Research progress in oil and gas production forecast method and technology

doi:10.3969/j.issn.1672-7703.2025.05.010

Abstract

Abstract: Oil and gas production forecast is a critical technical approach for optimizing development strategy and enhancing recovery factor of oil and gas fields. The theoretical system of oil and gas production decline has systematically been reviewed, and a comparative evaluation between conventional empirical models and analytical methods has been conducted in terms of their theoretical foundations, applicability, and limitations. In addition, innovative application of machine learning in production forecast of complex reservoirs has been discussed in detail. The analysis results show that: (1) Traditional methods show robustness for conventional reservoirs but exhibit constrained application performance in unconventional oil and gas reservoirs due to strong heterogeneity and nonlinear multiphase flow; (2) The data-driven models demonstrate superior prediction performance for unconventional reservoirs through automated feature extraction and spatiotemporal correlation modeling; (3) The physical-informed hybrid models effectively integrate data-driven advantages with physical mechanisms, delivering enhanced reliability in complex conditions and long-term production forecast. The study concludes that artificial intelligence significantly improves prediction accuracy and reliability in oil and gas production forecast, with machine learning and deep learning offering novel technical support for complex reservoir development. However, challenges persist in engineering applications, particularly in real-time computation and model interpretability, where further interdisciplinary research is needed on artificial intelligence and oil and gas domain to promote intelligent and high-quality development of the oil and gas industry.

Key words: production forecast, decline model, machine learning, deep learning, application analysis

CLC Number:

TE313

Liu Baolei, Zhang Xinyi. Research progress in oil and gas production forecast method and technology[J]. China Petroleum Exploration, 2025, 30(5): 128-144.

References

[1] 田建华，朱博华，卢志强，等.基于井控多属性机器学习的缝洞型储层预测方法[J].油气地质与采收率，2023,30(1):86-92.
Tian Jianhua，Zhu Bohua，Lu Zhiqiang，et al. Fracture-cavity reservoir prediction based on well-controlled multi-attribute machine learning [J]. Petroleum Geology and Recovery Efficiency，2023,30(1):86-92.
[2] 陈林，黎棚武，张绍俊，等.基于机器学习的岩芯渗透率及裂缝开度预测[J].西南石油大学学报（自然科学版），2023,45(4):155-163.
Chen Lin, Li Pengwu, Zhang Shaojun, et al. Prediction method of core permeability and fracture aperture based on machine learning [J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2023,45(4):155-163.
[3] Kaleem W, Tewari S, Fogat M, et al. A hybrid machine learning approach based study of production forecasting and factors influencing the multiphase flow through surface chokes [J]. Petroleum, 2023.DOI:10.1016/j.petlm.2023.06.001.
[4] Arps J J. Analysis of decline curves [J]. Transactions of the AIME, 1945,160(1):228-247.
[5] 白玉湖，陈桂华，徐兵祥，等.页岩油气产量递减典型曲线预测推荐做法[J].非常规油气，2017,4(3):49-53.
Bai Yuhu, Chen Guihua, Xu Bingxiang, et al. Recommended method for production decline typical curve prediction of shale oil and gas [J]. Unconventional Oil & Gas, 2017,4(3):49-53.
[6] 王强，曾济楚，梁斌.基于Arps算法的产量递减规律研究与应用[J].录井工程，2021,32(2):142-146,150.
Wang Qiang, Zeng Jichu, Liang Bin. Research and application of production decline law based on Arps algorithm [J]. Mud Logging Engineering, 2021,32(2):142-146,150.
[7] 俞启泰.七种递减曲线的特性研究[J].新疆石油地质，1994(1):49-56.
Yu Qitai. Characteristics study of seven types of decline curves [J]. Xinjiang Petroleum Geology, 1994(1):49-56.
[8] 俞启泰.广义递减曲线标准图版的制作与应用[J].石油勘探与开发，1990(2):84-87,69.
Yu Qitai. Development and application of standard charts for generalized decline curves [J]. Petroleum Exploration and Development, 1990(2):84-87,69.
[9] 俞启泰.一种新型递减曲线[J].石油勘探与开发，1999(3):92-95, 7-8,16-17.
Yu Qitai. A new type of decline curve [J]. Petroleum Exploration and Development, 1999(3):92-95,7-8,16-17.
[10] 俞启泰.Arps递减曲线与增长曲线的联系及其应用[J].油气采收率技术，1998(4):49-52,58,83.
Yu Qitai. The relationship between Arps decline curves and growth curves and their applications [J]. Petroleum Recovery Technology, 1998(4):49-52,58,83.
[11] 冯震，任宗孝，徐建平，等.基于大数据的非常规油气藏产能预测模型研究[J].石油化工应用，2021,40(7):35-38,68.
Feng Zhen, Ren Zongxiao, Xu Jianping, et al. Research on production prediction model of unconventional reservoirs based on big data [J]. Petrochemical Industry Application, 2021, 40(7):35-38,68.
[12] Ilk D, Rushing J A, Perego A D, et al. Exponential vs. hyperbolic decline in tight gas sands: understanding the origin and implications for reserve estimates using Arps’decline curves [C]. Denver: SPE Annual Technical Conference and Exhibition, 2008.
[13] 白玉湖，杨皓，陈桂华，等.页岩气产量递减典型曲线中关键参数的确定方法[J].特种油气藏，2013,20(2):65-68,154.
Bai Yuhu, Yang Hao, Chen Guihua, et al. Methods to determine the key parameters of typical production decline curves of shale gas reservoirs [J]. Special Oil and Gas Reservoirs, 2013,20(2):65-68,154.
[14] 张天泽.页岩储层产量曲线分析[J].大庆石油地质与开发，2017, 36(2):154-159.
Zhang Tianze. Analysis of production curves in shale reservoirs [J]. Petroleum Geology & Oilfield Development in Daqing, 2017,36(2):154-159.
[15] 刘文锋，张旭阳，盛舒遥，等.致密油产量递减分析新组合方法研究：以玛湖致密油藏为例[J].油气藏评价与开发，2021,11(6):911-916.
Liu Wenfeng, Zhang Xuyang, Sheng Shuyao, et al. A new combined method for production decline analysis in tight oil reservoirs: a case study of Mahu tight oil reservoir [J]. Reservoir Evaluation and Development, 2021,11(6):911-916.
[16] Meyet M, Dutta R, Burns C. Comparison of decline curve analysis methods with analytical models in unconventional plays [C]. Houston: SPE Annual Technical Conference and Exhibition, 2013.
[17] Ambrose R J, Clarkson C R, Youngblood J, et al. Life-cycle decline curve estimation for tight/shale reservoirs [C]. The Woodlands: SPE Hydraulic Fracturing Technology Conference and Exhibition, 2011.
[18] Clarkson C R, Qanbari F. An approximate semianalytical multiphase forecasting method for multifractured tight light-oil wells with complex fracture geometry [J]. Journal of Canadian Petroleum Technology, 2015,54(6):489-508.
[19] Wattenbarger R A, El-Banbi A H, Villegas M E, et al. Production analysis of linear flow into fractured tight gas wells [C]. Denver: SPE Rocky Mountain Petroleum Technology Conference, 1998.
[20] Duong A N. Rate-decline analysis for fracture-dominated shale reservoirs: part 2 [C]. Calgary: SPE Canada Unconventional Resources Conference, 2014.
[21] Patzek T W, Male F, Marder M. Gas production in the Barnett Shale obeys a simple scaling theory [J]. Proceedings of the National Academy of Sciences, 2013,110(49):19731-19736.
[22] Kanfar M S, Wattenbarger R A. Comparison of empirical decline curve methods for shale wells [C]. Calgary: SPE Canada Unconventional Resources Conference, 2012.
[23] Hallenbeck L D, Sylte J E, Ebbs D J, et al. Implementation of the Ekofisk field waterflood [J]. SPE Formation Evaluation, 1991,6(3):284-290.
[24] Cheng Y. Reservoir simulation [M]. Encyclopedia of life support systems (EOLSS). Oxford: Eolss Publishers Co., Ltd, 2009.
[25] Blasingame T A, McCray T L, Lee W J. Decline curve analysis for variable pressure drop/variable flowrate systems [C]. Houston: SPE Unconventional Resources Conference/Gas Technology Symposium, 1991.
[26] Ehlig-Economides C A, Ramey H J. Transient rate decline analysis for wells produced at constant pressure [J]. Society of Petroleum Engineers Journal, 1981,21(1):98-104.
[27] 韩国庆，舒晋，董亚，等.半解析产能预测模型及其流动耦合方法综述[J].非常规油气，2025,12(1):85-94.
Han Guoqing, Shu Jin, Dong Ya, et al. A review of semi-analytical productivity prediction models and their flow coupling methods [J]. Unconventional Oil & Gas, 2025,12(1): 85-94.

[28] Brown M, Ozkan E, Raghavan R, et al. Practical solutions for pressure-transient responses of fractured horizontal wells in unconventional shale reservoirs [J]. SPE Reservoir Evaluation & Engineering, 2011,14(6):663-676.

[29] Fetkovich M J. Decline curve analysis using type curves [J]. Journal of Petroleum Technology, 1980,32(6):1065-1077.
[30] Agarwal R G, Gardner D C, Kleinsteiber S W, et al. Analyzing well production data using combined-type-curve and decline-curve analysis concepts [J]. SPE Reservoir Evaluation & Engineering, 1999,2(5):478-486.
[31] Walsh M P, Lake L W. A generalized approach to primary hydrocarbon recovery [C]. Denver: SPE Annual Technical Conference and Exhibition, 2003.
[32] Behmanesh H, Hamdi H, Clarkson C R. Production data analysis of tight gas condensate reservoirs [J]. Journal of Natural Gas Science and Engineering, 2015,22:22-34.
[33] Warren J E, Root P J. The behavior of naturally fractured reservoirs [J]. Society of Petroleum Engineers Journal, 1963, 3(3):245-255.
[34] Kazemi H, Merrill Jr L S, Porterfield K L, et al. Numerical simulation of water-oil flow in naturally fractured reservoirs [J]. Society of Petroleum Engineers Journal, 1976,16(6):317-326.
[35] Ramey Jr H J. Pressure transient testing [J]. Journal of Petroleum Technology, 1982,34(7):1407-1413.
[36] Mattar L, McNeil R. The“flowing”gas material balance [J]. Journal of Canadian Petroleum Technology, 1998,37(2):52-55.
[37] Clarkson C R, Nobakht M, Kaviani D, et al. Production analysis of tight-gas and shale-gas reservoirs using the dynamic-slippage concept [J]. SPE Journal, 2012,17(1):230-242.
[38] Javadpour F. Nanopores and apparent permeability of gas flow in mudrocks (shales and siltstone) [J]. Journal of Canadian Petroleum Technology, 2009,48(8):16-21.
[39] Xiao C, Tian L. Modelling of fractured horizontal wells with complex fracture network in natural gas hydrate reservoirs [J]. International Journal of Hydrogen Energy, 2020,45(28):14266-14280.
[40] Wu K, Olson J E. Numerical investigation of complex hydraulic-fracture development in naturally fractured reservoirs [J]. SPE Production & Operations, 2016,31(4):300-309.
[41] Pedrosa O A, Aziz K. Use of a hybrid grid in reservoir simulation [J]. SPE Reservoir Engineering, 1986,1(6):611-621.
[42] Nelson P H. Pore-throat sizes in sandstones, tight sandstones, and shales [J]. AAPG Bulletin, 2009,93(3):329-340.
[43] Sun J, Schechter D. Optimization-based unstructured meshing algorithms for simulation of hydraulically and naturally fractured reservoirs with variable distribution of fracture aperture, spacing, length, and strike [J]. SPE Reservoir Evaluation & Engineering, 2015,18(4):463-480.
[44] 郭子熙，马骉，张帅，等.深度学习在油气产量预测中的研究进展与技术展望[J].天然气工业，2024,44(9):88-98.
Guo Zixi, Ma Biao, Zhang Shuai, et al. Research progress and technical prospects of deep learning in oil and gas production prediction [J]. Natural Gas Industry, 2024,44(9):88-98.
[45] 何佑伟，贺质越，汤勇，等.基于机器学习的页岩气井产量评价与预测[J].石油钻采工艺，2021,43(4):518-524.
He Youwei, He Zhiyue, Tang Yong, et al. Production evaluation and prediction of shale gas wells based on machine learning [J]. Oil Drilling & Production Technology, 2021,43(4): 518-524.
[46] 侯梦瑶，潘晓甜，张春晓，等.可解释机器学习在油气产量预测中的研究进展[J].石油化工应用，2023,42(10):5-8,25.
Hou Mengyao, Pan Xiaotian, Zhang Chunxiao, et al. Research progress of explainable machine learning in oil and gas production prediction [J]. Petrochemical Industry Application, 2023,42(10):5-8,25.
[47] 任芳玲，任思东，李佳佳，等.基于线性回归法和时间序列法的石油产量预测研究[J].河南科学，2018,36(6):817-822.
Ren Fangling, Ren Sidong, Li Jiajia, et al. Study on oil production prediction based on linear regression and time series methods [J]. Henan Science, 2018,36(6):817-822.
[48] Niu W, Lu J, Sun Y. A production prediction method for shale gas wells based on multiple regression [J]. Energies, 2021, 14(5):1461.
[49] Alharbi R, Alageel N, Alsayil M, et al. Prediction of oil production through linear regression model and big data tools [J]. International Journal of Advanced Computer Science and Applications, 2022,13(12):253-260.
[50] 李卓，刘斌，刘铁男，等.支持向量机在油田产量预测中的应用[J].大庆石油学院学报，2005(5):100-101,104,132.
Li Zhuo, Liu Bin, Liu Tienan, et al. Application of support vector machine in oilfield production prediction [J]. Journal of Daqing Petroleum Institute, 2005(5):100-101,104,132.
[51] Wen S, Wei B, You J, et al. Forecasting oil production in unconventional reservoirs using long short term memory network coupled support vector regression method: a case study [J]. Petroleum, 2023,9(4):647-657.
[52] 王一淋，赵磊，梅海燕，等.GM(1,1)与支持向量机组合模型在特高含水期油田产量预测中的应用[J].石油天然气学报，2009,31(1):271-273.
Wang Yilin, Zhao Lei, Mei Haiyan, et al. Application of GM(1,1) and SVM combined model in production prediction of ultra-high water cut oilfields [J]. Journal of Oil and Gas Technology, 2009,31(1):271-273.
[53] Wang Q, Chen D, Li M, et al. A novel method for petroleum and natural gas resource potential evaluation and prediction by support vector machines (SVM) [J]. Applied Energy, 2023,351: 121836.
[54] 闫春明，陈孔全，李洪燕，等.机器学习在油气田开发中的应用、挑战及发展趋势[J].应用化工，2024,53(8):2003-2009.
Yan Chunming, Chen Kongquan, Li Hongyan, et al. Application，challenge and development trend of machine learning in oil and gas field development [J]. Applied Chemical Industry, 2024,53(8):2003-2009.
[55] Liao L, Zeng Y, Liang Y, et al. Data mining: a novel strategy for production forecast in tight hydrocarbon resource in Canada by random forest analysis [C]. Dhahran: International Petroleum Technology Conference, 2020.
[56] Xue L, Liu Y, Xiong Y, et al. A data-driven shale gas production forecasting method based on the multi-objective random forest regression [J]. Journal of Petroleum Science and Engineering, 2021,196:107801.
[57] Chahar J, Verma J, Vyas D, et al. Data-driven approach for hydrocarbon production forecasting using machine learning techniques [J]. Journal of Petroleum Science and Engineering, 2022,217:110757.
[58] Ma H, Zhao W, Zhao Y, et al. A data-driven oil production prediction method based on the gradient boosting decision tree regression [J]. CMES-Computer Modeling in Engineering & Sciences, 2023,134(3):2067-2086.
[59] Cunha L B. Integrating static and dynamic data for oil and gas reservoir modelling [J]. Journal of Canadian Petroleum Technology, 2004,43(3):8-11.
[60] Alolayan O S, Raymond S J, Montgomery J B, et al. Towards better shale gas production forecasting using transfer learning [J]. Upstream Oil and Gas Technology, 2022,9:100072.
[61] 宋兆杰，何吉祥，宋宜磊，等.基于深度学习的页岩油生产井最终可采储量预测模型：以吉木萨尔凹陷芦草沟组为例[J].非常规油气，2025,12(1):95-105.
Song Zhaojie, He Jixiang, Song Yilei, et al. A deep learning-based prediction model for ultimate recoverable reserves of shale oil production wells: a case study of the Lucaogou Formation in Jimsar Sag [J]. Unconventional Oil & Gas, 2025,12(1):95-105.
[62] Odi U, Ayeni K, Alsulaiman N, et al. Applied transfer learning for production forecasting in shale reservoirs [C]. Manama: SPE Middle East Oil and Gas Show and Conference, 2021.
[63] Niu W, Sun Y, Zhang X, et al. An ensemble transfer learning strategy for production prediction of shale gas wells [J]. Energy, 2023,275:127443.
[64] Niu W, Sun Y, Yang X, et al. Toward production forecasting for shale gas wells using transfer learning [J]. Energy & Fuels, 2023,37(7):5130-5142.
[65] Sun J, Ma X, Kazi M. Comparison of decline curve analysis DCA with recursive neural networks RNN for production forecast of multiple wells [C]. Garden Grove: SPE Western Regional Meeting, 2018.
[66] Al-Shabandar R, Jaddoa A, Liatsis P, et al. A deep gated recurrent neural network for petroleum production forecasting [J]. Machine Learning with Applications, 2020,3:100013.
[67] Song X, Liu Y, Xue L, et al. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model [J]. Journal of Petroleum Science and Engineering, 2020,186:106682.
[68] Huang R, Wei C, Wang B, et al. Well performance prediction based on Long Short-Term Memory (LSTM) neural network [J]. Journal of Petroleum Science and Engineering, 2022,208: 109686.
[69] Yang R, Liu X, Yu R, et al. Long short-term memory suggests a model for predicting shale gas production [J]. Applied Energy, 2022,322:119415.
[70] Gao M, Wei C, Zhao X, et al. Production forecasting based on attribute-augmented spatiotemporal graph convolutional network for a typical carbonate reservoir in the Middle East [J]. Energies, 2022,16(1):407.
[71] Huang H, Gong B, Sun W. A deep-learning-based graph neural network-long-short-term memory model for reservoir simulation and optimization with varying well controls [J]. SPE Journal, 2023,28(6):2898-2916.
[72] Marcílio W E, Eler D M. From explanations to feature selection: assessing SHAP values as feature selection mechanism [C]. Recife: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2020.
[73] 闵超，文国权，李小刚，等.可解释机器学习在油气领域人工智能中的研究进展与应用展望[J].天然气工业，2024,44(9):114-126.
Min Chao, Wen Guoquan, Li Xiaogang, et al. Research progress and application prospects of explainable machine learning in artificial intelligence for oil and gas field [J]. Natural Gas Industry, 2024,44(9):114-126.
[74] Kong B, Chen Z, Chen S, et al. Machine learning-assisted production data analysis in liquid-rich Duvernay Formation [J]. Journal of Petroleum Science and Engineering, 2021,200: 108377.
[75] 张瑞，贾虎.基于多变量时间序列及向量自回归机器学习模型的水驱油藏产量预测方法[J].石油勘探与开发，2021,48(1):175-184.
Zhang Rui, Jia Hu. A water-flooding reservoir production prediction method based on multivariate time series and vector autoregressive machine learning model [J]. Petroleum Exploration and Development, 2021,48(1):175-184.
[76] Chen G, Tian H, Xiao T, et al. Time series forecasting of oil production in enhanced oil recovery system based on a novel CNN-GRU neural network [J]. Geoenergy Science and Engineering, 2024,233:212528.
[77] 刘传喜，王树平，刘延庆，等.油气田产量预测模型应用新方法[J].石油与天然气地质，2009,30(3):384-387.
Liu Chuanxi, Wang Shuping, Liu Yanqing, et al. New application method of production prediction models in oil and gas fields [J]. Oil & Gas Geology, 2009,30(3):384-387.
[78] 刘秀婷，杨军，程仲平，等.油田产量预测的新方法及其应用[J].石油勘探与开发，2002(4):74-76.
Liu Xiuting, Yang Jun, Cheng Zhongping, et al. A new method for oilfield production prediction and its application [J]. Petroleum Exploration and Development, 2002(4):74-76.
[79] Shoeibi Omrani P, Vecchia A L, Dobrovolschi I, et al. Deep learning and hybrid approaches applied to production forecasting [C]. Abu Dhabi: Abu Dhabi International Petroleum Exhibition and Conference, 2019.
[80] Liu X, Xu P, Zhao J, et al. Material machine learning for alloys: applications, challenges and perspectives [J]. Journal of Alloys and Compounds, 2022, 921: 165984.
[81] Cuomo S, Di Cola V S, Giampaolo F, et al. Scientific machine learning through physics-informed neural networks: where we are and what’s next [J]. Journal of Scientific Computing, 2022,92(3):1-62.