Cosmic velocity, density and halo mass function: Insights from deep learning

Abstract

We discuss an implementation of a deep learning framework to gain insight into dark matter (DM) structure formation. We investigate the contribution of velocity and density field information to the construction of the halo mass function (HMF) in cosmological N-body simulations. We train a Convolutional Neural Network (CNN) on the initial snapshot of a DM-only simulation to predict the halo mass that individual particles fall into at $z=0$, in the halo mass range of $10.5<\log (M/M_{\odot })<14$. We show that for the standard $\Lambda$CDM cosmology with amplitude of initial perturbations $A_s=2\times 10^{-9}$, the initial velocity and density fields have equivalent information, as expected in the linear regime, and manifest the power of our CNN to diagnose the redundant information. To investigate the non-linear effects, we increase the initial power spectrum. In the linear regime, this is equivalent to decreasing the initial redshift. The CNN model trained on the simulation snapshots with large $A_s$ shows a considerable improvement in the HMF prediction when adding the velocity field information. Using our CNN map without further physical assumptions, we precisely evaluate when these non-linear effects become vital. Eventually, for the simulation with $A_s=8\times 10^{-8}$, the model trained with only density information shows at least an $80\%$ increase in the mean squared error relative to the model with both velocity and density information. Our work shows the interpretability and ability of CNNs to read higher-order information from simple images, making them an excellent tool for cosmological studies.

14 pages, 12 figures, 1 table. Accepted for publication in Physical Review D

References in corpus (25)

• Simulating the joint evolution of quasars, galaxies and their large-scale distribution
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample
• Methods for Interpreting and Understanding Deep Neural Networks
• An overview of deep learning in medical imaging focusing on MRI
• Baryon Acoustic Oscillations in the Sloan Digital Sky Survey Data Release 7 Galaxy Sample
• Toward a halo mass function for precision cosmology: the limits of universality
• A Survey of Deep Learning Techniques for Autonomous Driving
• The Rockstar Phase-Space Temporal Halo Finder and the Velocity Offsets of Cluster Cores
• An excursion set model of hierarchical clustering: Ellipsoidal collapse and the moving barrier
• Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
• Learning to Predict the Cosmological Structure Formation
• General relativity and cosmic structure formation
• gevolution: a cosmological N-body code based on General Relativity
• Relativistic N-body simulations with massive neutrinos
• $k$-evolution: a relativistic N-body code for clustering dark energy
• An interpretable machine learning framework for dark matter halo formation
• $N$-body simulations for parametrised modified gravity
• Dark Energy Survey Year 1 Results: Measurement of the Galaxy Angular Power Spectrum
• Parametrising non-linear dark energy perturbations
• The Excursion set approach: Stratonovich approximation and Cholesky decomposition
• Late time sky as a probe of steps and oscillations in primordial Universe
• Deep learning insights into cosmological structure formation
• Matrix Formalism of Excursion Set Theory: A new approach to statistics of dark matter halo counting
• Modified initial power spectrum and too big to fail problem
• Relativistic matter bispectrum of cosmic structures on the light cone