Intelligent Portfolio Optimisation for Basin-Wide Offshore Decommissioning: Scheduling, Economics, and Market Coordination

About the Project

The North Sea faces one of the largest industrial decommissioning challenges in history: hundreds of oil and gas installations to be safely removed, repurposed, or abandoned at an estimated cost exceeding £20 billion over the next two decades. At the heart of the problem is a scheduling and resource coordination challenge far more complex than it first appears. Decommissioning projects compete for the same specialist vessels, port facilities, and skilled labour as the rapidly expanding offshore wind sector. Vessels are expensive to mobilise, weather windows are narrow, and current scheduling practice relies largely on bilateral negotiation rather than systematic optimisation. The result is higher costs and longer timelines than necessary.

This PhD will develop AI-driven planning and optimisation methods to address this problem rigorously and at scale. Working across the full UK Continental Shelf (UKCS) project portfolio, you will build computational models of decommissioning, offshore wind, and competing infrastructure projects, and apply scheduling and optimisation algorithms to find strategies that reduce both cost and time across the portfolio. You will model the stochastic uncertainties, including oil prices, weather, and regulatory timelines, that make this a hard real-world problem, and propose concrete commercial arrangements, such as vessel-sharing agreements or coordinated scheduling platforms, that could deliver improvements acceptable to all parties.

By the end of the studentship you will have produced: a basin-wide simulation framework capturing project interactions and shared resource competition; multi-objective optimisation tools that simultaneously balance industry NPV, government cost, and delivery time; commercially grounded coordination proposals for vessel and port scheduling; and direct policy-relevant findings for NSTA, HMRC, and the offshore industry.

Training and Opportunities

You will receive rigorous training in automated planning and scheduling, multi-objective optimisation, and stochastic modelling: a toolkit well suited to large-scale resource allocation problems. The studentship is based primarily at the University of Aberdeen’s National Decommissioning Centre (NDC) where you will work alongside a cohort of PhD students and engage directly with industry partners and regulators. The supervisory team will support you in presenting your work at leading international AI and energy conferences.

Candidate Background

Applicants should hold a first or upper second class honours degree in computer science, mathematics, operations research, engineering, or a closely related discipline with a strong quantitative component. Prior knowledge of the offshore energy industry is not required. What matters is analytical rigour, comfort with formal methods, and a commitment to research that carries tangible societal value.

We actively encourage applications from diverse career paths and backgrounds and across all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status, amongst other protected characteristics.