Abstract. An algorithm is developed to search for oil and gas deposits-analogues, based on clustering of Bayesian networks, built on parameters of the known deposits. Using Bayesian networks, it is possible to effectively represent oil and gas fields in the form of multivariate distributions, accounting for the complex relationships between the parameters. For each of the deposits in the database, a Bayesian network was built on a sample of its nearest neighbors obtained using the cosine distance metric. Clustering of the Bayesian networks built on the samples is performed by comparing the Hamming distance metric between adjacency matrices stretched into a one-dimensional vector. The developed approach is compared to other analogue search methods based on machine learning. Results of evaluation of the algorithm performance are presented, confirming that modeling and searching for analogues using Bayesian networks is a more comprehensive solution to the problem. The accuracy of restoring missing values for most parameters using the developed algorithm turned out to be higher than in existing classical clustering algorithms.

Keywords: oil and gas deposits, analogue deposits, parameter search, clustering, geological parameters, Bayesian networks

References:

1. Popova O. SPE Annual Caspian Technical Conference and Exhibition, Astana, Kazakhstan, 31 Oct.–1 Nov. 2018, рр. 1–13, DOI: 10.2118/192551-MS.
2. Neves L., Ferreira C., Vesely F. Marine and Petroleum Geology, 2019, vol. 110, рр. 717–736, DOI: 10.1016/j.marpetgeo.2019.07.038.
3. Olivo M. et al. Marine and Petroleum Geology, 2020, vol. 121, DOI: 10.1016/j.marpetgeo.2020.104604.
4. Voskresenskiy A. et al. Geosciences: Converting Knowledge into Resources, Saint-Petersburg, Russia, 6–9 Apr. 2018, рр. 1–5, DOI: 10.3997/2214-4609.202053163.
5. Vologin I.S., Islamov R.R., Nigmatullin F.N., Kharisova A.V., Loznyuk O.A. Oil Industry, 2019, no. 12, pp. 124–127. (in Russ.)
6. Podnebesnykh A.V., Khafizov A.R. Problemy sbora, podgotovki i transporta nefti i nefteproduktov, 2019, no. 3, pp. 9–18. (in Russ.)
7. Dumont M., Reninger P., Pryet A., Martelet G., Aunay B., Join J. Journal of Applied Geophysics, 2018, vol. 157, рр. 1–9, DOI: 10.1016/j.jappgeo.2018.06.020.
8. Ren Z., Sun L., Zhai Q. International Journal of Applied Earth Observation and Geoinformation, 2020, vol. 91, рр. 1–12, DOI: 10.1016/j.jag.2020.102154.
9. Rodríguez M.H. et al. SPE Economics and Management, New Orleans, Louisiana, USA, 30 Sep.–2 Oct. 2013, рр. 1–17, DOI: 10.2118/166449-MS.
10. Da Gama e Silva R. et al. Rio Oil & Gas Expo and Conference, Rio de Janeiro, Brazil, 24–27 Sep. 2018, рр. 1–9.
11. Bezborodov A.K., Deeva I.Yu. Almanac of scientific works of young scientists of ITMO University, 2021, рр. 1–6. (in Russ.)
12. Jensen Finn V. Bayesian Networks and Decision Graphs, Springer, 2001, 448 p., DOI: 10.1007/978-0-387-68282-2.
13. Martinelli G., Eidsvik J., Sinding-Larsen R., Rekstad S., Mukerji T. Petroleum Geoscience, 2013, no. 3(19), pp. 289–304, DOI: 10.1144/petgeo2012-057.
14. Scutari M. et al. International Journal of Approximate Reasoning, 2019, vol. 115, рр. 235–253, DOI: 10.1016/j.ijar.2019.10.003.
15. Zhang L., Li D., Tang X., Cao Z., Phoon K. Computers and Geotechnics, 2018, vol. 95, рр. 110–118, DOI: 10.1016/j.compgeo.2017.10.003.
16. Gower J. Biometrics, 1971, no. 4(27), pp. 857–871.
17. Steinhaus H. Bull. Acad. Polon. Sci., 1956, рр. 801–804.
18. Hyndman R.J., Koehler A.B. International Journal of Forecasting, 2006, no. 4(22), pp. 679–688, DOI: 10.1016/j.ijforecast.2006.03.001.