Cosmic Velocity Field Reconstruction Using AI

TL;DR

This paper presents a deep learning approach using a U-net architecture to accurately reconstruct non-linear cosmic velocity fields from dark matter density data, outperforming traditional perturbation methods.

Contribution

The authors develop a novel deep learning model that effectively maps 3D dark matter density to velocity fields, capturing complex non-linear features and vorticity with high accuracy.

Findings

Predicts velocity and momentum fields with 1-10% error up to k≈1.4 h/Mpc

Outperforms perturbation theory in velocity reconstruction

Successfully captures non-linearity and vorticity in simulated data

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 $2 {h^{-1}}{\rm Mpc}$, 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 $k\simeq1.4$ $h{\rm Mpc}^{-1}$ 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.