Abstract
This article proposes the mapping of earthquake potential zones in Regional Center 3 (Bali and Nusa Tenggara, Indonesia) using the clustering method. A suitable clustering method to group spatial and non-convex data, such as earthquake data, is the Density-Based Spatial Clustering of Application with Noise (DBSCAN). We modify the epsilon parameter with the magnitude because it reflects the impact of the earthquake happens so that the epsilon value will be different for each point. Before the clustering process, magnitude is converted to kilometers (km) to determine the earthquake impact region, which will be used as epsilon. The earthquake impact region is obtained by computing the radius of the earthquake using the McCue Earthquake Perception Radius equation. This approach gives a good result for mapping the potential earthquake zones indicated by the cluster validity index that gives an average higher than 0 using the Silhouette index.
Highlights
The earthquake in Bali and Nusa Tenggara (Regional Center 3), Indonesia, has increased in the last three years
The more frequent an area of earthquake tremors, it can be said that the area is a potential earthquake zone, but it is uncertain when and how significant the effect is because earthquake prediction is a difficult job
Data Preprocessing Before it is processed in the Density-Based Spatial Clustering of Application with Noise (DBSCAN) clustering, the magnitude is converted to kilometers
Summary
The earthquake in Bali and Nusa Tenggara (Regional Center 3), Indonesia, has increased in the last three years. The last earthquake that occurred at Regional Center 3 was the earthquake on July 16th, 2019, in Nusa Dua, Bali From some of these earthquake events, there needs to be a mapping of earthquake zones and affected areas. Data collection on earthquake-affected areas manually is done by visiting the earthquake location and recapitulating earthquake data that has occurred It has become the work of the Meteorology Climatology and Geophysics Council (BMKG) in general, which is to record and map the potential earthquake disasters. Several spatial pattern analysis techniques were applied, namely quadrant analysis, nearest neighbor average, global Moran's I, Getis-Ord general G, Anselin Local Moran's I, Getis-Ord Gi*, kernel density estimation, and geographical distributions Both local and global spatial statistics indicate that earthquakes in the Red Sea region are collected into several clusters. Three combinations of features were tested, namely non-spatial features, spatial features, and a combination of both, the results of predictive accuracy were not good when only spatial features were used
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Earth and Environmental Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
