CEE Seminar - Generative AI for the statistical computation of fluids

In recent years, there has been growing interest in applying neural networks to the data-driven approximation of partial differential equations (PDEs). In this talk, we present GenCFD, a generative AI algorithm for fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. On a set of challenging fluid flows, GenCFD provides an accurate approximation of relevant statistical quantities of interest while also efficiently generating high-quality realistic samples of turbulent fluid flows. This stands in stark contrast to ensemble forecasts from deterministic machine learning models, which are observed to fail on these challenging tasks. This talk will also highlight theoretical results that reveal the surprising mechanisms by which generative diffusion models like GenCFD succeed in capturing key physical properties where deterministic ML approaches fall short.