QUT Digital Learning of Particle-Laden Flows PhD Scholarship

A fully funded PhD scholarship is available at the Queensland University of Technology (QUT), Brisbane, Australia, in the School of Mechanical, Medical, and Process Engineering. The project focuses on machine learning for particle-laden fluid mechanics, a phenomenon relevant to a wide range of engineering processes from environmental and industrial transport to microscale applications such as aerosol delivery and particulate manipulation in confined devices.

As a scholarship recipient, you will join a team of leading researchers and undertake innovative research in scientific machine learning applied to fluid mechanics. The project will target strategies such as autoencoders and neural differential equations, working with both existing and newly generated data. You will address the challenge of forecasting and reconstructing the evolution of particle-laden turbulent flows from limited data using advanced machine learning techniques. The role also involves data generation and curation for model development, with access to QUT's high-performance computing facilities.

QUT is a major Australian university with a global outlook and a 'real world' focus, recognized as one of the nation’s fastest growing research universities. The student will be part of the Faculty of Engineering and benefit from international collaboration opportunities.

Funding includes a stipend of $37,010 per annum (tax-exempt, indexed annually) for up to 3.5 years, with a possible 6-month extension. Tuition fees are fully offset/sponsored for up to 4 years. The scholarship is open to candidates who meet QUT's PhD entry requirements, including English language proficiency. Eligible academic backgrounds include mechanical engineering, applied mathematics, civil engineering, geotechnical engineering, applied physics, or related disciplines. Applicants should demonstrate knowledge or experience in computational fluid dynamics, applied mathematical modelling, machine learning, multi-fidelity modelling, and numerical methods. Programming skills in MATLAB, Python, or C++ and enthusiasm to learn PyTorch are required. Experience with Nek5000, Basilisk, or OpenFOAM is desirable.

To apply, email Dr Tony Zahtila with a brief description of your academic and research background, motivation for the field, and interest in the scholarship, along with your CV. Shortlisted candidates will be invited to interview, and preferred candidates will be asked to submit an Expression of Interest (EOI) following QUT's research degree application process. Applications close on 30 June 2026.