IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v365y2024ics0306261924005622.html
   My bibliography  Save this article

Physics-informed machine learning for noniterative optimization in geothermal energy recovery

Author

Listed:
  • Yan, Bicheng
  • Gudala, Manojkumar
  • Hoteit, Hussein
  • Sun, Shuyu
  • Wang, Wendong
  • Jiang, Liangliang

Abstract

Geothermal energy is clean, renewable, and cost-effective and its efficient recovery management mandates optimizing engineering parameters while considering the underpinning physics, typically achieved through computationally intensive simulators. This study proposes a novel physics-informed machine learning (PIML) framework for geothermal reservoir optimization, integrating a data wrangler to process high-fidelity simulations, a forward network for forward predictions, and a control network to optimize engineering decision parameters while maximizing the objective function and satisfying various engineering constraints. The PIML incorporates an improved Hyperbolic-ReLU (HyperReLU) model to predict the produced geothermal fluid temperature robustly. The forward model uses a neural network to predict hyper-parameters of HyperReLU from reservoir model input and estimates the produced fluid temperature and energy. Further, the control network is trained with labels automatically generated by the forward model. During prediction, it can infer optimum decision parameters noniteratively by inputting uncertain reservoir parameters, ensuring it maximizes the objective function. Numerical experiments reveal that the HyperReLU enhances long-term predictive stability, and the forward network can achieve predictions of the produced temperature and energy within errors of 0.53±0.46% and 0.60±0.74%, respectively. We examine PIML to control the produced temperature drops or maximize the total energy recovery. Compared to the differential evolution (DE) optimizer, PIML closely matches DE with a 53.7% increase in total energy while running 5,465 times faster than DE. Moreover, PIML presents great efficiency and accuracy and is scalable for field-scale geothermal well-control design and other similar optimization problems.

Suggested Citation

  • Yan, Bicheng & Gudala, Manojkumar & Hoteit, Hussein & Sun, Shuyu & Wang, Wendong & Jiang, Liangliang, 2024. "Physics-informed machine learning for noniterative optimization in geothermal energy recovery," Applied Energy, Elsevier, vol. 365(C).
    • Handle: RePEc:eee:appene:v:365:y:2024:i:c:s0306261924005622
    DOI: 10.1016/j.apenergy.2024.123179
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924005622
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.123179?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. Ma, Y. & Li, Y.P. & Huang, G.H., 2023. "Planning China’s non-deterministic energy system (2021–2060) to achieve carbon neutrality," Applied Energy, Elsevier, vol. 334(C).
    2. Sun, Alexander Y., 2020. "Optimal carbon storage reservoir management through deep reinforcement learning," Applied Energy, Elsevier, vol. 278(C).
    3. Gkousis, Spiros & Thomassen, Gwenny & Welkenhuysen, Kris & Compernolle, Tine, 2022. "Dynamic life cycle assessment of geothermal heat production from medium enthalpy hydrothermal resources," Applied Energy, Elsevier, vol. 328(C).
    4. Chen, Bailian & Harp, Dylan R. & Lin, Youzuo & Keating, Elizabeth H. & Pawar, Rajesh J., 2018. "Geologic CO2 sequestration monitoring design: A machine learning and uncertainty quantification based approach," Applied Energy, Elsevier, vol. 225(C), pages 332-345.
    5. Kawai, Eiji & Ozawa, Akito & Leibowicz, Benjamin D., 2022. "Role of carbon capture and utilization (CCU) for decarbonization of industrial sector: A case study of Japan," Applied Energy, Elsevier, vol. 328(C).
    6. Gudala, Manojkumar & Govindarajan, Suresh Kumar & Yan, Bicheng & Sun, Shuyu, 2022. "Numerical investigations of the PUGA geothermal reservoir with multistage hydraulic fractures and well patterns using fully coupled thermo-hydro-geomechanical modeling," Energy, Elsevier, vol. 253(C).
    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. Xiao, Ting & Chen, Ting & Ma, Zhiwei & Tian, Hailong & Meguerdijian, Saro & Chen, Bailian & Pawar, Rajesh & Huang, Lianjie & Xu, Tianfu & Cather, Martha & McPherson, Brian, 2024. "A review of risk and uncertainty assessment for geologic carbon storage," Renewable and Sustainable Energy Reviews, Elsevier, vol. 189(PB).
    2. Wu, Hao & Lubbers, Nicholas & Viswanathan, Hari S. & Pollyea, Ryan M., 2021. "A multi-dimensional parametric study of variability in multi-phase flow dynamics during geologic CO2 sequestration accelerated with machine learning," Applied Energy, Elsevier, vol. 287(C).
    3. Chen, Bailian & Pawar, Rajesh J., 2019. "Characterization of CO2 storage and enhanced oil recovery in residual oil zones," Energy, Elsevier, vol. 183(C), pages 291-304.
    4. Cao, Meng & Sharma, Mukul M., 2023. "Effect of fracture geometry, topology and connectivity on energy recovery from enhanced geothermal systems," Energy, Elsevier, vol. 282(C).
    5. Wang, Sen & Qin, Chaoxu & Feng, Qihong & Javadpour, Farzam & Rui, Zhenhua, 2021. "A framework for predicting the production performance of unconventional resources using deep learning," Applied Energy, Elsevier, vol. 295(C).
    6. Sungil Kim & Kyungbook Lee & Minhui Lee & Taewoong Ahn, 2020. "Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation," Energies, MDPI, vol. 13(21), pages 1-19, November.
    7. Zhao, Haitao & Ezeh, Collins I. & Ren, Weijia & Li, Wentao & Pang, Cheng Heng & Zheng, Chenghang & Gao, Xiang & Wu, Tao, 2019. "Integration of machine learning approaches for accelerated discovery of transition-metal dichalcogenides as Hg0 sensing materials," Applied Energy, Elsevier, vol. 254(C).
    8. Bożena Gajdzik & Radosław Wolniak & Wies Grebski, 2023. "Process of Transformation to Net Zero Steelmaking: Decarbonisation Scenarios Based on the Analysis of the Polish Steel Industry," Energies, MDPI, vol. 16(8), pages 1-36, April.
    9. Yunqi Jiang & Huaqing Zhang & Kai Zhang & Jian Wang & Shiti Cui & Jianfa Han & Liming Zhang & Jun Yao, 2022. "Reservoir Characterization and Productivity Forecast Based on Knowledge Interaction Neural Network," Mathematics, MDPI, vol. 10(9), pages 1-22, May.
    10. Li, Hang & Ma, Hongling & Liu, Jiang & Zhu, Shijie & Zhao, Kai & Zheng, Zhuyan & Zeng, Zhen & Yang, Chunhe, 2023. "Large-scale CAES in bedded rock salt: A case study in Jiangsu Province, China," Energy, Elsevier, vol. 281(C).
    11. Amine Tadjer & Reidar B. Bratvold, 2021. "Managing Uncertainty in Geological CO 2 Storage Using Bayesian Evidential Learning," Energies, MDPI, vol. 14(6), pages 1-18, March.
    12. Jin, Wencheng & Atkinson, Trevor A. & Doughty, Christine & Neupane, Ghanashyam & Spycher, Nicolas & McLing, Travis L. & Dobson, Patrick F. & Smith, Robert & Podgorney, Robert, 2022. "Machine-learning-assisted high-temperature reservoir thermal energy storage optimization," Renewable Energy, Elsevier, vol. 197(C), pages 384-397.
    13. Wang, Anlun & Chen, Yinghe & Wei, Jianguang & Li, Jiangtao & Zhou, Xiaofeng, 2023. "Experimental study on the mechanism of five point pattern refracturing for vertical & horizontal wells in low permeability and tight oil reservoirs," Energy, Elsevier, vol. 272(C).
    14. Uddin, Mohammad Jalal, 2023. "Investigating the impulse responses of renewable energy in the context of China: A Bayesian VAR Approach," Renewable Energy, Elsevier, vol. 219(P2).
    15. Mao, Shaowen & Chen, Bailian & Malki, Mohamed & Chen, Fangxuan & Morales, Misael & Ma, Zhiwei & Mehana, Mohamed, 2024. "Efficient prediction of hydrogen storage performance in depleted gas reservoirs using machine learning," Applied Energy, Elsevier, vol. 361(C).
    16. Liu, Tianhao & Tian, Jun & Zhu, Hongyu & Goh, Hui Hwang & Liu, Hui & Wu, Thomas & Zhang, Dongdong, 2023. "Key technologies and developments of multi-energy system: Three-layer framework, modelling and optimisation," Energy, Elsevier, vol. 277(C).
    17. Chen, Guodong & Jiao, Jiu Jimmy & Jiang, Chuanyin & Luo, Xin, 2024. "Surrogate-assisted level-based learning evolutionary search for geothermal heat extraction optimization," Renewable and Sustainable Energy Reviews, Elsevier, vol. 189(PB).
    18. Sun, Alexander Y., 2020. "Optimal carbon storage reservoir management through deep reinforcement learning," Applied Energy, Elsevier, vol. 278(C).
    19. Sterkhov, K.V. & Khokhlov, D.A. & Zaichenko, M.N., 2024. "Zero carbon emission CCGT power plant with integrated solid fuel gasification," Energy, Elsevier, vol. 294(C).
    20. Aryanfar, Yashar & Mohtaram, Soheil & García Alcaraz, Jorge Luis & Sun, HongGuang, 2023. "Energy and exergy assessment and a competitive study of a two-stage ORC for recovering SFGC waste heat and LNG cold energy," Energy, Elsevier, vol. 264(C).

    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:appene:v:365:y:2024:i:c:s0306261924005622. 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.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.