<![CDATA[Indonesia is located in the Pacific Ring of Fire, so it often experiences earthquakes that have the potential to cause tsunamis. This study aims to evaluate the performance of Support Vector Machine (SVM) in predicting potential tsunamis in Indonesia using the knowledge discovery in databases method which includes data collection, processing, transformation, data mining, and evaluation. The data were taken from BMKG and categorized based on the depth and magnitude of the earthquake. SVM models were tested with various kernels such as Linear, Polynomial, RBF, and Sigmoid to determine the best performance. The results showed that the Polynomial kernel gave the highest accuracy of 97%, with 99% precision, 94% recall, and 97% F1-score. This model is expected to contribute to the tsunami early warning system in Indonesia and improve disaster mitigation.]]>
Copyrights © 2024
