I.R. Makhmutov, A.A. Evdoshchuk, D.V. Grandov, Yu.A. Plitkina, I.N. Amosova, V.A. Volkov
Substantiation of rocks typification in the fields of the Vankor cluster: application of modern well logging methods and machine learning algorithms
DOI 10.31087/0016-7894-2020-6-77-86

Modern petrophysics develops with a trend to digitalization, artificial intelligence, and processing of big datasets. With a significant amount of accumulated multidiscipline data (well logging, core, mud logging and production logging, testing, filter intervals, etc.) having different recording times, the standard methods of analysis require a multiple increase in labour costs. In this situation, the machine learning tools allow considerable speeding up procedure of consolidation, processing, and interpretation of input data. At the same time, in order to obtain the best possible result, modern high-tech well logging methods must be used. In the design of a system for the development of reservoirs having a high differentiation of properties over the section, it is important to ensure that entire volume of productive rocks is involved in the development. By the example of a field in the Krasnoyarsk Region, the authors propose an approach to mapping of high- and low-permeable reservoirs in the section with the use of integrated analysis of core data and high-tech well logging methods. The results of the developed technology application for rock typification in the fields of the Vankor cluster are published for the first time. The authors discuss the aspects of the machine learning algorithm development and estimate confidence of the results obtained. It is noted that application of the proposed tool for the PJSC Rosneft assets will improve the efficiency of development of the Nizhnekhetsky deposits.

 

Key words: rocks typification; machine learning; well logging; automation.

For citation: Makhmutov I.R., Evdoshchuk A.A., Grandov D.V., Plitkina Yu.A., Amosova I.N., Volkov V.A. Substantiation of rocks typification in the fields of the Vankor cluster: application of modern well logging methods and machine learning algorithms. Geologiya nefti i gaza. 2020;(6):77–86. DOI: 10.31087/0016-7894-
2020-6-77-86. In Russ.

References

1. Bobrov S.E., Evdoshchuk A.A., Rozbaeva G.L. Improvement of the geological model forecast accuracy based on identification of reservoir classes and study of the same in Nh-I reservoir of Suzunkoye field. Neftyanoe khozyaistvo. 2013;(2):46–50. In Russ.
2. Cannon D.E., Minh С.С., Kleinberg R.L. Quantitative NMR Interpretation. In: SPE Annual Technical Conference and Exhibition (27–30 September, New Orleans, Louisiana). SPE, 1998. pp. 227–236. DOI: 10.2523/49010-MS.
3. Kantemirov Yu.D., Khabarov A.V., Oshnyakov I.O., Kalabin A.A., Koshelev M.B., Dmitrievskii M.V. Primenenie metodov mashinnogo obucheniya dlya poiska propushchennykh produktivnykh intervalov i prognoza “skrytykh” petrofizicheskikh svoistv [Machine learning methods in the search for overlooked productive intervals and prediction of “hidden” petrophysical properties]. In: OOO “TNNTs” mat-ly konf. “Issledovanie skvazhin: Tselepolaganie. Tekhnologii. Effekt.” Ufa. 29.05.2020. In Russ.

I.R. Makhmutov  iD
Petrophysics Manager
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: irmakhmutov@tnnc.rosneft.ru

 

A.A. Evdoshchuk  iD
Expert
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: evdoschukaa@sibintek.ru

 

D.V. Grandov   iD
Chief Manager
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: grandovdv@sibintek.ru

 

Y.A. Plitkina  iD
Managing Director
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: yaplitkina@tnnc.rosneft.ru

 

I.N. Amosova   iD
Lead Specialist
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: amosovain@sibintek.ru

 

V.A. Volkov   iD
Head of Department
Tyumen Petroleum Research Center, LLC,
42, ul. Maksima Gor'kogo, Tyumen, 625048, Russia
e-mail: volkovva2@sibintek.ru

Licensed under a Creative Commons Attribution 4.0 License