Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jiko (Jurnal Informatika dan komputer)
Wahyu Sri Mulyani
Fakultas Teknologi Informasi dan Industri Universitas Stikubank (UNISBANK) Semarang
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
CLUSTERING ANALYSIS OF SIGNIFICANT WAVE HEIGHT DYNAMICS USING K-MEANS ALGORITHM IN THE SEMARANG–DEMAK COASTAL WATERS Wahyu Sri Mulyani; Aji Supriyanto
JIKO (Jurnal Informatika dan Komputer) Vol 8 No 3 (2025)
Publisher : Program Studi Teknik Informatika Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i3.10964

Abstract

Global climate change has led to an increase in the frequency and intensity of extreme events at sea, including in the Semarang-Demak coastal area. This region is highly vulnerable to the dynamics of Significant Wave Height (SWH), sea level rise, and coastal land subsidence. As a result, in addition to disrupting maritime navigation, frequent occurrences of tidal flooding (rob) have caused significant disturbances to economic activities and settlements in the coastal area. This study aims to develop a clustering model for SWH in the Semarang-Demak waters using the K-Means algorithm. The data used includes oceanographic and meteorological parameters from the Tanjung Emas Semarang Maritime Meteorological Station (BMKG) for the period 2019-2024. The clustering results show that K-Means successfully formed three clusters of sea waves representing calm, moderate, and high waves. Model evaluation using the Silhouette Score with a value of 0.725 and the Davies-Bouldin Index (DBI) of 0.425 indicates good performance, with K=3 as the optimal cluster. Temporal analysis reveals a clear seasonal pattern, where high energy conditions dominate during the west season (December-February), while calm conditions are prevalent during the east season (June-August). These findings provide a foundation for early warning systems and disaster risk management in this region, with further clustering tests using other algorithms and the need for improved data quality.
Co-Authors