Efficient and Effective Calibration of Spatio-Temporal Models - Dan Williamson & James Salter, Exeter
Alan Turing Institute via YouTube
Overview
Explore efficient and effective calibration techniques for spatio-temporal models in this 24-minute conference talk by Dan Williamson and James Salter from the University of Exeter. Delve into the world of Uncertainty Quantification (UQ) and its application in understanding complex physical systems and decision-making under uncertainty. Learn about Gaussian Process (GP) emulators as cost-effective alternatives to computationally expensive numerical models. Gain insights into the theoretical and numerical aspects of GP emulation, with a focus on real-world applications featuring 'large' characteristics such as complex physical and numerical models or numerous observations and parameters. Discover how these techniques are applied to global challenges like climate modeling, tsunami prediction, and earthquake analysis in this presentation from the Alan Turing Institute workshop on GP emulation.
Syllabus
Efficient an effective calibration of spatio-temporal models: Dan Williamson & James Salter, Exeter
Taught by
Alan Turing Institute