Interpretation of spontaneous potential anomalies from some simple geometrically shaped bodies using neural network inversion

• Autorzy: Al-Garni M.A.
• Języki publikacji: EN

Abstrakty

EN

A new approach is proposed in order to interpret spontaneous potential (self-potential) anomalies related to simple geometric-shaped models such as sphere, horizontal cylinder, and vertical cylinder. This approach is mainly based on using neural network inversion of SP anomalies, particularly modular algorithm, for estimating the parameters of different simple geometrical bodies. However, Hilbert transforms are involved to determine the origin location in order to reduce the parameters which minimize the ambiguity in the inverted models. The inversion has been tested first on synthetic data from different models, using only one well-trained network. The results of inversion show that the parameter values derived by the inversion are identical to the true values of parameters. Noise analysis has been also examined, where the results of the inversion produce acceptable results up to 10% of white Gaussian noise. The validity of the neural network inversion is demonstrated through published real field SP taken from southern Bavarian Woods, Germany. A comparable and acceptable agreement is shown between the results of inversion derived by the neural network and those from the real field data.

Słowa kluczowe

EN

neural network inversion; modular algorithm; Hilbert transform; spontaneous potential anomalies; semi-infinite vertical cylinder

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2010
• Tom: Vol. 58, no. 1
• Strony: 143--162
• Opis fizyczny: Bibliogr. 42 poz.

Twórcy

autor

Al-Garni M.A.

• Department of Geophysics, Faculty of Earth Sciences, King Abdulaziz University, Jeddah, Saudi Arabia,

Bibliografia

• Abdelazeem, M., and M. Gobashy (2006), Self-potential inversion using genetic algorithm, J. King Abdulaziz Univ., Earth Sci. 17, 83-101.
• Abdelrahman, E.M., and S.M. Sharafeldin (1997), A least-squares approach to depth determination from self-potential anomalies caused by horizontal cylinder and spheres, Geophysics 62, 1, 44-48.
• Abdelrahman, E.M., T.M. El-Araby, A.A. Ammar, and H.I. Hassanein (1997a), A least-squares approach to shape determination from residual self-pottential anomalies, Pure Appl. Geophys. 150, 121-128.
• Abdelrahman, E.M., A.A. Ammar, S.M. Sharafeldin, and H.I. Hassanein (1997b), Shape and depth solutions from numerical horizontal selfpotential gradients, Appl. Geophys. 36, 31-43.
• Abdelrahman, E.M., A.A. Ammar, H.I. Hassanein, and M.A. Hafez (1998), Derivative analysis of SP anomalies, Geophysics 63, 3, 890-497.
• Abdelrahman. E.M., H.M. El-Araby, A.G. Hassaneen, and M.A. Hafez (2003), New methods for shape and depth determinations from SP data, Geophysics 68, 4, 1202-1210.
• Al-Garni, M.A. (2009), Interpretation of some magnetic bodies using neural networks inversion, Arab. J. Geosci. 2, 2, 175-184.
• Asfahani, J., and M. Tlas (2005), A constrained nonlinear programming technique for interpretation of self-potential anomalies due to two-dimensional inclined sheets of finite depth extent, J. King Abdulaziz Univ., Earth Sci. 16, 21-33.
• Azom, F. (2000), Biologically inspired modular neural networks, Ph.D. Dissertation, Virginia Tech., Blacksburg, USA, 138 pp, http://scholar.lib.vt.edu/theses/available/etd-06092000-12150028/unrestricted/etd.pdf.
• Bescoby, D.J., G.C. Cawley, and P.N. Chroston (2006), Enhanced interpretation of magnetic survey data from archaeological sites using artificial neural networks, Geophysics 71, 5, H45-H53.
• Bhatt, A., and H.B. Helle (2002), Committee neural network for porosity and permeability prediction from well logs, Geophys. Prospect. 50, 6, 645-660.
• Bhattacharya, B.B., and N. Roy (1981), A note on the use of a nomogram for self-potential anomalies, Geophys. Prosp. 29, 1, 102-107.
• Bishop, C.M. (1995a), Training with noise is equivalent to Tikhonov regularization, Neural Comp. 7, 1, 108-116.
• Bishop, C.M. (1995b), Neural Networks for Pattern Recognition, Oxford University Press, Oxford, UK, 482 pp.
• Calderón-Macias, C., M.K. Sen, and P.L. Stoffa (2000), Artificial neural networks for parameter estimation in geophysics, Geophys. Prospect. 48, 1, 21-47.
• El-Kaliouby, H. (2001), Extracting IP parameters from TEM data. In: M.M. Paulton (ed.), Computational Neural Networks for Geophysical Data Processing, Pergamon, Amsterdam, 307-326.
• El-Kaliouby, H.M., and M.A. Al-Garni (2009), Inversion of self-potential anomalie caused by 2D inclined sheets using neural networks, J. Geophys. Eng. 6, 1, 29-34.
• El-Kaliouby, H.M., M.M. Poulton and E.A. El-Diwany (1999), Inversion of coincident loop TEM data for layered polarizable ground using neural networks, Society of Exploration Geophysicists Expanded Abstr. 18, 259-262.
• Furness, P. (1992), Modelling spontaneous mineralization potentials with a new integraf equation, J. Appl. Geophys. 29, 2, 143-155.
• Guptasarma, D. (1983), Effect of surface polarization on resistivity modeling, Geophysics 48, 1, 98-106.
• Haykin, S. (1994), Neural Networks: A Comprehensive Foundation, Macmillan Publication Co, New York.
• Jain, L.C., and N.M. Martin (1999), Fusion of Neural Networks, Fuzzy Sets and Genetic Algorithms, Industrial Applications, CRC Press.
• Jang, J.S.R., C.T. Sun, and E. Mizutani (1997), Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall, Inc.
• Masters, T. (1993), Practical Neural Network Recipes in C++, Academic Press, New York, 493 pp.
• Meiser, P. (1962), A method for quantitative interpretation of self-potential anomalies, Geophys. Prospect. 10, 203-218.
• Nabighian, M.N. (1972), The analytic signal of two-dimensional magnetic Dobies with polygonal cross-section: Its properties and use for automatem anomaly interpretation, Geophysics 37, 3, 507-512.
• Paul, M.K. (1965), Direct interpretation of self-potential anomalies caused by inclined sheets of infinite horizontal extensions, Geophysics 30, 3, 418-423.
• Poulton, M.M. (2001), Computational Neural Networks for Geophysical Data Processing, Pergamon Press, Amsterdam.
• Poulton, M.M. (2002), Neural networks as an intelligence amplification tool: A review of applications, Geophysics 67, 3, 979-993.
• Raiche, A. (1991), A pattern recognition approach to geophysical inversion Rusing neural nets, Geophys. J. Int. 105, 3, 629-648.
• Rao, D.A., and H.V.R. Babu (1983), Quantitative interpretation of self-potential anomalies due to two-dimensional sheet-like bodies, Geophysics 48, 12, 1659-1664.
• Shi, W., and F.D. Morgan (1996), Non-uniqueness in self-potential inversion, Society of Exploration Geophysicists Expanded Abstracts 15, 950-953.
• Spichak, V., and I. Popova (2000), Artificial neural network inversion of magnetotelluric data in terms of three-dimensional earth macroparameters, Geophys. J. Int. 142, 15-26.
• Sundararajan, N. (1982), Interpretation techniques in geophysical exploration using the Hilbert transforms, Ph.D. Thesis, Osmania University, Hyderabad, India.
• Sundararajan, N., P. Srinivasa Rao, and V. Sunitha (1998), An analytical metod to interpret self-potential anomalies caused by 2-D inclined sheets, Geophysics 63, 5, 1551-1555.
• Thomas, J.B. (1969), An Introduction to Statistical Communication Theory, John Wiley & Sons Inc., New York.
• Van der Baan, M., and C. Jutten (2000), Neural networks in geophysical applications, Geophysics 65, 4, 1032-1047.
• Williams, P.M. (1995), Bayesian regularization and pruning using a Laplace prior, Neural Comp. 7, 1, 117-143.
• Yarger, H.L., R.R. Robertson, and R.L. Wentland (1978), Diurnal drift removal from aeromagnetic data using least squares, Geophysics 43, 6, 1148-1156.
• Yüngül, S. (1950), Interpretation of spontaneous polarization anomalies caused by spheroidal orebodies, Geophysics 15, 2, 237-246.
• Zhang, L., M.M. Poulton, and T. Wang (2002), Borehole electrical resistivity modeling using neural networks, Geophysics 67, 6, 1790-1797.
• Zhang, Q., and K. Gupta (2000), Neural Networks for RF and Microwave Design, Artech House Inc., Norwood, MA.