Estimation of electrical resistivity using artifcial neural networks: a case study from Lublin Basin, SE Poland

• Autorzy: Ważny Jakub , Stefaniuk Michał , Cygal Adam

Identyfikatory

DOI

10.1007/s11600-021-00554-0

• Języki publikacji: EN

Abstrakty

EN

Artifcial neural networks method (ANNs) is a common estimation tool used for geophysical applications. Considering borehole data, when the need arises to supplement a missing well log interval or whole logging-ANNs provide a reliable solution. Supervised training of the network on a reliable set of borehole data values with further application of this network on unknown wells allows creation of synthetic values of missing geophysical parameters, e.g., resistivity. The main assumptions for boreholes are: representation of similar geological conditions and the use of similar techniques of well data collection. In the analyzed case, a set of Multilayer Perceptrons were trained on fve separate chronostratigraphic intervals of borehole, considered as training data. The task was to predict missing deep laterolog (LLD) logging in a borehole representing the same sequence of layers within the Lublin Basin area. Correlation between well logs data exceeded 0.8. Subsequently, magnetotelluric parametric soundings were modeled and inverted on both boreholes. Analysis showed that congenial Occam 1D models had better ftting of TM mode of MT data in each case. Ipso facto, synthetic LLD log could be considered as a basis for geophysical and geological interpretation. ANNs provided solution for supplementing datasets based on this analytical approach.

Słowa kluczowe

EN

artificial neural networks; well logging; electrical resistivity; LLD; magnetotellurics; parametric sounding; Lublin basin

PL

sztuczne sieci neuronowe; geofizyka otworowa; rezystancja; LLD; magnetotelluryka; sondowanie parametryczne; dorzecze Lubelskie

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2021
• Tom: Vol. 69, no. 2
• Strony: 631--642
• Opis fizyczny: Bibliogr. 14 poz.

Twórcy

autor

Ważny Jakub

• AGH University of Science and Technology, Kraków, Poland

• https://orcid.org/0000-0002-0508-3090

autor

Stefaniuk Michał

• AGH University of Science and Technology, Kraków, Poland

autor

Cygal Adam

• AGH University of Science and Technology, Kraków, Poland

Bibliografia

• 1. Constable S, Parker RL, Constable CG (1987) Occam’s inversion: a practical algorithm for generating smooth models from electromagnetic sounding data. Geophysics 52(3):289–300
• 2. Dennis JE, Schnabel RB (1983) Numerical methods for unconstrained optimization and nonlinear equations. Prentice-Hall, Englewood Cliffs NJ
• 3. Gardner GHF, Gardner LW, Gregory AR (1974) Formation velocity and density—the diagnostic basics for stratigraphic traps. Geophysics 39(6):770–780. https://doi.org/10.1190/1.1440465
• 4. Gąsior I, Reicher B (2014) Estymacja czasu interwałowego z profilowań geofizyki otworowej metodą sieci neuronowych. Nafta-Gaz 11(2014):765–770
• 5. Gholami R, Sharaki A R, Paghaleh J (2012) Prediction of hydrocarbon reservoirs permeability using support vector machine. Math Probl Eng 2012
• 6. Goutorbe B, Lucazeau F, Bonneville A (2006) Using neural networks to predict thermal conductivity from geophysical well logs. Geophys J Int 166:115–125. https://doi.org/10.1111/j.1365-246X.2006.02924.x
• 7. Jarzyna J, Oprychał A, Mozgowoj D (2007) Sztuczne sieci neuronowe dla uzupełnienia danych w geofizyce otworowej—wybrane przykłady. Geologia 33(4/1):81–102
• 8. Konaté AA, Pan H, Khan N, Yang JH (2015) Generalized regression and feed-forward back propagation neural networks in modelling porosity from geophysical well logs. J Pet Explor Prod Technol 5:157–166. https://doi.org/10.1007/s13202-014-0137-7
• 9. Murtagh F (1991) Multilayer perceptrons for classification and regression. Neurocomputing 2(5–6):183–197
• 10. Rolon L, Mohaghegh SD, Ameri S, Gaskari R, McDaniel B (2009) Using artificial neural networks to generate synthetic well logs. J Nat Gas Sci Eng 1(4–5):118–133
• 11. Rosenblatt F (1957) The Perceptron—a perceiving and recognizing automaton. Tech Report 85–460–1. Cornell Aeronaut Lab
• 12. Tadeusiewicz R (1993) Sieci neuronowe. Akademicka Oficyna Wydawnicza RM, Warszawa
• 13. Ważny J, Cygal A, Stefaniuk M (2019) Application of artificial neural networks to develop input data for acoustic and elastic inversion in the Wysin 1 well and for part of the Wysin-3D seismic image. CAGG-AGH-2019 [electronic document]: challenges in applied geology and geophysics: 100th anniversary of applied geology at agh university of science and technology: international scientific conference: 10–13 September 2019, Kraków: book of abstracts 169–170 http://www.cagg2019.agh.edu.pl/Book%20of%20Abstract%20pdf%20only/9%20Poster%20session/Wa%C5%BCny%20et%20al.pdf
• 14. Zhang D, Chen Y, Meng J (2018) Synthetic well logs generation via recurrent neural networks. Pet Explor Dev 45(4):629–639