Stats4Grads: Bayes Linear Methods for Multiscale Emulation of a Hydrocarbon Reservoir
1 October 2008 14:15 in CM105
This talk concerns uncertainty analysis for a complex physical system based on a computer simulation of that system. In this broad class of problems, we must deal with the same four basic types of uncertainty: input uncertainty, function uncertainty, model discrepancy, and observational error. A general methodology has been developed to deal with this class of problems, and this talk will give an introduction to that methodology and demonstrate how it may be applied to a hydrocarbon reservoir model of realistic size and complexity. We shall therefore analyse a particular problem in reservoir description, based upon our general approach to uncertainty analysis for complex models. In particular, we will highlight the value of fast approximate versions of the computer simulator for making informed prior judgements relating to the form of the full simulator. Our account is based on the use of Bayes linear methodology to simplify the specification and analysis for complex high-dimensional problems.
See the Stats4Grads page for more details about this series.