Data-Driven Digital Twins for Predicting Climate-Driven Deterioration in UK Bridges

Bridges in the UK are facing increasing challenges due to aging infrastructure and changing environmental and climate conditions. Rising temperatures, increased rainfall, flooding, and more frequent extreme weather events are expected to accelerate deterioration processes and place additional pressure on bridge asset management systems. At the same time, large volumes of inspection and condition data are routinely collected but are not fully exploited for long-term prediction and decision support.

This PhD project focuses on the development of data-driven digital twin approaches to improve the prediction of climate-driven deterioration in UK bridges. The research will explore how historical bridge inspection records, condition ratings, maintenance data, and environmental or climate exposure information can be integrated to support more reliable condition forecasting. The work will investigate data-driven and hybrid modelling approaches that combine engineering understanding with machine learning techniques, while also considering uncertainty and data limitations.

The project will be jointly supervised by Dr Yavuz Yardim (University of Edinburgh) and Dr Demetris Cotsovos  (Heriot-Watt University), leading to a joint PhD degree from the University of Edinburgh and Heriot-Watt University. The candidate will benefit from access to expertise and facilities across both institutions and will work on research questions that are directly relevant to real-world bridge engineering and infrastructure management practice. 

There may also be opportunities to engage with industry partners and real infrastructure datasets.

The exact research direction will be refined with the successful candidate, depending on their background and interests.

Candidate Profile: We seek a highly motivated individual with: 

- A 2:1 undergraduate degree (or equivalent) in civil engineering, structural engineering, data science, computer science, or a closely related discipline.
- Strong programming and data analysis skills (e.g. Python).
- Demonstrated experience in machine learning or data-driven modelling.
- An interest in bridges, infrastructure systems, and climate-related deterioration.
- The ability to work independently and as part of a multidisciplinary research team.
 

Applications are welcomed from self-funded students, or students who are applying for scholarships from the University of Edinburgh or elsewhere

Further information and other funding options.

Tuition fees + stipend are available for applicants who qualify as Home applicants.

Tuition fees + stipend are available for applicants who qualify as Home applicants (International students can  apply, but the funding only covers the Home fee rate)

Funding Details:

Duration: 42 months (3.5 years)

Start date: Flexible, but no later than July 2027

Stipend: Enhanced above UKRI standard rate

Research & Training Grant: £5,000 (UoE) or £3,500 (HWU)