1887
Volume 53 Number 1
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

This work looks at the application of neural networks in geophysical well‐logging problems and specifically their utilization for inversion of nuclear downhole data. Simulated neutron and γ‐ray fluxes at a given detector location within a neutron logging tool were inverted to obtain formation properties such as porosity, salinity and oil/water saturation. To achieve this, the forward particle‐radiation transport problem was first solved for different energy groups (47 neutron groups and 20 γ‐ray groups) using the multigroup code EVENT. A neural network for each of the neutron and γ‐ray energy groups was trained to re‐produce the detector fluxes using the forward modelling results from 504 scenarios. The networks were subsequently tested on unseen data sets and the input parameters (formation properties) were then predicted using a global search procedure. The results obtained are very encouraging with formation properties being predicted to within 10% average relative error. The examples presented show that neural networks can be applied successfully to nuclear well‐logging problems. This enables the implementation of a fast inversion procedure, yielding quick and reliable values for unknown subsurface properties such as porosity, salinity and oil saturation.

Loading

Article metrics loading...

/content/journals/10.1111/j.1365-2478.2005.00432.x
2004-12-23
2024-03-29
Loading full text...

Full text loading...

References

  1. Al‐NuaimyW., HuangY., NakhashM., FangM.T.C., NguyenV.T. and ErikseA.2000. Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition. Journal of Applied Geophysics43, 157–165.DOI: 10.1016/S0926-9851(99)00055-5
    [Google Scholar]
  2. Van Der BaanM. and JuttenC.2000. Neural networks in geophysical applications. Geophysics65, 1032–1047.DOI: 10.1190/1.1444797
    [Google Scholar]
  3. BealeR. and JacksonI.1990. Neural Computing: An Introduction . Institute of Physics (IOP) Publishing Ltd.
    [Google Scholar]
  4. BeamishD.2000. Quantitative 2D VLF data interpretation. Journal of Applied Geophysics45, 33–47.DOI: 10.1029/93JB01563
    [Google Scholar]
  5. BenaoudaW.G., WhitmarshR.B., RothwellR.G. and MacLeodC.1999. Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program. Geophysical Journal International136, 477–491.
    [Google Scholar]
  6. BishopC.M.1995. Neural Networks for Pattern Recognition . Oxford University Press.
    [Google Scholar]
  7. Calderon‐MaciasC., SenM.K. and StoffaP.L.1998. Automatic NMO correction and velocity estimation by a feed‐forward neural network. Geophysics63, 1696–1707.DOI: 10.1190/1.1444465
    [Google Scholar]
  8. Calderon‐MaciasC., SenM.K. and StoffaP.L.2000. Artificial neural networks for parameter estimation in geophysics. Geophysical Prospecting48, 21–47.
    [Google Scholar]
  9. DuderstadtJ.J. and HamiltonL.J.1976. Nuclear Reactor Analysis . John Wiley & Sons, Inc.
    [Google Scholar]
  10. EisbergR. and ResnickR.1985. Quantum Physics of Atoms, Molecules, Solids, Nuclei, and Particles . John Wiley & Sons, Inc.
    [Google Scholar]
  11. EllisD.V.1987. Well‐Logging for Earth Scientists . Elsevier Science Publishing Co.
    [Google Scholar]
  12. El‐QadyG. and UshijimaK.2001. Inversion of DC resistivity data using neural networks. Geophysical Prospecting49, 417–430.DOI: 10.1046/j.1365-2478.2001.00267.x
    [Google Scholar]
  13. GorbachevY.I.1995. Well Logging: Fundamentals of Methods . John Wiley & Sons, Inc.
    [Google Scholar]
  14. De Groot‐HedlinC. and ConstableS.1990. Occam's inversion to generate smooth, two‐dimensional models from magnetotelluric data. Geophysics55, 1613–1624.DOI: 10.1190/1.1442813
    [Google Scholar]
  15. HelleH.B., BhattA. and UrsinB.2001. Porosity and permeability prediction from wireline logs using artificial neural networks: A North Sea case study. Geophysical Prospecting49, 431–444.DOI: 10.1046/j.1365-2478.2001.00271.x
    [Google Scholar]
  16. InmanJ.R.1975. Resistivity inversion with ridge regression. Geophysics40, 798–817.DOI: 10.1190/1.1440569
    [Google Scholar]
  17. LeggetM., SandhamW.A. and DurraniT.S.1996. 3D Horizon tracking using artificial neural networks. First Break14, 413–418.
    [Google Scholar]
  18. LewisE.E. and MillerW.F.1993. Computational Methods of Neutron Transport . American Nuclear Society Inc., La Grange Park , IL .
    [Google Scholar]
  19. LiY.G. and OldenburgD.W.1994. Inversion of 3D DC resistivity data using an approximate inverse mapping. Geophysical Journal International116, 527–537.
    [Google Scholar]
  20. LokeM.H.1998. Rapid 2D resistivity and IP inversions using the least squares method . The RES2DINV manual.
    [Google Scholar]
  21. LokeM.H. and DahlinW.2002. A comparison of the Gauss–Newton and quasi‐Newton method in resistivity imaging inversion. Journal of Applied Geophysics49, 149–162.DOI: 10.1016/S0926-9851(01)00106-9
    [Google Scholar]
  22. MehrotraK., MohanC.K. and RankaS.1997. Elements of Artificial Neural Networks . The MIT Press.
    [Google Scholar]
  23. MejuM.A., FenningP.J. and HawkinsT.R.W.2000. Evaluation of small‐loop transient EM soundings to locate the Sherwood Sandstone aquifer and confining formations at well sites in the Vale of York, England. Journal of Applied Geophysics44, 217–236.DOI: 10.1016/S0926-9851(00)00005-7
    [Google Scholar]
  24. MuratM.E. and RudmanA.1992. Automated first arrival picking: A neural network approach. Geophysical Prospecting40, 587–604.
    [Google Scholar]
  25. NathS.K., ChakrabortyS., SinghS.K. and GangulyN.1999. Velocity inversion in cross‐hole seismic tomography by the counter‐propagation neural network, genetic algorithm and evolutionary programming techniques. Geophysical Journal International138, 108–124.DOI: 10.1046/j.1365-246x.1999.00835.x
    [Google Scholar]
  26. OldenburgD.W. and LiY.1994. Inversion of induced polarisation data. Geophysics59, 1327–1341.DOI: 10.1190/1.1443692
    [Google Scholar]
  27. De OliveiraC.R.E.1986. An arbitrary geometry finite element method for multigroup neutron transport with anisotropic scattering. Progress in Nuclear Energy18, 227–236.DOI: 10.1016/0149-1970(86)90029-6
    [Google Scholar]
  28. PainC.C., HerwangerJ.V., SaundersJ.H., WorthingtonM.H. and De OliveiraC.R.E.2003. Anisotropic resistivity inversion. Inverse Problems19, 1081–1111.DOI: 10.1088/0266-5611/19/5/306
    [Google Scholar]
  29. PoultonM.M., StenbergB.K. and GlassC.E.1992. Location of subsurface targets in geophysical data using neural networks. Geophysics57, 1534–1544.DOI: 10.1190/1.1443221
    [Google Scholar]
  30. RothG. and TarantolaA.1994. Neural networks and inversion of seismic data. Journal of Geophysical Research99, 6753–6768.
    [Google Scholar]
  31. SasakiY.2001. Full 3D inversion of electromagnetic data on PC. Journal of Applied Geophysics46, 45–54.DOI: 10.1016/S0926-9851(00)00038-0
    [Google Scholar]
  32. SpichakV., FukuokaK., KobayashiT., MogiT., PopovaI. and ShimaH.2002. ANN reconstruction of geoelectrical parameters of the Minou fault zone by the scalar CSAMT data. Journal of Applied Geophysics49, 75–90.DOI: 10.1016/S0926-9851(01)00100-8
    [Google Scholar]
  33. WangY.H. and PrattR.G.2000. Seismic amplitude inversion for interface geometry of multi‐layered structures. Pure and Applied Geophysics157, 1601–1620.
    [Google Scholar]
  34. WhiteJ.E., IngersollD.T., WrightR.Q., HunterH.T., SlaterC.O., GreeneN.M., MacFarlaneR.E. and RoussinR.W.2000. Production and Testing of the VITAMIN‐B6 Fine group and the BUGLE‐96 Broad‐Group Neutron/Photon Cross‐section Libraries derived from ENDF/B‐VI Nuclear data . NUREG/CR‐6214/R1, ORNL‐6795/R1, Oak Ridge National Laboratory , Oak Ridge , TN .
    [Google Scholar]
  35. ZellA. et al . 1995. Stuttgart Neural Network Simulator (SNNS) User manual, version 4.2 . Institute for Parallel and Distributed High Performance Systems (IRVR), University of Stuttgart and Wilhelm‐Schickard Institute for Computer Science, University of Tubingen , Germany , Report No. 6/95.
    [Google Scholar]
  36. ZhangY. and PaulsonK.V.1997. Magnetotelluric inversion using regularized Hopfield neural networks. Geophysical Prospecting45, 725–743.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.1111/j.1365-2478.2005.00432.x
Loading
/content/journals/10.1111/j.1365-2478.2005.00432.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