<![CDATA[Forest fires are a serious problem that almost always occur in Indonesia every dry season. In 2019 and 2023, many forest fires occurred, especially in Gambus land, due to the prolonged El-Nino phenomenon. This has a negative impact on the economy, social and environment. Therefore, clustering is an important effort to find out the location of areas where forest fires occur. Clustering is a technique used in data mining which works by searching and grouping data that has the same characteristics between one data and other data obtained. This research aims to determine the results of clustering of hotspot distribution patterns in forest fires in Indonesia using the ST-DBSCAN method. The ST-DBSCAN method is a clustering method used to group data using spatial and temporal parameters. The results of this research produced five clusters, noise of 31, and silhouette coefficient of 0.401 with optimal parameters, there are Eps1 = 0.3, Eps2 = 7, and MinPts = 14.]]>
Copyrights © 2024
