Galaxies, Human Eyes and Artificial Neural Networks
arXiv:astro-ph/9412027 · doi:10.1126/science.267.5199.859
Abstract
Quantitative morphological classification of galaxies is important for understanding the origin of type frequency and correlations with environment. But galaxy morphological classification is still mainly done visually by dedicated individuals, in the spirit of Hubble's original scheme, and its modifications. The rapid increase in data on galaxy images at low and high redshift calls for re-examination of the classification schemes and for new automatic methods. Here we show results from the first systematic comparison of the dispersion among human experts classifying a uniformly selected sample of over 800 digitised galaxy images. These galaxy images were then classified by six of the authors independently. The human classifications are compared with each other, and with an automatic classification by Artificial Neural Networks (ANN). It is shown that the ANNs can replicate the classification by a human expert to the same degree of agreement as that between two human experts.
arXiv commentTo appear in Science. 13 pages, uuencoded compressed postscript file (not including 3 figures). Also available at (131.111.68.35) ftp://cast0.ast.cam.ac.uk/pub/lahav/science/ science5.ps.Z with figures science_fig1.ps.Z, science_fig2.ps.Z and science_fig3.ps.Z in same directory
Cited by in corpus (62)
- Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
- Galaxy Zoo: the dependence of morphology and colour on environment
- The Morphology-Density Relation in the Sloan Digital Sky Survey
- Data Mining and Machine Learning in Astronomy
- Inclination- and dust-corrected galaxy parameters: Bulge-to-disc ratios and size-luminosity relations
- The Millennium Galaxy Catalogue: Bulge/Disc Decomposition of 10095 Nearby Galaxies
- An investigation into the prominence of spiral galaxy bulges
- Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
- Photometric Supernova Classification With Machine Learning
- The Southern Sky Redshift Survey
- Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
- A Catalogue of Morphologically Classified Galaxies from the Sloan Digital Sky Survey: North Equatorial Region
- The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
- Transfer learning for galaxy morphology from one survey to another
- An automatic taxonomy of galaxy morphology using unsupervised machine learning
- Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
- Tidal dwarf galaxies in the nearby Universe
- Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
- Unsupervised self-organised mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys
- The Morphological Butcher-Oemler effect in the SDSS Cut&Enhance Galaxy Cluster Catalog
- A Study of Nine High-Redshift Clusters of Galaxies : III. HST Morphology of Clusters 0023+0423 and 1604+4304
- Quantitative Morphology of Galaxies in the Core of the Coma Cluster
- Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
- Ideas for Citizen Science in Astronomy
- Homogenization of the Stellar Population along Late-Type Spiral Galaxies
- Unsupervised star, galaxy, qso classification: Application of HDBSCAN
- Lightcurve Classification in Massive Variability Surveys
- The ESO-Sculptor Survey: Luminosity functions of galaxies per spectral type at redshifts 0.1-0.5
- A K-band central disk surface-brightness correlation with scale-length for early-type disk galaxies, and the inclination correction
- Objective Classification of Galaxy Spectra using the Information Bottleneck Method
- 2MASS photometry of edge-on spiral galaxies. I. Sample and general results
- The FIRST Classifier: Compact and Extended Radio Galaxy Classification using Deep Convolutional Neural Networks
- AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
- Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
- A review of unsupervised learning in astronomy
- Photometric redshifts and K-corrections for Sloan Digital Sky Survey Seven Data Release
- Critical analysis of the luminosity functions per galaxy type measured from redshift surveys
- Automated Source Classification using a Kohonen Network
- A galaxy classification grid that better recognises early-type galaxy morphology
- A catalogue of structural and morphological measurements for DES Y1
- Galaxy Morphology Classification using Neural Ordinary Differential Equations
- The influence of bulge profile shapes on claims for a scale-free Hubble sequence for spirals
- Explaining deep learning of galaxy morphology with saliency mapping
- Galaxy morphology prediction using capsule networks
- Eigengalaxies: describing galaxy morphology using principal components in image space
- Reproducible -means clustering in galaxy feature data from the GAMA survey
- Soft clustering analysis of galaxy morphologies: A worked example with SDSS
- Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
- Galaxy Zoo Morphology and Photometric Redshifts in the Sloan Digital Sky Survey
- Artificial Neural Networks as Non-Linear Extensions of Statistical Methods in Astronomy
- CzSL: Learning from citizen science, experts and unlabelled data in astronomical image classification
- On the application of dimensionality reduction and clustering algorithms for the classification of kinematic morphologies of galaxies
- Principal component analysis of IUE galaxy spectra
- Neural Networks and the Classification of Active Galactic Nucleus Spectra
- Approaches to Automated Morphological Classification of Galaxies
- Dependence of Spiral Galaxy Distribution on Viewing Angle in RC3
- The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
- Morphology in the Era of Large Surveys
- Identifying Anomalous DESI Galaxy Spectra with a Variational Autoencoder
- Bar Properties and Star-by-Star Bar Membership via Action Conservation