Araştırma Makalesi

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

Cilt: 9 Sayı: 2 29 Aralık 2024
PDF İndir
EN TR

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

Öz

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.

Anahtar Kelimeler

Destekleyen Kurum

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

Etik Beyan

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

Kaynakça

  1. AFAD. (2023, February 12). Açıklamalı Afet Yönetimi Terimleri Sözlüğü. https://www.afad.gov.tr/aciklamali-afet-yonetimi-terimleri-sozlugu
  2. EM-DAT. (2023, February 18). Disaster Classification. https://www.emdat.be/
  3. 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
  4. 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
  5. 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.
  6. Bilham, R. (2009). The seismic future of cities. Bulletin of earthquake engineering, 7, 839-887. https://doi.org/10.1007/s10518-009-9147-0
  7. 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
  8. Jia, J. (2016). Modern earthquake engineering: Offshore and land-based structures. Springer.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Yazılım Mühendisliği (Diğer)

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

29 Aralık 2024

Gönderilme Tarihi

28 Mart 2024

Kabul Tarihi

10 Haziran 2024

Yayımlandığı Sayı

Yıl 2024 Cilt: 9 Sayı: 2

Kaynak Göster

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
AMA
1.Habek GC, Kahramanli Örnek H. Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques. Sinopfbd. 2024;9(2):266-286. doi:10.33484/sinopfbd.1460421
Chicago
Habek, Gül Cihan, ve Humar Kahramanli Örnek. 2024. “Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques”. Sinop Üniversitesi Fen Bilimleri Dergisi 9 (2): 266-86. https://doi.org/10.33484/sinopfbd.1460421.
EndNote
Habek GC, Kahramanli Örnek H (01 Aralık 2024) Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques. Sinop Üniversitesi Fen Bilimleri Dergisi 9 2 266–286.
IEEE
[1]G. C. Habek ve H. Kahramanli Örnek, “Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques”, Sinopfbd, c. 9, sy 2, ss. 266–286, Ara. 2024, doi: 10.33484/sinopfbd.1460421.
ISNAD
Habek, Gül Cihan - Kahramanli Örnek, Humar. “Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques”. Sinop Üniversitesi Fen Bilimleri Dergisi 9/2 (01 Aralık 2024): 266-286. https://doi.org/10.33484/sinopfbd.1460421.
JAMA
1.Habek GC, Kahramanli Örnek H. Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques. Sinopfbd. 2024;9:266–286.
MLA
Habek, Gül Cihan, ve Humar Kahramanli Örnek. “Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques”. Sinop Üniversitesi Fen Bilimleri Dergisi, c. 9, sy 2, Aralık 2024, ss. 266-8, doi:10.33484/sinopfbd.1460421.
Vancouver
1.Gül Cihan Habek, Humar Kahramanli Örnek. Regional Analysis of Earthquakes and Earthquake Magnitude Estimation with Machine Learning Techniques. Sinopfbd. 01 Aralık 2024;9(2):266-8. doi:10.33484/sinopfbd.1460421

Cited By


Sinopfbd' de yayınlanan makaleler CC BY-NC 4.0 ile lisanslanmıştır.  88x31.png