A new fully funded four-year (1+3 MRes/PhD) studentship is now available through the Cambridge EPSRC Centre for Doctoral Training in Future Infrastructure and Built Environment: Unlocking Net Zero (FIBE3 CDT). The project is delivered in collaboration with Ward & Burke, a leading engineering firm specialising in the end-to-end delivery of water and wastewater infrastructure across Ireland and the UK. This is an opportunity to work at the frontier of infrastructure engineering + AI + sustainability, tackling a real-world problem with direct industry impact.
Author: Dr Niaz Chowdhury (LinkedIn)
Designation: Lecturer (Computer Science)
Affiliation: Ulster University, Birmingham, UK
Why this research matters
Combined storm overflows (often linked to combined sewer overflows) are a growing challenge across the UK and beyond. As rainfall patterns intensify and infrastructure ages, water and wastewater networks are under pressure—making it essential to design upgrades that genuinely work, are cost-effective, and support the net zero transition.
Hydraulic models are central to how engineers design sewage network upgrades and plan interventions to reduce overflow events. Yet, despite their importance, the sector currently lacks:
- Global-scale views of model performance
- Consistent quantitative metrics to compare models across sites
- Clarity on model dependencies (e.g., assumptions, setup choices, and “fudge factors”)
In practice, outputs can vary significantly depending on the modeller and modelling approach. As a third party, it’s often unclear how these dependencies interact—meaning decisions can be made based on model outputs without fully understanding:
- the quality of the model outputs,
- whether the solution has been optimised sufficiently, or
- whether better alternatives exist.
This project addresses that gap: creating methods that help infrastructure teams understand when a model is good enough, where optimisation is worthwhile, and which interventions are most effective—across performance, cost, and carbon.
What the project will do
The core aim is to develop AI-enabled tools that support a meta-analysis of hydraulic models—so different sites and models can be assessed and compared in a robust, scalable way.
Crucially, the approach will not rely on computationally expensive modelling alone. Instead, it will use meta-analysis techniques and data-driven methods to evaluate:
- the scale and cost of interventions,
- the “quality” of modelling,
- sensitivity to further optimisation, and
- the likely benefit of additional refinement.
The result: a practical framework that helps engineers and decision-makers allocate effort and investment where it will have the greatest impact.
Project objectives (at a glance)
During the MRes/PhD, you will:
- Develop a detailed understanding of current hydraulic modelling practice
- Create a new framework to quantitatively assess and rank catchment and sewage network hydraulic models
- leveraging AI and big data/meta-analysis techniques
- designed to be computationally efficient
- Provide guidance on which sites and models would significantly benefit from further optimisation
- Assess cost, complexity, and embodied carbon of different intervention types for a holistic decision lens
- Evaluate blue/green and sustainable solutions that could improve network performance
Who should apply?
Applicants should have (or expect to obtain by the start date) at least a high 2.1, preferably at Master’s level, in any STEM subject.
You don’t need to come from a single “perfect” discipline—this research naturally sits at the intersection of:
- civil/environmental engineering,
- data science/AI,
- systems modelling,
- sustainability and net zero infrastructure.
If you enjoy tackling messy real-world problems, thinking critically about evidence quality, and building tools that improve decision-making, you’ll fit well.
Funding and eligibility
- Fully funded studentships (fees + maintenance) are available in the first instance for eligible Home students.
- A limited number of international students may be considered for funding later in the recruitment process.
Key sources for eligibility and funding guidance are provided below.
How to apply
Applications must be submitted online via the University of Cambridge Applicant Portal, stating the project title:
“Development of AI tools for meta-analysis of hydraulic models for preventing combined storm overflows” and noting Prof. Dongfang Liang as supervisor on or before 15th April 2026.
Please note there is a £20 application fee.
Early application is strongly encouraged. Applications are reviewed soon after submission, and an offer may be made before the stated deadline.
Enquiries and contact
- Project-specific enquiries: Professor Dongfang Liang — dl359@cam.ac.uk
- General enquiries: cdtcivil-courseadmin@eng.cam.ac.uk
