Overview
This course covers the application of Machine Learning in Fluid Mechanics, highlighting how ML techniques are utilized in this field. The learning outcomes include understanding the history of Machine Learning, exploring techniques such as orthogonal decomposition and autoencoders, and applying ML in areas like flow control and turbulent energy cascade modeling. The course teaches skills in pattern recognition, low-dimensional pattern analysis, and building reduced order models. The teaching method involves presenting theoretical concepts and practical applications in a concise video format. The intended audience for this course includes students, researchers, and professionals interested in the intersection of Machine Learning and Fluid Mechanics.
Syllabus
Introduction
What is Machine Learning
Machine Learning is not Magic
History of Machine Learning
AI Winter
Patterns
orthogonal decomposition
lowdimensional patterns
boundary layer simulations
turbulent energy cascade
closure modeling
superresolution
autoencoders
reduced order models
flow control
inspiration from biology
Taught by
Steve Brunton