JERALD: high-fidelity dark matter, stellar mass and neutral hydrogen maps from fast N-body simulations

TL;DR

JERALD is a new fast deep learning method that produces high-resolution maps of dark matter, stellar mass, and neutral hydrogen from lower-resolution simulations, closely matching detailed hydrodynamic results across a range of scales.

Contribution

It extends Lagrangian Deep Learning techniques to generate high-fidelity cosmic maps from approximate simulations, improving resolution and accuracy for large-scale structure analysis.

Findings

Maps match high-resolution simulation power spectra within 90% up to k~1 h/Mpc.

Neutral hydrogen spectra agree within 70% up to k~10 h/Mpc.

The method is fast, accurate, and applicable across redshifts from 5 to 0.

Abstract

We present a new code and approach, JERALD -- JAX Enhanced Resolution Approximate Lagrangian Dynamics -- , that improves on and extends the Lagrangian Deep Learning method of Dai & Seljak (2021), producing high-resolution dark matter, stellar mass and neutral hydrogen maps from lower-resolution approximate $N$-body simulations. The model is trained using the Sherwood-Relics simulation suite (for a fixed cosmology), specifically designed for the intergalactic medium and the neutral hydrogen distribution in the cosmic web. The output is tested in the redshift range from $z=5$ to $z=0$ and the generalization properties of the learned mapping is demonstrated. JERALD produces maps with dark matter, stellar and neutral hydrogen power spectra in excellent agreement with full-hydrodynamic simulations with $8\times$ higher resolution, at large and intermediate scales; in particular, JERALD's neutral hydrogen power spectra agree with their higher-resolution full-hydrodynamic counterparts within 90% up to $k\simeq1\,h$Mpc$^{-1}$ and within 70% up to $k\simeq10\,h$Mpc$^{-1}$. JERALD provides a fast, accurate and physically motivated approach that we plan to embed in a statistical inference pipeline, such as Simulation-Based Inference, to constrain dark matter properties from large- to intermediate-scale structure observables.