%0 Generic %1 ramanah2020superresolution %A Ramanah, Doogesh Kodi %A Charnock, Tom %A Villaescusa-Navarro, Francisco %A Wandelt, Benjamin D. %D 2020 %K library %T Super-resolution emulator of cosmological simulations using deep physical models %U http://arxiv.org/abs/2001.05519 %X We present an extension of our recently developed Wasserstein optimized model to emulate accurate high-resolution features from computationally cheaper low-resolution cosmological simulations. Our deep physical modelling technique relies on restricted neural networks to perform a mapping of the distribution of the low-resolution cosmic density field to the space of the high-resolution small-scale structures. We constrain our network using a single triplet of high-resolution initial conditions and the corresponding low- and high-resolution evolved dark matter simulations from the Quijote suite of simulations. We exploit the information content of the high-resolution initial conditions as a well constructed prior distribution from which the network emulates the small-scale structures. Once fitted, our physical model yields emulated high-resolution simulations at low computational cost, while also providing some insights about how the large-scale modes affect the small-scale structure in real space.

@misc{ramanah2020superresolution, abstract = {We present an extension of our recently developed Wasserstein optimized model to emulate accurate high-resolution features from computationally cheaper low-resolution cosmological simulations. Our deep physical modelling technique relies on restricted neural networks to perform a mapping of the distribution of the low-resolution cosmic density field to the space of the high-resolution small-scale structures. We constrain our network using a single triplet of high-resolution initial conditions and the corresponding low- and high-resolution evolved dark matter simulations from the Quijote suite of simulations. We exploit the information content of the high-resolution initial conditions as a well constructed prior distribution from which the network emulates the small-scale structures. Once fitted, our physical model yields emulated high-resolution simulations at low computational cost, while also providing some insights about how the large-scale modes affect the small-scale structure in real space.}, added-at = {2020-01-17T07:38:26.000+0100}, author = {Ramanah, Doogesh Kodi and Charnock, Tom and Villaescusa-Navarro, Francisco and Wandelt, Benjamin D.}, biburl = {https://www.bibsonomy.org/bibtex/2ea443ad8875c697da470635330485a3b/gpkulkarni}, description = {Super-resolution emulator of cosmological simulations using deep physical models}, interhash = {d9819d818a2053588cf46f5333c139b0}, intrahash = {ea443ad8875c697da470635330485a3b}, keywords = {library}, note = {cite arxiv:2001.05519Comment: 10 pages, 9 figures. For submission to MNRAS}, timestamp = {2020-01-17T07:38:26.000+0100}, title = {Super-resolution emulator of cosmological simulations using deep physical models}, url = {http://arxiv.org/abs/2001.05519}, year = 2020 }