Scientific Article
- Title
- Prediction of Tsunami Alert Levels Using Deep Learning
- Authors
- M. de la Asunción — University of Málaga (EDANYA Group)
- Journal
- Earth and Space Science (AGU), Vol. 11, Issue 3, e2023EA003385
- DOI
- 10.1029/2023EA003385
- Publication date
- 20 March 2024
- Abstract
- Tsunami simulations require powerful computational resources to be performed efficiently.Although the modern graphics processing units (GPUs) allow the acceleration of this kind of simulations, theycan still last many minutes or even hours for simulations which have to deal with very high spatial resolutions orsimulation times. In this paper, we propose a method to predict the alert or inundation level of a tsunamigenerated by an earthquake using deep learning methods. In particular, we train multilayer perceptron (MLP)neural networks for predicting the alert level due to a tsunami at given coastal locations. Ensemble methods areused to improve the predictions of the neural networks. Tsunamis caused by ruptures of several fault segments atdifferent time instants, application to real events, probabilistic forecasting and comparison with other machinelearning algorithms are also addressed. Results on realistic scenarios confirm that good accuracies are obtained.The inference times of the trained networks and ensembles are also very low, lasting less than one second topredict the results of thousands of simulations. The proposed method could be used in a tsunami early warningsystem along with the application of scaling laws.
- Full text
- Read on AGU (open access)
