Melbourne: Researchers found a new model that has the potential to significantly improve emergency response by lowering flood forecasting time from hours to days and allowing flood behaviour to be reliably anticipated at super-fast speeds as an event unfolds.
The study was published in Nature Water.
Niels Fraehr, a PhD student at the University of Melbourne, collaborated with Professor Q J Wang, Dr Wenyan Wu, and Professor Rory Nathan from the Faculty of Engineering and Information Technology to create the Low-Fidelity, Spatial Analysis, and Gaussian Process Learning (LSG) model to predict the effects of flooding.
The model can make predictions that are as accurate as our most advanced simulation models but at 1000 times faster rates. According to Professor Nathan, the development has tremendous promise as an emergency response tool.
“Currently, our most advanced flood models can accurately simulate flood behaviour, but they’re very slow and can’t be used during a flood event as it unfolds,” said Professor Nathan, who has 40 years of experience in engineering and environmental hydrology.
“This new model provides results a thousand times more quickly than previous models, enabling highly accurate modelling to be used in real-time during an emergency. Being able to access up-to-date modelling during a disaster could help emergency services and communities receive much more accurate information about flooding risks and respond accordingly. It’s a game-changer.”
When tested on two vastly different yet equally complex river systems in Australia, the LSG model predicted floods with 99 per cent accuracy on the Chowilla floodplain in Southern Australia in 33 seconds, rather than 11 hours, and the Burnett River in Queensland in 27 seconds, rather than 36 hours, when compared to currently used advanced models.
The new model's speed also helps responders to account for the significant volatility in weather forecasts. Due to the limits of current flood forecast models, flood simulations often focus on the most likely scenario.
In contrast, the researchers' LSG model allows them to mimic how the uncertainty inherent in weather forecasts translates to on-the-ground flood impacts as a flood event progresses. The model employs mathematical transformations and a sophisticated machine learning approach to swiftly exploit massive volumes of data while utilising widely available computing platforms.
Professor Nathan stated that the model, the result of two years of development effort, has a number of potential benefits in Australia and around the world.
“This new model also has potential benefits in helping us design more resilient infrastructure. Being able to simulate thousands of different flooding scenarios, instead of just a handful, will help design infrastructure that holds up to more unpredictable or extreme weather events,” Professor Nathan said.
“As our climate becomes more extreme, it’s models like these that will help us all be better prepared to weather the storm.” (ANI)
