Predicting the Earthquake Magnitude along Zagros Fault Using Time Series and Ensemble Model

Document Type : Regular Article


1 Ph.D. Candidate, Environmental Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran

2 Research Assistant, Geotechnical Earthquake Engineering, International Institute of Earthquake Engineering and Seismology, Tehran, Iran

3 Master of Science Student, Structural Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran

4 Master of Science Student, Structural Engineering, School of Civil Engineering, Islamic Azad University, Tehran, Iran


Predicting the earthquake magnitude is a complex problem, which has been carried out in recent years. The machine learning, geophysical, and regression methods were used to predict earthquake magnitude in literature. Iran is located in a highly seismically active area; thus, earthquake prediction is considered as a great demand there. In this study, two time series algorithms are utilized to predict the magnitude of the earthquake based on previous earthquakes. These models are autoregressive conditional heteroscedasticity (GARCH), autoregressive integrated moving average (ARIMA), and the combination of ARIMA and GARCH by multiple linear regression (MLR) technique (model 3). The 9017 events are used to train and predict earthquake magnitude. On the other hand, 6188 events are applied for training models, and then 2829 events are utilized for testing it. The statistical parameters, such as correlation coefficient, root mean square error (RMSE), normalized square error (NMSE), and fractional bias, are calculated to evaluate the accuracy of each model. The results demonstrate that the ARIMA and model 3 can predict future earthquake magnitude better than other models.


Google Scholar


Main Subjects

[1]       Aven T. On how to define, understand and describe risk. Reliab Eng Syst Saf 2010;95:623–31. doi:10.1016/j.ress.2010.01.011.
[2]       Florido E, Martínez-Álvarez F, Morales-Esteban A, Reyes J, Aznarte-Mellado JL. Detecting precursory patterns to enhance earthquake prediction in Chile. Comput Geosci 2015;76:112–20. doi:10.1016/j.cageo.2014.12.002.
[3]       Špičák A, Vaněk J. Earthquake swarms reveal submarine magma unrest induced by distant mega-earthquakes: Andaman Sea region. J Asian Earth Sci 2016;116:155–63. doi:10.1016/j.jseaes.2015.11.017.
[4]       Verdugo R, González J. Liquefaction-induced ground damages during the 2010 Chile earthquake. Soil Dyn Earthq Eng 2015;79:280–95. doi:10.1016/j.soildyn.2015.04.016.
[5]       Keefer DK. Landslides caused by earthquakes. Geol Soc Am Bull 1984;95:406–21.
[6]       Cecioni C, Bellotti G, Romano A, Abdolali A, Sammarco P, Franco L. Tsunami Early Warning System based on Real-time Measurements of Hydro-acoustic Waves. Procedia Eng 2014;70:311–20. doi:10.1016/j.proeng.2014.02.035.
[7]       Fazendeiro Sá L, Morales‐Esteban A, Durand Neyra P. A Seismic Risk Simulator for Iberia. Bull Seismol Soc Am 2016;106:1198–209. doi:10.1785/0120150195.
[8]       Tsai C-W, Lai C-F, Chao H-C, Vasilakos A V. Big data analytics: a survey. J Big Data 2015;2:21. doi:10.1186/s40537-015-0030-3.
[9]       Rouet-Leduc B, Hulbert C, Lubbers N, Barros K, Humphreys CJ, Johnson PA. Machine Learning Predicts Laboratory Earthquakes. Geophys Res Lett 2017;44:9276–82. doi:10.1002/2017GL074677.
[10]     Asencio–Cortés G, Morales–Esteban A, Shang X, Martínez–Álvarez F. Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure. Comput Geosci 2018;115:198–210. doi:10.1016/j.cageo.2017.10.011.
[11]     Wang Q, Jackson DD, Kagan YY. California Earthquakes, 1800-2007: A Unified Catalog with Moment Magnitudes, Uncertainties, and Focal Mechanisms. Seismol Res Lett 2009;80:446–57. doi:10.1785/gssrl.80.3.446.
[12]     Naderpour H, Rafiean AH, Fakharian P. Compressive strength prediction of environmentally friendly concrete using artificial neural networks. J Build Eng 2018;16:213–9. doi:10.1016/j.jobe.2018.01.007.
[13]     Shishegaran A, Ghasemi MR, Varaee H. Performance of a novel bent-up bars system not interacting with concrete. Front Struct Civ Eng 2019;13:1301–15. doi:10.1007/s11709-019-0552-4.
[14]     Shishegaran A, Khalili MR, Karami B, Rabczuk T, Shishegaran A. Computational predictions for estimating the maximum deflection of reinforced concrete panels subjected to the blast load. Int J Impact Eng 2020;139:103527. doi:10.1016/j.ijimpeng.2020.103527.
[15]     Shishegaran A, Daneshpajoh F, Taghavizade H, Mirvalad S. Developing conductive concrete containing wire rope and steel powder wastes for route deicing. Constr Build Mater 2020;232:117184. doi:10.1016/j.conbuildmat.2019.117184.
[16]     Mohammadkhani MR, Shishegaran A, Shokrollahi B. Forecasting probable maximum precipitation using innovative algorithm to estimate atmosphere precipitable water vapor. Math Model Eng 2019;5:90–6. doi:10.21595/mme.2019.20935.
[17]     Shishegaran A, Amiri A, Jafari MA. Seismic performance of box-plate, box-plate with UNP, box-plate with L-plate and ordinary rigid beam-to-column moment connections. J Vibroengineering 2018;20:1470–87. doi:10.21595/jve.2017.18716.
[18]     Shishegaran A, Rahimi S, Darabi H. Introducing box-plate beam-to-column moment connections. Vibroengineering PROCEDIA 2017;11:200–4. doi:10.21595/vp.2017.18548.
[19]     Reza Ghasemi M, Shishegaran A. Role of slanted reinforcement on bending capacity SS beams. Vibroengineering PROCEDIA 2017;11:195–9. doi:10.21595/vp.2017.18544.
[20]     Naderpour H, Fakharian P. A synthesis of peak picking method and wavelet packet transform for structural modal identification. KSCE J Civ Eng 2016;20:2859–67. doi:10.1007/s12205-016-0523-4.
[21]     Naderpour H, Nagai K, Fakharian P, Haji M. Innovative models for prediction of compressive strength of FRP-confined circular reinforced concrete columns using soft computing methods. Compos Struct 2019;215:69–84. doi:10.1016/j.compstruct.2019.02.048.
[22]     Naderpour H, Fakharian P. Predicting the torsional strength of reinforced concrete beams strengthened with FRP sheets in terms of artificial neural networks. J Struct Constr Eng 2018;5:20–35. doi:10.22065/JSCE.2017.70668.1023.
[23]     Box GEP, Jenkins GM, Reinsel GC, Ljung GM. Time series analysis: forecasting and control. John Wiley & Sons; 2015.
[24]     Matei M. Assessing volatility forecasting models: why GARCH models take the lead. Rom J Econ Forecast 2009;12:42–65.
[25]     Bollerslev T. Generalized autoregressive conditional heteroskedasticity. J Econom 1986;31:307–27.
[26]     Bates JM, Granger CWJ. The Combination of Forecasts. J Oper Res Soc 1969;20:451–68. doi:10.1057/jors.1969.103.
[27]     Chang JC, Hanna SR. Air quality model performance evaluation. Meteorol Atmos Phys 2004;87. doi:10.1007/s00703-003-0070-7.