Machine Learning for Computational Fluid Dynamics

This course surveys how machine learning can enhance computational fluid dynamics by accelerating simulations, improving turbulence closure models, and developing reduced-order models. It emphasizes incorporating physical knowledge, evaluating computational tradeoffs, and supporting reproducible research.

Syllabus

Intro
ML FOR COMPUTATIONAL FLUID DYNAMICS
Learning data-driven discretizations for partial differential equations
ENHANCEMENT OF SHOCK CAPTURING SCHEMES VIA MACHINE LEARNING
FINITENET: CONVOLUTIONAL LSTM FOR PDES
INCOMPRESSIBILITY & POISSON'S EQUATION
REYNOLDS AVERAGED NAVIER STOKES (RANS)
RANS CLOSURE MODELS
LARGE EDDY SIMULATION (LES)
COORDINATES AND DYNAMICS
SVD/PCA/POD
DEEP AUTOENCODER
CLUSTER REDUCED ORDER MODELING (CROM)
SPARSE TURBULENCE MODELS