Evaluation of datasets and deep learning methods used in earthquake prediction in the context of the February 6, 2023 earthquake

Yıl 2026, Cilt: 32 Sayı: 2

İlkay Sibel Kervancı

https://doi.org/10.5505/pajes.2025.71240

Öz

On February 6, 2023, Türkiye experienced its most severe earthquakes in over 80 years, beginning with a 7.8 (Mw) earthquake, followed by two consecutive 7.5 (Mw) earthquakes nine hours later. The most distinctive feature of this earthquake compared to others is not only that it was more destructive than the others, but also that its impact covered a vast geographical area. There are many studies on earthquake prediction; these studies address topics such as emergency preparations and response planning, risk analysis, or damage estimation. Due to the success of deep learning (DL) algorithms in various fields, using DL methods in earthquake prediction has become a very popular research topic in recent years. Studies using DL methods for earthquake prediction were examined in terms of the DL algorithms and data sets used, with a focus on of whether the earthquakes that occurred on February 6, 2023 and after could be predicted before the earthquake occurred. According to the findings suggest that ionospheric reactions observed before and after the earthquake and the use of the earthquake time series that occurred before the earthquake can be used to predict future earthquakes. However, these results are still preliminary predictions, therefore, it is crucial to expand the early warning system network and to increase the accuracy of real-time prediction models using DL algorithms. Additionally, this study aims to guide future research through a multidisciplinary review of the existing literature. Ultimately, such work will help improve prediction models and contribute to better preparedness for earthquake risks.

Anahtar Kelimeler

Deep learning , Earthquake prediction , February 6 , 2023 , Earthquake datasets

Deprem tahmininde kullanılan veri setleri ve derin öğrenme yöntemlerinin 6 Şubat 2023 depremi açısından değerlendirilmesi

Öz

Türkiye 6 Şubat 2023'te 7.8 (Mw) büyüklüğünde depremin ardından dokuz saat sonra büyüklüğü 7.5 (Mw) olan art arda iki deprem ile 80 yılı aşkın süredir Türkiye de yaşanan en şiddetli depremleri yaşamış oldu. Bu depremi diğer depremlerden ayıran en belirgin özellik sadece diğerlerinden daha yıkıcı olması değil aynı zamanda etki alanının oldukça geniş bir coğrafyaya yayılmış olmasıdır. Deprem tahmini ile ilgili oldukça fazla çalışma bulunmakta, bunlar acil durum hazırlıkları ve müdahale planlamaları, risk analizi veya hasar tahmini gibi konuları ele almaktadır. Derin öğrenme algoritmalarının birçok alanda elde ettiği başarılar sonucunda, deprem tahmininde derin öğrenme yöntemlerinin kullanımı son yıllarda oldukça popüler bir araştırma konusu haline gelmiştir. Deprem tahmini için derin öğrenme yöntemlerini kullanan çalışmalar incelenmiş ve bunun sonucunda kullanılan derin öğrenme algoritmaları ve veri setleri incelenerek 6 Şubat ve sonrasında gerçekleşen depremlerin, deprem gerçekleşmeden önce tahmin edilip edilemeyeceği sorusuna yanıt aranmıştır. Elde edilen bulgulara göre hem deprem öncesinde hem de sonrasında 'İyonosferik tepkilerin' varlığı ve depremden önce gerçekleşen deprem zaman serisinin kullanımı ile gelecekteki depremlerin tahminlerinin yapılabileceği sonucuna ulaşılmıştır. Ancak buralardan elde edilen sonuçlar tahmin mahiyetindedirler bu sebepten erken uyarı sistemleri ağının genişletilmesi ve gerçek zamanlı çalışan derin öğrenme algoritmaları ile yapılan tahmin sistemlerinin doğruluğunu artırmak oldukça önemlidir. Ayrıca literatürün farklı bakış açısını içeren multi disipliner yaklaşımla inceleyerek gelecekte yapılacak çalışmalara rehberlik etmek amaçlanmaktadır. Sonuç olarak bu tür bir araştırma daha iyi tahmin modelleri geliştirilmesine yardımcı olarak toplumların deprem riskine karşı daha hazırlıklı olmasına katkı sağlayacaktır.

Kaynakça

• [1] Galkina A, Grafeeva N. “Machine learning methods for earthquake prediction: A survey”. Proceedings of the fourth conference on software engineering and information management (SEIM-2019), Saint Petersburg, Russia, 2019.
• [2] United States Geological Surve, https://www.usgs.gov/ (26 06 2024).
• [3] Gürsoy G, Varol A, Nasab A. “Importance of Machine Learning and Deep Learning Algorithms in Earthquake Prediction: A Review”. 2023 11th International Symposium on Digital Forensics and Security (ISDFS), IEEE, 1-6, 2023.
• [4] Meier MA, Ross ZE, Ramachandran A, Balakrishna A, Nair S, Kundzicz P, Yue Y. “Reliable Real-Time Seismic Signal/Noise Discrimination With Machine Learning”. Journal of Geophysical Research: Solid Earth, 124(1), 788-800, 2019.
• [5] Wang Q, Guo Y, Yu L, Li P. “Earthquake prediction based on spatio-temporal data mining: an LSTM network approach”. IEEE Transactions on Emerging Topics in Computing, 8(1), 148-158, 2017.
• [6] Rundle JB, Donnellan A, Fox G, Crutchfield JP. “Nowcasting Earthquakes by Visualizing the Earthquake Cycle with Machine Learning: A Comparison of Two Methods”. Surveys in Geophysics, 43(2), 483-501, 2022.
• [7] Kervanci IS, Akay MF, Özceylan E. “Bitcoin price prediction using LSTM, GRU and hybrid LSTM-GRU with bayesian optimization, random search, and grid search for the next days”. Journal of Industrial and Management Optimization, 20(2), 570-588, 2024.
• [8] Mousavi SM, Sheng Y, Zhu W, Beroza GC. “STanford EArthquake Dataset (STEAD): A global data set of seismic signals for AI”. IEEE Access, 7, 179464-179476, 2019.
• [9] Choubik Y, Mahmoudi A, Himmi MM. “Fully Convolutional Networks for Local Earthquake Detection,” International Journal of Advanced Computer Science and Applications, 12(2), 2021.
• [10] Zhang S, Ku B, Ko H. “Learnable Maximum Amplitude Structure for Earthquake Event Classification”. IEEE Geoscience and Remote Sensing Letters, 19, 1-5, 2022.
• [11] Shakeel M, Itoyama K, Nishida K, Nakadai K. “EMC: Earthquake Magnitudes Classification on Seismic Signals via Convolutional Recurrent Networks”. 2021 IEEE/SICE International Symposium on System Integration (SII), IEEE, 388-393, 2021.
• [12] Rouet‐Leduc B, Hulbert C, Lubbers N, Barros K, Humphreys CJ, Johnson PA. “Machine Learning Predicts Laboratory Earthquakes”. Geophysical Research Letters, 44(18), 9276-9282, 2017.
• [13] Corbi F, Sandri L, Bedford J, Funiciello F, Brizzi S, Rosenau M, Lallemand S. “Machine Learning Can Predict the Timing and Size of Analog Earthquakes”. Geophysical Research Letter, 46(3), 1303-1311, 2019.
• [14] Johnson PA, Rouet-Leduc B, Pyrak-Nolte LJ, Beroza, GC, Marone, CJ, Hulbert C, Reade W. “Laboratory earthquake forecasting: A machine learning competition”. Proceedings of the national academy of sciences, 118(5), e2011362118, 2021.
• [15] Juang CH, Yuan H, Lee DH, Lin PS. “Simplified cone penetration test-based method for evaluating liquefaction resistance of soils”. Journal of geotechnical and geoenvironmental engineering, 129(1), 66-80, 2003.
• [16] Goh AT, Goh S. “Support vector machines: their use in geotechnical engineering as illustrated using seismic liquefaction data”. Computers and Geotechnics, 34(5), 410-421, 2007.
• [17] Zhang J, Wang Y. “An ensemble method to improve prediction of earthquake-induced soil liquefaction: a multi-dataset study”. Neural Computing and Applications, 33, 1533–1546, 2020.
• [18] Juang C, Chen CJ. “A rational method for development of limit state for liquefaction evaluation based on shear wave velocity measurements”. International Journal for numerical and analytical methods in geomechanics, 24(1), 1-27, 2000.
• [19] Ahmad M, Tang XW, Qiu JN, Ahmad F, Gu WJ. “Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential”. Frontiers of Structural and Civil Engineering, 15, 490–505, 2021.
• [20] Asim KM, Martínez-Álvarez F, Basit A, Iqbal T. “Earthquake magnitude prediction in Hindukush region using machine learning techniques”. Natural Hazards, 85, 471–486, 2017.
• [21] Florido E, Asencio–Cortés G, Aznarte JL, Rubio-Escudero C, Martínez–Álvarez F. “A novel tree-based algorithm to discover seismic patterns in earthquake catalogs”. Computers & Geosciences, 115, 96-104, 2018.
• [22] Shodiq MN, Kusuma DH, Rifqi MG. “Neural Network for Earthquake Prediction Based on Automatic Clustering in Indonesia”. International Journal on Informatics Visualization, 2(1), 37-43, 2018.
• [23] Bao Z, Zhao J, Huang P, Yong S, Wang XA. “A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction”. Sensors, 21(13), 4434, 2021.
• [24] Öncel Çekim H, Karakavak HN, Özel G, Tekin S. “Earthquake magnitude prediction in Turkey: a comparative study of deep learning methods, ARIMA and singular spectrum analysis”. Environmental Earth Sciences, 82(16), 387, 2023.
• [25] Utku A, Akcayol MA. “Hybrid Deep Learning Model for Earthquake Time Prediction”. Gazi University Journal of Science, 37(3), 1172-1188, 2024.
• [26] Liu Y, Zhao Q, Wang Y. “Peak ground acceleration prediction for on-site earthquake early warning with deep learning”. Scientific reports, 14(1), 5485, 2024.
• [27] Senkaya M, Silahtar A, Erkan EF, Karaaslan H. “Prediction of local site influence on seismic vulnerability using machine learning: A study of the 6 February 2023 Türkiye earthquakes”. Engineering Geology, 107605, 2024.
• [28] Morales-Esteban A, Martínez-Álvarez F, Troncoso A, Justo JL, Rubio-Escudero C. “Pattern recognition to forecast seismic time series”. Expert Systems with Applications, 37(12), 8333-8342, 2012.
• [29] Asencio-Cortes G, Martinez-Alvarez F, Troncoso A, Morales-Esteban A. “Medium–large earthquake magnitude prediction in Tokyo with artificial neural networks”. Neural Computing and Applications, 28(5), 1043-1055, 2017.
• [30] Reyes J, Morales-Esteban A. “Neural networks to predict earthquakes in Chile”. Applied Soft Computing Journal, 13(2), 1314-1328, 2013.
• [31] Asim KM, Moustafa SS, Niaz IA, Elawadi EA, Iqbal T, Martínez-Álvarez F. “Seismicity analysis and machine learning models for short-term low magnitude seismic activity predictions in Cyprus”. Soil Dynamics and Earthquake Engineering, 130, 105932, 2020.
• [32] Hanna AM, Ural D, Saygılı G. “Neural network model for liquefaction potential in soil deposits using Turkey and Taiwan earthquake data”. Soil Dynamics and Earthquake Engineering, 27(6), 521-540, 2007.
• [33] Akyol AA, Arikan O, Arikan F. “A machine learning-based detection of earthquake precursors using ionospheric data”. Radio Science, 55(11), 1-21, 2020.
• [34] Rayan A, Artuner H. “LSTM-based deep learning methods for prediction of earthquakes using ionospheric data”. Gazi University Journal of Science, 35(4), 1417-1431, 2022.
• [35] Saqib M, Adil MA, Freeshah M. “Pre-earthquake Ionospheric Perturbation Analysis Using Deep Learning Techniques”. Advances in Geomatics, 1(1), 48-67, 2023.
• [36] Akhoondzadeh M. “Kalman Filter, ANN-MLP, LSTM and ACO Methods Showing Anomalous GPS-TEC Variations Concerning Turkey’s Powerful Earthquake (6 February 2023)”. Remote Sensing, 15(12), 3061, 2023.
• [37] Haider SF, Shah M, Li B, Jamjareegulgarn P, de Oliveira-Júnior JF, Zhou C. “Synchronized and Co-Located Ionospheric and Atmospheric Anomalies Associated with the 2023 Mw 7.8 Turkey Earthquake”. Remote Sensing, 16(2), 222, 2024.
• [38] Gorshkov AL, Kossobokov VG, Novikova OV. “Prediction Results for the Strongest Earthquakes of February 6, 2023 in Southern Turkey”. Izvestiya, Physics of the Solid Earth, 60, 339–345, 2024.
• [39] Hacıefendioğlu K, Başağa HB, Kahya V, Özgan K, Altunışık AC. “Automatic Detection of Collapsed Buildings after the 6 February 2023 Türkiye Earthquakes Using Post-Disaster Satellite Images with Deep Learning-Based Semantic Segmentation Models”. Buildings, 14(3), 582, 2024.
• [40] Nicholas SV. “Identifying the Occurrence Time of the Destructive Kahramanmaraş-Gazientep Earthquake of Magnitude M7.8 in Turkey on 6 February 2023”. Applied Sciences, 14(3), 1215, 2024.
• [41] Biswas S, Kumar D, Bera KU. “Prediction of earthquake magnitude and seismic vulnerability mapping using artificial intelligence techniques: a case study of Turkey”. Res. Square, 1, 1-54, 2023.
• [42] Maletckii B, Astafyeva E, Sanchez SA, Kherani EA, De Paula ER. “The 6 February 2023 Türkiye earthquake sequence as detected in the ionosphere”. Space Physics, 128(9), e2023JA031663, 2023.
• [43] Özer E. “The effect of fluid viscous dampers on performance of a residential building”. Pamukkale University Journal of Engineering Sciences, 30(5), 650-659, 2023.