This study highlights the integration of ArcGIS and Deep Learning models to advance coastal flood risk prediction and prevention. By combining spatial analysis with predictive modeling, the proposed approach improves the accuracy and resolution of flood mapping, supporting faster and more effective disaster preparedness. Our results demonstrate that the model can be adapted to prioritize precision, recall, or balance, depending on application needs. This integrated method shows strong potential for expanding to other vulnerable coastal areas, contributing to enhanced global flood resilience.
Keywords
Acknowledgement
This research was funded by the Ministry of Trade, Industry, and Energy (MOTIE) of Korea under the "Regional Innovation Cluster Development Program (PN92750, P0025418)", supervised by the Korea Institute for Advancement of Technology (KIAT). And This research was supported by an in-house grant from KIOST (PEA0331, Research of prediction techniques to reduce damage from marine disasters)