Utilizing Historical Earthquake Catalogs and GNSS Time Series for Earthquake Prediction via Deep Learning in the Bolu Region Bolu İli Çevresinde Geçmiş Deprem Kataloğu ve GNSS Zaman Serilerinin Derin Öğrenme ile Deprem Tahmininde Kullanımı
Turk Deprem Arastirma Dergisi, cilt.7, sa.3, ss.571-589, 2025 (Scopus, TRDizin)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 7 Sayı: 3
- Basım Tarihi: 2025
- Doi Numarası: 10.46464/tdad.1706258
- Dergi Adı: Turk Deprem Arastirma Dergisi
- Derginin Tarandığı İndeksler: Scopus, TR DİZİN (ULAKBİM)
- Sayfa Sayıları: ss.571-589
- Anahtar Kelimeler: Anahtar Kelimeler Derin öğrenme, Deep learning, Deprem tahmini, Earthquake prediction, GNSS, GNSS zaman serileri, Kuzey Anadolu Fay Zonu, LSTM, LSTM, North Anatolian Fault Zone, Stres birikimi, Stress accumulation
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Ankara Üniversitesi Adresli: Evet
Özet
This study aims to develop an LSTM-based earthquake prediction model using GNSS data and instrumental earthquake catalogs for the Bolu region, located along the North Anatolian Fault Zone. Stress time series derived from GNSS observations were used as model inputs, and with hyperparameter optimization, small and moderate magnitude earthquakes were predicted with high accuracy. However, the absence of earthquakes with magnitude M > 6.0 in the study area limited the model’s ability to learn from such large events. The findings demonstrate that GNSS data effectively reflect stress accumulation and, when integrated with the LSTM approach, can yield meaningful predictions. Using the best-performing parameters, the regional stress was observed to rise above 65 units by the end of 2023, indicating the potential for an earthquake of approximately M > 5.0. The results highlight the applicability and potential contribution of the proposed model to earthquake forecasting efforts.