Estimation of absolute permeability using artificial neural networks (multilayer perceptrons) based on well logs and laboratory data from Silurian and Ordovician deposits in SE Poland

• Autorzy: Waszkiewicz Sebastian , Krakowska-Madejska Paulina , Puskarczyk Edyta

Identyfikatory

DOI

10.1007/s11600-019-00347-6

• Języki publikacji: EN

Abstrakty

EN

Permeability is a property of rocks which refers to the ability of fluids to flow through each substance. It depends on several factors as pore shape and diameter. Also the presence and type of clay has a large influence on the permeability value. Permeability can be measured on rock sample in the laboratory by injecting fluid through the rock under known condition, but this provides only point information. Due to the dependence of the parameter on many factors, the deterministic estimation of permeability based on laboratory measurement and well logs is problematic. Many empirical methods for determining permeability are available in the literature and interpretation systems. An interesting approach to the problem is the use of artificial neural networks based on laboratory measurement and modern, high-resolution logging tools. The authors decided to use MLP artificial neural networks, which allow permeability estimation and can be used both in the test well and applied to neighbouring wells. The network was checked in several variants. Obtained results show the legitimacy of using artificial neural networks in the issue of estimating permeability. However, they also show limitations resulting from the lack of accurate data or influence of geological setting and processes.

Słowa kluczowe

EN

permeability; well logs; artificial neural networks

PL

przepuszczalność; geofizyka otworowa; sztuczne sieci neuronowe

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2019
• Tom: Vol. 67, no. 6
• Strony: 1885--1894
• Opis fizyczny: Bibliogr. 30 poz.

Twórcy

autor

Waszkiewicz Sebastian

• Department of Geophysics, Faculty of Geology Geophysics and Environmental Protection, AGH University of Science and Technology, Krakow, Poland

autor

Krakowska-Madejska Paulina

• Department of Geophysics, Faculty of Geology Geophysics and Environmental Protection, AGH University of Science and Technology, Krakow, Poland

autor

Puskarczyk Edyta

• Department of Geophysics, Faculty of Geology Geophysics and Environmental Protection, AGH University of Science and Technology, Krakow, Poland

Bibliografia

• 1. Amaefule JO, Altunbay M, Tiab D, Kersey DG, Keelan DK (1993) Enhanced reservoir description: using core and log data to identify hydraulic (flow) units and predict permeability in uncored intervals/wells. SPE Paper 26436:1–16. https://doi.org/10.2118/26436-MS
• 2. Aminzade F, de Groot P (2006) Neural networks and other soft computing techniques with application in the oil industry. EAGE Publications, Houten, p 129
• 3. Asquith G, Krygowski D (2004) Basic well log analysis. AAPG, Oklahoma, https://doi.org/10.1306/Mth16823
• 4. Beard DC, Weyl PK (1973) Influence of texture on porosity and permeability of unconsolidated sand. Am Assoc of Petrol Geol Bull 57(2):349–369
• 5. Bhatt A, Helle HB (2002) Committee neural networks for porosity and permeability prediction from well logs. Geophys Prospec 50(6):645–660. https://doi.org/10.1046/j.1365-2478.2002.00346.x
• 6. Bloch S (1991) Empirical prediction of porosity and permeability in sandstones. Am Assoc Petrol Geol Bull 75(7):1145–1160
• 7. Carman PC (1937) Fluid flow through granular beds. Trans Inst Chem Eng 15:150–167. https://doi.org/10.1016/S0263-8762(97)80003-2
• 8. Falas T, Stafylopatis AG (1999) The impact of the error function selection in neural network-based classifiers. In Proceedings of the international joint conference on neural networks, Washington, DC, USA, pp 1799–1804, DOI: 10.1109/IJCNN.1999.832651
• 9. Huang Z, Shimeld J, Williamson M, Katsube J (1996) Permeability prediction with artificial neural network modeling in the Venture gas field, offshore Eastern Canada. Geophys 61(2):422–436. https://doi.org/10.1190/1.1443970
• 10. Iturrarán-Viveros U, Parra JO (2014) Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data. J Appl Geophys 107:45–54
• 11. Jarzyna J, Puskarczyk E (2009) Permeability of rocks on the basis of mercury porosimetry and NMR measurements. Geologia 35(2/1):599–606 (in Polish)
• 12. Kozeny J (1927) Uber Kapillare Letung des Wassers im Boden, Sitzungsberichte: Royal Academy of Science, Vienna. Proc Class I 136:271–306
• 13. Krakowska P, Puskarczyk E (2015) Tight reservoir properties derived by nuclear magnetic resonance, mercury porosimetry and computed microtomography laboratory techniques: case study of Palaeozoic clastic rocks. Acta Geophys 63(3):789–814. https://doi.org/10.1515/acgeo-2015-0013
• 14. Krogh A, Vedelsby J (1994) Neural network ensembles, cross validation and active learning. In: NIPS'94 proceedings of the 7th international conference on neural information processing systems, pp 231–238
• 15. Lucia FJ (1995) Rock-fabric/petrophysical classification of carbonate pore space for reservoir characterization. Am Assoc Petrol Geol Bull 79(9):1275–1300
• 16. McCulloch WS, Pitts J (1943) A logical calculus of the ideas immanent in nervous activity. Bull of Math Biophys 5:115–133. https://doi.org/10.1007/BF02478259
• 17. Neuzil CE (1994) How permeable are clays and shales? Water Resour Res 30(2):145–150
• 18. Romeo G (1994) Seismic signals detection and classification using artificial neural networks. Ann Geofis 37:343–353. https://doi.org/10.4401/ag-4211
• 19. Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386–408. https://doi.org/10.1037/h0042519
• 20. Schön J (2011) Physical properties of rocks: a workbook. Elsevier, Amsterdam
• 21. Statistica Tutorial (2011) StatSoft Polska, EPS
• 22. Such P, Leśniak G (2006) Warunki konieczne i wystarczające do up-scalingu danych petrofizycznych. Nafta-Gaz 11:565–570 (in Polish)
• 23. Sudakov O, Burnaev E, Koroteev D (2019) Driving digital rock towards machine learning: Predicting permeability with gradient boosting and deep neural networks. Comput Geosci 127:121–136
• 24. Tadeusiewicz R (1993) Sieci neuronowe. Akademicka Oficyna Wydawnicza, Warsaw, Poland (in Polish)
• 25. Tiab D, Donaldson EC (2000) Petrophysics, theory and practice of measuring reservoir rock and fluid transport properties. Elsevier, N.Y., 899 s. (sec. ed.)
• 26. Tutak M, Brodny J (2019) Predicting methane concentration in longwall regions using artificial neural networks. Int J Environ Res Public Health 16(8):1406. https://doi.org/10.3390/ijerph16081406
• 27. Wawrzyniak-Guz K (2016) Acoustic full waveforms as a bridge between seismic data and laboratory results in petrophysical interpretation. Acta Geophys 64:2356–2381
• 28. Węgrzyn H, Huk-Skiba A, Dubiel J, Karapeta M, Byś I, Cieśla M, Polak J (2015) Unpublished documentation of the results of measurements. Polish Oil Gas Company Archive, Warsaw, Poland (in Polish)
• 29. Xiao L, Liu XP, Zou CC, Hu XX, Mao ZQ, Shi YJ, GuoHP Li GR (2014) Comparative study of models for predicting permeability from nuclear magnetic resonance (NMR) logs in two Chinese tight sandstone reservoirs. Acta Geophys 62(1):11–141. https://doi.org/10.2478/s11600-013-0165-6
• 30. Zawisza L (1993) Określanie współczynnika przepuszczalności absolutnej oraz przepuszczalności względnych skał na podstawie pomiarów geofizycznych w otworach wiertniczych. AGH Publishing, Kraków, Poland (in Polish)

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).