PhD Studentship on Effective Emulation of Numerical Simulators with Application to Tsunami Modelling

University College London

United Kingdom


Vacancy Information
Applications are invited for a PhD funding opportunity in the UCL Department of Statistical Science, available from September 2019. The studentship will be 3 years in duration and covers tuition fees up to the overseas rate, plus an annual stipend (£17,009 in 2019/20). This funding is provided by the Lloyd's Tercentenary Research Foundation, the Lighthill Risk Network and the Alan Turing Institute.


Studentship Description
Uncertainty Quantification (UQ) techniques help propagate uncertainties from inputs to outputs in complex simulators, such as climate or tsunami computer models that run on supercomputers. Typically UQ makes use of surrogate models - also known as emulators - that are much faster to run than simulators, in order to sample uncertainties efficiently. These are often Gaussian Process (GP) emulators that need to be fitted using a smart design of computer experiments. However, building efficient GPs and making many predictions is still a challenge in many practical settings.

This PhD project includes hardware acceleration of GP fitting and prediction in collaboration with Warwick University and the Research Software Engineering team of the Alan Turing Institute, and is linked to the project: Uncertainty quantification of multi-scale and multi-physics computer models. As part of this PhD project, it will be also possible to explore new extensions of GP surrogate models. The project includes an application to tsunami modelling that will be carried out as part of an international project on Indonesian tsunamis with various experts providing support and data.


Person Specification
The requirement for admission to the MPhil/PhD in Statistical Science is a 1st class or high upper 2nd class Bachelor’s degree, or a Master’s degree with merit or distinction, in Mathematics, Statistics, Computer Science, or a related quantitative discipline. Overseas qualifications of an equivalent standard are also acceptable. Further details can be found on the Departmental website.

The ideal candidate will have both statistical and computational expertise, for instance through a Master degree in Computational Statistics, Data Science or equivalent. Informal enquiries to Professor Serge Guillas are welcome.


All candidates should apply for admission to the Research Degree: Statistical Science (RRDSTASING01) by completing the online form and, in addition (and very importantly), send a separate covering letter making their case for the funding. The covering letter should be sent to Dr Russell Evans at the email address below.

Contact Name: Dr Russell Evans
Contact Details:

In your application, please refer to