GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples

Abstract

Next generation large sky surveys will observe up to billions of galaxies for which basic structural parameters are needed to study their evolution. This is a challenging task that, for ground-based observations, is complicated by seeing limited point-spread function (PSF). To perform a fast and accurate analysis of galaxy surface brightness, we have developed a family of supervised Convolutional Neural Networks (CNN) to derive Sersic profile parameters of galaxies. This work presents the first two Galaxy Light profile convolutional neural Networks (GaLNets) of this family. The first one is trained using galaxy images only (GaLNet-1), and the second is trained with both galaxy images and the local PSF (GaLNet-2). We have compared the results from the GaLNets with structural parameters (total magnitude, effective radius, Sersic index etc.) derived on a set of galaxies from the Kilo-Degree Survey (KiDS) by 2DPHOT, as a representative of "standard" PSF convolved Sersic fitting tools. The comparison shows that GaLNet-2 can reach an accuracy as high as 2DPHOT, while GaLNet-1 performs worse because it misses the information on the local PSF. Both GaLNets are three orders of magnitude faster than standard methods in terms of computational speed. This first application of CNNs to ground-based galaxy surface photometry shows that they are promising tools to perform parametric analyses of very large galaxy samples, like the ones expected from Vera Rubin/LSST surveys. However, the GaLNets can be easily modified for space observations from Euclid and the China Space Station Telescope.

Accepted for publication by APJ

References in corpus (62)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Detailed Structural Decomposition of Galaxy Images
• The size distribution of galaxies in the Sloan Digital Sky Survey
• Euclid Definition Study Report
• The Two Phases of Galaxy Formation
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Strong size evolution of the most massive galaxies since z~2
• The Sloan Lens ACS Survey. V. The Full ACS Strong-Lens Sample
• The DEEP Groth Strip Survey II. Hubble Space Telescope Structural Parameters of Galaxies in the Groth Strip
• Size evolution of the most massive galaxies at 1.7<z<3 from GOODS NICMOS survey imaging
• The cosmological size and velocity dispersion evolution of massive early-type galaxies
• Galaxy And Mass Assembly (GAMA): The galaxy stellar mass function at z < 0.06
• The fourth data release of the Kilo-Degree Survey: ugri imaging and nine-band optical-IR photometry over 1000 square degrees
• Galaxy And Mass Assembly (GAMA): mass-size relations of z$<$0.1 galaxies subdivided by Sérsic index, colour and morphology
• The first and second data releases of the Kilo-Degree Survey
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• The Formation of Massive, Compact Galaxies at z=2 in the Illustris Simulation
• The third data release of the Kilo-Degree Survey and associated data products
• The effects of seeing on Sersic profiles. II. The Moffat PSF
• Size evolution of normal and compact galaxies in the EAGLE simulation
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• The BOSS Emission-Line Lens Survey (BELLS). I. A large spectroscopically selected sample of Lens Galaxies at redshift ~ 0.5
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Geometry of Star-Forming Galaxies from SDSS, 3D-HST and CANDELS
• On the estimation of galaxy structural parameters: the Sersic Model
• GALAPAGOS: From Pixels to Parameters
• Curvature in the scaling relations of early-type galaxies
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Galaxy And Mass Assembly (GAMA): ${\mathcal{M}}_{\star }-R_{\mathrm{e}}$ relations of $z=0$ bulges, discs and spheroids
• The diverse evolutionary paths of simulated high-z massive, compact galaxies to z=0
• LinKS: Discovering galaxy-scale strong lenses in the Kilo-Degree Survey using Convolutional Neural Networks
• The BOSS Emission-Line Lens Survey. IV. : Smooth Lens Models for the BELLS GALLERY Sample
• Deep learning for galaxy surface brightness profile fitting
• Hyper Suprime-Cam Subaru Strategic Program: A Mass-Dependent Slope of the Galaxy Size-Mass Relation at $z<1$
• 2DPHOT: A Multi-purpose Environment for the Two-dimensional Analysis of Wide-field Images
• 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
• A catalog of polychromatic bulge-disk decompositions of ~ 17.600 galaxies in CANDELS
• Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks
• Evolution of galaxy size--stellar mass relation from the Kilo Degree Survey
• The Origin of Color Gradients in Early-Type Systems and Their Compactness at High-z
• Beyond Ellipse(s): Accurately Modelling the Isophotal Structure of Galaxies with $Isofit$ and $Cmodel$
• PyMorph: Automated Galaxy Structural Parameter Estimation using Python
• Photometry of high-redshift blended galaxies using deep learning
• High-quality strong lens candidates in the final Kilo Degree survey footprint
• Hierarchical Inference With Bayesian Neural Networks: An Application to Strong Gravitational Lensing
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• KiDS-SQuaD II: Machine learning selection of bright extragalactic objects to search for new gravitationally lensed quasars
• AutoProf -- I. An automated non-parametric light profile pipeline for modern galaxy surveys
• The first sample of spectroscopically confirmed ultra-compact massive galaxies in the Kilo Degree Survey
• A catalogue of structural and morphological measurements for DES Y1
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• New insight on galaxy structure from GALPHAT I. Motivation, methodology, and benchmarks for Sersic models
• Unsupervised feature-learning for galaxy SEDs with denoising autoencoders
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• Star-Galaxy Image Separation with Computationally Efficient Gaussian Process Classification
• Large Synoptic Survey Telescope Galaxies Science Roadmap
• Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language 'captioning' model
• Rejection criteria based on outliers in the KiDS photometric redshifts and PDF distributions derived by machine learning

Cited by in corpus (16)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• A Robust Study of High-Redshift Galaxies: Unsupervised Machine Learning for Characterising morphology with JWST up to z ~ 8
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• HOLISMOKES -- IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images
• From Images to Features: Unbiased Morphology Classification via Variational Auto-Encoders and Domain Adaptation
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Forklens: Accurate weak-lensing shear measurement with deep learning
• HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
• Total and dark mass from observations of galaxy centers with Machine Learning
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• Optimizing Redshift Distribution Inference through Joint Self-Calibration and Clustering-Redshift Synergy
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• Impact of PSF misestimation and galaxy population bias on precision shear measurement using a CNN
• The $10\mathrm{kpc}$ collar of early-type galaxies -- probing evolution by focusing on the inner stellar density profile
• Identification of gravitational lenses obscured by foreground light in the KiDS dataset using U-Nets and ResNets