Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andriushchenko, P., Deeva, I., Kalyuzhnaya, A., Bubnova, A., Voskresenskiy, A., Bukhanov, N.: Analysis of parameters of oil and gas fields using Bayesian networks. In: Data Science in Oil & Gas, vol. 2020, pp. 1–10. European Association of Geoscientists & Engineers (2020)
Chickering, D.M.: Optimal structure identification with greedy search. J. Mach. Learn. Res. 3(Nov), 507–554 (2002)
Cohen, K., et al.: 2013 The ICS International Chronostratigraphic Chart. episodes 36, pp. 199–204. Episodes 36 (Sept 2013). https://doi.org/10.18814/epiiugs/2013/v36i3/002
Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Mach. Learn. 9(4), 309–347 (1992)
De Jager, G.: The influence of geological data on the reservoir modelling and history matching process (2012). https://doi.org/10.4233/uuid:b06f57c2-24b5-407b-a69c-e68c8bd7ff01
Gallagher, K., Charvin, K., Nielsen, S., Sambridge, M., Stephenson, J.: Markov chain monte carlo (MCMC) sampling methods to determine optimal models, model resolution and model choice for earth science problems. Mar. Pet. Geol. 26(4), 525–535 (2009)
Gámez, J.A., Mateo, J.L., Puerta, J.M.: Learning Bayesian networks by hill climbing: efficient methods based on progressive restriction of the neighborhood. Data Min. Knowl. Discovery 22(1), 106–148 (2011)
Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrics 27, 857–871 (1971)
Han, S., Li, M., Zhang, Q., Li, H.: A mathematical model based on Bayesian theory and Gaussian copula for the discrimination of gabbroic rocks from three tectonic settings. J. Geol. 127(6), 611–626 (2019)
Henrion, M.: Propagating uncertainty in Bayesian networks by probabilistic logic sampling. In: Machine Intelligence and Pattern Recognition, vol. 5, pp. 149–163. Elsevier (1988)
Hernández-Maldonado, V., Díaz-Viera, M., Erdely, A.: A multivariate Bernstein copula model for permeability stochastic simulation. Geofísica Int. 53(2), 163–181 (2014)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Li, Y., Deutsch, C.V.: Implementation of the iterative proportion fitting algorithm for geostatistical facies modeling. Nat. Resour. Res. 21(2), 221–231 (2012)
Martinelli, G., Eidsvik, J., Sinding-Larsen, R., Rekstad, S., Mukerji, T.: Building Bayesian networks from basin-modelling scenarios for improved geological decision making. Pet. Geosci. 19(3), 289–304 (2013)
Masoudi, P., Asgarinezhad, Y., Tokhmechi, B.: Feature selection for reservoir characterisation by Bayesian network. Arab. J. Geosci. 8(5), 3031–3043 (2015)
Perez-Valiente, M., Rodriguez, H., Santos, C., Vieira, M., Embid, S.: Identification of reservoir analogues in the presence of uncertainty. In: Society of Petroleum Engineers - SPE Intelligent Energy International 2014 (Apr 2014). https://doi.org/10.2118/167811-MS
Robinson, R.W.: Counting labeled acyclic digraphs. New directions in the theory of graphs, pp. 239–273 (1973)
Scutari, M., Graafland, C.E., Gutiérrez, J.M.: Who learns better Bayesian network structures: accuracy and speed of structure learning algorithms. Int. J. Approximate Reasoning 115, 235–253 (2019)
Sun, S.Q., Wan, J.: Geological analogs usage rates high in global survey. Oil Gas J. 100, 49–50 (2002)
Voskresenskiy, A., Bukhanov, N., Filippova, Z., Brandao, R., Segura, V., Brazil, E.: Feature selection for reservoir analogues similarity ranking as model-based causal inference (Sept 2020). https://doi.org/10.3997/2214-4609.202035170
Voskresenskiy, A., et al.: Variations in ranked list of reservoir analogs as an effect of search preferences 2020(1), 1–5 (2020). https://doi.org/10.3997/2214-4609.202053163. https://www.earthdoc.org/content/papers/10.3997/2214-4609.202053163
Acknowledgement
We would like to thank Gazprom Neft for the provided reservoir dataset. This research is partially financially supported by The Russian Scientific Foundation, Agreement №19-11-00326. Participation in the ICCS conference was supported by the NWO Science Diplomacy Fund project №483.20.038 “Russian-Dutch Collaboration in Computational Science”.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Deeva, I. et al. (2021). Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12742. Springer, Cham. https://doi.org/10.1007/978-3-030-77961-0_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-77961-0_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77960-3
Online ISBN: 978-3-030-77961-0
eBook Packages: Computer ScienceComputer Science (R0)