As flooding becomes an all-too-normal part of everyday life, methods of quickly and accurately predicting such severe weather events are becoming increasingly vital.
Now a team of engineers and scientists from the University of Exeter have developed a model – 1,000 times faster than existing flood prediction systems – to determine when and where flooding will occur.
The model uses artificial intelligence to ‘learn’ about flooding in the same way biological neural networks in the human brain process data.
It uses information about the drainage and sewage systems to predict the volume and flow of flood water in real time.
Professor Dragan Savic, who headed the development of the new model at the university, said: “Our model can be trained to use data from rainfall events to distinguish between urban areas that suffer from flooding and those that don’t. Once it has learnt, it can then be used to classify new rainfall events into those likely to cause flooding and those that do not pose a threat.”
The system which is designed for urban areas promises to provide instant updates as bad weather conditions unfold.
Although it is not yet in general use, tests showed its ability to predict flooding and it is hoped the model will soon be rolled out nationwide.
A report commissioned by UK Water Industry Research (UKWIR) showed the model had “great potential” in the water industry.
Tests during periods of rain in locations including Dorchester in Dorset showed the model accurately predicted the actual outcomes.
Earlier this year academics at Imperial College London teamed up with hydrogeologists and modellers from the British Geological Survey to develop a model promising to more accurately predict the time and location of groundwater flooding in southern England.
An accurate rapid prediction system would to help the Environment Agency provide communities with advanced warnings.
The Exeter-based Met Office and the Environment Agency currently use computer models to predict how heavy rainfall moves over the land surface, potentially leading to flooding. But the models are unable to show exactly where the rain will accumulate and most likely cause problems.
The Met Office keeps the public informed about extended periods of heavy rain or even snow and ice by issuing severe weather warnings, telling people to ‘be aware’, ‘be prepared’ or ‘take action’.
When flooding is likely within six hours, the Environment Agency issues flood alerts and warnings to the public via its website, text messages and the media.
And when flooding is imminent within one hour teams are dispatched to flood locations and residents instructed to stay in a safe location with means of escape.