The natural world contains an awe-inspiring variety of colouration across plant and animal species, but the causes of this diversity are not well understood. The aim of this PhD is to help unravel the mysteries of natural colour diversity using cutting-edge machine learning and computer vision technologies.
In this PhD project, we seek to harness the potential of machine learning and computer vision approaches to revolutionise the measurement, classification and understanding of colour pattern diversity. The project is multidisciplinary, bringing together the fields of biology, computer science, and data analytics to unlock nature's palette in new and powerful ways.
As a PhD researcher on this project, you will play a central role in advancing our knowledge of coloration diversity. Key objectives include:
(1) Collecting and curating large-scale datasets of plant and animal coloration, encompassing a wide range of species and habitats
(2) Developing innovative machine learning pipelines to analyse and extract valuable insights from image-based data
(3) Applying state-of-the-art computer vision techniques to automatically detect, classify, and quantify colours and patterns across diverse organisms.
(4) Collaborating with ecologists and evolutionary biologists to gain a deeper understanding of the ecological and evolutionary significance of colouration diversity.
(5) Contributing to the development of user-friendly software tools to enable broader access to colouration data and analysis techniques.
We welcome applications from candidates with a strong background in computer science and machine learning (or related fields) to tackle this novel and exciting opportunity. Ideal candidates would have a familiarity with various machine learning frameworks (e.g. TensorFlow, PyTorch), computer vision libraries (e.g. OpenCV) and programming languages (e.g. R, Python, MATLAB). An interest in biodiversity, ecology and evolutionary biology is also desirable. The student can expect to work closely with all supervisors and their respective research groups and to be supported in publishing their work in top peer-reviewed journals.
Key publications from the research group:
He et al. (2023) Using pose estimation to identify regions and points on natural history specimens. PLOS Computational Biology 19:e1010933. DOI: https://doi.org/10.1371/journal.pcbi.1010933
He et al. (2022) Deep learning image segmentation reveals patterns of UV reflectance evolution in passerine birds. Nature Communications 13:5068. DOI: https://doi.org/10.1038/s41467-022-32586-5
Cooney et al. (2022) Latitudinal gradients in avian colourfulness. Nature Ecology and Evolution 6:622–629. DOI: https://doi.org/10.1038/s41559-022-01714-1
Cooney et al. (2019) Sexual selection predicts the rate and direction of colour divergence in a large avian radiation. Nature Communications 10:1773. DOI: https://doi.org/10.1038/s41467-019-09859-7
Continue with Facebook
