Utilizing Historical Earthquake Catalogs and GNSS Time Series for Earthquake Prediction via Deep Learning in the Bolu Region

Year 2025, Volume: 7 Issue: 3, 571 - 589

Fulya Battal Şamiloğlu , Veysel Işık , Bahadır Aktuğ , Andaç Töre Şamiloğlu

https://doi.org/10.46464/tdad.1706258

Abstract

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.

Keywords

Deep Learning , GNSS , LSTM , Stress Accumulation , Earthquake Prediction , North Anatolian Fault Zone

Bolu İli Çevresinde Geçmiş Deprem Kataloğu ve GNSS Zaman Serilerinin Derin Öğrenme ile Deprem Tahmininde Kullanımı

Abstract

Bu çalışma, Kuzey Anadolu Fay Zonu üzerindeki Bolu çevresinde, GNSS verileri ve aletsel dönem deprem katalogları kullanılarak LSTM tabanlı bir deprem tahmin modeli geliştirmeyi amaçlamaktadır. GNSS verilerinden hesaplanan stres zaman serileri modele girdi olarak verilmiş ve hiperparametre optimizasyonu ile küçük ve orta büyüklükteki depremler yüksek doğrulukla tahmin edilmiştir. Ancak, çalışma alanında M> 6.0 büyüklüğünde deprem yaşanmamış olması, modelin bu tür büyük olayları öğrenmesini sınırlamıştır. Bulgular, GNSS verilerinin stres birikimini yansıttığını ve LSTM yaklaşımıyla bütünleştirildiğinde anlamlı öngörüler sağladığını ortaya koymuştur. En iyi performansın elde edildiği parametrelerle, bölgedeki stresin 2023 yılı sonunda tekrar 65 birimin üzerine çıktığı ve yaklaşık M>5.0 büyüklüğünde bir depremin olası olduğuna işaret ettiği belirlenmiştir. Elde edilen bulgular, önerilen modelin deprem öngörüsü alanında uygulanabilirliğini ve potansiyel katkısını ortaya koymaktadır.

Keywords

Derin Öğrenme , GNSS Zaman Serileri , LSTM , Stres Birikimi , Deprem Tahmini , Kuzey Anadolu Fay Zonu

References

• AFAD, 2025. Deprem Kataloğu, T.C. İçişleri Bakanlığı Afet ve Acil Durum Yönetimi Başkanlığı, Erişim adresi: https://deprem.afad.gov.tr/event-catalog.
• Aktug B., Ozener H., Dogru A., Sabuncu A., Turgut B., Halicioglu K., Yilmaz O., Havazli E., 2016. Slip rates and seismic potential on the East Anatolian Fault System using an improved GPS velocity field, Journal of Geodynamics, Volumes 94-95, Pages 1-12, ISSN 0264-3707, https://doi.org/10.1016/j.jog.2016.01.001.
• Asim M., Khan R.A., Uddin M., 2018. Analysis of seismic data using recurrent neural networks, Microsystem Technologies, 24(12), 4959-4968, https://doi.org/10.1007/s00542-018-4085-7.
• Banna M.H.A., Tuba R.T., Tuba M., AlZain M.A., 2021. A bidirectional LSTM with attention mechanism for earthquake prediction, IEEE Access, 9, 141883-141892.
• Bao Y., Li H., Zhang Y., Wu Y., 2021. Deep learning-based earthquake prediction using geoelectric signals, IEEE Access, 9, 149182-149194.
• Barka A.A., 1992. The North Anatolian Fault Zone. Annales Tectonicae, 6; 164-195.
• Barka A., 1996. Slip distribution along the North Anatolian fault associated with the large earthquakes of the period 1939 to 1967, Bulletin of the Seismological Society of America, 86(5), 1238-1254.
• Bengio Y., 2012. Practical recommendations for gradient-based training of deep architectures, In Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, Springer.
• Bergmeir C., Benítez J.M., 2012. On the use of cross-validation for time series predictor evaluation, Information Sciences, 191, 192-213.
• Bergstra J., Bengio Y., 2012. Random search for hyper-parameter optimization, Journal of Machine Learning Research, 13, 281-305.
• Bilal M.A., Ji Y., Wang Y., Akhter M.P., Yaqub M., 2022. An early warning system for earthquake prediction from seismic data using batch normalized graph convolutional neural network with attention mechanism (BNGCNNAtt.), Sensors, 22(17); 6482.
• Bozkurt E., 2001. Neotectonics of Turkey-a synthesis, Geodinamica Acta, 14(1-3), 3-30, https://doi.org/10.1080/09853111.2001.11105302.
• Cambaz D., Kalafat D., Örgülü G., Kekovalı K., Kadirioğlu F.T., Özel N.M., Erdoğan S., 2019. Türkiye'deki deprem kayıtlarının güncellenmesi ve analizi üzerine Kandilli Rasathanesi veritabanı uygulamaları, Jeofizik Dergisi, 34(2), 45-57.
• Cheloni D., Tolomei C., Salvi S., Atzori S., Serpelloni E., 2025. Doğu Anadolu Fay Zonu boyunca GNSS ve InSAR verileriyle sismojenik segmentlerin gerinim alanlarının modellenmesi, Remote Sensing, 17(13), 2270.
• Chollet F., 2018. Deep Learning with Python. Manning Publications, Shelter Island, NY.
• Çağlayan A., Işık V., Saber R., 2019. An assessment of Holocene seismic activity on 1944 Earthquake Segment, North Anatolian Fault Zone (Turkey), Geosciences Journal, 1-18.
• Feurer M., Klein A., Eggensperger K., Springenberg J.T., Blum M., Hutter F., 2015. Efficient and robust automated machine learning, Advances in Neural Information Processing Systems (NeurIPS), 28.
• Goodfellow I., Bengio Y., Courville A., 2016. Deep Learning, MIT Press, pp 295-310.
• HGM, 2024. Türkiye Ulusal Sabit Jeodezik İstasyon Ağı-TUSAGA, Erişim adresi: https://www.harita.gov.tr/sunum/.
• Hobbs B.E., Means W.D., Williams P.F., 1976. An Outline of Structural Geology, Wiley, New York.
• Hochreiter S., Schmidhuber J., 1997. Long short-term memory, Neural Computation, 9(8), 1735-1780.
• Hofmann-Wellenhof B., Lichtenegger H., Collins J., 2001. Global Positioning System: Theory and Practice, Springer.
• Hsu C.Y., Pratomo B.A., 2022. LSTM-based deep learning for earthquake early warning system using seismic waveform data, IEEE Access, 10, 34727-34735.
• Hubert-Ferrari A., Barka A., Jacques E., Nalbant S.S., Meyer B., Armijo R., Tapponnier P., King G.C.P., 2002. Seismic hazard in the Marmara Sea region: new constraints from fault slip rates and historical earthquakes, Geophysical Journal International, 153(3), 597-622.
• Hutton L.K., Boore D.M., 1987. The ML scale in southern California, Bulletin of the Seismological Society of America, 77(6), 2074-2094.
• Hyndman R.J., Athanasopoulos G., 2018. Forecasting: Principles and Practice (2nd ed.).
• Kalafat D., Kekovalı K., Pınar A., Yılmazer M., Kara M., 2011. A revised and extended earthquake catalog for Turkey since 1900 (M ≥ 4.0), Journal of Seismology, 15(3), 609-625.
• Kanamori H., Anderson D.L., 1975. Theoretical basis of some empirical relations in seismology, Bulletin of the Seismological Society of America, 65(5), 1073-1095.
• Kavianpour S., Eshghi K., Naseri S., 2021a. Seismic data analysis using deep learning approaches: A comprehensive review, Journal of Seismology and Earthquake Engineering, 23(1), 67-89.
• Kavianpour S., Far M.H., Amini A., 2021b. Earthquake prediction using a hybrid CNN–LSTM model based on seismic time series data, Natural Hazards, 107, 1547-1569.
• Kingma D.P., Ba J.L., 2014. Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980.
• Kingma D.P., Ba J.L., 2015. Adam: A method for stochastic optimization, International Conference on Learning Representations (ICLR).
• Kreemer C., Holt W.E., Haines A.J., 2003. An integrated global model of present-day plate motions and plate boundary deformation, Geophysical Journal International, 154(1), 8-34, https://doi.org/10.1046/j.1365-246X.2003.01917.x.
• Kuna D., Narsetty S., Naveen P., 2020. Preliminary analysis of standalone Galileo and NavIC in the context of positioning performance for low latitude region, Procedia Computer Science, 171, 225-234, https://doi.org/10.1016/j.procs.2020.04.024.
• Kurt H., Cemen I., Wysession M., 2013. Seismicity and strain accumulation around the Karlıova Triple Junction (Turkey), Journal of Geodynamics, 65, 56-66.
• McClusky S., Balassanian S., Barka A., Demir C., Ergintav S., Georgiev, I., Gurkan O., Hamburger M., Hurst K., Kahle H., Kastens K., Kekelidze G., King R., Kotzev V., Lenk O., Mahmoud S., Mishin A., Nadariya M., Ouzounis A., Paradissis D., Peter Y., Prilepin M., Reilinger R., Sanli I., Seeger H., Tealeb A., Toksöz M.N., Veis G., 2000. GPS constraints on plate kinematics and dynamics in the eastern Mediterranean and Caucasus, Journal of Geophysical Research: Solid Earth, 105(B3), 5695-5719. https://doi.org/10.1029/1999JB900351.
• Özener H., Aktuğ B., Doğru A., Taşcı L., 2013. Geodetic and seismological investigation of crustal deformation near İzmir (Western Anatolia), Journal of Asian Earth Sciences, 74; 1-12.
• Quinteros Cartaya Y., Flores C.E., García A., Moreno M., 2025. A deep learning-based approach for near real-time earthquake detection and magnitude estimation using high-rate GNSS time series, Seismological Research Letters, 96(3), 1123-1140.
• Reilinger R., McClusky S., Vernant P., Lawrence S., Ergintav S., Çakmak R., Dinçer F., 2006. GPS constraints on continental deformation in the Africa-Arabia-Eurasia continental collision zone and implications for the dynamics of plate interactions, Journal of Geophysical Research: Solid Earth, 111(B5), https://doi.org/10.1029/2005JB004051.
• Seyitoğlu G., Işık V., Candan O., 2015. Bolu’nun güneyindeki Seben bölgesinde yüzeylenen genç tektonik yapılar ve aktif faylanma açısından önemi, Türk Jeoloji Bülteni, 58(2); 49-74.
• Snoek J., Larochelle H., Adams R.P., 2012. Practical Bayesian optimization of machine learning algorithms, Advances in Neural Information Processing Systems (NeurIPS), 25, 2951-2959.
• Şengör A.M.C., Özeren S., Genç T., Zor E., 2003. East Anatolian high plateau as a mantle-supported, north–south shortened domal structure, Geophysical Research Letters, 30(24); TUR 8-1–TUR 8-4.
• Yavaş C.E., Chen L., Kadlec C., Ji Y., 2024. Predictive modeling of earthquakes in Los Angeles with machine learning and neural networks, Scientific Reports, 14(1),24440.
• Zhang Y., Wang Y., Jiang H., 2019. Application of a hybrid model based on deep learning for earthquake prediction, IEEE Access, 7; 114274-114286. https://doi.org/10.1109/ACCESS.2019.2935351.
• Zheng Y., Liu F., Hsieh H.P., 2013. U-Air: When urban air quality inference meets big data, Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1436-1444.
• Zhou Y., Zhang Z., Liu Z., Chen W., 2022. Deep learning-based GNSS time series modeling for crustal deformation analysis, Journal of Geophysical Research: Solid Earth, 127(5), e2021JB023663, https://doi.org/10.1029/2021JB023663.