Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods

Bengkulu is one of the provinces that lies in the ring of fire which has dynamic number of earthquakes each year. There were 2,989 earthquakes recorded in the Bengkulu from 2000 to 2021 with spatially different and unique attributes. The occurrences over Bengkulu were also included on the top twenty...

Full description

Saved in:
Bibliographic Details
Main Authors: Arie Vatresia, Ferzha Utama, Intan Hati, Lindung Mase
Format: Article
Language:English
Published: Pouyan Press 2024-07-01
Series:Journal of Soft Computing in Civil Engineering
Subjects:
Online Access:https://www.jsoftcivil.com/article_196432_c0ea8a47053a0d85f93bd9dcc9eae900.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718197098381312
author Arie Vatresia
Ferzha Utama
Intan Hati
Lindung Mase
author_facet Arie Vatresia
Ferzha Utama
Intan Hati
Lindung Mase
author_sort Arie Vatresia
collection DOAJ
description Bengkulu is one of the provinces that lies in the ring of fire which has dynamic number of earthquakes each year. There were 2,989 earthquakes recorded in the Bengkulu from 2000 to 2021 with spatially different and unique attributes. The occurrences over Bengkulu were also included on the top twenty of significant event of earthquake that caused a lot of damage and death with the highest level of magnitude (8.4 SR). Due to its novel occurrences, how the points of earthquake clustered is still an interesting research question to be answered to empowered the location to be ready for the disaster. With the accelerating movement of artificial intelligence, this research used three methods to process earthquake data (Elbow, CLARANS, and Silhouette Coefficient) to find a better understanding of the cluster’s discovery. Matuschka method was occupied to uncover the earthquakes intensity and level of damage caused by earthquakes in the areas based on the MMI scale. This research succeeded to generate the six best cluster types based on the time of occurrence and level of damage during with the information. Furthermore, this research also mapped the severity of risk over the district to see the distribution of clusters produced. This research found that the area of Rejang Lebong is the most vulnerable to the earthquake with the class of heavy damage based on MMI value. Another class that involved into moderate risk is Muko-Muko area. The Validation performance showed a value of 0.55 which involved on feasible rate.
format Article
id doaj-art-079faffd7e464f9781071e1aca727d8a
institution DOAJ
issn 2588-2872
language English
publishDate 2024-07-01
publisher Pouyan Press
record_format Article
series Journal of Soft Computing in Civil Engineering
spelling doaj-art-079faffd7e464f9781071e1aca727d8a2025-08-20T03:12:26ZengPouyan PressJournal of Soft Computing in Civil Engineering2588-28722024-07-0183718610.22115/scce.2023.381204.1589196432Discovering Bengkulu Province Earthquake Clusters with CLARANS MethodsArie Vatresia0Ferzha Utama1Intan Hati2Lindung Mase3Associate Professor, Department of Informatics, Faculty of Engineering, University of Bengkulu, Bengkulu, IndonesiaLecturer, Department of Information System, Faculty of Engineering, University of Bengkulu, Bengkulu, IndonesiaGraduate Student, Department of Informatics, Faculty of Engineering, University of Bengkulu, Bengkulu, IndonesiaAssociate Professor, Department of Civil Engineering, Faculty of Engineering, University of Bengkulu, Bengkulu, IndonesiaBengkulu is one of the provinces that lies in the ring of fire which has dynamic number of earthquakes each year. There were 2,989 earthquakes recorded in the Bengkulu from 2000 to 2021 with spatially different and unique attributes. The occurrences over Bengkulu were also included on the top twenty of significant event of earthquake that caused a lot of damage and death with the highest level of magnitude (8.4 SR). Due to its novel occurrences, how the points of earthquake clustered is still an interesting research question to be answered to empowered the location to be ready for the disaster. With the accelerating movement of artificial intelligence, this research used three methods to process earthquake data (Elbow, CLARANS, and Silhouette Coefficient) to find a better understanding of the cluster’s discovery. Matuschka method was occupied to uncover the earthquakes intensity and level of damage caused by earthquakes in the areas based on the MMI scale. This research succeeded to generate the six best cluster types based on the time of occurrence and level of damage during with the information. Furthermore, this research also mapped the severity of risk over the district to see the distribution of clusters produced. This research found that the area of Rejang Lebong is the most vulnerable to the earthquake with the class of heavy damage based on MMI value. Another class that involved into moderate risk is Muko-Muko area. The Validation performance showed a value of 0.55 which involved on feasible rate.https://www.jsoftcivil.com/article_196432_c0ea8a47053a0d85f93bd9dcc9eae900.pdfearthquakebengkuluclusteringelbowclarans
spellingShingle Arie Vatresia
Ferzha Utama
Intan Hati
Lindung Mase
Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
Journal of Soft Computing in Civil Engineering
earthquake
bengkulu
clustering
elbow
clarans
title Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
title_full Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
title_fullStr Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
title_full_unstemmed Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
title_short Discovering Bengkulu Province Earthquake Clusters with CLARANS Methods
title_sort discovering bengkulu province earthquake clusters with clarans methods
topic earthquake
bengkulu
clustering
elbow
clarans
url https://www.jsoftcivil.com/article_196432_c0ea8a47053a0d85f93bd9dcc9eae900.pdf
work_keys_str_mv AT arievatresia discoveringbengkuluprovinceearthquakeclusterswithclaransmethods
AT ferzhautama discoveringbengkuluprovinceearthquakeclusterswithclaransmethods
AT intanhati discoveringbengkuluprovinceearthquakeclusterswithclaransmethods
AT lindungmase discoveringbengkuluprovinceearthquakeclusterswithclaransmethods