An emulator or a surrogate is a statistical approximation of a complex numerical model. Emulators are fast to run and include a measure of their own uncertainty. This makes them suitable for a number of applications in climate science. Emulators were originally devised for uncertainty quantification but their application goes far beyond simply estimated the errors on model outputs. I will explain what an emulator is, how it can be calculated and some applications in model prediction, sensitivity analysis and quantifying uncertainty. Current research topics will also be discussed.
This talk was given on 3-20-2015.