Interpretable and Generalizable Machine Learning for Fluid Dynamics - Steven Brunton
Offered By: Kavli Institute for Theoretical Physics via YouTube
Course Description
Overview
Explore interpretable and generalizable machine learning techniques for fluid dynamics in this conference talk from the Machine Learning for Climate KITP conference. Delve into the challenges of informing society about future climate changes at regional and local scales, and discover how big data and machine learning algorithms can provide unprecedented insights into climate systems. Examine the potential for descriptive inference to enable climate scientists to ask causal questions and validate theories. Learn about the integration of machine learning with modeling experiments and model parameterizations to address complex climate-related questions. Gain insights into sparse identification of nonlinear dynamics, joint loss functions, and the incorporation of physical constraints in machine learning models for fluid dynamics applications.
Syllabus
Introduction
Review Paper
Machine Learning for Fluid Dynamics
Patterns in Data
Example
Machine Learning Philosophy
Sparse Identification of Nonlinear Dynamics
Joint Loss
Constraints
Taught by
Kavli Institute for Theoretical Physics
Related Courses
From Climate Science to ActionOnline Learning Campus - World Bank Group via Coursera Climate Change in Four Dimensions
University of California, San Diego via Coursera Our Earth: Its Climate, History, and Processes
University of Manchester via Coursera Monitoring Climate from Space
European Space Agency via FutureLearn Climate Change: The Science
The University of British Columbia via edX