Next-Generation Marine Ecosystem Indicators: Machine Learning for Smarter Marine Spatial Planning in a Changing Climate (TRIFONOVA_UEA_ARIES26)
Key Details
- Application deadline
- 7 January 2026
- Location
- UEA
- Funding type
- Competition funded project (Students worldwide)
- Start date
- 1 October 2026
- Mode of study
- Full or part time
- Programme type
- PhD
)
Welcome to Norwich
According to the Sunday Times, this city is one of the best places to live in the UK.
Project description
Primary Supervisor - Dr Neda Trifonova
Background
The UK marine environment is a complex, high-demand space. It provides vital services, including food provision through fisheries and aquaculture, and energy security via offshore wind generation. Balancing these uses while preserving biodiversity and protecting marine ecosystem health is increasingly challenging. As human pressures and climate change accelerate, we urgently need smart, evidence-based tools to plan, manage, and protect our marine ecosystems.
At the forefront of this innovation is machine learning. Its ability to process complex, multidimensional datasets is transforming marine ecology and redefining how we detect and respond to ecosystem change.
Methodology
This PhD will place you at the forefront of this emerging field. You will address a key challenge: assessing what makes a reliable measurable indicator of change in marine ecosystems (e.g., shift in species populations) and interpreting what these indicators reveal about ecosystem health.
You will develop and apply cutting-edge machine-learning techniques to identify the most informative indicators of ecosystem change and use them to build dynamic Bayesian network (DBN) ecosystem models. The project’s key objectives are to: 1) Identify critical indicators relating to ecosystem health and resilience; 2) Incorporate indicators into DBN models to simulate how ecosystems respond to future climate and human use scenarios; 3) Investigate the merits and drawbacks of DBN models in different geographic locations and over varying timescales; 4) Translate DBN model outputs into policy-relevant insights supporting the design of effective Marine Protected Areas (MPAs) and informed Marine Spatial Planning.
Training
Based at the University of East Anglia, you will gain expertise in marine ecosystem modelling using both field-based and modelled physical and biological data. Collaboration with Centre for the Environment, Fisheries and Aquaculture Science will provide exposure to how science informs UK policy on marine biodiversity and MPAs design. You will gain sea-going field experience and be trained in a range of state-of-the-art instruments aboard the RV CEFAS Endeavour.
Person Specification
We seek an enthusiastic individual who is interested in marine ecology, computing, with some prior experience in programming and data handling, eager to communicate findings to wider stakeholders and help shape the UK’s marine conservation strategies and the sustainable use of the marine environment.
Entry requirements
At least UK equivalence Bachelors (Honours) 2:1. English Language requirement (Faculty of Science equivalent: IELTS 6.5 overall, 6 in each category).
Acceptable first degree: environmental, marine or mathematical sciences (or similar)
Funding
ARIES studentships are subject to UKRI terms and conditions. Successful candidates who meet UKRI’s eligibility criteria will be awarded a fully-funded studentship, which covers fees, maintenance stipend (£20,780 p.a. for 2025/26) and a research training and support grant (RTSG). A limited number of studentships are available for international applicants, with the difference between 'home' and 'international' fees being waived by the registering university. Please note, however, that ARIES funding does not cover additional costs associated with relocation to, and living in, the UK, such as visa costs or the health surcharge.
ARIES is committed to equality, diversity, widening participation and inclusion in all areas of its operation. We encourage applications from all sections of the community regardless of gender, ethnicity, disability, age, sexual orientation and transgender status. Projects have been developed with consideration of a safe, inclusive and appropriate research and fieldwork environment. Academic qualifications are considered alongside non-academic experience, with equal weighting given to experience and potential.
Please visit www.aries-dtp.ac.uk for further information.
References
Trifonova, N.I., Scott, B.E., De Dominicis, M., Waggitt, J.J. and Wolf, J., 2021. Bayesian network modelling provides spatial and temporal understanding of ecosystem dynamics within shallow shelf seas. Ecological Indicators, 129, p.107997.
Hogg, O.T., Kerr, M., Fronkova, L., Martinez, R., Procter, W., Readdy, L. and Darby, C., 2024. Assessing efficacy in MPA design decisions using a bespoke and interactive fisheries management tool. Biological Conservation, 300, p.110848.
Hogg, O.T., Huvenne, V.A.I., Griffiths, H.J., Linse, K. (2018) On the ecological relevance of landscape mapping and its application in the spatial planning of very large marine protected areas. Science of The Total Environment, 626: 384-398.
O’Leary, B.C., Copping, J.P., Mukherjee, N., Dorning, S.L., Stewart, B.D., McKinley, E., Addison, P.F.E., Williams, C., Carpenter, G., Righton, D., Yates, K.L. (2021) The nature and extent of evidence on methodologies for monitoring and evaluating marine spatial management measures in the UK and similar coastal waters: a systematic map. Environ Evidence, 10, 13.