Turkey's Earthquakes: Damage Prediction and Feature Significance Using A Multivariate Analysis

TL;DR

This paper uses machine learning to predict earthquake damage in Turkey, identifying key factors like magnitude and building stability, to improve disaster response and reduce fatalities.

Contribution

It introduces a multivariate analysis approach with machine learning models, especially Random Forest, for damage prediction in Turkish earthquakes, emphasizing feature importance.

Findings

Random Forest outperforms other models in damage prediction

Earthquake magnitude and building stability are primary damage determinants

Model can aid in disaster preparedness and response planning

Abstract

Accurate damage prediction is crucial for disaster preparedness and response strategies, particularly given the frequent earthquakes in Turkey. Utilizing datasets on earthquake data, infrastructural quality metrics, and contemporary socioeconomic factors, we tested various machine-learning architectures to forecast death tolls and fatalities per affected population. Our findings indicate that the Random Forest model provides the most reliable predictions. The model highlights earthquake magnitude and building stability as the primary determinants of damage. This research contributes to the reduction of fatalities in future seismic events in Turkey.