Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey

Abstract

The scale of ongoing and future electromagnetic surveys pose formidable challenges to classify astronomical objects. Pioneering efforts on this front include citizen science campaigns adopted by the Sloan Digital Sky Survey (SDSS). SDSS datasets have been recently used to train neural network models to classify galaxies in the Dark Energy Survey (DES) that overlap the footprint of both surveys. Herein, we demonstrate that knowledge from deep learning algorithms, pre-trained with real-object images, can be transferred to classify galaxies that overlap both SDSS and DES surveys, achieving state-of-the-art accuracy $\gtrsim 99.6\%$. We demonstrate that this process can be completed within just eight minutes using distributed training. While this represents a significant step towards the classification of DES galaxies that overlap previous surveys, we need to initiate the characterization of unlabelled DES galaxies in new regions of parameter space. To accelerate this program, we use our neural network classifier to label over ten thousand unlabelled DES galaxies, which do not overlap previous surveys. Furthermore, we use our neural network model as a feature extractor for unsupervised clustering and find that unlabeled DES images can be grouped together in two distinct galaxy classes based on their morphology, which provides a heuristic check that the learning is successfully transferred to the classification of unlabelled DES images. We conclude by showing that these newly labeled datasets can be combined with unsupervised recursive training to create large-scale DES galaxy catalogs in preparation for the Large Synoptic Survey Telescope era.

arXiv comment14 pages, 12 Figures, 6 appendices, 2 visualizations see \<https://www.youtube.com/watch?v=n5rI573i6ws> and \<https://www.youtube.com/watch?v=1F3q7M8QjTQ>

References in corpus (20)

• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Residual Learning for Image Recognition
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• Cosmological Results from High-z Supernovae
• New Constraints on ${\Omega }_M$, ${\Omega }_{\Lambda }$, and w from an Independent Set of Eleven High-Redshift Supernovae Observed with HST
• The Dark Energy Survey: more than dark energy - an overview
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Using transfer learning to detect galaxy mergers
• Neural computation as a tool for galaxy classification : methods and examples
• Galaxies, Human Eyes and Artificial Neural Networks
• Automatic Selection of t-SNE Perplexity
• A Survey on Deep Transfer Learning
• Morphological classification of galaxies and its relation to physical properties

Cited by in corpus (27)

• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• FETCH: A deep-learning based classifier for fast transient classification
• FAIR for AI: An interdisciplinary and international community building perspective
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Self-Supervised Representation Learning for Astronomical Images
• Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
• Deep Transfer Learning for Star Cluster Classification: I. Application to the PHANGS-HST Survey
• A review of unsupervised learning in astronomy
• Galaxy Morphology Classification using Neural Ordinary Differential Equations
• Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
• StarcNet: Machine Learning for Star Cluster Identification
• Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• Star Cluster Classification using Deep Transfer Learning with PHANGS-HST
• On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks
• Connecting optical morphology, environment, and HI mass fraction for low-redshift galaxies using deep learning
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• Unveiling Galaxy Morphology through an Unsupervised-Supervised Hybrid Approach
• Accelerating the search for Axion-Like Particles with machine learning
• FAIR AI Models in High Energy Physics
• Data-driven detection of multi-messenger transients
• Galaxy Zoo JWST: Up to 75% of discs are featureless at $3<z<7$
• AGNet: Weighing Black Holes with Deep Learning
• Visualization in Astrophysics: Developing New Methods, Discovering Our Universe, and Educating the Earth
• Galaxy Morphological Classification with Efficient Vision Transformer