Constraining cosmological parameters from N-body simulations with Bayesian Neural Networks
This work addresses precision cosmology challenges for researchers by providing a method to better estimate uncertainties, though it is incremental as it applies an existing technique to a specific domain.
The authors tackled the problem of extracting cosmological parameters from N-body simulations by using Bayesian Neural Networks, achieving improved uncertainty estimation and the ability to capture complex distributions and non-Gaussianities.
In this paper, we use The Quijote simulations in order to extract the cosmological parameters through Bayesian Neural Networks. This kind of model has a remarkable ability to estimate the associated uncertainty, which is one of the ultimate goals in the precision cosmology era. We demonstrate the advantages of BNNs for extracting more complex output distributions and non-Gaussianities information from the simulations.