Cosmic Velocity Field Reconstruction Using AI

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