Skip to main content

Advertisement

SpringerLink
Log in

Lithology prediction in the subsurface by artificial neural networks on well and 3D seismic data in clastic sediments: a stochastic approach to a deterministic method

  • Original Paper
  • Published:
GEM - International Journal on Geomathematics Aims and scope Submit manuscript

Abstract

A small area covered by a seismic volume was selected for the analysis of using artificial neural networks for the purpose of lithology modelling in a stochastic approach to an otherwise deterministic method. Subsurface lithology was simplified to three categories (sandstone, marl and coal) in accordance with the general geological composition of the Pannonian age sediments in the eastern part of Drava Depression. Two approaches to artificial neural networks were used—training and prediction with a large number of networks with different architecture, and with the same architecture but with the variability of dataset distribution of cases for error calculation in the learning process. Out of a 1000 total cases, 100 realizations of each approach were singled out upon which the data points with probability of 50%, 75% and 90% of occurrence of certain lithology category were upscaled in the model. Six models were generated by indicator kriging. Although in theory, the higher accuracy data should provide a more accurate result, the geologically most sound results were obtained by 50% accuracy data. In higher accuracy results, sandstone lithology was unrealistically over emphasized as a result of the upscaling process, variography and statistical analysis. Presented research can be used in all geoenergy-related subsurface explorations, including hydrocarbon and geothermal explorations, and subsurface characterization for CO2 storage potential and underground energy storage potential as well.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

[modified from Cvetković et al. (2019), after Dolton (2006) and Schmid et al. (2008)]

Fig. 2

[modified from Malvić and Cvetković (2013)]

Fig. 3
Fig. 4
Fig. 5
Fig. 6

(Füst and Geiger 2010; Hatvani et al. 2017)

Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Agatonovic-Kustrin, S., Beresford, R.: Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J. Pharm. Biomed. Anal. 22, 717–727 (2000). https://doi.org/10.1016/S0731-7085(99)00272-1

    Article  Google Scholar 

  • Alman, D.H., Ningfang, L.: Overtraining in back-propagation neural networks: a CRT color calibration example. Color Res. Appl. 27, 122–125 (2002). https://doi.org/10.1002/col.10027

    Article  Google Scholar 

  • Anderson, J.A., Rosenfeld, E.: Neurocomputing: foundations of research. MIT Press, Cambridge (1988)

    Google Scholar 

  • Bjørlykke, K.: Petroleum geoscience. Springer, Berlin (2010)

    Book  Google Scholar 

  • Bowman, M., Smyth, H.R., Good, T.R., Passey, S.R., Hirst, J.P.P., Jordan, C.J.: The Value of Outcrop Studies in Reducing Subsurface Uncertainty and Risk in Hydrocarbon Exploration and Production. Geological Society, London (2016)

    Google Scholar 

  • Brcković, A., Kovačević, M., Cvetković, M., Močilac, I.K., Rukavina, D., Saftić, B.: Application of artificial neural networks for lithofacies determination based on limited well data. Cent. Eur. Geol. (2017). https://doi.org/10.1556/24.60.2017.012

    Article  Google Scholar 

  • Cressie, N.: The origins of kriging. Math. Geol. (1990). https://doi.org/10.1007/BF00889887

    Article  MathSciNet  MATH  Google Scholar 

  • Cvetković, M.: Modelling of maturation, expulsion and accumulation of bacterial methane within Ravneš Member (Pliocene age), Croatia onshore. Open Geosci. (2016). https://doi.org/10.1515/geo-2016-0002

    Article  Google Scholar 

  • Cvetković, M.: Possibilities for well log correlation using standard deviation trends in neogene-quaternary sediments, sava depression, Pannonian Basin. Geol. Croat. (2017). https://doi.org/10.4154/gc.2017.07

    Article  Google Scholar 

  • Cvetković, M., Emanović, I., Stopar, A., Slavinić, P.: Petroleum system modeling and assessment of the remaining hydrocarbon potential in the eastern part of Drava Depression. Interpretation (2018). https://doi.org/10.1190/int-2017-0078.1

    Article  Google Scholar 

  • Cvetković, M., Matoš, B., Rukavina, D., Kolenković Močilac, I., Saftić, B., Baketarić, T., Baketarić, M., Vuić, I., Stopar, A., Jarić, A., Paškov, T.: Geoenergy potential of the Croatian part of Pannonian Basin: insights from the reconstruction of the pre-Neogene basement unconformity. J. Maps. 15, 651–661 (2019). https://doi.org/10.1080/17445647.2019.1645052

    Article  Google Scholar 

  • Dolton, G.L.: Pannonian Basin Province, Central Europe (Province 4808)—petroleum geology, total petroleum systems, and petroleum resource assessment. US Geol Surv Bull 2204, 47 (2006)

    Google Scholar 

  • Dubrule, O.: Introducing more geology in stochastic reservoir modelling. In: Soares, A. (ed.) Geostatistics Tróia ’92, pp. 351–369. Springer, Dordrecht (1993)

    Chapter  Google Scholar 

  • Falivene, O., Cabrera, L., Sáez, A.: Optimum and robust 3D facies interpolation strategies in a heterogeneous coal zone (Tertiary As Pontes basin, NW Spain). Int. J. Coal Geol. (2007). https://doi.org/10.1016/j.coal.2006.08.008

    Article  Google Scholar 

  • Feng, R., Luthi, S.M., Gisolf, D., Angerer, E.: Reservoir lithology classification based on seismic inversion results by Hidden Markov Models: applying prior geological information. Mar. Pet. Geol. 93, 218–229 (2018). https://doi.org/10.1016/j.marpetgeo.2018.03.004

    Article  Google Scholar 

  • Forgotson, J.M.: Review and classification of quantitative mapping techniques. Am. Assoc. Pet. Geol. Bull. 44, 83–100 (1960)

    Google Scholar 

  • Füst, A., Geiger, J.: Monitoring planning and evaluation using geostatistics, I. Geostatistical support for verification sampling based on professional opinion. Földtani Közlöny. 140, 303–312 (2010)

    Google Scholar 

  • Gringarten, E., Deutsch, C.: Methodology for Variogram interpretation and modeling for improved reservoir characterization. In: Proceedings of SPE Annual Technical Conference and Exhibition. Society of Petroleum Engineers (1999)

  • van Gulijk, C., Hughes, P., Figueres-Esteban, M., El-Rashidy, R., Bearfield, G.: The case for IT transformation and big data for safety risk management on the GB railways. Proc. Inst. Mech. Eng. Part O J Risk Reliab. 232, 151–163 (2018). https://doi.org/10.1177/1748006X17728210

    Article  Google Scholar 

  • Harzhauser, M., Latal, C., Piller, W.E.: The stable isotope archive of Lake Pannon as a mirror of Late Miocene climate change. Palaeogeogr. Palaeoclimatol. Palaeoecol. 249, 335–350 (2007). https://doi.org/10.1016/j.palaeo.2007.02.006

    Article  Google Scholar 

  • Harzhauser, M., Mandic, O.: Neogene lake systems of Central and South-Eastern Europe: Faunal diversity, gradients and interrelations. Palaeogeogr. Palaeoclimatol. Palaeoecol. 260, 417–434 (2008). https://doi.org/10.1016/j.palaeo.2007.12.013

    Article  Google Scholar 

  • Hatvani, I.G., Leuenberger, M., Kohán, B., Kern, Z.: Geostatistical analysis and isoscape of ice core derived water stable isotope records in an Antarctic macro region. Polar Sci. 13, 23–32 (2017). https://doi.org/10.1016/j.polar.2017.04.001

    Article  Google Scholar 

  • He, Y., Chen, D., Li, B.G., Huang, Y.F., Hu, K.L., Li, Y., Willett, I.R.: Sequential indicator simulation and indicator kriging estimation of 3-dimensional soil textures. Soil Res. 47, 622 (2009). https://doi.org/10.1071/SR08218

    Article  Google Scholar 

  • Hegde, J., Rokseth, B.: Applications of machine learning methods for engineering risk assessmen: a review. Saf. Sci. 122, 104492 (2020). https://doi.org/10.1016/j.ssci.2019.09.015

    Article  Google Scholar 

  • Hengl, T., Toomanian, N., Reuter, H.I., Malakouti, M.J.: Methods to interpolate soil categorical variables from profile observations: lessons from Iran. Geoderma (2007). https://doi.org/10.1016/j.geoderma.2007.04.022

    Article  Google Scholar 

  • Hernitz, Z.: Subsurface structure-tectonic relations in the area of eastern Slavonia (In Croatian: Dubinski strukturno—tektonski odnosi u području istočne Slavonije) (1980)

  • Hohn, M.E.: Geostatistics and Petroleum Geology. Springer, Dordrecht (1999)

    Book  Google Scholar 

  • Jakab, N.: Stochastic modeling in geology: determining the sufficient number of models. Cent. Eur. Geol. 60, 135–151 (2017). https://doi.org/10.1556/24.60.2017.005

    Article  Google Scholar 

  • James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning. Springer, New York (2013)

    Book  Google Scholar 

  • Journel, A.G.: Nonparametric estimation of spatial distributions. J. Int. Assoc. Math. Geol. 15, 445–468 (1983). https://doi.org/10.1007/BF01031292

    Article  MathSciNet  Google Scholar 

  • Juhász, G., Pogácsás, G., Magyar, I., Vakarcs, G.: Tectonic versus climatic control on the evolution of fluvio-deltaic systems in a lake basin, Eastern Pannonian Basin. Sediment. Geol. 202, 72–95 (2007). https://doi.org/10.1016/j.sedgeo.2007.05.001

    Article  Google Scholar 

  • Kanevski, M., Dumolard, P.: Advanced Mapping of Environmental Data. ISTE, London (2008)

    Book  Google Scholar 

  • Kappen, H.J.: Chapter 13 An introduction to stochastic neural networks. In: Moss, F., Gielen, S. (eds.) Neuro-Informatics and Neural Modelling, pp. 517–552. Elsevier (2001)

  • Kováč, M., Baráth, I., Fordinál, K., Grigorovich, A.S., Halásová, E., Hudáčková, N., Joniak, P., Sabol, M., Slamková, M., Sliva, Ľ., Vojtko, R.: Late Miocene to Early Pliocene sedimentary environments and climatic changes in the Alpine–Carpathian–Pannonian junction area: a case study from the Danube Basin northern margin (Slovakia). Palaeogeogr. Palaeoclimatol. Palaeoecol. 238, 32–52 (2006). https://doi.org/10.1016/j.palaeo.2006.03.015

    Article  Google Scholar 

  • Kovačić, M.: Sedimentology of the Upper Miocene deposits from the southwest part of the Pannonian Basin (In Croatian) (2004)

  • Kovačić, M., Županić, J., Babić, L., Vrsaljko, D., Miknić, M., Bakrac, K., Hecimovic, I., Avanić, R., Brkić, M.: Lacustrine basin to delta evolution in the Zagorje Basin, a Pannonian sub-basin (Late Miocene: Pontian, NW Croatia). Facies 50, 19–33 (2004). https://doi.org/10.1007/s10347-003-0001-6

    Article  Google Scholar 

  • Kovács, Á., Špelić, M., Balázs, A., Magyar, I., Sztanó, O.: Late Miocene variation of accommodation in the Drava Trough: stratigraphic forward modeling and field observations. In: Tari, G., Sachsenhofer, R. (eds.) Paratethys Petroleum Systems Between Central Europe and the Caspian Region, p. 149. AAPG Europe, Vienna (2019)

    Google Scholar 

  • Krige, D.G.: A statistical approach to some basic mine valuation problems on the Witwatersrand. J. Chem. Metall. Min. Soc. S. Afr. 52, 119–139 (1952). https://doi.org/10.2307/3006914

    Article  Google Scholar 

  • Krijgsman, W., Stoica, M., Vasiliev, I., Popov, V.V.: Rise and fall of the Paratethys Sea during the Messinian Salinity Crisis. Earth Planet. Sci. Lett. 290, 183–191 (2010). https://doi.org/10.1016/j.epsl.2009.12.020

    Article  Google Scholar 

  • Lean, Y., Shouyang, W., Kin, K.L.: Basic learning principles of artificial neural networks. In: Hillier, F. (ed.) Foreign-Exchange-Rate Forecasting with Artificial Neural Networks, pp. 27–37. Springer, New York (2007)

    MATH  Google Scholar 

  • Magyar, I., Geary, D.H., Müller, P.: Paleogeographic evolution of the Late Miocene Lake Pannon in Central Europe. Palaeogeogr. Palaeoclimatol. Palaeoecol. 147, 151–167 (1999). https://doi.org/10.1016/S0031-0182(98)00155-2

    Article  Google Scholar 

  • Magyar, I., Radivojević, D., Sztanó, O., Synak, R., Ujszászi, K., Pócsik, M.: Progradation of the paleo-Danube shelf margin across the Pannonian Basin during the Late Miocene and Early Pliocene. Glob. Planet. Change. 103, 168–173 (2013). https://doi.org/10.1016/j.gloplacha.2012.06.007

    Article  Google Scholar 

  • Malvić, T., Cvetković, M.: Lithostratigraphic units in the Drava Depression (Croatian and Hungarian parts): a correlation. Nafta 63, 27–33 (2013)

    Google Scholar 

  • Mason, I.M., Greenhalgh, S.A., Hatherly, P.: Underground seismic mapping of coal seam discontinuities at West Wallsend No. 2 Colliery. Explor. Geophys. 16, 357–364 (1985). https://doi.org/10.1071/eg985357

    Article  Google Scholar 

  • Matheron, G.: Les variables régionalisées et leur estimation. Une application de la théorie des fonctions aléatoires aux sciences de la nature. Masson, Paris (1965)

  • McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943). https://doi.org/10.1007/BF02478259

    Article  MathSciNet  MATH  Google Scholar 

  • Nikravesh, M., Aminzadeh, F.: Chapter 1 Soft computing for intelligent reservoir characterization and modeling. In: Nikravesh, M., Aminzadeh, F., Zadeh, L.A. (eds.) Soft Computing and Intelligent Data Analysis in Oil Exploration, pp. 3–32. Elsevier (2003)

  • Novak Zelenika, K., Malvić, T.: Stochastic simulations of dependent geological variables in sandstone reservoirs of neogene age: a case study of the kloštar field, Sava depression. Geol. Croat. 64, 173–183 (2011). https://doi.org/10.4154/gc.2011.15

    Article  Google Scholar 

  • Nowak, M., Verly, G.: The practice of sequential Gaussian simulation. In: Leuangthong, O., Deutsch, C.V. (eds.) Geostatistics Banff 2004, pp. 387–398. Springer, Dordrecht (2005)

    Chapter  Google Scholar 

  • Paulsen, M., Rasmussen, T.K., Nielsen, O.A.: Output variability caused by random seeds in a multi-agent transport simulation model. Procedia Comput. Sci. 130, 850–857 (2018). https://doi.org/10.1016/j.procs.2018.04.078

    Article  Google Scholar 

  • Pavelić, D., Kovačić, M.: Sedimentology and stratigraphy of the Neogene rift-type North Croatian Basin (Pannonian Basin System, Croatia): a review. Mar. Pet. Geol. 91, 455–469 (2018). https://doi.org/10.1016/j.marpetgeo.2018.01.026

    Article  Google Scholar 

  • Piller, W.E., Harzhauser, M., Mandic, O.: Miocene Central Paratethys stratigraphy: current status and future directions. Stratigraphy 4, 151–168 (2007)

    Google Scholar 

  • Rögl, F., Steininger, F.F.: Vom Zerfall der Tethys zu Mediterran und Paratethys: Die neogene Paläogeographie und Palinspastik des zirkum-mediterranen Raumes. Ann. des Naturhistorischen Museums Wien. 85, 135–163 (1983)

    Google Scholar 

  • Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65, 386–408 (1958). https://doi.org/10.1037/h0042519

    Article  Google Scholar 

  • Royden, L.: Late Cenozoic tectonics of the Pannonian Basin system. In: Royden, L.H., Horvath, F. (eds.) The Pannonian Basin: A Study in Basin Evolution. AAPG Memoir 45. AAPG, Tulsa (1988)

    Google Scholar 

  • Sacchi, M., Horváth, F.: Towards a new time scale for the Upper Miocene continental series of the Pannonian Basin (Central Paratethys), Stephan Mueller. Spec. Publ. Ser. 3, 79–94 (2002). https://doi.org/10.5194/smsps-3-79-2002

    Article  Google Scholar 

  • Saftić, B., Velić, J., Sztanó, O., Juhász, G., Ivković, Ž.: Tertiary subsurface facies, source rocks and hydrocarbon reservoirs in the SW part of the Pannonian Basin (Northern Croatia and south-western Hungary). Geol. Croat. 56, 101–122 (2003)

    Google Scholar 

  • Schmid, S.M., Bernoulli, D., Fügenschuh, B., Matenco, L., Schefer, S., Schuster, R., Tischler, M., Ustaszewski, K.: The Alpine-Carpathian-Dinaridic orogenic system: Correlation and evolution of tectonic units. Swiss J. Geosci. 101, 139–183 (2008). https://doi.org/10.1007/s00015-008-1247-3

    Article  Google Scholar 

  • Selley, R.C., Sonnenberg, S.A.: Methods of Exploration. Elements of Petroleum Geology, pp. 41–152. Elsevier, New York (2015)

    Book  Google Scholar 

  • Sheriff, R.E.: Vertical and lateral seismic resolution and attenuation: part 7. Geophysical methods. In: Morton-Thompson, D., Woods, A.M. (eds.) ME 10: Development Geology Reference Manual, pp. 388–389. AAPG, Tulsa (1992)

    Google Scholar 

  • Sztanó, O., Szafián, P., Magyar, I., Horányi, A., Bada, G., Hughes, D.W., Hoyer, D.L., Wallis, R.J.: Aggradation and progradation controlled clinothems and deep-water sand delivery model in the Neogene Lake Pannon, Makó Trough, Pannonian Basin, SE Hungary. Glob. Planet. Change. 103, 149–167 (2013). https://doi.org/10.1016/j.gloplacha.2012.05.026

    Article  Google Scholar 

  • Taner, M.T.: Seismic attributes. CSEG Rec. 26, 26–48 (2001)

    Google Scholar 

  • Taner, M.T., Sheriff, R.E., Koehler, E., D, F.: Extraction and interpretation of the complex seismic trace. In: 6th Annual Convention Proceedings, vol. 2, pp. 305–316. SEG, Huston, Texas (1976)

    Google Scholar 

  • Tetko, I.V., Livingstone, D.J., Luik, A.I.: Neural network studies. 1. Comparison of overfitting and overtraining. J. Chem. Inf. Model. 35, 826–833 (1995). https://doi.org/10.1021/ci00027a006

    Article  Google Scholar 

  • Tu, J.V.: Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J. Clin. Epidemiol. 49, 1225–1231 (1996). https://doi.org/10.1016/S0895-4356(96)00002-9

    Article  Google Scholar 

  • Velić, J.: Geologija nafte [Petroleum Geology]. University of Zagreb, Faculty of Mining, Geology and Petroleum Engineering, Zagreb (2007)

    Google Scholar 

  • Walton, C., Evans, B., Urosevic, M.: Imaging coal seam structure using 3-D seismic methods. Explor. Geophys. 31, 509–514 (2000). https://doi.org/10.1071/EG00509

    Article  Google Scholar 

Download references

Acknowledgements

The authors applied the SDC approach for the sequence of authors. Authors would like to thank the Schlumberger company which donated the Petrel software and Croatian Hydrocarbon Agency and Ministry of Environmental Protection and Energy for the data permissions without which the analysis presented in this work could not be performed.

Author information

Authors and Affiliations

  1. Croatian Geological Survey, Sachsova 2, 10000, Zagreb, Croatia

    Ana Kamenski

  2. Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb, Pierottijeva 6, 10000, Zagreb, Croatia

    Marko Cvetković, Iva Kolenković Močilac & Bruno Saftić

Authors
  1. Ana Kamenski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marko Cvetković
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Iva Kolenković Močilac
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bruno Saftić
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marko Cvetković.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 35 kb)

Supplementary material 2 (DOCX 26 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kamenski, A., Cvetković, M., Kolenković Močilac, I. et al. Lithology prediction in the subsurface by artificial neural networks on well and 3D seismic data in clastic sediments: a stochastic approach to a deterministic method. Int J Geomath 11, 8 (2020). https://doi.org/10.1007/s13137-020-0145-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13137-020-0145-3

Keywords

Mathematics Subject Classification

Search

Navigation