Statistical Pattern Recognition and Geostatistical Data Integration

  • Jef Caers
  • Sanjay Srinivasan
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 80)


Statistical pattern recognition, particularly the neural network approach, has found many applications in reservoir characterization, enabling the use of multi-variate, imprecise and uncertain reservoir data. Geostatistics is a well-established field for 3D spatial modeling and uncertainty quantification of the reservoir facies and petro-physical properties. In this paper we present a theoretical and practical framework for developing and applying pattern recognition tools within the traditional geostatistical framework. We show that the power of soft computing tools within a geostatistical framework allows the modeler to make maximum use of the reservoir data. Geostatistics aims at integrating geophysical and reservoir engineering data, yet at the same time honoring geological continuity information provided by well data or by analog outcrop information. However, the traditional geostatistical framework does not allow an easy integration of “non-linear” reservoir data. Due to the nature of the governing physical laws, seismic amplitude data and production history data both exibit a non-linear and multiple point relationship with petrophysical properties such as porosity and permeability. In this paper we show how statistical pattern recognition tools can be integrated into traditional and novel geostastical simulation methods in order to deal with the imprecise and non-linear aspects of reservoir data. Probabilistic type neural networks such as the proposed logistic regression network are ideal tools to model the probabilistic relation between reservoir data and reservoir properties. The output of these types of neural networks is a conditional probability, rather than the single estimate provided by more traditional neural networks. A framework is presented where these networks can be integrated within any geostatistical simulation algorithm. We provide two examples of this novel approach. First we show how neural networks axe trained to build a non-linear relation between seismic amplitude data and reservoir facies. The trained neural network is used to constrain a fluvial reservoir to seismic amplitude data. A second example shows the worth of using neural networks in understanding and calibrating the non-linear relationship between the permeability heterogeneity and well test response data. The resultant neural network calibrated relationship is then used to condition multiple reservoir models to well test data using an iterative Gaussian simulation method.


Markov Chain Monte Carlo Seismic Data Training Image Pressure Profile Permeability Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Almeida, A. and Journel A.G. (1993). Joint simulation of multiple variables with a Markov-type co-regionalization model. Math Geology, 26(5):565–588.CrossRefGoogle Scholar
  2. Bishop, CM. (1995). Neural networks for pattern recognition, Oxford University Press, New York.Google Scholar
  3. Behrens, R., Macleod, M.K. and Iran, T.T. (1996). Incorporating seismic attribute maps in 3D reservoir models: in, Proceedings to the SPE Annual Conference and Technical Exhibition, Society of Petroleum Engineers, Denver, Oct. 4–7, SPE paper no. 36499.Google Scholar
  4. Caers, J. (1999). Stochastic reservoir characterization using multiple-point statistics. In: Proceedings of the IAMG 99, Fifth Annual Conference of the International Association for Mathematical Geology, Lippard, S.G. et al (eds.), 2, 467–472.Google Scholar
  5. Caers, J. (2001a). Automatic histogram and variogram reproduction in simulated annealing simulation. Mathematical Geology, 33(2):167–190.CrossRefGoogle Scholar
  6. Caers, J. (2001b). Geostatistical reservoir modeling using statistical pattern recognition. Journal of Petroleum Science and Engineering, in press.Google Scholar
  7. Caers, J. and Ma, X. (2001). Modeling conditional distributions of facies from seismic using neural nets. Mathematical Geology, acccepted for publication.Google Scholar
  8. Dagan, G. (1985). Stochastic modeling of groundwater flow by unconditional and conditional probabilities: The inverse problem. Water Resources Research, 21(1): 65–72.CrossRefGoogle Scholar
  9. Deutsch, C.V. (1993). Conditioning reservoir models to well test information. In: 4th International Geostatistics Congress, Troia, (ed. Soares, A.), 505–518, Kluwer Ac. Publ., Holland.Google Scholar
  10. Deutsch, C.V. and Journel, A.G. (1998). GSLIB — Geostatistical Software Library and User’s Guide, 2nd edn. Oxford University Press, New York, 369pp.Google Scholar
  11. Doyen, Ph. and Psaila, M. (1994). Bayesian sequential indicator simulation of channel sands from 3d seismic data in the Oselung field, in, Proceedings to the SPE Annual Conference and Technical Exhibition, Society of Petroleum Engineers, 465–474, SPE paper no. 38698.Google Scholar
  12. Eide, A.L., Omre, H. and Ursin, B. (1996). Stochastic reservoir charateriza-tion conditioned on seismic data. Pre-prints of the International Geostatistics Congress, Wollongong, September 1996, Australia,Google Scholar
  13. Gomez-Hernandez, J. and Journel, A.G., (1993). Joint sequential simulation of multi-Gaussian fields. In: Geostatistics-Troia, 4th International Geostatistics congress (ed. Soares A.), 85–94. Kluwer Ac. Publ., Holland.Google Scholar
  14. Gomez-Hernandez, J., Sahuquillo, A. and Capilla, J.E. (1997). Stochastic simulation of transmissivity fields conditional to both transmissivity and piezo-metric data — 1. Theory. Journal of Hydrology, 203: 162–174.CrossRefGoogle Scholar
  15. Goovaerts, P. (1998). Geostatistics for natural resources evaluation. Oxford University Press.Google Scholar
  16. Horne, R.N. (1995). Modern well-test analysis. Petroway, Inc, Palo Alto, California.Google Scholar
  17. Isaaks, E. (1990). The application of Monte Carlo methods to the analysis of spatially correlated data. Ph.D. thesis, Stanford University, Stanford, USAGoogle Scholar
  18. Journel, A.G. (1999). Markov models for cross-covariances. Mathematical Geology, 31(8): 955–964.CrossRefGoogle Scholar
  19. Journel, A.G. (2001). Combining knowledge from diverse information sources: an alternative to Bayesian analysis. Submitted manuscript.Google Scholar
  20. Kitanidis, P.K. and Vomvoris, E.G. (1983). A geostatistical approach to the inverse problem in groundwater modeling (steady state) and one-dimensional simulations. Water Resources Research, 19(3): 677–690.CrossRefGoogle Scholar
  21. Noetinger, B. (1994). The effective permeability of a hetrogeneous porous medium, Transport in Porous Media, 15: 99–127.CrossRefGoogle Scholar
  22. Omre, H. and Tjelmeland, H. (1996). A Bayesian framework for intergrated reservoir characterization. In: E.Y. Baafi and N.A. Schofield, editor, Geostatistics-Wollongong, 41–52. Kluwer Ac. Publ., Holland.Google Scholar
  23. Payrazyan, K., & Scheevel, J. (2000). Principal component analysis applied to 3D seismic data for reservoir property estimation, in, Proceedings to the SPE Annual Conference and Technical Exhibition, Society of Petroleum Engineers, SPE # 56734.Google Scholar
  24. RamaRao, B.S., LaVenue, A.M., de Marsily, G. and Marietta, M.G. (1995). Pilot point methodology for automated calibration of an ensemble of conditionally simulated transmissivity fields, 1. Theory and computational experiments. Water Resources Research, 31(3): 475–493.CrossRefGoogle Scholar
  25. Scholle, P.A. and Spearing, D. (1992). Sandstone Depositional Environments, The American Association of Petroleum Geologists, Oklahoma.Google Scholar
  26. Srinivasan, S., (2000). Integration of production data into reservoir models: a forward modeling perspective. Ph.D. thesis, Stanford University.Google Scholar
  27. Srivastava, M., (1993). Reservoir characterization with probability field simulation, in, Proceedings to the SPE Annual Conference and Technical Exhibition, Society of Petroleum Engineers, Washington DC, SPE paper no. 24753.Google Scholar
  28. Tarantola, A. (1987). Inverse Problem Theory. Elsevier, Amsterdam.Google Scholar
  29. Wen, X.H. (1997). Constraints on the spatial distribution of permeability due to a single well pressure transient test. Stanford Center for Reservoir Forecasting (SCRF), Report No. 10.Google Scholar
  30. Xu, W., Iran, T., Srivastava, R. and Journel, A.G. (1992). Integrating seismic data ub reservoir modeling: the co-located cokriging alternative. SPE paper no. 24742.Google Scholar
  31. Yao, T. (1998). Porosity modeling in a W. Texas carbonate reservoir conditioned to seismic data: solving the difference of scale and precision problem. SCRF report no. 11Google Scholar
  32. Yilmaz, O. (1987). Seismic data processing. SEG publications: Investigations in Geophysics.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Jef Caers
    • 1
  • Sanjay Srinivasan
    • 2
  1. 1.Petroleum EngineeringStanford UniversityStanfordUSA
  2. 2.Petroleum EngineeringUniversity of CalgaryAlbertaCanada

Personalised recommendations