DOI QR코드

DOI QR Code

Assessment of maximum liquefaction distance using soft computing approaches

  • Kishan Kumar (Department of Civil Engineering, National Institute of Technology Patna) ;
  • Pijush Samui (Department of Civil Engineering, National Institute of Technology Patna) ;
  • Shiva S. Choudhary (Department of Civil Engineering, National Institute of Technology Patna)
  • 투고 : 2023.05.25
  • 심사 : 2024.05.03
  • 발행 : 2024.05.25

초록

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (Re), maximum fault distance (Rf), or maximum hypocentral distance (Rh), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (Re, Rf, or Rh) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

키워드

참고문헌

  1. Adarsh, S., Dhanya, R., Krishna, G., Merlin, R. and Tina, J. (2012), "Prediction of ultimate bearing capacity of cohesionless soils using soft computing techniques", ISRN Artificial Intelligence, 2012, 1-10. https://doi.org/10.5402/2012/628496
  2. Alessio, G., Alfonsi, L., Brunori, C.A., Burrato, P., Casula, G., Cinti, F.R., Civico, R., Colini, L., Cucci, L., De Martini, P.M., Falcucci, E., Galadini, F., Gaudiosi, G., Gori, S., Mariucci, M. T., Montone, P., Moro, M., Nappi, R., Nardi, A. andVillani, F. (2013), "Liquefaction phenomena associated with the Emilia earthquake sequence of May-June 2012 (Northern Italy)", Nat. Hazard. Earth System Sci., 13(4), 935-947. https://doi.org/10.5194/nhess-13-935-2013.
  3. Alibrahim, H. and Ludwig, S.A. (2021), "Hyperparameter optimization: Comparing genetic algorithm against grid search and bayesian optimization", Proceedings of the 2021 IEEE Congress on Evolutionary Computation (CEC).
  4. Ambraseys, N.N. (1988), "Engineering seismology: Part II", Earthq. Eng. Struct. D., 17(1), 51-105. https://doi.org/10.1002/eqe.4290170102.
  5. Anitescu, C., Atroshchenko, E., Alajlan, N. and Rabczuk, T. (2019), "Artificial neural network methods for the solution of second order boundary value problems", Comput, Mater. Continua, 59(1). https://doi.org/10.32604/cmc.2019.06641
  6. Ardeshiri-Lajimi, S., Yazdani, M. and Assadi-Langroudi, A. (2016), "A study on the liquefaction risk in seismic design of foundations", Geomech. Eng., 11(6), 805-820. https://doi.org/10.12989/gae.2016.11.6.805.
  7. Armaghani, D.J., Harandizadeh, H., Momeni, E., Maizir, H. and Zhou, J. (2022), "An optimized system of GMDH-ANFIS predictive model by ICA for estimating pile bearing capacity", Artif. Intell. Rev., 55(3), 2313-2350. https://doi.org/10.1007/s10462-021-10065-5.
  8. Aydan, O ., Ulusay, R. and Kumsar, H. (2000), "Liquefaction phenomenon in the earthquakes of Turkey, including recent Erzincan, Dinar and Adana-Ceyhan earthquakes", Proceedings of the 12th World Conference on Earthquake Engineering, Auckland, 30 January -4 February.
  9. Bai, X.D., Cheng, W.C., Ong, D.E.L. and Li, G. (2021), "Evaluation of geological conditions and clogging of tunneling using machine learning", Geomech. Eng., 25(1), 59-73. https://doi.org/10.12989/gae.2021.25.1.059.
  10. Bengio, Y. (2000), "Gradient-based optimization of hyperparameters", Neural Comput., 12(8), 1889-1900. https://doi.org/10.1162/089976600300015187
  11. Bergstra, J. and Bengio, Y. (2012), "Random search for hyper-parameter optimization", J. Machine Learning Res., 13(2).
  12. Bottou, L. (2010). "Large-scale machine learning with stochastic gradient descent", Proceedings of the COMPSTAT'2010: 19th International Conference on Computational Statistics, Paris France, August 22-27, 2010 Keynote, Invited and Contributed Papers.
  13. Pirrotta, C., Barbano, M.S., Guarnieri, P. and Gerardi, F. (2009), "A new dataset and empirical relationships between magnitude/intensity and epicentral distance for liquefaction in central-eastern Sicily", Ann. Geophys., 50(6), 763-774. https://doi.org/10.4401/ag-3055.
  14. Cetin, K.O., Mylonakis, G., Sextos, A. and Stewart, J.P. (2022), "Reconnaissance of 2020 M 7.0 Samos Island (Aegean Sea) earthquake", Bull. Earthq. Eng., 20(14), 7707-7712. https://doi.org/10.1007/s10518-021-01212-y.
  15. Chen, T. and Guestrin, C. (2016), "Xgboost: A scalable tree boosting system", Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, August.
  16. Dibike, Y.B., Velickov, S., Solomatine, D. and Abbott, M.B. (2001), "Model induction with support vector machines: introduction and applications", J. Comput. Civil Eng., 15(3), 208-216. https://doi.org/10.1061/(ASCE)0887-3801(2001)15:3(208).
  17. Galli, P. (2000), "New empirical relationships between magnitude and distance for liquefaction", Tectonophysics, 324(3), 169-187. https://doi.org/10.1016/S0040-1951(00)00118-9.
  18. Gazetas, G. and Botsis, J. (1981), "Local soil effects and liquefaction in the 1978 Thessaloniki earthquakes", Proceedings of the International Conference on Recent Advances Geotechnical Earthquake Engineering & Soil Dynamics. University of Missouri-Rolla, Rolla, Missouri, April.
  19. Goh, A.T.C. and Goh, S.H. (2007), "Support vector machines: their use in geotechnical engineering as illustrated using seismic liquefaction data", Comput. Geotech., 34(5), 410-421. https://doi.org/10.1016/j.compgeo.2007.06.001.
  20. Guo, X.C., Yang, J.H., Wu, C.G., Wang, C.Y. and Liang, Y.C. (2008), "A novel LS-SVMs hyper-parameter selection based on particle swarm optimization", Neurocomput., 71(16), 3211-3215. https://doi.org/10.1016/j.neucom.2008.04.027.
  21. Hoang, N.D. and Bui, D.T. (2018), "Predicting earthquake-induced soil liquefaction based on a hybridization of kernel Fisher discriminant analysis and a least squares support vector machine: A multi-dataset study", Bull. Eng. Geol. Environ., 77(1), 191-204. https://doi.org/10.1007/s10064-016-0924-0.
  22. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Comput., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
  23. Hu, J. (2021), "Data cleaning and feature selection for gravelly soil liquefaction", Soil Dyn. Earthq. Eng., 145, 106711. https://doi.org/10.1016/j.soildyn.2021.106711.
  24. Hu, J. (2022a), "Empirical relationships between earthquake magnitude and maximum distance based on the extended global liquefaction-induced damage cases", Acta Geotechnica, 18, 1-15. https://doi.org/10.1007/s11440-022-01637-y.
  25. Hu, J. (2022b), "The database of earthquake-induced liquefaction", Mendeley Data, VI. https://doi.org/10.17632/3d2483vxb2.1.
  26. Hu, J. and Liu, H. (2019), "Bayesian network models for probabilistic evaluation of earthquake-induced liquefaction based on CPT and Vs databases", Eng. Geol., 254(1), 76-88. https://doi.org/10.1016/j.enggeo.2019.04.003.
  27. James, G., Witten, D., Hastie, T. and Tibshirani, R. (2013), An introduction to statistical learning, 112, Springer.
  28. Javadi, A.A. and Rezania, M. (2009), "Applications of artificial intelligence and data mining techniques in soil modeling", Geomech. Eng., 1(1), 53-74. https://doi.org/10.12989/gae.2009.1.1.053.
  29. Jiang, W., Li, Z.Y. and Lu, K.Y. (2019), "Preliminary analysis of liquefaction characteristics induced by the Songyuan earthquake of May 28 in Jilin", China, 39(3), 52-60. https://doi.org/10.13197/j.eeev.2019.03.52.Jiangw.006.
  30. Kamran, M., Shahani, N.M. and Armaghani, D.J. (2022), "Decision support system for underground coal pillar stability using unsupervised and supervised machine learning approaches", Geomech. Eng., 30(2), 107-121. https://doi.org/10.12989/gae.2022.30.2.107.
  31. Kumar, D.R., Samui, P. and Burman, A. (2022), "Prediction of probability of liquefaction using soft computing techniques", J. Institution of Engineers (India): Series A, 103(4), 1195-1208. https://doi.org/10.1007/s40030-022-00683-9
  32. Kumar, K., Samui, P. and Choudhary, S.S. (2023), "State parameter based liquefaction probability evaluation", Int. J. Geosynthetics Ground Eng., 9(6), 76. https://doi.org/10.1007/s40891-023-00495-2.
  33. Kumar, P., Rao, B., Burman, A., Kumar, S. and Samui, P. (2023), "Spatial variation of permeability and consolidation behaviors of soil using ordinary kriging method", Groundwater for Sustain. Development, 20, 100856. https://doi.org/10.1016/j.gsd.2022.100856.
  34. Kumar, P. and Samui, P. (2022), "Design of an energy pile based on CPT data using soft computing techniques", Infrastructures, 7(12), 169. https://doi.org/10.3390/infrastructures7120169.
  35. Kuribayashi, E. and Tatsuoka, F. (1975), "Brief review of liquefaction during earthquakes in Japan", Soils Found., 15(4), 81-92. https://doi.org/10.3208/sandf1972.15.4_81.
  36. LeCun, Y. and Bengio, Y. (1995), "Convolutional networks for images, speech, and time series. In The handbook of brain theory and neural networks. The MIT Press,Cambridge, Massachusetts, USA.
  37. Lee, C.Y. and Chern, S.G. (2013). Application of a support vector machine for liquefaction assessment", J. Mar. Sci.Tech. (Taiwan), 21(3), 318-324. https://doi.org/10.6119/JMST-012-0518-3.
  38. Liu, L.L., Yang, C. and Wang, X.M. (2021), "Landslide susceptibility assessment using feature selection based machine learning models", Geomech. Eng., 25(1), 1-16. https://doi.org/10.12989/gae.2021.25.1.001
  39. Mahmoodzadeh, A., Taghizadeh, M., Mohammed, A.H., Ibrahim, H.H., Samadi, H., Mohammadi, M. and Rashidi, S. (2022), "Tunnel wall convergence prediction using optimized LSTM deep neural network", Geomech. Eng., 31(6), 545-556. https://doi.org/10.12989/gae.2022.31.6.545.
  40. Ochoa, L.H., Nino, L.F. and Vargas, C.A. (2018), "Fast estimation of earthquake epicenter distance using a single seismological station with machine learning techniques", Dyna, 85(204), 161-168. https://doi.org/10.15446/dyna.v85n204.68408
  41. Pal, M. and Deswal, S. (2008), "Modeling pile capacity using support vector machines and generalized regression neural network", J. Geotech. Geoenviron. Eng., 134(7), 1021-1024. https://doi.org/10.1061/(asce)1090-0241(2008)134:7(1021).
  42. Papadopoulos, G.A. and Lefkopoulos, G. (1993), "Magnitude-distance relations for liquefaction in soil from earthquakes", Bull. Seismol. Soc. Am., 83(3), 925-938. https://doi.org/10.1785/bssa0840062019.
  43. Papathanassiou, G., Pavlides, S., Christaras, B. and Pitilakis, K. (2005), "Liquefaction case histories and empirical relations of earthquake magnitude versus distance from the broader Aegean region", J. Geodynam., 40(2-3), 257-278. https://doi.org/10.1016/j.jog.2005.07.007.
  44. Samaniego, E., Anitescu, C., Goswami, S., Nguyen-Thanh, V.M., Guo, H., Hamdia, K., Zhuang, X. and Rabczuk, T. (2020), "An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications", Comput. Method. Appl. M., 362, 112790. https://doi.org/10.1016/j.cma.2019.112790.
  45. Samui, P. (2007), "Seismic liquefaction potential assessment by using relevance vector machine", Earthq. Eng. Eng. Vib., 6, 331-336. https://doi.org/10.1007/s11803-007-0766-7
  46. Samui, P. and Sitharam, T.G. (2008), "Least-square support vector machine applied to settlement of shallow foundations on cohesionless soils", Int. J. Numer. Anal. Method. Geomech., 32(17), 2033-2043. https://doi.org/10.1002/nag.731.
  47. Schuster, M. and Paliwal, K.K. (1997), "Bidirectional recurrent neural networks", IEEE T. Signal Pr., 45(11), 2673-2681. https://doi.org/10.1109/78.650093
  48. Talwani, P. and Cox, J. (1985), "Paleoseismic evidence for recurrence of earthquakes near Charleston, South Carolina", Science, 229(4711), 379-381. https://doi.org/10.1126/science.229.4711.379.
  49. Wang, C.Y., Wong, A., Dreger, D.S. and Manga, M. (2006), "Liquefaction limit during earthquakes and underground explosions: Implications on ground-motion attenuation", Bull. Seismol. Soc. Am., 96(1), 355-363. https://doi.org/10.1785/0120050019
  50. Xu, G., Liu, Z., Sun, Y., Wang, X., Lin, L. and Ren, Y. (2016), "Experimental characterization of storm liquefaction deposits sequences", Mar. Geol., 382, 191-199. https://doi.org/10.1016/j.margeo.2016.10.015.
  51. Xu, X., Xu, G., Yang, J., Xu, Z. and Ren, Y. (2021), "Field observation of the wave-induced pore pressure response in a silty soil seabed", Geo-Marine Lett., 41(1), 13. https://doi.org/10.1007/s00367-020-00680-6