Learning the Evolution of the Universe in N-body Simulations
This work reduces storage requirements for large N-body simulations, benefiting cosmologists by enabling more efficient reconstruction of cosmic history from fewer snapshots.
This paper addresses the computational and storage burden of N-body simulations used in cosmology by developing a deep neural network to predict intermediate time steps. The model successfully reconstructs the nonlinear N-body simulation between two widely separated snapshots, outperforming cubic Hermite interpolation.
Understanding the physics of large cosmological surveys down to small (nonlinear) scales will significantly improve our knowledge of the Universe. Large N-body simulations have been built to obtain predictions in the non-linear regime. However, N-body simulations are computationally expensive and generate large amount of data, putting burdens on storage. These data are snapshots of the simulated Universe at different times, and fine sampling is necessary to accurately save its whole history. We employ a deep neural network model to predict the nonlinear N-body simulation at an intermediate time step given two widely separated snapshots. Our results outperform the cubic Hermite interpolation benchmark method in interpolating N-body simulations. This work can greatly reduce the storage requirement and allow us to reconstruct the cosmic history from far fewer snapshots of the universe.