Open Access
Open access
Lecture Notes in Computer Science, том 12742 LNCS, номера страниц: 394-407

Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks

Deeva Irina 1
Bubnova Anna 1
Andriushchenko Petr 1
Voskresenskiy Anton 1, 2
Bukhanov Nikita 1, 3
2
 
Gazpromneft-GEO, Saint-Petersburg, Russia
3
 
Gazpromneft Science and Technology Center, Saint-Petersburg, Russia
Тип документаBook Chapter
Дата публикации2021-06-10
Springer Nature
Springer Nature
Название журналаLecture Notes in Computer Science
Квартиль по SCImago3
Квартиль по Web of Science
Импакт-фактор 2021
ISSN03029743, 16113349
Краткое описание
In this paper, a multipurpose Bayesian-based method for data analysis, causal inference and prediction in the sphere of oil and gas reservoir development is considered. This allows analysing parameters of a reservoir, discovery dependencies among parameters (including cause and effects relations), checking for anomalies, prediction of expected values of missing parameters, looking for the closest analogues, and much more. The method is based on extended algorithm MixLearn@BN for structural learning of Bayesian networks. Key ideas of MixLearn@BN are following: (1) learning the network structure on homogeneous data subsets, (2) assigning a part of the structure by an expert, and (3) learning the distribution parameters on mixed data (discrete and continuous). Homogeneous data subsets are identified as various groups of reservoirs with similar features (analogues), where similarity measure may be based on several types of distances. The aim of the described technique of Bayesian network learning is to improve the quality of predictions and causal inference on such networks. Experimental studies prove that the suggested method gives a significant advantage in missing values prediction and anomalies detection accuracy. Moreover, the method was applied to the database of more than a thousand petroleum reservoirs across the globe and allowed to discover novel insights in geological parameters relationships.
Цитируется в публикациях: 1
Метрики

Поделиться

Цитировать
ГОСТ |
Цитировать
1. Deeva I. и др. Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks // Lecture Notes in Computer Science. 2021. С. 394–407.
RIS |
Цитировать

TY - GENERIC

DO - 10.1007/978-3-030-77961-0_33

UR - http://dx.doi.org/10.1007/978-3-030-77961-0_33

TI - Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks

T2 - Computational Science – ICCS 2021

AU - Deeva, Irina

AU - Bubnova, Anna

AU - Andriushchenko, Petr

AU - Voskresenskiy, Anton

AU - Bukhanov, Nikita

AU - Nikitin, Nikolay O.

AU - Kalyuzhnaya, Anna V.

PY - 2021

PB - Springer International Publishing

SP - 394-407

SN - 0302-9743

SN - 1611-3349

SN - 9783030779603

SN - 9783030779610

ER -

BibTex |
Цитировать

@incollection{Deeva_2021,

doi = {10.1007/978-3-030-77961-0_33},

url = {https://doi.org/10.1007%2F978-3-030-77961-0_33},

year = 2021,

publisher = {Springer International Publishing},

pages = {394--407},

author = {Irina Deeva and Anna Bubnova and Petr Andriushchenko and Anton Voskresenskiy and Nikita Bukhanov and Nikolay O. Nikitin and Anna V. Kalyuzhnaya},

title = {Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks},

booktitle = {Computational Science {\textendash} {ICCS} 2021}

}

MLA
Цитировать
Deeva, Irina, et al. “Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks.” Lecture Notes in Computer Science, 2021, pp. 394–407. Crossref, https://doi.org/10.1007/978-3-030-77961-0_33.