# Fast and Accurate Non-Linear Predictions of Universes with Deep Learning

arXiv: https://arxiv.org/abs/2012.00240 · HTML: https://mlsanity.com/paper/2012.00240/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation](https://mlsanity.com/paper/2111.08030/) (2021)
- [Field Level Neural Network Emulator for Cosmological N-body Simulations](https://mlsanity.com/paper/2206.04594/) (2022)
- [Machine Learning and Cosmology](https://mlsanity.com/paper/2203.08056/) (2022)
- [COmoving Computer Acceleration (COCA): N-body simulations in an emulated frame of reference](https://mlsanity.com/paper/2409.02154/) (2024)
- [Simple lessons from complex learning: what a neural network model learns about cosmic structure formation](https://mlsanity.com/paper/2206.04573/) (2022)
- [Bayesian deep learning for cosmic volumes with modified gravity](https://mlsanity.com/paper/2309.00612/) (2023)
- [Super-resolving Dark Matter Halos using Generative Deep Learning](https://mlsanity.com/paper/2111.06393/) (2021)

## Abstract (arXiv)

Cosmologists aim to model the evolution of initially low amplitude Gaussian density fluctuations into the highly non-linear "cosmic web" of galaxies and clusters. They aim to compare simulations of this structure formation process with observations of large-scale structure traced by galaxies and infer the properties of the dark energy and dark matter that make up 95% of the universe. These ensembles of simulations of billions of galaxies are computationally demanding, so that more efficient approaches to tracing the non-linear growth of structure are needed. We build a V-Net based model that transforms fast linear predictions into fully nonlinear predictions from numerical simulations. Our NN model learns to emulate the simulations down to small scales and is both faster and more accurate than the current state-of-the-art approximate methods. It also achieves comparable accuracy when tested on universes of significantly different cosmological parameters from the one used in training. This suggests that our model generalizes well beyond our training set.