Four ARC Linkage PhD Research Positions at Murdoch University, Perth, Australia
This collaborative research between ecologists, statisticians, computer scientists and the mining industry will develop AI-driven tools to more effectively monitor the vegetation against restoration targets and deepen our understanding of how a community reassembles after disturbance by mining. Such tools will benefit both industry and regulators by enhancing the on-ground decisions and practices applied in ecosystem rehabilitation.
Three of the projects will focus on community ecology aspects while the 4th project will be in the field of machine learning within computer science and aims to develop an AI‑assisted tool. All four projects will be tightly linked hence the successful PhD candidates (and their supervisors) will be working as a team.
Our Linkage Project will focus on the fields of dark-diversity and community ecology, using existing data on vegetation characterised by contrasting community assembly processes, involving species-rich kwongan shrublands and Jarrah forests of Western Australia, myall woodlands and Nullarbor scrub vegetation of South Australian semi-deserts, and species-poor salt-marsh vegetation of South Africa.
Brief descriptions of the PhD topics
Topic 1: Dark-diversity and community completeness in natural and rehabilitated vegetation, focusing on patterns of species pools and other taxon-based indices in spatial-scaling and phylogenetic contexts.
Topic 2: Dark-diversity and community completeness in natural and rehabilitated vegetation, focusing on patterns of functional trait spaces pools and other functional indices in spatial-scaling and trait-nature contexts.
Topic 3: Theoretical aspects of community saturation and community completeness in context of contrasting community-assembly scenarios (niche-focused assembly vs. neutral community assembly), using real data sets and modelling approaches.
Topic 4: Development of AI-based monitoring tools for monitoring and assessing the success of ecological restoration using species and trait-based data.
The Team of Supervisors
Prof Ladislav Mucina, Murdoch University, Project Leader
community ecology; biodiversity science; ecological restoration; evolutionary biology; biogeography; data analysis in ecology
https://www.researchgate.net/profile/Ladislav_Mucina
Prof Hamid Laga, Murdoch University
computer vision; machine learning; applied mathematics and statistics
https://scholar.google.com.au/citations?user=Qxmqp-0AAAAJ&hl=en
A/Prof Rachel Standish, Murdoch University
community ecology; ecological restoration
https://restoreecology.wordpress.com/
Dr Alethea Rea, Murdoch University
statistics and modelling
https://scholar.google.com.au/citations?user=_iQwkTUAAAAJ&hl=en
Prof Erik Veneklaas, The University of Western Australia;
functional ecology; ecological restoration
https://researchgate.net/profile/Erik-Veneklaas
A/Prof Michael Renton, The University of Western Australia
ecological and evolutionary modelling; applied mathematics and statistics
https://research-repository.uwa.edu.au/en/persons/michael-renton
Dr Mark Dobrowolski, Iluka Resources Ltd
ecological restoration; community ecology; soil science
https://www.researchgate.net/profile/Mark-Dobrowolski-2
Dr Lucy Commander, Alcoa in Australia Ltd
ecological restoration; seed ecology
https://www.researchgate.net/profile/Lucy-Commander
Prof Meelis Pärtel, University of Tartu, Estonia
community and functional ecology; biodiversity science; ecological restoration
https://www.etis.ee/CV/Meelis_P%C3%A4rtel/eng/
A/Prof Stefano Chelli, University of Camerino, Italy
community and functional ecology; biodiversity science, ecological restoration
https://www.researchgate.net/profile/Stefano_ChelliEligibility
- The positions are open for candidates from both Australia and overseas
- Honours or Masters of Science degrees or equivalent authorising enrolment in a PhD programme in Australia. Suitable areas of study include:
- Ecology (Topics 1,2,3)
- Computer Science, or Mathematics, or Electrical Engineering with strong programming and mathematical skills (Topic 4)
- High-level communication skills in speaking, communicating, and writing in English
- Willingness and ability to work in a scientific team, including sharing ideas and data
- Relevant prior studies including one or more of the following:
- Community ecology (theory and methodology)
- Functional ecology focusing on plant functional traits
- Ecology and evolution
- Theory and applications in vegetation rehabilitation and restoration
- Programming and mathematics skills
- Prior experience with image processing, computer vision and machine learning are desirable for the PhD Topic 4
- Understanding, and preferably experience with use, of basic exploratory statistics (incl. multivariate analysis)
- Experience of programming in R, and use of R software tools
- Ability to commence the PhD project by enrolment at MU in July 2025
- Bonus: Knowledge of basic methodologies used in machine learning and AI since all ecology-focused PhD project will be cooperating with a PhD student (and her/his supervisors) focusing on building on AI tools
- Bonus: Previous successful publications relevant to the field covered by the selected Topics
How to Apply
Using email sent to (Ladislav.Mucina@murdoch.edu.au)Required Documents
- CV in English
- List of publications (published or submitted); PDFs of all publications to be provided
- List of 1 reference persons in the scientific fields covered by the ARC Linkage project
- Declaration of interest to pursue research in one of the Topics listed in Description