Application of convolutional neural networks for stellar spectral classification

Sharma, Kaushal; Kembhavi, Ajit; Kembhavi, Aniruddha; Sivarani, T.; Abraham, Sheelu; Vaghmare, Kaustubh

doi:10.1093/mnras/stz3100

Application of convolutional neural networks for stellar spectral classification

Journal Article · Wed Nov 06 00:00:00 EST 2019 · Monthly Notices of the Royal Astronomical Society

DOI:https://doi.org/10.1093/mnras/stz3100· OSTI ID:1706198

^[1]; Kembhavi, Ajit ^[1]; Kembhavi, Aniruddha ^[2]; Sivarani, T. ^[3]; Abraham, Sheelu ^[4]; Vaghmare, Kaustubh ^[1]

Inter University Centre for Astronomy and Astrophysics, Pune 411007, India
PRIOR, Allen Institute for Artificial Intelligence, Seattle 98103, USA, Department of Computer Science and Engineering, University of Washington, Seattle 98195, USA
Indian Institute of Astrophysics, Koramangala, Bengaluru 560034, India
Department of Physics, Mar Thoma College, Chungathara 679334, Nilambur, India

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, $$\rm {\log g}$$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two 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 generalization. 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, Random Forest, and 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 Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

View Journal Article

Sponsoring Organization:: USDOE

OSTI ID:: 1706198

Journal Information:: Monthly Notices of the Royal Astronomical Society, Journal Name: Monthly Notices of the Royal Astronomical Society Journal Issue: 2 Vol. 491; ISSN 0035-8711

Publisher:: Oxford University PressCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (66)

Applied Regression Analysis Draper, Norman R.; Smith, Harry https://doi.org/10.1002/9781118625590	book	January 1998
A catalogue of spectral classification and photometric data of B-type stars Hamdy, M. A.; Abo Elazm, M. S.; Saad, S. M. Astrophysics and Space Science, Vol. 203, Issue 1 https://doi.org/10.1007/BF00659414	journal	January 1993
Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Savitzky, Abraham.; Golay, M. J. E. Analytical Chemistry, Vol. 36, Issue 8 https://doi.org/10.1021/ac60214a047	journal	July 1964
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Stellar spectral classification using principal component analysis and artificial neural networks Singh, H. P.; Gulati, R. K.; Gupta, R. Monthly Notices of the Royal Astronomical Society, Vol. 295, Issue 2 https://doi.org/10.1046/j.1365-8711.1998.01255.x	journal	April 1998
Automated classification of stellar spectra -- II. Two-dimensional classification with neural networks and principal components analysis Bailer-Jones, C. A. L.; Irwin, M.; Von Hippel, T. Monthly Notices of the Royal Astronomical Society, Vol. 298, Issue 2 https://doi.org/10.1046/j.1365-8711.1998.01596.x	journal	August 1998
Consistent distances from Baade-Wesselink analyses of Cepheids and RR Lyraes Kovacs, G. Monthly Notices of the Royal Astronomical Society, Vol. 342, Issue 4 https://doi.org/10.1046/j.1365-8711.2003.06786.x	journal	July 2003
An absolutely calibrated T _eff scale from the infrared flux method : Dwarfs and subgiants Casagrande, L.; Ramírez, I.; Meléndez, J. Astronomy and Astrophysics, Vol. 512 https://doi.org/10.1051/0004-6361/200913204	journal	March 2010
Coudé-feed stellar spectral library – atmospheric parameters Wu, Yue; Singh, H. P.; Prugniel, P. Astronomy & Astrophysics, Vol. 525 https://doi.org/10.1051/0004-6361/201015014	journal	December 2010
Automatic spectral classification of stellar spectra with low signal-to-noise ratio using artificial neural networks Navarro, S. G.; Corradi, R. L. M.; Mampaso, A. Astronomy & Astrophysics, Vol. 538 https://doi.org/10.1051/0004-6361/201016422	journal	February 2012
The atmospheric parameters and spectral interpolator for the MILES stars Prugniel, Ph.; Vauglin, I.; Koleva, M. Astronomy & Astrophysics, Vol. 531 https://doi.org/10.1051/0004-6361/201116769	journal	July 2011
Carbon and oxygen abundances in stellar populations Nissen, P. E.; Chen, Y. Q.; Carigi, L. Astronomy & Astrophysics, Vol. 568 https://doi.org/10.1051/0004-6361/201424184	journal	August 2014
New atmospheric parameters and spectral interpolator for the MILES cool stars Sharma, Kaushal; Prugniel, Philippe; Singh, Harinder P. Astronomy & Astrophysics, Vol. 585 https://doi.org/10.1051/0004-6361/201526111	journal	December 2015
Gaia FGK benchmark stars: Effective temperatures and surface gravities Heiter, U.; Jofré, P.; Gustafsson, B. Astronomy & Astrophysics, Vol. 582 https://doi.org/10.1051/0004-6361/201526319	journal	October 2015
PEPSI deep spectra: II. Gaia benchmark stars and other M-K standards Strassmeier, K. G.; Ilyin, I.; Weber, M. Astronomy & Astrophysics, Vol. 612 https://doi.org/10.1051/0004-6361/201731633	journal	April 2018
A database of high and medium-resolution stellar spectra Prugniel, Ph.; Soubiran, C. Astronomy & Astrophysics, Vol. 369, Issue 3 https://doi.org/10.1051/0004-6361:20010163	journal	April 2001
Analysis of neutron capture elements in metal-poor stars Mishenina, T. V.; Kovtyukh, V. V. Astronomy & Astrophysics, Vol. 370, Issue 3 https://doi.org/10.1051/0004-6361:20010295	journal	May 2001
A spectroscopic survey for λ Bootis stars: II. The observational data Paunzen, E.; Duffee, B.; Heiter, U. Astronomy & Astrophysics, Vol. 373, Issue 2 https://doi.org/10.1051/0004-6361:20010630	journal	July 2001
Abundances for metal-poor stars with accurate parallaxes: I. Basic data Gratton, R. G.; Carretta, E.; Claudi, R. Astronomy & Astrophysics, Vol. 404, Issue 1 https://doi.org/10.1051/0004-6361:20030439	journal	May 2003
S$\mathsf{_{B^9}}$: The ninth catalogue of spectroscopic binary orbits Pourbaix, D.; Tokovinin, A. A.; Batten, A. H. Astronomy & Astrophysics, Vol. 424, Issue 2 https://doi.org/10.1051/0004-6361:20041213	journal	August 2004
Non-LTE line formation for heavy elements in four very metal-poor stars Mashonkina, L.; Zhao, G.; Gehren, T. Astronomy & Astrophysics, Vol. 478, Issue 2 https://doi.org/10.1051/0004-6361:20078060	journal	December 2007
Empirical calibration of the λ 4000 Å break Gorgas, J.; Cardiel, N.; Pedraz, S. Astronomy and Astrophysics Supplement Series, Vol. 139, Issue 1 https://doi.org/10.1051/aas:1999375	journal	October 1999
MK classifications for F-and G-type stars. II. Harlan, E. A.; Taylor, D. C. The Astronomical Journal, Vol. 75 https://doi.org/10.1086/110956	journal	March 1970
Spectral classification of high-proper-motion stars Lee, S. -G. The Astronomical Journal, Vol. 89 https://doi.org/10.1086/113569	journal	May 1984
The Oosterhoff period-metallicity relation for RR Lyrae stars at the blue fundamental edge of the instability strip. Sandage, Allan The Astronomical Journal, Vol. 106 https://doi.org/10.1086/116675	journal	August 1993
Discoveries on Southern Objective-Prism Plates. II. New Probable Field Horizontal-Branch Stars MacConnell, D. J.; Frye, R. L.; Bidelman, W. P. Publications of the Astronomical Society of the Pacific, Vol. 83 https://doi.org/10.1086/129082	journal	February 1971
The luminosity scale of RR Lyrae stars with the Baade-Wesselink method. II - The absolute magnitudes of 13 field RR Lyrae stars Liu, Tianxing; Janes, Kenneth A. The Astrophysical Journal, Vol. 354 https://doi.org/10.1086/168688	journal	May 1990
Stellar spectral classification using automated schemes Gulati, R. K.; Gupta, Ranjan; Gothoskar, Pradeep The Astrophysical Journal, Vol. 426 https://doi.org/10.1086/174069	journal	May 1994
Lithium in an extreme halo star Hobbs, L. M.; Pilachowski, Catherine The Astrophysical Journal, Vol. 326 https://doi.org/10.1086/185115	journal	March 1988
The Kinematics of the Gould Belt: an Expanding Group? Rountree Lesh, Janet The Astrophysical Journal Supplement Series, Vol. 17 https://doi.org/10.1086/190179	journal	December 1968
A library of stellar spectra Jacoby, G. H.; Hunter, D. A.; Christian, C. A. The Astrophysical Journal Supplement Series, Vol. 56 https://doi.org/10.1086/190983	journal	October 1984
G. P. Kuiper's spectral classifications of proper-motion stars Bidelman, W. P. The Astrophysical Journal Supplement Series, Vol. 59 https://doi.org/10.1086/191069	journal	October 1985
Kinematics of Metal-poor Stars in the Galaxy. II. Proper Motions for a Large Nonkinematically Selected Sample Beers, Timothy C.; Chiba, Masashi; Yoshii, Yuzuru The Astronomical Journal, Vol. 119, Issue 6 https://doi.org/10.1086/301410	journal	June 2000
Accurate Two‐Dimensional Classification of Stellar Spectra with Artificial Neural Networks Weaver, Wm. Bruce; Torres‐Dodgen, Ana V. The Astrophysical Journal, Vol. 487, Issue 2 https://doi.org/10.1086/304651	journal	October 1997
Maps of Dust Infrared Emission for Use in Estimation of Reddening and Cosmic Microwave Background Radiation Foregrounds Schlegel, David J.; Finkbeiner, Douglas P.; Davis, Marc The Astrophysical Journal, Vol. 500, Issue 2 https://doi.org/10.1086/305772	journal	June 1998
A Stellar Spectral Flux Library: 1150–25000 Å Pickles, A. J. Publications of the Astronomical Society of the Pacific, Vol. 110, Issue 749 https://doi.org/10.1086/316197	journal	July 1998
Neutron‐Capture Elements in the Early Galaxy: Insights from a Large Sample of Metal‐poor Giants Burris, Debra L.; Pilachowski, Catherine A.; Armandroff, Taft E. The Astrophysical Journal, Vol. 544, Issue 1 https://doi.org/10.1086/317172	journal	November 2000
Rotation Velocities of Red and Blue Field Horizontal‐Branch Stars Behr, Bradford B. The Astrophysical Journal Supplement Series, Vol. 149, Issue 1 https://doi.org/10.1086/378352	journal	November 2003
Contributions to the Nearby Stars (NStars) Project: Spectroscopy of Stars Earlier than M0 within 40 Parsecs: The Northern Sample. I. Gray, R. O.; Corbally, C. J.; Garrison, R. F. The Astronomical Journal, Vol. 126, Issue 4 https://doi.org/10.1086/378365	journal	October 2003
The Indo‐US Library of Coude Feed Stellar Spectra Valdes, Francisco; Gupta, Ranjan; Rose, James A. The Astrophysical Journal Supplement Series, Vol. 152, Issue 2 https://doi.org/10.1086/386343	journal	June 2004
An Analysis of the Shapes of Interstellar Extinction Curves. V. The IR‐through‐UV Curve Morphology Fitzpatrick, E. L.; Massa, D. The Astrophysical Journal, Vol. 663, Issue 1 https://doi.org/10.1086/518158	journal	July 2007
A Triple Main Sequence in the Globular Cluster NGC 2808 Piotto, G.; Bedin, L. R.; Anderson, J. The Astrophysical Journal, Vol. 661, Issue 1 https://doi.org/10.1086/518503	journal	April 2007
Starmind: a Fuzzy Logic Knowledge-Based System for the Automated Classification of Stars in the mk System Manteiga, M.; Carricajo, I.; Rodríguez, A. The Astronomical Journal, Vol. 137, Issue 2 https://doi.org/10.1088/0004-6256/137/2/3245	journal	January 2009
Spectral Classification and Redshift Measurement for the Sdss-Iii Baryon Oscillation Spectroscopic Survey Bolton, Adam S.; Schlegel, David J.; Aubourg, Éric The Astronomical Journal, Vol. 144, Issue 5 https://doi.org/10.1088/0004-6256/144/5/144	journal	October 2012
The Baryon Oscillation Spectroscopic Survey of Sdss-Iii Dawson, Kyle S.; Schlegel, David J.; Ahn, Christopher P. The Astronomical Journal, Vol. 145, Issue 1 https://doi.org/10.1088/0004-6256/145/1/10	journal	December 2012
An Expert Computer Program for Classifying Stars on the mk Spectral Classification System Gray, R. O.; Corbally, C. J. The Astronomical Journal, Vol. 147, Issue 4 https://doi.org/10.1088/0004-6256/147/4/80	journal	March 2014
Mixed Populations in Globular Clusters: et tu, 47 tuc? Anderson, J.; Piotto, G.; King, I. R. The Astrophysical Journal, Vol. 697, Issue 1 https://doi.org/10.1088/0004-637X/697/1/L58	journal	April 2009
Multiple Stellar Populations in the Galactic Globular Cluster ngc 6752 Milone, A. P.; Piotto, G.; King, I. R. The Astrophysical Journal, Vol. 709, Issue 2 https://doi.org/10.1088/0004-637X/709/2/1183	journal	January 2010
Measuring Reddening with Sloan Digital sky Survey Stellar Spectra and Recalibrating sfd Schlafly, Edward F.; Finkbeiner, Douglas P. The Astrophysical Journal, Vol. 737, Issue 2 https://doi.org/10.1088/0004-637X/737/2/103	journal	August 2011
Updating quasi-Newton matrices with limited storage Nocedal, Jorge Mathematics of Computation, Vol. 35, Issue 151 https://doi.org/10.1090/S0025-5718-1980-0572855-7	journal	September 1980
Rotation-invariant convolutional neural networks for galaxy morphology prediction Dieleman, Sander; Willett, Kyle W.; Dambre, Joni Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2 https://doi.org/10.1093/mnras/stv632	journal	April 2015
Searching for exoplanets using artificial intelligence Pearson, Kyle A.; Palafox, Leon; Griffith, Caitlin A. Monthly Notices of the Royal Astronomical Society, Vol. 474, Issue 1 https://doi.org/10.1093/mnras/stx2761	journal	October 2017
An application of deep learning in the analysis of stellar spectra Fabbro, S.; Venn, K. A.; O'Briain, T. Monthly Notices of the Royal Astronomical Society, Vol. 475, Issue 3 https://doi.org/10.1093/mnras/stx3298	journal	December 2017
Radio Galaxy Zoo: Claran – a deep learning classifier for radio morphologies Wu, Chen; Wong, Oiwei Ivy; Rudnick, Lawrence Monthly Notices of the Royal Astronomical Society, Vol. 482, Issue 1 https://doi.org/10.1093/mnras/sty2646	journal	October 2018
Detection of bars in galaxies using a deep convolutional neural network Abraham, Sheelu; Aniyan, A. K.; Kembhavi, Ajit K. Monthly Notices of the Royal Astronomical Society, Vol. 477, Issue 1 https://doi.org/10.1093/mnras/sty627	journal	March 2018
Deep-learnt classification of light curves Mahabal, A.; Sheth, K.; Gieseke, F. 2017 IEEE Symposium Series on Computational Intelligence (SSCI) https://doi.org/10.1109/SSCI.2017.8280984	conference	November 2017
Medium-resolution Isaac Newton Telescope library of empirical spectra Sanchez-Blazquez, P.; Peletier, R. F.; Jimenez-Vicente, J. Monthly Notices of the Royal Astronomical Society, Vol. 371, Issue 2 https://doi.org/10.1111/j.1365-2966.2006.10699.x	journal	September 2006
Reducing the Dimensionality of Data with Neural Networks Hinton, G. E. Science, Vol. 313, Issue 5786 https://doi.org/10.1126/science.1127647	journal	July 2006
Scalable training of L ¹ -regularized log-linear models Andrew, Galen; Gao, Jianfeng Proceedings of the 24th international conference on Machine learning - ICML '07 https://doi.org/10.1145/1273496.1273501	conference	January 2007
Extracting and composing robust features with denoising autoencoders Vincent, Pascal; Larochelle, Hugo; Bengio, Yoshua Proceedings of the 25th international conference on Machine learning - ICML '08 https://doi.org/10.1145/1390156.1390294	conference	January 2008
Learning Deep Architectures for AI Bengio, Y. Foundations and Trends® in Machine Learning, Vol. 2, Issue 1 https://doi.org/10.1561/2200000006	journal	January 2009
Measurement of Inequality of Incomes Gini, Corrado The Economic Journal, Vol. 31, Issue 121 https://doi.org/10.2307/2223319	journal	March 1921
Abundances in the Local Region. ii. f, g, and k Dwarfs and Subgiants Luck, R. Earle The Astronomical Journal, Vol. 153, Issue 1 https://doi.org/10.3847/1538-3881/153/1/21	journal	December 2016
An Empirical Template Library of Stellar Spectra for a Wide Range of Spectral Classes, Luminosity Classes, and Metallicities Using SDSS BOSS Spectra Kesseli, Aurora Y.; West, Andrew A.; Veyette, Mark The Astrophysical Journal Supplement Series, Vol. 230, Issue 2 https://doi.org/10.3847/1538-4365/aa656d	journal	June 2017
The 13th Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-IV Survey Mapping Nearby Galaxies at Apache Point Observatory Albareti, Franco D.; Prieto, Carlos Allende; Almeida, Andres The Astrophysical Journal Supplement Series, Vol. 233, Issue 2 https://doi.org/10.3847/1538-4365/aa8992	journal	December 2017
The Gaia FGK Benchmark Stars Version 2.1 Jofré, Paula; Heiter, Ulrike; Maia, Marcelo Tucci Research Notes of the AAS, Vol. 2, Issue 3 https://doi.org/10.3847/2515-5172/aadc61	journal	July 2018

Similar Records

On the construction of a new stellar classification template library for the LAMOST spectral analysis pipeline

Journal Article · Thu May 01 00:00:00 EDT 2014 · Astronomical Journal (New York, N.Y. Online) · OSTI ID:22340278

Automated Stellar Spectra Classification with Ensemble Convolutional Neural Network

Journal Article · Mon Jan 03 19:00:00 EST 2022 · Advances in Astronomy · OSTI ID:1983018

Deep Gaze Velocity Analysis During Mammographic Reading for Biometric Identification of Radiologists

Journal Article · Tue Jan 23 19:00:00 EST 2018 · Journal of Human Performance in Extreme Environments · OSTI ID:1422583

Application of convolutional neural networks for stellar spectral classification

Citation Formats

References (66)

Similar Records

Related Subjects