Explaining dark matter halo density profiles with neural networks
This work addresses the challenge of interpreting complex astrophysical data for scientists, though it is incremental as it builds on known relations while uncovering new insights.
The researchers tackled the problem of explaining dark matter halo density profiles by using explainable neural networks to connect halo evolutionary history with density profiles, discovering that the profile beyond the virial radius is described by a single parameter related to recent mass accretion rate.
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.