Researchers use AI to develop early flood warning system

29 Jan 2024

Image: © SANGUN/

Data from Storm Babet, which devastated Co Cork last October, could improve the accuracy of an AI model designed to predict future flooding events.

Several areas across Ireland have experienced significant flooding, which has had detrimental effects on residents and businesses in recent months.

To address this, CeADAR, the Irish research centre for applied AI, is developing an early warning system for communities that are at risk of severe flooding.

The project is part of a €9m initiative, led by University College Dublin, to create an Earth observations sector in Ireland.

Researchers at the centre used data collected by the European Space Agency’s Sentinel-1 satellite to map historical flooding events in flood-prone areas in the country. The project focused on areas such as Carrick-on-Shannon in Co Leitrim, Midleton in Co Cork, Athlone in Co Westmeath and Limerick City.

This data was fed into an AI model, which is designed to predict the extent of future floods. This early detection could be used to forewarn at-risk communities ahead of potential flooding and give local authorities a chance to put emergency measures in place to limit damage.

Extreme weather such as heavy rain, high winds and storms are increasing in frequency due to the climate crisis, with recent research highlighting humans’ role in this.

While there have been several storms in recent months that have caused severe damage to various parts of the country, October 2023 saw particularly devastating flood damage in Cork.

Storm Babet brought knee-high flooding to parts of the county, particularly in Midleton where hundreds of buildings were flooded and millions of euro worth of damage occurred.

Dr Omid Memarian Sorkhabi, a postdoctoral researcher leading the development of the AI model at CeADAR, said that data gleaned from Storm Babet could help refine the model and improve its accuracy, which could go a long way towards early warnings of similar events in the future.

“Flooding events like the one that hit Midleton during Storm Babet are devastating for households and businessowners whose properties are worst affected. The silver lining is that Sentinel-1 was right over the area at the time so we have gathered a lot of valuable data that will help predict the extent of the next event and ensure that future damage is limited,” he said.

“We’re in the process of developing, testing and validating the tool. But there’s huge potential for it to be made available to local authorities and other research projects. There is also a global scope to this. Sentinel-1 is always monitoring, so there’s a lot of historical data on other parts of the world on which we could train and expand the model.”

‘An invaluable resource’

The project is funded by the Department of Enterprise, Trade and Employment, and Enterprise Ireland under the Disruptive Technology Innovation Fund.

Dr Oisín Boydell, director of applied research at CeADAR, said the project has major implications for communities in areas at high risk of flooding.

“Predicting when and where a flood will strike allows time to organise mitigation measures, like preparing sandbags and evacuating people and livestock from certain areas. Traditionally, flood prediction and mapping would have been based on weather models and low-resolution elevation maps, whereas this one is very much data driven, based on events over the past decade and the current situation in a given area,” he said.

“This creates an accuracy level that’s down to approximately 20 metres. The fine-grained and detailed picture would be an invaluable resource for many and we look forward to seeing it scaled up in the coming years.”

AI is also being used further afield as a way to help boost weather predictions. In November last year, Google-owned DeepMind claimed its AI model GraphCast could make accurate predictions of the weather in less than one minute and give earlier warnings of extreme storms, while IBM announced an expanded collaboration with NASA to work on a foundation model aimed at making weather and climate applications faster, more accurate and more accessible.

10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.

Jenny Darmody is the editor of Silicon Republic