AI to be used in early warning system for flood-prone areas
Athlone was one of four areas around the county which was studied by Ireland's centre for Applied Artificial Intelligence in the development of a sophisticated early warning system for communities at risk of severe flooding.
The new system, which was developed by CeADAR, uses a combination of artificial intelligence (AI) and satellite technology, and is designed to predict the extent of future flooding events in flood-prone regions across the country with researchers saying it is accurate up to a distance of approximately 20 metres.
It is hoped that the new model can soon be used to forewarn threatened communities ahead of periods of heavy rainfall, giving local authorities time to implement emergency measures to limit damage to homes and businesses, evacuate residents and protect livestock.
As well as conducting studies in Athlone as part of the project, CeADAR also examined ares of Carrick-on-Shannon in Leitrim; Midleton in Cork and Limerick City.
The flood prediction model forms part of CAMEO, a €9 million project being led by UCD to develop an Earth Observations (EO) services sector in Ireland. The overall project is being jointly funded by the Department of Enterprise, Trade and Employment and Enterprise Ireland.
The development of an early warning system for flood-prone communities comes at a time when flooding in Ireland is predicted to worsen due to climate change, with increasing concentrations of greenhouse gas emissions leading to more intense precipitation events during winter, worse floods in historically vulnerable areas as well as in areas that never flooded previously.
The Irish Fiscal Advisory Council has warned that extreme flooding events resulting from climate changes could cost the State around €500 million a year by the end of the decade.
Director fo Applied Research at CeADAR, Dr. Oisín Boydell, said the early-warning project being spearheaded by the organisation has “major implications” for communities in areas at high risk from flooding, and said that being able to predict when and where a flood will strike “allows time to organise mitigation measures.”
While flood risk incidents were traditionally based on weather models and low-resolution elevation maps, Dr. Boydell said new system is “very much data driven, based on events over the past decade and the current situation in a given area, and this creates an accuracy level that's down to approximately 20 metres.”
He added that the new system will be “an invaluable resource for many” and said CeADAR is looking forward to “seeing it scaled up in the coming years.”