Answers are grounded in this paper and cite their sources.
This study proposes a GIS and deep learning-based integrated simulation framework to enhance the prediction and management of coastal flood risks. The framework integrates spatial datasets—including digital elevation models (DEMs), storm surge data, and terrain characteristics—preprocessed through ArcGIS Pro and Jupyter-based pipelines to estimate flood heights. A hybrid deep learning model, combining convolutional neural networks (CNNs) and long short-term memory (LSTM) networks in a parallel structure, is designed to learn spatial features and temporal dynamics simultaneously from time-series flood maps. The fused output is used to generate a probabilistic flood risk index. Experimental results using coastal datasets from Busan demonstrated that the hybrid model outperformed standalone CNN and LSTM models, achieving superior macro and weighted averages across multiple performance metrics. Notably, CNN exhibited perfect recall for early warnings, while LSTM showed the highest precision for policy decision support. The hybrid model balanced both strengths, proving robust even under imbalanced data conditions. The integration with ArcGIS Pro allows for high-resolution flood visualization and intuitive risk mapping, supporting real-time alerts and disaster response planning. This approach offers strong scalability to other coastal regions and practical utility for real-world early flood warning systems and climate resilience strategies.
No takes yet. Share an insight, caveat, or question.
Park et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: