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 RMSE∼0.57mK and dimensionless power spectrum residuals ranging from 10−2−10−1mK2 for 1283, 2563 and 5123 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.
@article{arxiv.2502.00852,
title = {Cosmological super-resolution of the 21-cm signal},
author = {Simon Pochinda and Jiten Dhandha and Anastasia Fialkov and Eloy de Lera Acedo},
journal= {arXiv preprint arXiv:2502.00852},
year = {2025}
}
Comments
10 pages, 2 figures, accepted submission for the Machine Learning and the Physical Sciences Workshop at the 38th conference on Neural Information Processing Systems (NeurIPS), OpenReview link: https://openreview.net/forum?id=QGgeqMV8Er