Explore data-driven closure modeling for complex dynamical systems in this 51-minute conference talk from the Alan Turing Institute. Delve into the challenges of predicting turbulence and cloud dynamics, and discover how machine learning techniques can improve existing closure models. Learn about the application of derivative-free Kalman methods for learning closure models from indirect and limited data. Examine examples of sparse identification of dynamical systems and the process of learning stochastic closures. Gain insights into cutting-edge approaches for addressing closure problems in complex systems where numerically resolving all degrees of freedom remains infeasible.
Overview
Syllabus
Jinlong Wu - Data-Driven Closure Modeling Using Derivative-free Kalman Methods
Taught by
Alan Turing Institute
Related Courses
-
Data-Driven Closure Modeling Using Derivative-free Kalman Methods
-
Data-Driven Dynamical Systems with Machine Learning
-
Machine Learning for Computational Fluid Dynamics
-
Differentiable Programming for Data-driven Modeling, Optimization, and Control
-
Generative Machine Learning Approaches for Data-Driven Modeling and Reductions of Non-Linear Dynamics
-
Data-Driven Reduced Order Models of Forced Systems Using Invariant Foliations
