ARTIFICIAL NEURAL NETWORK MODELLING OF EARTHQUAKES AROUND USAK CITY

Öz

In Turkish Earthquake Code 2007 (TEC, 2007), Usak city is located in the second-degree seismic zone while Esme, a town and district of Usak Province, is in the first-degree seismic zone. However cities in neighbourhood of Usak, such as Gediz, Simav towns of Kütahya city and Dinar district of Afyon city have many active faults which led to severe seismic damages in and around Usak. Despite this, Usak has only 2 active seismic stations which are in Usak city centre and Esme town. This paper aims to constitute artificial neural network (ANN) models by using seismic data of neighbour stations and to estimate peak ground acceleration (PGA) in the districts without stations. The results of models are validated by comparing the predicted and measured seismic data of the Usak central station. In addition, PGAs obtained by models are compared with design values in TEC 2007

Anahtar Kelimeler

• Artificial Neural Network, Peak Ground Acceleration, Feed Forward Back-Propagation Algorithm

UŞAK İLİ ÇEVRESİNDEKİ DEPREMLERİN YAPAY SİNİR AĞLARI İLE MODELLENMESİ

Öz

Deprem Bölgelerinde Yapılacak Binalar Hakkında Yönetmelik 2007 (DBYBHY, 2007)’de, Uşak ilinin büyük bir kısmı 2. derece deprem bölgesinde olup, Eşme ilçesi 1. derece deprem bölgesinde bulunmaktadır. Ancak il sınırlarına yakın çevrede bulunan Kütahya’ya bağlı Gediz, Simav ve Afyon’a bağlı Dinar ilçelerindeki uzun ve aktif faylarda meydana gelen depremler, Uşak il ve ilçelerinde önemli ölçüde hissedilmekte ve etkileri gözlenmektedir. Buna karşın il sınırları içerisinde, biri merkezde diğeri Eşme’de olmak üzere yalnızca 2 adet deprem kayıt istasyonu bulunmaktadır. Çalışmada hedeflenen, çevredeki deprem kayıt istasyonlarında ölçülmüş kayıtlar kullanılarak, yapay sinir ağları (YSA) modelleri oluşturmak ve il sınırları içinde istasyon olmayan bölgelerdeki en büyük yer ivmesi tahmini yapabilmektir. Oluşturulan modeller kullanılarak istasyon olan merkez ilçede meydana gelmiş en yüksek ivme değerleri tahmin edilmiş ve ölçülmüş veriler ile karşılaştırılmış, böylece modellerin doğruluğu irdelenmiştir. Buna ek olarak, tüm ilçeler için elde edilen en büyük yer ivmesi değerleri DBYBHY 2007’de öngörülen değerler ile kıyaslanmıştır

Anahtar Kelimeler

• Yapay Sinir Ağları, Maksimum Yer İvmesi, İleri Beslemeli Geri-Yayılım Algoritması

Kaynakça

1. [1] DBYBHY (2007). Deprem Bölgelerinde Yapılacak Binalar Hakkında Yönetmelik, Resmi Gazete Tarihi: 06.03.2007, Resmi Gazete Sayısı: 26454, Ankara, Türkiye.
2. [2] Türkiye Deprem Bölgeleri Haritası (1996). Bayındırlık ve İskan Bakanlığı, Afet İşleri Genel Müdürlüğü, Deprem Araştırma Dairesi Başkanlığı, Ankara, Türkiye.
3. [3] Atkinson, G.M., Boore, D.M. 2006. Earthquake ground-motion prediction equations for eastern North America, Bulletin of the Seismological Society of America, Cilt 96, Sayı 6, s.2181–2205.
4. [4] Boore, D.M., Joyner, W.B., Fumal, T.E. 1997. Equations for estimating horizontal response spectra and peak acceleration from western North American earthquakes: a summary of recent work, Seismological Research Letters,Cilt 68, Sayı 1, s.128–153.
5. [5] Campbell, K.W. 1997. Empirical near-source attenuation relationships for horizontal and vertical components of peak ground acceleration, peak ground velocity, and pseudo-absolute acceleration response spectra, Seismological Research Letters, Cilt 68, Sayı 1, s.54–179.
6. [6] Spudich, P., Fletcher, J.B., Hellweg, M. 1997. SEA96—a new predictive relation for earthquake ground motions in extensional tectonic regimes, Seismological Research Letters, Cilt 68, Sayı 1, s.190–198.
7. [7] Ambraseys, N.N., Simpson, K.A., Bommer, J.J. 1996. Prediction of horizontal response spectra in Europe, Earthquake Engineering and Structural Dynamics, Cilt 25, Sayı 4, s.371–400.
8. [8] Alavi, A.H., Gandomi, A.H. 2011. Prediction of principal groundmotion parameters using a hybrid method coupling artificial neural networks and simulated annealing, Computers and Structures Cilt 89 (23-24), s.2176-2194.

9. [9] Gandomi, A.H., Alavi, A.H., Mousavi, M., Tabatabaei, S.M. 2011. A hybrid computational approach to derive new ground-motion attenuation models, Engineering Applications of Artificial Intelligence, Cilt 24 (4), s.717-732.
10. [10] Gullu, H., Ercelebi, E. 2007. A neural network approach for attenuation relationships: an application using strongegroundemotion data from Turkey, Engineering Geology, Cilt 93, s.65-81.
11. [11] Bojorquez, E., Bojorquez, J., Ruiz, S.E., Reyes-Salazar, A. 2012. Prediction of inelastic response spectra using artificial neural Networks, Mathematical Problems in Engineering, Cilt 2012, Article ID 937480, 15 pages, DOİ:10.1155/2012/937480.
12. [12] Panakkat, A., Adeli. 2007. Neural Network Models for Earthquake Magnitude Prediction Usıng Multiple Seismicity Indicators, International Journal of Neural Systems, Cilt 17, Sayı 1. DOI: http://dx.doi.org/10.1142/S01290 65707000890.
13. [13] Yuen, K.V., Mu, H.Q. 2011. Peak Ground Acceleration Estimation by Linear and Nonlinear Models with Reduced Order Monte Carlo Simulation, Computer-Aided Civil and Infrastructure Engineering, Cilt 26, s.30–47.
14. [14] Kamatchi, P., Rajasankar, J., Ramana, G.V., Nagpal, A.K. 2010. A neural network based methodology to predict sitespecific spectral acceleration values, Earthquake Engineering and Engineering Vibration, Cilt 9, Sayı 4, s.459-472.
15. [15] Derras, B., Bard, P.Y., Cotton, F., Bekkouche, A. 2012. Adapting the neural network approach to PGA prediction: an example based on the KiK-net data, Bulletin of the Seismological Society of America, Cilt 102, Sayı 4, s. 1446-146. DOİ: 10.1785/0120110088.
16. [16] Pozos-Estrada, A., Gomez, R., Hong, H.P. 2014. Use of Neural Network to Predict the Peak Ground Accelerations and Pseudo Spectral Accelerations for Mexican Inslab and Interplate Earthquakes, Geofisica Internacional, Cilt 53, s.39-57.
17. [17] Gandomi, M., Soltanpour, M., Zolfaghari, M., Gandomi, A.H. 2016. Prediction of Peak Ground Acceleration of Iran’s Tectonic Regions using a Hybrid Soft Computing Technique, Geoscience Frontiers, Cilt 7, s.75-82.
18. [18] Kia, A., Sensoy, S. 2014. Assessment the Effective Ground Motion Parameters on Seismic Performance of R/C Buildings Using Artificial Neural Network, Indian Journal of Science and Technology, Cilt 7, s.2076-2082.
19. [19] Thomas, S., Pillai G.N., Pal, K. 2016. Prediction of peak ground acceleration using ϵ-SVR, ν-SVR and Ls-SVR algorithm, Geomatics, Natural Hazards and Risk, DOI: 10.1080/19475705.2016.1176604.
20. [20] Kerh, T., Ting, S.B. 2005. Neural network estimation of ground peak acceleration at stations along Taiwan high-speed rail system, Engineering Applications of Artificial Intelligence, Cilt 18, s.857–866.
21. [21] Gandomi, M., Soltanpour, M., Zolfaghari, M.R., Gandomi, A.H. 2016. Prediction of peak ground acceleration of Iran’s tectonic regions using a hybrid soft computing technique, Geoscience Frontiers, Cilt 7, s.75-82.
22. [22] Lee, S.C., Han, S.W. 2002. Neuralnetwork-based models for generating artificial earthquakes and response spectra, Computers & Structures, Cilt 80, Sayı 20–21, s.1627–1638.
23. [23] Garcia, S.R., Romo, M.P., Mayoral, J.M. 2007. Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks, Geofisica Internacional, Cilt 46, Sayı 1, s.51– 63.
24. [24] Günaydın, K., Günaydın, A. 2008. Peak ground acceleration prediction by artificial neural networks for northwestern Turkey, Mathematical Problems in Engineering, Cilt 2008, Article ID 919420, 20 pages.
25. [25] Arjun, C.R., Kumar, A. 2009. Artificial neural network-based estimation of peak ground acceleration, Journal of Earthquake Technology, Cilt 46, s.19–28. [26] http://www.bilgiustam.com/beyni n-sirlari/ (Erişim Tarihi: 20.08.2015).
26. [27] Şen, Z. 2004. Yapay Sinir Ağları İlkeleri, İstanbul Su Vakfı [28] Mehrotra, K., Mohan, C.K., Ranka S. 2000. Elements of Artificial Neural Network, USA MIT Press.
27. [29] Türkiye Ulusal Kuvvetli Yer Hareketi Veri Tabanı. http://kyhdata.deprem.gov.tr/2K/ kyhdata_v4.php
28. [30] Papazachos, B. C., Kiratzi, A. A., Karakostas, B. G. 1997. Towards a Homogeneous Moment-magnitude Determination for Earthquakes in Greece and the Surrounding Area, Bulletin of the Seismological Society of America, Cilt 87, s.474– 483.
29. [31] Ma, L., Xu, F., Wang, X., Tang, L. 2010. Earthquake Prediction Based on Levenberg-Marquardt Algorithm Constrained BackPropagation Neural Network Using DEMETER Data, Knowledge Science, Engineering and Management, 4th International Conference, KSEM 2010, Belfast, Northern Ireland, UK, September 1-3, 2010. Proceedings. DOI: 10.1007/978-3-642-15280-1_57.
30. [32] Ulusal Deprem Araştırma Programı, UDAP-Ç-13-06 Türkiye Sismik Tehlike Haritasının Güncellenmesi, Aralık 2014, Ankara. [33] Türkiye Deprem Tehlike Haritaları İnteraktif Web Uygulaması. https://testtdth.afad.gov.tr/