Application of machine learning to decline curve analysis (DCA) for gas-condensate production wells with complex production history due to add-on perforation of new reservoirs
Abstract
For every oil and gas operator, DCA plays an essential role since it provides crucial information for production planning and reserves estimation. DCA is the analysis of the decline in production rate or pressure over time, which can be done by fitting a curve through production or pressure historical data points and making a forecast for the well based on the assumption that the same declining trend will continue in the future. However, the conventional DCA method has been shown to have some limitations. On the other hand, machine learning has been vigorously and extensively researched in the last decade; its applications can be found in every aspect of life as well as in the oil and gas industry. Therefore, it is the ideal time to study the application of machine learning to DCA, to complement this important analysis. In this case study, machine learning was used to predict the decline of wellhead pressure, thereby determining well life as well as estimating reserves. The method was applied to 2 wells with very complex production histories due to add-on perforation of new reservoirs. The prediction was verified to have high reliability by comparison with dynamic modeling results.
References
J.J. Arps, “Analysis of decline curves”, Transactions of the AIME, Volume 160, Issue 1, pp. 228 - 247, 1945. DOI: 10.2118/945228-G.
Jing-Jing Liu and Jian-Chao Liu, “Integrating deep learning and logging data analytics for lithofacies classification and 3D modeling of tight sandstone reservoirs”, Geoscience Frontiers, Volume 13, Issue 1, 2022. DOI: 10.1016/j.gsf.2021.101311.
Nguyen Ngoc Tan, Tran Ngoc The Hung, Hoang Ky Son, and Tran Vu Tung, “Supervised machine learning application of lithofacies classification for a hydrodynamically complex gas condensate reservoir in Nam Con Son basin”, Petrovietnam Journal, Volume 6, pp. 27 - 35, 2022. DOI: 10.47800/PVJ.2022.06-03.
R.S. Miller, S. Rhodes, D. Khosla, and F. Nino, “Application of artificial intelligence for depositional facies recognition - Permian basin”, Unconventional Resources Technology Conference, Denver, Colorado, USA, 22-24 July 2019. DOI: 10.15530/urtec-2019-193.
Tran Vu Tung, Ngo Huu Hai, Hoang Ky Son, Tran Ngoc The Hung, and Joseph J. Lambiase, “Depositional facies prediction using artificial intelligence to improve reservoir characterization in a Mature field of Nam Con Son basin, Offshore Vietnam”, Offshore Technology Conference Asia, Kuala Lumpur, Malaysia, 2 - 6 November 2020. DOI: 10.4043/30086-MS.
Hoang Ky Son, Tran Vu Tung, Nguyen Ngoc Tan, Truong Anh Tu, Pham Hoang Duy, Tran Ngoc Trung, Trinh Xuan Vinh, and Ngo Tuan Anh, “Successful application of machine learning to improve dynamic modeling and history matching for complex gas-condensate reservoirs in Hai Thach field, Nam Con Son basin, offshore Vietnam”, SPE Symposium: Artificial Intelligence - Towards a Resilient and Efficient Energy Industry, Virtually, 18 - 19 October 2021. DOI: 10.2118/208657-MS.
Hoang Ky Son, Tran Vu Tung, Nguyen Ngoc Tan, Truong Anh Tu, Pham Hoang Duy, Tran Ngoc Trung, Trinh Xuan Vinh, and Ngo Tuan Anh, “Successful case study of machine learning application to streamline and improve history matching process for complex gas-condensate reservoirs in Hai Thach field, offshore Vietnam”, SPE Middle East Oil & Gas Show and Conference, November 28 -December 1, 2021. DOI: 10.2118/204835-MS.
Tran Ngoc Trung, Trieu Hung Truong, Tran Vu Tung, Ngo Huu Hai, Dao Quang Khoa, Nguyen Thanh Tinh, and Hoang Ky Son, “Virtual multiphase flowmetering using adaptive neuro-fuzzy inference system (ANFIS): A case study of Hai Thach - Moc Tinh field, offshore Vietnam”, SPE Journal, Volume 27, Issue 1, pp. 504 - 518, 2021. DOI: 10.2118/206741-PA.
Kyungbook Lee, Jungtek Lim, Daeung Yoon, and Hyungsik Jung, “Prediction of shale-gas production at Duvernay formation using deep-learning algorithm”, SPE Journal, Volume 24, Issue 6, pp. 2423 - 2437, 2019. DOI: 10.2118/195698-PA.
Cheng Zhan, Sathish Sankaran, Vincent LeMoine, Jeremy Graybill, and Didi-Ooi Sher Mey, “Application of machine learning for production forecasting for unconventional resources”, Unconventional Resources Technology Conference, Denver, Colorado, USA, 22-24 July 2019. DOI: 10.15530/urtec-2019-47.
Dongkwon Han, Jihun Jung, and Sunil Kwon, “Comparative study on supervised learning models for production forecasting of shale reserviors based on a data-driven approach”, Applied Sciences, Volume 10, Issue 4, pp. 1267 - 1285, 2020. DOI: 10.3390/app10041267.
Triệu Hùng Trường, Trần Vũ Tùng và nnk, “Nghiên cứu xây dựng bộ công cụ trí tuệ nhân tạo hỗ trợ đánh giá phân tích, liên kết tài liệu địa chất, địa vật lý giếng khoan và số liệu khai thác để nâng cao hiệu quả quản lý, khai thác mỏ khí condensate Hải Thạch - Mộc Tinh Lô 05-2; 05-3, thuộc Biển Đông Việt Nam”, Đề tài cấp Nhà nước thuộc “Chương trình khoa học và công nghệ trọng điểm cấp quốc gia phục vụ đổi mới, hiện đại hóa công nghệ khai thác và chế biến khoáng sản đến năm 2025”, Mã số 077.2021.CNKK.QG/HĐKHCN, Quyết định số 196/QĐ-BCT ngày 22/1/2021.
Jamil Al-Azzeh, Abdelwadood Mesleh, Maksym Zaliskyi, Roman Odarchenko, and Valeriyi Kuzmin, “A method of accuracy increment using segmented regression”, Algorithms, Volume 15, Issue 10, pp. 378 - 399, 2022. DOI: 10.3390/a15100378.
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.