Seismic Microzonation and Earthquake Forecasting in Western Anatolia Using K-Means Clustering and Entropy-Based Magnitude Volatility Analysis

KARAKAVAK H. N., ÖNCEL ÇEKİM H., ÖZEL KADILAR G., Tekin S.

GEOTECHNICAL AND GEOLOGICAL ENGINEERING, no.2, 2025 (ESCI) identifier

  • Publication Type: Article / Article
  • Publication Date: 2025
  • Doi Number: 10.1007/s10706-024-03062-2
  • Journal Name: GEOTECHNICAL AND GEOLOGICAL ENGINEERING
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Aerospace Database, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Compendex, Computer & Applied Sciences, Geobase, INSPEC, Metadex, Civil Engineering Abstracts
  • Hacettepe University Affiliated: Yes

Abstract

Western Anatolia stands out as one of the globally active seismic regions. Characterized by significant tectonic activity and complex fault systems, this region has not been studied in detail so far. For this purpose, earthquakes from 1900 to 2021 are classified using the k-means clustering algorithm. For each determined cluster, seismic pattern variability is evaluated in detail with approximate and sample entropy methods. The study reveals distinct spatial patterns in earthquake magnitudes and depths by investigating sub-regional seismicity. Furthermore, long short-term memory models are used to predict mean earthquake magnitudes. The findings indicate regional heterogeneity, with the second cluster showing the highest magnitudes and emphasizing higher seismic risk. This study provides new insights into earthquake prediction in Western Anatolia by integrating clustering, machine learning and entropy-based techniques for a comprehensive seismic hazard assessment and sets an example for other active fault zones to be examined with similar stages.