Description

Many problems in science and technology, involving understanding, forecasting and control of physical systems, are addressed by the analysis of computer simulators for the systems. For example climate simulators are used to analyse climate.

All such applications raise many interesting and imporant problems in uncertainty analysis for the physical systems that are being modelled. For example, we need to make appropriate choices for model parameters which are typically unknown, we need to match the model's performance to data that is measured with error, there are structural discrepancies between model and system and the model may be extremely time consuming to evaluate at any choice of input parameters. A technology has been developed using Bayesian statistical analysis for addressing all of these problems. It is widely applicable across an enormous range of scientific and technological areas of application. The supervisors of this project have applied this methodology to climate models, galaxy formation simulations, oil reservoirs, models of systems biology, HIV models, energy investment models and natural hazard models.

This project will introduce and explore these ideas in the context of a systems biology model. These models represent the behaviour of genetic and metabolic networks that govern important plant functions. We will take a pre-existing state-of-the-art model which has been built to run in the statistical program R, and we will develop various aspects of uncertainty quantification for this biological system based on the general technology described above.

Prerequisites

Resources

For an introduction to these techniques as applied to a complex model of Galaxy Formation see our paper entitled "Galaxy Formation: Bayesian History Matching for the Observable Universe" which can be found at Statistical Science Volume 29, No 1.

An excellent web-site which describes (in sometimes overwhelming detail!) the types of analyses which this project gives an introduction to is:

The MUCM Web-site

This is the web-site for the Managing Uncertainty in Complex Models (MUCM) project, a consortium in which we were involved, (with the Universities of Sheffield, Aston, LSE and Southampton). There are an enormous number of links to follow at this site.