Computational Geosciences

, Volume 21, Issue 3, pp 427–440 | Cite as

Smart Interpretation – automatic geological interpretations based on supervised statistical models

  • Mats Lundh Gulbrandsen
  • Knud Skou Cordua
  • Torben Bach
  • Thomas Mejer Hansen
Original Paper


A method that infers a statistical model, which describes a relation between the knowledge of a geologist (quantified by geological interpretations) and the available information (such as geophysical data, well log data, etc.) that a geologist uses when he/she interprets is proposed and tested. The statistical model is then used to perform automatic geological interpretations wherever the same kinds of information, as used for the initial interpretations, are available. This methodology is named Smart Interpretation (SI). In this study, we look at two different approaches to infer such a model, and we demonstrate the applicability of the model to predict the depth to a low resistivity subsurface layer, based on interpretations from a geological expert, using a 19-layered resistivity model obtained from inversion of airborne electromagnetic (AEM) data. This study shows that SI is capable of making predictions with great accuracy. The method is fast and is able to handle large amounts of data of different origin, which suggest that the method may become a very useful approach to assist in geological modeling based on increasingly large amounts of data of different nature.


Geological modeling Fast semi-automatic interpretations Quantitative geology Machine learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abraham, J.D., Cannia, J.C., Bedrosian, P.A., johnsen, M.R., Ball, L.B., Sibray, S.S.: Airborne electromagnetic mapping of the base of aquifer in areas of western nebraska. U.S. Geological Survey Scientific Investigations Report (5219) (2011)Google Scholar
  2. 2.
    Auken, E., Chandra, S., Vignoli, G., Shankeel, A., Sen, M.K., Gupta, S.: Large scale mapping of groundwater resources in india with results from test sites in different geological terrain. Conference abstract at the 13th SAGA Biennial Conference & Exhibition (2013)Google Scholar
  3. 3.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press (1995)Google Scholar
  4. 4.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2007)Google Scholar
  5. 5.
    Bosch, A.J., Bakker, M.A., Gunnink, J.L., Paap, B.F.: Airborne electromagnetic measurements as basis for a 3d geological model of an elsterian incision. Zeitschrift der Deutschen Gesellschaft für Geowissenschaften 160(3), 249–258 (2009)CrossRefGoogle Scholar
  6. 6.
    Carle, S.: T-PROGS: Transition Probability Geostatistical Software. USA University of California: user manual (1999)Google Scholar
  7. 7.
    Carle, S., Fogg, G.: Transition probability-based indicator geostatistics. Math. Geol. 28, 453–476 (1996)CrossRefGoogle Scholar
  8. 8.
    Christiansen, A.V., Foged, N., Auken, E.: A concept for calculating accumulated clay thickness from borehole lithological logs and resistivity models for nitrate vulnerability assessment. J. Appl. Geophys. 108, 69–77 (2014)CrossRefGoogle Scholar
  9. 9.
    Gunnink, J.L., Bosch, J.H.A., Siemon, B., Roth, B., Auken, E.: Combining ground-based and airborne em through artificial neural networks for modelling glacial till under saline groundwater conditions. Hydrol. Earth Syst. Sci. Discuss. 16, 3061–3074 (2012)CrossRefGoogle Scholar
  10. 10.
    Gunnink, J.L., Siemon, B.: Applying airborne electromagnetics in 3d stochastic geohydrological modelling for determining groundwater protection. Near Surface Geophysics 13, 45–60 (2015)CrossRefGoogle Scholar
  11. 11.
    Hansen, T.M., Mosegaard, K., Pedersen-Tatalovic, R., Uldall, A., Jacobsen, N.L.: Attribute-guided well-log interpolation applied to low-frequency impedance estimation. Geophysics 73(6), R83–R95 (2008)CrossRefGoogle Scholar
  12. 12.
    He, X., Koch, J., Sonnenborg, T., Jørgensen, F., Schamper, C., Refsgaard, J.: Transition probability-based stochastic geological modeling using airborne geophysical data and borehole data. Water Resour. Res. 50, 3147–3169 (2014a)CrossRefGoogle Scholar
  13. 13.
    He, X., Sonnenborg, T., Jørgensen, F., Jensen, K.: The effect of training image and secondary data integration with multiple-point geostatistics in groundwater modelling. Hydrol. Eath Syst. Sci. Discuss 18, 2943–2954 (2014b)CrossRefGoogle Scholar
  14. 14.
    Høyer, A.-S., Jørgensen, F., Foged, N., He, X., Christiansen, A.V.: Three-dimensional geological modelling of aem resistivity data - a comparison of three methods. J. Appl. Geophys. 115, 65–78 (2015)CrossRefGoogle Scholar
  15. 15.
    Jørgensen, F., Møller, R.R., Nebel, L., Jensen, N.-P., Christiansen, A.V., Sandersen, P.B.E.: A method for cognitive 3d geological voxel modelling of aem data. Bull. Eng. Geol. Environ. 72, 421–432 (2013)CrossRefGoogle Scholar
  16. 16.
    Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)CrossRefGoogle Scholar
  17. 17.
    Marker, P., Christiansen, A.V., Bauer-Gottwein, P., Jørgensen, F., Høyer, A.-S., Auken, E.: Large-scale 3-d modeling by integration of resistivity models and borehole data through inversion. Hydrol. Earth Syst. Sci. 18, 4349–4362 (2014)CrossRefGoogle Scholar
  18. 18.
    Mathews, V.J., Sicuranze, G.L.: Polynomial Signal Processing. Wiley (2000)Google Scholar
  19. 19.
    Menke, W.: Geophysical Data Analysis: Discrete Inverse Theory. ELSEVIER, third edition (2012)Google Scholar
  20. 20.
    Mielby, S.: Den nationale grundvandskortlægning i danmark- faglige resultater fra geus 2010. Technical report, GEUS (2010)Google Scholar
  21. 21.
    Sandersen, P.B., Pjetursson, R.T.: The integrated groundwater mapping concept of denmark transferred to thailand. Precented at DWRIP (2014)Google Scholar
  22. 22.
    Pedersen, J., Effersø, F., Jørgensen, F., Refsgaard, J.C., Auken, E., Schamper, C., Christiansen, A.V.: Skytem case study: Skytem - a new airborne mapping tool. SkyTEM homepageGoogle Scholar
  23. 23.
    Seeger, M.: Gaussian processes for machine learning. Int. J. Neural Syst. 14(2), 69–106 (2004)CrossRefGoogle Scholar
  24. 24.
    Siemon, B., Christiansen, A.V., Auken, E.: A review of helicopter-borne electromagnetic methods for groundwater exploration. Near Surface Geophysics 7(5-6), 629–646 (2009)Google Scholar
  25. 25.
    Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Statistics and Copmputing 14, 199–222 (2004)CrossRefGoogle Scholar
  26. 26.
    Sørensen, K.I., Auken, E.: Skytem - a new high-resolution helicopter transient electromagnetic system. Explor. Geophys. 35, 191–199 (2004)Google Scholar
  27. 27.
    Tarantola, A.: Inverse Problem Theory and Methods for Model Parameter Estimation. Siam (2005)Google Scholar
  28. 28.
    Tikhonov, A., Arsenin, V.: Solution of ill-posed problems. Wiley (1977)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  • Mats Lundh Gulbrandsen
    • 1
  • Knud Skou Cordua
    • 1
  • Torben Bach
    • 2
  • Thomas Mejer Hansen
    • 1
  1. 1.Niels Bohr InstituteUniversity of CopenhagenCopenhagenDenmark
  2. 2.I∙GIS A/SRisskovDenmark

Personalised recommendations