<![CDATA[This study aims to implement the K-Means Clustering algorithm for geospatial mapping of plantation commodities in Bireuen Regency. The dataset consists of 255 records collected from 17 sub-districts during the 2020–2024 period, obtained from the Bireuen Regency Plantation Office. The analyzed commodities include rubber (Hevea brasiliensis), nutmeg (Myristica fragrans), and sugar palm (Arenga pinnata). The clustering variables comprise the area of immature plants (TBM), productive plants (TM), damaged plants (TR), production yield, and productivity per hectare. The data were normalized using the Min-Max Scaling method before being grouped into three clusters (low, medium, and high) using the K-Means algorithm. Clustering performance was evaluated using the Silhouette Score and Davies–Bouldin Index (DBI). The results indicate that the sugar palm commodity achieved the best clustering performance, with Silhouette Scores ranging from 0.7493 to 0.8824 and DBI values from 0.0000 to 0.4080. Rubber produced its best result in 2021 with a DBI of 0.4705, while nutmeg also demonstrated good clustering quality. The clustering results were visualized as geospatial choropleth maps using GeoPandas and integrated into a Flask-based Web GIS. The findings demonstrate that the proposed system effectively supports plantation commodity classification and provides reliable geospatial information to assist data-driven plantation planning and resource allocation in Bireuen Regency.]]>
Copyrights © 2026
