Efficient an effective calibration of spatio-temporal models: Dan Williamson & James Salter, Exeter

Uncertainty quantification (UQ) employs theoretical, numerical and computational tools to characterise uncertainty. It is increasingly becoming a relevant tool to gain a better understanding of physical systems and to make better decisions under uncertainty. Realistic physical systems are usually described by numerical models, often simulated using computer code. The computationally expensive and complex codes can be replaced by inexpensive and functionally simple Gaussian Process (GP) emulators that approximate the functional relationships essential for the purposes of UQ.

This workshop brings together early-career researchers and experts in the field, exploring the theoretical as well as the numerical aspects of GP emulation. Real applications are emphasised, especially those having 'large' features. 'Large' features could include complex physical and numerical models and/or a large number of observations or parameters. Specifically, climate, tsunami and earthquake problems are targeted due to their relevance as global challenges.

numerical tools,theoretical tools,machine learning,big data,computer science,GP emulation,UQ,artificial intelligence,Real applications,tsunami,global challenges,James Salter,complex codes,Uncertainty quantification,numerical models,turing,climate,data ethics,the alan turing institute,Dan Williamson,computational tools,computer code,Gaussian Process emulators,Realistic physical systems,data science,earthquake,