Cosmic Velocity Field Reconstruction Using AI
| Autor: | Ziyong Wu, Zhenyu Zhang, Shuyang Pan, Haitao Miao, Xiaolin Luo, Xin Wang, Cristiano G. Sabiu, Jaime Forero-Romero, Yang Wang, Xiao-Dong Li |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Physics
Cosmology and Nongalactic Astrophysics (astro-ph.CO) 010504 meteorology & atmospheric sciences Dark matter FOS: Physical sciences Astronomy and Astrophysics General Relativity and Quantum Cosmology (gr-qc) Astrophysics Vorticity 01 natural sciences General Relativity and Quantum Cosmology Computational physics Convolution Momentum Space and Planetary Science 0103 physical sciences Vector field Deconvolution Perturbation theory Divergence (statistics) 010303 astronomy & astrophysics 0105 earth and related environmental sciences Astrophysics - Cosmology and Nongalactic Astrophysics |
| Popis: | 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. 10 pages, 6 figures, 4 tables, accepted for publication in ApJ |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|