Cosmic Velocity Field Reconstruction Using AI

Abstract

We develop a deep learning technique to infer the non-linear velocity field from the dark matter density field. The deep learning architecture we use is an "U-net" style convolutional neural network, which consists of 15 convolution layers and 2 deconvolution layers. This setup maps the 3-dimensional density field of $32^3$-voxels to the 3-dimensional velocity or momentum fields of $20^3$-voxels. Through the analysis of the dark matter simulation with a resolution of $2h^{-1}\mathrm{Mpc}$, we find that the network can predict the the non-linearity, complexity and vorticity of the velocity and momentum fields, as well as the power spectra of their value, divergence and vorticity and its prediction accuracy reaches the range of $k\simeq 1.4$ $h{\mathrm{Mpc}}^{-1}$ with a relative error ranging from 1% to $\lesssim$10%. A simple comparison shows that neural networks may have an overwhelming advantage over perturbation theory in the reconstruction of velocity or momentum fields.

arXiv comment10 pages, 6 figures, 4 tables, accepted for publication in ApJ

References in corpus (67)

• Detection of the Baryon Acoustic Peak in the Large-Scale Correlation Function of SDSS Luminous Red Galaxies
• Machine learning and the physical sciences
• A high-bias, low-variance introduction to Machine Learning for physicists
• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• Properties of Dark Matter Haloes in Clusters, Filaments, Sheets and Voids
• Fingers of God
• Solving Large Scale Structure in Ten Easy Steps with COLA
• A Dynamical Classification of the Cosmic Web
• Looking for $\Lambda$ with the Rees-Sciama Effect
• Cosmic flows in the nearby universe from Type Ia Supernovae
• Wiener Reconstruction of The Large Scale Structure
• Learning to Predict the Cosmological Structure Formation
• Photometric Supernova Classification With Machine Learning
• A kinematic classification of the cosmic web
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• SFI++ I: A New I-band Tully-Fisher Template, the Cluster Peculiar Velocity Dispersion and H0
• Rejuvenating the matter power spectrum: restoring information with a logarithmic density mapping
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Non-Gaussian information from weak lensing data via deep learning
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• 2MTF I. The Tully-Fisher Relation in the 2MASS J, H and K Bands
• Reconstructing the Cosmic Velocity and Tidal Fields with Galaxy Groups Selected from the Sloan Digital Sky Survey
• Cosmic web alignments with the shape, angular momentum and peculiar velocities of dark matter haloes
• Fast cosmic web simulations with generative adversarial networks
• Deep-Learning continuous gravitational waves
• The Velocity Field from Type Ia Supernovae Matches the Gravity Field from Galaxy Surveys
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Distinguishing standard and modified gravity cosmologies with machine learning
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Reconstruction of cosmological density and velocity fields in the Lagrangian Zel'dovich Approximation
• Machine learning cosmological structure formation
• Evaluating machine learning techniques for predicting power spectra from reionization simulations
• Cosmological inference from Bayesian forward modelling of deep galaxy redshift surveys
• Identifying Reionization Sources from 21cm Maps using Convolutional Neural Networks
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Cosmological constraints from the redshift dependence of the Alcock-Paczynski effect: application to the SDSS-III BOSS DR12 galaxies
• A Comparison of Local SNIa with the IRAS PSCz Gravity Field
• Peculiar Velocity Reconstruction with Fast Action Method: Tests on Mock Redshift Surveys
• The Cosmological Mean Density and its Local Variations Probed by Peculiar Velocities
• An interpretable machine learning framework for dark matter halo formation
• On the dissection of degenerate cosmologies with machine learning
• Estimating cosmic velocity fields from density fields and tidal tensors
• Linearisation with Cosmological Perturbation Theory
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• A deep learning model to emulate simulations of cosmic reionization
• Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal
• Observational biases in Lagrangian reconstructions of cosmic velocity fields
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Nonlinearity and stochasticity in the density--velocity relation
• Cosmological constraints from the redshift dependence of the Alcock-Paczynski test: galaxy density gradient field
• Cosmological constraints from the redshift dependence of the Alcock-Paczynski test and volume effect: galaxy two-point correlation function
• Reconstructing Cosmic Peculiar Velocities from the Mildly Nonlinear Density Field
• The Clustering of Galaxies in the Completed SDSS-III Baryon Oscillation Spectroscopic Survey: Cosmic Flows and Cosmic Web from Luminous Red Galaxies
• Beta-Skeleton Analysis of the Cosmic Web
• The velocity-density relation in the spherical model
• Straightening the Density-Displacement Relation with a Logarithmic Transform
• Detectability of Cosmic Dark Flow in the Type Ia Supernova Redshift-Distance Relation
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• Nonlinear stochastic growth rates and redshift space distortions
• Superclusters from velocity divergence fields

Cited by in corpus (16)

• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Large-scale density and velocity field reconstructions with neural networks
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Convolutional Neural Network-reconstructed velocity for kinetic SZ detection
• The cosmic web connection to the dark matter halo distribution through gravity
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Sensitivity tests of cosmic velocity fields to massive neutrinos
• Neural network reconstruction of density and velocity fields from the 2MASS Redshift Survey
• Fast generation of mock galaxy catalogues with COLA
• DarkAI: Reconstructing the density, velocity and tidal field of dark matter from a DESI-like bright galaxy sample
• Deep learning for cosmological parameter inference from a dark matter halo density field
• Peculiar Velocity Reconstruction From Simulations and Observations Using Deep Learning Algorithms
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Map Reconstruction of radio observations with Conditional Invertible Neural Networks
• AVISM: Algorithm for Void Identification in coSMology
• Cosmological constraints from the density gradient weighted correlation function