Multifield Cosmology with Artificial Intelligence

TL;DR

This paper demonstrates that convolutional neural networks trained on multifield hydrodynamic simulation maps can accurately infer cosmological parameters while effectively marginalizing over complex astrophysical effects, outperforming gravity-only models.

Contribution

The study introduces a novel multifield neural network approach that extracts cosmological information from hydrodynamic simulations, effectively marginalizing astrophysical uncertainties.

Findings

Neural networks infer $\Omega_{m}$ and $\sigma_8$ with a few percent precision.

Multifield maps improve parameter constraints over single-field models.

Networks trained on multifields outperform gravity-only N-body simulations in parameter inference.

Abstract

Astrophysical processes such as feedback from supernovae and active galactic nuclei modify the properties and spatial distribution of dark matter, gas, and galaxies in a poorly understood way. This uncertainty is one of the main theoretical obstacles to extract information from cosmological surveys. We use 2,000 state-of-the-art hydrodynamic simulations from the CAMELS project spanning a wide variety of cosmological and astrophysical models and generate hundreds of thousands of 2-dimensional maps for 13 different fields: from dark matter to gas and stellar properties. We use these maps to train convolutional neural networks to extract the maximum amount of cosmological information while marginalizing over astrophysical effects at the field level. Although our maps only cover a small area of $(25~h^{-1}{\rm Mpc})^2$, and the different fields are contaminated by astrophysical effects in very different ways, our networks can infer the values of $\Omega_{\rm m}$ and $\sigma_8$ with a few percent level precision for most of the fields. We find that the marginalization performed by the network retains a wealth of cosmological information compared to a model trained on maps from gravity-only N-body simulations that are not contaminated by astrophysical effects. Finally, we train our networks on multifields -- 2D maps that contain several fields as different colors or channels -- and find that not only they can infer the value of all parameters with higher accuracy than networks trained on individual fields, but they can constrain the value of $\Omega_{\rm m}$ with higher accuracy than the maps from the N-body simulations.