Skip to main content
SpringerLink
Log in

3D inversion of DC data using artificial neural networks

  • Published:
Studia Geophysica et Geodaetica Aims and scope Submit manuscript

Abstract

In this paper, we investigate the applicability of artificial neural networks in inverting three-dimensional DC resistivity imaging data. The model used to produce synthetic data for training the artificial neural network (ANN) system was a homogeneous medium of resistivity 100 Ωm with an embedded anomalous body of resistivity 1000 Ωm. The different sizes for anomalous body were selected and their location was changed to different positions within the homogeneous model mesh elements. The 3D data set was generated using a finite element forward modeling code through standard 3D modeling software. We investigated different learning paradigms in the training process of the neural network. Resilient propagation was more efficient than any other paradigm. We studied the effect of the data type used on neural network inversion and found that the use of location and the apparent resistivity of data points as the input and corresponding true resistivity as the output of networks produces satisfactory results. We also investigated the effect of the training data pool volume on the inversion properties. We created several synthetic data sets to study the interpolation and extrapolation properties of the ANN. The range of 100–1000 Ωm was divided into six resistivity values as the background resistivity and different resistivity values were also used for the anomalous body. Results from numerous neural network tests indicate that the neural network possesses sufficient interpolation and extrapolation abilities with the selected volume of training data. The trained network was also applied on a real field dataset, collected by a pole-pole array using a square grid (8 ×8) with a 2-m electrode spacing. The inversion results demonstrate that the trained network was able to invert three-dimensional electrical resistivity imaging data. The interpreted results of neural network also agree with the known information about the investigation area.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aristodemou E., Pain C., De Oliveira C., Goddard T. and Harris C., 2005. Inversion of nuclear well-logging data using neural networks. Geophys. Prospect., 53, 103–120.

    Article  Google Scholar 

  • Baum E. and Haussler D., 1989. What size net gives valid generalization? In: Touretzky D. (Ed.), Advances in Neural Information Processing Systems I. Morgan Kaufman, San Mateo, CA, 80–90.

    Google Scholar 

  • Battiti R., 1992. First and second order methods for learning: between steepest descent and Newton’s method. Neural Comput., 4(2), 141–166.

    Article  Google Scholar 

  • Calderon-Macias C., Sen M. and Stoffa P., 2000. Artificial neural networks for parameter estimation in geophysics. Geophys. Prospect., 48, 21–47.

    Article  Google Scholar 

  • Chambers J.E., Ogilvy R.D., Kuras O., Cripps J.C. and Meldrum P.I., 2002. 3D electrical imaging of known targets at a controlled environmental test site. Environ. Geol., 41, 690–704.

    Article  Google Scholar 

  • Claerbout J.F. and Muir F., 1973. Robust modeling with erratic data. Geophysics, 38, 826–844.

    Article  Google Scholar 

  • Cranganu C., 2007. Using artificial neural networks to predict the presence of overpressured zones in the Anadarko Basin, Oklahoma. Pure Appl. Geophys., 164, 2067–2081.

    Article  Google Scholar 

  • Edwards L.S., 1977. A modified pseudosection for resistivity and induced-polarization. Geophysics, 42, 1020–1036.

    Article  Google Scholar 

  • El-Qady G., Monteiro Santos F.A., Hassaneen A.Gh. and Trindade L., 2005. 3D inversion of VES data from Saqqara archaeological area Egypt. Near Surf. Geophys., 3, 227–233.

    Google Scholar 

  • El-Qady G. and Ushijima K., 2001. Inversion of DC resistivity data using neural networks. Geophys. Prospect., 49, 417–430.

    Article  Google Scholar 

  • Hagan M.T., Demuth H.B. and Beale M.H., 1996. Neural Network Design. PWS Publishing, Boston, MA.

    Google Scholar 

  • Hagan M.T. and Menhaj M., 1994. Training feed forward networks with the Marquardt algorithms. IEEE Trans. Neural Netw., 5, 989–993.

    Article  Google Scholar 

  • Haykin S., 1994. Neural Networks: A Comprehensive Foundation. Macmilan, New York, ISBN: 0-02-352761-7.

    Google Scholar 

  • Ho T.L., 2009. 3-D inversion of borehole-to-surface electrical data using a back-propagation neural network. J. Appl. Geophys., 68, 489–499, doi: 10.1016/j.jappgeo.2008.06.002.

    Article  Google Scholar 

  • Irie B. and Miyake S., 1988. Capabilities of three-layered perceptrons. In: Caudill M. and Butler C. (Eds.), IEEE Conference on Neural Networks, Vol. 1. SOS Printing, San Diego, CA., 641–648.

    Chapter  Google Scholar 

  • Lippman R., 1987. An introduction to computing with neural nets. IEEE Trans. Acoust. Speech Signal Process., 4, 4–22.

    Google Scholar 

  • Loke M.H. and Barker R.D., 1996a. Practical techniques for 3D resistivity surveys and data Inversion. Geophys. Prospect., 44, 499–523.

    Article  Google Scholar 

  • Loke M.H. and Barker R.D., 1996b. Rapid least-squares inversion of apparent resistivity pseudo-sections using quasi-Newton method. Geophys. Prospect., 44, 131–152.

    Article  Google Scholar 

  • Loke M.H., 2000. Electrical Imaging Surveys for Environmental and Engineering Studies. A Practical Guide to 2D and 3D Surveys. http://www.terrajp.co.jp/lokenote.pdf.

  • Loke M.H., 2007. Res3Dinv Software, Version 2.14. Geoelectrical imaging 2D&3D, Pinang, Malaysia.

    Google Scholar 

  • McGillivray P.R. and Oldenburg D.W., 1990. Methods for calculating Frechet derivatives and sensitivities for the non-linear inverse problem: A comparative study. Geophys. Prospect., 38, 499–524.

    Article  Google Scholar 

  • Mehrotra K., Mohan C. and Ranka S., 1991. Bounds on the number of samples needed for learning. IEEE Trans. Neural Netw., 2, 548–558.

    Article  Google Scholar 

  • Poulton M. and El-Fouly A., 1991. Preprocessing GPR signatures for cascading neural network classification. SEG Expanded Abstracts, 10, 507–509, doi: 10.1190/1.1888789.

    Article  Google Scholar 

  • Poulton M., Sternberg K. and Glass C., 1992. Neural network pattern recognition of subsurface EM images. J. Appl. Geophys., 29, 21–36.

    Article  Google Scholar 

  • Powell M.J.D., 1977. Restart procedures for the conjugate gradient method. Math. Program., 12, 241–254.

    Article  Google Scholar 

  • Rajavelu A., Musavi M. and Shirvaikar M., 1989. A neural network approach to character recognition. Neural Netw., 2, 387–393.

    Article  Google Scholar 

  • Riedmiller M. and Braun H., 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. IEEE International Conference on Neural Networks (ICNN’93), 586–591, ISBN: 978-0780309999.

  • Sasaki Y., 1989. Two-dimensional joint inversion of magnetotelluric and dipole-dipole resistivity data. Geophysics, 54, 254–262.

    Article  Google Scholar 

  • Scales L.E., 1985. Introduction to Non-Linear Optimization. Springer-Verlag, New York.

    Google Scholar 

  • Singh U.K., Tiwari R.K. and Singh S.B., 2005. One-dimensional inversion of geoelectrical resistivity sounding data using artificial neural networks — a case study. Comput. Geosci., 31, 99–108.

    Article  Google Scholar 

  • Slater L. and Binley A., 2003. Evaluation of permeable reactive barrier (PRB) integrity using electrical imaging methods. Geophysics, 68, 911–921.

    Article  Google Scholar 

  • Soupios P.M., Georgakopoulos P., Papadopoulos N., Saltas V., Andeadakis A., Vallianatos F., Sarris A. and Makris J.P., 2007. Use of engineering geophysics to investigate a site for a building foundation. J. Geophys. Eng., 4, 94–103.

    Article  Google Scholar 

  • Spichak V.V., 2007. Neural network reconstruction of macro-parameters of 3-D geoelectric structures. In: Spichak V. (Ed.), Electromagnetic Sounding of the Earth’s Interior. Elsevier, Amsterdam, The Netherlands, 223–260.

    Google Scholar 

  • Spichak V.V., Fukuoka K., Kobayashi T., Mogi T., Popova I. and Shima H., 1999. Neural network based interpretation of insufficient and noisy MT data in terms of the target macro — parameters. In: Zhdanov M. and Wannamaker P. (Eds.), Extended Abstracts of 2nd Symposium on 3D Electromagnetics, Salt-Lake City, USA, 297–300 (http://www.igemi.troitsk.ru/~spichak/Spichak-pdf/EM3D99.PDF).

  • Spichak V.V., Fukuoka K., Kobayashi T., Mogi T., Popova I. and Shima H., 2002. Artificial neural network reconstruction of geoelectrical parameters of the Minou fault zone by scalar CSAMT data. J. Appl. Geophys., 49, 75–90.

    Article  Google Scholar 

  • Spichak V.V. and Popova I.V., 2000. Artificial neural network inversion of MT — data in terms of 3D earth macro-parameters. Geophys. J. Int., 42, 15–26.

    Article  Google Scholar 

  • Spitzer K., 1998. The three-dimensional DC sensitivity for surface and subsurface sources. Geophys. J. Int., 134, 736–746.

    Article  Google Scholar 

  • Sultan S.A., Monteiro-Santos F.A. and Helal A., 2006. A study of the groundwater seepage at Hibis Temple using geoelectrical data, Kharga Oasis, Egypt. Near Surf. Geophys., 4, 347–354.

    Google Scholar 

  • Tsourlos P. and Ogilvy R., 1999. An algorithm for the 3-D Inversion of Topographic Resistivity and Induced Polarization data: Preliminary Results. J. Balkan Geophys. Soc., 2(2), 30–45.

    Google Scholar 

  • Werbos P.J., 1994. The Roots of Back-Propagation. From Order Derivatives to Neural Networks and Political Forecasting. John Wiley &Sons, New York.

    Google Scholar 

  • Wiener J.M., Rogers J.A., Rogers J.F. and Moll R.F., 1991. Predicting carbonate permeabilities from wireline logs using a back-propagation neural network. SEG Expanded Abstracts, 10, 285–288.

    Article  Google Scholar 

  • Winkler E., 1994. Inversion of electromagnetic data using neural networks. Extended Abstracts of 56th EAEG Meeting, P124.

  • Zhao S. and Yedlin M.J., 1996. Some refinements on the finite-difference method for 3-D dc resistivity modeling. Geophysics, 61, 1301–1307.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Physics, University of Malaya, 50603 WP, Kuala Lumpur, Malaysia

    Ahmad Neyamadpour & W. A. T. Wan Abdullah

  2. Department of Geology, University of Malaya, 50603 WP, Kuala Lumpur, Malaysia

    Samsudin Taib

  3. Department of engineering, Azad Islamic University, Masjed e Soleyman branch, 6491796581, Azad, I.R. Iran

    Ahmad Neyamadpour & Danesh Niamadpour

Authors
  1. Ahmad Neyamadpour
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. W. A. T. Wan Abdullah
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Samsudin Taib
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Danesh Niamadpour
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ahmad Neyamadpour.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Neyamadpour, A., Wan Abdullah, W.A.T., Taib, S. et al. 3D inversion of DC data using artificial neural networks. Stud Geophys Geod 54, 465–485 (2010). https://doi.org/10.1007/s11200-010-0027-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11200-010-0027-5

Keywords

Search

Navigation