Comparative Analysis of SVM and RF Algorithms for Tsunami Prediction: A Performance Evaluation Study

Abstract

This study explores the use of machine learning algorithms, specifically SVM and RF, for predicting tsunamis, a crucial aspect of disaster management. The research utilized earthquake data from 2001 to 2023, evaluating these models based on accuracy, precision, recall, F1-score, and ROC AUC, emphasizing features like magnitude, depth, and alert levels. The SVM model demonstrated an accuracy of 65.61%, precision of 70.59%, recall of 19.67%, F1-score of 30.77%, and ROC AUC of 62.15%. In comparison, the RF model showed an accuracy of 61.15%, precision of 50.00%, higher recall of 36.07%, F1-score of 41.90%, and ROC AUC of 63.84%. These results highlight the distinct strengths of each model: SVM's precision makes it suitable for minimizing false positives, while RF's higher recall indicates its effectiveness in detecting actual tsunamis. The findings underscore the significance of selecting the appropriate model for tsunami prediction based on specific disaster management needs and the inherent trade-offs in model selection. The research concludes that SVM and RF models provide valuable yet distinct contributions to tsunami prediction. Their application should be customized to disaster management requirements, balancing accuracy and operational efficiency. This study contributes to disaster risk management and opens avenues for further research in enhancing the accuracy and reliability of machine learning in natural disaster prediction and response systems.