AUTOMATED MORPHOLOGICAL CLASSIFICATION OF APM GALAXIES BY SUPERVISED ARTIFICIAL NEURAL NETWORKS

Abstract

We train Artificial Neural Networks to classify galaxies based solely on the morphology of the galaxy images as they appear on blue survey plates. The images are reduced and morphological features such as bulge size and the number of arms are extracted, all in a fully automated manner. The galaxy sample was first classified by 6 independent experts. We use several definitions for the mean type of each galaxy, based on those classifications. We then train and test the network on these features. We find that the rms error of the network classifications, as compared with the mean types of the expert classifications, is 1.8 Revised Hubble Types. This is comparable to the overall rms dispersion between the experts. This result is robust and almost completely independent of the network architecture used.

The full paper contains 25 pages, and includes 22 figures. It is available at ftp://ftp.ast.cam.ac.uk/pub/hn/apm2.ps . The table in the appendix is available on request from [email protected]. Mon. Not. R. Astr. Soc., in press

Cited by in corpus (48)

• Weak Gravitational Lensing
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Asymmetry of Galaxies: Physical Morphology for Nearby and High Redshift Galaxies
• The K-Band Galaxy Luminosity Function
• Data Mining and Machine Learning in Astronomy
• Structural and Photometric Classification of Galaxies - I. Calibration Based on a Nearby Galaxy Sample
• The 2dF Galaxy Redshift Survey: Spectral Types and Luminosity Functions
• The Millennium Galaxy Catalogue: morphological classification and bimodality in the colour-concentration plane
• The Millennium Galaxy Catalogue: Bulge/Disc Decomposition of 10095 Nearby Galaxies
• Estimating photometric redshifts with artificial neural networks
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• Gas Mass Fractions and the Evolution of Spiral Galaxies
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• Morphological number-count and redshift distributions to I < 26 from the Hubble Deep Field: Implications for the evolution of Ellipticals, Spirals and Irregulars
• Galaxy Morphology Classification with Deep Convolutional Neural Networks
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Galaxy Colour, Morphology, and Environment in the Sloan Digital Sky Survey
• Morphology of galaxies in the WINGS clusters
• A Study of Nine High-Redshift Clusters of Galaxies : III. HST Morphology of Clusters 0023+0423 and 1604+4304
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Automated Galaxy Morphology: A Fourier Approach
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Detection of Bars in Galaxies using a Deep Convolutional Neural Network
• Morphological Classification of Galaxies using Photometric Parameters: the Concentration index versus the Coarseness parameter
• Objective Classification of Galaxy Spectra using the Information Bottleneck Method
• Automated Clustering Algorithms for Classification of Astronomical Objects
• Random Forest identification of the thin disk, thick disk and halo Gaia-DR2 white dwarf population
• A Principal Component Analysis approach to the Star Formation History of elliptical galaxies in Compact Groups
• Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• Classifying Galaxy Morphologies with Few-Shot Learning
• Neural Network identification of halo white dwarfs
• Bars formed in galaxy merging and their classification with deep learning
• Quantitative Morphology of Moderate Redshift Galaxies : How Many Peculiars are There ?
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• Galaxy morphology prediction using capsule networks
• Rapid sorting of radio galaxy morphology using Haralick features
• ASTErIsM - Application of topometric clustering algorithms in automatic galaxy detection and classification
• Estimation of the masses in the Local Group by Gradient Boosted Decision Trees
• Random Forest classification of Gaia DR3 white dwarf-main sequence spectra: a feasibility study
• Scientific Data Mining in Astronomy
• The ESO Nearby Abell Cluster Survey VIII. Morphological and spectral classification of galaxies
• A machine learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field
• J-PLUS: Discovery and characterisation of ultracool dwarfs using Virtual Observatory tools II. Second data release and machine learning methodology
• Classifying galaxies according to their HI content
• Objective Subclass Determination of Sloan Digital Sky Survey Unknown Spectral Objects
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies