A prediction method of ground motion for regions without available observation data (LGB-FS) and its application to both Yangbi and Maduo earthquakes in 2021

Jin Chen; Hong Tang; Wenkai Chen; Naisen Yang

doi:10.1007/s12583-021-1560-6

Turn off MathJax

Article Contents

Article Navigation > Journal of Earth Science > 0 > In press

A prediction method of ground motion for regions without available observation data (LGB-FS) and its application to both Yangbi and Maduo earthquakes in 2021

doi: 10.1007/s12583-021-1560-6

1. State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;
2. Key Laboratory of Environmental Change and Natural Disaster, Ministry of Education, Beijing Normal University, Beijing 100875, China;
3. Lanzhou Institute of Seismology, China Earthquake Administration, Lanzhou 730000, China

Received Date: 2021-07-13

Abstract

Currently available earthquake attenuation equations are locally applicable, and methods based on observation data are not applicable in areas without available observation data. To solve the above problems and further improve the prediction accuracy of ground motion parameters, we present a prediction model referred to as a light gradient boosting machine with feature selection (LGB-FS). It is based on a light gradient boosting machine (LightGBM) constructed using historical strong motion data from the NGA-west2 database and can quickly simulate the distribution of strong motion near the epicenter after an earthquake. Cases study shows that cmpared with GMPE methods and those based on real-time observation data, the model has a better prediction effect in areas without available observation data and be applied to Yangbi earthquake and Maduo earthquake. The feature importance evaluation based on both information gains and partial dependence plots (PDPs) revealed the complex relationships between multiple factors and ground motion parameters, allowing us to better understand their mechanisms and connections.
- LightGBM,
- ground motion parameters,
- NGA-west2,
- feature selection,
- Yangbi,
- Maduo.

References

Abrahamson, N. A., Silva, W. J., 2008. Summary of the Abrahamson & Silva NGA ground motion relations. Earthquake Spectra, 24(1): 67-97. https://doi.org/10.1193/1.2924360

Abrahamson, N. A., Silva, W. J., Kamai, R., 2014. Summary of the ASK14 ground-motion relation for active crustal regions. Earthquake Spectra, 30(3): 1025-1055. https://doi.org/10.1193/070913EQS198M

Akkar, S., Sandikkaya, M. A., Bommer, J., 2014. Empirical ground-motion models for point and extended-source crustal earthquake scenarios in Europe and the Middle East. Bulletin of Earthquake Engineering, 12: 389-390. https://doi.org/10.1007/s10518-013-9461-4

Alavi, A. H., Gandomi, A. H., 2011. Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing. Computer & Structures, 89(23-24): 2176-2194. https://doi.org/10.1016/j.compstruc.2011.08.019

Alavi, A. H., Gandomi, A. H., Modaresnezhad, M., et al., 2011. New ground-motion prediction equations using multi expression programing. Journal of Earthquake Engineering, 15(4): 511-536. https://doi.org/10.1080/13632469.2010.526752

Ambraseys, N. N., Douglas, J., 2003. Near-field horizontal and vertical earthquake ground motions. Soil Dynamics and Earthquake Engineering, 23: 1–18. https://doi.org/10.1016/S0267-7261(02)00153-7

Ambraseys, N. N., Simpson, K. A., Bommer, J., 1996. Prediction of horizontal response spectra in Europe. Earthquake Engineering & Structural Dynamics, 25(4): 371–400. https://doi.org/10.1002/(SICI)1096-9845(199604)25:4<371::AID-EQE550>3.0.CO;2-A

Aptikaev, F., Kopnichev, J., 1980. Correlation between seismic vibration parameters and type of faulting. In: Proceedings of Seventh World Conference on Earthquake Engineering. 8-13 September, 1980. Istanbul.

Boore, D. M., Stewart, J. P., Seyhan, E., et al., 2013. NGA-West2 equations for predicting response spectral accelerations for shallow crustal earthquakes. In: PEER Report No. 2013. Pacific Earthquake Engineering Research Center, University of California, Berkeley, California.

Bozorgnia, Y., Abrahamson, N. A., Atik, L. A., et al., 2014. Nga-west2 research project. Earthquake Spectra, 131(3): 409-444.

Breiman, L., Friedman, J., Olshen, R., et al., 1984. Classification and Regression Trees (CART). Biometrics, 40(3): 358. https://doi.org/10.2307/2530946

Campbell, K. W., 1985. Strong motion attenuation relations: a ten-year perspective. Earthquake Spectra, 1(4): 759–804. https://doi.org/10.1193/1.1585292

Campbell, K.W., Bozorgnia, Y., 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. Earthquake Spectra, 24(1): 139–171. https://doi.org/10.1193/1.2857546

Campbell, K. W., Bozorgnia, Y., 2014. NGA-West2 ground motion model for the average Horizontal components of PGA, PGV, and 5%-damped linear Response Spectra. Earthquake Spectra, 30(3): 1087-1115. https://doi.org/10.1193/062913EQS175M

Chiou, B. S. J., Youngs, R. R., 2014. Update of the Chiou and Youngs NGA ground motion model for average horizontal component of peak ground motion and response spectra. Earthquake Spectra, 30(3): 1117-1153. https://doi.org/10.1193/072813EQS219M

Derakhshani, A., Foruzan, A. H., 2019. Predicting the principal strong ground motion parameters: a deep learning approach. Applied Soft Computing, 80: 192-201. https://doi.org/10.1016/j.asoc.2019.03.029

Derras, B., Bard, P. Y., Cotton, F., et al., 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(4): 1446-1461. https://doi.org/10.1785/0120110088

Derras, B., Bard, P. Y., Cotton, F., 2014. Towards fully data driven ground-motion prediction models for Europe. Bulletin of Earthquake Engineering, 12(1): 495-516. https://doi.org/10.1007/s10518-013-9481-0

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 Reviews, 61(1-2): 43–104. https://doi.org/10.1016/S0012-8252(02)00112-5

Friedman, J. H., 2001. Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5): 1189–1232. https://doi.org/10.1214/aos/1013203451

Gandomi, A. H., Alavi, A. H., Mousavi, M., et al., 2011. A hybrid computational approach to derive new ground-motion prediction equations. Engineering Application of Artificial Intelligence, 24(4): 717-732. https://doi.org/10.1016/j.engappai.2011.01.005

Heath, D., Wald, D. J., Worden, C. B., et al., 2020. A Global Hybrid Vs30 Map with a Topographic-Slope-Based Default and Regional Map Insets. Earthquake Spectra, 36(3): 1570-1584. https://doi.org/10.1177/8755293020911137

Idriss, I. M., 2013. NGA-West2 model for estimating average horizontal values of pseudo-absolute spectral accelerations generated by crustal earthquakes. In: PEER Report No. 2013. Pacific Earthquake Engineering Research Center, University of California, Berkeley, California.

Jafariavval, Y., Derakhshani, A., 2020. New formulae for capacity energy-based assessment of liquefaction triggering. Marine Georesources & Geotechnology, 38(2): 214-222. https://doi.org/10.1080/1064119X.2019.1566297

Kayabali, K., Beyaz, T., 2011. Strong motion attenuation relationship for Turkey-a different perspective. Bulletin of Engineering Geology & the Environment, 70: 467-481. https://doi.org/10.1007/s10064-010-0335-6

Ke, G.L., Meng, Q., Finley, T., et al., 2017. LightGBM: A highly efficient gradient boosting decision tree. In: NIPS’17: Proceeding of the 31st International Conference on Neural Information Processing Systems. December 2017. New York.

Mohammadnejad, A. K., Mousavi, S. M., Torabi, M., et al., 2012. Robust attenuation relations for peak time-domain parameters of strong ground motions. Environmental Earth Science, 67: 53–70. https://doi.org/10.1007/s12665-011-1479-9

Molnar, C., 2019. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Leanpub.

Nagelkerke, N. J. D., 1991. A note on a general definition of the coefficient of determination. Biometrika, 78(3). https://doi.org/10.1093/biomet/78.3.691

Sen, Z., 2011. Supervised fuzzy logic modeling for building earthquake hazard assessment. Expert Systems with Application, 38(12): 14564-14573. https://doi.org/10.1016/j.eswa.2011.05.026

Shiuly, A., Roy, N., Sahu, R. B., 2020. Prediction of peak ground acceleration for himalayan region using artificial neural network and genetic algorithm. Arabian Journal of Geoscience, 13(5): 1-10. https://doi.org/10.1007/s12517-020-5211-5

Sonia, T., Pillai, G. N., Pal, K., 2016. Prediction of peak ground acceleration using ϵ-svr, ν-svr and ls-svr algorithm. Geomatics Natural Hazards & Risk, 8(2): 1-17. https://doi.org/10.1080/19475705.2016.1176604

Tobler, W. R., 1970. A computer movie simulating urban growth in the detroit region. Economic Geography, 46: 234–240.

Tuv, E., Borisov, A., Runger, G., et al., 2009. Feature selection with ensembles, artificial variables, and redundancy elimination. Journal of Machine Learning Research, 10(3): 1341-1366. https://doi.org/10.1145/1577069.1755828

Wen, R., Xu, P., Y. Ren, P., et al., 2017. Development of the strong-motin Flatfile. Earthquake Engineering and Engineering Dynamics, 37(3): 38-47. (in Chinese with English abstract)

Worden, C. B., Wald, D. J., Allen, T. I., et al., 2010. A revised ground-motion and intensity interpolation scheme for shakemap. Bulletin of the Seismological Society of America, 100(6): 3083-3096. https://doi.org/10.1785/0120100101

Yenier, E., Erdoğan, Ö., Akkar, S., 2008. Empirical relationships for magnitude and source-to-site distance conversions using recently compiled Turkish strong-ground motion database. In: The 14th World Conference on Earthquake Engineering. October 12-17, 2008. Beijing.

Youngs, R. R., Day, S. M., Stevens, J. L., 1988. Near field ground motions on rock for large subduction earthquakes. In: Thun, J. L. V., ed., Earthquake Engineering and Soil Dynamics II: Recent Advances in Ground-Motion Evaluation. American Society of Civil Engineers, Reston. 445–462.

Youngs, R. R., Chiou, B., Silva, W. J., et al., 1997. Strong ground motion attenuation relationships for subduction zone earthquakes. Seismological Research Letters, 68(1): 58–73. https://doi.org/10.1785/gssrl.68.1.58

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

PDF View

Article Metrics

Article views(136) PDF downloads(12) Cited by()

Proportional views

A prediction method of ground motion for regions without available observation data (LGB-FS) and its application to both Yangbi and Maduo earthquakes in 2021

1. State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;

2. Key Laboratory of Environmental Change and Natural Disaster, Ministry of Education, Beijing Normal University, Beijing 100875, China;

3. Lanzhou Institute of Seismology, China Earthquake Administration, Lanzhou 730000, China

Received Date: 2021-07-13

Key words:

Abstract: Currently available earthquake attenuation equations are locally applicable, and methods based on observation data are not applicable in areas without available observation data. To solve the above problems and further improve the prediction accuracy of ground motion parameters, we present a prediction model referred to as a light gradient boosting machine with feature selection (LGB-FS). It is based on a light gradient boosting machine (LightGBM) constructed using historical strong motion data from the NGA-west2 database and can quickly simulate the distribution of strong motion near the epicenter after an earthquake. Cases study shows that cmpared with GMPE methods and those based on real-time observation data, the model has a better prediction effect in areas without available observation data and be applied to Yangbi earthquake and Maduo earthquake. The feature importance evaluation based on both information gains and partial dependence plots (PDPs) revealed the complex relationships between multiple factors and ground motion parameters, allowing us to better understand their mechanisms and connections.

HTML

Reference (39)

[1]	Abrahamson, N. A., Silva, W. J., 2008. Summary of the Abrahamson & Silva NGA ground motion relations. Earthquake Spectra, 24(1): 67-97. https://doi.org/10.1193/1.2924360
[2]	Abrahamson, N. A., Silva, W. J., Kamai, R., 2014. Summary of the ASK14 ground-motion relation for active crustal regions. Earthquake Spectra, 30(3): 1025-1055. https://doi.org/10.1193/070913EQS198M
[3]	Akkar, S., Sandikkaya, M. A., Bommer, J., 2014. Empirical ground-motion models for point and extended-source crustal earthquake scenarios in Europe and the Middle East. Bulletin of Earthquake Engineering, 12: 389-390. https://doi.org/10.1007/s10518-013-9461-4
[4]	Alavi, A. H., Gandomi, A. H., 2011. Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing. Computer & Structures, 89(23-24): 2176-2194. https://doi.org/10.1016/j.compstruc.2011.08.019
[5]	Alavi, A. H., Gandomi, A. H., Modaresnezhad, M., et al., 2011. New ground-motion prediction equations using multi expression programing. Journal of Earthquake Engineering, 15(4): 511-536. https://doi.org/10.1080/13632469.2010.526752
[6]	Ambraseys, N. N., Douglas, J., 2003. Near-field horizontal and vertical earthquake ground motions. Soil Dynamics and Earthquake Engineering, 23: 1–18. https://doi.org/10.1016/S0267-7261(02)00153-7
[7]	Ambraseys, N. N., Simpson, K. A., Bommer, J., 1996. Prediction of horizontal response spectra in Europe. Earthquake Engineering & Structural Dynamics, 25(4): 371–400. https://doi.org/10.1002/(SICI)1096-9845(199604)25:4<371::AID-EQE550>3.0.CO;2-A
[8]	Aptikaev, F., Kopnichev, J., 1980. Correlation between seismic vibration parameters and type of faulting. In: Proceedings of Seventh World Conference on Earthquake Engineering. 8-13 September, 1980. Istanbul.
[9]	Boore, D. M., Stewart, J. P., Seyhan, E., et al., 2013. NGA-West2 equations for predicting response spectral accelerations for shallow crustal earthquakes. In: PEER Report No. 2013. Pacific Earthquake Engineering Research Center, University of California, Berkeley, California.
[10]	Bozorgnia, Y., Abrahamson, N. A., Atik, L. A., et al., 2014. Nga-west2 research project. Earthquake Spectra, 131(3): 409-444.
[11]	Breiman, L., Friedman, J., Olshen, R., et al., 1984. Classification and Regression Trees (CART). Biometrics, 40(3): 358. https://doi.org/10.2307/2530946
[12]	Campbell, K. W., 1985. Strong motion attenuation relations: a ten-year perspective. Earthquake Spectra, 1(4): 759–804. https://doi.org/10.1193/1.1585292
[13]	Campbell, K.W., Bozorgnia, Y., 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. Earthquake Spectra, 24(1): 139–171. https://doi.org/10.1193/1.2857546
[14]	Campbell, K. W., Bozorgnia, Y., 2014. NGA-West2 ground motion model for the average Horizontal components of PGA, PGV, and 5%-damped linear Response Spectra. Earthquake Spectra, 30(3): 1087-1115. https://doi.org/10.1193/062913EQS175M
[15]	Chiou, B. S. J., Youngs, R. R., 2014. Update of the Chiou and Youngs NGA ground motion model for average horizontal component of peak ground motion and response spectra. Earthquake Spectra, 30(3): 1117-1153. https://doi.org/10.1193/072813EQS219M
[16]	Derakhshani, A., Foruzan, A. H., 2019. Predicting the principal strong ground motion parameters: a deep learning approach. Applied Soft Computing, 80: 192-201. https://doi.org/10.1016/j.asoc.2019.03.029
[17]	Derras, B., Bard, P. Y., Cotton, F., et al., 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(4): 1446-1461. https://doi.org/10.1785/0120110088
[18]	Derras, B., Bard, P. Y., Cotton, F., 2014. Towards fully data driven ground-motion prediction models for Europe. Bulletin of Earthquake Engineering, 12(1): 495-516. https://doi.org/10.1007/s10518-013-9481-0
[19]	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 Reviews, 61(1-2): 43–104. https://doi.org/10.1016/S0012-8252(02)00112-5
[20]	Friedman, J. H., 2001. Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5): 1189–1232. https://doi.org/10.1214/aos/1013203451
[21]	Gandomi, A. H., Alavi, A. H., Mousavi, M., et al., 2011. A hybrid computational approach to derive new ground-motion prediction equations. Engineering Application of Artificial Intelligence, 24(4): 717-732. https://doi.org/10.1016/j.engappai.2011.01.005
[22]	Heath, D., Wald, D. J., Worden, C. B., et al., 2020. A Global Hybrid Vs30 Map with a Topographic-Slope-Based Default and Regional Map Insets. Earthquake Spectra, 36(3): 1570-1584. https://doi.org/10.1177/8755293020911137
[23]	Idriss, I. M., 2013. NGA-West2 model for estimating average horizontal values of pseudo-absolute spectral accelerations generated by crustal earthquakes. In: PEER Report No. 2013. Pacific Earthquake Engineering Research Center, University of California, Berkeley, California.
[24]	Jafariavval, Y., Derakhshani, A., 2020. New formulae for capacity energy-based assessment of liquefaction triggering. Marine Georesources & Geotechnology, 38(2): 214-222. https://doi.org/10.1080/1064119X.2019.1566297
[25]	Kayabali, K., Beyaz, T., 2011. Strong motion attenuation relationship for Turkey-a different perspective. Bulletin of Engineering Geology & the Environment, 70: 467-481. https://doi.org/10.1007/s10064-010-0335-6
[26]	Ke, G.L., Meng, Q., Finley, T., et al., 2017. LightGBM: A highly efficient gradient boosting decision tree. In: NIPS’17: Proceeding of the 31st International Conference on Neural Information Processing Systems. December 2017. New York.
[27]	Mohammadnejad, A. K., Mousavi, S. M., Torabi, M., et al., 2012. Robust attenuation relations for peak time-domain parameters of strong ground motions. Environmental Earth Science, 67: 53–70. https://doi.org/10.1007/s12665-011-1479-9
[28]	Molnar, C., 2019. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Leanpub.
[29]	Nagelkerke, N. J. D., 1991. A note on a general definition of the coefficient of determination. Biometrika, 78(3). https://doi.org/10.1093/biomet/78.3.691
[30]	Sen, Z., 2011. Supervised fuzzy logic modeling for building earthquake hazard assessment. Expert Systems with Application, 38(12): 14564-14573. https://doi.org/10.1016/j.eswa.2011.05.026
[31]	Shiuly, A., Roy, N., Sahu, R. B., 2020. Prediction of peak ground acceleration for himalayan region using artificial neural network and genetic algorithm. Arabian Journal of Geoscience, 13(5): 1-10. https://doi.org/10.1007/s12517-020-5211-5
[32]	Sonia, T., Pillai, G. N., Pal, K., 2016. Prediction of peak ground acceleration using ϵ-svr, ν-svr and ls-svr algorithm. Geomatics Natural Hazards & Risk, 8(2): 1-17. https://doi.org/10.1080/19475705.2016.1176604
[33]	Tobler, W. R., 1970. A computer movie simulating urban growth in the detroit region. Economic Geography, 46: 234–240.
[34]	Tuv, E., Borisov, A., Runger, G., et al., 2009. Feature selection with ensembles, artificial variables, and redundancy elimination. Journal of Machine Learning Research, 10(3): 1341-1366. https://doi.org/10.1145/1577069.1755828
[35]	Wen, R., Xu, P., Y. Ren, P., et al., 2017. Development of the strong-motin Flatfile. Earthquake Engineering and Engineering Dynamics, 37(3): 38-47. (in Chinese with English abstract)
[36]	Worden, C. B., Wald, D. J., Allen, T. I., et al., 2010. A revised ground-motion and intensity interpolation scheme for shakemap. Bulletin of the Seismological Society of America, 100(6): 3083-3096. https://doi.org/10.1785/0120100101
[37]	Yenier, E., Erdoğan, Ö., Akkar, S., 2008. Empirical relationships for magnitude and source-to-site distance conversions using recently compiled Turkish strong-ground motion database. In: The 14th World Conference on Earthquake Engineering. October 12-17, 2008. Beijing.
[38]	Youngs, R. R., Day, S. M., Stevens, J. L., 1988. Near field ground motions on rock for large subduction earthquakes. In: Thun, J. L. V., ed., Earthquake Engineering and Soil Dynamics II: Recent Advances in Ground-Motion Evaluation. American Society of Civil Engineers, Reston. 445–462.
[39]	Youngs, R. R., Chiou, B., Silva, W. J., et al., 1997. Strong ground motion attenuation relationships for subduction zone earthquakes. Seismological Research Letters, 68(1): 58–73. https://doi.org/10.1785/gssrl.68.1.58

A prediction method of ground motion for regions without available observation data (LGB-FS) and its application to both Yangbi and Maduo earthquakes in 2021

doi: 10.1007/s12583-021-1560-6

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views