Painting with baryons: augmenting N-body simulations with gas using deep generative models

1 code implementation • 28 Mar 2019 • Tilman Tröster, Cameron Ferguson, Joachim Harnois-Déraps, Ian G. McCarthy

We train two deep generative models, a variational auto-encoder and a generative adversarial network, on pairs of matter density and pressure slices from the BAHAMAS hydrodynamical simulation.

Generative Adversarial Network