1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 49, Issue 4
  5. Article
Volume 49, Issue 4
  • E-ISSN: 1365-2478

Abstract

The inversion of geoelectrical resistivity data is a difficult task due to its non‐linear nature. In this work, the neural network (NN) approach is studied to solve both 1D and 2D resistivity inverse problems. The efficiency of a widespread, supervised training network, the back‐propagation technique and its applicability to the resistivity problem, is investigated. Several NN paradigms have been tried on a basis of trial‐and‐error for two types of data set. In the 1D problem, the batch back‐propagation paradigm was efficient while another paradigm, called resilient propagation, was used in the 2D problem. The network was trained with synthetic examples and tested on another set of synthetic data as well as on the field data. The neural network gave a result highly correlated with that of conventional serial algorithms. It proved to be a fast, accurate and objective method for depth and resistivity estimation of both 1D and 2D DC resistivity data. The main advantage of using NN for resistivity inversion is that once the network has been trained it can perform the inversion of any vertical electrical sounding data set very rapidly.

Loading

Article metrics loading...

/content/journals/10.1046/j.1365-2478.2001.00267.x
2001-12-21
2024-04-20

  • From This Site

    /content/journals/10.1046/j.1365-2478.2001.00267.x
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. AartsE. & KorstJ.1989.Simulated Annealing and Boltzmann Machines: A Stochastic Approach to Combinatorial Optimization and Neural Computing.John Wiley & Sons, Inc.
     [Google Scholar]
  2. ArgiloS.M.1967. Two computer programs for the calculation of standard graphs for resistivity prospection. Geophysical Prospecting15, 71–91.
    [Google Scholar]
  3. AshidaY.1996. Data processing of reflection seismic data by use of neural networks. Journal of Applied Geophysics35, 89–98.DOI: 10.1016/0926-9851(96)00010-9
     [Google Scholar]
  4. BaumE. & HausslerD.1989. What size net gives valid generalization? In: Advances in Neural Information Processing Systems I (ed. D.Touretzky ), pp. 80–90. Morgan Kaufman.
     [Google Scholar]
  5. BertsekasD.P. & TsitsiklisJ.N.1996.Neuro‐Dynamic Programming.Athena Scientific, Belmont, MA.
    [Google Scholar]
  6. BishopC.M.1995.Neural Networks for Pattern Recognition. Oxford University Press.
     [Google Scholar]
  7. BrownM. & PoultonM.1996. Locating buried objects for environmental site investigations using neural networks. Journal of Environmental and Engineering Geophysics1, 179–188.
    [Google Scholar]
  8. Calderón‐MaciasC., SenM., StoffaP.2000. Artificial neural networks for parameter estimation in geophysics. Geophysical Prospecting48, 21–47.DOI: 10.1046/j.1365-2478.2000.00171.x
     [Google Scholar]
  9. CarpenterG. & GrossbergS.1987. Art2: Self‐organization of stable category recognition codes for analog input patterns. Applied Optics26, 4919–4930.
    [Google Scholar]
  10. ChybaJ.1983. On the interpretation of resistivity soundings by the least‐squares method. Geophysical Prospecting31, 795–799.
    [Google Scholar]
  11. ConstableS., ParkerR., ConstableC.1987. Occam's inversion: a practical algorithm for generating smooth models from electromagnetic sounding data. Geophysics52, 289–300.
    [Google Scholar]
  12. DaiH. & MacBethC.1995. Automatic picking of seismic arrivals in local earthquake data using an artificial neural network. Geophysical Journal International120, 758–774.
    [Google Scholar]
  13. DeyA. & MorrisonH.1979. Resistivity modelling for arbitrarily shaped two‐dimensional structures. Geophysical Prospecting27, 106–136.
    [Google Scholar]
  14. El‐QadyG., HassaneenA.GH., UshijimaK.1998. Reconnaissance electrical resistivity survey of geothermal reservoir at H. Faraun hot spring, Sinai, Egypt. In: Proceedings of the 99th Meeting of the Society of Exploration Geophysics of Japan (SEGJ), Tokyo, Japan, pp. 121–126.
  15. El‐QadyG., UshijimaK., El‐SayedA.2000. Delineation of a geothermal reservoir by 2D inversion of resistivity data at Hamam Faraun area, Sinai, Egypt. In: Proceedings of the World Geothermal Congress 2000, Oita, Japan, pp. 1103–1108.
  16. GhoshD.1971. The application of linear filter theory on the direct interpretation of geoelectrical resistivity sounding measurements. Geophysical Prospecting19, 192–217.
    [Google Scholar]
  17. GriffithD. & BarkerR.1993. Two‐dimensional resistivity imaging and modeling in areas of complex geology. Journal of Applied Geophysics29, 211–226.
    [Google Scholar]
  18. HaykinS.1994.Neural Networks: A Comprehensive Foundation. Macmillan Publishing Co.
    [Google Scholar]
  19. HopfieldJ.1984. Neurons with graded response have collective computational properties like those of two‐state neurons. Proceedings of the National Academy of Sciences, USA81, 3088–3092.
    [Google Scholar]
  20. HuangS. & HuangY.1991. Bounds on the number of hidden neurons in multilayer perceptrons. IEEE Transactions on Neural Networks2, 47–55.DOI: 10.1109/72.80290
     [Google Scholar]
  21. HushD. & HorneB.1993. Progress in supervised neural networks – what's new since Lippman?IEEE Transactions on Signal Processing10, 8–39.
    [Google Scholar]
  22. InmanJ.1975. Resistivity inversion with ridge regression. Geophysics40, 798–817.
    [Google Scholar]
  23. IrieB. & MiyakeS.1988. Capabilities of three‐layered perceptrons. In: Proceedings of the 1st IEEE International Conference on Neural Networks, Vol. 1 (eds M.Caudill and C.Butler ), pp. 641–648. SOS Printing, San Diego, CA.
    [Google Scholar]
  24. JisongL., MizunagaH., UshijimaK.1999. Interpretation of Mise‐à‐la‐masse data using neural network. Butsuri-Tansa (SEGJ)52, 43–53.
    [Google Scholar]
  25. JohansenH.1977. A man/computer interpretation system for resistivity sounding over a horizontally stratified earth. Geophysical Prospecting25, 667–691.
    [Google Scholar]
  26. KoefoedO.1979.Geosounding Principles 1: Resistivity Sounding Measurements. Elsevier Science Publishing Co.
    [Google Scholar]
  27. KohonenT.1989.Self‐Organization and Associative Memory, 3rd edn. Springer‐Verlag, Inc.
     [Google Scholar]
  28. KunetzG. & RocroiJ.1970. Automatic processing of electrical soundings. Geophysical Prospecting18, 157–198.
    [Google Scholar]
  29. KungS. & HwangJ.1988. An algebraic projection analysis for optimal hidden units size and learning rates in back propagation learning. In: Proceedings of the 1st IEEE International Conference on Neural Networks, Vol. 1 (eds M.Caudill and C.Butler ), pp. 363–370. SOS Printing, San Diego, CA.
    [Google Scholar]
  30. LippmanR.1987. An introduction to computing with neural nets. IEEE Transactions on Acoustics, Speech and Signal Processing4, 4–22.
    [Google Scholar]
  31. LokeM. & BarkerR.1996. Rapid least‐squares inversion of apparent resistivity pseudo‐sections using a quasi‐Newton method. Geophysical Prospecting44, 131–152.
    [Google Scholar]
  32. McCormackM., ZauchaD., DushekD.1993. First‐break refraction picking and seismic data trace editing using neural network. Geophysics58, 67–78.
    [Google Scholar]
  33. MeheniY., GuerinR., BenderitterY., TabbaghA.1996. Subsurface DC resistivity mapping: approximate 1D interpretation. Journal of Applied Geophysics34, 255–270.
    [Google Scholar]
  34. MehrotraK., MohanC., RankaS.1991. Bounds on the number of samples needed for learning. IEEE Transactions on Neural Networks2, 548–558.DOI: 10.1109/72.97932
     [Google Scholar]
  35. MejuM.1992. An effective ridge regression procedure for resistivity data inversion. Computer and Geosciences18, 99–118.
    [Google Scholar]
  36. MejuM.1994.Geophysical Data Analysis: Understanding Inverse Problem Theory and Practice. Course Notes Series 6, Society of Exploration Geophysicists, Tulsa, OK.
    [Google Scholar]
  37. MuratM. & RudmanA.1992. Automated first arrival picking: a neural network approach. Geophysical Prospecting40, 587–604.
    [Google Scholar]
  38. NigrinA.1993.Neural Networks for Pattern Recognition. MIT Press, Cambridge, MA.
    [Google Scholar]
  39. PattersonD.1996. Artificial Neural Networks – Theory and Applications. Prentice‐Hall, Inc.
     [Google Scholar]
  40. PearsonW., WienerJ., MollR.1990. Aeromagnetic structural interpretation using neural networks: a case study from the northern Denver‐Julesberg Basin. 60th SEG meeting, San Francisco, USA, Expanded Abstracts, 587–590.
  41. PekerisC.1940. Direct method of interpretation in resistivity prospecting. Geophysics5, 31–42.
    [Google Scholar]
  42. PeltonW., RijoL., SwiftC.1978. Inversion of two‐dimensional resistivity and induced‐polarization data. Geophysics43, 788–803.
    [Google Scholar]
  43. PoultonM. & El‐FoulyA.1991. Preprocessing GPR signatures for cascading neural network classification. 61st SEG meeting, Houston, USA, Expanded Abstracts, 507–509.
  44. PoultonM., SternbergK., GlassC.1992. Neural network pattern recognition of subsurface EM images. Journal of Applied Geophysics29, 21–36.
    [Google Scholar]
  45. RaicheA.1991. A pattern recognition approach to geophysical inversion using neural networks. Geophysical Journal International105, 629–648.
    [Google Scholar]
  46. RajaveluA., MusaviM., ShirvaikarM.1989. A neural network approach to character recognition. Neural Networks2, 387–393.
    [Google Scholar]
  47. RiedmillerM. & BraunH.1993. A direct adaptive method for faster back propagation learning: the RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks 1993, San Francisco, USA, Expanded Abstracts, 586–591.
  48. RijoL., PeltonW., FeitosaE., WarsS.1977. Interpretation of apparent resistivity data from Apodi Valley, Rio Grande de Norte, Brasil. Geophysics42, 811–822.
    [Google Scholar]
  49. RöthG. & TarantolaA.1994. Neural networks and inversion of seismic data. Journal of Geophysical Research99, 6753–6768.
    [Google Scholar]
  50. RumelhartD.E., HintonG.E., WilliamsR.J.1986. Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1 (eds D.E.Rumelhart and J.L.McClelland ), pp. 318–362. MIT Press, Cambridge, MA.
    [Google Scholar]
  51. SasakiY.1981. Automatic interpretation of resistivity sounding data over two‐dimensional structure (I). Geophysical Exploration of Japan (Butsuri Tanko)34, 341–350 (in Japanese).
     [Google Scholar]
  52. SasakiY.1989. Two‐dimensional joint inversion of magnetotelluric and dipole–dipole resistivity data. Geophysics54, 254–262.
    [Google Scholar]
  53. SmithM.1993. Neural Networks for Statistical Modeling. Van Nostrand Reinhold, New York.
    [Google Scholar]
  54. SmithN. & VozoffK.1984. Two‐dimensional DC resistivity inversion for dipole–dipole data. IEEE Transactions on Geoscience and Remote Sensing22, 21–28.
    [Google Scholar]
  55. SzaraniecE.1980. Direct resistivity interpretation by accumulation of layers. Geophysical Prospecting28, 257–268.
    [Google Scholar]
  56. TaylorC.L. & VascoD.W.1990. Inversion of gravity gradiometry data using neural network. 60th SEG meeting, San Francisco, USA, Expanded Abstracts, 591–593.
  57. TrippA., HohmannG., SwiftC.1984. Two‐dimensional resistivity inversion. Geophysics49, 1708–1717.
    [Google Scholar]
  58. UchidaT.1991. Two‐dimensional resistivity inversion for Schlumberger sounding. Geophysical Exploration of Japan (Butsuri Tanko)44, 1–17.
    [Google Scholar]
  59. UchidaT. & MurakamiY.1990.Development of a Fortran code for two‐dimensional Schlumberger inversion. Open File Report No. 150, Geological Survey of Japan.
     [Google Scholar]
  60. WerbosP.J.1994.The Roots of Back‐Propagation. John Wiley & Sons, Inc.
     [Google Scholar]
  61. WienerJ., RogersJ., MollR.1991. Predicting carbonate permeabilities from wireline logs using a back‐propagation neural network. 61st SEG meeting, Houston, USA, Expanded Abstracts, 285–288.
  62. WinklerE.1994. Inversion of electromagnetic data using neural networks. 56th EAEG meeting, Vienna, Austria, Extended Abstracts, P124.
  63. ZhdanovM. & KellerG.1994. The Geoelectrical Methods in Geophysical Exploration: Methods in Geochemistry and Geophysics. Elsevier Science Publishing Co.
    [Google Scholar]
  64. ZohdyA.R.1989. A new method for automatic interpretation of Schlumberger and Wenner sounding curves. Geophysics54, 245–253.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.1046/j.1365-2478.2001.00267.x
Loading
Inversion of DC resistivity data using neural networks
Geophysical Prospecting 49, 417 (2001); https://doi.org/10.1046/j.1365-2478.2001.00267.x
/content/journals/10.1046/j.1365-2478.2001.00267.x
/content/journals/10.1046/j.1365-2478.2001.00267.x
Loading

Data & Media loading...

  • Article Type: Research Article

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error