Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow

Simple item page
dc.contributor.authorWiewel, Steffenen_US
dc.contributor.authorBecher, Moritzen_US
dc.contributor.authorThuerey, Nilsen_US
dc.contributor.editorAlliez, Pierre and Pellacini, Fabioen_US
dc.date.accessioned2019-05-05T17:39:28Z
dc.date.available2019-05-05T17:39:28Z
dc.date.issued2019
dc.description.abstractWe propose a method for the data-driven inference of temporal evolutions of physical functions with deep learning. More specifically, we target fluid flow problems, and we propose a novel LSTM-based approach to predict the changes of the pressure field over time. The central challenge in this context is the high dimensionality of Eulerian space-time data sets. We demonstrate for the first time that dense 3D+time functions of physics system can be predicted within the latent spaces of neural networks, and we arrive at a neural-network based simulation algorithm with significant practical speed-ups. We highlight the capabilities of our method with a series of complex liquid simulations, and with a set of single-phase buoyancy simulations. With a set of trained networks, our method is more than two orders of magnitudes faster than a traditional pressure solver. Additionally, we present and discuss a series of detailed evaluations for the different components of our algorithm.en_US
dc.description.number2
dc.description.sectionheadersFluids
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13620
dc.identifier.issn1467-8659
dc.identifier.pages71-82
dc.identifier.urihttps://doi.org/10.1111/cgf.13620
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13620
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectPhysical simulation
dc.titleLatent Space Physics: Towards Learning the Temporal Evolution of Fluid Flowen_US
Files
Collections
38-Issue 2