This PhD proposal aims to develop a framework for small-scale digital twins of Antarctic vegetation combining 3D reconstruction, IoT data, and physics-machine learning to model moss beds with high fidelity, simulating their dynamics under varying conditions. This will improve monitoring and prediction of ecological change, enabling scenario testing to inform conservation and climate change mitigation. This research is positioned at the intersection of AI, environmental science, and conservation technology.
Antarctica is one of the most challenging environments on Earth for plants to live. Plants need sunlight, warmth, and liquid water to be able to grow and survive. Antarctica is dark for half of the year, extremely cold, and water is frozen most of the time. Most plants are unable to survive this environment, but mosses can because they have different physiological strategies to other plants. This has enabled them to form large green turfs that stand out amongst the frozen white and grey landscape. Because they are the dominant plant life in Antarctica, mosses are extremely important for providing habitat for invertebrates, microbes and fungi which make up more than 99% of terrestrial biodiversity in Antarctica. However, long term monitoring has revealed that these moss forests are stressed in many places and have been dying off, but there is evidence of recovery as well.
This PhD proposal seeks to develop a framework for small-scale digital twins (or replicas) of Antarctic vegetation by merging 3D reconstruction techniques, IoT sensor data with physics-informed neural networks to create highly accurate models of moss beds and simulate their dynamics. This integration will enhance our ability to monitor, predict, and test different "what-if" scenarios for changes in this critical region.
Physics-informed neural networks (PINNs) not only leverage historical data but also embed fundamental physical principles directly into machine learning frameworks. Recent research demonstrates that PINNs can outperform traditional process-based models and standard neural networks, particularly in data-sparse regimes typical of ecological applications.
The integration of physics-informed neural networks with digital twin technology positions this research at the intersection of artificial intelligence, environmental science, and conservation technology, offering new insights into the behaviour of Antarctic vegetation.
The Digital Twin implementation will aim to create interactive digital replicas capable of real-time visualization, predictive modelling, and scenario testing. By providing a novel tool for monitoring and predicting changes in this fragile ecosystem, the research will contribute to global efforts in climate change mitigation and environmental conservation.
A comprehensive long-term data set is available for developing and validating models and digital twins. The data set spans decades of research and includes photographs of the mosses, moss health, moss physiology, water availability, microclimate temperature, microclimate light intensity, multispectral drone imagery, and hyperspectral ground-based imagery.
This is an exciting opportunity to showcase how deep learning can benefit Antarctic research and biological monitoring.
More information on the SAEF website
Faculty: Faculty of Science, Medicine and Health
Study area: Computer Science & Information Technology, Environmental & Biological Science
Student type: Domestic students, International students
Student status: Future Students
Scholarship amount
UOW Base Rate ($36,943 per annum for 2026)
Duration
4 years
Application process
Interested applicants need to prepare the following:
- a one-page cover letter outlining relevant experience,
- a Curriculum Vitae (three-page max.),
- The most recent academic transcripts, and (iv) contact details for two academic referees.
Eligibility requirements
- Knowledge in deep learning, machine learning, modelling and simulation
- Good programming skills (eg PyTorch, Tensorflow, Python, Omniverse, PhysicsNeMo)
- Ability to work in a multidisciplinary team environment, as well as independently
Application closing date
30 November 2025
Contact information
Diana King