Information Support for Prospecting and Exploration Operations


Annotation:

The article presents the implementation of the «supervised learning» approach for identifying heavy-oil-bearing reservoirs. At the first stage, the analysis was carried out concerning the current state of the problem of information support for prospecting and exploration operations and rating of wells with the help of the Russian patent search system Exactus System and the American Free Patents Online system. It was established that the classical statistical analysis integrated with machine learning methods is the powerful tool for interpretation of the chemical variable rock structure using fairly-well representative sample. Input data reflect more than 40 physicochemical features of rock and fluid, and they were collected from 2012 to 2016. Comparative analysis of the features values by basic statistical characteristics is given, category, ordinal, discrete and continuous features are highlighted. The need is defined related to elimination of blowout control for six features, scaling, the transformation of two categorical features into discrete ones was performed. Fixed six features with a predominance of missing values were eliminated. The depth of location of the productive strata, which is more than 4 thousand meters, was established.  Features of speed and duration of prospecting and exploration operations, the years of their beginning and end were synthesized. It was revealed that the most productive in terms of the number of detections of heavy-oil-bearing reservoirs was the year 2015. To improve the classification efficiency, two of the three classes of the target feature are summarized. A priori distribution of the target feature by classes was estimated (getting into the «other» class is 8 times more likely than getting into the «heavy-oil-bearing reservoir» class). Dimensions of the problem is reduced by the method of principal components, since the percentage of dispersion explained by the first two principal components is greater than 70. The problem of quadratic optimization with a soft gap is formulated. Classification is performed by the support vector machine method with a Gaussian Radial Basis Function and the regularization parameter equal to one. Classification accuracy is 93 %. The approach can be recommended for improving the estimate accuracy of the deposits rate at the initial development stage.

References:
  1. Graf T., Tsangl G. Arrangement, method and system of the seam stochastic study during oilfield operations. Patent RF. № 2496972. Applied: July 18, 2018. Published: October 27, 2013. Bulletin № 30.
  2. Rules for the development of hydrocarbon deposits. Available at: http://www.garant.ru/products/ipo/prime/doc/71375396/ (accessed: May 13, 2019). (In Russ.).
  3. Poplygin V.V., Galkin S.V., Ivanov S.A. The method of the prompt prediction of the main indicators of oil deposits development. Patent RF. № 2480584. Applied: October 26, 2011. Published: April 27, 2013. Bulletin № 12.
  4. Saetgaraev R.Kh., Kashapov I.Kh., Zvezdin E.Yu., Andaeva E.A. The method of rapid determination of the characteristics of the borehole zone of low-yield wells used at the development of wells, and the system that implements it. Patent RF. № 2559247. Applied: July 28, 2014. Published: August 10, 2015. Bulletin № 22.
  5. Soykan O. Self-improving classification system. US Pat. 802779. Published: September 27, 2011.
  6. Georgi D.T., Chen S., Jacobi D. Pore-scale geometric models for interpretation of downhole formation evaluation data. US Pat. 7257490. Published: August 14, 2007.
  7. Saleri N.G., Toronyi R.M. Petroleum reservoir operation using geotechnical analysis. US Pat. 9946986. Published: April 17, 2018.
  8. Vladov Yu.R., Nesterenko M.Yu., Vladova A.Yu., Nesterenko Yu.M. Method for identifying the geodynamic activity of the developed hydrocarbon field subsoil. Patent RF. № 2575469. Applied: November 12, 2014. Published: February 20, 2016. Bulletin № 5.
  9. Gzara Kais B.M., Dzhain V. Determination of characteristics of bed components on site of works performance. Patent RF. № 2574329. Published: February 10, 2016. Bulletin № 4.
  10. Suares-Rivera R., Khandverger D.A., Soudergren T.L. Method and apparatus for multidimensional data analysis to identify rock heterogeneity. Patent RF. № 2474846. Published: November 20, 2014. Bulletin № 32.
  11. Bekarevich A.A., Budadin O.N., Morozova T.J., Toporov V.I. Method for adaptive forecasting of residual operating life of complex objects, and device for its implementation. Patent RF. № 2533321. Published: November 20, 2014. Bulletin № 32.
  12. Vladova A.Yu. Clustering Analysis of Changes in the Spatial Position of the Trunk Oil Pipeline Sections Based on the In-line Inspection Datasets. Bezopasnost truda v promyshlennosti = Occupational Safety in Industry. 2018. № 1. pp. 22–25. (In Russ.). DOI: 10.24000/0409-2961-2018-1-22-25
  13. Özdemir A., Şahinoplu A., Turgay O. High Accuracy Estimation with Computer-Aided Hydrochemical Methods of Oil and Gas Deposits in Wildcat Sedimentary Basins. Journal of Applied Geology and Geophysics (IOSR-JAGG). 2018. Vol. 6. Iss. 4. Ver. II. pp. 62–104.
  14. Rybkina A.I., Odintsova A.A., Gvishiani A.D. Samokhina O.O., Astapenkova A.A. Development of geospatial database on hydrocarbon extraction methods in the 20th century for large and super large oil and gas deposits in Russia and other countries. Available at: https://cyberleninka.ru/article/v/development-of-g eospatial-database-on-hydrocarbon-extraction-methods-in-the-20th-century-for-large-and-super-large-oil-and-gas-deposits-in (accessed: May 13, 2019).
  15. Nusratov O.G., Abdullayeva G.G., Ismayilov I.A. Integrated Expert Analytical System for Assessment of Oil-and-Gas Saturation of Strata. Available at: https://www.researchgate.net/publication/276291723_Integrated_Expert_Analytical_System_for_Assessment_of_Oil-and-Gas_Saturation_of_Strata (accessed: May 13, 2019).
  16. Barsegyan A.A., Kupriyanov M.S., Kholod I.I., Tess M.D., Elizarov S.I. Data and process analysis. 3-e izd. Saint-Petersburg: BKhV-Peterburg, 2009. 512 p. (In Russ.).
  17. Flakh P. Machine learning. Science and art of building algorithms that extract knowledge from data. Moscow: DMK Press, 2015. 400 p. (In Russ.).
  18. Plot different SVM classifiers in the iris dataset. Available at: https://scikit-learn.org/0.19/auto_examples/svm/plot_iris.html (accessed: May 13, 2019).
DOI: 10.24000/0409-2961-2019-6-14-21
Year: 2019
Issue num: June
Keywords : reservoir binary classifier machine learning dataset
Authors:
  • Vladova A.Yu.
    Vladova A.Yu.
    avladova@mail.ru, Professor Financial University under the Government of the Russian Federation, Moscow, Russia Dr. Sci. (Eng.), Lead Researcher IPU RAN, Moscow, Russia
  • Vladov Yu.R.
    Vladov Yu.R.
    Dr. Sci. (Eng.), Laboratory Head ONTs UrO RAN, Orenburg, Russia Lead Researcher NOTs Orenburg State University, Orenburg, Russia