1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
2 Southwest Petroleum University Branch of PetroChina Key Laboratory of Logging, Chengdu 610500, China
3 Geological Research Institute of CNPC Logging Co., Ltd., Xi'an 710200, China
4 Second Oil Production Plant of Changqing Oilfield Branch, Qingyang 745000, China
Show less
文章历史+
Received
Published
Revised
2025-03-04
2026-03-08
2025-11-28
Online Date
2026-07-09
PDF (12335K)
摘要
页岩油的储层改造是后续开发的关键,然而影响储层产能的因素众多,不同水平井产能主控因素尚不明确,从而使得产能预测精度不高。为了明确页岩油水平井初期产能控制因素,以鄂尔多斯盆地长7段为研究对象,采用Pearson相关分析、主成分分析、灰色关联法对产能影响因素进行筛选降维,并基于筛选结果,建立机器学习预测模型,对初期产能进行合理预测。研究表明:通过权衡不同方法获得的各因素间的关联度,最终确定段数、每米加砂量、含油饱和度、焖井时间、抽深、孔隙度为该区域的产能主控因素;以筛选的主控因素作为输入参数,基于5种单一机器学习算法建立的融合模型有着较高的预测精度,其R2、RMSE(root mean squared error)和MRE(mean relative error)分别达到了0.958 1、0.173 8、1.119 1%;相较于单一的机器学习算法模型,融合模型能够更好地对水平井初期产能进行预测,提升预测精度,后续可结合多元数据优化模型算法提升模型预测效果,对实际页岩油水平井开发优化具有重要指导意义。
Abstract
Reservoir stimulation of shale oil is the key to subsequent development. However, there are numerous factors affecting reservoir productivity, and the main controlling factors of productivity for different horizontal wells remain unclear, leading to low accuracy in productivity prediction. To identify the main controlling factors of initial productivity of shale oil horizontal wells, taking the Chang 7 Member of the Ordos Basin as the research object, Pearson correlation analysis, principal component analysis, and grey relational analysis were used to screen and reduce the dimensionality of productivity-influencing factors. Based on the screening results, a machine learning prediction model was established to reasonably predict the initial productivity. The results show these as follows. By weighing the correlation degree between various factors obtained by different methods, the number of fracturing stages, proppant dosage per meter, oil saturation, soaking time, pumping depth, and porosity are finally determined as the main controlling factors of productivity in this area; taking the screened main controlling factors as input parameters, the integrated model established based on 5 single machine learning algorithms has high prediction accuracy, with R2, RMSE (root mean squared error), and MRE (mean relative error) reaching 0.958 1, 0.173 8, and 1.119 1% respectively; compared with single machine learning algorithm models, the integrated model can better predict the initial productivity of horizontal wells and improve prediction accuracy. In the future, the model algorithm can be optimized by combining multi-source data to enhance the prediction effect, which has important guiding significance for the optimization of actual shale oil horizontal well development.
LUO Jiang, XIONG Jian, GOU Yan-hong, LIU Xiang-jun, WU Guo-cai, CHENG Dao-jie, ZHANG Feng-sheng.
Main Controlling Factors and Productivity Prediction in Initial Production Stage of Shale Oil Horizontal Wells[J].
Science Technology and Engineering, 2026, 26(7): 2844-2856 DOI:10.12404/j.issn.1671-1815.2501399
HeXiao, WuJianfa, YongRui, et al. Accumulation conditions and key exploration and development technologies of marine shale gas fields in Changning Weiyuan Block, Sichuan Basin[J]. Acta Petrologica Sinica, 2021, 42(2): 259-272.
WangZhigang. Reservoir forming conditions and key technologies for efficient exploration and development of Fuling large marine shale gas field[J]. Acta Petrologica Sinica, 2019, 40(3): 370-382.
DuYushan, JiangLong, ChengZiyan, et al. Development progress and key research directions of shale oil in Jiyang, Shengli[J]. Petroleum Geology and Recovery Efficiency, 2024, 31(5): 77-98.
ZhaoHongbing. Research on evaluation technology of main control factors of productivity of Volume Fractured Horizontal Wells in tight reservoirs[D]. Xi'an: Xi'an University of Petroleum, 2021.
QiYin, LiJiaxin, ChenQiang, et al. Evaluation of main controlling factors of shale oil productivity based on machine learning: a case study of the Xi 233 Block in Qingcheng Oilfield[J]. Drilling & Production Technology, 2024, 47(6): 61-68.
ZhaoJun, YuChunyong, HouGuowen, et al. Analysis of geological influencing factors of stimulation measures for shale oil wells in the Lower Sub-member of the First Member of Shahejie Formation in Qikou Sag[J]. Mud Logging Engineering, 2024, 35(3): 121-129.
ChenJingyou. Research and application of Deep Learning methods in the integration of fracturing, soaking and production in shale oil reservoirs[D]. Wuhan: Yangtze University, 2024.
LiuWei, CaoXiaopeng, HuHuifang, et al. Analysis of influencing factors of shale oil horizontal well production and optimization decision of fracturing parameters[J]. Reservoir Evaluation and Development, 2024, 14(5): 764-770.
SongYanzhi, YangQian, RenZheyu, et al. Productivity calculation and influencing factors of fractured horizontal wells in shale gas reservoirs[J]. Daqing Petroleum Geology and Development, 2023, 42(3): 158-166.
ChengBingjie, XuTianji, LuoShiyi, et al. Prediction method and practice of deep shale favorable reservoir based on machine learning[J]. Petroleum Exploration and Development, 2022, 49(5): 918-928.
YaoDonghua, ZhouLihong, WangWenge, et al. Comprehensive well logging evaluation of shale oil-taking the second member of Kongdian Formation in Cangdong sag as an example[J]. Acta Petrologica Sinica, 2022, 43(7): 912-924.
[25]
蒋文超. 基于机器学习与模型融合的大庆油田 SN 区块油井压裂效果预测技术[J]. 大庆石油地质与开发, 2023, 42(1): 64-72.
[26]
JiangWenchao. Prediction technology of oil well fracturing effect in SN Block of Daqing Oilfield based on machine learning and model fusion[J]. Petroleum Geology & Oilfield Development in Daqing, 2023, 42(1): 64-72.
ZhuDawei, HuYongle, CuiMingyue, et al. Coupling of local grid refinement and embedded discrete fracture model to predict productivity of fractured wells[J]. Petroleum Exploration and Development, 2020, 47(2): 341-348.
PuBaoping, WeiJianguang, ZhouXiaofeng, et al. Coupling of local grid refinement and embedded discrete fracture model to predict productivity of fractured wells[J]. Science Technology and Engineering, 2023, 23(28): 12045-12056.
YangHongmei, XueMin, YangYang, et al. Prediction of reasonable soak time in Shale Reservoirs based on Machine Learning[J]. Journal of Xi'an University of Petroleum, 2022, 37(2): 65-72.
[33]
SungilK, KwangH K, Jung-TekL. Synergistic enhancement of productivity prediction using machine learning and integrated data from six shale basins of the USA[J]. Geoenergy Science and Engineering, 2023, 229: 212068.
[34]
ChunhuaL, HanQ J, inlongY, et al. Shale oil production prediction and fracturing optimization based on machine learning[J]. Journal of Petroleum Science and Engineering, 2022, 217: 110900.
[35]
ChengB J, XuT J, LuoS Y, et al. Method and practice of deep favorable shale reservoirs prediction based on machine learning[J]. Petroleum Exploration and Development, 2022, 49(5): 1056-1068.
[36]
ZhouG Z, GuZ Q, SunS M, et al. A CNN-BiGRU-AM neural network for AI applications in shale oil production prediction[J]. Applied Energy, 2023, 344: 121249.
[37]
LiuZ, ZengJ H, QiaoJ C, et al. An advanced prediction model of shale oil production profile based on source-reservoir assemblages and artificial neural networks[J]. Applied Energy, 2023, 333: 120604.
[38]
ZhangS W, ZhangM Z, WangZ, et al. Research on shale gas productivity prediction method based on optimization algorithm[J]. Journal of Combinatorial Optimization, 2023, 45(5): 1233-1234.
[39]
LiX L, XiaoK, LiX B, et al. A well rate prediction method based on LSTM algorithm considering manual operations[J]. Journal of Petroleum Science & Engineering, 2022, 210: 110047.
[40]
SunR, HuJ, ZhangY, et al. A semi-analytical model for investigating the productivity of fractured horizontal wells in tight oil reservoirs with micro-fractures[J]. Journal of Petroleum Science and Engineering, 2020, 186(1): 476-487.
GuoXusheng, HuZongquan, ShenBaojian, et al. Classification of source-reservoir coupling types of shale oil and gas in China and its exploration significance[J]. Acta Petrolei Sinica, 2024, 45(11): 1565-1578.
ZhaoZhe, BaiBin, LiuChang, et al. Current status, advances, and prospects of CNPC's exploration of onshore moderately to highly mature Shale Oil Reservoirs[J]. Oil & Gas Geology, 2024, 45(2): 327-340.
ZhangXiaohui, FengShunyan, LiangXiaowei, et al. Sedimentary microfacies and sedimentary evolution characteristics of the Chang 7 Member of the Yanchang Formation in the Longdong Area of the Ordos Basin[J]. Acta Geologica Sinica, 2020, 94(3): 957-967.
GuoQiheng, LiShixiang, JinZhenkui, et al. Characteristics and exploration direction of shale oil in the Chang 73 Sub-member of the Yanchang Formation in the Ordos Basin[J]. Petroleum Exploration and Development, 2023, 50(4): 767-781.
[51]
魏之焜. 鄂尔多斯盆地城壕地区长7段致密油成藏条件研究[D]. 西安: 西安石油大学, 2016.
[52]
WeiZhikun. Study on the reservoir-forming conditions of tight oil in the Chang 7 Member in the Chenghao Area of the Ordos Basin[D]. Xi'an: Xi'an Shiyou University, 2016.
GaoShengli, GaoJiyang, WeiXueke. Quantitative evolution of the paleostructure on the bottom surface of the Yanchang Formation in the Ordos Basin and its petroleum geological significance[J]. Science Technology and Engineering, 2024, 24(5): 1782-1788.
FuJinhua, LiShixiang, NiuXiaobing, et al. Geological characteristics and exploration practice of Shale Oil in the Chang 7 Member of the Triassic System in the Ordos Basin[J]. Petroleum Exploration and Development, 2020, 47(5): 870-883.
FuSuotang, FuJinhua, NiuXiaobing, et al. Reservoir-forming conditions and key exploration and development technologies of the Qingcheng Oilfield[J]. Acta Petrolei Sinica, 2020, 41(7): 777-795.
LeiQihong, HeYou'an, GuoQiheng, et al. Key scientific and technological issues in the development of horizontal wells for shale oil in the Ordos Basin[J]. Natural Gas Geoscience, 2023, 34(6): 939-949.
XueTing, HuangTianjing, ChengLiangbing, et al. Main controlling factors of horizontal well productivity of shale oil in Qingcheng Oilfield, Ordos Basin and optimization of development countermeasures[J]. Natural Gas Geoscience, 2021, 32(12): 1880-1888.
WeiJiaxin, ZhangYan, ShangJiaohui, et al. Analysis of productivity control factors in the initial development stage of Shale Oil: a case study of the Li 151 Block in Changqing Oilfield[J]. Reservoir Evaluation and Development, 2021, 11(4): 550-558.
MaWenli, LiZhiping, GaoChuang, et al. Pearson-MIC analysis method for main controlling factors of initial productivity of shale gas wells[J]. China Sciencepaper, 2018, 13(15): 1765-1771.
DengZhiying, SongZhaojie, ChengYouyou, et al. Main controlling factors of under-injection in water injection wells of Chang 8 reservoir in Jiyuan Oilfield[J]. Science Technology and Engineering, 2019, 19(28): 122-128.
WangChengwang, LiShuguang, WangYubin, et al. Review of research on well logging prediction methods for gas reservoir productivity[J]. Science Technology and Engineering, 2023, 23(28): 11927-11936.
FuYuxuan, TanChengqian, HouBin, et al. Evaluation of main controlling factors of low-yield and inefficient wells based on principal component analysis and grey relational method[J]. Journal of Chongqing University of Science and Technology (Natural Science Edition), 2023, 25(3): 23-28.
WangDanqun, LiZhiping, MaoDelei. Productivity prediction of staged fractured wells in tight gas reservoirs based on neural network model[J]. Science Technology and Engineering, 2023, 23(1): 189-197.
GuoJiancheng, LinBotao, XiangJianhua, et al. Analysis of influencing factors of post-fracturing flow-back rate and productivity of Longmaxi shale in Sichuan Basin[J]. Petroleum Science Bulletin, 2019, 4(3): 273-287.
LiYanzun, BaiYuhu, ChenGuihua, et al. Understanding of influencing factors of shale oil and gas productivity based on data analysis[J]. Mathematics in Practice and Theory, 2020, 50(14): 106-113.
GaoLi, HanZhu, LiangFei, et al. Productivity prediction model of fractured horizontal wells in tight gas reservoirs based on dendritic bifurcation fracture network[J]. Science Technology and Engineering, 2024, 24(26): 11208-11214.
JiangYuling, ChenXiaoyu, BaoHanyong. A new rapid prediction model for production decline of shale gas staged fracturing horizontal wells—taking the Fuling shale gas field as an example[J]. Natural Gas Geoscience, 2021, 32(6): 845-850.
WeiMingqiang, DuanYonggang, FangQuantang, et al. Production decline curve analysis method of fractured horizontal wells in Shale Gas Reservoirs[J]. Natural Gas Geoscience, 2016, 27(5): 898-904.
WangNutao, DuLingyun, HeHaibo, et al. A new method for production decline analysis of oil and gas wells[J]. Natural Gas Geoscience, 2020, 31(3): 335-339.
LiYalong, LiuXiangui, HuZhiming, et al. Review on numerical models for productivity prediction of shale gas horizontal wells[J]. Advances in Earth Science, 2020, 35(4): 350-362.
YuanYu, ZhangSuian, WuYanqiang, et al. A multi-point productivity calculation model based on non-linear fitting method[J]. Journal of Xi'an Shiyou University (Natural Science Edition), 2019, 34(2): 66-72.