Fast, high-fidelity Lyman $\alpha$ forests with convolutional neural networks

Abstract

Full-physics cosmological simulations are powerful tools for studying the formation and evolution of structure in the universe but require extreme computational resources. Here, we train a convolutional neural network to use a cheaper N-body-only simulation to reconstruct the baryon hydrodynamic variables (density, temperature, and velocity) on scales relevant to the Lyman-$\alpha$ (Ly$\alpha$) forest, using data from Nyx simulations. We show that our method enables rapid estimation of these fields at a resolution of $\sim$20kpc, and captures the statistics of the Ly$\alpha$ forest with much greater accuracy than existing approximations. Because our model is fully-convolutional, we can train on smaller simulation boxes and deploy on much larger ones, enabling substantial computational savings. Furthermore, as our method produces an approximation for the hydrodynamic fields instead of Ly$\alpha$ flux directly, it is not limited to a particular choice of ionizing background or mean transmitted flux.

arXiv comment10 pages, 6 figures

References in corpus (33)

• Radiative transfer in a clumpy universe: IV. New synthesis models of the cosmic UV/X-ray background
• Where are the Baryons?
• Equation of State of the Photoionized Intergalactic Medium
• New Constraints on the free-streaming of warm dark matter from intermediate and small scale Lyman-$\alpha$ forest data
• Probing the Universe with the Lyman-alpha Forest: I. Hydrodynamics of the Low Density IGM
• The Opacity of the Lyman Alpha Forest and Implications for Omega_{baryon} and the Ionizing Background
• The Evolution of the Intergalactic Medium
• Strong bound on canonical ultra-light axion dark matter from the Lyman-alpha forest
• Nyx: A Massively Parallel AMR Code for Computational Cosmology
• Detecting shock waves in cosmological smoothed particle hydrodynamics simulations
• The Power Spectrum of Mass Fluctuations Measured from the Lyman-alpha Forest at Redshift z=2.5
• The Lyman-$\alpha$ forest in optically-thin hydrodynamical simulations
• New Constraints on IGM Thermal Evolution from the Lyα Forest Power Spectrum
• Revealing reionization with the thermal history of the intergalactic medium: new constraints from the Lyman-$\alpha$ flux power spectrum
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Bias, redshift space distortions and primordial nongaussianity of nonlinear transformations: application to Lyman alpha forest
• Inhomogeneous Reionization Models in Cosmological Hydrodynamical Simulations
• An emulator for the Lyman-$\alpha$ forest in beyond-$\Lambda$CDM cosmologies
• TARDIS Paper I: A Constrained Reconstruction Approach to Modeling the z~2.5 Cosmic Web Probed by Lyman-alpha Forest Tomography
• Galactic Wind Effects on the Lyman-alpha Absorption in the Vicinity of Galaxies
• Detecting shocked intergalactic gas with X-ray and radio observations
• The impact of AGN feedback on the 1D power spectra from the Ly$\alpha$ forest using the Horizon-AGN suite of simulations
• The Low Column Density Lyman-alpha Forest
• Simulating the effect of high column density absorbers on the one-dimensional Lyman-alpha forest flux power spectrum
• Inhomogeneous HeII reionization in Hydrodynamic Simulations
• LyMAS: Predicting Large-Scale Lyman-alpha Forest Statistics from the Dark Matter Density Field
• Modeling the Lyman-alpha Forest in Collisionless Simulations
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Simulating intergalactic gas for DESI-like small scale Lymanα forest observations
• Inferring high redshift large-scale structure dynamics from the Lyman-alpha forest
• TARDIS Paper II: Synergistic Density Reconstruction from Lyman-alpha Forest and Spectroscopic Galaxy Surveys with Applications to Protoclusters and the Cosmic Web
• Teaching neural networks to generate Fast Sunyaev Zel'dovich Maps
• The impact of galactic winds from LBGs on the Intergalactic Medium

Cited by in corpus (8)

• The CAMELS project: public data release
• HyPhy: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
• LyMAS reloaded: improving the predictions of the large-scale Lyman-α forest statistics from dark matter density and velocity fields
• Ly$\alpha$NNA: A Deep Learning Field-level Inference Machine for the Lyman-$\alpha$ Forest
• Differentiable Cosmological Hydrodynamics for Field-Level Inference and High Dimensional Parameter Constraints
• Modeling the Cosmological Lyman-$\alpha$ Forest at the Field Level
• Neural network emulator to constrain the high-$z$ IGM thermal state from Lyman-$\alpha$ forest flux auto-correlation function
• Bridging Simulations and EFT: A Hybrid Model of the Lyman-Alpha Forest Field