Building of Informatics, Technology and Science
Vol 7 No 3 (2025): December 2025

Komparasi Klasterisasi Data Historis Gempa Bumi Menggunakan DBSCAN, K-Means, dan Agglomerative Clustering

Lakeisyah, Eka Therina (Unknown)
Tania, Ken Ditha (Unknown)
Afrina, Mira (Unknown)



Article Info

Publish Date
08 Dec 2025

Abstract

Earthquakes are one of the natural disasters that are prone to occur on the island of Sumatera and pose a serious challenge because they can have a devastating impact on human life, such as loss of life, material losses, and environmental damage. Therefore, earthquake hazard zone mapping is needed to provide information about the potential and history of disasters and is an important tool for disaster mitigation efforts. This study aims to map earthquake vulnerability in Sumatra by comparing three clustering algorithms, namely DBSCAN, K-Means, and Agglomerative Clustering, based on earthquake data in Sumatra from 1973 to 2023. This is to find the best algorithm so that it can provide recommendations for appropriate earthquake risk mitigation strategies. The results show that the K-Means algorithm is the best because it obtained the highest Silhouette Coefficient value, namely 0.3948 with a total of 3 clusters. It is hoped that this research can improve understanding of earthquake hazard zones on the island of Sumatra and provide practical contributions in the form of mitigation strategy recommendations tailored to the characteristics of each cluster to support the application of this research for the government and local communities.

Copyrights © 2025






Journal Info

Abbrev

bits

Publisher

Subject

Computer Science & IT

Description

Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. ...