Abstract
Application of the artificial neural network (ANN) to predict pseudospectral acceleration or peak ground acceleration is explored in the study. The training of ANN model is carried out using feed-forward back-propagation method and about 600 records from 39 California earthquakes. The statistics of the residuals or modeling error for the trained ANN-based models are almost the same as those for the parametric ground motion prediction equations, derived through regression analysis; the residual or modeling error can be modeled as a normal variate. The similarity and differences between the predictions by these two approaches are shown. The trained ANN-based models, however, are not robust because the models with almost identical mean square errors do not always lead to the same predictions. This undesirable behaviour for predicting the ground motion measures has not been shown or discussed in the literature; the presented results, at least, serve to raise questions and caution on this problem. A practical approach to ameliorate this problem, perhaps, is to consider several trained ANN models, and to take the average of the predicted values from the trained ANN models as the predicted ground motion measure.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Abrahamson N A and Yongs R R (1992). A stable algorithm for regression analyses using the random effects model. Bull Seismol Soc Am82(1): 505–510.
Adams J and Halchuk S (2003). Fourth generation seismic hazard maps of Canada: values for over 650 Canadian localities intended for the 2005 National Building Code of Canada. Open-File 4459, Geological Survey of Canada, Ottawa, Ontario, Canada.
Ahmad I, El Naggar M H and Khan A N (2008). Neural network based attenuation of strong motion peaks in Europe. Journal of Earthquake Engineering12(5): 663–680.
Ambraseys N N, Simpson K A and Bommer J J (1996). Prediction of horizontal response spectra in Europe. Earthquake Engineering and Structural Dynamics25(4): 371–400.
Amiri G G, Bagheri A and Razaghi S A S (2009). Generation of multiple earthquake accelerograms compatible with spectrum via the wavelet packet transform and stochastic neural networks. Journal of Earthquake Engi neering13(7): 899–915.
Atkinson G M and Boore D M (2003). Empirical groundmotion relations for subduction-zone earthquakes and their application to Cascadia and other regions. Bull Seismol Soc Am93: 1 703–1 729.
Benjamin J R and Cornell C A (1970). Probability, Statistics and Decision for Civil Engineers. McGraw-Hill, New York.
Boore D M, Joyner W B and Fumal T E (1997). Equations for estimating horizontal response spectra and peak acceleration from western North America. Seism Res Lett68: 128–153.
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. Seism Res Lett68(1): 154–179.
Douglas J (2003). Earthquake ground motion estimation using strong-motion records: A review of equations for the estimation of peak ground acceleration and response spectral ordinates. Earth-Science Reviews61(1–2): 43–104.
Emami S M R, Harada T and Iwao Y (1996). Prediction of peak horizontal acceleration using an artificial neural network model. Structural Engineering and Earthquake Engineering JSCE 13(2): 111s–118s.
Frankel A, Mueller C, Barnhard T, Perkins D, Leyendecker E V, Dickman N, Hanson S and Hopper M (1996). National seismic hazard maps. Open-File 96-532, U.S. Department of the Interior, U.S. Geological Survey, Denver, CO, pp. 5–8.
Funahashi K (1989). On the approximate realization of continuous mappings by neural networks. Neural Networks2(3): 183–192.
Garcia S R, Romo M P and Mayoral J M (2007). Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks. Geofisica Internacional46(1): 51–63.
Goda K and Hong H P (2009). Deaggregation of seismic loss of spatially distributed buildings. Bull Earthq Eng7: 255–272.
Günaydin K and Günaydin A (2008). Peak ground acceleration prediction by artificial neural networks for northwestern Turkey. Mathematical Problems in Engineering Art. No.: 919420
Hagan M T and Menhaj M (1994). Training feed-forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks5(6): 989–993.
Haykin S (1999). Neural Networks: A Comprehensive Foundation. 2nd edition. Prentice-Hall, Englewood Cliffs, NJ, USA, pp. 156–255.
Hong H P and Goda K (2007). Orientation-dependent ground motion measure for seismic hazard assessment. Bull Seismol Soc Am97: 1 525–1 538.
Hong H P, Zhang Y and Goda K (2009). Effect of the spatial correlation on the estimated ground motion prediction equations. Bull Seismol Soc Am99(2A): 928–934.
Joyner W B and Boore D M (1993). Methods for regression analysis of strong-motion data. Bull Seismol Soc Am83(2): 469–487.
Kerh T and Chu D (2002). Neural networks approach and microtremor measurements in estimating peak ground acceleration due to strong motion. Advances in Engineering Software33(11–12): 733–742.
Lee S C and Han S W (2002). Neural-network-based models for generating artificial earthquakes and response spectra. Computers and Structures80(20–21): 1 627–1 638.
Lin C C J and Ghaboussi J (2001). Generating multiple spectrum compatible accelerograms using stochastic neural networks. Earthquake Engineering and Structural Dynamics30(7): 1 021–1 042.
Marquardt D W (1963). An algorithm for least squares estimation of non-linear parameters. Journal of the Society for Industrial and Applied Mathematics11(2): 431–41.
McGuire R K (2004). Seismic Hazard and Risk Analysis. Earthquake Engineering Research Institute, Oakland, CA, pp. 74–91.
Nguyen D and Widrow B (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proceedings of the International Joint Conference on Neural Networks. IEEE, San Diego, CA., 3: 21–26.
Pacific Earthquake Engineering Research (PEER) Center (2006). Next Generation Attenuation database. http://peer.berkeley.edu/nga/index.html. (last accessed April 4th, 2006).
Press W H, Teukolsky S A, Vetterling A W T and Flannery B P (1992). Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, New York. pp. 683–688.
Principe C, Euliano N R and Lefebvre W C (1999). Neural and Adaptive Systems: Fundamentals through Simulation. John Wiley and Sons, New York, NY, USA.
Rumelhart D E, Hinton G E and Williams R J (1986). Learning Internal Representation by Error Backpropagation, in Parallel Distributed Processing: Explorations Microstructure of Cognition (Vol. 1). MIT Press, Cambridge, Mass, USA, pp. 318–362.
Singh S K, Mena E, Castro R and Carmona C (1987). Empirical prediction of ground motion in Mexico City from coastal earthquakes. Bull Seismol Soc Am77: 1 862–1 867.
Wang H S (1993). Intelligent determination of peak ground motion parameters based on intensity assessed by artificial neural network. Acta Seismologica Sinica6(3): 705–712.
Youngs R R, Silva W J and Humphrey J R (1997). Strong ground motion attenuation relationships for subduction zone earthquakes. Seism Res Lett68: 58–72.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Hong, H., Liu, T. & Lee, CS. Observations on the application of artificial neural network to predicting ground motion measures. Earthq Sci 25, 161–175 (2012). https://doi.org/10.1007/s11589-012-0843-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11589-012-0843-5
Key words
- neural network
- peak ground acceleration
- pseudospectral acceleration
- seismic ground motion measures
- uncertainty