Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Interpretable and Structure-Preserving Data-Driven Methods for Physical Simulations

DataLearning@ICL via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive presentation on interpretable and structure-preserving data-driven methods for physical simulations. Delivered by Youngsoo Choi from Lawrence Livermore National Laboratory, this 51-minute talk delves into the importance of physical simulations in modern science and examines various data-driven approaches. Learn about conditional generative adversarial networks, the pros and cons of black-box approaches, and methods to achieve interpretability. Discover how Dynamic Mode Decomposition (DMD) accelerates 3D printing process simulations and how time-windowing Wavelet DMD improves accuracy. Investigate other interpretable data-driven methods, including Parameterized Latent Space Dynamics Identification (LaSDI) and its application to radial advection problems. Explore physics-constrained models, projection-based linear subspace reduced order models, and space-time ROM for maximal compression. Gain insights into component-wise ROM for lattice-structure design optimization, PROM for wind turbine blade design optimization, and database local ROMs for multi-start airplane wing optimization. Conclude with an overview of data-driven methods categorized by their level of intrusiveness.

Syllabus

Intro
Awesome reduced order model team and collaborators
Physical simulations play an important role in modern scienc
How does conditional generative adversarial network perform?
Pro and cons of black-box approach
How can we get an interpretability?
DMD accelerates 3D printing process simulation
Time-windowing Wavelet DMD improves accuracy
Are there other data-driven interpretable methods?
Parameterized latent space dynamics identification (LaSDI)
Performance of LaSDI to radial advection problem
gLaSDI: physics-informed greedy latent space dynamics identificat
How about physics-constrained model?
Projection-based linear subspace reduced order model
Space-time ROM achieves the maximal compression
Component-wise ROM accelerates lattice-structure design optir
PROM accelerates wind turbine blade design optimization
Database local ROMs accelerate multi-start airplane wing optin
Category of data-driven methods via level of intrusiveness

Taught by

DataLearning@ICL

Reviews

Start your review of Interpretable and Structure-Preserving Data-Driven Methods for Physical Simulations

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.