A volumetric deep Convolutional Neural Network for simulation of dark matter halo catalogues

@article{Berger2018AVD,
title={A volumetric deep Convolutional Neural Network for simulation of dark matter halo catalogues},
author={P. Berger and G. Stein},
journal={ArXiv},
year={2018},
volume={abs/1805.04537}
}
• Published 2018
• Computer Science, Physics
• ArXiv
For modern large-scale structure survey techniques it has become standard practice to test data analysis pipelines on large suites of mock simulations, a task which is currently prohibitively expensive for full N-body simulations. Instead of calculating this costly gravitational evolution, we have trained a three-dimensional deep Convolutional Neural Network (CNN) to identify dark matter protohalos directly from the cosmological initial conditions. Training on halo catalogues from the Peak… Expand
24 Citations
A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys
• Physics
• 2019
We present a deep machine learning (ML)-based technique for accurately determining $\sigma_8$ and $\Omega_m$ from mock 3D galaxy surveys. The mock surveys are built from the AbacusCosmos suite ofExpand
The mass-Peak Patch algorithm for fast generation of deep all-sky dark matter halo catalogues and its N-Body validation.
• Physics
• 2018
We present a detailed description and validation of our massively-parallel update to the mass-Peak Patch method, a fully predictive initial-space algorithm to quickly generate dark matter haloExpand
Modeling assembly bias with machine learning and symbolic regression
• Physics
• 2020
Upcoming 21cm surveys will map the spatial distribution of cosmic neutral hydrogen (HI) over unprecedented volumes. Mock catalogues are needed to fully exploit the potential of these surveys.Expand
Cosmic Velocity Field Reconstruction Using AI
We develop a deep-learning technique to infer the nonlinear velocity field from the dark matter density field. The deep-learning architecture we use is a “U-net” style convolutional neural network,Expand
Deep learning insights into cosmological structure formation
• Physics, Computer Science
• ArXiv
• 2020
A deep learning framework is built to learn this non-linear relationship between the mass of dark matter and dark matter halos, and techniques to physically interpret the learnt mapping are developed. Expand
Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Physics
• 2019
We present a novel halo painting network that learns to map approximate 3D dark matter fields to realistic halo distributions. This map is provided via a physically motivated network with which weExpand
AI-assisted superresolution cosmological simulations
• Medicine, Computer Science
• Proceedings of the National Academy of Sciences
• 2021
A deep neural network is built to enhance low-resolution dark-matter simulations, generating superresolution realizations that agree remarkably well with authentic high-resolution counterparts on their statistical properties and are orders-of-magnitude faster. Expand
Learning to predict the cosmological structure formation
• Siyu He, +4 authors B. Póczos
• Physics, Medicine
• Proceedings of the National Academy of Sciences
• 2019
A deep neural network is built, the Deep Density Displacement Model (D3M), which learns from a set of prerun numerical simulations, to predict the nonlinear large-scale structure of the Universe with the Zel’dovich Approximation (ZA), an analytical approximation based on perturbation theory, as the input. Expand
Insights into cosmological structure formation with machine learning.
Our modern understanding of cosmological structure formation posits that small matter density fluctuations present in the early Universe, as traced by the cosmic microwave background, grow viaExpand
Distinguishing standard and modified gravity cosmologies with machine learning
We present a convolutional neural network to identify distinct cosmological scenarios based on the weak-lensing maps they produce. Modified gravity models with massive neutrinos can mimic theExpand

References

SHOWING 1-10 OF 54 REFERENCES
The mass-Peak Patch algorithm for fast generation of deep all-sky dark matter halo catalogues and its N-Body validation.
• Physics
• 2018
We present a detailed description and validation of our massively-parallel update to the mass-Peak Patch method, a fully predictive initial-space algorithm to quickly generate dark matter haloExpand
Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Physics
• 2018
We present a method to reconstruct the initial conditions of the universe using observed galaxy positions and luminosities under the assumption that the luminosities can be calibrated with weakExpand
Fast cosmic web simulations with generative adversarial networks
This paper demonstrates the application of a machine learning technique called Generative Adversarial Networks (GAN) to learn models that can efficiently generate new, physically realistic realizations of the cosmic web, and finds a good match for the correlation matrix of full Pk$P_{k}$ range for 100 Mpc data and of small scales for 500 Mpc, with ∼20% disagreement for large scales. Expand
An accurate tool for the fast generation of dark matter halo catalogues.
We present a new parallel implementation of the PINpointing Orbit Crossing-Collapsed HIerarchical Objects (PINOCCHIO) algorithm, a quick tool, based on Lagrangian Perturbation Theory, for theExpand
Dark energy survey year-1 results : Galaxy mock catalogues for BAO
Mock catalogues are a crucial tool in the analysis of galaxy surveys data, both for the accurate computation of covariance matrices, and for the optimization of analysis methodology and validation ofExpand
Classifying the large-scale structure of the universe with deep neural networks
We present the first application of deep neural networks to the semantic segmentation of cosmological filaments and walls in the Large Scale Structure of the Universe. Our results are based on a deepExpand
Estimating Cosmological Parameters from the Dark Matter Distribution
This paper presents the application of deep 3D convolutional networks to volumetric representation of dark-matter simulations as well as the results obtained using a recently proposed distribution regression framework, showing that machine learning techniques are comparable to, and can sometimes outperform, maximum-likelihood point estimates using "cosmological models". Expand
ICE-COLA: towards fast and accurate synthetic galaxy catalogues optimizing a quasi-N-body method
• Physics
• 2016
Next generation galaxy surveys demand the development of massive ensembles of galaxy mocks to model the observables and their covariances, what is computationally prohibitive using $N$-bodyExpand
halogen: a tool for fast generation of mock halo catalogues
• Physics
• 2015
We present a simple method of generating approximate synthetic halo catalogues: HALOGEN. This method uses a combination of $2^{nd}$-order Lagrangian Perturbation Theory (2LPT) in order to generateExpand
Comparing approximate methods for mock catalogues and covariance matrices II : power spectrum multipoles
We study the accuracy of several approximate methods for gravitational dynamics in terms of halo power spectrum multipoles and their estimated covariance matrix. We propagate the differences inExpand