• Northumbria University Featured PhD Programmes
  • University of Birmingham Featured PhD Programmes
  • University of Warwick Featured PhD Programmes
  • University of Manchester Featured PhD Programmes
  • University of Macau Featured PhD Programmes
  • FindA University Ltd Featured PhD Programmes
  • Queen’s University Belfast Featured PhD Programmes
  • University of Stirling Featured PhD Programmes
University of Dundee Featured PhD Programmes
University of Glasgow Featured PhD Programmes
University of Kent Featured PhD Programmes
Aberdeen University Featured PhD Programmes
FindA University Ltd Featured PhD Programmes

Using artificial intelligence to improve decision-making in conservation conflicts

Project Description

The conservation of biodiversity is increasingly coming into conflict with stakeholders who rely on natural resources for their livelihoods and well-being [1]. Long-term conservation of populations therefore requires an understanding of conflict among stakeholders, and a strategy for managing conflict effectively. Conflict and cooperation between rational decision-makers can be studied formally using game theory. But conservation conflicts are highly complex, meaning that simple game-theoretic models are unlikely to understand and predict human decision-making [2].
Meanwhile, artificial intelligence has shown rapid progress in recent years, particularly in the context of decision-making in complex games [3]. The use of flexible artificial intelligence provides a promising avenue for investigating situations of human conflict and finding solutions to major global problems. For conservation conflicts, the initial development of artificial intelligence in stakeholder decision-making is available in the recently published GMSE R package (Generalised Management Strategy Evaluation) [4], which uses genetic algorithms to model human decision-making and its effect populations [5]. Nevertheless, modelling complex negotiations, interactions among stakeholders, and the biological impact on populations remains a challenge, and requires new conceptual ideas and modelling techniques.
This project will develop and apply artificial intelligence to simulate the decision-making of stakeholders under situations of conservation conflict and the biological response of populations. Stakeholders and organisms will be modelled discretely using an agent-based modelling framework, allowing for potentially complex interactions within simulations [6].
The primary objective is to develop a flexible tool for the agent-based modelling of stakeholder decision-making and its ecological consequences under conditions of conservation conflict, and to then apply this tool to one or more real-world case studies. Additional objectives might include the modelling and simulation of multi-species ecological systems under management, or the development of a graphical user interface for model users.
The student should have a background or very strong interest in programming (ideally in R, C, or C++), and an interest in applying social-ecological modelling to conservation biology. They will benefit from a team of experts in modelling and game-theory, and will interact more broadly with a network of researchers involved in case studies of real-world conservation conflicts.

Funding Notes

Please note that this project is in competition with others for funding, and success will depend on the quality of applications received.

To apply, please email Dr. Duthie (CC Dr. Mill and Prof. Bunnefeld ) with (1) a one page cover letter indicating why you are interested in this project, (2) your CV with contact information for two references, and (3) full transcripts of previous qualifications obtained. The deadline for application is 27 JUL 2018.


[1] Redpath, SM, et al. (2013). Understanding and managing conservation conflicts. Trends in Ecology & Evolution, 28(2), 100-109.
[2] Redpath, SM, et al. (2018). Games as tools to address conservation conflicts. Trends in Ecology and Evolution, 33(6), 415-426.
[3] Moravčík, M, et al. (2017). DeepStack: Expert-level artificial intelligence in heads-up no-limit poker. Science, 356(6337), 508-513.
[4] Duthie, AB, et al. (2018). GMSE: an R package for generalised management strategy evaluation. Methods in Ecology and Evolution. In review. (pre-print here)
[5] Hamblin, S (2013). On the practical usage of genetic algorithms in ecology and evolution. Methods in Ecology and Evolution, 4(2), 184-194.
[6] McLane, AJ, et al. (2011). The role of agent-based models in wildlife ecology and management. Ecological Modelling, 222(8), 1544–1556.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

Cookie Policy    X