Earthquake Probability Prediction with Decision Tree Algorithm: The Example of Izmir, Türkiye

Abstract

This study investigates earthquake records in the Izmir province of western Türkiye, focusing on seismic activity prediction through the application of decision tree models. Utilizing earthquake data from 1900 to 2024, including magnitude, depth, latitude, and longitude variables, the aim is to estimate future seismic events in a region known for its significant earthquake risks. The decision tree model, a machine learning approach, was trained with 80% of the dataset and tested on the remaining 20%. Performance was assessed using metrics such as precision, recall, F1 score, and overall accuracy, with the model achieving an accuracy rate of 92%. However, its ability to predict larger earthquakes was hindered due to the limited availability of data for higher-magnitude events. A chi-square test demonstrated a statistically significant relationship between earthquake depth and magnitude. Additionally, a risk analysis map was created using Geographic Information Systems (GIS), highlighting fault lines and areas prone to frequent seismic activity. The study concludes that while the decision tree model is effective for predicting smaller earthquakes, the accuracy for larger events could be improved with more comprehensive data. These findings underscore the importance of targeted earthquake preparedness in Izmir, particularly in coastal areas susceptible to both seismic events and secondary hazards like tsunamis.

Keywords

• artifiial intelligence
• decision tree
• earthquake
• Izmir

References

1. D. Abdullah and E. D. Putra, “Comparasi edge detection roberts dan morfologi pada deteksi plat nomor kendaraan roda dua,” J. Sci. Appl. Informatics, vol. 1, no. 3, pp. 66–69, 2018.
2. S. Ahamed and E. G. Daub, “Machine learning approach to earthquake rupture dynamics,” arXiv preprint arXiv:1906.06250, 2019.
3. F. Ahmed et al., “Earthquake magnitude prediction using machine learning techniques,” in 2024 IEEE Int. Conf. Interdiscip. Approaches Technol. Manag. Soc. Innov. (IATMSI), 2024, vol. 2, pp. 1–5.
4. A. Ardakani and V. Kohestani, “Evaluation of liquefaction potential based on CPT results using C4.5 decision tree,” J. AI Data Mining, vol. 3, pp. 85–92, 2015.
5. K. M. Asim, A. Idris, F. Martínez-Álvarez, and T. Iqbal, “Short term earthquake prediction in Hindukush region using tree based ensemble learning,” in 2016 Int. Conf. Front. Inf. Technol. (FIT), 2016, pp. 365–370.
6. K. M. Asim, F. Martínez-Álvarez, A. Basit, and T. Iqbal, “Earthquake magnitude prediction in Hindukush region using machine learning techniques,” Nat. Hazards, vol. 85, pp. 471–486, 2017.
7. Y. Cai, M. L. Shyu, Y. X. Tu, Y. T. Teng, and X. X. Hu, “Anomaly detection of earthquake precursor data using long short-term memory networks,” Appl. Geophys., vol. 16, pp. 257–266, 2019.
8. M. Cassel, “Machine learning and the construction of a seismic attribute-seismic facies analysis data base,” M.S. thesis, Univ. Oklahoma, 2018. [Online]. Available: https://shareok.org/

9. R. Chen et al., “Rigorous assessment and integration of the sequence and structure based features to predict hot spots,” BMC Bioinformatics, vol. 12, pp. 1–14, 2011.
10. R. L. Church, “Geographical information systems and location science,” Comput. Oper. Res., vol. 29, no. 6, pp. 541–562, 2002.
11. İ. Cürebal and E. Özşahin, Harita Bilgisi (Bilgisayar Uygulamalı Tasarım ve Analiz). Bursa, Türkiye: Ekin Basın Yayın Dağıtım, 2022.
12. K. Demertzis, K. Kostinakis, K. Morfidis, and L. Iliadis, “A comparative evaluation of machine learning algorithms for the prediction of R/C buildings' seismic damage,” arXiv preprint arXiv:2203.13449, 2022.
13. A. Doğru, E. Görgün, H. Ozener, and B. Aktuğ, “Geodetic and seismological investigation of crustal deformation near Izmir (Western Anatolia),” J. Asian Earth Sci., vol. 82, pp. 21–31, 2014.
14. T. M. Franke, T. Ho, and C. A. Christie, “The chi-square test: Often used and more often misinterpreted,” Am. J. Eval., vol. 33, no. 3, pp. 448–458, 2012.
15. E. Gok and O. Polat, “An assessment of the microseismic activity and focal mechanisms of the Izmir (Smyrna) area from a new local network (IzmirNET),” Tectonophysics, vol. 635, pp. 154–164, 2014.
16. S. Goswami, S. Chakraborty, S. Ghosh, A. Chakrabarti, and B. Chakraborty, “A review on application of data mining techniques to combat natural disasters,” Ain Shams Eng. J., vol. 9, no. 3, pp. 365–378, 2018.
17. J. Han, J. Kim, S. Park, S. Son, and M. Ryu, “Seismic vulnerability assessment and mapping of Gyeongju, South Korea using frequency ratio, decision tree, and random forest,” Sustainability, vol. 12, no. 18, p. 7787, 2020.
18. C. Jiang, X. Wei, X. Cui, and D. You, “Application of support vector machine to synthetic earthquake prediction,” Earthq. Sci., vol. 22, pp. 315–320, 2009.
19. A. Karbassi, B. Mohebi, S. Rezaee, and P. Lestuzzi, “Damage prediction for regular reinforced concrete buildings using the decision tree algorithm,” Comput. Struct., vol. 130, pp. 46–56, 2014.
20. G. Q. King, “Geography and GIS technology,” J. Geogr., vol. 90, no. 2, pp. 66–72, 1991.
21. S. B. Kotsiantis, “Decision trees: A recent overview,” Artif. Intell. Rev., vol. 39, pp. 261–283, 2013.
22. A. Li and L. Kang, “Knn-based modeling and its application in aftershock prediction,” in 2009 Int. Asia Symp. Intell. Interact. Affect. Comput., 2009, pp. 83–86.
23. G. Lü et al., “Reflections and speculations on the progress in geographic information systems (GIS): A geographic perspective,” Int. J. Geogr. Inf. Sci., vol. 33, no. 2, pp. 346–367, 2019.
24. A. Mignan and M. Broccardo, “Neural network applications in earthquake prediction (1994–2019): Meta‐analytic and statistical insights on their limitations,” Seismol. Res. Lett., vol. 91, no. 4, pp. 2330–2342, 2020.
25. O. Onat and H. Tanyıldızı, “Machine learning-based estimation of the out-of-plane displacement of brick infill exposed to earthquake shaking,” Eng. Appl. Artif. Intell., vol. 136, p. 109007, 2024.
26. G. V. Otari and R. V. Kulkarni, “A review of application of data mining in earthquake prediction,” Int. J. Comput. Sci. Inf. Technol., vol. 3, no. 2, pp. 3570–3574, 2012.
27. O. Polat et al., “IzmirNet: A strong-motion network in metropolitan Izmir, Western Anatolia, Türkiye” Seismol. Res. Lett., vol. 80, pp. 831–838, 2009.
28. R. Rana and R. Singhal, “Chi-square test and its application in hypothesis testing,” J. Primary Care Specialties, vol. 1, no. 1, pp. 69–71, 2015.
29. N. S. M. Ridzwan and S. H. M. Yusoff, “Machine learning for earthquake prediction: A review (2017–2021),” Earth Sci. Inform., vol. 16, no. 2, pp. 1133–1149, 2023.
30. M. Senkaya, A. Silahtar, E. F. Erkan, and H. Karaaslan, “Prediction of local site influence on seismic vulnerability using machine learning: A study of the 6 February 2023 Türkiye earthquakes,” Eng. Geol., p. 107605, 2024.
31. I. Sikder and T. Munakata, “Application of rough set and decision tree for characterization of premonitory factors of low seismic activity,” Expert Syst. Appl., vol. 36, pp. 102–110, 2009.
32. M. Sokolova, N. Japkowicz, and S. Szpakowicz, “Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation,” in Australas. Joint Conf. Artif. Intell., pp. 1015–1021, 2006.
33. M. J. Somodevilla, A. B. Priego, E. Castillo, I. H. Pineda, D. Vilariño, and A. Nava, "Decision support system for seismic risks," J. Comput. Sci. Technol., vol. 12, 2012.
34. Ç. Tepe et al., “Updated historical earthquake catalog of İzmir region (western Anatolia) and its importance for the determination of seismogenic source,” Turk. J. Earth Sci., vol. 30, no. 8, pp. 779–805, 2021.
35. N. S. Turhan, “Karl Pearson's Chi-Square Tests,” Educ. Res. Rev., vol. 16, no. 9, pp. 575–580, 2020.
36. P. Xiong et al., “Towards advancing the earthquake forecasting by machine learning of satellite data,” Sci. Total Environ., vol. 771, p. 145256, 2021.
37. C. E. Yavas, L. Chen, C. Kadlec, and Y. Ji, “Predictive modeling of earthquakes in Los Angeles with machine learning and neural networks,” IEEE Access, 2024.
38. E. ZeeAbrahamsen and J. Haberman, “Correcting ‘confusability regions’ in face morphs,” Behav. Res. Methods, vol. 50, pp. 1686–1693, 2018.
39. J. Zhang, “Dive into decision trees and forests: A theoretical demonstration,” arXiv preprint arXiv:2101.08656, 2021.