Application of Machine Learning Algorithms for Solving Problems in the Oil and Gas Sector

Maiorov K.N.


The paper examines the life cycle of field development, analyzes the processes of the field development design stage for the application of machine learning methods. For each process, relevant problems are highlighted, existing solutions based on machine learning methods, ideas and problems are proposed that could be effectively solved by machine learning methods. For the main part of the processes, examples of solutions are briefly described; the advantages and disadvantages of the approaches are identified. The most common solution method is feed-forward neural networks. Subject to preliminary normalization of the input data, this is the most versatile algorithm for regression and classification problems. However, in the problem of selecting wells for hydraulic fracturing, a whole ensemble of machine learning models was used, where, in addition to a neural network, there was a random forest, gradient boosting and linear regression. For the problem of optimizing the placement of a grid of oil wells, the disadvantages of existing solutions based on a neural network and a simple reinforcement learning approach based on Markov decision-making process are identified. A deep reinforcement learning algorithm called Alpha Zero is proposed, which has previously shown significant results in the role of artificial intelligence for games. This algorithm is a decision tree search that directs the neural network: only those branches that have received the best estimates from the neural network are considered more thoroughly. The paper highlights the similarities between the tasks for which Alpha Zero was previously used, and the task of optimizing the placement of a grid of oil producing wells. Conclusions are made about the possibility of using and modifying the algorithm of the optimization problem being solved. Аn approach is proposed to take into account symmetric states in a Monte Carlo tree to reduce the number of required simulations.


Alpha Zero; machine learning; neural networks; oil and gas problems; oil production forecast; well placement optimization; deep reinforcement learning; Monte Carlo tree; Alpha Zero

Full Text

Текст статьи


PDF (Русский)
References References

Li Z. et al. Fourier neural operator for parametric partial differential equations // arXiv preprint arXiv:2010.08895. - 2020.

Valyuhov S., Kretinin A., Burakov A. Neural network modeling of hydrodynamics processes // Hydrodynamics-Optimizing Methods and Tools. 2011. Р. 201-222.

Нейросетевое имитационное моделирование нефтяных месторождений и гидрогеологических объектов / Б. П. Иваненко и др. Томск : Издательский Дом ТГУ, 2014. 188 с.

Подбор скважин-кандидатов для проведения гидроразрыва пласта на основе математического моделирования с использованием методов машинного обучения / А. Ф. Азбуханов и др. // Нефтяное хозяйство. 2019. № 11. С. 38-42.

Артеева Т. Е., Земенков Ю. Д. Оценка срока полезной эксплуатации трубопроводов с использованием различных моделей искусственных нейронных сетей // Нефть. Газ. Новации. 2020. №. 5. С. 72-74.

Compare M. et al. Reinforcement learning-based flow management of gas turbine parts under stochastic failures // The International Journal of Advanced Manufacturing Technology. 2018. Т. 99, № 9. С. 2981-2992.

Min B. H. et al. Optimal well placement based on artificial neural network incorporating the productivity potential // Energy Sources, Part A: Recovery, Utilization, and Environmental Effects. 2011. Т. 33, №. 18. С. 1726-1738.

Guerra N. Y. et al. Well Location Selection from Multiple Realisations of a Geomodel Using Productivity Potential Maps-A Heuristic Technique // International Oil Conference and Exhibition in Mexico. - Society of Petroleum Engineers, 2006.

Анализ неопределенностей при моделировании водогазового воздействия на нефтяной пласт с применением нейронных сетей / И. Н. Кошовкин и др. // Известия Томского политехнического университета. Инжиниринг георесурсов. 2010. Т. 316, № 1.

Гирич Н. А. Разработка алгоритма оптимизации процесса эксплуатации нефтяного месторождения Каймысовского свода на основе методов машинного обучения : магистерская диссертация. Томск, 2020. URL: 11683/62449.

Božek P. et al. Information technology and pragmatic analysis // Computing and informatics. 2018. Т. 37, № 4. С. 1011-1036.

Silver D. et al. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play // Science. 2018. Т. 362, № 6419. P. 1140-1144.

Pumperla M., Ferguson K. Deep learning and the game of Go // Manning. 2019. Т. 231. С. 279.


Article Metrics

Metrics Loading ...

Metrics powered by PLOS ALM


  • There are currently no refbacks.

Copyright (c) 2021 Майоров К.Н.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

ISSN 1813-7911