Deep learning insights into cosmological structure formation

Abstract

The evolution of linear initial conditions present in the early universe into extended halos of dark matter at late times can be computed using cosmological simulations. However, a theoretical understanding of this complex process remains elusive; in particular, the role of anisotropic information in the initial conditions in establishing the final mass of dark matter halos remains a long-standing puzzle. Here, we build a deep learning framework to investigate this question. We train a three-dimensional convolutional neural network (CNN) to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses. We find that anisotropies add a small, albeit statistically significant amount of information over that contained within spherical averages of the density field about final halo mass. However, the overall scatter in the final mass predictions does not change qualitatively with this additional information, only decreasing from 0.9 dex to 0.7 dex. Given such a small improvement, our results demonstrate that isotropic aspects of the initial density field essentially saturate the relevant information about final halo mass. Therefore, instead of searching for information directly encoded in initial conditions anisotropies, a more promising route to accurate, fast halo mass predictions is to add approximate dynamical information based e.g. on perturbation theory. More broadly, our results indicate that deep learning frameworks can provide a powerful tool for extracting physical insight into cosmological structure formation.

arXiv comment17 pages, 10 figures. Accepted in PRD

References in corpus (36)

• Auto-Encoding Variational Bayes
• A Universal Density Profile from Hierarchical Clustering
• The cosmological simulation code GADGET-2
• Large scale bias and the peak background split
• Interpretable machine learning: definitions, methods, and applications
• Ellipsoidal collapse and an improved model for the number and spatial distribution of dark matter haloes
• Five-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Likelihoods and Parameters from the WMAP data
• GADGET: A code for collisionless and gasdynamical cosmological simulations
• Mass function of dark matter halos
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• An excursion set model of hierarchical clustering: Ellipsoidal collapse and the moving barrier
• The 2dF Galaxy Redshift Survey: The power spectrum and the matter content of the universe
• Group Sparse Regularization for Deep Neural Networks
• Discovering physical concepts with neural networks
• PINOCCHIO: pinpointing orbit-crossing collapsed hierarchical objects in a linear density field
• Learning to Predict the Cosmological Structure Formation
• AI-assisted super-resolution cosmological simulations
• The mass-Peak Patch algorithm for fast generation of deep all-sky dark matter halo catalogues and its N-Body validation
• Cosmological constraints from noisy convergence maps through deep learning
• Excursion set peaks: a self-consistent model of dark halo abundances and clustering
• Super-resolution emulator of cosmological simulations using deep physical models
• Machine learning cosmological structure formation
• GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• GenetIC -- a new initial conditions generator to support genetically modified zoom simulations
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• An interpretable machine learning framework for dark matter halo formation
• From Dark Matter to Galaxies with Convolutional Networks
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Excursion set peaks: the role of shear
• Neural physical engines for inferring the halo mass distribution function
• Operationally meaningful representations of physical systems in neural networks
• A robust estimator of mutual information for deep learning interpretability
• Neural networks as optimal estimators to marginalize over baryonic effects
• Estimating Cosmological Parameters from the Dark Matter Distribution

Cited by in corpus (8)

• Massive $\nu$s through the CNN lens: interpreting the field-level neutrino mass information in weak lensing
• Anisotropic cosmology using observational datasets: exploring via machine learning approaches
• Inferring halo masses with Graph Neural Networks
• Interpreting Cosmological Information from Neural Networks in the Hydrodynamic Universe
• Excursion Sets with a "Perfect" Collapse Model
• Interpretability of deep-learning methods applied to large-scale structure surveys
• Cosmic velocity, density and halo mass function: Insights from deep learning
• Segmenting proto-halos with vision transformers