Preprints
https://doi.org/10.5194/nhess-2024-72
https://doi.org/10.5194/nhess-2024-72
13 May 2024
 | 13 May 2024
Status: this preprint is currently under review for the journal NHESS.

Advancing nearshore and onshore tsunami hazard approximation with machine learning surrogates

Naveen Ragu Ramalingam, Kendra Johnson, Marco Pagani, and Mario Martina

Abstract. Probabilistic tsunami hazard and risk assessment (PTHA and PTRA) are vital methodologies for computing tsunami risk and prompt measures to mitigate impacts. At large regional scales, their use and scope are currently limited by the computational costs of numerically intensive simulations behind them, which may be feasible only with advanced computational resources like high-performance computing (HPC) and may still require reductions in resolution, number of scenarios modelled, or use of simpler approximation schemes. To conduct PTHA and PTRA for large proportions of the coast, we therefore need to develop concepts and algorithms for reducing the number of events simulated and for more efficiently approximating the needed simulation results. This case study for a coastal region of Tohoku, Japan, utilises a limited number of tsunami simulations from submarine earthquakes along the subduction interface to build a wave propagation and inundation database and fits these simulation results through a machine learning-based variational encoder-decoder model. This is used as a surrogate to predict the tsunami waveform at the coast and the maximum inundation depths onshore at the different test sites. The performance of the surrogate models was assessed using a 5-fold cross validation assessment across the simulation events. Further to understand its real world performance and test the generalisability of the model, we used 5 very different tsunami source models from literature for historic events to further benchmark the model and understand its current deficiencies.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Naveen Ragu Ramalingam, Kendra Johnson, Marco Pagani, and Mario Martina

Status: open (until 24 Jun 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Naveen Ragu Ramalingam, Kendra Johnson, Marco Pagani, and Mario Martina
Naveen Ragu Ramalingam, Kendra Johnson, Marco Pagani, and Mario Martina

Viewed

Total article views: 236 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
179 52 5 236 11 5 7
  • HTML: 179
  • PDF: 52
  • XML: 5
  • Total: 236
  • Supplement: 11
  • BibTeX: 5
  • EndNote: 7
Views and downloads (calculated since 13 May 2024)
Cumulative views and downloads (calculated since 13 May 2024)

Viewed (geographical distribution)

Total article views: 236 (including HTML, PDF, and XML) Thereof 236 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 May 2024
Download
Short summary
By combining limited tsunami simulations with a machine learning, we developed a fast and efficient framework to predict tsunami impacts such as wave heights and inundation depths along different coastal regions. 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, essential for tsunami risk evaluations and enhancing coastal disaster preparedness.
Altmetrics