Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Enhancing Coastal Resilience: A Digital Twin Approach to Contrastive Graph Generative Models for Coastal Protection


This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Shagufta Henna, Dr Salem Gharbia, Dr Stephen Seawright  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

This PhD project is part of the Postgraduate Research Training Programme COASTAL CONNECTIVITY, which offers 12 PhD research scholarships to commence in 2024. Each project will include an enterprise placement of minimum 12 weeks duration and a bespoke training package in coastal management and research skills.

Project title (COASTCON09): Enhancing Coastal Resilience: A Digital Twin Approach to Contrastive Graph Generative Models for Coastal Protection

Earth's rising sea levels and the increased occurrence of severe storms, attributed to climate change caused by human activities, pose a significant threat to the sustainability of life. These changes have serious impacts on coastal regions, such as coastal erosion and flooding. Existing methods for coastal protection, including empirical models, simplify complex processes by learning parameterizations through data fitting. These models are widely employed in modelling dune erosion, demonstrating comparable performance to numerical methods with better computational efficiency. However, these models are constrained to specific physical features, such as dunes/shorelines, thereby overlooking sediment dynamics, other contributors, and their interactions with coastal erosion.

To address the limitations associated with empirical models, this project proposes a modelling framework integrated with Digital Twins. Digital Twins aim to provide a virtual representation of the coastal environment, incorporating real-time/simulated data and dynamic factors. By embracing Digital Twins, the project seeks to enhance prediction accuracy and consider various elements influencing coastal erosion, extending beyond sediment dynamics. This understanding will be further leveraged to design graph generative models based on contrastively learned representations, which are expected to perform effectively in downstream tasks. Ultimately, this approach will facilitate the development of predictive mitigation strategies for effective coastal protection.

Objectives of the research project

  1. Utilize Digital Twins to create a comprehensive virtual representation of the coastal environment, integrating real-time or simulated data and dynamic factors for improved predictive accuracy of coastal erosion.
  2. Develop an approach to contrastively learn feature representations with the assistance of Digital Twins, considering the complex interactions of various elements contributing to coastal erosion.
  3. Design advanced deep graph generative models based on contrastively learned representations, to enhance performance in downstream tasks related to coastal protection predictions.
  4. Leverage the graph generative models and Digital Twins to devise and plan various mitigation strategies for coastal protection.

A minimum of 2.1 honours degree (Level 8) in a relevant discipline.

Project Duration:

48 months (PhD)

Preferred Location:

ATU Donegal, Letterkenny Campus


Application Form / Terms of Conditions can be obtained on the website:

The closing date for receipt of applications is 5pm, (GMT) Monday 29th April, 2024.

Only selected applicants will be called for an online interview (shortlisting may apply).

Environmental Sciences (13)

Funding Notes

TU RISE is co-financed by the Government of Ireland and the European Union through the ERDF Southern, Eastern & Midland Regional Programme 2021- 27 and the Northern & Western Regional Programme 2021-27.
Funding for this Project includes:
• A student stipend (usually tax-exempt) valued at €22,000 per annum
• Annual waivers of postgraduate tuition fee
• Extensive research training programme
• Support for travel, consumables and dissemination expenses


Essential Qualifications and Skills: Minimum 2.1 honours degree in Computer Science, Engineering, IT, Mathematics or related field.

Desired skills: Proficiency in Python, or any other programming languages, Background in AI, machine learning, or computer vision, strong analytical skills with knowledge of statistical analysis, excellent written and verbal communication skills, ability to work independently and in multidisciplinary teams.