About the project
As a researcher on this project you will work at the forefront of Artificial intelligence (AI) methods to develop and test a purely AI-driven model used to simulate the propagation of flood inundation at high-performance.
Floods are the most devastating and costly among all natural hazards. The risk of flooding is expected to rise substantially in the coming decades due to the following:
- population growth increasing the exposure of people and assets
- the climate emergency changing the intensity and frequency of storms
- accelerating sea level rise
Flood inundation models are used to understand and design measures to mitigate the risk of flooding. Current models available are based on the solution of the two-dimensional shallow water equations. This is a system of nonlinear partial differential equations expressing the principles of mass and momentum conservation.
To simulate real-world problems accurately, these models need to be run using finely resolved topography. The long computing time often limits the size of the domains and or the duration of the events modelled. These techniques are not fit for purpose as there is a growing need for large domain simulations and for multiple simulations used in probabilistic forecast.
Recent new AI techniques such as deep learning, have started to find applications in flood inundation modelling. New research indicates that deep-learning algorithms have a huge potential to offer solutions. These may out perform conventional techniques of numerical integration of the shallow-water equations.
You'll join a world-leading research team and have access to our outstanding supercomputing facilities.
