High-resolution (HR) simulations in cosmology, in particular when including baryons, can take millions of CPU hours. On the other hand, low-resolution (LR) dark matter simulations of the same cosmological volume use minimal computing resources. We develop a denoising diffusion super-resolution emulator for large cosmological simulation volumes. Our approach is based on the image-to-image Palette diffusion model, which we modify to 3 dimensions. Our super-resolution emulator is trained to perform outpainting, and can thus upgrade very large cosmological volumes from LR to HR using an iterative outpainting procedure. As an application, we generate a simulation box with 8 times the volume of the Illustris TNG300 training data, constructed with over 9000 outpainting iterations, and quantify its accuracy using various summary statistics.
Cite
@article{arxiv.2311.05217,
title = {Super-Resolution Emulation of Large Cosmological Fields with a 3D Conditional Diffusion Model},
author = {Adam Rouhiainen and Michael Gira and Moritz Münchmeyer and Kangwook Lee and Gary Shiu},
journal= {arXiv preprint arXiv:2311.05217},
year = {2024}
}
Comments
20 pages, 11 figures, extended version of NeurIPS 2023 Machine Learning and the Physical Sciences workshop submission