Cosmological parameter estimation from large-scale structure deep learning

TL;DR

This paper introduces a lightweight deep CNN that accurately estimates cosmological parameters from simulated large-scale structure data, outperforming previous methods and demonstrating robustness against various data perturbations.

Contribution

The paper presents a novel, efficient CNN architecture that achieves unprecedented accuracy in cosmological parameter estimation from 3D dark matter distributions, surpassing prior CNN approaches.

Findings

Achieves 2.5% bias correction on $\sigma_8$

Provides constraints with $ riangle \Omega_m$=0.0015 and $ riangle \sigma_8$=0.0029

Demonstrates robustness against noise, smoothing, masking, and other data variations.

Abstract

We propose a light-weight deep convolutional neural network (CNN) to estimate the cosmological parameters from simulated 3-dimensional dark matter distributions with high accuracy. The training set is based on 465 realizations of a cubic box with a side length of $256\ h^{-1}\ \rm Mpc$, sampled with $128^3$ particles interpolated over a cubic grid of $128^3$ voxels. These volumes have cosmological parameters varying within the flat $\Lambda$CDM parameter space of $0.16 \leq \Omega_m \leq 0.46$ and $2.0 \leq 10^9 A_s \leq 2.3$. The neural network takes as an input cubes with $32^3$ voxels and has three convolution layers, three dense layers, together with some batch normalization and pooling layers. In the final predictions from the network we find a $2.5\%$ bias on the primordial amplitude $\sigma_8$ that can not easily be resolved by continued training. We correct this bias to obtain unprecedented accuracy in the cosmological parameter estimation with statistical uncertainties of $\delta \Omega_m$=0.0015 and $\delta \sigma_8$=0.0029, which are several times better than the results of previous CNN works. Compared with a 2-point analysis method using clustering region of 0-130 and 10-130 $h^{-1}$ Mpc, the CNN constraints are several times and an order of magnitude more precise, respectively. Finally, we conduct preliminary checks of the error-tolerance abilities of the neural network, and find that it exhibits robustness against smoothing, masking, random noise, global variation, rotation, reflection, and simulation resolution. Those effects are well understood in typical clustering analysis, but had not been tested before for the CNN approach. Our work shows that CNN can be more promising than people expected in deriving tight cosmological constraints from the cosmic large scale structure.