Stellar Spectral Interpolation using Machine Learning

Abstract

Theoretical stellar spectra rely on model stellar atmospheres computed based on our understanding of the physical laws at play in the stellar interiors. These models, coupled with atomic and molecular line databases, are used to generate theoretical stellar spectral libraries (SSLs) comprising of stellar spectra over a regular grid of atmospheric parameters (temperature, surface gravity, abundances) at any desired resolution. Another class of SSLs is referred to as empirical spectral libraries; these contain observed spectra at limited resolution. SSLs play an essential role in deriving the properties of stars and stellar populations. Both theoretical and empirical libraries suffer from limited coverage over the parameter space. This limitation is overcome to some extent by generating spectra for specific sets of atmospheric parameters by interpolating within the grid of available parameter space. In this work, we present a method for spectral interpolation in the optical region using machine learning algorithms that are generic, easily adaptable for any SSL without much change in the model parameters, and computationally inexpensive. We use two machine learning techniques, Random Forest (RF) and Artificial Neural Networks (ANN), and train the models on the MILES library. We apply the trained models to spectra from the CFLIB for testing and show that the performance of the two models is comparable. We show that both the models achieve better accuracy than the existing methods of polynomial based interpolation and the Gaussian radial basis function (RBF) interpolation.

Accepted for publication in MNRAS. 16 pages, 16 figures

References in corpus (45)

• Scikit-learn: Machine Learning in Python
• The Sloan Digital Sky Survey: Technical Summary
• Galactic Stellar and Substellar Initial Mass Function
• Playing Atari with Deep Reinforcement Learning
• Starburst99: Synthesis Models for Galaxies with Active Star Formation
• A grid of MARCS model atmospheres for late-type stars I. Methods and general properties
• A new extensive library of PHOENIX stellar atmospheres and synthetic spectra
• The Apache Point Observatory Galactic Evolution Experiment (APOGEE)
• MILES: A Medium resolution INT Library of Empirical Spectra
• The Indo-U.S. Library of Coude Feed Stellar Spectra
• The SEGUE Stellar Parameter Pipeline. I. Description and Initial Validation Tests
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
• ULySS: A Full Spectrum Fitting Package
• The Cannon: A data-driven approach to stellar label determination
• An extensive library of 2500-10500 Ang synthetic spectra
• Medium-resolution Isaac Newton Telescope library of empirical spectra - II. The stellar atmospheric parameters
• The Payne: self-consistent ab initio fitting of stellar spectra
• Coude-feed stellar spectral library - atmospheric parameters
• A new library of theoretical stellar spectra with scaled-solar and alpha-enhanced mixtures
• Spectroscopic ages and metallicities of stellar populations: validation of full spectrum fitting
• The atmospheric parameters and spectral interpolator for the stars of MILES
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Metallicity of M dwarfs III. Planet-metallicity and planet-stellar mass correlations of the HARPS GTO M dwarf sample
• Automated Classification of Stellar Spectra. II: Two-Dimensional Classification with Neural Networks and Principal Components Analysis
• A large stellar evolution database for population synthesis studies. IV. Integrated properties and spectra
• The Stellar Populations of Stripped Spiral Galaxies in the Virgo Cluster
• Automatic unsupervised classification of all SDSS/DR7 galaxy spectra
• Application of Convolutional Neural Networks for Stellar Spectral Classification
• Using the Galactic Dynamics of M7 Dwarfs to Infer the Evolution of Their Magnetic Activity
• Element abundances in the stars of the MILES spectral library: the Mg/Fe ratio
• New atmospheric parameters and spectral interpolator for the MILES cool stars
• Detection of Bars in Galaxies using a Deep Convolutional Neural Network
• Measuring 14 elemental abundances with R=1,800 LAMOST spectra
• Prospects for Measuring Abundances of >20 Elements with Low-resolution Stellar Spectra
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Unsupervised clustering of Type II supernova light curves
• A Machine Learning Method to Infer Fundamental Stellar Parameters from Photometric Light Curves
• The hot Gamma-Doradus and Maia stars
• Unsupervised Classification of Variable Stars
• Machine Learning on Difference Image Analysis: A comparison of methods for transient detection
• On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra
• An Active Instance-based Machine Learning method for Stellar Population Studies
• X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning
• A Long-term photometric variability and spectroscopic study of luminous blue variable AF And in M31

Cited by in corpus (5)

• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• Stellar Spectra Models Classification and Parameter Estimation Using Machine Learning Algorithms
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting
• A new code for low-resolution spectral identification of white dwarf binary candidates