Search the EPA Research Database

Project title

State-of-the-art early-warning flood prediction system for Ireland: design, implementation and computational modules

Primary Funding Agency

Irish Research Council

Co-Funding Organisation(s)

Lead Organisation

University of Galway

Lead Applicant

Not listed

Project Abstract

There is an urgent need to identify flood risks as flooding is one of the main hazards responsible for significant losses to human lives and socioeconomics. In 1995-2015, over 109million of people were affected by floods, with annual damages over US $75billion. Flood short- and long-term forecasting models are of significant importance for water recourses management, hazard assessment, policy suggestion, and extreme events management. In addition, climate change is fueling the concerns. Projected increases in rainfall, sea level and storm winds are likely to escalate the risk of flooding in the future. Consequently, an in-depth understanding of flood mechanisms and extent under various climate scenarios are needed. In this context, the aim of this research is to generate a significant step forward in our understanding of conditions under which coastal-fluvial floods occur, and to quantify extent of flood inundation under various climate scenarios and combinations of flood drivers. In this study, flood risk maps will be produced with limited hydraulic and hydrological data using different Machine Learning (ML) models as well as signal processing techniques. The main contribution of this study will be to demonstrate the state of the art of these models in flood prediction systems and to give insight into the most suitable models in terms of robustness, accuracy, effectiveness, and speed. Furthermore, the major trends in improving the quality of the flood prediction models will be investigated. To evaluate model performance, different statistical skill scores will be computed. The toolbox will be utilized and tested for the case of Cork, located in south-west of Ireland, which has a long history of coastal-fluvial flooding. The early-warning system methodology and toolbox will have a potential to be used to inform and guide hydrologists, local authorities and flood risk management agencies on flood risk detection as well as climate scientists.

Grant Approved

�105,604.00

Research Hub

Climate Change

Research Theme

3. Climate Solutions, Transition Management and Opportunities

Start Date

01/09/2023

Initial Projected Completion Date

31/08/2023