1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 59, Issue 4
  5. Article
Volume 59, Issue 4
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

An artificial neural network method is proposed as a computationally economic alternative to numerical simulation by the Biot theory for predicting borehole seismoelectric measurements given a set of formation properties. Borehole seismoelectric measurements are simulated using a finite element forward model, which solves the Biot equations together with an equation for the streaming potential. The results show that the neural network method successfully predicts the streaming potentials at each detector, even when the input pressures are contaminated with 10% Gaussian noise. A fast inversion methodology is subsequently developed in order to predict subsurface material properties such as porosity and permeability from streaming potential measurements. The predicted permeability and porosity results indicate that the method predictions are more accurate for the permeability predictions, with the inverted permeabilities being in excellent agreement with the actual permeabilities. This approach was finally verified by using data from a field experiment. The predicted permeability results seem to predict the basic trends in permeabilities from a packer test. As expected from synthetic results, the predicted porosity is less accurate. Investigations are also carried out to predict the zeta potential. The predicted zeta potentials are in agreement with values obtained through experimental self potential measurements.

© 2011 European Association of Geoscientists & Engineers
Loading

Article metrics loading...

/content/journals/10.1111/j.1365-2478.2010.00935.x
2011-03-01
2024-04-20

  • From This Site

    /content/journals/10.1111/j.1365-2478.2010.00935.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. Anguiano‐RojasP., Dorantes‐HuertaD., SpurlinJ. and Mejia‐OlveraA.2003. Neural Networks for the Modelling of electrical and Induction logs. SPWLA 44th Annual Logging Symposium, Expanded Abstratcs, 22–25.
  2. AristodemouE., PainC., OliveiraC. D., GoddardA. and HarrisC.2005. Inversion of nuclear well‐logging data using neural networks. Geophysical Prospecting53, 103–120.
    [Google Scholar]
  3. BealeR. and JacksonT.1990. Neural Computing: An Introduction . IOP Publishing Ltd.
    [Google Scholar]
  4. BeamishD.1999. Characteristics of near‐surface electrokinetic coupling. Geophysical Journal International137, 231–242.
    [Google Scholar]
  5. BeamishD. and PeartR.1998. Electrokinetic geophysics a review. Terra Nova10, 48–55.
    [Google Scholar]
  6. BiotM.1956. The theory of propagation of elastic waves in a fluid‐saturated porous solid. i. Low frequency range. Journal of the Acoustical Society of America28, 168–178.
    [Google Scholar]
  7. BishopC.1995. Neural Networks for Pattern Recognition . Oxford University Press.
    [Google Scholar]
  8. BockrisJ. and ReddyA.1970. Modern Electrochemistry . Plenum Press.
    [Google Scholar]
  9. BrodingR., BuchananS. and HearnD.1963. Field experiments on the electroseismic effect. IEEE Transactions on Geoscience Electronics1, 23–31.
    [Google Scholar]
  10. ButlerK., RussellR., KepicA. and MaxwellM.1996. Measurement of the seismoelectric response from a shallow boundary. Geophysics61, 1769–1778.
    [Google Scholar]
  11. CarmineL., AristodemouE., PainC., MuggeridgeA. and OliveiraC. D.2008. Inversion of time‐dependent nuclear well‐logging data using neural networks. Geophysical Prospecting56, 115–140.
    [Google Scholar]
  12. EllisD. and SingerJ.2007. Well Logging for Earth Scientists . Springer.
    [Google Scholar]
  13. GaramboisS. and DietrichM.2001. Seismoelectric wave conversions in porous media: Field measurements and transfer function analysis. Geophysics66, 1417–1430.
    [Google Scholar]
  14. HaartsenM. and PrideS.1997. Electroseismic waves from point sources in layered media. Journal of Geophysical Research102, 24745–24769.
    [Google Scholar]
  15. HelleH., BhattA. and UrsinB.2001. Porosity and permeability prediction from wireline logs using artificial neural networks: a North sea case study. Geophysical Prospecting49, 431–444.
    [Google Scholar]
  16. MaitiS., TiwariR. and KümpelH.2007. Neural network modelling and classification of lithofacies using well log data: a case study from KTB borehole site. Geophysical Journal International169, 733–746.
    [Google Scholar]
  17. MarkovM.G. and VerzhbitskiyV.V.2004. Simulation of the electroseismic effect produced by an acoustic multipole source in a fluid‐filled borehole. SPWLA 45th Annual Logging Symposium, Expanded Abstracts.
  18. MartnerS. and SparksN.1959. The electroseismic effect. Geophysics24, 297–308.
    [Google Scholar]
  19. MatsuokaK.1992. Noise injection into inputs in backpropagation learning. IEEE Transactions on Systems, Man, and Cybernetics22, 436–440.
    [Google Scholar]
  20. MehrotraK., MohanC. and RankaS.1997. Elements of Artificial Neural Networks . MIT Press.
    [Google Scholar]
  21. MikhailovO., HaartsenM. and ToksözM.1997. Electroseismic investigation of the shallow subsurface: Field measurements and numerical modeling. Geophysics 62, 97–105.
    [Google Scholar]
  22. MikhailovO., QueenJ. and ToksözM.2000. Using borehole electroseismic measurements to detect and characterize fractured (permeable) zones. Geophysics65, 1098–1112.
    [Google Scholar]
  23. NeevJ. and YeattsF.1989. Electrokinetic effects in fluid‐saturated poroelastic media. Physics Review B40, 9135–9141.
    [Google Scholar]
  24. PainC., SaundersJ., WorthingtonM., SingerJ., Stuart‐BrugesW., MasonG. and GoddardA.2005. A mixed finite‐element method for solving the poroelastic Biot equations with electrokinetic coupling. Geophysical Journal International160, 592–608.
    [Google Scholar]
  25. ParkhomenkoE. and GaskarovI.1971. Borehole and laboratory studies of the seismoelectric effect of the second kind in rocks. Izv. Akad. Sci. USSR, Physics Solid Earth9, 663–666.
    [Google Scholar]
  26. PrideS.1994. Governing equations for the coupled electromagnetics and acoustics of porous media. Physics Review B50, 15678–15696.
    [Google Scholar]
  27. PrideS. and HaartsenM.1996. Electroseismic wave properties. The Journal of the Acoustical Society of America100, 1301–1315.
    [Google Scholar]
  28. QuireinJ., ChenD., GrableJ., WienerJ., SmithH., PerkinsT. and TruaxJ.2003. An assessment of neural networks applied to pulsed neutron data for predicting open hole triple combo data. SPWLA 44th Annual Logging Symposium, Expanded Abstracts.
  29. SaundersJ.2005. Electrical inversion and characterization methods in geophysics . PhD thesis, Imperial College London.
  30. SingerJ., SaundersJ., HollowayL., StollJ., PainC., Stuart‐BrugesW. and MasonG.2006. Electrokinetic logging has the potential to measure permeability. Petrophysics 47, 427–441.
    [Google Scholar]
  31. TangX., ChengC. and ToksözM.1991. Dynamic permeability and borehole Stoneley waves: A simplified Biot‐Rosenbaum model. Journal of the Acoustical Society of America90, 1632–1646.
    [Google Scholar]
  32. ThompsonA. and GistG.1993. Geophysical applications of electrokinetic conversion. The Leading Edge12, 1169–1173.
    [Google Scholar]
  33. ThompsonR.1936. The seismic electric effect. Geophysics1, 327–335.
    [Google Scholar]
  34. vander Baan M. and JuttenC.2000. Neural networks in geophysical applications. Geophysics65, 1032–1047.
    [Google Scholar]
  35. WorthingtonM. and HuntC.2000. Borehole electrokinetic responses in fracture dominated hydraulically conductive zones. Geophysical Research Letters27, 1315–1318.
    [Google Scholar]
  36. WurmstichB. and MorganF.1994. Modeling of streaming potential responses caused by oil well pumping. Geophysics59, 46–56.
    [Google Scholar]
  37. ZellA., MamierG. and VogtM.1995. Stuttgart Neural Network Simulation (SNNS) User manual, version 4.2. Institute for Parallel and Distributed High Performance System(IRIV).
    [Google Scholar]
  38. ZhangL., PoultonM. and WangT.2002. Borehole electrical resistivity modeling using neural networks. Geophysics67, 1790–1797.
    [Google Scholar]
  39. ZhuZ., HaartsenM. and ToksözM.1999. Experimental studies of electrokinetic conversions in fluid‐saturated borehole models. Geophysics64, 1349–1356.
    [Google Scholar]
  40. ZhuZ. and ToksözM.2005. Seismoelectric and seismomagnetic measurements in fractured borehole models. Geophysics70, F45–F51.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.1111/j.1365-2478.2010.00935.x
Loading
Artificial neural network forward modelling and inversion of electrokinetic logging data
Geophysical Prospecting 59, 721 (2011); https://doi.org/10.1111/j.1365-2478.2010.00935.x
/content/journals/10.1111/j.1365-2478.2010.00935.x
/content/journals/10.1111/j.1365-2478.2010.00935.x
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Artificial neural network; Biot theory; Borehole seismoelectric; Inversion

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