Komparasi Algoritma K-Means dan DBSCAN dalam Klasterisasi Kualitas Udara di Wilayah Jabodetabek Berdasarkan Indeks Standar Pencemar Udara

Abstract

Air quality is a critical environmental issue because it directly impacts public health and the sustainability of urban environments. The Greater Jakarta area, as a hub of economic activity and population mobility, faces high levels of air pollution; however, a comprehensive understanding of air quality patterns remains limited due to the complexity of the data and the variation in pollutant parameters. This study aims to analyze and compare the performance of clustering algorithms in grouping air quality levels based on Air Pollutant Standard Index (ISPU) data in the Greater Jakarta area. The methods used were K-Means and DBSCAN with six input parameters PM2.5, PM10, SO₂, NO₂, O₃, and CO—which underwent data preprocessing, the clustering process, and evaluation using the Silhouette Score and the Davies-Bouldin Index (DBI). The results indicate that K-Means with three clusters yields the best performance, achieving a Silhouette Score of 0.324 and a DBI of 1.142, while DBSCAN achieves a Silhouette Score of 0.013 and a DBI of 1.240. These findings indicate that K-Means is more effective in forming cohesive groupings of air quality patterns and can be utilized as a basis for decision-making in the monitoring and control of urban air quality.