If you would like more information or have any questions about this scholarship, please contact the project supervisors.
Intelligent systems for automated classification of airborne health risks
Applications will remain open until a candidate has been appointed
Supporting a PhD candidate developing real-time Australian airborne allergen models
Key details
Project supervisor
Deakin school and faculty
Additional supervisors
Location
Geelong Waurn Ponds Campus
Value and duration
This scholarship is available over three years and offers:
- a stipend of $37,450 per annum tax exempt (2026 rate)
- a fixed top-up stipend of $10,000 per annum
- a top-up stipend of $7,000 per annum (2026 rate)
- a relocation allowance of $500–1,500 (for single to family) for students moving from interstate
For international students, the awardee will also receive:
- tuition fees offset for the duration of four years
- single Overseas Student Health Cover policy for the duration of the student visa
Research aim
Do you want to improve the accuracy and responsiveness of airborne health risk alerts, supporting better outcomes for the community and more resilient surveillance systems?
This project seeks to develop intelligent systems to automatically classify airborne health risks, particularly allergenic particles such as pollen and fungal spores, in real time. Using high-resolution imaging data from automated environmental sensors and other data sources, the research will apply advanced machine learning methods to identify and track airborne particles linked to asthma, hay fever, and other respiratory conditions.
Australia’s diverse flora and unique bioaerosol profile require tailored models that go beyond existing international solutions. Australia currently lacks automated systems capable of accurately detecting and classifying airborne allergens, particularly pollen from native and introduced plant species, in real time. Existing machine learning models are largely based on Northern Hemisphere data and fail to capture Australia’s unique and diverse bioaerosol profile. This limits their reliability in health forecasting and emergency preparedness.
This project aims to address that gap by developing intelligent classification models tailored to Australian conditions. Using high-resolution imaging data from automated environmental sensors and expert-annotated reference samples, the research will train and validate machine learning models focused on key allergenic particles such as grass, tree, and weed pollen, and fungal spores. A key component will be the refinement and expansion of particle trigger libraries using expert microscopy and curated reference data from the AirHealth lab.
Background information
Our project will use annotated imaging datasets from Swisens automated bioaerosol sensors, which capture high-resolution holographic images of airborne particles. As the PhD candidate, you will preprocess this data, label it using expert-validated pollen reference sets, and apply deep learning methods (e.g. convolutional neural networks) to develop accurate classification models. Cross-validation and external test sets will be used to assess model performance.
To ensure reliability, model outputs will be validated against manually collected samples from traditional air sampling devices, where airborne particles are captured onto adhesive surfaces and identified under a microscope. Reference slide libraries maintained by AirHealth and collaborators will support accurate annotation of under-represented taxa.
You will also evaluate the integration of the trained models into Australia’s existing pollen forecasting infrastructure, including deployment and testing at selected monitoring sites. The research will aim to produce robust models that generalise across regions, species, and seasonal variation.
Am I eligible?
To be eligible you must:
- meet Deakin's PhD entry requirements
- enrol full time
- hold an honours degree (first class) or an equivalent standard masters degree with a substantial research component
Please refer to the research degree entry pathways page for further information.
Ready to apply?
Please email your CV and cover letter (including your interest in the project) to A/Prof Svetlana Stevanovic. Your CV should highlight your skills, education, publications and relevant work experience. If successful, you will be invited to submit a formal application.
Research degree entry requirements
Set yourself up for success. Each type of Deakin research degree has specific entry requirements designed to ensure that graduate researchers are well prepared for the challenges of advanced study.
