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

TL;DR

This paper introduces a deep learning model that efficiently and accurately predicts the non-linear evolution of cosmic structures, outperforming existing methods and generalizing across different cosmological parameters.

Contribution

We develop a V-Net based neural network that emulates complex cosmological simulations, providing faster and more accurate predictions of structure formation.

Findings

Model outperforms current approximate methods in accuracy and speed.

The neural network generalizes well to different cosmological parameters.

Achieves detailed non-linear predictions comparable to full simulations.

Abstract

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.