Learning to predict the cosmological structure formation
From MaRDI portal
Abstract: Matter evolved under influence of gravity from minuscule density fluctuations. Non-perturbative structure formed hierarchically over all scales, and developed non-Gaussian features in the Universe, known as the Cosmic Web. To fully understand the structure formation of the Universe is one of the holy grails of modern astrophysics. Astrophysicists survey large volumes of the Universe and employ a large ensemble of computer simulations to compare with the observed data in order to extract the full information of our own Universe. However, to evolve trillions of galaxies over billions of years even with the simplest physics is a daunting task. We build a deep neural network, the Deep Density Displacement Model (hereafter DM), to predict the non-linear structure formation of the Universe from simple linear perturbation theory. Our extensive analysis, demonstrates that DM outperforms the second order perturbation theory (hereafter 2LPT), the commonly used fast approximate simulation method, in point-wise comparison, 2-point correlation, and 3-point correlation. We also show that DM is able to accurately extrapolate far beyond its training data, and predict structure formation for significantly different cosmological parameters. Our study proves, for the first time, that deep learning is a practical and accurate alternative to approximate simulations of the gravitational structure formation of the Universe.
Recommendations
- A deep learning approach to cosmological dark energy models
- Deep learning approach to Hubble parameter
- Inverse cosmography: testing the effectiveness of cosmographic polynomials using machine learning
- Structure formation in the universe by exact methods
- Simulating the formation of cosmic structure
- Simulation-aided inference in cosmology
- scientific article; zbMATH DE number 7779329
Cited in
(12)- Can deep learning distinguish chaos from noise? Numerical experiments and general considerations
- Automated learning of gravitational mass of elliptical galaxies
- Lossless, scalable implicit likelihood inference for cosmological fields
- Fast and credible likelihood-free cosmology with truncated marginal neural ratio estimation
- CosmicNet. Part I. Physics-driven implementation of neural networks within Einstein-Boltzmann Solvers
- Tutorial on Amortized Optimization
- Deep learning approach to Hubble parameter
- Likelihood-free inference in state-space models with unknown dynamics
- Estimating the mass of the local group using machine learning applied to numerical simulations
- Probabilistic graph networks for learning physics simulations
- Introduction to latent variable energy-based models: a path toward autonomous machine intelligence
- Deep learning of CMB radiation temperature
This page was built for publication: Learning to predict the cosmological structure formation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218562)
