Cosmological super-resolution of the 21-cm signal

In this study, we train score-based diffusion models to super-resolve gigaparsec-scale cosmological simulations of the 21-cm signal. We examine the impact of network and training dataset size on model performance, demonstrating that a single simulation is sufficient for a model to learn the super-resolution task regardless of the initial conditions. Our best-performing model achieves pixelwise $\mathrm{R}\mathrm{M}\mathrm{S}\mathrm{E}\sim 0.57\mathrm{m}\mathrm{K}$ and dimensionless power spectrum residuals ranging from ${10}^{-2}-{10}^{-1}\mathrm{m}{\mathrm{K}}^2$ for ${128}^3$, ${256}^3$ and ${512}^3$ voxel simulation volumes at redshift $10$. The super-resolution network ultimately allows us to utilize all spatial scales covered by the SKA1-Low instrument, and could in future be employed to help constrain the astrophysics of the early Universe.