Articles | Volume 25, issue 5
https://doi.org/10.5194/nhess-25-1655-2025
https://doi.org/10.5194/nhess-25-1655-2025
Research article
 | 
09 May 2025
Research article |  | 09 May 2025

Advancing nearshore and onshore tsunami hazard approximation with machine learning surrogates

Naveen Ragu Ramalingam, Kendra Johnson, Marco Pagani, and Mario L. V. Martina

Data sets

Geoclaw inputs and processed outputs used in building tsunami ML surrogates for nearshore and onshore approximation Naveen Ragu Ramalingam https://doi.org/10.5281/zenodo.10817116

Copernicus Global Digital Elevation Model European Space Agency https://doi.org/10.5069/G9028PQB

Modelling study data Japan Cabinet Office https://www.geospatial.jp/ckan/organization/naikakufu-002

Observed water level, astronomical tide level, and tidal level deviation data from the 2011 off the Pacific coast of Tohoku Earthquake Tsunami NOWPHAS (Nationwide Ocean Wave information network for Ports and HArbourS) https://nowphas.mlit.go.jp/pastdata

2011 Tohoku Earthquake Tsunami field survey results CEC (Coastal Engineering Committee, Japan Society of Civil Engineers) https://www.coastal.jp/tsunami2011

Model code and software

naveenragur/tsunami-surrogates: nhess-2024-72 Naveen Ragu Ramalingam https://doi.org/10.5281/zenodo.15337936

Download
Short summary
By combining limited tsunami simulations with machine learning, we developed a fast and efficient framework to predict tsunami impacts such as wave heights and inundation depths at different coastal sites. Testing our model with historical tsunami source scenarios helped assess its reliability and broad applicability. This work enables more efficient and comprehensive tsunami hazard modelling workflow, which is essential for tsunami risk evaluations and enhancing coastal disaster preparedness.
Share
Altmetrics
Final-revised paper
Preprint