Industry-linked PhD Studentship - ground modelling of offshore windfarms (University of Strathclyde, Glasgow)

Developing novel ways to integrate geophysical and geotechnical data for automated ground modelling of offshore wind farms:


Sponsored by Energy Technology Partnership (ETP), Ørsted and University of Strathclyde, this joint university/industry PhD offers an exciting opportunity to undertake research on novel statistical and Bayesian machine learning methods for ground modelling, supported by a multi-disciplinary team of academics from two institutions (University of Strathclyde and University of Glasgow) and industry supervision from a world-leading offshore wind developer (Ørsted).

The research is aimed at advancing the state-of-the-art in automated ground modelling of offshore wind farms. There are many sources of information which are collected to characterise the ground of an offshore wind farm site (e.g. geophysical and geotechnical data). This project seeks to develop a rigorous, statistical framework to automatically combine these information to improve the quality of the ground model for an offshore wind farm site. This will be achieved using statistical and Bayesian machine learning techniques, including conditional autoregressive (CAR) and multi-output Gaussian process (GP) models.

In addition, the project will develop novel algorithms that use the integrated ground model to optimise the planning of new site investigation (SI) to collect more information to improve the quality and reduce the uncertainty of the ground model. As ground modelling and SI planning are important components of most building and construction projects, the skills acquired in this project will be in demand across a broad range of industries such as offshore wind, oil and gas, tunnelling etc. Furthermore, the advanced data science skills acquired in this project is highly valued and will be in demand across most industries.

This project will be suitable for a candidate who wishes to conduct applied research that makes an immediate impact in the real world, and has a strong interest in statistics and Bayesian machine learning.

Project Details:

The successful candidate will be based primarily at the Department of Civil and Environmental Engineering, University of Strathclyde. The candidate will be jointly supervised by Dr Stephen Suryasentana and Prof Zoe Shipton (Department of Civil and Environmental Engineering, University of Strathclyde), Dr Craig Anderson (School of Mathematics and Statistics, University of Glasgow) and Prof John Quigley (Department of Management Science, University of Strathclyde). Furthermore, the candidate will work closely with the industry sponsor (Ørsted), who is the world's largest developer of offshore wind power. The candidate will receive guidance from Ørsted’s technical specialists and gain significant experience in how ground modelling is carried out in the offshore wind industry. The unique combination of academic and industry contacts will be highly beneficial to the candidate’s learning and career development, and future employability.

There will also be opportunities to present at conferences in both the UK (e.g. the annual ETP conference) and internationally (e.g. Ørsted internal workshops at Copenhagen). There may also be opportunities for local/international collaborations and to spend a period at University of Oxford or abroad in the Data Science & Artificial Intelligence Research Centre at Nanyang Technological University (DSAIR@NTU) – Singapore.

This project will commence in 30 Mar 2021. The successful UK/EU candidate will receive a fully-funded scholarship for 3.5 years, which covers all university tuition fees and an annual stipend of £15,285 (tax-free) for the entire 3.5 years duration. Besides UK and EU candidates, international candidates of any other nationality are also welcome to apply, but they would need to find other funding sources to cover the university tuition fee difference between the Home rate (£4,407 per annum) and the International rate (£20,900 per annum).

We would expect the candidate to have a First Class or Upper Second Class Honours degree in a relevant area of mathematical sciences (e.g. Statistics, Mathematics, Machine Learning, Computer Science, Engineering, Geostatistics, Data Science, Geophysics, Physics), and to have some experience of programming in Python and/or R. Previous experience with Bayesian statistics, Gaussian processes and geophysical data would be an advantage.

How to apply:

Please send your application (and any informal inquiries) to This email address is being protected from spambots. You need JavaScript enabled to view it. by 5pm on Sunday 10 Jan 2021. Your application should include the following:

* A cover letter of at most two pages explaining why you are interested in the project and what skills and ideas you believe you would contribute to the project
* An up to date curriculum vitae (CV)
* Evidence of a first class or upper second class honours degree or a Masters degree (or equivalent) in subjects relevant to statistics, computer science, machine learning, engineering, geostatistics, geophysics, physics or mathematics.
Interviews will be carried out on a rolling basis, until the position is filled.