The Technical University of Denmark (DTU) and Jammerbugt Municipality have joined forces to establish an innovative early warning system for local flooding, designed specifically to address the unique challenges faced by residents in Aalborg, Denmark, and other areas within Jammerbugt Municipality.
Addressing Local Flooding Challenges with Advanced Technology
Living in close proximity to the Jammerbugt Bay poses a significant risk of flooding for Susanne Nielsen’s summer house in Slettestrand, North Jutland. The vulnerability to water intrusion intensifies as groundwater levels rise, putting her parents’ property at risk. To mitigate these risks and provide timely warnings to residents and decision-makers, DTU researchers have developed a sophisticated early warning system.
Unlike conventional flood warning systems that offer only generic alerts, this advanced tool offers localized predictions for flooding along rivers, streams, and coastal areas within Jammerbugt Municipality. Stakeholders can benefit from up to 48 hours’ notice of impending flooding events.
Revolutionary Approach: Wet Index and ai
At the heart of the system lies the “wet index,” a sophisticated model based on artificial intelligence (ai) that has been trained using diverse datasets, including satellite imagery, weather forecasts, ground and seawater levels, and landscape topography. This multifaceted approach allows for a nuanced understanding of water dynamics and interactions with the surrounding environment.
Associate Professor Roland Löwe, an expert in hydrology from DTU, explains the complexity of water movement in open landscapes. By employing ai and meticulously selected datasets, researchers have created a tool capable of accurately predicting local flooding events.
Trials and Future Developments
The early warning tool was successfully trialed by Jammerbugt Municipality in 2023, yielding encouraging results during the wet spring months. However, challenges arose during the drier summer months, necessitating further refinement.
Project Manager Heidi Egeberg Johansen of Jammerbugt Municipality acknowledges the tool’s potential but stresses the importance of accuracy and reliability. Plans are underway to retrain and adjust the model, with funding being sought to support ongoing development efforts.
Enhancing Water Management Strategies
In parallel with advancements in flood warning systems, DTU researchers have pioneered scientific machine-learning techniques to bolster water management strategies. By combining machine learning with scientific computing, researchers have significantly reduced computation times without compromising accuracy.
Associate Professor Allan Peter Engsig-Karup explains the benefits of this approach in predicting water movement through drainage systems. With scientific machine learning, calculations are performed up to 100 times faster than traditional methods, enabling decision-makers with real-time insights.
A New Era in Flood Resilience Planning
The integration of ai-driven solutions in flood management represents a transformative shift in resilience planning. With faster and more precise predictions, municipalities can proactively allocate resources, implement preventive measures, and adapt infrastructure to mitigate flood risks.
Roland Löwe emphasizes the practical implications of this technological advancement. By streamlining the decision-making process, communities can optimize their response strategies and enhance overall resilience to flooding events.
