This project will investigate the application of advanced data analysis techniques to water-quality datasets collected by our water industry partners from their lakes and catchments in Queensland. Cyanobacterial blooms are a persistent water-quality challenge for our industry partner, with bloom occurrence influenced by factors such as temperature, nutrient availability, rainfall, water retention and site-specific conditions. The TofR project will evalaute the importance of understanding these relationships and the limitations of relying on studies conducted using non-site-specific datasets. The project will involve processing, cleaning and exploring historical monitoring data to identify temporal patterns, correlations and key environmental variables associated with cyanobacterial bloom development. Statistical analysis and suitable machine learning or predictive modelling approaches will then be investigated to assess their ability to predict bloom occurrence or intensity. Model performance will be evaluated using appropriate validation and accuracy measures, with emphasis on identifying approaches that are practical for water industry applications. The outcomes will provide a data-driven understanding of bloom behaviour in the lake systems and explore the potential for predictive analytics to support proactive water-quality monitoring and treatment planning.
School
Chemical Engineering
Research Area
Water treatment | Machine learning | Artificial intelligence | Cyanobacteria
Suitable for recognition of Work Integrated Learning (industrial training)?
Yes
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
The student will be based at the Algae and Organic Matter Laboratory (https://www.unsw.edu.au/research/aom) under the supervision of Dr Naras Rao. We have world class facilities and deep water industry connections. The project is highly suitable for someone who wants to work with real water quality datasets from our industry partners in Queensland. Subject to availability and project requirements, there may also be an opportunity for the student to visit the industry partner’s site to gain first-hand insight into the water systems and operational context relevant to the project.
- The project is expected to contribute to and improve our industry partner's understanding of cyanobacterial blooms, including their occurrence, key influencing factors and potential approaches for improved monitoring and management. The analysis will provide industry-relevant insights into the patterns and relationships within their water-quality datasets and assess the potential of data-driven approaches to support proactive bloom prediction and management. The outcomes of the project are also expected to be developed into a research publication for presentation at OzWater, Australia’s leading water industry conference.
- Water industry partners from Queensland