A convolutional VAE trained on projected dark matter density slices produces synthetic fields whose power spectra roughly match the training simulation at intermediate scales, with small-scale smoothing and validation only against the same simulation.
The cosmological simulation code gadget-2.Monthly notices of the royal astronomical society, 364(4):1105–1134, 2005
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
astro-ph.CO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Variational autoencoder for generating realistic $N$-body simulations for dark matter halos
A convolutional VAE trained on projected dark matter density slices produces synthetic fields whose power spectra roughly match the training simulation at intermediate scales, with small-scale smoothing and validation only against the same simulation.