Application of Convolutional Neural Networks for Stellar Spectral Classification

Abstract

Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, log g, [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using Convolutional Neural Networks. Traditional machine learning (ML) methods with "shallow" architecture (usually up to 2 hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalisation. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like Artificial Neural Networks (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) to classify stellar spectra using the Jacoby Atlas, ELODIE and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coude Feed Stellar Spectra (CFLIB). We show that using convolutional neural networks, we are able to lower the error up to 1.23 spectral sub-classes as compared to that of 2 sub-classes achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS database with SNR>20.

21 pages, 19 figures. Submitted to MNRAS, under review

References in corpus (24)

• Scikit-learn: Machine Learning in Python
• Measuring Reddening with SDSS Stellar Spectra and Recalibrating SFD
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• An absolutely calibrated effective temperature scale from the InfraRed Flux Method
• An Analysis of the Shapes of Interstellar Extinction Curves. V. The IR-Through-UV Curve Morphology
• Spectral Classification and Redshift Measurement for the SDSS-III Baryon Oscillation Spectroscopic Survey
• The Thirteenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-IV Survey MApping Nearby Galaxies at Apache Point Observatory
• Gaia FGK Benchmark Stars: Effective temperatures and surface gravities
• Coude-feed stellar spectral library - atmospheric parameters
• The atmospheric parameters and spectral interpolator for the stars of MILES
• Abundances in the Local Region II: F, G and K Dwarfs and Subgiants
• Carbon and oxygen abundances in stellar populations
• Searching for Exoplanets Using Artificial Intelligence
• An Application of Deep Neural Networks in the Analysis of Stellar Spectra
• Non-LTE line formation for heavy elements in four very metal-poor stars
• An empirical template library of stellar spectra for a wide range of spectral classes, luminosity classes, and metallicities using SDSS BOSS spectra
• Multiple stellar populations in the Galactic globular cluster NGC 6752
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• New atmospheric parameters and spectral interpolator for the MILES cool stars
• Detection of Bars in Galaxies using a Deep Convolutional Neural Network
• Deep-Learnt Classification of Light Curves
• PEPSI deep spectra. II. Gaia benchmark stars and other M-K standards
• The Gaia FGK benchmark stars version 2.1

Cited by in corpus (31)

• APOGEE Net: Improving the derived spectral parameters for young stars through deep learning
• The CARMENES search for exoplanets around M dwarfs -- A deep learning approach to determine fundamental parameters of target stars
• Data mining techniques on astronomical spectra data. II : Classification Analysis
• Classifying Single Stars and Spectroscopic Binaries Using Optical Stellar Templates
• Stellar Parameter Determination from Photometry using Invertible Neural Networks
• Elemental abundances of nearby M dwarfs based on high-resolution near-infrared spectra obtained by the Subaru/IRD survey: Proof of concept
• A machine-learning photometric classifier for massive stars in nearby galaxies I. The method
• Data-Driven Selection and Spectral Classification of White Dwarf Stars
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Emission-line diagnostics of HII regions using conditional Invertible Neural Networks
• B/PS bulges in DESI Legacy edge-on galaxies I: Sample building
• Deep Learning in Searching the Spectroscopic Redshift of Quasars
• Estimating $T_{\mathrm{eff}}$, radius and luminosity of M-dwarfs using high resolution optical and NIR spectral features
• A new automated tool for the spectral classification of OB stars
• Stellar Spectral Interpolation using Machine Learning
• Using autoencoders and deep transfer learning to determine the stellar parameters of 286 CARMENES M dwarfs
• Photometric classification of HSC transients using machine learning
• GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters
• Morphological Parameters and Associated Uncertainties for 8 Million Galaxies in the Hyper Suprime-Cam Wide Survey
• The miniJPAS survey quasar selection II: Machine learning classification with photometric measurements and uncertainties
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• Noise-Net: Determining physical properties of HII regions reflecting observational uncertainties
• Advanced Classification of Hot Subdwarf Binaries Using Artificial Intelligence Techniques and Gaia DR3 data
• Spectral classification of young stars using conditional invertible neural networks I. Introducing and validating the method
• Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening
• StarUnLink: identifying and mitigating signals from communications satellites in stellar spectral surveys
• CoSHA: Code for Stellar properties Heuristic Assignment -- for the MaStar stellar library
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting
• Spectral classification of young stars using conditional invertible neural networks II. Application to Trumpler 14 in Carina
• Breaking the degeneracy in stellar spectral classification from single wide-band images
• Exploring Late Stellar Evolution in the Era of Large Surveys: Machine Learning Prospects for Hot Subdwarfs and White Dwarfs