Explore the concept of Known Boundary Emulation for complex computer models in this 26-minute talk by Ian Vernon from Cambridge University. Delve into uncertainty quantification techniques and the use of Gaussian Process emulators to approximate computationally expensive codes. Learn about covariance updates, efficient methods, and the application of parallel boundaries in model updating. Discover how these techniques can be applied to real-world challenges such as climate modeling, tsunami prediction, and earthquake analysis. Gain insights into the theoretical and numerical aspects of GP emulation, with a focus on handling 'large' features in complex physical and numerical models.
Known Boundary Emulation of Complex Computer Models - Ian Vernon, Cambridge
Alan Turing Institute via YouTube
Overview
Syllabus
Introduction
Models
Covariance Update
More Efficient Methods
True Function
Two Boundaries
In Action
Parallel Boundaries
Two Parallel Boundaries
Updating the Model
Applications
Rate Models
Taught by
Alan Turing Institute
Related Courses
-
Efficient and Effective Calibration of Spatio-Temporal Models - Dan Williamson & James Salter, Exeter
-
High-Dimensional Hierarchical Models for Large-Scale Geophysical Applications
-
Some Thoughts on Gaussian Processes for Emulation of Deterministic Computer Models
-
Deep and Multi-Fidelity Learning with Gaussian Processes
-
Deep Gaussian Processes for Bayesian Inversion - Matt Dunlop, Courant
-
Sequential Design Based on Mutual Information for Computer Experiments - Joakim Beck, KAUST
