Sparse Nonlinear Models for Fluid Dynamics with Machine Learning and Optimization

This course focuses on developing reduced-order models for fluid flows using the sparse identification of nonlinear dynamics (SINDy) algorithm. The learning outcomes include understanding SINDy, discovering partial differential equations, utilizing deep autoencoder coordinates, and modeling fluid flows with Galerkin regression. The course covers applications in various complex flow fields such as thermo syphon, electroconvection, and magnetohydrodynamics. The teaching method involves lectures on machine learning techniques and their application to fluid dynamics. This course is intended for individuals interested in fluid dynamics, machine learning, optimization, and engineering systems involving working fluids.