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

Article Article scientifique Article PINION : physics-informed neural network for accelerating radiative transfer simulations for cosmic reionization eng 2023-02-27 2023-05-02 author Korber Damien 0000-0002-3897-6856 403184 Département d'astronomie (ASTRO) author Bianco Michèle 0000-0002-6766-0017 978194 author Tolley Emma 0000-0002-1027-1213 author Kneib Jean-Paul 0000-0002-4616-4989 781250 902-915 10.1093/mnras/stad615 0035-8711 https://academic.oup.com/mnras/article/521/1/902/7059216 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 cannot 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 4D hydrogen fraction evolution from the smoothed gas and mass density fields from pre-computed N-body simulation. We trained PINION on the C2-Ray simulation outputs and a physics constraint on the reionization chemistry equation is enforced. With only five redshift snapshots, PINION can accurately predict the entire reionization history between z = 6 and 12. We evaluate the accuracy of our predictions by analyzing the dimensionless power spectra and morphology statistics estimations against C2-Ray results. We show that while the network’s predictions are in very good agreement with simulation to redshift z > 7, the network’s accuracy suffers for z < 7. We motivate how PINION performance could be improved using additional inputs and potentially generalized to large-scale simulations. Software: simulations Cosmology: dark ages Cosmology: reionization Cosmology: first stars Radiative transfer Dewey 520 Swiss National Science Foundation AstroSignals: A New Window on the Universe, with the New Generation of Large Radio-Astronomy Facilities 193826 CH Programmes 26 Département d'astronomie 12 false Monthly notices of the Royal Astronomical Society 521 1 645be9b3-46ab-4fc2-9d59-22c06b42cdf1 Article (Published version) Public Article_scientifique_from_crossref.pdf 3802009 application/pdf CC BY-4.0 8c7e78f970371f626133ade25ece16461378833769d8bcc4722c87cf2a12f63d openAccess Faculté des sciences / Département d'astronomie

Title	Published in	Access level	OA Policy	Year	Views	Downloads

PINION : physics-informed neural network for accelerating radiative transfer simulations for cosmic reionization	Monthly notices of the Royal Astronomical Society			2023	59	53

Archive ouverte UNIGE

Bianco, Michèle