Uncertainty quantification and propagation through complex chains of computational models
A PhD scholarship on the interface of Statistics and Computational Modelling, fully funded at UK/EU level, is available for suitably qualified students at the University of Southampton as part of the Centre for Doctoral Training in Next Generational Computational Modelling (http://www.ngcm.soton.ac.uk). The project is supervised by Professor David Woods (Southampton) and Dr Veronica Bowman (Defence Science and Technology Laboratory).
This project will explore how predictions can be made, and assessed, through complex chains of computer models. For example, consider predicting casualties from the release of a biological or chemical agent. Modelling such outcomes requires linking predictions of meteorology, atmospheric dispersion, sensor properties and dose response. Each model will be subject to uncertainties including uncertain inputs, uncertain tuning parameters, and uncertain physical mechanisms. Understanding the reliability and accuracy of the overall predictions of casualties requires understanding how the uncertainties from the individual models will propagate and combine.
Naively, simulation studies could be used to understand the uncertainty in predictions. However, typically the models will be too computationally expensive for such studies to be feasible. Furthermore, such studies would ignore some sources of error, such as model inaccuracies. In addition, there is a need to combine the model outputs with any available real data, at any of the stages of the model chain, to help calibrate and validate the predictions. This project will develop the necessary methodology for (i) construction of accurate statistical emulators, or surrogates, of chains of models to reduce computational cost; (ii) data fusion from a variety of models and data sources of different fidelities; and (iii) the necessary algorithms to allow computationally feasible Bayesian inference for multi-model chains.
The research will be motivated by, and demonstrated on, multi-model chains from Dstl which are used for hazard response, hazard management and government procurement programmes. The research will therefore have a clear and tangible application to real world problems.
The University of Southampton's £10 million Centre for Doctoral Training in Next Generation Computational Modelling was launched in November 2013 and is jointly funded by EPSRC, the University of Southampton, and its partners. The NGCM brings together world-class simulation modelling research activities from across the University of Southampton and hosts a 4-year doctoral training programme that is the first of its kind in the UK.
If you wish to discuss any details of the project informally, please contact Professor David Woods, Southampton Statistical Sciences Research Institute, Email: [log in to unmask], Tel: +44 (0) 2380 595117.
Details of how to apply are available at http://www.ngcm.soton.ac.uk/apply.html
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|