DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks

Abstract

Galaxy mergers, the dynamical process during which two galaxies collide, are among the most spectacular phenomena in the Universe. During this process, the two colliding galaxies are tidally disrupted, producing significant visual features that evolve as a function of time. These visual features contain valuable clues for deducing the physical properties of the galaxy mergers. In this work, we propose DeepGalaxy, a visual analysis framework trained to predict the physical properties of galaxy mergers based on their morphology. Based on an encoder-decoder architecture, DeepGalaxy encodes the input images to a compressed latent space $z$, and determines the similarity of images according to the latent-space distance. DeepGalaxy consists of a fully convolutional autoencoder (FCAE) which generates activation maps at its 3D latent-space, and a variational autoencoder (VAE) which compresses the activation maps into a 1D vector, and a classifier that generates labels from the activation maps. The backbone of the FCAE can be fully customized according to the complexity of the images. DeepGalaxy demonstrates excellent scaling performance on parallel machines. On the Endeavour supercomputer, the scaling efficiency exceeds 0.93 when trained on 128 workers, and it maintains above 0.73 when trained with 512 workers. Without having to carry out expensive numerical simulations, DeepGalaxy makes inferences of the physical properties of galaxy mergers directly from images, and thereby achieves a speedup factor of $\sim 10^5$.

arXiv comment7 pages, 7 figures. Accepted for publication at the 2020 IEEE/ACM Fifth Workshop on Deep Learning on Supercomputers (DLS)

References in corpus (22)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• The Structure of Cold Dark Matter Halos
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Deep Residual Learning for Image Recognition
• Going Deeper with Convolutions
• The merger rate of galaxies in the Illustris Simulation: a comparison with observations and semi-empirical models
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• The Major and Minor Galaxy Merger Rates at z < 1.5
• A Map of the Universe
• The merger rate of massive galaxies
• Galaxy Zoo: the fraction of merging galaxies in the SDSS and their morphologies
• A sparse octree gravitational N-body code that runs entirely on the GPU processor
• The Evolution of Galaxy Number Density at z < 8 and its Implications
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Using transfer learning to detect galaxy mergers
• The M31 Velocity Vector. I. Hubble Space Telescope Proper Motion Measurements
• Galaxy Merger Rates up to z $\sim$ 3 using a Bayesian Deep Learning Model $-$ A Major-Merger classifier using IllustrisTNG Simulation data
• 24.77 Pflops on a Gravitational Tree-Code to Simulate the Milky Way Galaxy with 18600 GPUs
• Automated Distant Galaxy Merger Classifications from Space Telescope Images using the Illustris Simulation
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• SiMon: Simulation Monitor for Computational Astrophysics

Cited by in corpus (3)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping