Determination of near-surface structures from multi-channel surface wave data using multi-layer perceptron neural network (MLPNN) algorithm

Caylak, C.; Kaftan, I.

doi:10.2478/s11600-014-0207-8

Artykuł - szczegóły

Tytuł artykułu

Determination of near-surface structures from multi-channel surface wave data using multi-layer perceptron neural network (MLPNN) algorithm

Autorzy

Caylak C. , Kaftan I.

Wybrane pełne teksty z tego czasopisma

https://www.springer.com/journal/11600

Identyfikatory

DOI

10.2478/s11600-014-0207-8

Warianty tytułu

Języki publikacji

Abstrakty

This study proposes the use of multi-layer perceptron neural networks (MLPNN) to invert dispersion curves obtained via multi-channel analysis of surface waves (MASW) for shear S-wave velocity profile. The dispersion curve used in inversion includes the fundamental-mode dispersion data. In order to investigate the applicability and performance of the proposed MLPNN algorithm, test studies were performed using both synthetic and field examples. Gaussian random noise with a standard deviation of 4 and 8% was added to the noise-free test data to make the synthetic test more realistic. The model parameters, such as S-wave velocities and thicknesses of the synthetic layered-earth model, were obtained for different S/N ratios and noise-free data. The field survey was performed over the natural gas pipeline, located in the Germencik district of Aydın city, western Turkey. The results show that depth, velocity, and location of the embedded natural gas pipe are successfully estimated with reasonably good approximation.

Słowa kluczowe

multi-layer perceptron neural networks multi-channel analysis dispersion curve near-surface structure

wielowarstwowe perceptronowe sieci neuronowe analiza wielokanałowa krzywa dyspersji warstwa przypowierzchniowa

Wydawca

Instytut Geofizyki PAN
Springer

Czasopismo

Acta Geophysica

Rocznik

2014

Tom

Vol. 62, no. 6

Strony

1310--1327

Opis fizyczny

Bibliogr. 55 poz.

Twórcy

autor

Caylak C.

Cumhuriyet University, Faculty of Engineering, Department of Geophysical Engineering, Sivas, Turkey

autor

Kaftan I.

ilknur.kaftan@deu.edu.tr

Dokuz Eylül University, Faculty of Engineering, Department of Geophysical Engineering, Buca-Izmir, Turkey

Bibliografia

[1] Ahl, A. (2003), Automatic 1D inversion of multifrequency airborne electromagnetic data with artificial neural networks: discussion and a case study, Geophys. Prospect. 51,2, 89–98, DOI: 10.1046/j.1365-2478.2003.00356.x. http://dx.doi.org/10.1046/j.1365-2478.2003.00356.x
[2] Al-Garni, M.A. (2009), Interpretation of some magnetic bodies using neural networks inversion, Arab. J. Geosci. 2,2, 175–184, DOI: 10.1007/s12517-008-0026-9. http://dx.doi.org/10.1007/s12517-008-0026-9
[3] Baddari, K., T. Aifa, N. Djarfour, and J. Ferahtia (2009), Application of a radial basis function artificial neural network to seismic data inversion, Comp. Geosci. 35,12, 2338–2344, DOI: 10.1016/j.cageo.2009.03.006. http://dx.doi.org/10.1016/j.cageo.2009.03.006
[4] Beaty, K.S., D.R. Schmitt, and M. Sacchi (2002), Simulated annealing inversion of multimode Rayleigh wave dispersion curves for geological structure, Geophys. J. Int. 151,2, 622–631, DOI: 10.1046/j.1365-246X.2002.01809.x. http://dx.doi.org/10.1046/j.1365-246X.2002.01809.x
[5] 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, 45–53, DOI: 10.1190/1.2231110. http://dx.doi.org/10.1190/1.2231110
[6] Bielecki, A., and J. Ombach (2004), Shadowing property in analysis of neural networks dynamics, J. Comput. Appl. Math. 164–165, 107–115, DOI: 10.1016/S0377-0427(03)00486-2. http://dx.doi.org/10.1016/S0377-0427(03)00486-2
[7] Bielecki, A., and J. Ombach (2011), Dynamical properties of a perceptron learning process: structural stability under numerics and shadowing, J. Nonlinear Sci. 21,4, 579–593, DOI: 10.1007/s00332-011-9094-1. http://dx.doi.org/10.1007/s00332-011-9094-1
[8] Bozkurt, E., and R.G. Park (1994), Southern Menderes Massif: an incipient metamorphic core complex in western Anatolia, Turkey, J. Geol. Soc. 151, 213–216, DOI: 10.1144/gsjgs.151.2.0213. http://dx.doi.org/10.1144/gsjgs.151.2.0213
[9] Çağlayan, A.M., E.M. Öztürk, Z. Öztürk, H. Sav, and U. Akat (1980), Structural observations on the southern Menderes Massif, Jeoloji Mühendisligi Dergisi 10, 9–18 (in Turkish).
[10] 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. http://dx.doi.org/10.1190/1.1444205
[11] Cybenko, G. (1989), Approximation by superpositions of a sigmoidal function, Math. Control Signal. Syst. 2,4, 303–314, DOI: 10.1007/BF02551274. http://dx.doi.org/10.1007/BF02551274
[12] Del Frate, F., F. Pacifici, G. Schiavon, and C. Solimini (2007), Use of neural networks for automatic classification from high-resolution images, IEEE Trans. Geosci. Remote Sens. 45,4, 800–809, DOI: 10.1109/TGRS.2007. 892009. http://dx.doi.org/10.1109/TGRS.2007.892009
[13] Dora, O.Ö., O. Candan, S. Dürr, and R. Oberhänsli (1995), New evidence on the geotectonic evolution of the Menderes Massif. In: Proc. Int. Earth Sciences Colloquium on the Aegean Region, Izmir, Turkey, 53–72.
[14] El-Qady, G., and K. Ushijima (2001), Inversion of DC resistivity data using neural networks, Geophys. Prospect. 49,4, 417–430, DOI: 10.1046/j.1365-2478.2001.00267.x. http://dx.doi.org/10.1046/j.1365-2478.2001.00267.x
[15] Feng, S., T. Sugiyama, and H. Yamanaka (2005), Effectiveness of multi-mode surface wave inversion in shallow engineering site investigations, Explor. Geophys. 36,1, 26–33, DOI: 10.1071/EG05026. http://dx.doi.org/10.1071/EG05026
[16] Haykin, S. (1999), Neural Network — A Comprehensive Foundation, 2nd ed., Prentice Hall, Englewood Cliffs.
[17] He, Q., and H. Zhou (2003), Application of artificial neural networks to seismic waveform inversion. In: W. Sandham and M. Leggett (eds.), Geophysical Applications of Artificial Neural Networks and Fuzzy Logic, Kluwer Academic Publishers, Boston, 89–101, DOI: 10.1007/978-94-017-0271-3_7. http://dx.doi.org/10.1007/978-94-017-0271-3_7
[18] Hetzel, R., U. Ring, C. Akal, and M. Troesch (1995), Miocene NNE-directed extensional unroofing in the Menderes Massif, southwestern Turkey, J. Geol. Soc. 152,4, 639–654, DOI: 10.1144/gsjgs.152.4.0639. http://dx.doi.org/10.1144/gsjgs.152.4.0639
[19] Hornik, K. (1991), Approximation capabilities of multilayer feedforward networks, Neural Networks 4,2, 251–257, DOI: 10.1016/0893-6080(91)90009-T. http://dx.doi.org/10.1016/0893-6080(91)90009-T
[20] Hornik, K. (1993), Some new results on neural network approximation, Neural Networks 6,8, 1069–1072, DOI: 10.1016/S0893-6080(09)80018-X. http://dx.doi.org/10.1016/S0893-6080(09)80018-X
[21] Hornik, K., M. Stinchcombe, and H. White (1989), Multilayer feedforward networks are universal approximators, Neural Networks 2,5, 359–366, DOI: 10.1016/0893-6080(89)90020-8. http://dx.doi.org/10.1016/0893-6080(89)90020-8
[22] Kaftan, I., M. Şalk, and Y. Şenol (2011), Evaluation of gravity data by using artificial neural networks case study: Seferihisar geothermal area (Western Turkey), J. Appl. Geophys. 75,4, 711–718, DOI: 10.1016/j.jappgeo.2011.09.017. http://dx.doi.org/10.1016/j.jappgeo.2011.09.017
[23] Koçyiğit, A., H. Yusufoğlu, and E. Bozkurt (1999), Evidence from the Gediz graben for episodic two-stage extension in western Turkey, J. Geol. Soc. 156,3, 605–616, DOI: 10.1144/gsjgs.156.3.0605. http://dx.doi.org/10.1144/gsjgs.156.3.0605
[24] Kůrková, V. (1992), Kolmogorov’s theorem and multilayer neural networks, Neural Networks 5,3, 501–506, DOI: 10.1016/0893-6080(92)90012-8. http://dx.doi.org/10.1016/0893-6080(92)90012-8
[25] Lips, A.L.W., D. Cassard, H. Sözbilir, H. Yılmaz, and J.R. Wijbrans (2001), Multistage exhumation of the Menderes Massif, western Anatolia (Turkey), Int. J. Earth Sci. 89,4, 781–792, DOI: 10.1007/s005310000101. http://dx.doi.org/10.1007/s005310000101
[26] Nagai, K., A. O’Neill, Y. Sanada, and Y. Ashida (2005), Genetic algorithm inversion of Rayleigh wave dispersion from CMPCC gathers over a shallow fault model, J. Environ. Eng. Geophys. 10,3, 275–286, DOI: 10.2113/JEEG10.3.275. http://dx.doi.org/10.2113/JEEG10.3.275
[27] Nasseri-Moghaddam, A., G. Cascante, C. Phillips, and D.J. Hutchinson (2007), Effects of underground cavities on Rayleigh waves — field and numerical experiments, Soil Dyn. Earthq. Eng. 27,4, 300–313, DOI: 10.1016/j.soildyn.2006.09.002. http://dx.doi.org/10.1016/j.soildyn.2006.09.002
[28] Neyamadpour, A., S. Taib, and W.A.T.W. Abdullah (2009), Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application, Comput. Geosci. 35,11, 2268–2274, DOI: 10.1016/j.cageo.2009.04.004. http://dx.doi.org/10.1016/j.cageo.2009.04.004
[29] Özer, S., and H. Sözbilir (2003), Presence and tectonic significance of Cretaceous rudist species in the so-called Permo-Carboniferous Göktepe Formation, central Menderes metamorphic massif, western Turkey, Int. J. Earth Sci. 92,3, 397–404, DOI: 10.1007/s00531-003-0333-z. http://dx.doi.org/10.1007/s00531-003-0333-z
[30] Özer, S., H. Sözbilir, İ. Özkar, V. Toker, and B. Sarı (2001), Stratigraphy of Upper Cretaceous-Palaeogene sequences in the southern and eastern Menderes Massif (western Turkey), Int. J. Earth Sci. 89,4, 852–866, DOI: 10.1007/s005310000142. http://dx.doi.org/10.1007/s005310000142
[31] Park, C.B., R.D. Miller, and J. Xia (1999), Multichannel analysis of surface waves, Geophysics 64,3, 800–808, DOI: 10.1190/1.1444590. http://dx.doi.org/10.1190/1.1444590
[32] Pezeshk, S., and M. Zarrabi (2005), A new inversion procedure for spectral analysis of surface waves using a genetic algorithm, Bull. Seismol. Soc. Am. 95,5, 1801–1808, DOI: 10.1785/0120040144. http://dx.doi.org/10.1785/0120040144
[33] Sandham, W.A., and D.J. Hamilton (2011), Inverse theory, Artificial Neural Networks. In: H.K. Gupta (ed.), Encyclopedia of Solid Earth Geophysics, Springer Netherlands, 618–625, DOI: 10.1007/978-90-481-8702-7_35. http://dx.doi.org/10.1007/978-90-481-8702-7_35
[34] Şengör, A.M.C. (1982), Factors governing the neotectonic evolution of the Aegean. In: O. Erol, V. Oygür (eds.), Proc. 1982 Meeting of Geological Society of Turkey “Neotectonics and Volcanism of Western Anatolia, Panel”, Ankara, Turkey, 59–71 (in Turkish).
[35] Şengör, A.M.C. (1987), Cross-faults and differential stretching of hanging walls in regions of low-angle normal faulting: examples from western Turkey, Geol. Soc. London Spec. Publ. 28,1, 575–589, DOI: 10.1144/GSL.SP.1987.028.01.38. http://dx.doi.org/10.1144/GSL.SP.1987.028.01.38
[36] Şengör, A.M.C., and Y. Yılmaz (1981), Tethyan evolution of Turkey: A plate tectonic approach, Tectonophysics 75,3–4, 181–241, DOI: 10.1016/0040-1951(81)90275-4.
[37] Şengör, A.M.C., M. Satır, and R. Akkök (1984), Timing of tectonic events in the Menderes Massif, western Turkey: Implications for tectonic evolution and evidence for pan-African basement in Turkey, Tectonics 3,7, 693–707, DOI: 10.1029/TC003i007p00693. http://dx.doi.org/10.1029/TC003i007p00693
[38] Seyitoğlu, G., and B.C. Scott (1992), The age of the Büyük Menderes graben (west Turkey) and its tectonic implications, Geol. Mag. 129,02, 239–242, DOI: 10.1017/S001675680000830X. http://dx.doi.org/10.1017/S001675680000830X
[39] Socco, L.V., and D. Boiero (2008), Improved Monte Carlo inversion of surface wave data, Geophys. Prospect. 56,3, 357–371, DOI: 10.1111/j.1365-2478. 2007.00678.x. http://dx.doi.org/10.1111/j.1365-2478.2007.00678.x
[40] Socco, L.V., and C. Strobbia (2004), Surface wave method for near-surface characterization: A tutorial, Near Surf. Geophys. 2,4, 165–185, DOI: 10.3997/1873-0604.2004015.
[41] Song, X., H. Gu, J. Liu, and X. Zhang (2007), Estimation of shallow subsurface shear-wave velocity by inverting fundamental and higher-mode Rayleigh waves, Soil Dyn. Earthq. Eng. 27,7, 599–607, DOI: 10.1016/j.soildyn. 2006.12.003. http://dx.doi.org/10.1016/j.soildyn.2006.12.003
[42] Song, X., H. Gu, X. Zhang, and J. Liu (2008), Pattern search algorithms for nonlinear inversion of high-frequency Rayleigh-wave dispersion curves, Comput. Geosci. 34,6, 611–624, DOI: 10.1016/j.cageo.2007.05.019. http://dx.doi.org/10.1016/j.cageo.2007.05.019
[43] Spichak, V., and I. Popova (2000), Artificial neural network inversion of magnetotelluric data in terms of three-dimensional earth macroparameters, Geophys. J. Int. 142,1, 15–26, DOI: 10.1046/j.1365-246x.2000.00065.x. http://dx.doi.org/10.1046/j.1365-246x.2000.00065.x
[44] Steeples, D.W. (2005), Near-surface geophysics: 75 years of progress, The Leading Edge 24,Suppl. 1, 82–85, DOI: 10.1190/1.2112395. http://dx.doi.org/10.1190/1.2112395
[45] Supranata, Y.E., M.E. Kalinski, and Q. Ye (2007), Improving the uniqueness of surface wave inversion using multiple-mode dispersion data, Int. J. Geomech. 7,5, 333–343, DOI: 10.1061/(ASCE)1532-3641(2007)7:5(333). http://dx.doi.org/10.1061/(ASCE)1532-3641(2007)7:5(333)
[46] Tallavó, F., G. Cascante, and M. Pandey (2009), Experimental and numerical analysis of MASW tests for detection of buried timber trestles, Soil Dyn. Earthq. Eng. 29,1, 91–102, DOI: 10.1016/j.soildyn.2008.01.011. http://dx.doi.org/10.1016/j.soildyn.2008.01.011
[47] Tso, B., and P.M. Mather (2009), Classification Methods for Remotely Sensed Data, 2nd ed., CRC Press, Boca Raton. http://dx.doi.org/10.1201/9781420090741
[48] Van der Baan, M., and C. Jutten (2000), Neural networks in geophysical applications, Geophysics 65,4, 1032–1047, DOI: 10.1190/1.1444797. http://dx.doi.org/10.1190/1.1444797
[49] 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. http://dx.doi.org/10.1190/1.1443281
[50] Xia, J., R.D. Miller, and C.B. Park (1999), Estimation of near-surface shear-wave velocity by inversion of Rayleigh waves, Geophysics 64,3, 691–700, DOI: 10.1190/1.1444578. http://dx.doi.org/10.1190/1.1444578
[51] Xia, J., R.D. Miller, and C.B. Park (2000), Advantages of calculating shear-wave velocity from surface waves with higher modes, SEG Tech. Progr. Expand. Abstr. 2000, 1295–1298, DOI: 10.1190/1.1815633. http://dx.doi.org/10.1190/1.1815633
[52] Xia, J., R.D. Miller, C.B. Park, and G. Tian (2003), Inversion of high frequency surface waves with fundamental and higher modes, J. Appl. Geophys. 52,1, 45–57, DOI: 10.1016/S0926-9851(02)00239-2. http://dx.doi.org/10.1016/S0926-9851(02)00239-2
[53] Xia, J., R.D. Miller, and Y. Xu (2008), Data-resolution matrix and model-resolution matrix for Rayleigh-wave inversion using a damped least-squares method, Pure Appl. Geophys. 165,7, 1227–1248, DOI: 10.1007/s00024-008-0364-2. http://dx.doi.org/10.1007/s00024-008-0364-2
[54] Xu, C., and S.D. Butt (2006), Evaluation of MASW techniques to image steeply dipping cavities in laterally inhomogeneous terrain, J. Appl. Geophys. 59,2, 106–116, DOI: 10.1016/j.jappgeo.2005.08.003. http://dx.doi.org/10.1016/j.jappgeo.2005.08.003
[55] 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. http://dx.doi.org/10.1046/j.1365-2478.1997.660299.x

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-5e0ffd54-8318-413f-9c9a-e81119c15b05