Postgraduate research project

Physics informed machine learning approach for integration of geotechnical and geophysical data to define centimetre-scale design parameters across kilometre-scale offshore wind farms

Funding
Fully funded (UK only)
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Environmental and Life Sciences
Closing date

About the project

Geoscience plays a pivotal role in delivering offshore wind power. Optimizing characterization of the seabed over the necessary areas requires novel techniques to define engineering properties at the scale and accuracy required. This project will integrate geophysics and geotechnics to correlate geotechnical engineering properties to geophysical parameters.

Offshore wind is a key strategic component for UK’s energy security and for decarbonisation of energy [1]. In April 2022, the British Energy Security Strategy [2] stated the ambitious goal of increasing offshore wind capacity from the current 15 GW to 50 GW by 2030. Currently, it takes about 5-10 years for an offshore wind farm to become operational. Six months saving from this time in a UK offshore wind farm by optimizing the ground investigation process, could reduce 2.2 million tonnes of CO2 equivalent in emissions for every 1 GW of wind farm capacity delivered.
 

All wind turbine foundation and anchor designs require geotechnical parameters as input, which are currently acquired through offshore geotechnical site investigation with discrete and intrusive in-situ testing and sampling for later laboratory testing. Current methods have evolved from the offshore hydrocarbons industry and are not fit for purpose to characterise the much larger areas required for offshore wind. Acceleration of offshore wind deployment requires smarter seabed characterization approaches that can bring cost-reduction and minimise environmental impact [1]. 

The objective is to develop a physics-informed machine-learning approach to correlate geophysical and geotechnical parameters at centimetric scale across kilometre-scale offshore wind farms. Such a method will both inform requirements of geophysical surveys and enable extraction of geotechnical parameters for engineering design from geophysical data. Ultimately the method will reduce the amount of geotechnical investigation required, and enable flexibility of windfarm layout post survey, in both cases reducing costs, increasing reliability and accelerating offshore wind deployment.

Training

All doctoral candidates will enrol in the Graduate School of NOCS (GSNOCS), where they will receive specialist training in oral and written presentation skills, have the opportunity to participate in teaching activities, and have access to a full range of research and generic training opportunities. GSNOCS attracts students from all over the world and from all science and engineering backgrounds. There are currently around 200 full and part-time PhD students enrolled (~60% UK and 40% EU & overseas). Specific training will include: offshore geotechnical data interpretation and analysis, machine learning, numerical modelling of large deformation problems, micro finite element analysis, and seismic wave propagation in porous media. The student will get further training through the ORE Supergen Impact Hub network, of which the University of Southampton (UoS) is a leader, that includes research webinars and workshops and from participating in the Society of Underwater Technology training course in offshore geophysics and geotechnics that the UoS hosts annually for 50 industry attendees. The student will also benefit from cross-university activities and opportunities through the Southampton Marine and Maritime Institute and will join the Centre of Excellence for Intelligent & Resilient Ocean Engineering.

[1] Greaves D., et al. (2022), UK perspective research landscape for offshore renewable energy and its role in delivering Net Zero, Progress in Energy, doi:10.1088/2516-1083/ac8c19 
[2] BESS (2022), British energy security strategy,