An integrated approach for understanding global earthquake patterns and enhancing seismic risk assessment

Ibrahim, Mariam; Al-Bander, Baidaa

Abstract

Earthquakes, as intricate natural phenomena, profoundly impact lives, infrastructure, and the environment. While previous research has explored earthquake patterns through data analysis methods, there has been a gap in examining the time intervals between consecutive earthquakes across various magnitude categories. Given the complexity and vastness of seismic data, this study aims to provide comprehensive insights into global seismic activity by employing sophisticated data analysis methodologies on a century-long dataset of seismic events. The four-phase methodology encompasses exploratory data analysis (EDA), temporal dynamics exploration, spatial pattern analysis, and cluster analysis. The EDA serves as the foundational step, providing fundamental insights into the dataset's attributes and laying the groundwork for subsequent analyses. Temporal dynamics exploration focuses on discerning variations in earthquake occurrences over time. Spatial analysis identifies geographic regions with heightened earthquake activity and uncovers patterns of seismic clustering. K-means clustering is employed to delineate distinct earthquake occurrence clusters or hotspots based on geographical coordinates. The study's findings reveal a notable increase in recorded earthquakes since the 1960s, peaking in 2018. Distinct patterns in seismic activity are linked to factors such as time, human activities, and plate boundaries. The integrated approach enriches understanding of global earthquake trends and patterns, contributing to improved seismic hazard assessments, early warning systems, and risk mitigation efforts.

Citation

Ibrahim, M., & Al-Bander, B. (2024). An integrated approach for understanding global earthquake patterns and enhancing seismic risk assessment. International Journal of Information Technology, 16(4), 2001-2014. https://doi.org/10.1007/s41870-024-01778-1

• Journal Article Type: Article
• Acceptance Date: Feb 2, 2024
• Online Publication Date: Mar 13, 2024
• Publication Date: Apr 1, 2024
• Deposit Date: May 8, 2024
• Journal: International Journal of Information Technology
• Print ISSN: 2070-3961
• Publisher: World Academy of Science, Engineering and Technology
• Peer Reviewed: Peer Reviewed
• Volume: 16
• Issue: 4
• Pages: 2001-2014
• DOI: https://doi.org/10.1007/s41870-024-01778-1
• Keywords: Seismic data, Clustering, Spatiotemporal analysis, Earthquakes, Data science analysis
• Public URL: https://keele-repository.worktribe.com/output/823714
• Publisher URL: https://link.springer.com/article/10.1007/s41870-024-01778-1