We are seeking a full-time Research Assistant in Intelligent Pile Driveability Forecasting to join the Civil Engineering research group at the Department of Engineering Science (central Oxford). This project is a collaboration with Dr Róisín Buckley (University of Glasgow) and Dr Stephen Suryasentana (University of Strathclyde). The post is funded by the Supergen Offshore Renewable Energy Hub and is fixed-term for 11 months, starting from 1 June 2021 or as soon as possible thereafter.
Prediction of monopile installation behaviour has been shown to be uncertain using currently available empirical methods used in industry; given the large-scale nature of next-generation offshore wind farms, considerable savings can be realised if a more optimal, automated and adaptive approach to driveability prediction is adopted. The aim of this project is to achieve a step-change improvement in the reliability of monopile driveability predictions towards reducing uncertainty and capital costs. The successful candidate will develop an intelligent framework to autonomously optimise pile driveability predictions using Bayesian machine learning fused with conventional wave equation analysis.
We are seeking candidates with a good first or 2.1 degree in engineering, statistics, physical sciences or computer science and have previous machine learning or Bayesian analysis experience. Applicants with relevant machine learning skills but whose previous work has been outside of engineering are also encouraged to apply.
Informal enquiries may be addressed to firstname.lastname@example.org.
Applications must be received before midday on 25th June 2021 You will be required to upload a covering letter/supporting statement describing how past experience and future plans fit with the advertised position, a detailed CV and the contact details of two referees as part of your online application.
The Department holds an Athena Swan Bronze award, highlighting its commitment to promoting women in Science, Engineering and Technology.
intelligent, artificial intelligence, monopile, installation