Prediction of fluid brine event zones by artificial intelligence methods based on new generation RTH seismic attributes and drilling data at the Kovykta gas condensate field

Capa

Citar

Texto integral

Acesso aberto Acesso aberto
Acesso é fechado Acesso está concedido
Acesso é fechado Somente assinantes

Resumo

A new method for predicting lithofacies, gas fluid and brine zones, zones with abnormally high reservoir pressure, as well as petrophysical properties of rocks using artificial intelligence methods based on a family of new seismic attributes of the RTH method and well drilling data is proposed. The main difference between RTH attributes and traditional ones obtained by migration transformation is their voxel nature and hyperattributive. It turned out that this is a key advantage of the new approach to solving problems of geological forecasting using artificial intelligence methods. The paper presents the results of applying a new method for processing and interpreting modern 3D seismic data, as well as geological forecasting based on it for the area of intense brine occurrence of the Kovykta gas condensate field.

Texto integral

Acesso é fechado

Sobre autores

A. Bugaev

V.A. Kotelnikov Institute of Radio Engineering and Electronics, Russian Academy of Sciences

Email: Gerokhin@kantiana.ru

Academician of the RAS

Rússia, Moscow

G. Erokhin

I. Kant Baltic Federal University

Autor responsável pela correspondência
Email: Gerokhin@kantiana.ru
Rússia, Kaliningrad

S. Ryabykh

“GIRS-M” LLC

Email: Gerokhin@kantiana.ru
Rússia, Moscow

A. Smirnov

Gazprom VNIIGAZ LLC

Email: Gerokhin@kantiana.ru
Rússia, Tyumen

Bibliografia

  1. Вахромеев А. Г., Хохлов Г. А. Перспективы прогноза зон рапопроявлений в Верхоленском (Жигаловском) газоносном районе Иркутской области / В сб. Особенности технологии проводки и заканчивания скважин в Вост. Сибири и Якутии / СНИИГГиМС, ВостСибНИИГГиМС, Новосибирск, Иркутск, 1988. С. 140‒142.
  2. Priezzhev I. I., Veeken P. C.H., Egorov S. V., Strecke U. Direct prediction of petrophysical and petroelastic reservoir properties from seismic and well-log data using nonlinear machine learning algorithms // The Leading Edge. 2019. 38: 949–958. https://doi.org/10.1190/tle38120949
  3. Смирнов А. С., Вахромеев А. Г., Ерохин Г. Н., Дмитриев А. Г. Прогноз рапопроявлений юга Сибирской платформы по сейсморазведочным данным // Геофизика. 2023. № 2. С. 93‒101, https://doi.org/10.34926/geo.2023.18.86.011
  4. Buddo I. V., Smirnov A. S., Misiurkeeva N. V., Shelohov I. A., Agafonov Y. A., Lushev M. A., Korotkov S. A., Trjasin E. Ju. Integration of Geomechanical, Geoelectric and Structural-tectonic Models for the Kovykta Gas Condensate Field Geological Model Improvement European Association of Geoscientists & Engineers // Saint Petersburg 2018. Apr 2018. V. 2018. P. 1‒6.
  5. Hampson D. P., Schuelke J. S., Quierin J. A. Use of multiattribute transforms to predict log properties from seismic data // Geophysics. 2001. 66. 220–236 http://dx.doi.org/10.1190/1.1444899.
  6. Luanxiao Z., Caifeng Z., Yuanyuan C., Wenlong S., Wang Y., Chen H., Geng J. Fluid and lithofacies prediction based on integration of well-log data and seismic inversion: A machine-learning approach // Geophysics. V. 86. No. 4. P. M151–M165.
  7. Erokhin G. Reverse Time Holography Approach based on the Vector Domain Common Image Gathers // SEG Technical Program Expanded Abstracts 2019: 4107‒4111., https://doi.org/10.1190/segam2019–3201622.1
  8. Erokhin G. Time-dependent scattering in reverse time holography method // 83rd EAGE Annual Conference & Exhibition, Jun 2022. V. 2022. P. 1‒5 https://doi.org/10.3997/2214–4609.202210094
  9. Baysal E., Kosloff D. D., Sherwood J. W.C. Reverse time migration // Geophysics. 1983. 48, 1514–1524, https://doi.org/10.1190/1.1441434
  10. Dickens T. A., Winbow G. A. RTM angle gathers using Poynting vectors // SEG Technical Program Expanded Abstracts 2011 ISSN (print): 1052–3812 ISSN Pages: 4424, https://doi.org/10.1190/1.3627841
  11. Koren Z., Ravve I. Full-azimuth subsurface angle domain wavefield decomposition and imaging Part 1: Directional and reflection image gathers // Geophysics. 2011. 76. S1‒S13.
  12. Kremlev A. N., Erokhin G. N., Starikov L.E, Rodin S. V. Fracture and cavernous reservoirs prospecting by the CSP prestack migration method // 73th Conference & Exhibition, 2011, EAGE, Extended Abstracts, B024.
  13. Chopra S., Castagna J. P. AVO // Publisher: Society of Exploration Geophysicists 2014. P. 304.
  14. Tarantola A. Inversion of seismic reflection data in the acoustic approximation //
  15. Geophysics. Article volume 49. issue 8Aug 1, 1984.
  16. Virieux J., Operto S. An overview of full-waveform inversion in exploration geophysics // Geophysics. 2009. 74. WCC1–WCC26. http://dx.doi.org/10.1190/1.3238367
  17. Popovici A., Tanushev N., Hardesty S. High-resolution, wide-azimuth beam tomography for velocity model building // SEG Technical Program Expanded Abstracts 2016. P. 5349‒5353.
  18. Агафонов В. М., Бугаев А. С., Ерохин Г. Н., Ронжин А. Л. Векторная сейсморазведка в обращенном времени: состояние и перспективы // Геофизика. 2022. 6. С. 77‒83.
  19. Aminzadeh F., Temizel C., Hajizadeh Y. Artificial Intelligence and Data Analytics for Energy Exploration and Production // Wiley. 2022. P. 577.
  20. Смирнов А. С., Касьянов В. В., Вахромеев А. Г. и др. Способ выявления и картирования флюидонасыщенных анизотропных каверново-трещинных коллекторов в межсолевых карбонатных пластах осадочного чехла // пат. 2690089 Рос. Федерация: МПК G01V 1/00 (2006.01), G01V 1/28 (2006.01), G01V 1/30 (2006.01)/; патентообладатель Общество с ограниченной ответственностью “Газпром геологоразведка”. – № 2018127233, заявл. 24.07.2018; опубл. 30.05.2019, Бюл. № 16. 20 с.
  21. Вахромеев А. Г., Сверкунов С. А., Смирнов А. С., Горлов И. В. Бурение скважин на нефть и газ в условиях аномально проницаемых трещинных коллекторов с аномально высоким пластовым давлением флюидной системы // Строительство нефтяных и газовых скважин на суше и на море. 2019. № 5. C. 11‒18. https://doi.org/10.30713/0130-3872-2019-5-11-18.

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar
2. Fig. 1. The research area of the KGKM of the area of intensive rapoprevention with AVPD.

Baixar (309KB)
Metadados
3. Fig. 2. Comparison of the results of temporary migration of PSTM (a) and RTH ATD (b).

Baixar (982KB)
Metadados
4. Fig. 3. A map of the average values of fracturing by RTH in the interval of the Atov horizon KGKM in cu.

Baixar (502KB)
Metadados
5. Fig. 4. A map of the average values of the angle of deviations from the vertical of the maximum scattering in the interval of the Atom horizon KGKM in degrees (positive values of the angle – clockwise).

Baixar (409KB)
Metadados
6. Fig. 5. Vertical cross section (a) and a map of the average values in the interval of the Bilchir horizon (b) of the cube of RTH velocity in m/s. The voxel size is 50x50x10 meters.

Baixar (1MB)
Metadados
7. Fig. 6. Comparison of the forecast of the rapid occurrence in the range of the Bilchir horizon of the KGKM by the scattered wave method [19] and the MLP method based on RTH attributes and drilling data (b). Red is the maximum probability (0.4), blue is the minimum probability.

Baixar (789KB)
Metadados
8. Fig. 7. Forecast by the RF method based on RTH attributes and drilling data for gas occurrences in the Khristoforovo-Balykhtinsky horizon of the KGKM. Red is the maximum probability (0.25), blue is the minimum probability. The average probability value is 0.018, the deviation is 0.23.

Baixar (779KB)
Metadados
9. Fig. 8. Forecast by the RF method based on RTH attributes and drilling data in the supra-Parfenovian range of fluid manifestation formations (a). Red is the maximum probability (0.7), blue is the minimum probability. The average probability value is 0.059, the deviation is 0.64. The profile diagram on the KGKM site (b).

Baixar (1MB)
Metadados
10. Fig. 9. Forecast of average porosity by the RF method in the roof–sole interval of the lower part of the Parthenovsky ridge according to RTH attributes and drilling data. The color scale ranges from 20% porosity (red) to 12% (blue).

Baixar (959KB)
Metadados
11. Fig. 10. Comparison of the average porosity in the lower part of the Parthenovian horizon, predicted by the RF method based on RTH attributes (red) and constructed according to GIS data after spatial averaging (green) for a number of wells. The vertical scale is the voxel number along the borehole. Voxel dimensions are 25x25x5 m. The well highlighted in blue did not participate in the training.

Baixar (444KB)
Metadados

Declaração de direitos autorais © Russian Academy of Sciences, 2024

Este site utiliza cookies

Ao continuar usando nosso site, você concorda com o procedimento de cookies que mantêm o site funcionando normalmente.

Informação sobre cookies