Abstract
Adaptive neuro-fuzzy inference systems (ANFIS) are used here to obtain the robust ground motion prediction model (GMPM). Avoiding a priori functional form, ANFIS provides fully data-driven predictive models. A large subset of the NGA-West2 database is used, including 2335 records from 580 sites and 137 earthquakes. Only shallow earthquakes and recordings corresponding to stations with measured V s30 properties are selected. Three basics input parameters are chosen: the moment magnitude (Mw), the Joyner–Boore distance (R JB) and V s30. ANFIS model output is the peak ground acceleration (PGA), peak ground velocity (PGV) and 5% damped pseudo-spectral acceleration (PSA) at periods from 0.01 to 4 s. A procedure similar to the random-effects approach is developed to provide between- and within-event standard deviations. The total standard deviation (SD) varies between [0.303 and 0.360] (log10 units) depending on the period. The ground motion predictions resulting from such simple three explanatory variables ANFIS models are shown to be comparable to the most recent NGA results (e.g., Boore et al., in Earthquake Spectra 30:1057–1085, 2014; Derras et al., in Earthquake Spectra 32:2027–2056, 2016). The main advantage of ANFIS compared to artificial neuronal network (ANN) is its simple and one-off topology: five layers. Our results exhibit a number of physically sound features: magnitude scaling of the distance dependency, near-fault saturation distance increasing with magnitude and amplification on soft soils. The ability to implement ANFIS model using an analytic equation and Excel is demonstrated.
Similar content being viewed by others
References
Abrahamson, N. A., Silva, W., & Kamai, R. (2013). Update of the AS08 Ground-Motion Prediction equations based on the NGA-West2 data set (p. 174). Rep: Pacific Earthquake Engineering Research Center.
Abrahamson, N., & Youngs, R. (1992). A stable algorithm for regression analyses using the random effects model. Oakland: Bulletin of the Seismological Society of America.
Ahmad, I., El Naggar, M. H., & Khan, A. N. (2008). Neural network based attenuation of strong motion peaks in Europe. Journal of Earthquake Engineering, 12, 663–680. https://doi.org/10.1080/13632460701758570.
Akbulut, S., Hasiloglu, A. S., & Pamukcu, S. (2004). Data generation for shear modulus and damping ratio in reinforced sands using adaptive neuro-fuzzy inference system. Soil Dynamics and Earthquake Engineering. https://doi.org/10.1016/j.soildyn.2004.04.006.
Ancheta, T.D., Darragh, R.B., Stewart, J.P. (2014). Pacific earthquake engineering peer NGA-West2 database.
Atik, L. Al, Abrahamson, N., & Bommer, J. (2010). The variability of ground-motion prediction models and its components. Seismological Research Letters, 81, 794–801.
Bommer, J. J., Stafford, P. J., & Akkar, S. (2010). Current empirical ground-motion prediction equations for Europe and their application to Eurocode 8. Bulletin of Earthquake Engineering, 8, 5–26. https://doi.org/10.1007/s10518-009-9122-9.
Boore, D. M. (2003). Simulation of ground motion using the stochastic method. In Y. Ben-Zion (Ed.), Seismic motion, lithospheric structures, earthquake and volcanic sources: The Keiiti Aki volume (pp. 635–676). Basel: Birkhäuser.
Boore, D. M., Stewart, J. P., Seyhan, E., & Atkinson, G. M. (2014). NGA-West2 equations for predicting PGA, PGV, and 5% damped PSA for shallow crustal earthquakes. Earthquake Spectra, 30, 1057–1085. https://doi.org/10.1193/070113EQS184M.
Chiou, B. S.-J., & Youngs, R. R. (2014). Update of the Chiou and Youngs NGA model for the average horizontal component of peak ground motion and response spectra. Earthquake Spectra, 30, 1117–1153. https://doi.org/10.1193/072813EQS219M.
Derras, B., Bard, P. Y., & Cotton, F. (2014). Towards fully data driven ground-motion prediction models for Europe. Bulletin of Earthquake Engineering, 12, 495–516. https://doi.org/10.1007/s10518-013-9481-0.
Derras, B., Bard, P. Y., & Cotton, F. (2016). Site-conditions proxies, ground-motion variability and data-driven GMPEs: Insights from NGA-West 2 and RESORCE data sets. Earthquake Spectra, 32, 2027–2056. https://doi.org/10.1193/060215EQS082M.
Derras, B., Bard, P. Y., & Cotton, F. (2017). VS30, slope, H800 and f0: Performance of various site-condition proxies in reducing ground-motion aleatory variability and predicting non-linear site response. Earth, Planets and Space, 69, 133. https://doi.org/10.1186/s40623-017-0718-z.
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, 102, 1446–1461. https://doi.org/10.1785/0120110088.
Douglas, J., & Edwards, B. (2016). Recent and future developments in earthquake ground motion estimation. Earth Science Review, 160, 203–219. https://doi.org/10.1016/j.earscirev.2016.07.005.
Jang, J. S. R. (1991). Fuzzy modeling using generalized neural networks and Kalman filter algorithm. AAAI, 91, 762–767.
Jang, J. S. R. (1993). ANFIS: Adaptive-network based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541.
Jang, J. S. R., Sun, C. T., & Mizutani, E. (1997). Neuro-fuzzy and soft computing, a computational approach to learning and machine intelligence. Upper Saddle River: Prentice Hall.
Karimi, I. (2006). Risk management of natural disasters : A fuzzy-probabilistic methodology and its application to seismic hazard. Aachen: Aachen University.
Kerh, T., & Ting, S. (2005). Neural network estimation of ground peak acceleration at stations along Taiwan high-speed rail system. Engineering Applications of Artificial Intelligence, 18(7), 857–866.
Liu, B., Ye, L., Xiao, M., & Miao, S. (2006). Peak ground velocity evaluation by artificial neural network for West America region (pp. 942–951). Berlin: Springer. https://doi.org/10.1007/11893257_104.
Mirrashid, M. (2014). Earthquake magnitude prediction by adaptive neuro-fuzzy inference system (ANFIS) based on fuzzy C-means algorithm. Natural Hazards, 74, 1577–1593. https://doi.org/10.1007/s11069-014-1264-7.
Mittal, A., Sharma, S., & Kanungo, D. P. (2012). A comparison of ANFIS and ANN for the prediction of peak ground acceleration in Indian Himalayan Region. Advances in Intelligent and Soft Computing (pp. 485–495). Berlin: Springer. https://doi.org/10.1007/978-81-322-0491-6_45.
Régnier, J., Bonilla, L., Bard, P., Bertrand, E., Hollender, F., Kawase, H., et al. (2016). International benchmark on numerical simulations for 1D, nonlinear site response (PRENOLIN): Verification phase based on canonical cases. Bulletin of the Seismological Society of America, 106, 2112–2135. https://doi.org/10.1785/0120150284.
Shi, Y., Mizumoto, M., Yubazaki, N., Otani, M. (1996). A learning algorithm for tuning fuzzy rules based on the gradient descent method. In Proceedings of the Fifth IEEE International Conference on Fuzzy Systems (Vol. 1, pp. 55–61).
Sugeno, M., & Kang, G. (1986). Fuzzy modelling and control of multilayer incinerator. Fuzzy Sets Systems, 18(3), 329–345.
Takagi, T., & Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE Trans: Syst. man.
Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8, 338–353. https://doi.org/10.1016/S0019-9958(65)90241-X.
Acknowledgments
The authors would like to thank the participants of the NGA-West2 programs for providing high-quality data and stimulating ideas. We also thank an anonymous reviewer for their constructive criticism and comments that helped us to improve this study.
Data and Resources
The datasets used in this article have been collected and disseminated by The Pacific Earthquake Engineering Research Center.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Ameur, M., Derras, B. & Zendagui, D. Ground Motion Prediction Model Using Adaptive Neuro-Fuzzy Inference Systems: An Example Based on the NGA-West 2 Data. Pure Appl. Geophys. 175, 1019–1034 (2018). https://doi.org/10.1007/s00024-017-1743-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00024-017-1743-3