Fault depth estimation using support vector classifier and features selection
Mohammad Ehsan Hekmatian1,2, Vahid E. Ardestani3, Mohammad Ali Riahi3, Ayyub Memar Koucheh Bagh2, and Jalal Amini4
1. Faculty of Basic Sciences of Science and Research Branch, Islamic Azad University, Tehran, Iran.
2. Nuclear Fuel Cycle Research School of Nuclear Science & Technology Research Institute (NSTRI), Tehran, Iran.
3. Institute of Geophysics, University of Tehran, Tehran, Iran.
4. Faculty of Engineering, University of Tehran, Tehran, Iran.
Abstract Depth estimation of subsurface faults is one of the problems in gravity interpretation. We tried using the support vector classifier (SVC) method in the estimation. Using forward and nonlinear inverse techniques, detecting the depth of subsurface faults with related error is possible but it is necessary to have an initial guess for the depth and this initial guess usually comes from non-gravity data. We introduce SVC in this paper as one of the tools for estimating the depth of subsurface faults using gravity data. We can suppose that each subsurface fault depth is a class and that SVC is a classification algorithm. To better use the SVC algorithm, we select proper depth estimation features using a proper features selection (FS) algorithm. In this research, we produce a training set consisting of synthetic gravity profiles created by subsurface faults at different depths to train the SVC code to estimate the depth of real subsurface faults. Then we test our trained SVC code by a testing set consisting of other synthetic gravity profiles created by subsurface faults at different depths. We also tested our trained SVC code using real data.
Mohammad Ehsan Hekmatian,Vahid E. Ardestani,Mohammad Ali Riahi et al. Fault depth estimation using support vector classifier and features selection[J]. APPLIED GEOPHYSICS, 2013, 10(1): 88-96.
[1]
Cortes, C., and Vapnik, V., 1995, Support vector networks: Machine Learning, 20, 273 - 297.
[2]
Gret, A. A., and Klingele, E. E., 1998, Application of artificial neural networks for gravity interpretation in two dimensions: Institute of Geodesy and Photogrammetry, Swiss Federal Institute of Technology, Zurich.
Hashemi, H., Tax, D. M. J., Duin, R. P. W., Javaherian, A., and Groot, P., 2008, Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier: Nonlin. Processes Geophys., 15, 863 - 871.
[5]
Hekmatian, M. E., 2004, Software package preparation entitled: QuantInt, to be used for quantitative interpretation of magnetic gravitational data and one sample interpretation in exploration of uranium: J. of Nuclear Sci. and Tech., 30, 37 - 48.
[6]
Osman, O., Albora, A. M., and Ucan, O. N., 2006, A new approach for residual gravity anomaly profile interpretations: Forced neural network (FNN): Ann Geophys-Italy, 49, 1201 - 1208.
[7]
Telford, W. M., Geldart, L. P., Sheriff, R. E., and Keys, D. A., 1976, Applied geophysics: Cambridge University Press, Cambridge.
[8]
van der Baan, M. and Jutten, C., 2000, Neural networks in geophysical applications: Geophysics, 65(4), 1032 - 1047.
[9]
van der Heijden, F., Duin, R. P. W., de Ridder, D., and Tax, D. M. J., 2004, Classification, parameter estimation, and state estimation: John Wiley & Sons, Ltd, Chichester, England.
2013, Vol. 10 
