This course covers machine learning applications in fluid dynamics, including turbulence modeling and control. Students will learn about Reynolds Averaged Navier-Stokes equations, turbulence closure models, deep learning techniques, and data-driven modeling of fluid flows. The teaching method includes lectures and practical applications. This course is designed for individuals interested in applying machine learning to fluid mechanics and turbulence analysis.
Overview
Syllabus
Machine Learning for Fluid Mechanics.
Machine Learning for Fluid Dynamics: Patterns.
Machine Learning for Fluid Dynamics: Models and Control.
What Is Turbulence? Turbulent Fluid Dynamics are Everywhere.
Turbulence is Everywhere! Examples of Turbulence and Canonical Flows.
Turbulence: Reynolds Averaged Navier-Stokes (Part 1, Mass Continuity Equation).
Turbulence: Reynolds Averaged Navier Stokes (RANS) Equations (Part 2, Momentum Equation).
Turbulence Closure Models: Reynolds Averaged Navier Stokes (RANS) & Large Eddy Simulations (LES).
Deep Learning for Turbulence Closure Modeling.
Deep Reinforcement Learning for Fluid Dynamics and Control.
Robust Principal Component Analysis (RPCA).
Robust Modal Decompositions for Fluid Flows.
Data-driven nonlinear aeroelastic models of morphing wings for control.
Data-driven Modeling of Traveling Waves.
Finite-Horizon, Energy-Optimal Trajectories in Unsteady Flows.
Modeling synchronization in turbulent flows.
Data-Driven Resolvent Analysis.
Taught by
Steve Brunton
