Higher Degree by Research Application Portal

Ocean currents are directed flows of seawater driven by external forces such as wind, tidal forces, instabilities and surface waves. These currents create a highly dynamic water column, with velocities fluctuating over depth and time as shown in Figure 1. Understanding and accurately forecasting this variability is essential for safe and efficient offshore operations, particularly during activities like offloading.

Forecasting ocean current velocity profiles from the surface to 50 m depth presents a significant research challenge. Real-world ocean data can pose significant difficulties, often exhibiting sudden changes, irregular patterns, lagged connections between cause-and-effect variables, and distributional shifts over time. These inherent characteristics complicate forecasting, making forecasts unreliable even over short horizons (e.g. days). Furthermore, traditional machine learning models typically assume that the training and test data come from the same distribution – an assumption that is rarely valid in real-world oceanographic settings.

This PhD project will focus on developing robust, physics-informed probabilistic forecasting models adaptable to real-world distributional shifts, delivering generalisable solutions. The project will use ocean and metocean measurements, combining physics-based modelling, statistical methods, and cutting-edge machine learning.

The ultimate goals will be to:

• produce reliable probabilistic forecasts and quantify predication uncertainty of near-surface ocean current vertical profiles; 
• and to improve our understanding of the physical drivers of observed variability in such profiles using machine learning methods (e.g. explainable AI).

We are seeking high calibre students who can apply and be considered for international or domestic scholarships at UWA, with the potential for additional support from the Shell Chair in Offshore Engineering.

Please send your CV and a cover letter to Maira Alvi (maira.alvi@uwa.edu.au).

We are seeking a motivated PhD candidate with:

• An interest in data-driven oceanographic modelling.
• Proficiency in programming languages, preferably Python.
• Knowledge of deep learning frameworks (e.g., PyTorch or TensorFlow/Keras).
• Experience with machine learning, deep learning algorithms, and statistical modelling.

The Doctor of Philosophy (PhD) is a program of independent, supervised research that is assessed solely on the basis of a thesis, sometimes including a creative work component, that is examined externally. The work presented for a PhD must be a substantial and original contribution to scholarship, demonstrating mastery of the subject of interest as well as an advance in that field of knowledge. 

Visit the course webpage for full details of this course including admission requirements, course rules and the relevant CRICOS code/s.