Journal
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
Volume 118, Issue 16, Pages -Publisher
NATL ACAD SCIENCES
DOI: 10.1073/pnas.2020324118
Keywords
deep learning; Lagrangian approach; cosmological; hydrodynamical simulation
Categories
Funding
- NSF [1814370, 1839217]
- NASA [80NSSC18K1274]
- US Department of Energy Office of Science User Facility [DE-AC02-05CH11231]
- Direct For Mathematical & Physical Scien [1839217] Funding Source: National Science Foundation
- Division Of Mathematical Sciences [1839217] Funding Source: National Science Foundation
Ask authors/readers for more resources
Generative models aim to learn complex relationships in data to create new simulated data, and Lagrangian deep learning (LDL) is proposed to achieve this by effectively describing physical laws in cosmological hydrodynamical simulations. By utilizing only around 10 layers, LDL outperforms full hydrodynamical simulations at significantly lower computational costs.
The goal of generative models is to learn the intricate relations between the data to create new simulated data, but current approaches fail in very high dimensions. When the true data-generating process is based on physical processes, these impose symmetries and constraints, and the generative model can be created by learning an effective description of the underlying physics, which enables scaling of the generative model to very high dimensions. In this work, we propose Lagrangian deep learning (LDL) for this purpose, applying it to learn outputs of cosmological hydrodynamical simulations. The model uses layers of Lagrangian displacements of particles describing the observables to learn the effective physical laws. The displacements are modeled as the gradient of an effective potential, which explicitly satisfies the translational and rotational invariance. The total number of learned parameters is only of order 10, and they can be viewed as effective theory parameters. We combine N-body solver fast particle mesh (FastPM) with LDL and apply it to a wide range of cosmological outputs, from the dark matter to the stellar maps, gas density, and temperature. The computational cost of LDL is nearly four orders of magnitude lower than that of the full hydrodynamical simulations, yet it outperforms them at the same resolution. We achieve this with only of order 10 layers from the initial conditions to the final output, in contrast to typical cosmological simulations with thousands of time steps. This opens up the possibility of analyzing cosmological observations entirely within this framework, without the need for large dark-matter simulations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available