Volume 32 Issue 1
Feb.  2026
Turn off MathJax
Article Contents
Article Navigation >  Journal of Geomechanics  > 2026  >  32(1): 227-244
SHEN B J，LI D，HE J H，et al.，2026. Intelligent prediction method and application of single-well in-situ stress in shale reservoirs driven by multi-source data[J]. Journal of Geomechanics，32（1）：227−244 doi: 10.12090/j.issn.1006-6616.2025126
Citation: SHEN B J，LI D，HE J H，et al.，2026. Intelligent prediction method and application of single-well in-situ stress in shale reservoirs driven by multi-source data[J]. Journal of Geomechanics，32（1）：227−244 doi: 10.12090/j.issn.1006-6616.2025126
shu

Intelligent prediction method and application of single-well in-situ stress in shale reservoirs driven by multi-source data

doi: 10.12090/j.issn.1006-6616.2025126
  • 1.

    Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China

  • 2.

    College of Energy (College of Modern Shale Gas Industry), Chengdu University of Technology, Chengdu 610059, Sichuan, China

  • 3.

    State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Efficient Development, Beijing 102206, China

Funds:  This research was financially supported by the National Science and Technology Major Project of China (Grant No. 2025ZD1404102-04)，the National Natural Science Foundation of China (Grant No. 42402148), the Development Fund of the National Key Laboratory of Shale Oil & Gas Enrichment Mechanisms and Efficient Development (Grant No. 33550000-24-ZC0699-0057), and Science and Technology Department Project of China Petroleum & Chemical Corporation (Grant No. P24181).
More Information
  • Received: 2025-09-02
  • Revised: 2026-01-05
  • Accepted: 2026-01-07
    • Available Online: 2026-01-16
  • Published: 2026-02-27
    Abstract
  •   Objective  Deep shale reservoirs are characterized by high temperature, high pressure, elevated in situ stress, and strong plasticity. Conventional in-situ stress testing methods and log interpretation models, often calibrated under simplified laboratory conditions, suffer from limited predictive accuracy, high operational cost, and poor generalizability—challenges that constrain their utility in guiding shale gas exploration and development.   Methods  Focusing on a structurally complex shale gas block in southern Sichuan as a representative case, we integrated dynamic and static multi-source data across drilling, logging, testing, and production stages. Along with experimental measurements of the physical and mechanical properties of rock under different conditions, we developed a hybrid stress prediction model by combining machine learning techniques with geomechanical principles. This multi-method, log-based intelligent prediction framework enables the generation of high-resolution in-situ stress profiles for efficient shale gas development.   Results  In the first member of the Longmaxi Formation (Long-1 Member), organic content, confining pressure, and lamination structures significantly influence mechanical anisotropy, particularly in Beds 1–4, which exhibit stronger anisotropy than the upper beds. Based on these findings, we developed a mechanically calibrated anisotropic stress interpretation model for deep shales. Using laboratory- and field-calibrated synthetic stress datasets, we established a standardized stress database for the southern Sichuan shale reservoir. Key sensitive logging parameters, including shear wave slowness, resistivity, acoustic logs, and Young's modulus were identified via Pearson correlation analysis. An optimized XGBoost model achieved interpretation accuracies above 90% for all three principal stress components, with an RMSE of 6.63, an MAE of 3.89, and a coefficient of determination (R2) of 0.91, indicating strong robustness and generalizability. The results revealed four distinct stress barrier layers from the Wufeng Formation to the Longmaxi Formation, and the top of Bed 1 and Bed 6 acted as dominant stress-sealing interfaces. Localized compressive stresses induced by fold-related deformation further enhanced vertical stress compartmentalization and increased the minimum horizontal principal stress, thereby exerting significant influence on hydraulic fracturing performance.   Conclusions  The study revealed the geological factors controlling the mechanical anisotropy of the shale in the Long-1 Member, and established an isotropic in-situ stress interpretation model suitable for deep shale reservoirs accordingly. An integrated intelligent model, L-XGBoost, was adopted to achieve a prediction accuracy exceeding 90% for three-dimensional in-situ stresses. The research also clarified the development characteristics of four sets of stress barrier layers within the Long-1 Member shale and their impact on fracturing effectiveness.  Significance  These insights provide a scientific basis for fine-scale stratigraphic subdivision and three-dimensional well pattern design for shale gas development in the tectonically complex southeastern Sichuan Basin.

     

    • Full-text Translaiton by iFLYTEK

    The full translation of the current issue may be delayed. If you encounter a 404 page, please try again later.
    FullText(HTML)
  • loading
    • References(64)
  • [1]
    ANDERSON R A, INGRAM D S, ZANIER A M, 1973. Determining fracture pressure gradients from well logs[J]. Journal of Petroleum Technology, 25(11): 1259-1268. doi: 10.2118/4135-pa
    [2]
    ASTM International. Standard Test Method for Triaxial Compressive Strength of Undrained Rock Core Specimens Without Pore Pressure Measurements: ASTM D2664/D2664M-20 [S]. West Conshohocken, PA: ASTM International, 2020.
    [3]
    BOWERS G L, 2001. Determining an appropriate pore-pressure estimation strategy[C]//Offshore technology conference. Houston, Texas: OnePetro.
    [4]
    DENG J G, CHEN Z R, GENG Y N, et al., 2013. Prediction model for in-situ formation stress in shale reservoirs[J]. Journal of China University of Petroleum, 37(6): 59-64. (in Chinese with English abstract)
    [5]
    EATON B A, 1975. The equation for geopressure prediction from well logs[C]//Fall meeting of the society of petroleum engineers of AIME. Dallas, Texas: OnePetro.
    [6]
    GE H K, LIN Y S, 1998. Distribution of in-situ stresses in oilfield[J]. Fault-Block Oil & Gas Field, 5(5): 1-5. (in Chinese with English abstract)
    [7]
    HAN H X, YIN S D, 2018. Determination of in-situ stress and geomechanical properties from borehole deformation[J]. Energies, 11(1): 131. doi: 10.3390/en11010131
    [8]
    HE J H, DING W L, WANG Z, et al., 2015. Main controlling factors of fracture network formation of volume fracturing in shale reservoirs and its evaluation method[J]. Geological Science and Technology Information, 34(4): 108-118. (in Chinese with English abstract)
    [9]
    HE J H, XIONG L, WANG R Y, et al., 2025. Disturbance factors of current geostress field of Longmaxi Formation shale in southeastern Sichuan Basin and their geological significance for gas exploitation[J]. Acta Petrolei Sinica, 46(4): 743-762. (in Chinese with English abstract)
    [10]
    HOTTMANN C E, JOHNSON R K, 1965. Estimation of formation pressures from log-derived shale properties[J]. Journal of Petroleum Technology, 17(6): 717-722.
    [11]
    HU D F, WEI Z H, LI Y P, et al., 2022. Deep shale gas exploration in complex structure belt of the southeastern Sichuan Basin: progress and breakthrough[J]. Natural Gas Industry, 42(8): 35-44. (in Chinese with English abstract)
    [12]
    HUANG R Z, 1984. A model for predicting formation fracture pressure[J]. Journal of East China Institute of Petroleum, 8(4): 335-347. (in Chinese with English abstract)
    [13]
    JAMSHIDIAN M, ZADEH M M, HADIAN M, et al., 2017. Estimation of minimum horizontal stress, geomechanical modeling and hybrid neural network based on conventional well logging data: a case study[J]. Geosystem Engineering, 20(2): 88-103. doi: 10.1080/12269328.2016.1227728
    [14]
    JU W, NIU X B, FENG S B, et al., 2020. The present-day in-situ stress state and fracture effectiveness evaluation in shale oil reservoir: a case study of the Yanchang formation Chang 7 oil-bearing layer in the Ordos Basin[J]. Journal of China University of Mining & Technology, 49(5): 931-940. (in Chinese with English abstract)
    [15]
    LI P, ZHANG J S, HE Q, et al, 2024. Safety assessment and heterogeneity of China’s energy supply under the carbon peaking goal[J]. Journal of Beijing Institute of Technology (Social Sciences Edition), 26(3): 51-63. (in Chinese with English abstract)
    [16]
    LIU R, HAO F, ENGELDER T, et al., 2019. Stress memory extracted from shale in the vicinity of a fault zone: implications for shale-gas retention[J]. Marine and Petroleum Geology, 102: 340-349. doi: 10.1016/j.marpetgeo.2018.12.047
    [17]
    LONG S X, FENG D J, LI F X, et al., 2018. Prospect of the deep marine shale gas exploration and development in the Sichuan Basin[J]. Natural Gas Geoscience, 29(4): 443-451. (in Chinese with English abstract) doi: 10.1016/j.ptlrs.2018.10.001
    [18]
    MA T S, XIANG G F, SHI Y F, et al., 2022. Horizontal in situ stresses prediction using a CNN-BiLSTM-attention hybrid neural network[J]. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 8(5): 152. doi: 10.1007/s40948-022-00467-2
    [19]
    MATTHEWS W R, KELLY J, 1967. How to predict formation pressure and fracture gradient[J]. Oil and Gas Journal, 65(8): 92-106.
    [20]
    Ministry of Land and Resources of the People's Republic of China , 2015 Regulation for Testing the Physical and Mechanical Properties of Rock—Part 20: Test for Determining the Density of Rock: DZ/T 0276.20—2015 [S]. Beijing: Standards Press of China. (in Chinese)
    [21]
    National Technical Committee on Petroleum and Natural Gas of Standardization Administration of China, 2013. Practices for Core Analysis: GB/T 29172-2012 [S]. Beijing: Standards Press of China. (in Chinese)
    [22]
    National Land and Resources Standardization Technical Committee, 2015. Regulation for Testing the Physical and Mechanical Properties of Rock - Part 31: Test for Determining the Tensile Strength of Rock (Brazilian Method): DZ/T 0276.31—2015 [S]. Beijing: Geological Publishing House. (in Chinese)
    [23]
    SINGH A, ZOBACK M D, 2022. Predicting variations of the least principal stress with depth: application to unconventional oil and gas reservoirs using a log-based viscoelastic stress relaxation model[J]. Geophysics, 87(3): MR105-MR116.
    [24]
    SU H G, LUO L M, 2023. Research status of ground stress test technology[J]. Shaanxi Coal, 42(1): 59-62. (in Chinese with English abstract)
    [25]
    SUN D S, PANG F, LI A W, et al., 2020. In-situ stress profile prediction based on the rheological model: a case study of Well AY-1 in the Qianbei area of Guizhou Province[J]. Natural Gas Industry, 40(3): 58-64. (in Chinese with English abstract)
    [26]
    SUN D S, ZHOU X Z, DAN YONG, et al., 2021. Measurement and Distribution Patterns of Minimum Horizontal Principal Stress in Shale Reservoirs[J]. Journal of China University of Petroleum (Edition of Natural Science), 45(5): 80-87. (in Chinese with English abstract)
    [27]
    TIAN R F, LI S, LIU T, et al., 2024. vP/vS prediction based on XGBoost algorithm and its application in reservoir detection[J]. Oil Geophysical Prospecting, 59(4): 653-663. (in Chinese with English abstract)
    [28]
    WANG J, CAO J X, ZHAO S, et al., 2022. S-wave velocity inversion and prediction using a deep hybrid neural network[J]. Science China Earth Sciences, 65(4): 724-741. doi: 10.1007/s11430-021-9870-8
    [29]
    WANG R Y, HU Z Q, ZHOU T, et al., 2021. Characteristics of fractures and their significance for reservoirs in Wufeng-Longmaxi shale, Sichuan Basin and its periphery[J]. Oil & Gas Geology, 42(6): 1295-1306.
    [30]
    WANG K M, 2023. Enrichment characteristics of deep shale gas in tectonically complex regions of the southeastern Sichuan Basin[J]. Natural Gas Geoscience, 34(2): 334-348. (in Chinese with English abstract) doi: 10.1016/j.jnggs.2023.04.001
    [31]
    WU M Y, CHANG X, GUO Y T, et al., 2025. Advances, challenges, and opportunities for hydraulic fracturing of deep shale gas reservoirs[J]. Advances in Geo-Energy Research, 15(1): 1-4. doi: 10.46690/ager.2025.01.01
    [32]
    XIA H Q, PENG M, SONG E C, 2019. Calculating method and application of rock anisotropic Biot coefficient[J]. Well Logging Technology, 43(5): 478-483. (in Chinese with English abstract)
    [33]
    ZHANG B, WANG X T, XU F Y, et al., 2025. Research on pore pressure prediction method based on XGBoost[J]. Progress in Geophysics, 40(2): 541-555. (in Chinese with English abstract)
    [34]
    ZHANG J C, WANG Z Y, NIE H K, et al., 2008. Shale gas and its significance for exploration[J]. Geoscience, 22(4): 640-646. (in Chinese with English abstract)
    [35]
    ZHANG J C, QI Y C, 2020. Impact of in-situ stresses on shale reservoir development and its countermeasures[J]. Oil & Gas Geology, 41(4): 776-783, 799. (in Chinese with English abstract)
    [36]
    ZHANG P X, GAO Q F, HE X P, et al., 2023. Characteristics of in-situ stress field and its influence on shale gas production from Longmaxi Formation in Nanchuan area[J]. Petroleum Geology and Recovery Efficiency, 30(4): 55-65. (in Chinese with English abstract)
    [37]
    ZHAO J Z, YONG R, HU D F, et al., 2024. Deep and ultra-deep shale gas fracturing in China: problems, challenges and directions[J]. Acta Petrolei Sinica, 45(1): 295-311. (in Chinese with English abstract)
    [38]
    ZHAO W Z, DONG D Z, LI J Z, et al., 2012. The resource potential and future status in natural gas development of shale gas in China[J]. Strategic Study of CAE, 14(7): 46-52. (in Chinese with English abstract)
    [39]
    邓金根, 陈峥嵘, 耿亚楠, 等, 2013. 页岩储层地应力预测模型的建立和求解[J]. 中国石油大学学报(自然科学版), 37(6): 59-64. doi: 10.3969/j.issn.1673-5005.2013.06.009
    [40]
    葛洪魁, 林英松, 1998. 油田地应力的分布规律[J]. 断块油气田, 5(5): 1-5.
    [41]
    何建华, 丁文龙, 王哲, 等, 2015. 页岩储层体积压裂缝网形成的主控因素及评价方法[J]. 地质科技情报, 34(4): 108-118.
    [42]
    何建华, 熊亮, 王濡岳, 等, 2025. 川东南地区龙马溪组页岩现今地应力场扰动因素及其开发地质意义[J]. 石油学报, 46(4): 743-762. doi: 10.7623/syxb202504006
    [43]
    胡东风, 魏志红, 李宇平, 等, 2022. 四川盆地东南部地区复杂构造带深层页岩气勘探进展与突破[J]. 天然气工业, 42(8): 35-44. doi: 10.3787/j.issn.1000-0976.2022.08.004
    [44]
    黄荣樽, 1984. 地层破裂压力预测模式的探讨[J]. 华东石油学院学报, 8(4): 335-347.
    [45]
    鞠玮, 牛小兵, 冯胜斌, 等, 2020. 页岩油储层现今地应力场与裂缝有效性评价: 以鄂尔多斯盆地延长组长7油层组为例[J]. 中国矿业大学学报, 49(5): 931-940.
    [46]
    李品, 张金锁, 贺琦, 等, 2024. 碳达峰目标下中国能源供给的安全评估及异质性[J]. 北京理工大学学报(社会科学版), 26(3): 51-63.
    [47]
    龙胜祥, 冯动军, 李凤霞, 等, 2018. 四川盆地南部深层海相页岩气勘探开发前景[J]. 天然气地球科学, 29(4): 443-451. doi: 10.11764/j.issn.1672-1926.2018.03.007
    [48]
    全国国土资源标准化技术委员会, 2015. 岩石物理力学性质试验规程第31部分: 岩石抗拉强度试验(劈裂法): DZ/T 0276.31—2015 [S]. 北京: 地质出版社.
    [49]
    全国石油天然气标准化技术委员会, 2013. 岩心分析方法: GB/T 29172-2012 [S]. 北京: 中国标准出版社.
    [50]
    苏宏刚, 罗黎明, 2023. 地应力测试技术研究现状[J]. 陕西煤炭, 42(1): 59-62.
    [51]
    孙东生, 庞飞, 李阿伟, 等, 2020. 基于流变模型的地应力剖面预测: 以贵州黔北地区安页1井为例[J]. 天然气工业, 40(3): 58-64. doi: 10.3787/j.issn.1000-0976.2020.03.007
    [52]
    孙东生, 禚喜准, 淡永, 等, 2021. 页岩储层水平最小主应力实测与分布规律[J]. 中国石油大学学报(自然科学版), 2021, 45(5): 80-87.
    [53]
    田仁飞, 李山, 刘涛, 等, 2024. 基于XGBoost算法的vP/vS预测及其在储层检测中的应用[J]. 石油地球物理勘探, 59(4): 653-663. doi: 10.13810/j.cnki.issn.1000-7210.2024.04.001
    [54]
    王俊, 曹俊兴, 赵爽, 等, 2022. 基于深度混合神经网络的横波速度反演预测方法[J]. 中国科学: 地球科学, 52(6): 1151-1169.
    [55]
    王濡岳, 胡宗全, 周彤, 等, 2021. 四川盆地及其周缘五峰组-龙马溪组页岩裂缝发育特征及其控储意义[J]. 石油与天然气地质, 42(6): 1295-1306. doi: 10.11743/ogg20210605
    [56]
    汪凯明, 2023. 川东南盆缘复杂构造区深层页岩气富集特征[J]. 天然气地球科学, 34(2): 334-348. doi: 10.11764/j.issn.1672-1926.2022.09.006
    [57]
    夏宏泉, 彭梦, 宋二超, 2019. 岩石各向异性Biot系数的获取方法及应用[J]. 测井技术, 43(5): 478-483. doi: 10.16489/j.issn.1004-1338.2019.05.007
    [58]
    张冰, 王晓婷, 徐福颖, 等, 2025. 基于XGBoost的孔隙压力预测方法研究[J]. 地球物理学进展, 40(2): 541-555. doi: 10.6038/pg2025JJ0121
    [59]
    张金才, 亓原昌, 2020. 地应力对页岩储层开发的影响与对策[J]. 石油与天然气地质, 41(4): 776-783, 799. doi: 10.11743/ogg20200411
    [60]
    张金川, 汪宗余, 聂海宽, 等, 2008. 页岩气及其勘探研究意义[J]. 现代地质, 22(4): 640-646. doi: 10.11817/j.issn.1672-7207.2021.10.015
    [61]
    张培先, 高全芳, 何希鹏, 等, 2023. 南川地区龙马溪组页岩气地应力场特征及对产量影响分析[J]. 油气地质与采收率, 30(4): 55-65. doi: 10.13673/j.pgre.202208024
    [62]
    赵金洲, 雍锐, 胡东风, 等, 2024. 中国深层—超深层页岩气压裂: 问题、挑战与发展方向[J]. 石油学报, 45(1): 295-311. doi: 10.7623/syxb202401017
    [63]
    赵文智, 董大忠, 李建忠, 等, 2012. 中国页岩气资源潜力及其在天然气未来发展中的地位[J]. 中国工程科学, 14(7): 46-52.
    [64]
    中华人民共和国国土资源部, 2015. 岩石物理力学性质试验规程第20部分: 岩石体密度试验: DZ/T 0276.20—2015 [S]. 北京: 中国标准出版社.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    Figures(12)  / Tables(4)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (85) PDF downloads(94) Cited by()
    Proportional views
    Related

    Website Copyright © Journal of Geomechanics  京ICP备18031784号  Total visits：

    Supported by: Beijing Renhe Information Technology Co., Ltd.    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return