The project aims to improve the way flood information is shared with the NSW State Emergency Service by helping develop and test simple tools that predict how river levels might rise during floods and clearly show the level of uncertainty in those predictions. This project will give the Taste of Research student the opportunity to work closely with Associate Professor Fiona Johnson and industry partner Schematic Intel to collaborate with the NSW State Emergency Service. The student will assist with analysing river and rainfall data, improving an existing Machine Learning flood forecasting model and explore how forecast information can be displayed in clear visual diagrams. The student will be responsible for translating the machine learning model into Google Colab code so for flood forecasts visualisation. This project will contribute to practical solutions that help emergency teams make better decisions during flood events. The overall goal is to make flood warnings easier to understand and more useful for real world emergency response.
School
Civil and Environmental Engineering
Research Area
Hydrology | Disaster resilience | Modelling | Computer science
Suitable for recognition of Work Integrated Learning (industrial training)?
Yes
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
The Taste of Research student would be based in the Hydrology Group in the Water Research Centre. The hydrology group has 2 postdoctoral researchers and 15 HDRs (MPhil and PhD) so can provide an excellent environment for the TOR student to be exposed to research. Water Research in Australia is UNSW is ranked 1st in Australia and 9th internationally for Water Resources in the 2024 Academic Ranking of World Universities by Academic Subject.
- Improved Machine Learning model for ensemble flood forecasts
- Google colab code to integrate ensemble flood forecasts into a schematic display for the Namoi River at Gunnedah
