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

Abstract

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 Patch semi-analytic code, we test various CNN architectures and find they generically achieve a Dice coefficient of ~92% in only 24 hours of training. We present a simple and fast geometric halo finding algorithm to extract halos from this powerful pixel-wise binary classifier and find that the predicted catalogues match the mass function and power spectra of the ground truth simulations to within ~10%. We investigate the effect of long-range tidal forces on an object-by-object basis and find that the network's predictions are consistent with the non-linear ellipsoidal collapse equations used explicitly by the Peak Patch algorithm.

arXiv comment12 pages, 8 figures, 1 table. Accepted to MNRAS

References in corpus (41)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Residual Learning for Image Recognition
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Toward a halo mass function for precision cosmology: the limits of universality
• Galaxies on FIRE (Feedback In Realistic Environments): Stellar Feedback Explains Cosmologically Inefficient Star Formation
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing
• Multi-scale initial conditions for cosmological simulations
• Rotation-Dependent Catastrophic Disruption of Gravitational Aggregates
• Dependence of the outer density profiles of halos on their mass accretion rate
• Solving Large Scale Structure in Ten Easy Steps with COLA
• Planck 2015 results. XXVII. The Second Planck Catalogue of Sunyaev-Zeldovich Sources
• The clustering of galaxies in the SDSS-III Baryon Oscillation Spectroscopic Survey: a large sample of mock galaxy catalogues
• Planck 2015 results. XV. Gravitational lensing
• CFHTLenS revisited: assessing concordance with Planck including astrophysical systematics
• A measurement of secondary cosmic microwave background anisotropies from the 2500-square-degree SPT-SZ survey
• Splashback in accreting dark matter halos
• FastPM: a new scheme for fast simulations of dark matter and halos
• EZmocks: extending the Zel'dovich approximation to generate mock galaxy catalogues with accurate clustering statistics
• Mock galaxy catalogs using the quick particle mesh method
• Modelling Baryon Acoustic Oscillations with Perturbation Theory and Stochastic Halo Biasing
• Coaxing Cosmic 21cm Fluctuations from the Polarized Sky using m-mode Analysis
• Line-Intensity Mapping: 2017 Status Report
• An accurate tool for the fast generation of dark matter halo catalogs
• Non-Gaussian information from weak lensing data via deep learning
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• ICE-COLA: Towards fast and accurate synthetic galaxy catalogues optimizing a quasi $N$-body method
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• The mass-Peak Patch algorithm for fast generation of deep all-sky dark matter halo catalogues and its N-Body validation
• Comparing approximate methods for mock catalogues and covariance matrices II: Power spectrum multipoles
• Comparing approximate methods for mock catalogues and covariance matrices I: correlation function
• Comparing approximate methods for mock catalogues and covariance matrices III: Bispectrum
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• HALOGEN: A tool for fast generation of mock halo catalogues
• Machine learning cosmological structure formation
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• Joint power spectrum and voxel intensity distribution forecast on the CO luminosity function with COMAP
• Dark Energy Survey Year 1 Results: galaxy mock catalogues for BAO
• Projected Constraints on Modified Gravity Cosmologies from 21 cm Intensity Mapping
• Measurement of the Cold Dark Matter-Neutrino Dipole in the TianNu Simulation

Cited by in corpus (40)

• Learning to Predict the Cosmological Structure Formation
• Large-scale dark matter simulations
• The Websky Extragalactic CMB Simulations
• AI-assisted super-resolution cosmological simulations
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The mass-Peak Patch algorithm for fast generation of deep all-sky dark matter halo catalogues and its N-Body validation
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Super-resolution emulator of cosmological simulations using deep physical models
• Distinguishing standard and modified gravity cosmologies with machine learning
• Field Level Neural Network Emulator for Cosmological N-body Simulations
• An interpretable machine learning framework for dark matter halo formation
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• ADDGALS: Simulated Sky Catalogs for Wide Field Galaxy Surveys
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• NECOLA: Towards a Universal Field-level Cosmological Emulator
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• A Bayesian method for combining theoretical and simulated covariance matrices for large-scale structure surveys
• Cosmic Velocity Field Reconstruction Using AI
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Modeling assembly bias with machine learning and symbolic regression
• Halo assembly bias from a deep learning model of halo formation
• AI-assisted super-resolution cosmological simulations III: Time evolution
• Deep learning insights into cosmological structure formation
• $\text{PineTree}$: A generative, fast, and differentiable halo model for wide-field galaxy surveys
• A sparse regression approach to modeling the relation between galaxy stellar masses and their host halos
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow
• Bridging the Educational Gap between Emerging and Established Scientific Computing Disciplines
• Predicting halo occupation and galaxy assembly bias with machine learning
• Segmenting proto-halos with vision transformers
• DeepVoid: A Deep Learning Void Detector
• Origin & evolution of the Universe
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations