Research Article
BibTex RIS Cite

Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques

Year 2024, Volume: 9 Issue: 2, 266 - 286, 29.12.2024
https://doi.org/10.33484/sinopfbd.1460421

Abstract

Natural disasters, which have been increasing in recent years due to the impact of climate change, pose a significant threat worldwide. Natural disasters, which can cause a large number of human losses and material damages due to their uncertain nature and sudden effects, vary depending on the location and natural environment of the countries. Türkiye located in the Alpine-Himalayan Earthquake Zone, is one of the countries most exposed to earthquake disasters. Although timely prediction of earthquakes is of vital importance in minimizing the destructive effects that may occur during the disaster and increasing resistance to the destructive effects of the disaster, it cannot yet be predicted successfully due to its non-linear chaotic behavior. However, many researchers continue to work on the subject, and earthquake prediction models are actively used in some countries where earthquake disasters occur frequently and cause great destruction. In this study, the magnitudes of future earthquakes were predicted using various machine learning models: Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Random Forests (RF), Gradient Boosting Algorithm (GB), Extreme Gradient Boosting Algorithm (XGBoost), 2-hidden-layer Artificial Neural Networks (ANN), and an ANN-KNN hybrid learning model. The performances of the established models were evaluated with MSE, MAE, RMSE, and R² metrics; and the ANN-KNN model showed that it was more effective than other models by exhibiting the highest performance with 0.0418 MSE, 0.0030 MAE, 0.0552 RMSE, and 0.7138 R² values. Additionally, unlike other studies, seven regions of Türkiye were considered separately and earthquakes were analyzed in detail according to their geography. The analysis results aim to add a new perspective to the literature.

Ethical Statement

The work does not require ethics committee approval and any private permission.

Supporting Institution

The authors have no received any financial support for the research, authorship, or publication of this study.

Thanks

-

References

  • AFAD. (2023, February 12). Açıklamalı Afet Yönetimi Terimleri Sözlüğü. https://www.afad.gov.tr/aciklamali-afet-yonetimi-terimleri-sozlugu
  • EM-DAT. (2023, February 18). Disaster Classification. https://www.emdat.be/
  • Santos, G. D. C. (2021). 2020 tropical cyclones in the Philippines: A review. Tropical Cyclone Research and Review, 10(3), 191-199. https://doi.org/10.1016/j.tcrr.2021.09.003
  • Winsemius, H. C., Aerts, J. C., Van Beek, L. P., Bierkens, M. F., Bouwman, A., Jongman, B., Kwadijk, J. C., Ligtvoet, W., Lucas, P. L., & Van Vuuren, D. P. (2016). Global drivers of future river flood risk. Nature Climate Change, 6(4), 381-385. https://doi.org/10.1038/nclimate2893
  • Özşahin, E. (2013, September 25-27). Türkiye’de yaşanmiş (1970-2012) doğal afetler üzerine bir değerlendirme. [Conference presentation]. Türkiye Deprem Mühendisliği ve Sismoloji Konferansı, Hatay, Türkiye.
  • Bilham, R. (2009). The seismic future of cities. Bulletin of earthquake engineering, 7, 839-887. https://doi.org/10.1007/s10518-009-9147-0
  • Kavianpour, P., Kavianpour, M., Jahani, E., & Ramezani, A. (2023). A CNN-BiLSTM model with attention mechanism for earthquake prediction. The Journal of Supercomputing, 79(17), 19194-19226. https://doi.org/10.1007/s11227-023-05497-5
  • Jia, J. (2016). Modern earthquake engineering: Offshore and land-based structures. Springer.
  • Çam, H., & Duman, O. (2016). Yapay Sinir Aği Yöntemiyle Deprem Tahmini: Türkiye Bati Anadolu Fay Hatti Uygulamasi. Gümüshane University Electronic Journal of the Institute of Social Science/Gümüshane Üniversitesi Sosyal Bilimler Enstitüsü Elektronik Dergisi, 7(17).
  • Mallouhy, R., Abou Jaoude, C., Guyeux, C., & Makhoul, A. (2019, December 18-20). Major earthquake event prediction using various machine learning algorithms [Conference presentation]. 2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), Paris, France. 10.1109/ICT-DM47966.2019.9032983
  • Wang, X., Zhong, Z., Yao, Y., Li, Z., Zhou, S., Jiang, C., & Jia, K. (2023). Small Earthquakes Can Help Predict Large Earthquakes: A Machine Learning Perspective. Applied Sciences, 13(11), 6424. https://doi.org/10.3390/app13116424
  • 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
  • Emre, Ö., Duman, T. Y., Özalp, S., Şaroğlu, F., Olgun, Ş., Elmacı, H., & Çan, T. (2018). Active fault database of Turkey. Bulletin of earthquake engineering, 16(8), 3229-3275. https://doi.org/10.1007/s10518-016-0041-2
  • Karcı, M., & Şahin, İ. (2022). Derin öğrenme yöntemleri kullanılarak deprem tahmini gerçekleştirilmesi. Artificial Intelligence Studies, 5(1), 23-34.
  • Kandilli. (2023, January 10). Kandilli Rasathanesi BDTİM Deprem Sorgulama Sistemi. http://www.koeri.boun.edu.tr/sismo/zeqdb/
  • AFAD. (2023, February 18). Genel Bilgiler. http://www.koeri.boun.edu.tr/sismo/bilgi/sss_tr.htm
  • USGS. (2023, January 21). Earthquakes. https://www.usgs.gov/
  • Habek, G. C. (2022). Makine Öğrenmesi Teknikleri ile Kripto Para Duygu Analizi. (Tez no. 763894) [Yüksek Lisans Tezi, Manisa Celal Bayar Üniversitesi].
  • Mitchell, T. M. (1997). Machine learning (Vol. 1). McGraw-hill New York.
  • Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
  • Freund, Y., Schapire, R., & Abe, N. (1999). A short introduction to boosting. Journal-Japanese Society For Artificial Intelligence, 14(5), 771-780.
  • Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. https://doi.org/10.1145/2939672.29397
  • Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937-1967. https://doi.org/10.1007/s10462-020-09896-5
  • Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  • Kurtgoz, Y., Karagoz, M., & Deniz, E. (2017). Biogas engine performance estimation using ANN. Engineering Science and Technology, an International Journal, 20(6), 1563-1570. https://doi.org/10.1016/j.jestch.2017.12.010
  • Akhter, M. N., Mekhilef, S., Mokhlis, H., Almohaimeed, Z. M., Muhammad, M. A., Khairuddin, A. S. M., Akram, R., & Hussain, M. M. (2022). An hour-ahead PV power forecasting method based on an RNN-LSTM model for three different PV plants. Energies, 15(6), 2243. https://doi.org/10.3390/en15062243
  • Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  • Akandeh, A., & Salem, F. M. (2019, August 04-07). Slim lstm networks: Lstm_6 and lstm_c6 [Conference presentation]. 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), Dallas, TX, USA. https://doi.org/10.1109/MWSCAS.2019.8884912
  • Clarke, M. (1974). Pattern classification and scene analysis. In: Wiley Online Library https://doi.org/10.2307/2344977
  • Akbulut, Y., Sengur, A., Guo, Y., & Smarandache, F. (2017). NS-k-NN: Neutrosophic set-based k-nearest neighbors classifier. Symmetry, 9(9), 179. https://doi.org/10.3390/sym9090179
  • Demir, F. (2021). Siber saldırı tespiti için makine öğrenmesi yöntemlerinin performanslarının incelenmesi. Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 23(2), 782-791. https://doi.org/10.25092/baunfbed.876338
  • Nguyen, V. V., Pham, B. T., Vu, B. T., Prakash, I., Jha, S., Shahabi, H., Shirzadi, A., Ba, D. N., Kumar, R., & Chatterjee, J. M. (2019). Hybrid machine learning approaches for landslide susceptibility modeling. Forests, 10(2), 157. https://doi.org/10.3390/f10020157
  • Robeson, S. M., & Willmott, C. J. (2023). Decomposition of the mean absolute error (MAE) into systematic and unsystematic components. PloS One, 18(2), https://doi.org/10.1371/journal.pone.0279774
  • Demirtaş, R., & Erkmen, C. (2000). Odak mekanizması çözümü. Deprem ve Jeoloji, TMMOB Jeoloji Mühendisleri Odası Yayınları, 52, 91-94.
  • Chen, J., & Zhu, S. (2020). Spatial and temporal b-value precursors preceding the 2008 Wenchuan, China, earthquake (Mw= 7.9): implications for earthquake prediction. Geomatics, Natural Hazards and Risk, 11(1), 1196-1211. https://doi.org/10.1080/19475705.2020.1784297

Makine Öğrenmesi Teknikleriyle Depremlerin Bölgesel Analizi ve Deprem Büyüklüğü Tahmini

Year 2024, Volume: 9 Issue: 2, 266 - 286, 29.12.2024
https://doi.org/10.33484/sinopfbd.1460421

Abstract

İklim değişikliğinin etkisiyle son yıllarda artan doğal afetler dünya çapında önemli bir tehdit oluşturuyor. Belirsiz doğası ve ani etkileri nedeniyle çok sayıda insan kaybına ve maddi hasara neden olabilen doğal afetler, ülkelerin bulunduğu konuma ve doğal ortamlarına göre değişiklik göstermektedir. Alp-Himalaya Deprem Bölgesi'nde yer alan Türkiye, deprem felaketlerine en fazla maruz kalan ülkelerden biridir. Depremlerin zamanında tahmini, afet sırasında oluşabilecek yıkıcı etkilerin en aza indirilmesi ve afetin yıkıcı etkilerine karşı direncin arttırılması açısından hayati öneme sahip olmasına rağmen, doğrusal olmayan kaotik davranışı nedeniyle henüz başarılı bir şekilde tahmin edilememektedir. Ancak pek çok araştırmacı konu üzerinde çalışmaya devam etmekte ve deprem felaketlerinin sıklıkla yaşandığı ve büyük yıkımlara neden olduğu bazı ülkelerde deprem tahmin modelleri aktif olarak kullanılmaktadır. Bu çalışmada gelecekte meydana gelebilecek depremlerin büyüklükleri Uzun Kısa Süreli Bellek (LSTM), Tekrarlayan Sinir Ağı (RNN), Rastgele Ormanlar (RF) ve Gradient Boosting Algoritması (GB) kullanılarak ölçülmektedir. Extreme Gradient Boosting Algoritması (XGBoost), 2 gizli katmanlı Yapay Sinir Ağları (ANN) ve ANN-KNN hibrit öğrenme modeli kullanılarak tahmin edilmeye çalışıldı. Kurulan modellerin performansları MSE, MAE, RMSE ve R² metrikleri ile değerlendirilmiş; ANN-KNN modeli ise 0.0418 MSE, 0.0030 MAE, 0.0552 RMSE ve 0.7138 R² değerleri ile en yüksek performansı sergileyerek diğer modellere göre daha etkili olduğunu göstermiştir. Ayrıca diğer çalışmalardan farklı olarak Türkiye'nin yedi bölgesi ayrı ayrı ele alınmış ve depremler coğrafyalarına göre detaylı bir şekilde analiz edilmiştir. Elde edilen analiz sonuçlarının literatüre yeni bir bakış açısı kazandırması amaçlanmaktadır.

References

  • AFAD. (2023, February 12). Açıklamalı Afet Yönetimi Terimleri Sözlüğü. https://www.afad.gov.tr/aciklamali-afet-yonetimi-terimleri-sozlugu
  • EM-DAT. (2023, February 18). Disaster Classification. https://www.emdat.be/
  • Santos, G. D. C. (2021). 2020 tropical cyclones in the Philippines: A review. Tropical Cyclone Research and Review, 10(3), 191-199. https://doi.org/10.1016/j.tcrr.2021.09.003
  • Winsemius, H. C., Aerts, J. C., Van Beek, L. P., Bierkens, M. F., Bouwman, A., Jongman, B., Kwadijk, J. C., Ligtvoet, W., Lucas, P. L., & Van Vuuren, D. P. (2016). Global drivers of future river flood risk. Nature Climate Change, 6(4), 381-385. https://doi.org/10.1038/nclimate2893
  • Özşahin, E. (2013, September 25-27). Türkiye’de yaşanmiş (1970-2012) doğal afetler üzerine bir değerlendirme. [Conference presentation]. Türkiye Deprem Mühendisliği ve Sismoloji Konferansı, Hatay, Türkiye.
  • Bilham, R. (2009). The seismic future of cities. Bulletin of earthquake engineering, 7, 839-887. https://doi.org/10.1007/s10518-009-9147-0
  • Kavianpour, P., Kavianpour, M., Jahani, E., & Ramezani, A. (2023). A CNN-BiLSTM model with attention mechanism for earthquake prediction. The Journal of Supercomputing, 79(17), 19194-19226. https://doi.org/10.1007/s11227-023-05497-5
  • Jia, J. (2016). Modern earthquake engineering: Offshore and land-based structures. Springer.
  • Çam, H., & Duman, O. (2016). Yapay Sinir Aği Yöntemiyle Deprem Tahmini: Türkiye Bati Anadolu Fay Hatti Uygulamasi. Gümüshane University Electronic Journal of the Institute of Social Science/Gümüshane Üniversitesi Sosyal Bilimler Enstitüsü Elektronik Dergisi, 7(17).
  • Mallouhy, R., Abou Jaoude, C., Guyeux, C., & Makhoul, A. (2019, December 18-20). Major earthquake event prediction using various machine learning algorithms [Conference presentation]. 2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), Paris, France. 10.1109/ICT-DM47966.2019.9032983
  • Wang, X., Zhong, Z., Yao, Y., Li, Z., Zhou, S., Jiang, C., & Jia, K. (2023). Small Earthquakes Can Help Predict Large Earthquakes: A Machine Learning Perspective. Applied Sciences, 13(11), 6424. https://doi.org/10.3390/app13116424
  • 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
  • Emre, Ö., Duman, T. Y., Özalp, S., Şaroğlu, F., Olgun, Ş., Elmacı, H., & Çan, T. (2018). Active fault database of Turkey. Bulletin of earthquake engineering, 16(8), 3229-3275. https://doi.org/10.1007/s10518-016-0041-2
  • Karcı, M., & Şahin, İ. (2022). Derin öğrenme yöntemleri kullanılarak deprem tahmini gerçekleştirilmesi. Artificial Intelligence Studies, 5(1), 23-34.
  • Kandilli. (2023, January 10). Kandilli Rasathanesi BDTİM Deprem Sorgulama Sistemi. http://www.koeri.boun.edu.tr/sismo/zeqdb/
  • AFAD. (2023, February 18). Genel Bilgiler. http://www.koeri.boun.edu.tr/sismo/bilgi/sss_tr.htm
  • USGS. (2023, January 21). Earthquakes. https://www.usgs.gov/
  • Habek, G. C. (2022). Makine Öğrenmesi Teknikleri ile Kripto Para Duygu Analizi. (Tez no. 763894) [Yüksek Lisans Tezi, Manisa Celal Bayar Üniversitesi].
  • Mitchell, T. M. (1997). Machine learning (Vol. 1). McGraw-hill New York.
  • Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
  • Freund, Y., Schapire, R., & Abe, N. (1999). A short introduction to boosting. Journal-Japanese Society For Artificial Intelligence, 14(5), 771-780.
  • Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. https://doi.org/10.1145/2939672.29397
  • Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937-1967. https://doi.org/10.1007/s10462-020-09896-5
  • Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  • Kurtgoz, Y., Karagoz, M., & Deniz, E. (2017). Biogas engine performance estimation using ANN. Engineering Science and Technology, an International Journal, 20(6), 1563-1570. https://doi.org/10.1016/j.jestch.2017.12.010
  • Akhter, M. N., Mekhilef, S., Mokhlis, H., Almohaimeed, Z. M., Muhammad, M. A., Khairuddin, A. S. M., Akram, R., & Hussain, M. M. (2022). An hour-ahead PV power forecasting method based on an RNN-LSTM model for three different PV plants. Energies, 15(6), 2243. https://doi.org/10.3390/en15062243
  • Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  • Akandeh, A., & Salem, F. M. (2019, August 04-07). Slim lstm networks: Lstm_6 and lstm_c6 [Conference presentation]. 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), Dallas, TX, USA. https://doi.org/10.1109/MWSCAS.2019.8884912
  • Clarke, M. (1974). Pattern classification and scene analysis. In: Wiley Online Library https://doi.org/10.2307/2344977
  • Akbulut, Y., Sengur, A., Guo, Y., & Smarandache, F. (2017). NS-k-NN: Neutrosophic set-based k-nearest neighbors classifier. Symmetry, 9(9), 179. https://doi.org/10.3390/sym9090179
  • Demir, F. (2021). Siber saldırı tespiti için makine öğrenmesi yöntemlerinin performanslarının incelenmesi. Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 23(2), 782-791. https://doi.org/10.25092/baunfbed.876338
  • Nguyen, V. V., Pham, B. T., Vu, B. T., Prakash, I., Jha, S., Shahabi, H., Shirzadi, A., Ba, D. N., Kumar, R., & Chatterjee, J. M. (2019). Hybrid machine learning approaches for landslide susceptibility modeling. Forests, 10(2), 157. https://doi.org/10.3390/f10020157
  • Robeson, S. M., & Willmott, C. J. (2023). Decomposition of the mean absolute error (MAE) into systematic and unsystematic components. PloS One, 18(2), https://doi.org/10.1371/journal.pone.0279774
  • Demirtaş, R., & Erkmen, C. (2000). Odak mekanizması çözümü. Deprem ve Jeoloji, TMMOB Jeoloji Mühendisleri Odası Yayınları, 52, 91-94.
  • Chen, J., & Zhu, S. (2020). Spatial and temporal b-value precursors preceding the 2008 Wenchuan, China, earthquake (Mw= 7.9): implications for earthquake prediction. Geomatics, Natural Hazards and Risk, 11(1), 1196-1211. https://doi.org/10.1080/19475705.2020.1784297
There are 36 citations in total.

Details

Primary Language English
Subjects Software Engineering (Other)
Journal Section Research Articles
Authors

Gül Cihan Habek 0000-0003-1748-3486

Humar Kahramanli Örnek 0000-0003-2336-7924

Publication Date December 29, 2024
Submission Date March 28, 2024
Acceptance Date June 10, 2024
Published in Issue Year 2024 Volume: 9 Issue: 2

Cite

APA Habek, G. C., & Kahramanli Örnek, H. (2024). Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques. Sinop Üniversitesi Fen Bilimleri Dergisi, 9(2), 266-286. https://doi.org/10.33484/sinopfbd.1460421


Articles published in Sinopjns are licensed under CC BY-NC 4.0.