Galaxy morphology prediction using capsule networks

Abstract

Understanding morphological types of galaxies is a key parameter for studying their formation and evolution. Neural networks that have been used previously for galaxy morphology classification have some disadvantages, such as not being invariant under rotation. In this work, we studied the performance of Capsule Network, a recently introduced neural network architecture that is rotationally invariant and spatially aware, on the task of galaxy morphology classification. We designed two evaluation scenarios based on the answers from the question tree in the Galaxy Zoo project. In the first scenario, we used Capsule Network for regression and predicted probabilities for all of the questions. In the second scenario, we chose the answer to the first morphology question that had the highest user agreement as the class of the object and trained a Capsule Network classifier, where we also reconstructed galaxy images. We achieved promising results in both of these scenarios. Automated approaches such as the one introduced here will greatly decrease the workload of astronomers and will play a critical role in the upcoming large sky surveys.

arXiv comment9 pages, 6 figures

References in corpus (24)

• Improving neural networks by preventing co-adaptation of feature detectors
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Detailed Structural Decomposition of Galaxy Images
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• 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 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• Galaxy Zoo: the dependence of morphology and colour on environment
• ANNz: estimating photometric redshifts using artificial neural networks
• Improving galaxy morphologies for SDSS with Deep Learning
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Estimating photometric redshifts with artificial neural networks
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• Galaxy Zoo: An independent look at the evolution of the bar fraction over the last eight billion years from HST-COSMOS
• Galaxy Zoo: Evidence for Diverse Star Formation Histories through the Green Valley
• AUTOMATED MORPHOLOGICAL CLASSIFICATION OF APM GALAXIES BY SUPERVISED ARTIFICIAL NEURAL NETWORKS
• Deep Recurrent Neural Networks for Supernovae Classification
• Galaxies, Human Eyes and Artificial Neural Networks
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• Galaxy And Mass Assembly (GAMA): Understanding the wavelength dependence of galaxy structure with bulge-disc decompositions
• Combining human and machine learning for morphological analysis of galaxy images
• A robust morphological classification of high-redshift galaxies using support vector machines on seeing limited images. II. Quantifying morphological k-correction in the COSMOS field at 1<z<2: Ks band vs. I band
• Exploring galaxy evolution with generative models

Cited by in corpus (9)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Photometric Redshifts from SDSS Images with an Interpretable Deep Capsule Network
• Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
• CapsNets Continuing the Convolutional Quest
• Rapid sorting of radio galaxy morphology using Haralick features
• Shifting Capsule Networks from the Cloud to the Deep Edge
• Pushing the Technical Frontier: From Overwhelmingly Large Data Sets to Machine Learning
• Deep Learning: a new definition of artificial neuron with double weight