Super-resolution emulator of cosmological simulations using deep physical models

Abstract

We present an extension of our recently developed Wasserstein optimized model to emulate accurate high-resolution features from computationally cheaper low-resolution cosmological simulations. Our deep physical modelling technique relies on restricted neural networks to perform a mapping of the distribution of the low-resolution cosmic density field to the space of the high-resolution small-scale structures. We constrain our network using a single triplet of high-resolution initial conditions and the corresponding low- and high-resolution evolved dark matter simulations from the Quijote suite of simulations. We exploit the information content of the high-resolution initial conditions as a well constructed prior distribution from which the network emulates the small-scale structures. Once fitted, our physical model yields emulated high-resolution simulations at low computational cost, while also providing some insights about how the large-scale modes affect the small-scale structure in real space.

arXiv comment11 pages, 10 figures. Accepted for publication in MNRAS

References in corpus (36)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• The cosmological simulation code GADGET-2
• Efficient Computation of CMB anisotropies in closed FRW models
• Improved Training of Wasserstein GANs
• Euclid Definition Study Report
• Wasserstein GAN
• Don't Decay the Learning Rate, Increase the Batch Size
• Towards Principled Methods for Training Generative Adversarial Networks
• Bayesian physical reconstruction of initial conditions from large scale structure surveys
• TensorFlow Distributions
• Precision cosmography with stacked voids
• Learning to Predict the Cosmological Structure Formation
• Constraints on Cosmology and Gravity from the Dynamics of Voids
• Physical Bayesian modelling of the non-linear matter distribution: new insights into the Nearby Universe
• Simulating nonlinear cosmological structure formation with massive neutrinos
• Nuisance hardened data compression for fast likelihood-free inference
• Automatic physical inference with information maximising neural networks
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Fast cosmic web simulations with generative adversarial networks
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Cosmological inference from Bayesian forward modelling of deep galaxy redshift surveys
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• From Dark Matter to Galaxies with Convolutional Networks
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Inferring high redshift large-scale structure dynamics from the Lyman-alpha forest
• Systematic-free inference of the cosmic matter density field from SDSS3-BOSS data
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Neural physical engines for inferring the halo mass distribution function
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems
• Cosmological N-body simulations: a challenge for scalable generative models

Cited by in corpus (45)

• The Quijote simulations
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Large-scale dark matter simulations
• AI-assisted super-resolution cosmological simulations
• New Interpretable Statistics for Large Scale Structure Analysis and Generation
• The GIGANTES dataset: precision cosmology from voids in the machine learning era
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• The CAMELS project: public data release
• CARPool: fast, accurate computation of large-scale structure statistics by pairing costly and cheap cosmological simulations
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• Lossless, Scalable Implicit Likelihood Inference for Cosmological Fields
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• A fast particle-mesh simulation of non-linear cosmological structure formation with massive neutrinos
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Machine Learning for Observational Cosmology
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• Multi-Fidelity Emulation for the Matter Power Spectrum using Gaussian Processes
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• HInet: Generating neutral hydrogen from dark matter with neural networks
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Fast and realistic large-scale structure from machine-learning-augmented random field simulations
• Modeling assembly bias with machine learning and symbolic regression
• Machine Learning and Cosmology
• Observing relativistic features in large-scale structure surveys -- II: Doppler magnification in an ensemble of relativistic simulations
• AI-assisted super-resolution cosmological simulations III: Time evolution
• Deep Forest: Neural Network reconstruction of the Lyman-alpha forest
• Deep learning insights into cosmological structure formation
• Bayesian Control Variates for optimal covariance estimation with pairs of simulations and surrogates
• Foreground Removal of CO Intensity Mapping Using Deep Learning
• Bayesian deep learning for cosmic volumes with modified gravity
• MF-Box: Multi-fidelity and multi-scale emulation for the matter power spectrum
• Deep Forest: Neural Network reconstruction of intergalactic medium temperature
• COmoving Computer Acceleration (COCA): $N$-body simulations in an emulated frame of reference
• Cosmological Inference with Cosmic Voids and Neural Network Emulators
• Hybrid summary statistics: neural weak lensing inference beyond the power spectrum
• Properties beyond mass for unresolved haloes across redshift and cosmology using correlations with local halo environment
• Stochastic Super-resolution of Cosmological Simulations with Denoising Diffusion Models
• Super-resolution simulation of the Fuzzy Dark Matter cosmological model
• Power Spectrum Emulators from Neural Networks and Tree-Based Methods
• Improving cosmological covariance matrices with machine learning
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders
• Differentiable Fuzzy Cosmic-Web for Field Level Inference