Uncertainty quantification and calibration for complex models

Prof Jeremy Oakley (University of Sheffield)

Frank Adams 2,

I will first give a short overview of the field of Uncertainty Quantification: a variety of problems related to uncertainty in mathematical or 'computer' models of physical systems. I will then present some recent work on calibration: finding model inputs such that the model outputs fit physical observations. Case studies will be given involving computationally expensive models, where we can only afford to evaluate the model at a relatively small number of input values. Methods will include both likelihood-based approaches and ''history-matching'', which aims to simplify the problem by first identifying and excluding "implausible" regions of input space.

Import this event to your Outlook calendar
▲ Up to the top