Cosmological parameter estimation from large-scale structure deep learning

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 $256h^{-1}\mathrm{Mpc}$, 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 $0.16\le {\Omega }_m\le 0.46$ and $2.0\le 10^9{A}_s\le 2.3$. 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.

arXiv comment17 pages, 10 figures, 1 table

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Machine learning and the physical sciences
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• The 2dF Galaxy Redshift Survey: Final Data Release
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• An interpretable machine learning framework for dark matter halo formation
• From Dark Matter to Galaxies with Convolutional Networks
• A deep learning model to emulate simulations of cosmic reionization
• The Role of Machine Learning in the Next Decade of Cosmology
• Cosmological model discrimination with Deep Learning
• CosmoFlow: Using Deep Learning to Learn the Universe at Scale
• Improved Photometric Classification of Supernovae using Deep Learning
• Fast Wiener filtering of CMB maps with Neural Networks
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• CMB-GAN: Fast Simulations of Cosmic Microwave background anisotropy maps using Deep Learning
• Model Comparison of Dark Energy models Using Deep Network
• Deconfusing intensity maps with neural networks

Cited by in corpus (1)

• Decoding Dark Matter Substructure without Supervision