Rapid Visual Screening Feature Importance for Seismic Vulnerability Ranking via Machine Learning and SHAP Values
Source abstract
Abstract
Structures inevitably suffer damage after an earthquake, with severity ranging from minimal damage of nonstructural elements to partial or even total collapse, possibly with loss of human lives. Thus, it is essential for engineers to understand the crucial factors that drive a structure towards suffering higher degrees of damage in order for preventative measures to be taken. In the present study, we focus on three well-known damage thresholds: the Collapse Limit State, Ultimate Limit State, and Serviceability Limit State. We analyze the features obtained via Rapid Visual Screening to determine whether or not a given structure crosses these thresholds. To this end, we use machine learning to perform binary classification for each damage threshold, and use explainability to quantify the effect of each parameter via SHAP values (SHapley Additive exPlanations). The quantitative results that we obtain demonstrate the potential applicability of ML methods for recalibrating the computation of structural vulnerability indices using data from recent earthquakes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Seismology and Earthquake Studies · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Lab of Mathematics and Informatics (ISCE), Department of Civil Engineering, Democritus University of Thrace, 67100 Xanthi, Greece
Lab of Reinforced Concrete and Seismic Design, Department of Civil Engineering, Democritus University of Thrace, 67100 Xanthi, Greece
References (50)
Show source-provided references
1. Palermo, V., Tsionis, G., and Sousa, M.L. (2018). Building Stock Inventory to Assess Seismic Vulnerability Across Europe, Publications Office of the European Union.
2. Federal Emergency Management Agency (US) (2017). Rapid Visual Screening of Buildings for Potential Seismic Hazards: A Handbook, Government Printing Office.
3. (2024, January 03). Greek Code for Seismic Resistant Structures–EAK, Available online: https://iisee.kenken.go.jp/worldlist/23_Greece/23_Greece_Code.pdf.
4. Lizundia, B., Durphy, S., Griffin, M., Holmes, W., Hortacsu, A., Kehoe, B., Porter, K., and Welliver, B. (2015). Improving the Seismic Performance of Existing Buildings and Other Structures, American Society of Civil Engineers.
5. Vulpe, A., Carausu, A., and Vulpe, G.E. (2001, January 12–17). Earthquake induced damage quantification and damage state evaluation by fragility and vulnerability models. Proceedings of the SMiRT 16, Washington, DC, USA.
6. (2024, January 03). NEHRP Handbook for the Seismic Evaluation of Existing Buildings. Available online: https://www.preventionweb.net/files/7543_SHARPISDRFLOOR120081209171548.pdf.
7. Derivation of vulnerability functions for European-type RC structures based on observational data10.1016/S0141-0296(03)00060-9 ↗
8. Eleftheriadou, A., and Karabinis, A. (2008, January 12–17). Damage probability matrices derived from earthquake statistical data. Proceedings of the 14th World Conference on Earthquake Engineering, Beijing, China.
9. Seismic vulnerability procedures for historical masonry structural aggregates: Analysis of the historical centre of Castelpoto (South Italy)10.1016/j.istruc.2023.01.022 ↗
10. Chieffo, N., Fasan, M., Romanelli, F., Formisano, A., and Mochi, G. (2021). Physics-based ground motion simulations for the prediction of the seismic vulnerability of masonry building compounds in Mirandola (Italy). Buildings, 11.10.3390/buildings11120667 ↗
11. Influence of construction age on seismic vulnerability of masonry buildings damaged after 2009 L’Aquila earthquake10.1016/j.soildyn.2022.107199 ↗
12. Towards a multi-parametric fragility model for Italian masonry buildings based on the informative level10.1016/j.istruc.2023.105613 ↗
13. Harirchian, E., Kumari, V., Jadhav, K., Das, R.R., Rasulzade, S., and Lahmer, T. (2020). A Machine Learning Framework for Assessing Seismic Hazard Safety of Reinforced Concrete Buildings. Appl. Sci., 10.10.3390/app10207153 ↗
14. Earthquake damage and rehabilitation intervention prediction using machine learning10.1016/j.engfailanal.2022.106949 ↗
15. A locally weighted machine learning model for generalized prediction of drift capacity in seismic vulnerability assessments10.1111/mice.12456 ↗
16. Machine learning-based seismic response and performance assessment of reinforced concrete buildings10.1007/s43452-023-00631-9 ↗
17. A survey on the explainability of supervised machine learning10.1613/jair.1.12228 ↗
18. Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems10.1016/j.engstruct.2021.112883 ↗
19. Pairwise acquisition prediction with shap value interpretation10.1016/j.jfds.2021.02.001 ↗
20. Karabinis, A. (2024, March 20). Calibration of Rapid Visual Screening in Reinforced Concrete Structures Based on Data after a Near Field Earthquake (7.9.1999 Athens-Greece). Available online: https://oasp.gr/sites/default/files/program_documents/261%20-%20Teliki%20ekthesi.pdf.
21. Machine-learning based vulnerability analysis of existing buildings10.1016/j.autcon.2021.103936 ↗
22. Karampinis, I., and Iliadis, L. (2023, January 14–17). A Machine Learning Approach for Seismic Vulnerability Ranking. Proceedings of the International Conference on Engineering Applications of Neural Networks, León, Spain.10.1007/978-3-031-34204-2_1 ↗
23. A review of class imbalance problem
24. Longadge, R., and Dongre, S. (2013). Class imbalance problem in data mining review. arXiv.
25. A review on class imbalance problem: Analysis and potential solutions10.20943/01201706.4351 ↗
26. An exhaustive literature review on class imbalance problem
27. Bansal, A., and Jain, A. (2022, January 22–25). Analysis of focussed under-sampling techniques with machine learning classifiers. Proceedings of the 2021 IEEE/ACIS 19th International Conference on Software Engineering Research, Management and Applications (SERA), Las Vegas, NE, USA.10.1109/SERA51205.2021.9509270 ↗
28. Mohammed, R., Rawashdeh, J., and Abdullah, M. (2020, January 7–9). Machine learning with oversampling and undersampling techniques: Overview study and experimental results. Proceedings of the 2020 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.10.1109/ICICS49469.2020.239556 ↗
29. Newaz, A., Hassan, S., and Haq, F.S. (2022). An empirical analysis of the efficacy of different sampling techniques for imbalanced classification. arXiv.
30. Hasanin, T., and Khoshgoftaar, T. (2018, January 6–9). The effects of random undersampling with simulated class imbalance for big data. Proceedings of the 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, USA.10.1109/IRI.2018.00018 ↗
31. Dealing with class imbalance in classifier chains via random undersampling10.1016/j.knosys.2019.105292 ↗
32. Liu, Y., Li, X., Kong, A.W.K., and Goh, C.K. (2016, January 6–9). Learning from small data: A pairwise approach for ordinal regression. Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece.
33. Gradient boosting machines, a tutorial10.3389/fnbot.2013.00021 ↗
34. What are decision trees?10.1038/nbt0908-1011 ↗
35. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗
36. Scikit-learn: Machine learning in Python
37. A gradient boosting method to improve travel time prediction10.1016/j.trc.2015.02.019 ↗
38. The problem of overfitting
39. Bengio, Y. (2012). Neural Networks: Tricks of the Trade, Springer. [2nd ed.].
40. On hyperparameter optimization of machine learning algorithms: Theory and practice10.1016/j.neucom.2020.07.061 ↗
41. Yu, T., and Zhu, H. (2020). Hyper-parameter optimization: A review of algorithms and applications. arXiv.
42. Snoek, J., Larochelle, H., and Adams, R.P. (2012, January 3–6). Practical bayesian optimization of machine learning algorithms. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NE, USA.
43. Head, T., Louppe, G., Shcherbatyi, I., Vinícius, Z., Schröder, C., and Campos, N. (2024, March 20). scikit-optimize/scikit-optimize: V0. 5.2. Version v0. Available online: https://zenodo.org/records/1207017.
44. Shapley, L.S. (1951). Notes on the n-Person Game: The Value of an n-Person Game, RAND Corporation.
45. Lundberg, S.M., Erion, G.G., and Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv.
46. Lundberg, S.M., and Lee, S.-I. (2017, January 4–9). A unified approach to interpreting model predictions. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA.
47. From local explanations to global understanding with explainable ai for trees
48. Zharmagambetov, A., Hada, S.S., Carreira-Perpiñán, M.Á., and Gabidolla, M. (2019). An experimental comparison of old and new decision tree algorithms. arXiv.
49. Cross-validation methods10.1006/jmps.1999.1279 ↗
50. Ferrer, L. (2022). Analysis and comparison of classification metrics. arXiv.