Prediction of the Peak Ground Acceleration for Zagros Earthquakes Using ANFIS and Data Partitioning Approach

Subject Areas :

seyyed Mohamadreza tabatabaei ¹ , Roohollah kimiaefar ² , Alireza Hajian ³ , Alireza Akbari ⁴

1 - Department of Physics, Central Tehran Branch, Islamic Azad University, Tehran, Iran.
2 - Department of Physics, Central Tehran Branch, Islamic Azad University, Tehran, Iran.
3 - Department of Physics, Central Tehran Branch, Islamic Azad University, Tehran, Iran.
4 - Department of Physics, East Tehran Branch, Islamic Azad University, Tehran, Iran

Received: 2021-08-21 Accepted : 2021-10-06 Published : 2021-10-22

Keywords: ANFIS, Outlier, peak ground acceleration, ZagrosEartquakes,

Abstract :

In this research, the prediction of Peak Ground Acceleration (PGA) is investigated through training the Adaptive Neuro Fuzzy Inference System (ANFIS) network using data partitioned into inlier and outlier groups. The partitioning procedure is based on an automated method which uses K Nearest Neighbor (KNN) search and Local Linear Model Tree (LOLIMOT) methods. The mentioned proved to enhance the prediction procedure at least 36 percent with respect to normal training mode with no data partitioning. Hereafter, a PGA catalogue reported by the Iranian ground acceleration network with 1571 records was used and the trained network was used for predicting the PGA map around the Mormori, 2014 earthquake epicenter. We used spatial information of the epicenter and the site, earthquake magnitude, Vs30, depth of the hypocenters and the epicentral distance foe the sites. The resulted map adapts well to the official report of the mentioned earthquake for the PGA analysis published by the International Institute of Earthquake Engineering and Seismology (IIEES). Finally, it is concluded that using machine learning algorithms could be beneficial in the cases where adequate data-sets are not provided by the seismological networks specifically in the concept of the strong ground motion analysis.

References:

Akhani M., Kashani A., Mousavi M., Gandomi A., “A hybrid computational intelligence approach to predict spectral acceleration”, Measurement, (2019) 138: 578-589.

Alavi A, Gandomi A., Modaresnezhad M., Mousavi M., “New Ground-Motion Prediction Equations Using Multi Expression Programing”, Journal of Earthquake Engineering, (2011), 15:4, 511-536, DOI: 10.1080/13632469.2010.526752.

AllamehZadeh M., Javan Doloiee G., Nasrollahnejad A., “Estimation of Maximum Peak Ground Acceleration via the ANFIS and FFBP Neural Networks”, 6^th Conference on Computational Methods in Structural Dynamics and Earthquake Engineering, (2017).

Allen, T.I., and Wald, D.J., “Topographic slope as a proxy for global seismic site conditions (VS30) and amplification around the globe” U.S. Geological Survey Open-File Report (2007)-1357, p 69.

Derakhshani A., Foruzan A. H., “Predicting the principal strong ground motion parameters: A deep learning approach”, Applied Soft Computing, (2019), 80, 192-201.

Derakhshani A., Foruzan A. H., “Predicting the principal strong ground motion parameters: A deep learning approach”, Applied Soft Computing, 80, (2019), 192-201, https://doi.org/10.1016/j.asoc.2019.03.029.

Estrada A.P., Roberto Gómez R., Hong H.P., “Use of Neural network to predict the peak ground accelerations and pseudo spectral accelerations for Mexican Inslab and Interplate Earthquakes”, Geofísica Internacional, (2014), 53(1), 39-57.

Derras B., Bard P. Y., Cotton F., Bekkouche A.,“Adapting the Neural Network Approach to PGA Prediction: An Example Based on the KiK‐net Data”. Bulletin of the Seismological Society of America (2012) 102 (4): 1446–1461. doi: https://doi.org/10.1785/0120110088.

Jang J. SR., ANFIS:Adaptive-Network-Based Fuzzy Inference System”,IEEE Transactions on Systems Man and Cybernetics,23,(1993),665-685.

Karimiparidari S., Zaré M., Memarian H., KijkoA., “Iranian earthquakes, a uniform catalog with moment magnitudes”, Journal of Seismology, (2013), 17, 897–911. https://doi.org/10.1007/s10950-013-9360-9.

Khamis A., Ismail Z., Haron K., Tarmizi A., “The Effects of Outliers Data on Neural Network Performance”. Journal of Applied Sciences, (2005), 5: 1394-1398.

Kimiaefar,R., Siahkoohi,HR., Hajian,A., Kalhor,A., Random noise attenuation by Wiener-ANFIS filtering”, Journal of Applied Geophysics ,159,(2018), 453-459.

Official Report, Mormori Earthquake of 18 August 2014, International Institute of Earthquake Engineering and Seismology (iiees.ac.ir), (2014). http://www.iiees.ac.ir/en/mormori-earthquake-of-18-august-2014-mw-6-2/.

Rajabi E., Ghodrati Amiri G., Ghasemi V., “Peak Ground Acceleration Prediction for Critical Aftershocks”, 8th International Conference on Seismology and Earthquake Engineering, Tehran, (2019).

Rojas, O., B. Otero, L. Alvarado, Sergi Mus and R. Tous. “Artificial Neural Networks as Emerging Tools for Earthquake Detection.” Computación y Sistemas, (2019), 23: 335-350.

Shiuly, A., Roy, N. & Sahu, R.B. “Prediction of peak ground acceleration for Himalayan region using artificial neural network and genetic algorithm”. Arabian Journal of Geoscience, 13, 215 (2020). https://doi.org/10.1007/s12517-020-5211-5 .

Tabatabaei, M., Kimiaefar, R., Hajian, A. et al. “Robust outlier detection in geo-spatial data based on LOLIMOT and KNN search”. Earth Science Informatics 14, 1065–1072 (2021). https://doi.org/10.1007/s12145-021-00610-9.

Takagi,T., Sugeno,M, “Fuzzy Identification of Systems and Its Application to Modeling and Control”, IEEE Transactions on Systems Man and Cybernetics,15,(1985),116-132.

Thomas S., Pillai G.N., Pal K, Jagtap P., “Prediction of ground motion parameters using randomized ANFIS (RANFIS)”, Applied Soft Computing, Volume 40, (2016), Pages 624-634.

Verges, J., Saura, E., Casciello, E., Fernàndez, M., Villaseñor, A., Jiménez-Munt, I., & García-Castellanos, D., Crustal-scale cross-sections across the NW Zagros belt: Implications for the Arabian margin reconstruction. Geological Magazine, (2011), 148(5-6), 739-761.