BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Uncertainty quantification for complex simulators using emulation 
 - Dr Richard Wilkinson\, The University of Sheffield
DTSTART:20161025T120000Z
DTEND:20161025T130000Z
UID:TALK68209@talks.cam.ac.uk
CONTACT:Max Holloway
DESCRIPTION:Many climate models are complex and expensive\, making it diff
 icult to use them in any statistical analysis. For example\, standard meth
 ods for estimating unknown parameters\, doing sensitivity analysis\, or qu
 antifying prediction uncertainty\, all require the simulator to be run ten
 s of thousands of times. Emulation (also known as surrogate modelling) is 
 the approach of building a cheaper statistical version of your simulator\,
  which approximates its behaviour\, but at a fraction of the cost.\n\nIn t
 his talk I will introduce Gaussian process emulators\, and discuss some re
 cent extensions\, particularly in examples with high dimensional inputs an
 d outputs. I will illustrate the approach by discussing recent work on emu
 lating subsurface flow models\, as well as highlighting recent work by oth
 ers in using emulators to train ice sheet models\, and to calibrate the NE
 MO ocean model.
LOCATION:British Antarctic Survey\, Room 307
END:VEVENT
END:VCALENDAR