AI Model Developed to Provide Early Warning System for Flooding in Cork
Researchers at CeADAR, Ireland’s centre for applied AI, have developed an Artificial Intelligence (AI) model that can act as an early warning system for communities at risk of flooding in areas like Midleton, Cork. The AI model utilizes data collected by the European Space Agency‘s Sentinel-1 satellite to map historical flooding events in various locations across Ireland, including Midleton, Carrick-on-Shannon, Athlone, and Limerick City.
The primary purpose of this AI model is to provide local authorities with advanced notice of heavy rain periods, enabling them to implement emergency measures to minimize damage to homes, businesses, and livestock, as well as evacuate residents if necessary. By analyzing the satellite data and predicting the extent of future flooding events, the model can accurately forecast flooding up to a distance of around 20 meters.
Dr. Omid Memarian Sorkhabi, the post-doctoral researcher spearheading the development of the AI model, monitored the flooding in Midleton during Storm Babet in real-time using the Sentinel-1 satellite. This satellite employs advanced radar technology to measure soil moisture and water bodies, even during cloudy or nighttime conditions. The data gathered during the storm will contribute to refining and enhancing the accuracy of the AI model.
Dr. Sorkhabi expressed the potential of the AI model in preventing future damage caused by flooding, stating, 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.
The director of applied research at CeADAR, Dr. OisÃn Boydell, highlighted the significance of this AI project for flood-prone communities. He acknowledged the increasing prevalence of floods in the country and the urgency to address them due to the escalating climate change situation. Dr. Boydell emphasized the need for accurate flood prediction to enable effective mitigation measures, such as preparing sandbags, evacuations, and protecting both people and livestock.
Traditionally, flood prediction and mapping relied on weather models and low-resolution elevation maps. However, this new AI model is data-driven, drawing upon events from the past decade and current conditions in a specific area. This approach provides a fine-grained and detailed picture of flood risks, offering invaluable resources for local authorities and communities. The goal is to scale up and expand the use of this AI model in the coming years.
The project is supported by the Department of Enterprise, Trade and Employment and Enterprise Ireland under the Disruptive Technology Innovation Fund. This funding reflects the importance of leveraging AI technology to address critical issues like flooding.
With its ability to provide early warnings and accurate flood predictions, the AI model developed by CeADAR holds great potential in safeguarding vulnerable communities at risk of flooding. By using advanced satellite data and applying AI algorithms, this system can offer valuable insights that enable proactive measures to mitigate the impact of floods, protect properties, and safeguard lives. As climate change continues to exacerbate extreme weather events, innovations like these are crucial for building resilience and enhancing disaster preparedness worldwide.
