Klasterisasi Kerawanan Gempa Bumi di Indonesia Menggunakan Algoritma Invasive Weed Optimization

Abadi, Muhammad Maulana Kharyska (2025) Klasterisasi Kerawanan Gempa Bumi di Indonesia Menggunakan Algoritma Invasive Weed Optimization. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) organized (4).pdf Download (1MB)
	Text (bab 1) 21082010143.-bab1.pdf Download (31kB)
	Text (bab 2) 21082010143.-bab2.pdf Restricted to Repository staff only until 23 May 2027. Download (279kB)
	Text (bab 3) 21082010143.-bab3.pdf Restricted to Repository staff only until 23 May 2027. Download (397kB)
	Text (bab 4) 21082010143.-bab4.pdf Restricted to Repository staff only until 23 May 2027. Download (3MB)
	Text (bab 5) 21082010143.-bab5.pdf Download (13kB)
	Text (daftar pustaka) 21082010143.-daftarpustaka.pdf Download (94kB)

Abstract

Earthquakes are one of the natural disasters that frequently occur in Indonesia due to its geographical position at the intersection of three major tectonic plates, resulting in a high level of earthquake risk for the country. This study aimed to cluster earthquake‐vulnerability areas in Indonesia using the Invasive Weed Optimization (IWO) algorithm, which was selected for its ability to produce more accurate clustering with optimal fitness values compared to other algorithms. Earthquake data were obtained from BMKG for the period January 2014 to November 2024, comprising 84733 events. After preprocessing, 81454 clean records were used for model development. The optimal number of clusters was determined to be four using the Elbow method. Over 70 iterations with an initial population of 20 individuals, IWO generated four vulnerability clusters: Low Vulnerability (46132 records), Very High Vulnerability (23573 records), Moderate Vulnerability (1413 records), and High Vulnerability (10336 records). Evaluation results showed that IWO outperformed other methods with Sum Square Errors of 510.513, Davies-Bouldin Index of 0.736, and Silhouette Score of 0.4927, compared to K-Means with Sum Square Errors of 512.710, Davies-Bouldin Index of 0.734, and Silhouette Score of 0.4910 and DBSCAN with Sum Square Errors of 1734.816, Davies-Bouldin Index of 1.339, and Silhouette Score of 0.4161. IWO provided the most compact and clearly separated clustering. Results were visualized in a web-based application to facilitate understanding of earthquake-prone zones and support more effective and targeted mitigation planning.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Arifiyanti, Amalia Anjani	NIDN0712089201	amalia_anjani.fik@upnjatim.ac.id
Thesis advisor	Kartika, Dhian Satria Yudha	NIDN0722058601	dhian.satria@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Muhammad Maulana

Date Deposited:

23 May 2025 04:00

Last Modified:

23 May 2025 04:00

URI:

https://repository.upnjatim.ac.id/id/eprint/36459