Estimating the Shapes of Gravity Sources through Optimized Support Vector Classifier (SVC)

• Autorzy: Hekmatian M. E. , Ardestani V. E. , Riahi M. A. , Bagh A. M. K. , Amini J.

Identyfikatory

DOI

10.1515/acgeo-2015-0022

• Języki publikacji: EN

Abstrakty

EN

In gravity interpretation methods, an initial guess for the approximate shape of the gravity source is necessary. In this paper, the support vector classifier (SVC) is applied for this duty by using gravity data. It is shown that using SVC leads us to estimate the approximate shapes of gravity sources more objectively. The procedure of selecting correct features is called feature selection (FS). In this research, the proper features are selected using inter/intra class distance algorithm and also FS is optimized by increasing and decreasing the number of dimensions of features space. Then, by using the proper features, SVC is used to estimate approximate shapes of sources from the six possible shapes, including: sphere, horizontal cylinder, vertical cylinder, rectangular prism, syncline, and anticline. SVC is trained using 300 synthetic gravity profiles and tested by 60 other synthetic and some real gravity profiles (related to a well and two ore bodies), and shapes of their sources estimated properly.

Słowa kluczowe

EN

gravity sources shapes; support vector classifier; SVC; feature; gravity profile; feature selection; FS

PL

grawitacja; kształt źródeł grawitacyjnych; klasyfikacja wektorów nośnych; cecha; wybór cech; FS

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2015
• Tom: Vol. 63, no. 4
• Strony: 1000--1024
• Opis fizyczny: Bibliogr. 16 poz., rys., tab., wykr.

Twórcy

autor

Hekmatian M. E.

• Faculty of Basic Sciences of Science and Research Branch, Islamic Azad University, Tehran, Iran
• Nuclear Fuel Cycle Research School of Nuclear Science and Technology Research Institute (NSTRI), Tehran, Iran

autor

Ardestani V. E.

• Institute of Geophysics, University of Tehran, Tehran, Iran

autor

Riahi M. A.

• Institute of Geophysics, University of Tehran, Tehran, Iran

autor

Bagh A. M. K.

• Nuclear Fuel Cycle Research School of Nuclear Science and Technology Research Institute (NSTRI), Tehran, Iran
• Faculty of Engineering of South Tehran Branch, Islamic Azad University, Tehran, Iran

autor

Amini J.

• Faculty of Engineering, University of Tehran, Tehran, Iran

Bibliografia

• [1] Ardestani, V.E. (2008), Modelling the karst zones in a dam site through microgravity data, Explor. Geophys. 39, 4, 204-209, DOI: 10.1071/EG08022.
• [2] Ardestani, V.E. (2009), Residual gravity map of a part of Institute of Geophysics of University of Tehran, University of Tehran, Tehran, Iran.
• [3] Baan, M., van der, and Ch. Jutten (2000), Neural networks in geophysical applications, Geophysics 65, 4, 1032-1047, DOI: 10.1190/1.1444797.
• [4] Belikov, M.V. (1978), Approximating of the external potentials of bodies rotation, M.Sc. Thesis on Physical-Mathematical Science, Institute of Theoretical Astronomy of the USSR Academy of Science, Leningrad State University (translation from Russian).
• [5] Blakely, J.R. (1996), Potential Theory in Gravity and Magnetic Applications, Cambridge University Press, Cambridge, 441 pp.
• [6] Camacho, A.G., F.G. Montesinos, and R. Vieira (2002), A 3-D gravity inversion tool based on exploration of model possibilities, Comput. Geosci. 28, 2, 191-204, DOI: 10.1016/S0098-3004(01)00039-5.
• [7] Duin, R.P.W., P. Juszczak, P. Paclik, E. Pekalska, D. de Ridder, D.M.J. Tax, and S. Verzakov (2007), PRTools4. 1 - A Matlab toolbox for pattern recognition, Delft University of Technology, Delft, Netherlands, http://www.prtools.org/.
• [8] Gret, A.A., and E.E. Klingele (1998), Application of Artificial Neural Networks for Gravity Interpretation in Two Dimensions, Institute of Geodesy and Photogrammetry, Swiss Federal Institute of Technology, Zürich, Switzerland.
• [9] Hashemi, H. (2010), Logical considerations in applying pattern recognition techniques on seismic data: Precise ruling, realistic solutions, CSEG Recorder 35, 4, 47-50.
• [10] Hashemi, H., D.M.J. Tax, R.P.W. Duin, A. Javaherian, and P. de Groot (2008), Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier, Nonlin. Process. Geophys. 15, 6, 863-871, DOI: 10.5194/npg-15-863-2008.
• [11] Heijden, F., van der, R.P.W. Duin, D. de Ridder, and D.M.J. Tax (2004), Classification, Parameter Estimation and State Estimation, An Engineering Approach using Mathlab, John Wiley & Sons Ltd, Chichester.
• [12] Hekmatian, M.E., V.E. Ardestani, M.A. Riahi, A.M. Koucheh Bagh, and J. Amini (2013), Fault depth estimation using support vector classifier and features selection, Appl. Geophys. 10, 1, 88-96, DOI: 10.1007/s11770-013-0371-7.
• [13] Osman, O., A.M. Albora, and O.N. Ucan (2006), A new approach for residual gravity anomaly profile interpretations: Forced Neural Network (FNN), Ann.Geophys. 49, 6, 1201-1208.
• [14] Plouff, D. (1976), Gravity and magnetic fields of polygonal prisms and application to magnetic terrain corrections, Geophysics 41, 4, 727-741, DOI: 10.1190/1.1440645.
• [15] Talwani, M., J.L. Worzel, and M. Landisman (1959), Rapid gravity computations for two-dimensional bodies with application to the Mendocino submarine fracture zone, J. Geophys. Res. 64, 1, 49-59, DOI: 10.1029/ JZ064i001p 00049.
• [16] Telford, W.M., L.P. Geldart, R.E. Sheriff, and D.A. Keys (1976), Applied Geophysics, Cambridge University Press, Cambridge.