Machine-learning computation of distance modulus for local galaxies

Abstract

Quickly growing computing facilities and an increasing number of extragalactic observations encourage the application of data-driven approaches to uncover hidden relations from astronomical data. In this work we raise the problem of distance reconstruction for a large number of galaxies from available extensive observations. We propose a new data-driven approach for computing distance moduli for local galaxies based on the machine-learning regression as an alternative to physically oriented methods. We use key observable parameters for a large number of galaxies as input explanatory variables for training: magnitudes in U, B, I, and K bands, corresponding colour indices, surface brightness, angular size, radial velocity, and coordinates. We performed detailed tests of the five machine-learning regression techniques for inference of $m-M$: linear, polynomial, k-nearest neighbours, gradient boosting, and artificial neural network regression. As a test set we selected 91 760 galaxies at $z<0.2$ from the NASA/IPAC extragalactic database with distance moduli measured by different independent redshift methods. We find that the most effective and precise is the neural network regression model with two hidden layers. The obtained root-mean-square error of 0.35 mag, which corresponds to a relative error of 16\%, does not depend on the distance to galaxy and is comparable with methods based on the Tully-Fisher and Fundamental Plane relations. The proposed model shows a 0.44 mag (20\%) error in the case of spectroscopic redshift absence and is complementary to existing photometric redshift methodologies. Our approach has great potential for obtaining distance moduli for around 250 000 galaxies at $z<0.2$ for which the above-mentioned parameters are already observed.

arXiv comment8 pages, 5 figures, Accepted for publication in A&A

References in corpus (29)

• HyperLEDA. III. The catalogue of extragalactic distances
• The Laniakea supercluster of galaxies
• Calibrating Redshift Distributions Beyond Spectroscopic Limits with Cross-Correlations
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• Galaxy groups and clouds in the Local (z~0.01) universe
• Reconstructed Density and Velocity Fields from the 2MASS Redshift Survey
• Photometric redshift estimation via deep learning
• Cepheid Period-Luminosity Relations in the Near-Infrared and the Distance to M31 from the Hubble Space Telescope Wide Field Camera 3
• Reconstructing the Cosmic Velocity and Tidal Fields with Galaxy Groups Selected from the Sloan Digital Sky Survey
• 3D Velocity and Density Reconstructions of the Local Universe with Cosmicflows-1
• A new perspective on Dark Energy modeling via Genetic Algorithms
• Cosmicflows-3: Cosmography of the Local Void
• A model independent null test on the cosmological constant
• Using neural networks to estimate redshift distributions. An application to CFHTLenS
• Genetic Algorithms and Supernovae Type Ia Analysis
• Clustering-based Redshift Estimation: Comparison to Spectroscopic Redshifts
• Redshift-Independent Distances in the NASA/IPAC Extragalactic Database: Methodology, Content and Use of NED-D
• An estimation of the Local growth rate from Cosmicflows-3 peculiar velocities
• Photometric redshifts with Quasi Newton Algorithm (MLPQNA). Results in the PHAT1 contest
• Pecular velocities of galaxies in the Leo Spur
• Sub-Megaparsec Individual Photometric Redshift Estimation from Cosmic Web Constraints
• A sample of galaxy pairs identified from the LAMOST spectral survey and the Sloan Digital Sky Survey
• Cosmic voids detection without density measurements
• Peculiar Velocities of 3000 Spiral Galaxies from the 2MFGC Catalog
• Deep ugrizY Imaging and DEEP2/3 Spectroscopy: A Photometric Redshift Testbed for LSST and Public Release of Data from the DEEP3 Galaxy Redshift Survey
• The distance modulus determined from Carmeli's cosmology fits the accelerating universe data of the high-redshift type Ia supernovae without dark matter
• Predicting Structures in the Zone of Avoidance
• The extinction law from photometric data: linear regression methods
• A new analytical solution for the distance modulus in flat cosmology

Cited by in corpus (5)

• Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
• The Voronoi tessellation method in astronomy
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• NGC 3521 as the Milky Way near twin: spectral energy distribution from UV to radio decameter ranges