Geological simulation and issues of petroleum fields development
Section editor – PhD in geology and mineralogy Prischepa O.M.
| Article # 14_2020 | submitted on 12/12/2019 displayed on website on 05/11/2020 |
| 15 p. | Egorov S.V., Priezzhev I.I. |
| Seismogeological modeling in order to determine the influence of the completeness of initial information and geological conditions on the result of forecast of poro-perm reservoirs properties | |
| The article is devoted to the study of the predictive capabilities of several of the most common machine learning algorithms in various geological and geophysical conditions. To solve this problem, several synthetic models have been calculated that simulate the possible conditions for reservoir properties. It is shown which algorithms allow to achieve the better positive effect. Keywords: geological modeling, seismic modeling, machine learning algorithm, poro-perm reservoir properties. |
|
| article citation | Egorov S.V., Priezzhev I.I. Seysmogeologicheskoe modelirovanie s tsel'yu opredeleniya vliyaniya polnoty iskhodnoy informatsii i geologicheskikh usloviy na rezul'tat prognoza emkostnykh svoystv kollektorov po seysmicheskim dannym [Seismogeological modeling in order to determine the influence of the completeness of initial information and geological conditions on the result of forecast of poro-perm reservoirs properties]. Neftegazovaya Geologiya. Teoriya I Praktika, 2020, vol. 15, no. 2, available at: http://www.ngtp.ru/rub/2020/14_2020.html |
| DOI | https://doi.org/10.17353/2070-5379/14_2020 |
References
Ampilov Yu.P. Ot seysmicheskoy interpretatsii k modelirovaniyu i otsenke mestorozhdeniy nefti i gaza [From seismic interpretation to modeling and evaluation of oil and gas fields]. Moscow: Izd-vo Spektr, 2008, 384 p.
Ampilov Yu.P., Barkov A.Yu., Yakovlev A.V. Primenenie neyronnykh setey dlya prognoza fil'tratsionno-emkostnykh svoystv po seysmicheskim atributam i rezul'tatam akusticheskoy inversii: stendovyy doklad R105 [Тhe implementation of neural network to рredict reservoir characteristics from seismic attributes and inversion results]. Geonauki – ot novykh idey k novym otkrytiyam: tret'ya Mezhdunarodnaya vystavka-konferentsiya (St. Petersburg, 7-10 Apr 2008). St. Petersburg: SEG-EAGE, 2008, p. 105.
Bakirova E.A. Geologiya nefti i gaza [Petroleum geology]. Moscow: Nedra, 1990, 240 p.
Breiman L., Friedman J.H. Estimating Optimal Transformations for Multiple Regression and Correlation // Journal of American Statistical Association, 1985, vol. 80, no. 391, pp. 580-598.
Chopra S., Marfurt K.J. Seismic attributes for prospect identification and reservoir characterization. - Tulsa: Society of Exploration Geophysicists, 2007, 481 p.
Flakh P. Mashinnoe obuchenie. Nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannykh [Machine learning. The science and art of building algorithms that extract knowledge from data]. Moscow: DMK Press, 2015, 400 p.
Herron D.A., Latimer R.B. First Steps in Seismic Interpretation // Geophysical monograph series, no. 16. - Tulsa: Society of Exploration Geophysicists, 2011, 203 p.
Metodicheskie rekomendatsii po ispol'zovaniyu dannykh seysmorazvedki (2D, 3D) dlya podscheta zapasov nefti i gaza [Guidelines for using seismic data (2D, 3D) to calculate oil and gas reserves]. Yu.P. Ampilov, V.M. Glogovskiy, V.V. Kolesov, M.B. Korostyshevskiy, V.B. Levyant, S.N. Ptetsov. Moscow: OAO «TsGE», 2006, 39 p.
Priezzhev I., Kobrunov А. Hybrid combination genetic algorithm and controlled gradient method to train a neural network // Geophysics, 2016, vol. 81, pp. 35-43. DOI: https://doi.org/10.1190/geo2015-0297.1
Priezzhev I.I., Egorov S.V. Gibridnoe obuchenie neyronnykh setey s tsel'yu prognoza parametrov neftegazovoy produktivnosti gornykh porod [Hybrid training of neural networks to predict the parameters of petroleum productivity]. Seysmicheskie tekhnologii, 2017, pp. 205-208.
Priezzhev I.I., Egorov S.V. Prognoz kubov uprugikh svoystv po dannym seysmorazvedki 3D i GIS pri pomoshchi algoritma «sluchaynogo lesa» [Spatial rock elastic characteristics prediction using 3D seismic and well logs data based on random forest algorithm]. Geofizika, 2018, no.2, pp. 10-16.
Priezzhev I.I., Egorov S.V., Gladkov E.A. Primenenie algoritmov mashinnogo obucheniya dlya resheniya zadach kolichestvennogo prognoza FES po seysmicheskim i skvazhinnym dannym [Quantitative prediction of reservoir properties using 3D seismic and well data based on machine learning algorithms]. Geofizika, 2018, no.3, pp.33-38.
Schuster G.T., Chen Yu. Seismic Inversion by Newtonian Machine Learning // Research Gate GEO-2019-0434.R2: Preprint (PDF Available) April 2019, 57 р. - https://www.researchgate.net/publication/332630844_Seismic_Inversion_by_Newtonian_Machine_Learning
Tikhonov A.N., Arsenin V.Y. Solutions of ill-posed problems. - Washington: V.H. Winston and Sons, 1977, 259 p.
Ampilov Yu.P., Barkov A.Yu., Yakovlev A.V. Primenenie neyronnykh setey dlya prognoza fil'tratsionno-emkostnykh svoystv po seysmicheskim atributam i rezul'tatam akusticheskoy inversii: stendovyy doklad R105 [Тhe implementation of neural network to рredict reservoir characteristics from seismic attributes and inversion results]. Geonauki – ot novykh idey k novym otkrytiyam: tret'ya Mezhdunarodnaya vystavka-konferentsiya (St. Petersburg, 7-10 Apr 2008). St. Petersburg: SEG-EAGE, 2008, p. 105.
Bakirova E.A. Geologiya nefti i gaza [Petroleum geology]. Moscow: Nedra, 1990, 240 p.
Breiman L., Friedman J.H. Estimating Optimal Transformations for Multiple Regression and Correlation // Journal of American Statistical Association, 1985, vol. 80, no. 391, pp. 580-598.
Chopra S., Marfurt K.J. Seismic attributes for prospect identification and reservoir characterization. - Tulsa: Society of Exploration Geophysicists, 2007, 481 p.
Flakh P. Mashinnoe obuchenie. Nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannykh [Machine learning. The science and art of building algorithms that extract knowledge from data]. Moscow: DMK Press, 2015, 400 p.
Herron D.A., Latimer R.B. First Steps in Seismic Interpretation // Geophysical monograph series, no. 16. - Tulsa: Society of Exploration Geophysicists, 2011, 203 p.
Metodicheskie rekomendatsii po ispol'zovaniyu dannykh seysmorazvedki (2D, 3D) dlya podscheta zapasov nefti i gaza [Guidelines for using seismic data (2D, 3D) to calculate oil and gas reserves]. Yu.P. Ampilov, V.M. Glogovskiy, V.V. Kolesov, M.B. Korostyshevskiy, V.B. Levyant, S.N. Ptetsov. Moscow: OAO «TsGE», 2006, 39 p.
Priezzhev I., Kobrunov А. Hybrid combination genetic algorithm and controlled gradient method to train a neural network // Geophysics, 2016, vol. 81, pp. 35-43. DOI: https://doi.org/10.1190/geo2015-0297.1
Priezzhev I.I., Egorov S.V. Gibridnoe obuchenie neyronnykh setey s tsel'yu prognoza parametrov neftegazovoy produktivnosti gornykh porod [Hybrid training of neural networks to predict the parameters of petroleum productivity]. Seysmicheskie tekhnologii, 2017, pp. 205-208.
Priezzhev I.I., Egorov S.V. Prognoz kubov uprugikh svoystv po dannym seysmorazvedki 3D i GIS pri pomoshchi algoritma «sluchaynogo lesa» [Spatial rock elastic characteristics prediction using 3D seismic and well logs data based on random forest algorithm]. Geofizika, 2018, no.2, pp. 10-16.
Priezzhev I.I., Egorov S.V., Gladkov E.A. Primenenie algoritmov mashinnogo obucheniya dlya resheniya zadach kolichestvennogo prognoza FES po seysmicheskim i skvazhinnym dannym [Quantitative prediction of reservoir properties using 3D seismic and well data based on machine learning algorithms]. Geofizika, 2018, no.3, pp.33-38.
Schuster G.T., Chen Yu. Seismic Inversion by Newtonian Machine Learning // Research Gate GEO-2019-0434.R2: Preprint (PDF Available) April 2019, 57 р. - https://www.researchgate.net/publication/332630844_Seismic_Inversion_by_Newtonian_Machine_Learning
Tikhonov A.N., Arsenin V.Y. Solutions of ill-posed problems. - Washington: V.H. Winston and Sons, 1977, 259 p.