SavedAdd your journal

Journals / International Journal of New Findings in Engineering, Science and Technology / 2026 / Cilt: 4 Sayı: 2

Machine Learning–Based Earthquake Probability Prediction for Istanbul Province

İstanbul Bölgesi için Makine Öğrenmesi Tabanlı Deprem Tahmini

Melih Karagöz(İSTANBUL GEDİK ÜNİVERSİTESİ)
Gizem Korkmaz(İSTANBUL GEDİK ÜNİVERSİTESİ)
Ceren Özmen(İSTANBUL GEDİK ÜNİVERSİTESİ)
Turgut Pura(İSTANBUL GEDİK ÜNİVERSİTESİ)0000-0002-4108-8518
Pages
26–42
Publication Date
2026-09-29
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Comparative analyses demonstrated that the Random Forest model achieved the best overall performance.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Turkey’s mountainous topography, young geological structure, and active tectonic plate movements create conditions in which earthquakes occur frequently and often cause severe damage.
📊
Key Findings & Data:In this study, geological and seismic data were used to predict whether earthquakes with a magnitude of M ≥ 3.5 would occur within the next seven days for Istanbul province in the Marmara Region.
💡
Conclusion & Impact:Comparative analyses demonstrated that the Random Forest model achieved the best overall performance.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Deprem · Makine Öğrenmesi · Random Forest

Abstract

Turkey’s mountainous topography, young geological structure, and active tectonic plate movements create conditions in which earthquakes occur frequently and often cause severe damage. In particular, the Marmara, Aegean, and Eastern Anatolia regions stand out as high-risk areas due to both dense fault systems and population distribution. In order to reduce the destructive impacts of earthquakes and implement effective mitigation measures, the ability to forecast seismic events in advance is of critical importance. In this study, geological and seismic data were used to predict whether earthquakes with a magnitude of M ≥ 3.5 would occur within the next seven days for Istanbul province in the Marmara Region. Machine learning models were trained using Random Forest, Support Vector Machines (SVM), and Long Short-Term Memory (LSTM) algorithms, and their performances were evaluated on a test dataset. Comparative analyses demonstrated that the Random Forest model achieved the best overall performance. Model effectiveness was assessed using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²), and the Random Forest model exhibited a more stable and consistent predictive capability compared to the other approaches. The results of this machine learning–based analysis indicate that the proposed method can generate meaningful probabilistic estimates for the occurrence of earthquakes with a magnitude of M ≥ 3.5 within a seven-day period for a selected district in Istanbul, highlighting its potential contribution to short-term seismic risk assessment.

Özet

Türkiye’nin dağlık yapısı, genç jeolojik oluşumu ve aktif levha hareketleri depremlerin bu bölgede sık ve yıkıcı olmasına zemin hazırlamaktadır. Özellikle Marmara, Ege ve Doğu Anadolu bölgeleri, hem fay yoğunluğu hem de nüfus dağılımı nedeniyle yüksek risk içeren alanlar olarak öne çıkmaktadır. Depremlerin oluşturduğu yıkımları azaltmak ve önlemler alabilmek için depremin önceden tahmin edilebilmesi büyük önem taşımaktadır. Bu çalışmada Marmara Bölgesi’ndeki İstanbul ili için jeolojik ve sismik veriler kullanılarak M >= 3.5 büyüklüğündeki depremlerin önümüzdeki 7 gün içerisinde meydana gelip gelmeyeceğinin tahmin edilmesi amaçlanmıştır. Random Forest, SVM, LSTM algoritmaları kullanılarak eğitim seti ile modeller eğitilmiş, eğitilen modeller test verisi ile test edilmiştir.Bu testler karşılaştırıldığında en iyi performansı gösteren modelin Random Forest olduğu görülmüştür.Ortalama mutlak hata (MAE), Kök Ortalama Kare Hata (RMSE), R2 (belirlilik katsayısı) değerleri ile model performansı karşılaştırıldığında Random Forest modeli genel ve kararlı bir yaklaşım göstermiştir.Yapılan makine öğrenmesi çalışmasıyla, İstanbul ilindeki seçilen bir ilçe için M >= 3.5 büyüklüğünde 7 günlük periyotta deprem olma olasılığını tahmin etmesi açısından anlamlı sonuçlar üretebileceğini göstermektedir.

🔖

Cite This Article

Karagöz, M., Korkmaz, G., Özmen, C., Pura, T. (2026). Machine Learning–Based Earthquake Probability Prediction for Istanbul Province. International Journal of New Findings in Engineering, Science and Technology, Cilt: 4 Sayı: 2, 26–42. https://doi.org/10.61150/ijonfest.1860675

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Demirelli, E., Solak, H. İ., & Tiryakioglu, İ. (2023). Makine öğrenmesi algoritmaları ile deprem katalogları kullanılarak deprem tahmini. Gümüşhane Üniversitesi Fen Bilimleri Dergisi 13(4), 979-989. https://doi.org/10.17714/gumusfenbil.1268504
  2. Doğan, A. (2023). Makine öğrenimi yöntemleri kullanılarak Türkiye’nin kuzeybatısı için deprem tahmini. Yerbilimleri, 44(2), 166-178. https://doi.org/10.17824/yerbilimleri.1325321
  3. Afet ve Acil Durum Yönetimi Başkanlığı. Türkiye’de afet yönetimi ve doğa kaynaklı afet istatistikleri. AFAD, Ankara, 2018. https://www.afad.gov.tr/kurumlar/afad.gov.tr/35429/xfiles/turkiye_de_afetler.pdf
  4. Moustra, M., N. Avraamides, M., & C. Christodoulou, C. (2011). Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals. Expert Systems with Applications, 38(12), 15032-15039. https://doi.org/10.1016/j.eswa.2011.05.043
  5. Kong, Q., Trugman, D. T., Ross, Z. E., Bianco, M. J., Meade, B. J., & Gerstoft, P. (2018). Machine learning in seismology: Turning data into insights. Seismological Research Letters, 90(1), 3-14. https://doi.org/10.1785/0220180259
  6. Bergen, K. J., Johnson, P. A., de Hoop, M. V., & Beroza, G. C. (2019). Machine learning for data-driven discovery in solid Earth geoscience. Science, 363(6433). https://doi.org/10.1126/science.aau0323
  7. Jiao, P., & Alavi, A. H. (2020). Artificial intelligence in seismology: Advent, performance and future trends. Geoscience Frontiers, 11(3), 739-744. https://doi.org/10.1016/j.gsf.2019.10.004
  8. Beroza, G. C., Segou, M., & Mostafa Mousavi, S. (2021). Machine learning and earthquake forecasting—next steps. Nature Communications, 12(1). https://doi.org/10.1038/s41467-021-24952-6
  9. Mousavi, S. M., & Beroza, G. C. (2023). Machine Learning in Earthquake Seismology. Annual Review of Earth and Planetary Sciences, 51(1), 105-129. https://doi.org/10.1146/annurev-earth-071822-100323
  10. Dascher‐Cousineau, K., Shchur, O., Brodsky, E. E., & Günnemann, S. (2023). Using Deep Learning for Flexible and Scalable Earthquake Forecasting. Geophysical Research Letters, 50(17). https://doi.org/10.1029/2023gl103909
  11. Zhang, H., Ke, S., Liu, W., & Zhang, Y. (2024). A combining earthquake forecasting model between deep learning and epidemic-type aftershock sequence (ETAS) model. Geophysical Journal International, 239(3), 1545-1556. https://doi.org/10.1093/gji/ggae349
  12. Dervisi, F., Segou, M., Poli, P., Baptie, B., Main, I., & Curtis, A. (2025). Towards a deep learning approach for short-term data-driven spatiotemporal seismicity rate forecasting. Earth, Planets and Space, 77(1). https://doi.org/10.1186/s40623-025-02241-6
  13. Pura, T., Güneş, P., Güneş, A., & Hameed, A. A. (2023). Earthquake Prediction for The Marmara Region of Düzce Province Using Artificial Intelligence. Applied Sciences 2023, 13(15), 8642. https://doi.org/10.20944/preprints202306.0671.v1
  14. Çam, H., & Duman, O. (2016). Yapay sinir ağı yöntemiyle deprem tahmini: Türkiye batı anadolu fay hattı uygulaması. Gümüşhane Üniversitesi Sosyal Bilimler Dergisi, 7(17), 227-248
  15. Can, C., Ergun, G., & Gokceoglu, C. (2014). Prediction of earthquake hazard by hidden Markov model (around Bilecik, NW Turkey). Open Geosciences, 6(3). https://doi.org/10.2478/s13533-012-0180-1
  16. Asencio–Cortés, G., Morales–Esteban, A., Shang, X., & Martínez–Álvarez, F. (2018). Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure. Computers & Geosciences, 115, 198-210. https://doi.org/10.1016/j.cageo.2017.10.011
  17. Mallouhy, R., Jaoude, C. A., Guyeux, C., & Makhoul, A. (2019). Major earthquake event prediction using various machine learning algorithms. 2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), 1-7. https://doi.org/10.1109/ict-dm47966.2019.9032983
  18. Sadhukhan, B., Chakraborty, S., & Mukherjee, S. (2023). Predicting the magnitude of an impending earthquake using deep learning techniques. Earth Science Informatics, 16(1), 803-823.