PhD Studentship: CENTA 2027-B07 Biodiversity Digital Twin: Leveraging Environmental DNA and Artificial Intelligence for Monitoring Biodiversity Loss

Biodiversity is declining at an alarming rate, affecting the delivery of ecosystem services on which we all rely for our well-being and the economy. These services include climate regulation, food provisioning, clean water and recreation, to name a few. With the exit from the EU, the UK established the 25-year environment plan to improve environmental quality within a generation, and the Environment Act 2021 to maintain biodiversity net gain while enabling growth. These necessary regulations demand a rapid response from industry to assess the impact of production processes on biodiversity.

However, we lack the tools to predict the impact of industrial processes on natural biological diversity, thereby limiting our ability to conserve critical resources and the services they provide. One of the main challenges that conservationists face is predicting the severity of biodiversity loss and identifying the main drivers of this loss. Traditional methods focus on individual species, missing by design the species interactions and with the environment. Holistic, community-level approaches are still largely missing.

In this project, the DR will develop state-of-the-art AI algorithms to monitor and predict biodiversity loss under different climate and pollution scenarios. The DR will apply graph neural networks (GNNs), especially temporal graph networks (TGNs) and spatiotemporal graph neural networks (STGNNs), to model historical biodiversity data obtained from freshwater lake ecosystems across England. This will be done using sediment core environmental DNA. GNN is a cutting-edge AI model. It will integrate spatiotemporal eDNA and environmental data to create a digital twin to simulate the dynamics of freshwater lake biodiversity. This Biodiversity Digital Twin will offer multi-scale, holistic modelling that tracks changes across taxonomic groups over space and time and links them to environmental change, identifying the main drivers of loss.

To make the tool accessible to end-users, the DR will develop an intuitive analytical dashboard. This dashboard will allow the direct assessment of production processes, land use, and other human activities on biodiversity. By synergistically combining advanced computational and bioinformatics technologies with end-user insights, the team aims to accelerate the transition from traditional to science-driven, technologically enhanced solutions for biodiversity conservation.

For further information on this project and details of how to apply to it please click the 'Apply' button above.

Further information on how to apply for a CENTA studentship can be found on the CENTA website: https://centa.ac.uk/apply/

Funding notes:

This project is offered through the CENTA3 DLA, funded by the Natural Environment Research Council (NERC). Funding covers: annual stipend, tuition fees (at home-fee level), Research Training Support Grant.

Academic requirements: at least a 2:1 at UK BSc level or a pass at UK MSc level or equivalent.

Further information: https://centa.ac.uk/apply/

International students are eligible for studentships to a maximum of 30% of the cohort. Funding does not cover any additional costs relating to moving or residing in the UK. International applicants must fulfil the University of Birmingham’s international student entry requirements, including English language. Further information: https://www.birmingham.ac.uk/postgraduate/pgt/requirements-pgt/international/index.aspx.

References:

Eastwood et al (2023) 100 years of anthropogenic impact causes changes in freshwater functional biodiversity. eLife, 12. (https://doi.org/10.7554/eLife.86576.3)

Rossi et al (2020). Temporal graph networks for deep learning on dynamic graphs. arXiv preprint, arXiv:2006.10637. (https://doi.org/10.48550/arXiv.2006.10637)

Trantas et al(2023). Digital twin challenges in biodiversity modelling. Ecological Informatics, 102357. (https://doi.org/10.1016/j.ecoinf.2023.102357)

Borowiec et al (2022). Deep learning as a tool for ecology and evolution. Methods in Ecology and Evolution, 13(8): 1640-1660. (https://doi.org/10.1111/2041-210X.13901).