Stats4Grads: Fast Linked Analyses for Scenario-based Hierarchies (FLASH)
16 March 2011 14:15 in CM221
When using computer models to provide policy support it is normal to encounter ensembles that test only a handful of feasible or idealized decision scenarios. I will present a new methodology for performing multi-level emulation of a complex model as a function of any decision that makes specific use of a scenario ensemble of opportunity on a fast or early version of a simulator and a small, well chosen, design on our current simulator of interest. The method exploits a geometrical approach to Bayesian inference and is designed to be fast, in order to facilitate detailed diagnostic checking of our emulators by allowing us to carry out many analyses very quickly. Our motivating application involved constructing an emulator for the UK Met Office climate model HadCM3 as a function of CO2 forcing, which was part of a NERC RAPID programme deliverable to the Met Office. Our application involved severe time pressure as well as limited access to runs of HadCM3 and a scenario ensemble of opportunity on a lower resolution version of the model.
See the Stats4Grads page for more details about this series.