Stochastic Super-resolution of Cosmological Simulations with Denoising Diffusion Models
arXiv:2310.06929 · doi:10.33232/001c.125902
Abstract
In recent years, deep learning models have been successfully employed for augmenting low-resolution cosmological simulations with small-scale information, a task known as "super-resolution". So far, these cosmological super-resolution models have relied on generative adversarial networks (GANs), which can achieve highly realistic results, but suffer from various shortcomings (e.g. low sample diversity). We introduce denoising diffusion models as a powerful generative model for super-resolving cosmic large-scale structure predictions (as a first proof-of-concept in two dimensions). To obtain accurate results down to small scales, we develop a new "filter-boosted" training approach that redistributes the importance of different scales in the pixel-wise training objective. We demonstrate that our model not only produces convincing super-resolution images and power spectra consistent at the percent level, but is also able to reproduce the diversity of small-scale features consistent with a given low-resolution simulation. This enables uncertainty quantification for the generated small-scale features, which is critical for the usefulness of such super-resolution models as a viable surrogate model for cosmic structure formation.
9 pages, 8 figures, to be submitted to OJA, comments welcome
References in corpus (13)
- Proceedings of the 29th International Conference on Machine Learning (ICML-12)
- AbacusSummit: A Massive Set of High-Accuracy, High-Resolution -Body Simulations
- Probabilistic Mass Mapping with Neural Score Estimation
- HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
- From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
- A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
- A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
- Posterior samples of source galaxies in strong gravitational lenses with score-based priors
- Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations
- Normalizing flows for random fields in cosmology
- A deep learning approach to halo merger tree construction
- Strong-Lensing Source Reconstruction with Denoising Diffusion Restoration Models
- Super-Resolution Emulation of Large Cosmological Fields with a 3D Conditional Diffusion Model