1887

Abstract

Summary

The article is devoted to the development of methodological techniques for the application of machine learning technologies, including deep learning, to the problems of in-depth analysis of geological and physical parameters based on the results of laboratory studies of core sections. To achieve this goal, we solve the problem of developing a specialized tabular format for describing the core sections of carbonate deposits, the formation of a database based on the developed format for further analysis and application of deep and surface training technologies. The Usinsk Deposit located in the Komi Republic was chosen as the object of research. The developed format allows all text descriptions of the geological characteristics of the section to be presented in a tabular form with a discrete encoding. On the example of permocarbon Deposit of Usinsk field, a unique database of 500 sections from 6 wells was formed according to the developed formatUsing the formed database, the ratio of mineralogical density and permeability with the categorization of points according to the danhem. As result of the experiments, a model was obtained, which allows to distinguish geological parameters from the photo of the plume.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202053225
2021-01-15
2024-03-29
Loading full text...

Full text loading...

References

  1. Школле Франсуа Глубокое обучение на Python. - СПб.: Питер, 2018. - 400 с.: ил. - (Серия «Библиотека программиста»).
    [Google Scholar]
  2. ГурбатоваИ.П., МелехинС.В., ЮрьевА.В.
    Особенности изучения петрофизических и упругих свойств керна в сложнопостроенных коллекторах нефти и газа при моделировании термобарических пластовых условий //Геология, геофизика и разработка нефтяных и газовых месторождений. - 2010. - № 5. - С. 67–72.
    [Google Scholar]
  3. КостинН.Г., ГубайдуллинМ.Г.
    Влияние размеров исследуемых образцов керна на величину коэффициента пористости карбонатных и терригенных коллекторов //Геологические опасности: материалы XVВсероссийской конференции с международным участием. - 2009. - С. 248–250.
    [Google Scholar]
  4. ПетерсильеВ.И., РабицЭ.Г., БеловЮ.Я.
    Методы и аппаратура для изучения фильтрационно-емкостных свойств пород-коллекторов на образцах большого размера. - М.: Недра, 1980. - 53 с.
    [Google Scholar]
  5. SHkolle Fransua Deep learning in Python - SPb.:Piter, 2018. - 400 p.: il. - (Series "Programmer's Library").
    [Google Scholar]
  6. GurbatovaI.P., MelekhinS.V., Yur'evA.V.
    Features of the study ofpetrophysical and elastic properties of the core in complex reservoirs of oil and gas in the modeling of thermobaric reservoir conditions // Geology, Geophysics and development of oil and gas fields. - 2010. - № 5. - pp. 67–72.
    [Google Scholar]
  7. KostinN.G., GubajdullinM.G.
    Influence of the sizes of the studied core samples on the porosity coefficient of carbonate and terrigenous reservoirs // Geological hazards: proceedings of the XV all-Russian conference with international participation. - 2009. - pp. 248–250.
    [Google Scholar]
  8. Petersil'eV.I., RabicE.G., BelovYU.YA.
    Methods and equipment for studying filtration-capacitance properties of reservoir rocks on large samples]. - M.: Nedra, 1980. - 53 p.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202053225
Loading
/content/papers/10.3997/2214-4609.202053225
Loading

Data & Media loading...

  • Published online: 15 Jan 2021
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error