Explaining dark matter halo density profiles with neural networks

TL;DR

This paper employs explainable neural networks to uncover how dark matter halo evolution influences their density profiles, revealing known and novel relationships without prior assumptions.

Contribution

It introduces a neural network approach that interprets dark matter halo profiles and their evolution, discovering key physical relations in an unsupervised manner.

Findings

Inner profiles relate to early halo assembly

Outer profiles depend on recent mass accretion rate

Neural networks recover known and new physical insights

Abstract

We use explainable neural networks to connect the evolutionary history of dark matter halos with their density profiles. The network captures independent factors of variation in the density profiles within a low-dimensional representation, which we physically interpret using mutual information. Without any prior knowledge of the halos' evolution, the network recovers the known relation between the early time assembly and the inner profile, and discovers that the profile beyond the virial radius is described by a single parameter capturing the most recent mass accretion rate. The results illustrate the potential for machine-assisted scientific discovery in complicated astrophysical datasets.