Predicting bulge to total luminosity ratio of galaxies using deep learning

Abstract

We present a deep learning model to predict the r-band bulge-to-total light ratio (B/T) of nearby galaxies using their multi-band JPEG images alone. Our Convolutional Neural Network (CNN) based regression model is trained on a large sample of galaxies with reliable decomposition into the bulge and disk components. The existing approaches to estimate the B/T use galaxy light-profile modelling to find the best fit. This method is computationally expensive, prohibitively so for large samples of galaxies, and requires a significant amount of human intervention. Machine learning models have the potential to overcome these shortcomings. In our CNN model, for a test set of 20000 galaxies, 85.7 per cent of the predicted B/T values have absolute error (AE) less than 0.1. We see further improvement to 87.5 per cent if, while testing, we only consider brighter galaxies (with r-band apparent magnitude < 17) with no bright neighbours. Our model estimates B/T for the 20000 test galaxies in less than a minute. This is a significant improvement in inference time from the conventional fitting pipelines, which manage around 2-3 estimates per minute. Thus, the proposed machine learning approach could potentially save a tremendous amount of time, effort and computational resources while predicting B/T reliably, particularly in the era of next-generation sky surveys such as the Legacy Survey of Space and Time (LSST) and the Euclid sky survey which will produce extremely large samples of galaxies.

arXiv comment11 pages, 3 tables, 8 figures, accepted for publication in MNRAS

References in corpus (48)

• Adam: A Method for Stochastic Optimization
• The Seventh Data Release of the Sloan Digital Sky Survey
• Deep Residual Learning for Image Recognition
• Coevolution (Or Not) of Supermassive Black Holes and Host Galaxies
• Detailed Structural Decomposition of Galaxy Images
• Secular Evolution and the Formation of Pseudobulges in Disk Galaxies
• The Relation between Black Hole Mass, Bulge Mass, and Near-Infrared Luminosity
• The Atlas3D project - XX. Mass-size and mass-sigma distributions of early-type galaxies: bulge fraction drives kinematics, mass-to-light ratio, molecular gas fraction and stellar initial mass function
• Structural Properties of Pseudo-Bulges, Classical Bulges and Elliptical Galaxies: an SDSS Perspective
• ANNz: estimating photometric redshifts using artificial neural networks
• A Catalog of Detailed Visual Morphological Classifications for 14034 Galaxies in the Sloan Digital Sky Survey
• Mergers and Bulge Formation in Lambda-CDM: Which Mergers Matter?
• Preparing Red-Green-Blue (RGB) Images from CCD Data
• Mask R-CNN
• The Fifteenth Data Release of the Sloan Digital Sky Surveys: First Release of MaNGA Derived Quantities, Data Visualization Tools and Stellar Library
• Xception: Deep Learning with Depthwise Separable Convolutions
• The Structure of Classical Bulges And Pseudobulges: The Link Between Pseudobulges And Sersic Index
• Inclination- and dust-corrected galaxy parameters: Bulge-to-disc ratios and size-luminosity relations
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Imfit: A Fast, Flexible New Program for Astronomical Image Fitting
• Bulge mass is king: The dominant role of the bulge in determining the fraction of passive galaxies in the Sloan Digital Sky Survey
• BUDDA: A New Two-Dimensional Bulge/Disk Decomposition Code for Detailed Structural Analysis of Galaxies
• Revisiting the Hubble sequence in the SDSS DR7 spectroscopic sample: a publicly available bayesian automated classification
• Estimating photometric redshifts with artificial neural networks
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• A catalogue of 2D photometric decompositions in the SDSS-DR7 spectroscopic main galaxy sample: preferred models and systematics
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• GALAPAGOS: From Pixels to Parameters
• Machine Learning in Astronomy: a practical overview
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Photometric redshifts with the Multilayer Perceptron Neural Network: application to the HDF-S and SDSS
• Estimating Photometric Redshifts Using Support Vector Machines
• ProFit: Bayesian Profile Fitting of Galaxy Images
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• Deep learning for galaxy surface brightness profile fitting
• HOLISMOKES -- II. Identifying galaxy-scale strong gravitational lenses in Pan-STARRS using convolutional neural networks
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks
• An Artificial Neural Network Approach For Ranking Quenching Parameters In Central Galaxies
• PyMorph: Automated Galaxy Structural Parameter Estimation using Python
• Neural Networks and Photometric Redshifts
• An Optimal Strategy for Accurate Bulge-to-disk Decomposition of Disk Galaxies
• Detection of Bars in Galaxies using a Deep Convolutional Neural Network
• Two dimensional bulge disk decomposition
• A difference boosting neural network for automated star-galaxy classification
• Predicting star formation properties of galaxies using deep learning
• The infra-red luminosities of ~332,000 SDSS galaxies predicted from artificial neural networks and the Herschel Stripe 82 survey
• Galaxy shape measurement with convolutional neural networks

Cited by in corpus (4)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• B/PS bulges in DESI Legacy edge-on galaxies I: Sample building
• HOLISMOKES -- X. Comparison between neural network and semi-automated traditional modeling of strong lenses
• Insights on Galaxy Evolution from Interpretable Sparse Feature Networks