SmartPipe: AI-Enabled Digital Twins and Distributed Fibre Optic Sensing for Multi-Hazard Risk Management of Water Networks

About the Project

UK water utilities face a dual challenge: aging infrastructure and a regulatory mandate to slash leakage by 17% by 2030. This project, SmartPipe, develops a "digital nervous system" for buried water networks using Distributed Fibre Optic Sensing and AI-enabled Digital Twins. By detecting "silent" failures - like slow leaks or soil erosion - before they become catastrophic bursts, we can prevent supply disruptions like the 2025 Tunbridge Wells crisis. Working with industry leaders, the researcher will create tools that ensure water networks are not only resilient to climate change but are managed equitably to protect all communities.

Leveraging Distributed Fibre Optic Sensing (DFOS), this project transforms pipelines into "smart assets" capable of real-time strain and temperature sensing. By integrating this "big data" with Artificial Intelligence and Digital Twins, we can move beyond reactive repairs. Furthermore, following frameworks for equitable infrastructure planning, this project will explore how digital oversight can prioritize resilience in vulnerable or underserved service areas, ensuring that the £104 billion investment cycle delivers social equity alongside technical reliability.

Research questions

• How can DFOS signatures be interpreted and decoupled to distinguish between ambient operational noise and early-stage pipeline distress (e.g. leakage-induced soil erosion or joint deformation)?
• How can physics-informed machine learning integrate soil–pipeline interaction and hydro-mechanical processes to quantify pipeline condition and Remaining Useful Life (RUL) under multi-hazard loading?
• How can a Digital Twin framework fuse real-time sensing data with environmental and operational data to enable scalable, automated early-warning systems for water networks?

The project will be supported by industry partners including WSP and Mott MacDonald, both of whom have extensive experience in water infrastructure, asset management, and digital engineering.

The i-Risk Doctoral Focal Award

i-Risk PhD research offers a unique opportunity to contribute to the generation of new knowledge in the forefront of informatics. i-Risk cohorts will advance understanding and deliver innovative tools and solutions for multi-hazard systemic risk resilience and sustainability practice. Doctoral Researchers will undertake a structured training programme and partner co-created interdisciplinary research projects.

Our Vision

The vision of i-Risk is to train the next generation of research practitioners and leaders who will be at the forefront of collaborative research and:

1. Integrate informatics with understanding of evolving risk throughout the environment
2. Collaborate with a broad range of partners from industry, government agencies, global organisations (e.g., the United Nations) and Non-Government Organisations to ensure research directly informs policy and practice, delivering widespread impact.

Eligibility

Applicants should have, or expect to achieve, an excellent academic record (UK First-class or 2.1 honours or international equivalent depending on the funding source) in Engineering, Earth Sciences, Computing or another related physical science discipline (MSc, MSci or BSc).

The project is inherently interdisciplinary, spanning geotechnical engineering, sensing technologies, and data science. While the i-Risk programme will provide strong training in digital informatics and transferable skills, the following prior competencies would be highly beneficial:

• Strong quantitative background: A solid foundation in mathematics, mechanics, or engineering science is essential to engage with soil-structure interaction modelling and physics-informed machine learning approaches.
• Programming skills: Prior experience in Python (or similar) is required for data processing, machine learning implementation, and integration within digital twin frameworks.
• Fundamentals of data analysis / machine learning: Familiarity with basic statistical analysis and machine learning concepts (e.g. regression, classification, time-series analysis) will enable the student to effectively develop and interpret AI models.
• Basic understanding of engineering systems: Background knowledge in civil, environmental, or mechanical engineering, particularly in infrastructure systems or geotechnics, would be advantageous for understanding pipeline behaviour and failure mechanisms.
• Willingness to work across disciplines: The project requires the ability to integrate experimental data, physical modelling, and computational methods, and to engage with both academic and industry stakeholders.

How to apply

You will need to submit an online application through our website here: https://uom.link/pgr-apply

Please quote the advert reference IRISK-26-UOM01 in your application. This PhD is being advertised as part of the Informatics for Multi-hazard Risk and Resilience (i-Risk) NERC Doctoral Focal Awards (DFA) in the Environmental Sciences.

Further details about i-Risk can be seen on their website https://github.com/i-risk-dfa.

Please note that your application will be assessed upon:

• Motivation and Career Aspirations
• Potential & Intellectual Excellence
• Suitability for specific project
• Fit to i-Risk

Please familiarise yourselves with i-Risk before applying. During the application process candidates will need to upload:

• A two-page personal statement split into two sections:
  • one page dedicated to your research interests in informatics and disaster risk reduction, the i-Risk DFA and your rationale for your choice of project
  • one page dedicated to answering the following questions:
1. Tell us about a time when you identified a new approach to a problem. What was your decision-making process? (~150 words)
2. Tell us about a time where you have performed data analytics. What was the task? What made it difficult? How did you handle it? (~150 words)
3. Tell us about a goal have you set for yourself that you have successfully achieved. How did you stay motivated? (~150 words)
4. Describe a situation where you demonstrated that you can constructively handle setbacks. How did you troubleshoot the problem? (~150 words)
• A curriculum vitae giving details of your academic record and stating your research interests
• Academic transcripts and degree certificates (translated if not in English)
• You will be asked to supply contact details for two referees on the application form (please make sure that the contact email you provide is an official university/ work email address as we may need to verify the reference)
• English Language certificate (if applicable)

You are encouraged to contact potential supervisors by email to discuss project specific aspects of the proposed project prior to submitting your application. If you have any general questions please contact irisk@mailbox.lboro.ac.uk. If you have any technical questions about making an application, please contact our admissions team by emailing FSE.doctoralacademy.admissions@manchester.ac.uk.

Please note that interviews are anticipated to be held remotely via Microsoft Teams week commencing 29June 2026.

Funding Notes

This 3.5-year PhD studentship is funded by the NERC i-Risk DFA and is open to Home (UK) and overseas students. The successful candidate will receive an annual tax-free stipend set at the UKRI rate (£21,805 for 2026/27; subject to annual uplift), and tuition fees will be paid. We expect the stipend to increase each year. The start date is October 2026.

We recommend that you apply early as the advert may be removed before the deadline.