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.

10 pages, 6 figures, 4 tables, accepted for publication in ApJ

References in corpus (8)

• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• Properties of Dark Matter Haloes in Clusters, Filaments, Sheets and Voids
• SFI++ I: A New I-band Tully-Fisher Template, the Cluster Peculiar Velocity Dispersion and H0
• Cosmic web alignments with the shape, angular momentum and peculiar velocities of dark matter haloes
• Cosmological constraints from the redshift dependence of the Alcock-Paczynski effect: application to the SDSS-III BOSS DR12 galaxies
• Observational biases in Lagrangian reconstructions of cosmic velocity fields
• Cosmological constraints from the redshift dependence of the Alcock-Paczynski test and volume effect: galaxy two-point correlation function
• Nonlinear stochastic growth rates and redshift space distortions

Cited by in corpus (1)

• Cosmological constraints from the density gradient weighted correlation function