PSI - Issue 78

Gianluca Quinci et al. / Procedia Structural Integrity 78 (2026) 845–851

851

(μ), dispersion (β), and ultimate di splacement (d u ), based on geometric and mechanical attributes such as total mass, pier height, and reinforcement configuration, the method offers a highly efficient alternative to conventional fragility derivation methods such as Cloud Analysis. Among the models investigated, Gaussian Process Regression (GPR) consistently yielded superior results across all target variables, as evidenced by validation metrics. The fragility curves generated through ML closely aligned with those derived from detailed nonlinear analyses, confirming the robustness and accuracy of the proposed approach. The key advantage of this method lies in its ability to rapidly estimate fragility curves for numerous structures without resorting to time-consuming numerical simulations. This makes it a powerful tool for first-level seismic risk screening and for setting intervention priorities in large-scale infrastructure management. Future developments will aim to extend the applicability of the framework to different structural typologies and damage criteria, and to incorporate epistemic uncertainty into the ML process, further enhancing the predictive capabilities and reliability of the methodology. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5 – 32. El - Maissi, A. M., Argyroudis, S. A., & Nazri, F. M. (2021). Seismic vulnerability assessment methodologies for roadway assets and networks: A state - of - the - art review. Sustainability, 13, 61. https://doi.org/10.3390/su13010061 Fajfar, P. (2000). A nonlinear analysis method for performance - based seismic design. Earthquake Spectra, 16(3), 573 – 592. https://doi.org/10.1193/1.1586128 Maulud, D., & Abdulazeez, A. M. (2020). A review on linear regression comprehensive in machine learning. Journal of Applied Science and Technology Trends, 1(2), 140 – 147. Quinci, G., Paolacci, F., & Phan, H. N. (2023). Artificial Neural Network Technique for Seismic Fragility Analysis of a Storage Tank Supported by Multi - Storey Frame. ASME J. Pressure Vessel Technol., 145(6), 061901. https://doi.org/10.1115/1.4063242 Quinci, G., Phan, N. H., & Paolacci, F. (2022). On the Use of Artificial Neural Network Technique for Seismic Fragility Analysis of a Three Dimensional Industrial Frame. ASME PVP Conference, Las Vegas, USA. https://doi.org/10.1115/PVP2022 - 83874 Quinci, G., Paolacci, F., Fragiadakis, M., & Bursi, O. S. (2025). A machine learning framework for seismic risk assessment of industrial equipment. Reliability Engineering & System Safety, 254, 110606. https://doi.org/10.1016/j.ress.2024.110606 Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian Processes for Machine Learning. MIT Press. Shinozuka, M., et al. (2000). Statistical analysis of fragility curves. Journal of Engineering Mechanics, 126(12), 1224 – 1231. Skokandić, D., Vlašić, A., Marić, M. K., Srbić, M., & Ivanković, A. M. (2022). Seismic assessment and retrofitting of existing road bridges: State of the art review. Materials, 15, 2523. https://doi.org/10.3390/ma15072523 Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199 – 222. Somvanshi, M., et al. (2016). A review of machine learning techniques using decision tree and support vector machine. 2016 International Conference on Computing Communication Control and Automation (ICCUBEA). IEEE. Xie, Y., Ebad Sichani, M., Padgett, J. E., & DesRoches, R. (2020). The promise of implementing machine learning in earthquake engineering: A state - of - the - art review. Earthquake Spectra, 36(4), 1769 – 1801. https://doi.org/10.1177/8755293020919419 Zhao, R., et al. (2021). State - of - the - art and annual progress of bridge engineering in 2020. Advances in Building Engineering, 29, 2 – 29. https://doi.org/10.1186/s43251 - 021 - 00050 References