Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Current Studies in SDGs Journal of Current Studies in SDGs
Harmon Prayogi
Universitas Negeri Surabaya
Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Environmental Science Social Sciences Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Data-Driven Seismic Hazard Zonation of Indonesia to Support SDG 11 Using DBSCAN and K-Means Clustering Atik Wintarti; Fadhilah Qalbi Annisa; Harmon Prayogi; Yuliani Puji Astuti; Ibnu Febry Kurniawan
Journal of Current Studies in SDGs Vol. 2 No. 2 (2026): June
Publisher : Sekolah Tinggi Agama Islam Sabilul Muttaqin Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63230/jocsis.2.2.224

Abstract

Objective: To examine ten years of earthquake data recorded across Indonesia drawing on 5,364 events with magnitudes above M 5.0 between 2016 and 2025. Method: DBSCAN algorithm was run after the optimal neighborhood radius was determined objectively from a k-distance plot. An elbow at about 65 km was identified and the value yielded 16 spatially distinct clusters alongside 460 noise events. K-means algorithm identified four seismic regimes. Results: Of the four regimes, one cluster (Cluster 1) concentrated every major earthquake in the catalog (64 events with M >= 7.0), even though it accounted for fewer than one event in ten. The three remaining clusters captured background seismicity at near-identical mean magnitudes of approximately from 5.33 to 5.35. At the conventional zonal level, Maluku-Sulawesi generated the most events about 40.8% from total events, while Sumatra registered the highest seismic energy output. A Gutenberg-Richter b-value of 0.98 was estimated for the full catalog. Novelty: Introducing earthquake zonation methods based on machine learning for earthquake catalog of Indonesia. These findings support multiple Sustainable Development Goals including the identification of underestimated high-energy rupture corridors informs evidence-based urban risk reduction (SDG 11), strengthens the scientific foundation for earthquake disaster preparedness (SDG 13), introduces an innovative and reproducible machine learning methodology applicable to infrastructure (SDG 9), and contributes a freely transferable workflow that adopt data-driven zonation methods (SDG 17)
Data-Driven Seismic Hazard Zonation of Indonesia to Support SDG 11 Using DBSCAN and K-Means Clustering Atik Wintarti; Fadhilah Qalbi Annisa; Harmon Prayogi; Yuliani Puji Astuti; Ibnu Febry Kurniawan
Journal of Current Studies in SDGs Vol. 2 No. 2 (2026): June
Publisher : Sekolah Tinggi Agama Islam Sabilul Muttaqin Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63230/jocsis.2.2.224

Abstract

Objective: To examine ten years of earthquake data recorded across Indonesia drawing on 5,364 events with magnitudes above M 5.0 between 2016 and 2025. Method: DBSCAN algorithm was run after the optimal neighborhood radius was determined objectively from a k-distance plot. An elbow at about 65 km was identified and the value yielded 16 spatially distinct clusters alongside 460 noise events. K-means algorithm identified four seismic regimes. Results: Of the four regimes, one cluster (Cluster 1) concentrated every major earthquake in the catalog (64 events with M >= 7.0), even though it accounted for fewer than one event in ten. The three remaining clusters captured background seismicity at near-identical mean magnitudes of approximately from 5.33 to 5.35. At the conventional zonal level, Maluku-Sulawesi generated the most events about 40.8% from total events, while Sumatra registered the highest seismic energy output. A Gutenberg-Richter b-value of 0.98 was estimated for the full catalog. Novelty: Introducing earthquake zonation methods based on machine learning for earthquake catalog of Indonesia. These findings support multiple Sustainable Development Goals including the identification of underestimated high-energy rupture corridors informs evidence-based urban risk reduction (SDG 11), strengthens the scientific foundation for earthquake disaster preparedness (SDG 13), introduces an innovative and reproducible machine learning methodology applicable to infrastructure (SDG 9), and contributes a freely transferable workflow that adopt data-driven zonation methods (SDG 17)
Co-Authors Atik Wintarti Fadhilah Qalbi Annisa Ibnu Febry Kurniawan Yuliani Puji Astuti