About the Project
This project is one of a number that are in competition for funding from the Red-ALERT CDT, hosted by the University of Bath for entry in September 2026.
Overview of the Research:
Protists and small invertebrates (i.e., plankton) form the foundation of aquatic food webs and respond rapidly to environmental change, making freshwater plankton sensitive indicators of ecosystem health. Monitoring these communities is therefore crucial for assessing the impacts of climate change, land use, and pollution on freshwater systems. Increasingly, environmental monitoring has relied on DNA metabarcoding, a powerful tool that has led to many advancements in our understanding of biodiversity and environmental health. Metabarcoding alone, however, provides relative rather than absolute abundance estimates, potentially missing a key dimension of environmental change. Complimentary approaches capable of quantifying biodiversity could therefore add much needed context to ongoing assessments.
This project will evaluate whether high-throughput quantitative imaging can be an effective tool for ecological surveillance. Using open-source imaging devices (e.g., the PlanktoScope), we will collect regular water samples from the Cam & Wellow Living Lab, and capture in situ images of freshwater plankton across temporal and environmental gradients. These images will be used to record diversity, abundance, and prevalence of plankton, but also morphological traits and indicators of organismal health (deformities, parasitism, and size), which cannot be determined from metabarcoding alone.
By building automated image classification pipelines, and integrating these with community annotation platforms, we will use machine learning to identify taxa and quantify community structure in routine sampling. These imaging surveys will be used to benchmark biodiversity assessments against temporal metabarcoding datasets, assessing how imaging-based diversity metrics align with molecular profiles, and how both can offer a complementary approach to digital water fingerprinting.
Combining open hardware, machine learning, and ecological expertise, this project will test the feasibility of image-based biodiversity monitoring, enabling continuous, widespread and cost-effective ecosystem surveillance. This could underpin new citizen science initiatives and contribute to national environmental monitoring frameworks, improving our capacity to detect and respond to ecological change.
Training:
The student will receive training in quantitative ecology, image analysis, and machine learning, alongside molecular biodiversity assessment techniques (e.g., DNA metabarcoding). They will gain experience in field sampling and environmental data collection, supported by supervisors across academia, independent research organisations, and government.
Interdisciplinarity:
The project bridges ecology, data science and machine learning, and bioinformatics, integrating fieldwork and microscopy with data science and molecular ecology. The student will work collaboratively with diverse teams, including citizen science networks, to develop cross-disciplinary expertise to innovate environmental research.
Project Keywords: Freshwater, plankton, protists, invertebrates, quantitative imaging, metabarcoding, biodiversity
Industrial Partner: Sophie Pitois, Centre for Environment, Fisheries, and Aquaculture Science (Cefas), sophie.pitois@cefas.gov.uk
Candidate Requirements:
Applicants should hold, or expect to receive, a First Class or good Upper Second-Class UK Honours degree (or the equivalent) in a relevant subject – e.g. biomedical engineering, electronic engineering, chemistry, biochemistry, etc. Academic qualifications are considered alongside significant relevant non-academic experience. A master’s level qualification would also be advantageous.
Equality, Diversity, and Inclusion:
We value a diverse research environment and aim to be an inclusive university, where difference is celebrated and respected. We welcome and encourage applications from under-represented groups.
If you have circumstances that you feel we should be aware of that have affected your educational attainment, then please feel free to tell us about it in your application form. The best way to do this is a short paragraph at the end of your personal statement.
Enquiries and Applications:
Formal applications should be submitted via the Red-ALERT CDT online application form prior to the closing date of this advert.
Funding Notes
Candidates may be considered for a NERC Red-ALERT studentship tenable for 3.5 years. Funding covers tuition fees, a stipend (£20,780 p/a in 2025/6) and access to a training support budget.
