IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v285y2023ics0360544223026051.html
   My bibliography  Save this article

Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing

Author

Listed:
  • Min, Chao
  • Wen, Guoquan
  • Gou, Liangjie
  • Li, Xiaogang
  • Yang, Zhaozhong

Abstract

Machine learning approaches are widely studied in the production prediction of CBM wells after hydraulic fracturing, but rarely used in practice due to the low generalization ability and the lack of interpretability. A novel methodology is proposed to discover the latent causality existed in the observed data of CBM wells, which is aimed at finding an indirect way to interpret the machine learning models. Based on the theory of causal discovery, a causal graph is derived with explicit variables, including the input, output and treatment variables. The proposed method can capture the underlying nonlinear relationship between the factors and the output, which remedies the limitation of the traditional machine learning routines based on the correlation analysis of factors. The experiment on the data of a CBM reservoir shows that the detected causal relationship between the production and the geological/engineering factors, is coincident with the actual physical mechanism. Meanwhile, compared with the traditional methods, the interpretable machine learning models have better performance in predicting production capability, averaging 5%–31% improvement in accuracy. An application is presented to optimize the fracturing scheme and validated by numerical simulation, which shows the ineterpretable method can improve the stimulated production in a high extent.

Suggested Citation

  • Min, Chao & Wen, Guoquan & Gou, Liangjie & Li, Xiaogang & Yang, Zhaozhong, 2023. "Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing," Energy, Elsevier, vol. 285(C).
  • Handle: RePEc:eee:energy:v:285:y:2023:i:c:s0360544223026051
    DOI: 10.1016/j.energy.2023.129211
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544223026051
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.energy.2023.129211?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Wente Niu & Jialiang Lu & Yuping Sun, 2021. "A Production Prediction Method for Shale Gas Wells Based on Multiple Regression," Energies, MDPI, vol. 14(5), pages 1-11, March.
    2. Liu, Huihu & Sang, Shuxun & Wang, Geoff G.X. & Li, Yangmin & Li, Mengxi & Liu, Shiqi, 2012. "Evaluation of the synergetic gas-enrichment and higher-permeability regions for coalbed methane recovery with a fuzzy model," Energy, Elsevier, vol. 39(1), pages 426-439.
    3. Li, Yujie & Zhai, Cheng & Xu, Jizhao & Sun, Yong & Yu, Xu, 2022. "Feasibility investigation of enhanced coalbed methane recovery by steam injection," Energy, Elsevier, vol. 255(C).
    4. Lan, Wenjian & Wang, Hanxiang & Liu, Qihu & Zhang, Xin & Chen, Jingkai & Li, Ziling & Feng, Kun & Chen, Shengshan, 2021. "Investigation on the microwave heating technology for coalbed methane recovery," Energy, Elsevier, vol. 237(C).
    5. Fan, Zhanglei & Fan, Gangwei & Zhang, Dongsheng & Zhang, Lei & Zhang, Shuai & Liang, Shuaishuai & Yu, Wei, 2021. "Optimal injection timing and gas mixture proportion for enhancing coalbed methane recovery," Energy, Elsevier, vol. 222(C).
    6. Nie, Bin & Sun, Sijia, 2023. "Thermal recovery of coalbed methane: Modeling of heat and mass transfer in wellbores," Energy, Elsevier, vol. 263(PD).
    7. Vishal, V. & Singh, Lokendra & Pradhan, S.P. & Singh, T.N. & Ranjith, P.G., 2013. "Numerical modeling of Gondwana coal seams in India as coalbed methane reservoirs substituted for carbon dioxide sequestration," Energy, Elsevier, vol. 49(C), pages 384-394.
    8. Guo, Zixi & Zhao, Jinzhou & You, Zhenjiang & Li, Yongming & Zhang, Shu & Chen, Yiyu, 2021. "Prediction of coalbed methane production based on deep learning," Energy, Elsevier, vol. 230(C).
    9. Vishal, Vikram & Mahanta, Bankim & Pradhan, S.P. & Singh, T.N. & Ranjith, P.G., 2018. "Simulation of CO2 enhanced coalbed methane recovery in Jharia coalfields, India," Energy, Elsevier, vol. 159(C), pages 1185-1194.
    10. Du, Shuyi & Wang, Jiulong & Wang, Meizhu & Yang, Jiaosheng & Zhang, Cong & Zhao, Yang & Song, Hongqing, 2023. "A systematic data-driven approach for production forecasting of coalbed methane incorporating deep learning and ensemble learning adapted to complex production patterns," Energy, Elsevier, vol. 263(PE).
    11. Luo, D.K. & Dai, Y.J. & Xia, L.Y., 2011. "Economic evaluation based policy analysis for coalbed methane industry in China," Energy, Elsevier, vol. 36(1), pages 360-368.
    12. Wang, Chenghong & Shen, Qie & Zhang, Jie & Qiao, Xin & Yu, Hongyuan & Shen, Keyi & Sun, Daming, 2023. "Study on a coalbed methane liquefaction system based on thermoacoustic refrigeration method," Energy, Elsevier, vol. 262(PB).
    13. Fan, Cheng & Xiao, Fu & Yan, Chengchu & Liu, Chengliang & Li, Zhengdao & Wang, Jiayuan, 2019. "A novel methodology to explain and evaluate data-driven building energy performance models based on interpretable machine learning," Applied Energy, Elsevier, vol. 235(C), pages 1551-1560.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wang, Ziwei & Qin, Yong & Shen, Jian & Li, Teng & Zhang, Xiaoyang & Cai, Ying, 2022. "A novel permeability prediction model for coal based on dynamic transformation of pores in multiple scales," Energy, Elsevier, vol. 257(C).
    2. Zhou, Lijun & Zhou, Xihua & Fan, Chaojun & Bai, Gang & Yang, Lei & Wang, Yiqi, 2023. "Modelling of flue gas injection promoted coal seam gas extraction incorporating heat-fluid-solid interactions," Energy, Elsevier, vol. 268(C).
    3. Guo, Zixi & Zhao, Jinzhou & You, Zhenjiang & Li, Yongming & Zhang, Shu & Chen, Yiyu, 2021. "Prediction of coalbed methane production based on deep learning," Energy, Elsevier, vol. 230(C).
    4. Zhang, Hewei & Shen, Jian & Wang, Geoff & Li, Kexin & Fang, Xiaojie & Jing, Qu, 2023. "Differential heat transfer characteristics of coal macerals and their control mechanism: At the mesoscale," Energy, Elsevier, vol. 280(C).
    5. Du, Shuyi & Wang, Meizhu & Yang, Jiaosheng & Zhao, Yang & Wang, Jiulong & Yue, Ming & Xie, Chiyu & Song, Hongqing, 2023. "An enhanced prediction framework for coalbed methane production incorporating deep learning and transfer learning," Energy, Elsevier, vol. 282(C).
    6. Li, Yujie & Zhai, Cheng & Xu, Jizhao & Yu, Xu & Sun, Yong & Cong, Yuzhou & Tang, Wei & Zheng, Yangfeng, 2023. "Effects of steam treatment on the internal moisture and physicochemical structure of coal and their implications for coalbed methane recovery," Energy, Elsevier, vol. 270(C).
    7. Dai, Shijie & Xu, Jiang & Jia, Li & Chen, Jieren & Yan, Fazhi & Chen, Yuexia & Peng, Shoujian, 2023. "On the 3D fluid behavior during CBM coproduction in a multi pressure system: Insights from experimental analysis and mathematical models," Energy, Elsevier, vol. 283(C).
    8. Zhang, Baoxin & Deng, Ze & Fu, Xuehai & Yu, Kun & Zeng, Fanhua (Bill), 2023. "An experimental study on the effects of acidization on coal permeability: Implications for the enhancement of coalbed methane production," Energy, Elsevier, vol. 280(C).
    9. Zhou, Lijun & Zhou, Xihua & Fan, Chaojun & Bai, Gang, 2022. "Coal permeability evolution triggered by variable injection parameters during gas mixture enhanced methane recovery," Energy, Elsevier, vol. 252(C).
    10. Fan, Lurong & Ma, Ning & Zhang, Wen, 2023. "Multi-stakeholder equilibrium-based subsidy allocation mechanism for promoting coalbed methane scale extraction-utilization," Energy, Elsevier, vol. 277(C).
    11. Huang, Qiang & Shen, Jian & Zhang, Bing & Zhao, Gang & Cheng, Ming & Cai, Ying & Li, Chao, 2023. "Real-time monitoring of coalbed methane production network following liquid CO2 injection in a low-efficiency well network: Response to gas and water production characteristics," Energy, Elsevier, vol. 285(C).
    12. Zhang, Kai & Lau, Hon Chung & Bokka, Harsha Kumar & Hadia, Nanji J., 2022. "Decarbonizing the power and industry sectors in India by carbon capture and storage," Energy, Elsevier, vol. 249(C).
    13. Ningning Zhao & Tianfu Xu & Kairan Wang & Hailong Tian & Fugang Wang, 2018. "Experimental study of physical‐chemical properties modification of coal after CO2 sequestration in deep unmineable coal seams," Greenhouse Gases: Science and Technology, Blackwell Publishing, vol. 8(3), pages 510-528, June.
    14. Chen, Zhelun & O’Neill, Zheng & Wen, Jin & Pradhan, Ojas & Yang, Tao & Lu, Xing & Lin, Guanjing & Miyata, Shohei & Lee, Seungjae & Shen, Chou & Chiosa, Roberto & Piscitelli, Marco Savino & Capozzoli, , 2023. "A review of data-driven fault detection and diagnostics for building HVAC systems," Applied Energy, Elsevier, vol. 339(C).
    15. Fu, Shenguang & Wang, Liang & Li, Shuohao & Ni, Sijia & Cheng, Yuanping & Zhang, Xiaolei & Liu, Shimin, 2024. "Re-thinking methane storage mechanism in highly metamorphic coalbed reservoirs — A molecular simulation considering organic components," Energy, Elsevier, vol. 293(C).
    16. Jia, Kunqi & Guo, Ge & Xiao, Jucheng & Zhou, Huan & Wang, Zhihua & He, Guangyu, 2019. "Data compression approach for the home energy management system," Applied Energy, Elsevier, vol. 247(C), pages 643-656.
    17. Liu, Wei & Han, Dongyang & Xu, Hao & Chu, Xiangyu & Qin, Yueping, 2023. "Modeling of gas migration in a dual-porosity coal seam around a borehole: the effects of three types of driving forces in coal matrix," Energy, Elsevier, vol. 264(C).
    18. Chengwang Wang & Zixi Guo & Lifeng Zhang & Yunwei Kang & Zhenjiang You & Shuguang Li & Yubin Wang & Huaibin Zhen, 2022. "3D Fracture Propagation Simulation and Pressure Decline Analysis Research for I-Shaped Fracture of Coalbed," Energies, MDPI, vol. 15(16), pages 1-20, August.
    19. Liang, Xinbin & Zhu, Xu & Chen, Siliang & Jin, Xinqiao & Xiao, Fu & Du, Zhimin, 2023. "Physics-constrained cooperative learning-based reference models for smart management of chillers considering extrapolation scenarios," Applied Energy, Elsevier, vol. 349(C).
    20. Jeeyoung Lim & Joseph J. Kim & Sunkuk Kim, 2021. "A Holistic Review of Building Energy Efficiency and Reduction Based on Big Data," Sustainability, MDPI, vol. 13(4), pages 1-18, February.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:285:y:2023:i:c:s0360544223026051. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.