Behzad Kiani

Advancing Infectious Disease Modeling with Machine Learning and Spatial Epidemiology

Machine learning (ML) is transforming the field of spatial epidemiology, offering powerful tools to enhance disease prediction and risk mapping. However, many ML approaches lack explicit spatial components or are applied without careful integration into public health frameworks. This project aims to evaluate, refine, and apply ML techniques to improve the modeling of infectious diseases in space and time.

You will explore how different ML models (e.g., Random Forest, XGBoost, Neural Networks, or ensemble models) can outperform or complement traditional spatial methods (e.g., Bayesian models, spatial lag/error models, GWR) in predicting infectious disease outcomes such as dengue, leptospirosis, or salmonella. The project includes comparative modeling, spatial feature engineering, and visualizing results through spatial risk maps and dashboards.

Climate-Informed Spatial Risk Forecasting of Enteric Diseases in Australia

We are seeking a highly motivated PhD candidate to join an exciting research project investigating the impact of climate variability and climate change on the spatial and temporal distribution of enteric diseases across Australia, with a primary focus on salmonellosis and campylobacteriosis.

Foodborne diseases remain a major public health challenge in Australia, causing substantial morbidity, healthcare burden, and economic costs. Emerging evidence suggests that climatic factors such as temperature, rainfall, humidity, and extreme weather events may influence disease risk by affecting pathogen survival, environmental persistence, food safety systems, and human behaviour. However, there remains a critical need for robust, climate-informed forecasting approaches that can identify when and where disease risks are likely to increase.

This project will utilise national surveillance data, environmental and climate datasets, and advanced geospatial analytical methods to investigate climate–disease relationships across Australia. The successful candidate will develop and apply state-of-the-art spatial epidemiological and machine learning approaches to identify disease hotspots, quantify climate-sensitive risk factors, and generate climate-informed risk forecasting tools that can support public health preparedness and decision-making.

The project offers opportunities to work with large national datasets, cutting-edge geospatial methods, and interdisciplinary collaborations spanning epidemiology, environmental health, climate science, and public health intelligence. Findings from the research are expected to contribute to the development of early warning systems and climate adaptation strategies for infectious disease prevention.

Potential research areas include:

• Spatial epidemiology of salmonellosis and campylobacteriosis.
• Climate-sensitive infectious disease modelling.
• Geospatial analysis and disease hotspot detection.
• Machine learning for public health forecasting.
• Climate change and health security.
• Development of decision-support tools for disease preparedness and prevention.

The project is suitable for candidates with backgrounds in epidemiology, public health, biostatistics, environmental health, geography, data science, mathematics, computer science, or related disciplines. Experience with statistical analysis, GIS, R, Python, or spatial modelling would be advantageous.