Application of machine learning algorithm to forecast production for fracture basement formation, Central arch, Bach Ho field
Abstract
Oil production forecast is a big challenge in the oil and gas industry. Simulation model and prediction results play an important role in field operation and management. Currently, dynamic simulation model, decline curve analysis are popular tools applied to forecast production. The dynamic simulation model shows a remarkable effect for sedimentary objects. However, production forecasting by this method for fracture basement formation sometimes gives unreliable results because the fracture basement formation is a complex of geological objects, which causes difficulties in predicting the geological characteristics. The decline curve analysis (DCA) method uses simple extrapolated mathematical functions to forecast oil production, therefore the results do not reflect the production operations such as opening/closing production interval.
To avoid the disadvantages of these traditional methods, Vietnam Petroleum Institute (VPI) has studied the applicability of machine learning to forecast oil production for fracture basement formation of Bach Ho field. The study results show that the random forest model has improved the production forecast with low relative error (4%).
References
Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Édouard Duchesnay, “Scikit-learn: Machine learning in Python”, Journal of Machine Learning Research, Vol. 12, pp. 2825 - 2830, 2011.
Tran Dang Tu, Nguyen The Duc, Le Quang Duyen, Pham Truong Giang, Le Vu Quan, Le Quoc Trung, Tran Xuan Quy, and Pham Chi Duc “An applied machine learning approach to production forecast for basement formation - Bach Ho field”, Petrovietnam Journal, Vol. 6, pp. 48 - 57, 2019.
Diederik P. Kingma and Jimmy Ba, “Adam: A method for stochastic optimization”, 3rd International Conference for Learning Representations, San Diego, USA, 7 - 9 May 2015. DOI: 10.48550/arXiv.1412.6980.
Robert E Schapire, “The strength of weak learnability”, Machine Learning, Vol. 5, pp. 197 - 227, 1990. DOI: 10.1007/BF00116037.
Oliver Kramer, “Scikit-learn”, Machine learning for evolution strategies. Springer, 2016, pp. 45 - 53. DOI: 10.1007/978-3-319-33383-0.
Tianqi Chen and Carlos Guestrin, “XGBoost: A scalable tree boosting system”, 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 13 - 17 August 2016. DOI: 10.1145/2939672.2939785.
1. The Author assigns all copyright in and to the article (the Work) to the Petrovietnam Journal, including the right to publish, republish, transmit, sell and distribute the Work in whole or in part in electronic and print editions of the Journal, in all media of expression now known or later developed.
2. By this assignment of copyright to the Petrovietnam Journal, reproduction, posting, transmission, distribution or other use of the Work in whole or in part in any medium by the Author requires a full citation to the Journal, suitable in form and content as follows: title of article, authors’ names, journal title, volume, issue, year, copyright owner as specified in the Journal, DOI number. Links to the final article published on the website of the Journal are encouraged.
