Multi-Frequency Complex-Valued Domain Adaptation Methods for Reliable Electromagnetic Solvers

This project’s main aim is to design a complementary physics-guided, data-driven method that can accurately solve complex electromagnetic problems in a timely manner. The primary bottleneck so far preventing this approach is the disparity between trained theoretical models and reality, which will be overcome using novel physics-guided deep learning models, domain adaptation and data augmentation techniques. The method will solve complex electromagnetic problems using deep neural networks guided/regularized by physical theorems. This project will have significant economic and societal benefits, such as supporting the efficient design and operation of medical microwave imaging.

For this scholarship, you will design and code multi-frequency complex-valued domain adaptation methods that enable building reliable electromagnetic solvers. You will generate synthetic electromagnetic data for training the deep neural networks and will also be involved in the pre-processing and calibration of electromagnetic data. 

You will be embedded with the world-leading UQ’s Electromagnetic Innovations team led by Professor Amin Abbosh. The required instruments for this project are accessible at UQ’s Microwave Labs, e.g., the multi-port vector network analyzer, near-field measurement systems, dielectric properties measurement systems, bio-model phantoms, etc. For the extensive simulations and deep learning model training required in this project, you will be using UQ’s High-Performance Computing cluster that is equipped with the most advanced GPUs. 

This is an Fellowship support scheme scholarship project that aligns with a recently awarded Australian Government grant.

The scholarship includes:

• living stipend of $36,400 per annum tax free (2025 rate), indexed annually
• your tuition fees covered

Learn more about the Fellowship support scheme scholarship.

You must contact the principal supervisor for this project to discuss your interest. You should only complete the online application after you have reached agreement on supervision.

Always make sure you are approaching your potential supervisor in a professional way. We have provided some guidelines for you on how to contact a supervisor.

Your application will be assessed on a competitive basis.

We take into account your:

• previous academic record
• publication record
• honours and awards
• employment history.

A working knowledge of deep learning and electromagnetics would be of benefit to someone working on this project.

You will demonstrate academic achievement in the fields of machine learning and signal processing and the potential for scholastic success.

A background or knowledge of applied electromagnetics is highly desirable.

Additional desirable skills and experience include:

• Proficiency in programming languages such as Python and/or C++.
• Experience with machine learning and deep learning libraries such as PyTorch and TensorFlow.
• Knowledge of machine learning algorithms and deep learning methods.
• Skills in data preprocessing, feature extraction, and classification techniques.
• Experience in handling and processing large datasets.
• Ability to conduct thorough literature reviews and stay up to date with the latest research trends in AI and deep learning.
• Experience in writing research papers, reports, and documentation.

This project requires candidates to commence no later than Research Quarter 3, 2025. To allow time for your application to be processed, we recommend applying no later than 31 March, 2025 31 December, 2024.

You can start in an earlier research quarter. See application dates.

Before you apply

1. Check your eligibility for the Doctor of Philosophy (PhD).
2. Prepare your documentation.
3. Contact Dr Alina Bialkowski (alina.bialkowski@uq.edu.au) to discuss your interest and suitability.

When you apply

You apply for this scholarship when you submit an application for a PhD. You don’t need to submit a separate scholarship application.

In your application ensure that under the ‘Scholarships and collaborative study’ section you select:

• My higher degree is not collaborative
• I am applying for, or have been awarded a scholarship or sponsorship
• UQ Earmarked Scholarship type.

Apply now