Discovering the building blocks of dark matter halo density profiles with neural networks

TL;DR

This paper introduces a neural network model that accurately predicts dark matter halo density profiles from raw data, capturing both the standard NFW profile and the variability in outer regions, revealing insights into halo boundaries.

Contribution

The study presents a novel encoder-decoder neural network that learns the mapping from raw density fields to profiles, uncovering the splashback boundary without prior dynamical information.

Findings

Neural network recovers the NFW profile up to the virial radius.

A 2D latent space models profiles within the virial radius.

A 3D latent space captures outer profile variability and splashback boundary.

Abstract

The density profiles of dark matter halos are typically modeled using empirical formulae fitted to the density profiles of relaxed halo populations. We present a neural network model that is trained to learn the mapping from the raw density field containing each halo to the dark matter density profile. We show that the model recovers the widely-used Navarro-Frenk-White (NFW) profile out to the virial radius, and can additionally describe the variability in the outer profile of the halos. The neural network architecture consists of a supervised encoder-decoder framework, which first compresses the density inputs into a low-dimensional latent representation, and then outputs $\rho(r)$ for any desired value of radius $r$. The latent representation contains all the information used by the model to predict the density profiles. This allows us to interpret the latent representation by quantifying the mutual information between the representation and the halos' ground-truth density profiles. A two-dimensional representation is sufficient to accurately model the density profiles up to the virial radius; however, a three-dimensional representation is required to describe the outer profiles beyond the virial radius. The additional dimension in the representation contains information about the infalling material in the outer profiles of dark matter halos, thus discovering the splashback boundary of halos without prior knowledge of the halos' dynamical history.