Spatio-Temporal Clustering and Mechanism Analysis of the 2018 Palu Earthquake Sequence


Simanjuntak A. V. H., ANSARI K., Mase L. Z., Setiadi T. A. P., Muksin U.

Geotechnical and Geological Engineering, cilt.43, sa.8, 2025 (ESCI) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 43 Sayı: 8
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s10706-025-03350-5
  • Dergi Adı: Geotechnical and Geological Engineering
  • Derginin Tarandığı İndeksler: 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
  • Anahtar Kelimeler: Banggai earthquake, Bayesian inversion, LSTM forecasting, Mamuju earthquake, Palu earthquake, STDM clustering, Sulawesi, Supershear
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

Sulawesi Island in eastern Indonesia exhibits a distinctive K-shaped seismic pattern marked by destructive earthquakes, extensive damage, and subaerial landslide-induced tsunamis (SLTs). The 2018 Palu earthquake (Mw 7.5) alone triggered over 1000 aftershocks in five years and was likely followed by the 2019 Banggai (Mw 6.9), 2021 Mamuju (Mw 6.25), and a seismic swarm in Mamasa. This study investigates the spatio-temporal evolution and source mechanisms of these events using stochastic moment tensor inversion with rotated regional-teleseismic waveform data recorded up to 5000 km from the epicenters. An earthquake catalog (2018-2022) was analyzed using clustering in space-time-depth-magnitude (STDM) domains to identify seismic patterns and discontinuities. The identified breakpoints help differentiate foreshocks, mainshocks, and aftershock sequences. In addition, a Long Short-Term Memory (LSTM) neural network was used to model and predict linearized STDM series. Results show distinct mechanisms among major events, and the LSTM model demonstrates potential for forecasting future seismic trends. These findings contribute to a better understanding of complex seismic behavior along the Palu-Koro Fault system and provide insights into earthquake hazard mitigation in eastern Indonesia.