ON THE PREDICTION OF STRUCTURAL REACTIONS TO BIG EARTHQUAKES IN TURKEY

The prediction of structural reactions to big earthquakes is vital in giving warnings for potential damages early enough to minimize losses of life and properties. In the current study we describe buildings by fixed construction and environmental related parameters. Our models are based on real data of damaged buildings collected after the occurrence of three big earthquakes in Turkey. We extend our previous work to include the soil type for damaged buildings. We employ different techniques, namely neural networks (NN) and support vector machines (SVM) to improve the prediction accuracy. The results show that support vector machines, and in particular support vector regression gives better results compared to neural networks. Although we only used averages of soil type for each region, we observed that adding soil type has improved accuracy of predictions for building damages. It is to be noted that these types of predictions are important to ensure the serviceability and safety of existing structures. Our models are vital for the authorities to make fast and reliable decisions and can be also used to improve the development of new constructions codes.

Keywords:

earthquakes,

PDF

___

Bol, E., “Determination of the relationship between soil properties and earthquake damage with the aid of neural networks: a case study in Adapazarı”, Turkey, Nat. Hazards Earth Syst. Sci 12: 2965–2975, 2012.
Davis, Paul M.; Jakson, David D.; Johnston Malcom J.S.: “Further evidence of localized geomagnetic field changes before the 1974 Thanksgiving Day Earthquake, Hollister, California”, Geophysical Reasearch Letter, Vol. 7, Issue 7 (513-516), 1980.
Duma, G. and Ruzhin, Y.: “ Diurnal changes of earthquake activity and geomagnetic Sq-variation”, Natural Hazards and Earth Systems Sciences, 3 (171-177), 2003.
Fawzy, D.E. and Arslan, G.; “Development of building damage functions for big earthquakes in Turkey”, Procedia – Social and Behavioral Sciences, 195 (2290-2297), 2015.
Friswell, M.I., Penny, Jet, and Gravey, SD, “ A combined gentic and eigensensitivity algorithm for the location of damage in structure”, Computers and Structures, 69: 547-556, 1998.
Grünthal, G., (ed.). "European Macroseismic Scale 1998", Cahiers du Centre Européen de Géodynamique et de Séismologie Volume 15, Luxembourg, 1998
Housner, G.W., Bergman, L.A., et al. “Structural control: past, present and future”, Journal of Engineering Mechanics, 123 (9): 897-971, 1997.
Heaton, J., Encog: “Library of Interchangeable Machine Learning Models for Java and C#”, Journal of Machine Learning Research 16: 1243-1247, 2015.
Haykin, S.; “Neural Networks: A Comprehensive Foundation”, Prentice Hall, 1999.
Hornik, K.: ”Approximation Capabilities of Multilayer Feedforward Networks, Neural Networks”, 4(2), 251–257, 1991
MTA (Mineral Research & Exploration General Directorate) mta.gov.tr.
Rikitake T., et al.: “Changes in the Geomagnetic Field Associated with Earthquakes in the Izu Peninsula, Japan”, Journal of geomagnetism and geoelectricity, Vol. 32, 12 (721-739), 1980.
Ruzhin, Yuri; Kamogawa Masashi; Novikov, Victor: “Interrelation of geomagnetic storms and earthquakes: Insight from lab experiments and field observations”, 40th COSPAR Scientific Assembly. Held 2-10 August 2014, in Moscow, Russia, Abstract A3.1-68-14
Smola, A.J., Schölkopf, B., “A tutorial on support vector regression”, Statistics and Computing 14: 199-222, 2004.
Vapnik, V., Chervonenkis, A., “A note on one class of perceptrons, Automation and Remote Control”, 25, 1964.
Vapnik, V., Chervonenkis, A., “Theory of Pattern Recognition” [in Russian]. Nauka, Moscow, 1974. (German Translation: Wapnik W. & Tscherwonenkis A., Theorie der Zeichenerkennung, Akademie-Verlag, Berlin, 1979).
Vapnik, V.,”Statistical Learning Theory”, John Wiley and Sons, New York, 1998.