Bulletin of Earthquake Engineering

, Volume 12, Issue 1, pp 495–516 | Cite as

Towards fully data driven ground-motion prediction models for Europe

  • Boumédiène Derras
  • Pierre Yves Bard
  • Fabrice Cotton
Original Research Paper


We have used the Artificial Neural Network method (ANN) for the derivation of physically sound, easy-to-handle, predictive ground-motion models from a subset of the Reference database for Seismic ground-motion prediction in Europe (RESORCE). Only shallow earthquakes (depth smaller than 25 km) and recordings corresponding to stations with measured \(V_{s30}\) properties have been selected. Five input parameters were selected: the moment magnitude \(M_{W}\), the Joyner–Boore distance \(R_{JB}\), the focal mechanism, the hypocentral depth, and the site proxy \(V_{S30}\). A feed-forward ANN type is used, with one 5-neuron hidden layer, and an output layer grouping all the considered ground motion parameters, i.e., peak ground acceleration (PGA), peak ground velocity (PGV) and 5 %-damped pseudo-spectral acceleration (PSA) at 62 periods from 0.01 to 4 s. A procedure similar to the random-effects approach was developed to provide between and within event standard deviations. The total standard deviation (\(\sigma \)) varies between 0.298 and 0.378 (log\(_{10}\) unit) depending on the period, with between-event and within-event variabilities in the range 0.149–0.190 and 0.258–0.327, respectively. Those values prove comparable to those of conventional GMPEs. Despite the absence of any a priori assumption on the functional dependence, our results exhibit a number of physically sound features: magnitude scaling of the distance dependency, near-fault saturation distance increasing with magnitude, amplification on soft soils and even indications for nonlinear effects in softer soils.


Neural networks ground motion RESORCE Pseudo-Spectral Acceleration \(\sigma \) 



The authors thank S. Akkar, J. Douglas and A. Laurendeau for their generous help with computer codes of the random-effect procedure. We acknowledge the support from the Tassili program: 13MDU901 (Prédiction du mouvement sismique et estimation du risque sismique lié aux effets de site) and from the SIGMA (Seismic Ground Motion assessment) project. We also want to emphasize the background work of all strong motion network operators, without whom GMPEs and Hazard assessment studies could not exist. We also thank J. Douglas (Guest Reviewer) and anonymous reviewers for their constructive criticism and comments that helped us to improve this manuscript.

Data and Resources

The RESORCE database used in this article have been collected and disseminated by the Euro-Mediterranean Seismological Centre (EMSC) data management center at http://jaguar.emsc-csem.org/sigma/

Supplementary material

10518_2013_9481_MOESM1_ESM.xlsx (77 kb)
Supplementary material 1 (xlsx 77 KB)
10518_2013_9481_MOESM2_ESM.docx (182 kb)
Supplementary material 2 (docx 182 KB)


  1. Abrahamson NA, Youngs RR (1992) A stable algorithm for regression analyses using the random-effects model. Bull Seismol Soc Am 82:505–510Google Scholar
  2. Akkar S, Bommer JJ (2010) Empirical equations for the prediction of PGA, PGV and spectral accelerations in Europe, the Mediterranean region and the Middle East. Seismol Res Lett 81:195–206CrossRefGoogle Scholar
  3. Akkar S, Çagnan Z (2010) A local ground-motion predictive model for Turkey and its comparison with other regional and global ground-motion models. Bull Seismol Soc Am 100:2978–2995CrossRefGoogle Scholar
  4. Akkar S, Sandıkkaya MA, Şenyurt M, Azari AS, Ay BÖ (2013) Reference database for seismic ground-motion in Europe (RESORCE), Bull Earthq Eng, submitted to this issueGoogle Scholar
  5. Al Atik L, Abrahamson N, Bommer JJ, Scherbaum F, Cotton F, Kuehn N (2010) The variability of ground-motion prediction models and its components. Seismol Res Lett 81:794–801CrossRefGoogle Scholar
  6. Alavi AH, Gandomi AH (2011) Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing. Comput Struct 89:2176–2194Google Scholar
  7. Anderson JG (2000) Expected shape of regressions for ground-motion parameters on rock. Bull Seismol Soc Am 90:S43–S52Google Scholar
  8. Assimaki D, Li W (2008) Site amplification and attenuation via downhole array seismogram inversion: a comparative study of the 2003 Miyagi-Oki, aftershock sequence. Bull Seism Soc Am 98:301–330Google Scholar
  9. Bindi D, Pacor F, Luzi L, Puglia R, Massa M, Ameri G, Paolucci R (2011) Ground motion prediction equations derived from the Italian strong motion database. Bull Earthq Eng 9:1899–1920Google Scholar
  10. Bommer JJ, Douglas J, Scherbaum F, Cotton F, Bungum H, Fäh D (2010) On the selection of ground-motion prediction equations for seismic hazard analysis. Seismol Res Lett 81:783–793Google Scholar
  11. Cadet H, Bard PY, Duval AM, Bertrand E (2012) Site effect assessment using KiK-net data—part 2—site amplification prediction equation (SAPE) based on \(f_{0}\) and \(V_{sz}\). Bull Earthq Eng 10:451–489. doi:  10.1007/s10518-011-9298-7 Google Scholar
  12. Castellaro S, Mulargia F, Rossi PM (2008) \(V_{s30}\): proxy for seismic amplification? Seism Res Lett 79:540–543Google Scholar
  13. Demuth H, Beale M, Hagan M (2009) Neural Network Toolbox\(^{{\rm Tm}}\) 6.User’s Guide. The MathWorks, Inc.Google Scholar
  14. Derras B, Bekkouche A, Zendagui D (2010) Neuronal approach and the use of kik-net network to generate response spectrum on the surface. Jordan J Civ Eng 4:12–21Google Scholar
  15. Derras B, Bard PY, Cotton F, Bekkouche A (2012) Adapting the neural network approach to PGA prediction: an example based on the KiK-net data. Bull Seism Soc Am 102:1446–1461 http://www.bssaonline.org/content/102/4/1446.abstract
  16. Douglas J, Jousset P (2011) Modeling the difference in ground-motion magnitude-scaling in small and large earthquakes. Seismol Res Lett 82:504–508Google Scholar
  17. García SR, Romo MP, Mayoral JM (2007) Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks. Geofísica Int 46:51–63Google Scholar
  18. Hu YH, Hwang JN (2002) Handbook of neural network signal processing. Acoust Soc Am 111:2525–2526Google Scholar
  19. Irshad A, El Naggar H, Khan AN (2008) Neural networks based attenuation of strong motion peaks in Europe. J Earthq Eng 12:663–680Google Scholar
  20. Kerh T, Ting SB (2005) Neural network estimation of ground peak acceleration at stations along Taiwan high-speed rail system. Eng Appl Artif Intell 18:857–866Google Scholar
  21. Kokusho T, Sato K (2008) Surface-to-base amplification evaluated from KiK-net vertical array strong motion records. Soil Dyn Earthq Eng 28:707–716Google Scholar
  22. Lee VW, Trifunac MD (2010) Should average shear-wave velocity in the top 30m of soil be used to describe seismic amplification. Soil Dyn Earthq Eng 30:1250–1258Google Scholar
  23. Liu B-Y, Ye LY, Xiao ML, Miao S (2006) Peak ground velocity evaluation by artificial neural network for West America region. In: 13th international conference on neural information processing 4234:942–951Google Scholar
  24. Mucciarelli M, Gallipoli MR (2006) Comparison between \(V_{s30}\) and other estimates of site amplification in Italy. In: Proceedings 1st European conference on earthquake engineering and seismology, Cd-Rom edition, paper 270Google Scholar
  25. Peter A, Harald B, Wolfgang M (2008) A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Netw 21:786–795Google Scholar
  26. Robitaille B, Marcos B, Veillette M, Payr G (1996) Modified quasi-Newton methods for training neural networks. Comput Chem Eng 20:1133–1140Google Scholar
  27. Sandıkkaya MA, Akkar S, Bard PY (2013) A nonlinear site amplification model for the next pan European ground motion prediction equations. Bull Seism Soc Am, February 2013, 103:19–32, doi: 10.1785/0120120008
  28. Wolfgang M (1997) Networks of spiking neurons: the third generation of neural network models. Neural Netw 10:1659–1671Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Boumédiène Derras
    • 1
  • Pierre Yves Bard
    • 2
  • Fabrice Cotton
    • 3
  1. 1.Risk Assessment and Management Laboratory (RISAM)Université Abou Bekr Belkaïd, Faculté de Technologie. BP 230-13048TlemcenAlgerie
  2. 2.Institut de Sciences de la Terre (ISTerre)Université Joseph FourierGrenoble cedex 9France
  3. 3.Institut de Sciences de la Terre (ISTerre)Université Joseph FourierGrenoble cedex 9France

Personalised recommendations