Psi-GAN: A power-spectrum-informed generative adversarial network for the emulation of large-scale structure maps across cosmologies and redshifts

Simulations of the dark matter distribution throughout the Universe are essential in order to analyse data from cosmological surveys. $N$-body simulations are computationally expensive, and many cheaper alternatives (such as lognormal random fields) fail to reproduce accurate statistics of the smaller, non-linear scales. In this work, we present $\text{textsc}Psi-GAN$ ($\mathbf{\text{P}}$ower-$\mathbf{\text{s}}$pectrum-$\mathbf{\text{i}}$nformed $\mathbf{\text{G}}$enerative $\mathbf{\text{A}}$dversarial $\mathbf{\text{N}}$etwork), a machine learning model which takes a two-dimensional lognormal dark matter density field and transforms it into a more realistic field. We construct $\text{textsc}Psi-GAN$ so that it is continuously conditional, and can therefore generate realistic realisations of the dark matter density field across a range of cosmologies and redshifts in $z\in [0,3]$. We train $\text{textsc}Psi-GAN$ as a generative adversarial network on $2000$ simulation boxes from the Quijote simulation suite. We use a novel critic architecture that utilises the power spectrum as the basis for discrimination between real and generated samples. $\text{textsc}Psi-GAN$ shows agreement with $N$-body simulations over a range of redshifts and cosmologies, consistently outperforming the lognormal approximation on all tests of non-linear structure, such as being able to reproduce both the power spectrum up to wavenumbers of $1h{\mathrm{M}\mathrm{p}\mathrm{c}}^{-1}$, and the bispectra of target $N$-body simulations to within $\sim 5$ per cent. Our improved ability to model non-linear structure should allow more robust constraints on cosmological parameters when used in techniques such as simulation-based inference.