Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs

Abstract

Classifying the morphologies of galaxies is an important step in understanding their physical properties and evolutionary histories. The advent of large-scale surveys has hastened the need to develop techniques for automated morphological classification. We train and test several convolutional neural network architectures to classify the morphologies of galaxies in both a 3-class (elliptical, lenticular, spiral) and 4-class (+irregular/miscellaneous) schema with a dataset of 14034 visually-classified SDSS images. We develop a new CNN architecture that outperforms existing models in both 3 and 4-way classification, with overall classification accuracies of 83% and 81% respectively. We also compare the accuracies of 2-way / binary classifications between all four classes, showing that ellipticals and spirals are most easily distinguished (>98% accuracy), while spirals and irregulars are hardest to differentiate (78% accuracy). Through an analysis of all classified samples, we find tentative evidence that misclassifications are physically meaningful, with lenticulars misclassified as ellipticals tending to be more massive, among other trends. We further combine our binary CNN classifiers to perform a hierarchical classification of samples, obtaining comparable accuracies (81%) to the direct 3-class CNN, but considerably worse accuracies in the 4-way case (65%). As an additional verification, we apply our networks to a small sample of Galaxy Zoo images, obtaining accuracies of 92%, 82% and 77% for the binary, 3-way and 4-way classifications respectively.

18 pages, 18 figures, accepted for publication in MNRAS

References in corpus (16)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ADADELTA: An Adaptive Learning Rate Method
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• The SAURON project -- X. The orbital anisotropy of elliptical and lenticular galaxies: revisiting the (V/sigma,epsilon) diagram with integral-field stellar kinematics
• The Evolution of Galaxy Structure over Cosmic Time
• Machine Learning in Astronomy: a practical overview
• Two-dimensional multi-component photometric decomposition of CALIFA galaxies
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• Deep learning for galaxy surface brightness profile fitting
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Galaxy And Mass Assembly: Automatic Morphological Classification of Galaxies Using Statistical Learning
• Bars formed in galaxy merging and their classification with deep learning
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks

Cited by in corpus (19)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The evolution of barred galaxies in the EAGLE simulations
• Galaxy classification: a deep learning approach for classifying Sloan Digital Sky Survey images
• Automatic detection of low surface brightness galaxies from SDSS images
• The galaxy morphology-density relation in the EAGLE simulation
• HOLISMOKES -- X. Comparison between neural network and semi-automated traditional modeling of strong lenses
• From Images to Features: Unbiased Morphology Classification via Variational Auto-Encoders and Domain Adaptation
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• Morphological Classification of Galaxies Using SpinalNet
• A deep learning approach to halo merger tree construction
• The classification of real and bogus transients using active learning and semi-supervised learning
• A morphological segmentation approach to determining bar lengths
• Deep learning-based astronomical multimodal data fusion: A comprehensive review
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• Mapping Diffuse Radio Sources Using TUNA: A Transformer-Based Deep Learning Approach
• COUGS-DESI: A Catalog of Unusual Galaxies with Polar Structures in the DESI Legacy Imaging Surveys
• Convolutional Deep Denoising Autoencoders for Radio Astronomical Images
• Galaxy 3D Shape Recovery using Mixture Density Network
• Uncertainty-Aware Neural Networks for Fuzzy Dark Matter Model Selection from \texorpdfstring{$x_{\mathrm{HI}}$}{x_HI} Measurements