Hybrid CatBoost and SVR Model for Earthquake Prediction Using the LANL Earthquake Dataset
Informatica · 04.03.2025 · 49 (14)
DOI: 10.31449/inf.v49i14.6524 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informatica, online erschienen am 04.03.2025. Verfasst von Arush Kaushal und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Earthquakes have the potential to cause catastrophic structural and economic damage. This research explores the application of machine learning for earthquake prediction using LANL (Los Alamos National Laboratory) dataset. The data, obtained from a laboratory stick-slip friction experiment, simulate real earthquakes through digitized acoustic signals recorded against the time to failure of a granular layer. We introduced a hybrid model combining CatBoost and Support Vector Regression (SVR) to predict the time of the next earthquake, evaluating its performance against individual CatBoost and SVR models. The hybrid model demonstrated superior accuracy with a Mean Absolute Error (MAE) of 0.0825, outperforming the individual models. We implemented feature engineering to optimize the predictive capability of the models. Additionally, we compared our hybrid model's performance with previous studies to validate its efficacy. Our findings underscore the potential of machine learning, particularly hybrid models, in enhancing earthquake prediction accuracy. This study highlights the robustness and effectiveness of the hybrid CatBoost-SVR model, paving the way for advanced AI algorithms in seismology and contributing to improved disaster preparedness and mitigation strategies.
Zitieren
APA
Kaushal, A., Gupta, A. K., & Sehgal, V. K. (2025). Hybrid CatBoost and SVR Model for Earthquake Prediction Using the LANL Earthquake Dataset. Informatica, 49(14). https://doi.org/10.31449/inf.v49i14.6524
Vancouver
Kaushal A, Gupta AK, Sehgal VK. Hybrid CatBoost and SVR Model for Earthquake Prediction Using the LANL Earthquake Dataset. Informatica. 2025;49(14). doi:10.31449/inf.v49i14.6524
BibTeX
@article{Kaushal2025,
author = {Kaushal, Arush and Gupta, Ashok Kumar and Sehgal, Vivek Kumar},
title = {Hybrid CatBoost and SVR Model for Earthquake Prediction Using the LANL Earthquake Dataset},
journal = {Informatica},
year = {2025},
volume = {49},
number = {14},
doi = {10.31449/inf.v49i14.6524}
}
EUVIMED