Simultaneous estimation of shape factor and depth of subsurface cavities from rresidual gravity anomalies using feed-forward back-propagation neural networks

• Autorzy: Hajian A. , Zomorrodian H. , Styles P.
• Języki publikacji: EN

Abstrakty

EN

We develop a new method of using feed-forward back-propagation (FFBP) neural networks to simultaneously estimate shape factor and depth of gravity anomalies. The advantages compared to neural network methods are the following: no pre-assumptions are made on source shape, the FFBP neural network estimates both depth and shape factor of source bodies and, once trained, works well for any new data in the training space, without repeating the initial calculations. The optimum number of neurons in the hidden layer was achieved with a novel multi-start algorithm. The FFBP model after training with suitable data sets and testing with different levels of noisy data is more robust than non-linear least squares minimization methods, especially for data with higher noise levels. The FFBP was tested for two sets of gravity field data over a major container terminal at Freeport, Grand Bahama, and a cavity anomaly at the Medford site, Florida, USA. The estimated parameters of the cavities agree well with the actual values.

Słowa kluczowe

EN

gravity anomaly; subsurface cavity; depth and shape estimation; feed-forward back-propagation neural networks

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2012
• Tom: Vol. 60, no. 4
• Strony: 1043--1075
• Opis fizyczny: Bibliogr. 70 poz.

Twórcy

autor

Hajian A.

autor

Zomorrodian H.

autor

Styles P.

• Department of Physics, Najafabad Branch, Islamic Azad University, Isfahan, Iran,

Bibliografia

• Abdelrahman, E.M., and T.M. El-Araby (1993), A least-squares minimization approach to depth determination from moving average residual gravity anomalies, Geophysics 58, 12, 1779-1784, DOI: 10.1190/1.1443392.
• Abdelrahman, E.M., and S.M. Sharafeldin (1995), A least-squares minimization approach to shape determination from gravity data, Geophysics 60, 2, 589-590, DOI: 10.1190/1.1443797.
• Abdelrahman, E.M., A.I. Bayoumi, Y.E. Abdelhady, M.M. Gobashy, and H.M. El-Araby (1989), Gravity interpretation using correlation factors between successive least-squares residual anomalies, Geophysics 54, 12, 1614-1621, DOI: 10.1190/1.1442629.
• Abdelrahman, E.M., A.I. Bayoumi, and H.M. El-Araby (1991), A least-squares minimization approach to invert gravity data, Geophysics 56, 1, 115-118, DOI: 10.1190/1.1442946.
• Abdelrahman, E.M., H.M. El-Araby, T.M. El-Araby, and E.R. Abo-Ezz (2001), Three least-squares minimization approaches to depth, shape, and amplitude coefficient determination from gravity data, Geophysics 66, 4, 1105-1109, DOI: 10.1190/1.1487058.
• Beiki, M., and L.B. Pedersen (2010), Eigenvector analysis of gravity gradient tensor to locate geologic bodies, Geophysics 75, 6, I37-I49, DOI: 10.1190/1.3484098.
• Bielecki, A. (2003), Mathematical model of architecture and learning process of artificial neural networks, TASK Quart. 7, 1, 93-114.
• Bishop, C.M., and G. Hinton (1995), Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
• Blakely, R.J., and R.W. Simpson (1986), Approximating edges of source Dobies from magnetic or gravity anomalies, Geophysics 51, 7, 1494-1498, DOI: 10.1190/1.1442197.
• Bowin, C., E. Scheer, and W. Smith (1986), Depth estimates from ratios of gravity, geoid, and gravity gradient anomalies, Geophysics 51, 1, 123-136, DOI: 10.1190/1.1442025.
• Butler, D.K. (1984), Microgravimetric and gravity gradient techniques for detection of subsurface cavities, Geophysics 49, 7, 1084-1096, DOI: 10.1190/1.1441723.
• Calderón-Macías, C., M.K. Sen, and P.L. Stoffa (1997), Hopfield neural networks, and mean field annealing for seismic deconvolution and multiple attenuation, Geophysics 62, 3, 992-1002, DOI: 10.1190/1.1444205.
• Calderón-Macías, C., M.K. Sen, and P.L. Stoffa (1998), Automatic NMO correction and velocity estimation by a feedforward neural network, Geophysics 63, 5, 1696-1707, DOI: 10.1190/1.1444465.
• Chamoli, A., R.P. Srivastava, and V.P. Dimri (2006), Source depth characterization of potential field data of Bay of Bengal by continuous wavelet transform, Indian J. Marine Sci. 35, 3, 195-204.
• Chentouf, R. (1997), Construction de Réseaux de Neurones Multicouches pour l’Approximation, Ph.D. Thesis, Institut National Polytechnique, Grenoble.
• Dai, H., and C. MacBeth (1994), Split shear-wave analysis using an artificial neural network, First Break 12, 605-613.
• Dowla, F.U., S.R. Taylor, and R.W. Anderson (1990), Seismic discrimination with artificial neural networks: Preliminary results with regional spectral data, Bull. Seismol. Soc. Am. 80, 5, 1346-1373.
• Efron, B., and R.J. Tibshirani (1993), An Introduction to the Bootstrap, Chapman & Hall, London.
• Elawadi, E., A. Salem, and K. Ushijima (2001), Detection of cavities and tunnels from gravity data using a neural network, Exploration Geophys. 32, 4, 204-208, DOI: 10.1071/EG01204.
• Essa, K.S. (2007), A simple formula for shape and depth determination from residua gravity anomalies, Acta Geophys. 55, 2, 182-190, DOI: 10.2478/s11600-007-0003-9.
• Günaydın, K., and A. Günaydın (2008), Peak ground acceleration prediction by artificial neural networks for Northwestern Turkey, Math. Probl. Eng. 2008, DOI: 10.1155/2008/919420.
• Gupta, O.P. (1983), A least-squares approach to depth determination from gravity data, Geophysics 48, 3, 357-360, DOI: 10.1190/1.1441473.
• Hajian, A. (2004), Depth Estimation of Gravity Anomalies by Neural Network, M.Sc. Thesis, Tehran University, Iran (in Persian).
• Hajian, A. (2008), Depth estimation of gravity anomalies by Hopfield Network. In: Proc. 5th Annual Meeting, AOGS: Asia Oceania Geosciences Society, Busan, Korea, Ext. Abstr. SE92-D3-PM2-P001.
• Hajian, A., P. Styles, and H. Zomorrodian (2011), Depth estimation of cavities from microgravity data through multi adaptive neuro fuzzy interference system. In: “Near Surface” 2011, Proc. 17th European Meeting of Environmental and Engineering Geophysics, 12-14 September 2011, Leicester, UK, Ext. Abstr. B08, ftp://ftp.sisyphe.jussieu.fr/public/Alain%20Tabbagh/Leicester-NSG2011/B08.pdf.
• Haykin, S. (1999), Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice-Hall Inc., Englewood Cliffs.
• Hérault, J., and C. Jutten (1994), Réseaux Neuronaux et Traitement du Signal, Hermès Édition, Traitement du Signal.
• Hjorth, J.S.U. (1994), Computer Intensive Statistical Methods Validation, Model Selection, and Bootstrap, Chapman & Hall Inc., London.
• Ho, T.L. (2009), 3-D inversion of borehole-to-surface electrical data using a backpropagation neural network, J. Appl. Geophys. 68, 4, 489-499, DOI: 10.1016/j.jappgeo.2008.06.002.
• Huang, Z., J. Shimeld, M. Williamson, and J. Katsube (1996), Permeability prediction with artificial neural network modeling in the Ventura gas field, offshore eastern Canada, Geophysics 61, 2, 422-436, DOI: 10.1190/1.1443970.
• Hush, D.R., and B.G. Horne (1993), Progress in supervised neural networks, IEEE Sign. Process. Mag. 10, 1, 8-39, DOI: 10.1109/79.180705.
• Kröse, B., and P. van der Smagt (1996), An Introduction to Neural Networks, 8th ed., The University of Amsterdam.
• Kumar, A.R.S., K.P. Sudheer, S.K. Jain, and P.K. Agarwal (2005), Rainfall-runoff modeling using artificial neural networks: Comparison of network types, Hydrol. Process. 19, 6, 1277-1291, DOI: 10.1002/hyp.5581.
• Langer, H., G. Nunnari, and L. Occhipinti (1996), Estimation of seismic waveform governing parameters with neural networks, J. Geophys. Res. 101, B9, 20109-20118, DOI: 10.1029/96JB00948.
• Levenberg, K. (1944), A method for the solution of certain nonlinear problems in least squares, Quart. Appl. Math. 2, 164-168.
• Li, X. (2006), Understanding 3D analytic signal amplitude, Geophysics 71, 2, 13-16, DOI: 10.1190/1.2184367.
• Lines, L.R., and S. Treitel (1984), A review of least-squares inversion and its application to geophysical problems, Geophys. Prospect. 32, 2, 159-186., DOI: 10.1111/j.1365-2478.1984.tb00726.x.
• Lippmann, R.P. (1987), An introduction to computing with neural nets, IEEE ASSP Mag. 4, 2, 4-22, DOI: 10.1109/MASSP.1987.1165576.
• Marquardt, D.W. (1963), An algorithm for least-squares estimation of nonlinear parameters, SIAM J. Appl. Math. 11, 2, 431-441, DOI: 10.1137/0111030.
• McCormack, M.D., D.E. Zaucha, and D.W. Dushek (1993), First-break refraction event picking and seismic data trace editing using neural networks, Geophysics 58, 1, 67-78, DOI: 10.1190/1.1443352.
• McCulloch, W.S., and W. Pitts (1943), A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biol. 5, 4, 115-133, DOI: 10.1007/BF02478259.
• Mohan, N.L., L. Anandababu, and S.V.S. Rao (1986), Gravity interpretation Rusing the Mellin transform, Geophysics 51, 1, 114-122, DOI: 10.1190/1.1442024.
• Murat, M.E., and A.J. Rudman (1992), Automated first arrival picking: A neural network approach, Geophys. Prospect. 40, 6, 587-604, DOI: 10.1111/j.1365-2478.1992.tb00543.x.
• Nandi, B.K., R.K. Shaw, and B.N.P. Agarwal (1997), A short note on identification of the shape of simple causative sources from gravity data, Geophys. Prospect. 45, 3, 513-520, DOI: 10.1046/j.1365-2478.1997.450279.x.
• Nettleton, L.L. (1976), Gravity and Magnetic in Oil Prospecting, McGraw-Hill, New York.
• Oruç, B. (2010), Depth estimation of simple causative sources from gravity gradient tensor invariants and vertical component, Pure Appl. Geophys. 167, 10, 1259-1272, DOI: 10.1007/s00024-009-0021-4.
• Osman, O., A.M. Albora, and O.N. Ucan (2007), Forward modeling with forced neural networks for gravity anomaly profile, Math. Geol. 39, 6, 593-605, DOI: 10.1007/s11004-007-9114-8.
• Panizzo, A., and R. Briganti (2007), Analysis of wave transmission behind lowcrested breakwaters using neural networks, Coast. Eng. 54, 9, 643-656, DOI: 10.1016/j.coastaleng.2007.01.001.
• Plutowski, M., S. Sakata, and H. White (1994), Cross-validation estimates IMSE. In: J.D. Cowan, G. Tesauro, and J. Alspector (eds.), Advances in Neural Information Processing Systems, 6, Morgan Kaufman, San Mateo, 391-398.
• Poulton, M.M. (ed.) (2001), Computational Neural Networks for Geophysical Data Processing, Elsevier, Kidlington, 335 pp., online version available at: http://www.knovel.com/web/portal/browse/display?_EXT_KNOVEL_DISPLAY_bookid=1902&.
• Poulton, M.M., B.K. Sternberg, and C.E. Glass (1992), Location of subsurface target in geophysical data using neural networks, Geophysics 57, 12, 1534- 1544, DOI: 10.1190/1.1443221.
• Principe, J.C., N.R. Euliano, and W.C. Lefebvre (1999), Neural and Adaptive Systems: Fundamentals through Simulations, John Wiley & Sons, New York.
• Reid, A.B., J.M. Allsop, H. Granser, A.J. Millett, and I.W. Somerton (1990), Magnetic interpretation in three dimensions using Euler deconvolution, Geophysics 55, 1, 80-91, DOI: 10.1190/1.1442774.
• Romeo, G. (1994), Seismic signals detection and classification using artificial neural networks, Ann. Geophys. 37, 3, 343-353.
• Roth, G., and A. Tarantola (1994), Neural networks and inversion of seismic data, J. Geophys. Res. 99, B4, 6753-6768, DOI: 10.1029/93JB01563.
• Roy, A. (1962), Ambiguity in geophysical interpretation, Geophysics 27, 1, 90-99, DOI: 10.1190/1.1438985.
• Roy, L., N.P. Agarwal, and R.K. Shaw (2000), A new concept in Euler deconvolution of isolated gravity anomalies, Geophys. Prospect. 48, 3, 559-575, DOI: 10.1046/j.1365-2478.2000.00203.x.
• Rumelhart, D.E., G.E. Hinton, and R.J. Williams (1986), Learning internal representation by error back propagation. In: D.E. Rumelhart and J.L. Mc Clelland (eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1. Foundations, MIT Press, Cambridge, USA, 318-362.
• Salem, A., E. Elawadi, and K. Ushijima (2003), Short note: Depth determination from residual gravity anomaly data using a simple formula, Comput. Geosci. 29, 6, 801-804, DOI: 10.1016/S0098-3004(03)00106-7.
• Shao, J., and D. Tu (1995), The Jackknife and Bootstrap, Springer-Verlag, New York.
• Sharma, B., and L.P. Geldart (1968), Analysis of gravity anomalies of twodimensional faults using Fourier transforms, Geophys. Prospect. 16, 1, 77- 93, DOI: 10.1111/j.1365-2478.1968.tb01961.x.
• Shaw, R.K., and B.N.P. Agarwal (1990), The application of Walsh transforms to interpret gravity anomalies due to some simple geometrically shaped causative sources: A feasibility study, Geophysics 55, 7, 843-850, DOI: 10.1190/1.1442898.
• Styles, P., R. McGrath, E. Thomas, and N.J. Cassidy (2005), The use of microgravity for cavity characterization in karstic terrains, Quart. J. Eng. Geol. Hydrogeol. 38, 2, 155-169, DOI: 10.1144/1470-9236/04-035.
• Thompson, D.T. (1982), EULDPH: A new technique for making computer-assisted depth estimates from magnetic data, Geophysics 47, 1, 31-37, DOI: 10.1190/1.1441278.
• Tibshirani, R. (1996), A comparison of some error estimates for neural Network models, Neural Comput. 8, 1, 152-163, DOI: 10.1162/neco.1996.8.1.152.
• van der Baan, M., and C. Jutten (2000), Neural networks in geophysical applications, Geophysics 65, 4, 1032-1047, DOI: 10.1190/1.1444797.
• Wang, L.X., and J.M. Mendel (1992), Adaptive minimum prediction-error deconvolution and source wavelet estimation using Hopfield neural networks, Geophysics 57, 5, 670-679, DOI: 10.1190/1.1443281.
• Weiss, S.M., and C.A. Kulikowski (1991), Computer Systems That Learn, Morgan Kaufmann, San Mateo.
• Zhang, Y., and K.V. Paulson (1997), Magnetotelluric inversion using regularized Hopfield neural networks, Geophys. Prospect. 45, 5, 725-743, DOI: 10.1046/ j.1365-2478.1997.660299.x.
• Zurada, J. (1992), Introduction to Artificial Neural Systems, West Publishing Company, St. Paul.