Abstract
This paper presents a study of the nonlinear estimation of the ground motion prediction equation (GMPE) using neural networks. The general regression neural network (GRNN) was chosen for its high learning rate. A separate GRNN was tested as well as a GRNN in cascade connection with linear regression (LR). Measurements of induced seis-micity in the Legnica-Głogów Copper District were used in this study. Various sets of input variables were tested. The basic variables used in every case were seismic energy and epicentral distance, while the additional variables were the location of the epicenter, the location of the seismic station, and the direction towards the epicenter. The GRNN improves the GMPE. The best results were obtained when the epicenter location was used as an additional input. The GRNN model was analysed for how it can improve the GMPE with respect to LR. The bootstrap resampling method was used for this purpose. It proved the statistical significance of the improvement of the GMPE. Additionally, this method allows the determination of smoothness parameters for the GRNN. Parameters derived through this method have better generalisation capabilities than the smoothness parameters estimated using the holdout method.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Abrahamson, N., and W. Silva (2008), Summary of the Abrahamson & Silva NGA ground-motion relations, Earthq. Spectra 24, 1, 67–97, DOI: 10.1193/1.2924360.
Akkar, S., and J.J. Bommer (2010), Empirical equations for the prediction of PGA, PGV, and spectra accelerations in Europe, the Mediterranean Region, and the Middle East, Seismol. Res. Lett. 81, 2, 195–206, DOI: 10.1785/gssrl.81.2.195.
Arjun, C.R. (2013), Neural Network-Based Estimation of Strong Ground Motion Parameters, Lambert Academic Publishing, Saarbrücken.
Boore, D.M., and G.M. Atkinson (2008), Ground-motion prediction equations for the average horizontal component of PGA, PGV, and 5%-damped PSA at spectral periods between 0.01 s and 10.0 s, Earthq. Spectra 24, 1, 99–138, DOI: 10.1193/1.2830434.
Campbell, K.W., and Y. Bozorgnia (2008), NGA ground motion model for the geometric mean horizontal component of PGA, PGV, PGD and 5% damped linear elastic response spectra for periods ranging from 0.01 to 10 s, Earthq. Spectra 24, 1, 139–171, DOI: 10.1193/1.2857546.
Cornell, C.A. (1968), Engineering seismic risk analysis, Bull. Seismol. Soc. Am. 58, 5, 1583–1606.
Derras, B., and A. Bekkouche (2011), Use of the Artificial Neural Network for Peak Ground Acceleration estimation, Lebanese Sci. J. 12, 2, 101–115.
Derras, B., P.-Y. Bard, F. Cotton, and A. Bekkouche (2012), Adapting the neural network approach to PGA prediction: An example based on the KiK‐net data, Bull. Seismol. Soc. Am. 102, 4, 1446–1461, DOI: 10.1785/0120110088.
Douglas, J. (2011), Ground-motion prediction equations 1964–2010, BRGM/RP-59356-FR, 444 pp.
Efron, B. (1979), Bootstrap methods: another look at the jackknife, Ann. Stat. 7, 1, 1–26, DOI: 10.1214/aos/1176344552.
García, S.R., M.P. Romo, and N. Sarmiento (2003), Modeling ground motion in Mexico City using artificial neural networks, Geofís. Int. 42, 2, 173–183.
Golik, A., and M.J. Mendecki (2012), Ground-motion prediction equations for induced seismicity in the main anticline and main syncline, Upper Silesian Coal Basin, Poland, Acta Geophys. 60, 2, 410–425, DOI: 10.2478/s11600-011-0070-9.
Güllü, H., and E. Erçelebi (2007), A neural network approach for attenuation relationships: An application using strong ground motion data from Turkey, Eng. Geol. 93, 3, 65–81, DOI: 10.1016/j.enggeo.2007.05.004.
Günaydin, K., and A. Günaydin (2008), Peak ground acceleration prediction by artificial neural networks for northwestern Turkey, Math. Problems Eng. 2008, article ID 919420, 1–20, DOI: 10.1155/2008/919420.
Hanna, A.M., D. Ural, and G. Saygili (2007), Neural network model for liquefaction potential in soil deposits using Turkey and Taiwan earthquake data, Soil Dyn. Earthq. Eng. 27, 6, 521–540, DOI: 10.1016/j.soildyn.2006.11.001.
Hong, H., T. Liu, and C.-S. Lee (2012), Observations on the application of artificial neural network to predicting ground motion measures, Earthq. Sci. 25, 2, 161–175, DOI: 10.1007/s11589-012-0843-5.
Joyner, W.B., and D.M. Boore (1988). Measurement, characterization, and prediction of strong ground motion. In: Proc. Earthquake Engineering & Soil Dynamics II. Geotechnical Division, ASCE Special Publication 20, 43–102.
Joyner, W.B., and D.M. Boore (1993), Methods for regression analysis of strong-motion data, Bull. Seismol. Soc. Am. 83, 2, 469–487.
Lasocki, S. (2013), Site specific prediction equations for peak acceleration of ground motion due to earthquakes induced by underground mining in Legnica-Głogów Copper District in Poland, Acta Geophys. 61, 5, 1130–1155, DOI: 10.2478/s11600-013-0139-8.
Moody, J. (1994), Prediction risk and architecture selection for neural networks. In: J. Cherkassy, J.H. Friedman, and H. Wechsler. (eds.), From Statistics to Neural Networks: Theory and Pattern Recognition Applications, NATO ASI Series, Springer, Berlin, 147–165, DOI: 10.1007/978-3-642-79119-2.
Parzen, E. (1962), On estimation of a probability density function and mode, Ann. Math. Statist. 33, 3, 1065–1076, DOI: 10.1214/aoms/1177704472.
Pozos-Estrada, A., R. Gómez, and H.P. Hong (2014). Use of neural network to predict the peak ground accelerations and pseudo spectral accelerations for Mexican Inslab and Interplate Earthquakes, Geofís. Int. 53, 1, 39–57, DOI: 10.1016/S0016-7169(14)71489-8.
Specht, D.F. (1991), A general regression neural network, IEEE Trans. Neural Network 2, 6, 568–576, DOI: 10.1109/72.97934.
Trifunac, M.D., and A.G. Brady (1976), Correlations of peak acceleration, velocity and displacement with earthquake magnitude, distance and site conditions, Earthq. Eng. Struct. Dyn. 4, 5, 455–471, DOI: 10.1002/eqe.4290040504.
Wasserman, P.D. (1993). Advanced Methods in Neural Computing, John Wiley & Sons, Inc. New York.
Yaghmaei-Sabegh, S. (2012). A new method for ranking and weighting of earthquake ground-motion prediction models, Soil Dyn. Earthq. Eng. 39, 78–87, DOI: 10.1016/j.soildyn.2012.03.006.
Yaghmaei-Sabegh, S., and H.-H. Tsang (2011), A new site classification approach based on neural networks, Soil Dyn. Earthq. Eng. 31, 7, 974–981, DOI: 10.1016/j.soildyn.2011.03.004.
Yaghmaei-Sabegh, S., and H.-H. Tsang (2014), Site class mapping based on earthquake ground motion data recorded by regional seismographic network, Nat. Hazards 73, 3, 2067–2087, DOI: 10.1007/s11069-014-1177-5.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivs license (http://creativecommons.org/licenses/by-ncnd/3.0/).
About this article
Cite this article
Wiszniowski, J. Applying the General Regression Neural Network to Ground Motion Prediction Equations of Induced Events in the Legnica-Głogów Copper District in Poland. Acta Geophys. 64, 2430–2448 (2016). https://doi.org/10.1515/acgeo-2016-0104
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1515/acgeo-2016-0104