PINION: Physics-informed neural network for accelerating radiative transfer simulations for cosmic reionization

Abstract

With the advent of the Square Kilometre Array Observatory (SKAO), scientists will be able to directly observe the Epoch of Reionization by mapping the distribution of neutral hydrogen at different redshifts. While physically motivated results can be simulated with radiative transfer codes, these simulations are computationally expensive and can not readily produce the required scale and resolution simultaneously. Here we introduce the Physics-Informed neural Network for reIONization (PINION), which can accurately and swiftly predict the complete 4-D hydrogen fraction evolution from the smoothed gas and mass density fields from pre-computed N-body simulation. We trained PINION on the C${}^2$-Ray simulation outputs and a physics constraint on the reionization chemistry equation is enforced. With only five redshift snapshots and a propagation mask as a simplistic approximation of the ionizing photon mean free path, PINION can accurately predict the entire reionization history between $z=6$ and $12$. We evaluate the accuracy of our predictions by analysing the dimensionless power spectra and morphology statistics estimations against C${}^2$-Ray results. We show that while the network's predictions are in good agreement with simulation to redshift $z>7$, the network's accuracy suffers for $z<7$ primarily due to the oversimplified propagation mask. We motivate how PINION performance can be drastically improved and potentially generalized to large-scale simulations.

15 pages, 15 figures, 1 table

References in corpus (18)

• Wilkinson Microwave Anisotropy Probe (WMAP) Three Year Results: Implications for Cosmology
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• Transients from Initial Conditions in Cosmological Simulations
• Model-independent evidence in favor of an end to reionization by z~6
• Improved upper limits on the 21-cm signal power spectrum of neutral hydrogen at $\mathbf{z}\approx 9.1$ from LOFAR
• New observations of z~7 galaxies: evidence for a patchy reionization
• Deep multi-redshift limits on Epoch of Reionisation 21cm Power Spectra from Four Seasons of Murchison Widefield Array Observations
• Rapid Decline of Lyman-alpha Emission Toward the Reionization Era
• 21 cm signal from cosmic dawn: Imprints of spin temperature fluctuations and peculiar velocities
• Constraining the intergalactic medium at $z\approx$ 9.1 using LOFAR Epoch of Reionization observations
• Multi-redshift limits on the 21cm power spectrum from PAPER
• Initial LOFAR observations of Epoch of Reionization windows: II. Diffuse polarized emission in the ELAIS-N1 field
• Bubble size statistics during reionization from 21-cm tomography
• Constraining the state of the intergalactic medium during the Epoch of Reionization using MWA 21-cm signal observations
• The short ionizing photon mean free path at z=6 in Cosmic Dawn III, a new fully-coupled radiation-hydrodynamical simulation of the Epoch of Reionization
• Mapmaking for Precision 21 cm Cosmology
• Redshifted 21-cm bispectrum: Impact of the source models on the signal and the IGM physics from the Cosmic Dawn
• Large HI optical depth and Redshifted 21-cm signal from cosmic dawn

Cited by in corpus (6)

• Extracting the Global 21-cm signal from Cosmic Dawn and Epoch of Reionization in the presence of Foreground and Ionosphere
• Solving the Pulsar Equation using Physics-Informed Neural Networks
• A fast method of reionization parameter space exploration using GPR trained SCRIPT
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Reionisation time fields reconstruction from 21 cm signal maps
• CosmoUiT: A Vision Transformer-UNet Hybrid for Fast and Accurate Emulation of 21-cm Maps from the Epoch of Reionization