HInet: Generating neutral hydrogen from dark matter with neural networks

Abstract

Upcoming 21cm surveys will map the spatial distribution of cosmic neutral hydrogen (HI) over very large cosmological volumes. In order to maximize the scientific return of these surveys, accurate theoretical predictions are needed. Hydrodynamic simulations currently are the most accurate tool to provide those predictions in the mildly to non-linear regime. Unfortunately, their computational cost is very high: tens of millions of CPU hours. We use convolutional neural networks to find the mapping between the spatial distribution of matter from N-body simulations and HI from the state-of-the-art hydrodynamic simulation IllustrisTNG. Our model performs better than the widely used theoretical model: Halo Occupation Distribution (HOD) for all statistical properties up to the non-linear scales $k\lesssim 1$ h/Mpc. Our method allows the generation of 21cm mocks over very big cosmological volumes with similar properties as hydrodynamic simulations.

arXiv comment10+5 pages, 7+3 figures. Added supplementary figures and sections to the Appendix for clarification, conclusions unchanged. Version appearing in ApJ

References in corpus (67)

• Machine learning and the physical sciences
• Simulating Galaxy Formation with the IllustrisTNG Model
• Simulating galaxy formation with black hole driven thermal and kinetic feedback
• Analytic model for galaxy and dark matter clustering
• First Results from the TNG50 Simulation: Galactic outflows driven by supernovae and black hole feedback
• Halo occupation numbers and galaxy bias
• The Halo Occupation Distribution: Towards an Empirical Determination of the Relation Between Galaxies and Mass
• The imprints of primordial non-gaussianities on large-scale structure: scale dependent bias and abundance of virialized objects
• The age dependence of halo clustering
• How Many Galaxies Fit in a Halo? Constraints on Galaxy Formation Efficiency from Spatial Clustering
• The Dependence of Halo Clustering on Halo Formation History, Concentration, and Occupation
• Cosmological parameters from lensing power spectrum and bispectrum tomography
• Baryon Acoustic Oscillation Intensity Mapping as a Test of Dark Energy
• Galacticus: A Semi-Analytic Model of Galaxy Formation
• The Quijote simulations
• Measurement of 21 cm brightness fluctuations at z ~ 0.8 in cross-correlation
• Late-time cosmology with 21cm intensity mapping experiments
• On the environmental dependence of halo formation
• Cosmology and the Bispectrum
• Power Spectrum Correlations Induced by Non-Linear Clustering
• Learning to Predict the Cosmological Structure Formation
• Ingredients for 21cm intensity mapping
• The Bispectrum: From Theory to Observations
• Lack of clustering in low-redshift 21-cm intensity maps cross-correlated with 2dF galaxy densities
• Constraining $M_{\nu }$ with the Bispectrum I: Breaking Parameter Degeneracies
• Measuring neutrino masses with large-scale structure: Euclid forecast with controlled theoretical error
• Cosmological information in the redshift-space bispectrum
• Modeling Biased Tracers at the Field Level
• Halo assembly bias and the tidal anisotropy of the local halo environment
• Simulating nonlinear cosmological structure formation with massive neutrinos
• Galaxy Power Spectrum Multipoles Covariance in Perturbation Theory
• Constraining $M_{\nu }$ with the Bispectrum II: The Total Information Content of the Galaxy Bispectrum
• Using HI to probe large scale structures at z ~ 3
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Limitations to the "basic'' HOD model and beyond
• HI Fluctuations at Large Redshifts: I--Visibility correlation
• Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
• Intensity Mapping across Cosmic Times with the Lyman-Alpha Line
• Simulations and symmetries
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• On the spatial distribution of neutral hydrogen in the Universe: bias and shot-noise of the HI Power Spectrum
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Modeling the neutral hydrogen distribution in the post-reionization Universe: intensity mapping
• High-redshift post-reionization cosmology with 21cm intensity mapping
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Baryonic acoustic oscillations from 21cm intensity mapping: the Square Kilometre Array case
• Super-resolution emulator of cosmological simulations using deep physical models
• Weighing neutrinos with cosmic neutral hydrogen
• Statistics of Dark Matter Substructure: III. Halo-to-Halo Variance
• The atomic Hydrogen content of the post-reionization Universe
• Reconstructing large-scale structure with neutral hydrogen surveys
• Warm dark matter signatures on the 21cm power spectrum: Intensity mapping forecasts for SKA
• Intensity Mapping as a Probe of Axion Dark Matter
• Forecasts on Primordial non-Gaussianity from 21 cm Intensity Mapping experiments
• Insights from probability distribution functions of intensity maps
• Removing Astrophysics in 21 cm maps with Neural Networks
• A deep learning model to emulate simulations of cosmic reionization
• Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array
• Intensity mapping with neutral hydrogen and the Hidden Valley simulations
• Modelling the cosmic neutral hydrogen from DLAs and 21 cm observations
• Cross-correlating 21 cm and galaxy surveys: implications for cosmology and astrophysics
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• Modelling the post-reionization neutral hydrogen ($\mathrm{HI}$) 21-cm bispectrum
• Deep-Learning Study of the 21cm Differential Brightness Temperature During the Epoch of Reionization
• Teaching neural networks to generate Fast Sunyaev Zel'dovich Maps
• Imprints of non-standard Dark Energy and Dark Matter Models on the 21cm Intensity Map Power Spectrum
• Extreme Spheres: Counts-in-cells for 21cm intensity mapping

Cited by in corpus (19)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• The CAMELS project: public data release
• Finding universal relations in subhalo properties with artificial intelligence
• Machine Learning for Observational Cosmology
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
• Modeling HI at the field level
• Machine Learning methods to estimate observational properties of galaxy clusters in large volume cosmological N-body simulations
• Wavelet Moments for Cosmological Parameter Estimation
• Eliminating polarization leakage effect for neutral hydrogen intensity mapping with deep learning
• HyPhy: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
• MAHGIC: A Model Adapter for the Halo-Galaxy Inter-Connection
• A deep learning approach to halo merger tree construction
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Probing the cosmic web in Ly$\alpha$ emission over large scales: an Intensity Mapping forecast for DECaLS/BASS and DESI
• Large, fast and accurate HI intensity maps with latent overlap diffusion
• Prediction of Individual Halo Concentrations Across Cosmic Time Using Neural Networks