Effective emergency shelter planning is essential for reducing flood impacts and improving disaster response.
This study presents an integrated framework combining machine learning algorithms and clustering techniques to identify suitable temporary shelter locations in flood-prone urban areas. The proposed approach integrates flood susceptibility assessment, spatial analysis, and accessibility considerations to support more informed decision-making.
The results demonstrate the potential of geospatial artificial intelligence approaches for enhancing flood risk management and urban resilience. This work contributes to the development of practical decision-support frameworks for disaster preparedness and emergency planning.
Integrated Machine-Learning and Clustering Framework for Flood Emergency Shelter Selection
Flood disasters pose significant challenges for urban resilience and emergency management. This research introduces a data-driven framework integrating machine learning and spatial clustering approaches to support the selection of temporary shelters in flood-prone cities.