Predicting large scale cosmological structure evolution with GAN-based autoencoders
This work addresses the problem of efficient cosmological simulation for researchers, but it is incremental as it adapts existing GAN-based methods to a specific domain with mixed success.
The paper tackled predicting large-scale cosmological structure evolution using GAN-based autoencoders, finding that they perform well for 2D dark matter simulations with density fields alone but poorly for 3D simulations unless velocity fields are added, which greatly improves results with consistent predictions across time differences.
Cosmological simulations play a key role in the prediction and understanding of large scale structure formation from initial conditions. We make use of GAN-based Autoencoders (AEs) in an attempt to predict structure evolution within simulations. The AEs are trained on images and cubes issued from respectively 2D and 3D N-body simulations describing the evolution of the dark matter (DM) field. We find that while the AEs can predict structure evolution for 2D simulations of DM fields well, using only the density fields as input, they perform significantly more poorly in similar conditions for 3D simulations. However, additionally providing velocity fields as inputs greatly improves results, with similar predictions regardless of time-difference between input and target.