector regression , 2015, 1508.00369.

[13]  Chao Liu,et al.  Mapping the Milky Way with LAMOST I: method and overview , 2017, 1701.07831.

[14]  Carlos Dafonte,et al.  ANNs and Wavelets: A Strategy for Gaia RVS Low S/N Stellar Spectra Parameterization , 2010 .

[15]  Annie C. Robin,et al.  ABUNDANCES, STELLAR PARAMETERS, AND SPECTRA FROM THE SDSS-III/APOGEE SURVEY , 2015, 1501.04110.

[16]  Yude Bu,et al.  ELM: AN ALGORITHM TO ESTIMATE THE ALPHA ABUNDANCE FROM LOW-RESOLUTION SPECTRA , 2016 .

[17]  M. Tsantaki,et al.  New Teff and [Fe/H] spectroscopic calibration for FGK dwarfs and GK giants , 2016, 1608.08392.

[18]  Wei Zhang,et al.  Estimating stellar atmospheric parameters, absolute magnitudes and elemental abundances from the LAMOST spectra with Kernel-based principal component analysis , 2016, 1610.00083.

[19]  Haifeng Yang,et al.  SVM-Lattice: A Recognition and Evaluation Frame for Double-Peaked Profiles , 2020, IEEE Access.

[20]  H. Rix,et al.  Prospects for Measuring Abundances of >20 Elements with Low-resolution Stellar Spectra , 2017, 1706.00111.

[21]  Jifu Zhang,et al.  DoPS: A Double-Peaked Profiles Search Method Based on the RS and SVM , 2019, IEEE Access.

[22]  Tan Yang,et al.  An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters , 2015, 1508.00338.

[23]  Jo Bovy,et al.  Deep learning of multi-element abundances from high-resolution spectroscopic data , 2018, Monthly Notices of the Royal Astronomical Society.

[24]  Yongheng Zhao,et al.  SDSS/SEGUE SPECTRAL FEATURE ANALYSIS FOR STELLAR ATMOSPHERIC PARAMETER ESTIMATION , 2014, 1504.02558.

[25]  Nicholas Troup,et al.  ASPCAP: THE APOGEE STELLAR PARAMETER AND CHEMICAL ABUNDANCES PIPELINE , 2015, 1510.07635.

[26]  Observatoire de la Côte d'Azur,et al.  Gaia Data Release 1. Summary of the astrometric, photometric, and survey properties , 2016, 1609.04172.

[27]  Olivier Bienayme,et al.  THE RADIAL VELOCITY EXPERIMENT (RAVE): FIFTH DATA RELEASE , 2013, 1609.03210.

[28]  I. Jolliffe.  Principal Component Analysis , 2002 .

[29]  Carlos Dafonte,et al.  On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra , 2016, ArXiv.

[30]  Jianghui Cai,et al.  A Novel Clustering Algorithm Based on DPC and PSO , 2020, IEEE Access.

[31]  Du Bing,et al.  Analysis of Stellar Spectra from LAMOST DR5 with Generative Spectrum Networks , 2018, Publications of the Astronomical Society of the Pacific.

[32]  H. Rix,et al.  Masses and Ages for 230,000 LAMOST Giants, via Their Carbon and Nitrogen Abundances , 2016, 1609.03195.