Large-scale density and velocity field reconstructions with neural networks

Abstract

We assess a neural network (NN) method for reconstructing 3D cosmological density and velocity fields (target) from discrete and incomplete galaxy distributions (input). We employ second-order Lagrangian Perturbation Theory to generate a large ensemble of mock data to train an autoencoder (AE) architecture with a Mean Squared Error (MSE) loss function. The AE successfully captures nonlinear features arising from gravitational dynamics and the discreteness of the galaxy distribution. It preserves the positivity of the reconstructed density field and exhibits a weaker suppression of the power on small scales than the traditional linear Wiener filter (WF), which we use as a benchmark. In the density reconstruction, the reduction of the AE MSE relative to the WF is $\sim 15\%$, whereas, for the velocity reconstruction, a relative reduction of up to a factor of two can be achieved. The AE is advantageous to the WF at recovering the distribution of the target fields, especially at the tails. In fact, trained with an MSE loss, any NN estimate approaches the unbiased mean of the underlying target given the input. This implies a slope of unity in the linear regression of the true on the NN-reconstructed field. Only for the special case of Gaussian fields, the NN and WF estimates are equivalent. Nonetheless, we also recover a linear regression slope of unity for the WF with non-Gaussian fields.

arXiv comment18 pages, 13 figures. Accepted in MNRAS

References in corpus (66)

• The Seventh Data Release of the Sloan Digital Sky Survey
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample
• The 2dF Galaxy Redshift Survey: Spectra and redshifts
• The Sixteenth Data Release of the Sloan Digital Sky Surveys: First Release from the APOGEE-2 Southern Survey and Full Release of eBOSS Spectra
• The DESI Experiment Part I: Science,Targeting, and Survey Design
• The 6dF Galaxy Survey: Final Redshift Release (DR3) and Southern Large-Scale Structures
• The Tenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Apache Point Observatory Galactic Evolution Experiment
• LSST Science Book, Version 2.0
• The 2MASS Redshift Survey - Description and Data Release
• The density and peculiar velocity fields of nearby galaxies
• Cosmicflows-3
• The 6dF Galaxy Survey: z \approx 0 measurement of the growth rate and sigma_8
• The WiggleZ Dark Energy Survey: the growth rate of cosmic structure since redshift z=0.9
• ANNz: estimating photometric redshifts using artificial neural networks
• Interpreting large-scale redshift-space distortion measurements
• Transients from Initial Conditions: A Perturbative Analysis
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the luminous red galaxy sample from the anisotropic correlation function between redshifts 0.6 and 1
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the luminous red galaxy sample from the anisotropic power spectrum between redshifts 0.6 and 1.0
• The Clustering of the SDSS Main Galaxy Sample II: Mock galaxy catalogues and a measurement of the growth of structure from Redshift Space Distortions at $z=0.15$
• Cosmological parameters from the comparison of peculiar velocities with predictions from the 2M++ density field
• Cosmic flows in the nearby universe from Type Ia Supernovae
• The 2M++ galaxy redshift catalogue
• Wiener Reconstruction of The Large Scale Structure
• The 2dF Galaxy Redshift Survey: Spherical Harmonics analysis of fluctuations in the final catalogue
• AbacusSummit: A Massive Set of High-Accuracy, High-Resolution $N$-Body Simulations
• Estimating photometric redshifts with artificial neural networks
• 4MOST - 4-metre Multi-Object Spectroscopic Telescope
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the emission line galaxy sample from the anisotropic power spectrum between redshift 0.6 and 1.1
• Reconstructed Density and Velocity Fields from the 2MASS Redshift Survey
• Local Gravity versus Local Velocity: Solutions for $\beta$ and nonlinear bias
• The 6dF Galaxy Survey: Peculiar Velocity Field and Cosmography
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Growth rate of structure measurement from anisotropic clustering analysis in configuration space between redshift 0.6 and 1.1 for the Emission Line Galaxy sample
• Joint analysis of 6dFGS and SDSS peculiar velocities for the growth rate of cosmic structure and tests of gravity
• Wiener Reconstruction of Large-Scale Structure from Peculiar Velocities
• Bayesian reconstruction of the cosmological large-scale structure: methodology, inverse algorithms and numerical optimization
• Photometric redshifts with the Multilayer Perceptron Neural Network: application to the HDF-S and SDSS
• Action Principle Solutions For Galaxy Motions Within 3000 Km/s
• An Artificial Neural Network Approach to Classification of Galaxy Spectra
• Wiener Reconstruction of Density, Velocity, and Potential Fields from All-Sky Galaxy Redshift Surveys
• Cosmic flows in the nearby Universe: new peculiar velocities from SNe and cosmological constraints
• Growth rate of cosmological perturbations at z ~ 0.1 from a new observational test
• Neural computation as a tool for galaxy classification : methods and examples
• 3D Velocity and Density Reconstructions of the Local Universe with Cosmicflows-1
• Comparison of Velocity and Gravity Fields: The Mark III Tully-Fisher Catalog Versus the IRAS 1.2 Jy Survey
• Cosmological Parameters from the Comparison of the 2MASS Gravity Field with Peculiar Velocity Surveys
• The peculiar velocity field up to $z\sim 0.05$ by forward-modeling Cosmicflows-3 data
• Time-analyticity of Lagrangian particle trajectories in ideal fluid flow
• Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification
• Consistency of the growth rate in different environments with the 6dF Galaxy Survey: measurement of the void-galaxy and galaxy-galaxy correlation functions
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• The velocity field of 2MRS Ks=11.75 galaxies: constraints on beta and bulk flow from the luminosity function
• Learning cosmology and clustering with cosmic graphs
• Wiener Reconstruction of the IRAS 1.2Jy Galaxy Redshift Survey: Cosmographical Implications
• Constrained realizations of 2MRS density and peculiar velocity fields: growth rate and local flow
• On density and velocity fields and beta from the IRAS PSCz survey
• Peculiar-velocity cosmology with Types Ia and II supernovae
• Power spectrum multipoles on the curved sky: an application to the 6-degree Field Galaxy Survey
• The 2MASS Redshift Survey in the Zone of Avoidance
• A comparison of the galaxy peculiar velocity field with the PSCz gravity field-- A Bayesian hyper-parameter method
• Cosmic Velocity Field Reconstruction Using AI
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• Convolutional Neural Network-reconstructed velocity for kinetic SZ detection
• Cosmology from Galaxy Redshift Surveys with PointNet
• De-noising non-Gaussian fields in cosmology with normalizing flows

Cited by in corpus (7)

• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Neural network reconstruction of density and velocity fields from the 2MASS Redshift Survey
• Dynamics of pairwise motions in the fully non-linear regime in LCDM and Modified Gravity cosmologies
• Peculiar Velocity Reconstruction From Simulations and Observations Using Deep Learning Algorithms
• The Velocity Field Olympics: Assessing velocity field reconstructions with direct distance tracers
• AVISM: Algorithm for Void Identification in coSMology
• From Redshift to Real Space: Combining Linear Theory With Neural Networks