A Review on Application of Machine Learning Techniques in Seismic Analysis of Timber Structures

Abstract:

In the last two decades, great progress in Machine Learning can be seen in various fields of structural engineering including seismic analysis. This paper focuses on the cross-filed of Machine Learning (ML) and seismic engineering and provides an overview on different ML techniques been used in seismic analysis studies, compare these techniques and their application to study the seismic response of timber structures. The comparison of common supervised ML techniques in this paper are Multi Linear Regression, Regression Tree, Regression Forest, K Nearest Neighbor, Support Vector Regression and Artificial Neural Networks. The recent increase in studies of ML is largely focused on Reinforced Concrete (RC) structures but its application for the behavior of timber structures is still to be explored. Timber structures are considered as the best performing material under strong ground motions. However, the problems associated with timber structures are lack of experimental data, standard numerical models and design codes. It has been observed that application of ML in this domain is new but considered as an increasingly dynamic area of high impact result where new horizons of research topics are waiting to be investigated. The review of different studies demonstrated the potential of improving the prediction of seismic performance and structural behavior by the use of ML. These methods allow more efficient and accurate modelling of complex problems than traditional methods.

• Periodical: Construction Technologies and Architecture (Volume 17)
• Pages: 139-147
• DOI: https://doi.org/10.4028/p-5xmU1e
• Online since: April 2025
• Authors: Syed Ashraf Abbas*
• Keywords: Machine Learning, Numerical Modelling, Seismic Analysis, Timber Structures

References

[1] H. M. Somasekharaiah, M. S. Y. B, and M. B. S, "A Comparative Study on Lateral Force Resisting System For Seismic Loads," p.1138–1144, 2016.

[2] Q. Liu, W. Zhang, M. W. Bhatt, and A. Kumar, "No Title," Nonlinear Eng., vol. 10, no. 1, p.574–582, 2021, doi:.

DOI: 10.1515/nleng-2021-0048

[3] S. Fenves and T. Norabhoompipat, "POTENTIALS FOR ARTIFICIAL INTELLIGENCE APPLICATIONS IN STRUCTURAL ENGINEERING DESIGN AND DETAILING.," [No source Inf. available].

[4] J. Bennett, L. Creary, and R. Englemore, "James Bennett, Lewis Creary, Robert Englemore and Robert klosh COMPUTER S C I E N C E D E P A R T M E N T School of Humanities and Sciences STANFORD UNIVERSITY," no. September, 1978.

[5] R. Sun, "tngineering," vol. 5, 1990.

[6] M. C. Porcu, C. Bosu, and I. Gavrić, "Non-linear dynamic analysis to assess the seismic performance of cross-laminated timber structures," J. Build. Eng., vol. 19, p.480–493, 2018.

DOI: 10.1016/j.jobe.2018.06.008

[7] Y. Xie, M. Eeri, M. E. Sichani, J. E. Padgett, M. Eeri, and M. Eeri, "The promise of implementing machine learning in earthquake engineering : A state-of-the-art review," 2020.

DOI: 10.1177/8755293020919419

[8] A. Alam, "Define machine learning and describe the main types of machine learning," no. August, 2023.

[9] D. H. Maulud and A. M. Abdulazeez, "A Review on Linear Regression Comprehensive in Machine Learning," vol. 01, no. 04, p.140–147, 2020.

DOI: 10.38094/jastt1457

[10] O. Karayel and G. Özay, "Seismic Performance Assessment of Reinforced Concrete Building Stock Using Artificial Neural Network and Linear Regression Analysis BT - Sustainable Civil Engineering at the Beginning of Third Millennium," 2024, p.374–386.

DOI: 10.1007/978-981-97-1781-1_35

[11] M. Mondol, "Analysis and Prediction of Earthquakes using different Machine Learning techniques," p.2–10, 2021.

[12] S. Kwag, D. Hahm, M. Kim, and S. Eem, "Development of a Probabilistic Seismic Performance Assessment Model of Slope Using Machine Learning Methods," 2020.

DOI: 10.3390/su12083269

[13] B. U. Gokkaya, J. W. Baker, and G. G. Deierlein, "Estimation and impacts of model parameter correlation for seismic performance assessment of reinforced concrete structures," Struct. Saf., vol. 69, p.68–78, 2017.

DOI: 10.1016/j.strusafe.2017.07.005

[14] Z. Jabari, S. Mohammad, I. Khodakarami, and F. Behnamfar, "Development of seismic fragility curves for RC / MR frames using machine learning methods," Asian J. Civ. Eng., vol. 24, no. 3, p.823–836, 2023.

DOI: 10.1007/s42107-022-00533-w

[15] H. D. Nguyen, Y.-J. Lee, J. M. LaFave, and M. Shin, "Seismic fragility analysis of steel moment frames using machine learning models," Eng. Appl. Artif. Intell., vol. 126, p.106976, 2023.

DOI: 10.1016/j.engappai.2023.106976

[16] H. Dabiri, A. Faramarzi, A. Dall'Asta, E. Tondi, and F. Micozzi, "A machine learning-based analysis for predicting fragility curve parameters of buildings," J. Build. Eng., vol. 62, p.105367, 2022.

DOI: 10.1016/j.jobe.2022.105367

[17] A. Cutler, D. R. Cutler, and J. R. Stevens, "Random Forests," no. February 2014, 2011.

DOI: 10.1007/978-1-4419-9326-7

[18] J. Yang, H. Zhuang, G. Zhang, B. Tang, and C. Xu, "Seismic performance and fragility of two-story and three-span underground structures using a random forest model and a new damage description method," Tunn. Undergr. Sp. Technol., vol. 135, p.104980, 2023.

DOI: 10.1016/j.tust.2022.104980

[19] F. Kazemi, N. Asgarkhani, and R. Jankowski, "Machine learning-based seismic fragility and seismic vulnerability assessment of reinforced concrete structures," Soil Dyn. Earthq. Eng., vol. 166, p.107761, 2023.

DOI: 10.1016/j.soildyn.2023.107761

[20] R. Segura, J. E. Padgett, A. M. Asce, P. Paultre, and M. Asce, "Metamodel-Based Seismic Fragility Analysis of Concrete Gravity Dams," vol. 146, no. 7, p.1–17, 2020.

DOI: 10.1061/(ASCE)ST.1943-541X.0002629

[21] S. Mangalathu, "Stripe ‐ based fragility analysis of multispan concrete bridge classes using machine learning techniques," no. April, p.1–18, 2019.

DOI: 10.1002/eqe.3183

[22] K. Taunk, S. De, S. Verma, and A. Swetapadma, "MACHINE LEARNING CLASSIFICATION WITH K-NEAREST NEIGHBOURS," no. January 2021, 2019.

DOI: 10.1109/ICCS45141.2019.9065747

[23] Y. Shi, K. Yang, Z. Yang, and Y. B. T.-M. E. A. I. Zhou, Eds., "Contents," Academic Press, 2022, pp. v–ix.

DOI: 10.1016/B978-0-12-823817-2.00004-8

[24] L. Y. Hu, M. W. Huang, S. W. Ke, and C. F. Tsai, "The distance function effect on k ‑ nearest neighbor classification for medical datasets," 2016.

DOI: 10.1186/s40064-016-2941-7

[25] V. Calofir, R. Munteanu, M. Simoiu, and K. Lemnaru, "Results in Engineering Innovative approach to estimate structural damage using linear regression and K-nearest neighbors machine learning algorithms," Results Eng., vol. 22, no. April, p.102250, 2024.

DOI: 10.1016/j.rineng.2024.102250

[26] N. Saleem, S. Mangalathu, B. Ahmed, and J.-S. Jeon, "Machine learning-based peak ground acceleration models for structural risk assessment using spatial data analysis," Earthq. Eng. Struct. Dyn., vol. 53, no. 1, p.152–178, Jan. 2024.

DOI: 10.1002/eqe.4021

[27] S. Mangalathu, H. Sun, C. C. Nweke, Z. Yi, and H. V Burton, "Classifying earthquake damage to buildings using machine learning," Earthq. Spectra, vol. 36, no. 1, p.183–208, Jan. 2020.

DOI: 10.1177/8755293019878137

[28] A. Roy and S. Chakraborty, "Support vector machine in structural reliability analysis: A review," Reliab. Eng. Syst. Saf., vol. 233, p.109126, 2023.

DOI: 10.1016/j.ress.2023.109126

[29] R. Sainct, C. Feau, J.-M. Martinez, and J. Garnier, "Efficient methodology for seismic fragility curves estimation by active learning on Support Vector Machines," Struct. Saf., vol. 86, p.101972, 2020.

DOI: 10.1016/j.strusafe.2020.101972

[30] S. N. Mahmoudi and L. Chouinard, "Seismic fragility assessment of highway bridges using support vector machines," Bull. Earthq. Eng., vol. 14, no. 6, p.1571–1587, 2016.

DOI: 10.1007/s10518-016-9894-7

[31] M. S. B. Maind, "Research Paper on Basic of Artificial Neural Network," no. January, p.96–100, 2014.

[32] E. Binali, "Activation functions used in artificial neural networks," no. October, 2023.

[33] Z. Liu and Z. Zhang, "Artificial Neural Network based method for seismic fragility analysis of steel frames," KSCE J. Civ. Eng., vol. 22, May 2017.

DOI: 10.1007/s12205-017-1329-8

[34] Z. Wang, N. Pedroni, I. Zentner, and E. Zio, "Seismic fragility analysis with artificial neural networks: Application to nuclear power plant equipment," Eng. Struct., vol. 162, p.213–225, 2018.

DOI: 10.1016/j.engstruct.2018.02.024

[35] G. Quinci, H. N. Phan, and F. Paolacci, On the Use of Artificial Neural Network Technique for Seismic Fragility Analysis of a Three-Dimensional Industrial Frame. 2022.

DOI: 10.1115/PVP2022-83874

[36] S. Hwang, S. Mangalathu, J. Shin, and J. Jeon, "Jo ur na l P re of," J. Build. Eng., p.101905, 2020.

DOI: 10.1016/j.jobe.2020.101905

[37] S. Bhatta and J. Dang, "Seismic damage prediction of RC buildings using machine learning," no. September 2022, p.3504–3527, 2023.

DOI: 10.1002/eqe.3907

[38] M. Noureldin, T. Ali, and J. Kim, "Machine learning-based seismic assessment of framed structures with soil-structure interaction," vol. 17, no. 2, p.205–223, 2023.

DOI: 10.1007/s11709-022-0909-y

[39] D. Asta, "University of Birmingham A machine learning-based analysis for predicting fragility curve parameters of buildings Fragility curves of buildings ; a critical review and a machine learning-based study," 2024.

DOI: 10.1016/j.jobe.2022.105367

[40] M. Ludian, "Seismic vulnerability assessment model of civil structure using machine learning algorithms : a case study of the 2014," Nat. Hazards, vol. 120, no. 7, p.6481–6508, 2024.

DOI: 10.1007/s11069-024-06465-9

[41] E. Nazarian, T. Taylor, T. Weifeng, and F. Ansari, "Machine-learning-based approach for post event assessment of damage in a turn-of-the-century building structure," J. Civ. Struct. Heal. Monit., vol. 8, no. 2, p.237–251, 2018.

DOI: 10.1007/s13349-018-0275-6

[42] J. Chen, H. Xiong, and C. E. Ventura, "Seismic reliability evaluation of a tall concrete-timber hybrid structural system," Struct. Des. Tall Spec. Build., vol. 31, no. 10, p. e1933, Jul. 2022.

DOI: 10.1002/tal.1933

[43] Z. Xin, D. Ke, H. Zhang, Y. Yu, and F. Liu, "Non-destructive evaluating the density and mechanical properties of ancient timber members based on machine learning approach," Constr. Build. Mater., vol. 341, p.127855, 2022.

DOI: 10.1016/j.conbuildmat.2022.127855

[44] Y. Xinzhe, L. Liujun, Z. Haibin, Z. Yanping, C. Genda, and D. Cihan, "Machine Learning-Based Seismic Damage Assessment of Residential Buildings Considering Multiple Earthquake and Structure Uncertainties," Nat. Hazards Rev., vol. 24, no. 3, p.4023024, Aug. 2023.

DOI: 10.1061/NHREFO.NHENG-1681

[45] K. Chawgien and E. Junda, "Interpretable machine learning models for the estimation of seismic drifts in CLT buildings," vol. 70, no. December 2022, 2023.

DOI: 10.1016/j.jobe.2023.106365