Modeling
Data-driven models for unsteady fluid flows
Intermediate Level*
Lectures by Aditya Nair. Dive into the fascinating world of fluid dynamics and learn how data-driven modeling techniques are revolutionizing the study and prediction of unsteady fluid flows. This playlist comprises five in-depth videos, each focusing on different aspects and methodologies of data-driven modeling in fluid dynamics.
*This playlist is designed for students, researchers, and professionals looking to understand the applications of data-driven techniques in fluid dynamics. Whether you are new to fluid dynamics or looking to deepen your understanding and skills, this series will provide you with the tools and knowledge necessary to analyze and model unsteady fluid flows using data-driven methodologies.
Lectures by Aditya Nair. Dive into the fascinating world of fluid dynamics and learn how data-driven modeling techniques are revolutionizing the study and prediction of unsteady fluid flows. This playlist comprises five in-depth videos, each focusing on different aspects and methodologies of data-driven modeling in fluid dynamics.
*This playlist is designed for students, researchers, and professionals looking to understand the applications of data-driven techniques in fluid dynamics. Whether you are new to fluid dynamics or looking to deepen your understanding and skills, this series will provide you with the tools and knowledge necessary to analyze and model unsteady fluid flows using data-driven methodologies.
Physics informed machine learning
Intermediate Level
Lectures by Steve Brunton. This playlist involves improving machine learning by embedding partially known physics and also discovering new physics with machine learning. We put a premium on machine learning models that are more interpretable and generalizable by promoting low-dimensional and sparse models. There are many ways to incorporate known physics, such as symmetries, conservation laws, and invariances.
Lectures by Steve Brunton. This playlist involves improving machine learning by embedding partially known physics and also discovering new physics with machine learning. We put a premium on machine learning models that are more interpretable and generalizable by promoting low-dimensional and sparse models. There are many ways to incorporate known physics, such as symmetries, conservation laws, and invariances.
