Fast Generation of Large-scale Structure Density Maps via Generative Adversarial Networks

TL;DR

This paper demonstrates that Generative Adversarial Networks can rapidly produce realistic 3D density maps of large-scale cosmic structures, significantly speeding up simulations of universe evolution.

Contribution

The study introduces a GAN-based method for fast, high-fidelity generation of large-scale structure density maps, outperforming traditional simulation speeds.

Findings

GANs can generate thousands of realistic density maps in seconds

Generated maps are indistinguishable from those from N-body simulations

The method enables efficient study of cosmic structure evolution

Abstract

Generative Adversarial Networks (GANs) are a recent advancement in unsupervised machine learning. They are a cat-and-mouse game between two neural networks: [1] a discriminator network which learns to validate whether a sample is real or fake compared to a training set and [2] a generator network which learns to generate data that appear to belong to the training set. Both networks learn from each other until training is complete and the generator network is able to produce samples that are indistinguishable from the training set. We find that GANs are well-suited for fast generation of novel 3D density maps that are indistinguishable from those obtained from N-body simulations. In a matter of seconds, a fully trained GAN can generate thousands of density maps at different epochs in the history of the universe. These GAN-generated maps can then be used to study the evolution of large-scale structure over time.