PkANN - II. A non-linear matter power spectrum interpolator developed using artificial neural networks

Understand

In this paper we introduce PkANN, a freely available software package for interpolating the non-linear matter power spectrum, constructed using Artificial Neural Networks (ANNs).

• Previously, using Halofit to calculate matter power spectrum, we demonstrated that ANNs can make extremely quick and accurate predictions of the power spectrum.
• Now, using a suite of 6380 N-body simulations spanning 580 cosmologies, we train ANNs to predict the power spectrum over the cosmological parameter space spanning $3\sigma$ confidence level (CL) around the concordance cosmology.
• When presented with a set of cosmological parameters ($\Omega_{\rm m} h^2, \Omega_{\rm b} h^2, n_s, w, \sigma_8, \sum m_\nu$ and redshift $z$), the trained ANN interpolates the power spectrum for $z\leq2$ at sub-per cent accuracy for modes up to $k\leq0.9\,h\textrm{Mpc}^{-1}$.