<![CDATA[Clustering is a method in data mining that aims to group data based on certain similarities or characteristics. One of the clustering methods or algorithms is the Spatial-Temporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN) algorithm. This algorithm was chosen because of its ability to analyse data based on spatial and temporal dimensions simultaneously, using the parameters of spatial distance (ε₁), temporal distance (ε₂), and minimum number of points (MinPts). This study aims to determine the results of the ST-DBSCAN algorithm in clustering earthquake points in the Sulawesi Region. The data analysed is secondary data obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) for the period 2019-2023, covering 12109 earthquake points with magnitude ≥ 3 on the Richter scale. The results show that earthquake points in Sulawesi are concentrated in subduction zones and active faults. The most earthquake-prone areas include North Sulawesi and Gorontalo, which are affected by the subduction of the Pacific and Eurasian Plates. In addition, Central Sulawesi, West Sulawesi, South Sulawesi and Southeast Sulawesi are also at high risk due to the activity of the Palu-Koro Fault. Earthquake intensity around the Flores Sea and Banda Sea increases in 2021-2022 due to subduction of the Indo-Australian Plate. The optimal parameters for clustering varied every year during the study. The optimal parameters for clustering varied every year during the study period. This study provides new insights into seismic activity patterns in Sulawesi that can be utilised to support disaster mitigation and earthquake risk reduction policies.]]>
Copyrights © 2025
