Robust Multi-Output Machine Learning Regression for Seismic Hazard Model Using Peak Crust Acceleration Case Study, Turkey, Iraq and Iran

Abstract

This paper for the first time improved a Robust Multi-Output machine learning regression model for seismic hazard zoning of Turkey, Iraq and Iran using constructed 3-D shear-wave velocity (Vs), seismic tomography dataset model for the crust and uppermost mantle beneath the study area. The focus of this paper’s opportunity is to develop a scientific framework leveraging machine learning that will ultimately provide the rapid and more complete characterization of earthquake properties. This work can be targeted at improving the seismic hazard zones system ability to detect and associate seismic signals, or at estimating other seismic characteristics (crust acceleration and crust energy) while traditionally, methods cannot monitor the earthquakes system. This work has derived some physical equations for extraction of many variables as inputs for our developed machine learning model based on a reliable understanding of the tomography data to physical variables by preparing huge dataset from different physical conditions of crust. We have extracted the velocity values of the shear waves from the original NETCDF file, which contains the S velocity values for every one km of the depths of the crust for the study area from one km down to the uppermost mantle beneath the Middle East. For the first time, this study calculated new seismic hazard parameter called Peak Crust Acceleration (PCA) for seismic hazard analysis by considering the transmitted initial seismic energy through the Earth’s crust layers from hypocenter. All machine learning algorithms in this study wrote in python language using anaconda platform the open-source Individual Edition (Distribution).

Keywords

robust multi-output regressor / tomography / peak crust acceleration / NETCDF / machine learning / hazards

References

[1] Agard P, Omrani J, Jolivet L, . Zagros Orogeny: A Subduction-Dominated Process. Geological Magazine, 2011, 148(5–6): 692-725.

[2] Aho T, Zenko B D, Zeroski S, . Multi-Target Regression with Rule Ensembles. J., Mach. Learn. Res., 2009, 373: 2055-2066.

[3] Allen M B, Saville C, Blanc E J P, . Orogenic Plateau Growth: Expansion of the Turkish-Iranian Plateau across the Zagros Fold-and-Thrust Belt. Tectonics, 2013, 32(2): 171-190.

[4] Appice A, Džeroski S. Stepwise Induction of Multi-Target Model Trees, 2007, Heidelberg, Berlin: Springer Machine Learning: ECML 2007

[5] Asim K M, Martínez-Álvarez F, Basit A, . Earthquake Magnitude Prediction in Hindukush Region Using Machine Learning Techniques. Natural Hazards, 2017, 85(1): 471-486.

[6] Berberian M, King G C P. Towards a Paleogeography and Tectonic Evolution of Iran. Canadian Journal of Earth Sciences, 1981, 18(2): 210-265.

[7] Borchani H, Varando G, Bielza C, . A Survey on Multi-Output Regression. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2015, 5(5): 216-233

[8] Böse M, Heaton T H, Hauksson E. Real-Time Finite Fault Rupture Detector (FinDer) for Large Earthquakes. Geophysical Journal International, 2012, 191(2): 803-812.

[9] Breiman L, Friedman J H. Predicting Multivariate Responses in Multiple Linear Regression. Journal of the Royal Statistical Society Series B: Statistical Methodology, 1997, 59(1): 3-54.

[10] Brown P, Zidek J. Adaptive Multivariate Ridge Regression. Ann. Stat., 1980, 8(1): 64-74.

[11] Brownlee, J., 2020. How to Develop Multi-Output Regression Models with Python, on March 27, 2020 in Ensemble Learning, Machine Learning Mastery, https://machinelearningmastery.com/multi-output-regression-models-with-python/

[12] Erdik M, Doyuran V, Akkaş N, . A Probabilistic Assessment of the Seismic Hazard in Turkey. Tectonophysics, 1985, 117(3/4): 295-344.

[13] Gitis V, Derendyaev A. Machine Learning Methods for Seismic Hazards Forecast. Geosciences, 2019, 9(7): 308

[14] Haitovsky Y. On Multivariate Ridge Regression. Biometrika, 1987, 74 3 563-570.

[15] Kaviani, A., 2020. 3-D Shear-Wave Velocity (Vs) Model for the Crust and Uppermost Mantle beneath the Middle East. Incorporated Research Institutions for Seismology (IRIS). IRIS Data Management Center. http://ds.iris.edu/spud/earthmodel

[16] Kaviani, A., Paul, A., Moradi, A., et al., 2020. Crustal and Uppermost Mantle Shear-Wave Velocity Structure beneath the Middle East from Surface-Wave Tomography. Geophys. J. Int., https://doi.org/10.17611/DP/18050884

[17] Keskin M. Magma Generation by Slab Steepening and Breakoff beneath a Subduction-Accretion Complex: An Alternative Model for Collision-Related Volcanism in Eastern Anatolia, Turkey. Geophysical Research Letters, 2003, 30: 1-4.

[18] Kramer S L. U. S. Department of Transportation, Federal Highway Administration, Washington, D. C. Geotechnical Earthquake Engineering, 1996, Upper Saddle River, NJ: Prentice-Hall, Inc.

[19] Kuhn M, Johnson K. Applied Predictive Modeling, 2013, New York: Springer

[20] Micchelli C A, Pontil M. On Learning Vector-Valued Functions. Neural Computation, 2005, 17(1): 177-204.

[21] Numan, N. M. S., 1997. A Plate Tectonic Scenario for the Phanerozoic Succession in Iraq. Iraqi Geological Journal, 89–90

[22] Perol T, Gharbi M, Denolle M. Convolutional Neural Network for Earthquake Detection and Location. Science Advances, 2018, 4(2): e1700578

[23] Seber D, Vallve M, Sandvol E, . Middle-East Tectonics: Applications of 20 Geographical Information Systems (GIS). GSA Today, 1997, 7: 1-5

[24] Similä T, Tikka J. Input Selection and Shrinkage in Multiresponse Linear Regression. Computational Statistics & Data Analysis, 2007, 52 406-422.

[25] Spyromitros-Xious, E., Groves, W., Tsoumakas, G., et al., 2012. MultiLabel Classication Methods for Multi-Target Regression. arXiv preprint arXiv:1211.6581, Cornel University Library, Ithaca

[26] Stöcklin J. Structural History and Tectonics of Iran: A Review. American Association of Petroleum Geologists Bulletin, 1968, 52: 1229-58.

[27] Thomas S, Pillai G N, Pal K, . Prediction of Ground Motion Parameters Using Randomized ANFIS (RANFIS). Applied Soft Computing, 2016, 40: 624-634.

[28] Trugman Daniel T, Shearer Peter M. Strong Correlation between Stress Drop and Peak Ground Acceleration for Recent M1 - 4 Earthquakes in the San Francisco Bay Area. Bulletin of the Seismological Society of America, 2018, 108(2): 929-945.

[29] Tsoumakas, G., Spyromitros-Xious, E., Vrekou, A., et al., 2014. MultiTarget Regression via Random Linear Target Combinations. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Springer Verlag, Nancy. 225–240

[30] USGS, 2020. “M6.7-4 km ENE of Doganyol, Turkey’. United States Geological Survey. Retrieved 24 January 2020

[31] Wong, I., Thomas, P., Abrahamson, N., 2004. The PEER-Lifelines Validation of Software Used in Probabilistic Seismic Hazard Analysis. In Geotechnical Engineering for Transportation Projects, 807–815

[32] Zhu W Q, Beroza G C. PhaseNet: A Deep-Neural-Network-Based Seismic Arrival-Time Picking Method. Geophysical Journal International, 2019, 216(1): 261-273

[33] Zukerman W. Turkey Earthquake Reveals a New Active Fault Zone. New Scientist, 2011, 212 2836 4