Application Deadline: 05 December 2025
Details
AI_CDT_DecisionMaking
Details
The UK water sector is in crisis. Worsening floods and droughts are two of the biggest threats facing the UK from climate change [1], and the poor water quality of UK rivers is widely considered to be a national scandal. The recent Independent Water Commission Review [2] gave 88 recommendations, strongly emphasising the need for regional-level strategic planning, building on Manchester’s blueprint for integrated water management (for which the main Supervisor of this PhD project is a Scientific Adviser). As a direct outcome, the UK government is establishing a new independent water authority, tasked with regulating water companies and validating regional water management strategies. This signals a major shift in national water governance and creates an unprecedented opportunity to reimagine the digital infrastructure underpinning water planning and monitoring in the UK, placing AI at its core.
With the advent of new high-resolution datasets [3] and national-scale physically based modelling platforms [4, 5], there is now a technical foundation for developing a data-driven, spatially distributed, high-resolution national modelling system. This system would be valuable not only to the new water authority but also to environmental consultancies, local councils, and water companies for flood forecasting, water resource planning, and optimisation of long-term infrastructure investment [6].
Current practice for predictive modelling in water resources includes a spectrum of hydrological models, from purely data-driven ones to those based on well-detailed physics. The most used data-driven model is based on a Long Short-Term Memory (LSTM) recurrent neural network [7,8], whereas a more detailed physics-based model is based on a finite-difference model from partial differential equations for water flow and transport, SHETRAN [9]. While physics-based models are more accurate and allow extrapolation, they are expensive to solve. Practitioners are turning to data-driven models, but those tend to miss the extrapolation abilities, do not transfer to other geographical settings and need to be trained every time from scratch. Furthermore, none of the current models account for uncertainties in the prediction, which are key to informing decision-making in water management.
There are two aims in this project: i) we will develop and apply physics-informed machine learning models, which help to bridge the gap between purely data-driven models and physics-based models for water resource prediction. ii) we will empower such models with the ability to provide a measure of confidence in the predictions, indispensable for effective decision-making.
Desirable Student Background:
A student with an MSc in Physics, Computer Science, Statistics, Mathematics or a related field is the ideal candidate for this project. They don’t need to have previous knowledge of water resource management. This PhD project will emphasise method development.
Before you apply
We strongly recommend that you contact the supervisor(s) for this project before you apply. Please include details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project. For any questions please contact the UKRI AI Decisions CDT Team (aidecisionscdt@manchester.ac.uk).
How to apply:
Please apply under the University of Manchester application portal and select ‘PhD in Artificial Intelligence’ (OAA Applicant Portal)
When applying, you’ll need to specify the full name of this project, the name of your supervisor, if you already having funding or if you wish to be considered for available funding through the university, details of your previous study, and names and contact details of two referees.
Your application will not be processed without all of the required documents submitted at the time of application, and we cannot accept responsibility for late or missed deadlines. Incomplete applications will not be considered.
After you have applied you will be asked to upload the following supporting documents:
- Final Transcript and certificates of all awarded university level qualifications
- Interim Transcript of any university level qualifications in progress
- CV
- Supporting statement: A one or two page statement outlining your motivation to pursue postgraduate research and why you want to undertake postgraduate research at Manchester, any relevant research or work experience, the key findings of your previous research experience, and techniques and skills you’ve developed. (This is mandatory for all applicants and the application will be put on hold without it).
- Contact details for two referees (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)
Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. (Equality, diversity and inclusion | The University of Manchester)
We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.
We also support applications from those returning from a career break or other roles. We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs. Our selection process is free from bias, and we are committed to ensuring fair and equal opportunities for all applicants.
We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs, including a part-time study option.
Funding Notes
This is a fully funded AI UKRI CDT 4 year program; Home tuition fees will be provided, along with a tax-free stipend (subject to individual circumstances), set at the UKRI rate (e.g. ÂŁ20,780 for 2025/26) . The start date is September 2026.
The Project will be based in University of Manchester.
References
[1] Committee on Climate Change (2017). UK Climate Change Risk Assessment 2017: Synthesis Report. https://www.theccc.org.uk/uk-climate-change-risk-assessment-2017/synthesis-report/
[2] Independent Water Commission (2025). Review of the Water Sector: Final Report. https://www.gov.uk/government/publications/independent-water-commission-review-of-the-water-sector
[3] Lewis, E., Quinn, N., Blenkinsop, S., Fowler, H., Freer, J., Tanguy, M., Hitt, O., Coxon, G., Bates, P. and R. Woods (2018). A rule based quality control method for hourly rainfall data and a 1 km resolution gridded hourly rainfall dataset for Great Britain: CEH-GEAR1hr. Journal of Hydrology, 564, 930-943. doi: 10.1016/j.jhydrol.2018.07.034.
[4] Lewis, E., Birkinshaw, S., Kilsby, C. and H. Fowler (2018). Development of a system for automated setup of a physically-based, spatially-distributed hydrological model for catchments in Great Britain. Environmental Modelling & Software, 108, 102-110. doi: 10.1016/j.envsoft.2018.07.006.
[5] Smith, B., Birkinshaw, S., Lewis E., McGrady E. and P. Sayers (2024). Physically-based modelling of UK river flows under climate change. Frontiers in Water, 6. doi: 10.3389/frwa.2024.1468855.
[6] Ur Rehman, A., Glenis, V., Lewis, E. and C. Kilsby (2024). Multi-objective optimisation framework for Blue-Green Infrastructure placement using detailed flood model. Journal of Hydrology, 638, 131571. doi: 10.1016/j.jhydrol.2024.131571.
[7] Kratzert, F., Klotz, D., Brenner, C., Schulz, K. and M. Herrnegger (2018). Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrology and Earth System Sciences, 22 (11), 6005-6022. doi: 10.5194/hess-22-6005-2018
[8] Nearing, G., Cohen, D., Dube, V. et al. (2024). Global prediction of extreme floods in ungauged watersheds. Nature, 627, 559–563. doi: 10.1038/s41586-024-07145-1
[9] https://research.ncl.ac.uk/shetran/index.htm
