Predicting the Characteristics of Tsunamis Using Machine Learning

Shuchen Lu

2024

Abstract

This study examines the pressing need to advance tsunami prediction methods, emphasizing the drawbacks of existing strategies and the potential of machine learning. Accurate forecasting is crucial for risk management because tsunamis are a global threat with brief warning times. Since existing methods—like analytical and empirical modelling—have shortcomings, new approaches need to be looked into. This study uses a large historical dataset spanning 1800 to 2024 and focuses on seismic characteristics and maximum water height. The methodology makes use of a random forest regression model that integrates machine learning, data exploration, and visualization. Among the results are informative bar charts, heat maps, interactive maps, and dependable machine-learning models with low mean square error. The discussion emphasizes the importance of specific tsunami incidents, the impact of geo-visualization on vulnerability assessment, and the efficacy of machine learning models. While acknowledging the limitations of the models, the paper emphasizes the interdisciplinary nature of the results and their practical significance for disaster management. The conclusions highlight the study’s combined contributions to academic understanding and practical application, and they also project future developments in predictive models and their continuous improvement to improve response to disasters globally.

Paper Citation

in Harvard Style

Lu S. (2024). Predicting the Characteristics of Tsunamis Using Machine Learning. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 293-298. DOI: 10.5220/0012827900004547

in Bibtex Style

@conference{icdse24,
author={Shuchen Lu},
title={Predicting the Characteristics of Tsunamis Using Machine Learning},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={293-298},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012827900004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Predicting the Characteristics of Tsunamis Using Machine Learning
SN - 978-989-758-690-3
AU - Lu S.
PY - 2024
SP - 293
EP - 298
DO - 10.5220/0012827900004547
PB - SciTePress