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.

17 pages, 10 figures. Accepted in PRD

References in corpus (9)

• Five-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Likelihoods and Parameters from the WMAP data
• Group Sparse Regularization for Deep Neural Networks
• AI-assisted super-resolution cosmological simulations
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• From Dark Matter to Galaxies with Convolutional Networks
• Excursion set peaks: the role of shear
• 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