English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Simulations of turbulent flows in 3D are one of the most expensivesimulations in computational fluid dynamics (CFD). Many works have been writtenon surrogate models to replace numerical solvers for fluid flows with faster,learned, autoregressive models. However, the intricacies of turbulence in threedimensions necessitate training these models with very small time steps, whilegenerating realistic flow states requires either long roll-outs with many stepsand significant error accumulation or starting from a known, realistic flowstate - something we aimed to avoid in the first place. Instead, we propose toapproach turbulent flow simulation as a generative task directly learning themanifold of all possible turbulent flow states without relying on any initialflow state. For our experiments, we introduce a challenging 3D turbulencedataset of high-resolution flows and detailed vortex structures caused byvarious objects and derive two novel sample evaluation metrics for turbulentflows. On this dataset, we show that our generative model captures thedistribution of turbulent flows caused by unseen objects and generateshigh-quality, realistic samples amenable for downstream applications withoutaccess to any initial state.

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation