ASCL.net

Astrophysics Source Code Library

Making codes discoverable since 1999

ASCL Code Record

[ascl:2209.010] HyPhy: Hydrodynamical Physics via Deep Generative Painting

HyPhy maps from dark matter only simulations to full hydrodynamical physics models. It uses a fully convolutional variational auto-encoder (VAE) to synthesize hydrodynamic fields conditioned on dark matter fields from N-body simulations. After training, HyPhy can probabilistically map new dark matter only simulations to corresponding full hydrodynamical outputs and generate posterior samples for studying the variance of the mapping. This conditional deep generative model is implemented in TensorFlow.

Code site:
https://github.com/bhorowitz/HyPhy-public
Described in:
https://ui.adsabs.harvard.edu/abs/2021arXiv210612675H
Bibcode:
2022ascl.soft09010H

Views: 966

ascl:2209.010
Add this shield to your page
Copy the above HTML to add this shield to your code's website.