<![CDATA[Tsunami impact assessment must be conducted rapidly and accurately to ensure adequate emergency risk responses and management, allowing the city to recover swiftly. Significant progress has been made in numerical analysis techniques, yielding more precise assessments and predictions of tsunami forces. However, these advancements come with high computational costs, potentially limiting their applicability for uncertainty quantification and probabilistic risk analysis. Reduced-order modeling is a numerical approach that seeks to find a model in a lower-dimensional space while still representing the physical features of the full-order model with acceptable accuracy. Proper orthogonal decomposition is one such reduced-order modeling method, widely used in various engineering fields. This study proposes a framework to estimate tsunami propagation and land inundation using a surrogate-based reduced-order modeling method. A neural network is employed as the surrogate model. Two error measures are used to analyze its performance: the root mean square error and the average relative error of projection. Results indicate that the root mean square error decreases as more bases are used. However, the average relative error of projection in the online phase does not significantly decrease with an increased number of bases, suggesting that a moderate number of basesbetween five and tenis sufficient for the proposed framework.]]>
Copyrights © 2025
