Seismic Magnitude Prediction in Thailand Using Machine Learning
1
Issued Date
2025-01-01
Resource Type
Scopus ID
2-s2.0-105031752720
Journal Title
6th Research Invention and Innovation Congress Innovative Electricals and Electronics Ri2c 2025
Start Page
329
End Page
333
Rights Holder(s)
SCOPUS
Bibliographic Citation
6th Research Invention and Innovation Congress Innovative Electricals and Electronics Ri2c 2025 (2025) , 329-333
Suggested Citation
Wasayangkool K., Krutphong K., Napasiripakorn B., Suebyeam S., Srisomboon K., Lee W. Seismic Magnitude Prediction in Thailand Using Machine Learning. 6th Research Invention and Innovation Congress Innovative Electricals and Electronics Ri2c 2025 (2025) , 329-333. 333. doi:10.1109/RI2C67120.2025.11282810 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/115635
Title
Seismic Magnitude Prediction in Thailand Using Machine Learning
Corresponding Author(s)
Other Contributor(s)
Abstract
Earthquake prediction plays a critical role in disaster preparedness, particularly in regions with growing infrastructure and seismic vulnerability, such as Thailand. This study presents a machine learning-based framework to predict the magnitude of earthquakes using geospatial and temporal features. A dataset of seismic events from 2010 to 2023 was compiled from public sources, covering Thailand and neighboring regions. After data cleaning and feature engineering, three regression models - Linear Regression, Random Forest, and XGBoost were trained and evaluated using standard metrics: MAE, RMSE, R<sup>2</sup>, and Explained Variance Score. The results demonstrate that XGBoost significantly outperforms the other models, achieving the lowest prediction errors and highest explanatory power. Feature importance analysis confirms the influence of spatial variables such as depth and latitude over temporal features. Residual analysis further supports the reliability and stability of tree-based models, particularly in handling nonlinear relationships. This research highlights the practical applicability of machine learning for earthquake risk mitigation and provides a foundation for integrating predictive models into urban planning, early-warning systems, and disaster resilience strategies in Thailand.