Is it Possible to Generate Good Earthquake Risk Models Using Genetic Algorithms?

Claus Aranha, Yuri Cossich Lavinas, Marcelo Ladeira, Bogdan Enescu

2014

Abstract

Understanding the mechanisms and patterns of earthquake occurrence is of crucial importance for assessing and mitigating the seismic risk. In this work we analyze the viability of using Evolutionary Computation (EC) as a means of generating models for the occurrence of earthquakes. Our proposal is made in the context of the "Collaboratory for the Study of Earthquake Predictability" (CSEP), an international effort to standardize the study and testing of earthquake forecasting models. We use a standard Genetic Algorithm (GA) with real valued genome, where each allele corresponds to a bin in the forecast model. The design of an appropriate fitness function is the main challenge for this task, and we describe two different proposals based on the log-likelihood of the candidate model against the training data set. The resulting forecasts are compared with the Relative Intensity algorithm, which is traditionally employed by the CSEP community as a benchmark, using data from the Japan Meteorological Agency (JMA) earthquake catalog. The forecasts generated by the GA were competitive with the benchmarks, specially in scenarios with a large amount of inland seismic activity.

References

  1. Aranha, C. and Enescu, B. (2014). A study on the viability of evolution methods for the generation of earthquake predictability models. In The 28th annual conference of the Japan Society on Artificial Intelligence.
  2. Cabalar, A. F. and Cevik, A. (2009). Genetic programmingbased attenuation relationship: An application of recent earthquakes in Turkey. Computers and Geosciences, 35:1884-1896.
  3. Kennet, B. L. N. and Sambridge, M. S. (1992). Earthquake location genetic algorithms for teleseisms. Physics of the Earth and Planetary Interiors, 75(1-3):103-110.
  4. Kerh, T., Gunaratnam, D., and Chan, Y. (2010). Neural computing with genetic algorithm in evaluating potentially hazardous metropolitan areas result from earthquake. Neural Comput. Appl., 19(4):521-529.
  5. Kermani, E., Jafarian, Y., and Baziar, M. H. (2009). New predictive models for the vmax=amax ratio of strong ground motions using genetic programming. International Journal of Civil Engineering, 7(4):236-247.
  6. Koza, J. R., Keane, M. A., and Streeter, M. J. (2003). What's AI done for me lately? Genetic programming's human-competitive results. IEEE Intelligent Systems, 18(3):25-31.
  7. Nanjo, K. Z. (2011). Earthquake forecasts for the CSEP Japan experiment based on the RI algorithm. Earth Planets Space, 63:261-274.
  8. Nanjo, K. Z., Tsuruoka, H., Hirata, N., and Jordan, T. H. (2011). Overview of the first earthquake forecast testing experiment in Japan. Earth Planets Space, 63:159-169.
  9. Nicknam, A., Abbasnia, R., Eslamian, Y., Bozorgnasab, M., and Mosabbeb, E. A. (2010). Source parameters estimation of 2003 Bam earthquake Mw 6.5 using empirical Green's function method, based on an evolutionary approach. J. Earth Syst. Sci., 119(3):383-396.
  10. Press, W. H., Teukolsky, S. A., Vetterling, W. T., and Flannery, B. P. (2007). Numerical Recipes, The Art of Scientific Computing. Cambridge University Press, third edition.
  11. Ramos, J. I. E. and VĂ¡zques, R. A. (2011). Locating seismic-sense stations through genetic algorithms. In Proceedings of the GECCO'11, pages 941-948, Dublin, Ireland. ACM.
  12. Saegusa, A. (1999). Japan tries to understand quakes, not predict them. Nature, 397:284-284.
  13. Schorlemmer, D., Gerstenberger, M., Wiemer, S., Jackson, D., and Rhoades, D. A. (2007). Earthquake likelihood model testing. Seismological Research Letters, 78(1):17-29.
  14. Zechar, J. D. and Jordan, T. H. (2010). The area skill score statistic for evaluating earthquake predictability experiments. Pure and Applied Geophysics, 167(8- 9):893-906.
  15. Zhang, Q. and Wang, C. (2012). Using genetic algorithms to optimize artificial neural network: a case study on earthquake prediction. In Second International Conference on Genetic and Evolutionary Computing, pages 128-131. IEEE.
  16. Zhou, F. and Zhu, X. (2014). Earthquake prediction based on LM-BP neural network. In Liu, X. and Ye, Y., editors, Proceedings of the 9th International Symposium on Linear Drives for Industry Applications, Volume 1, volume 270 of Lecture Notes in Electrical Engineering, pages 13-20. Springer Berlin Heidelberg.
Download


Paper Citation


in Harvard Style

Aranha C., Lavinas Y., Ladeira M. and Enescu B. (2014). Is it Possible to Generate Good Earthquake Risk Models Using Genetic Algorithms? . In Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014) ISBN 978-989-758-052-9, pages 49-58. DOI: 10.5220/0005072600490058


in Bibtex Style

@conference{ecta14,
author={Claus Aranha and Yuri Cossich Lavinas and Marcelo Ladeira and Bogdan Enescu},
title={Is it Possible to Generate Good Earthquake Risk Models Using Genetic Algorithms?},
booktitle={Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)},
year={2014},
pages={49-58},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005072600490058},
isbn={978-989-758-052-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)
TI - Is it Possible to Generate Good Earthquake Risk Models Using Genetic Algorithms?
SN - 978-989-758-052-9
AU - Aranha C.
AU - Lavinas Y.
AU - Ladeira M.
AU - Enescu B.
PY - 2014
SP - 49
EP - 58
DO - 10.5220/0005072600490058