IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i13p4765-d851268.html
   My bibliography  Save this article

Optimization of Critical Parameters of Deep Learning for Electrical Resistivity Tomography to Identifying Hydrate

Author

Listed:
  • Yang Liu

    (School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China
    National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing 100028, China)

  • Changchun Zou

    (School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China
    National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing 100028, China)

  • Qiang Chen

    (Key Laboratory of Gas Hydrate, Ministry of Natural Resources, Qingdao Institute of Marine Geology, Qingdao 266071, China
    Laboratory for Marine Mineral Resources, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266071, China)

  • Jinhuan Zhao

    (Key Laboratory of Gas Hydrate, Ministry of Natural Resources, Qingdao Institute of Marine Geology, Qingdao 266071, China
    Laboratory for Marine Mineral Resources, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266071, China)

  • Caowei Wu

    (School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China
    National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing 100028, China)

Abstract

As a new energy source, gas hydrates have attracted worldwide attention, but their exploration and development face enormous challenges. Thus, it has become increasingly crucial to identify hydrate distribution accurately. Electrical resistivity tomography (ERT) can be used to detect the distribution of hydrate deposits. An ERT inversion network (ERTInvNet) based on a deep neural network (DNN) is proposed, with strong learning and memory capabilities to solve the ERT nonlinear inversion problem. 160,000 samples about hydrate distribution are generated by numerical simulation, of which 10% are used for testing. The impact of different deep learning parameters (such as loss function, activation function, and optimizer) on the performance of ERT inversion is investigated to obtain a more accurate hydrate distribution. When the Logcosh loss function is enabled in ERTInvNet, the average correlation coefficient (CC) and relative error (RE) of all samples in the test sets are 0.9511 and 0.1098. The results generated by Logcosh are better than MSE, MAE, and Huber. ERTInvNet with Selu activation function can better learn the nonlinear relationship between voltage and resistivity. Its average CC and RE of all samples in the test set are 0.9449 and 0.2301, the best choices for Relu, Selu, Leaky_Relu, and Softplus. Compared with Adadelta, Adagrad, and Aadmax, Adam has the best performance in ERTInvNet with the optimizer. Its average CC and RE of all samples in the test set are 0.9449 and 0.2301, respectively. By optimizing the critical parameters of deep learning, the accuracy of ERT in identifying hydrate distribution is improved.

Suggested Citation

  • Yang Liu & Changchun Zou & Qiang Chen & Jinhuan Zhao & Caowei Wu, 2022. "Optimization of Critical Parameters of Deep Learning for Electrical Resistivity Tomography to Identifying Hydrate," Energies, MDPI, vol. 15(13), pages 1-17, June.
    • Handle: RePEc:gam:jeners:v:15:y:2022:i:13:p:4765-:d:851268
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/13/4765/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/15/13/4765/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sun, Yi-Fei & Zhong, Jin-Rong & Chen, Guang-Jin & Cao, Bo-Jian & Li, Rui & Chen, Dao-Yi, 2021. "A new approach to efficient and safe gas production from unsealed marine hydrate deposits," Applied Energy, Elsevier, vol. 282(PB).
    2. Jinhuan Zhao & Changling Liu & Qiang Chen & Changchun Zou & Yang Liu & Qingtao Bu & Jiale Kang & Qingguo Meng, 2022. "Experimental Investigation into Three-Dimensional Spatial Distribution of the Fracture-Filling Hydrate by Electrical Property of Hydrate-Bearing Sediments," Energies, MDPI, vol. 15(10), pages 1-12, May.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Francesco Grimaccia & Marco Montini & Alessandro Niccolai & Silvia Taddei & Silvia Trimarchi, 2022. "A Machine Learning-Based Method for Modelling a Proprietary SO 2 Removal System in the Oil and Gas Sector," Energies, MDPI, vol. 15(23), pages 1-15, December.

    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. Xie, Yan & Zhu, Yu-Jie & Cheng, Li-Wei & Zheng, Tao & Zhong, Jin-Rong & Xiao, Peng & Sun, Chang-Yu & Chen, Guang-Jin & Feng, Jing-Chun, 2023. "The coexistence of multiple hydrates triggered by varied H2 molecule occupancy during CO2/H2 hydrate dissociation," Energy, Elsevier, vol. 262(PA).
    2. Zhu, Yi-Jian & Chu, Yan-Song & Huang, Xing & Wang, Ling-Ban & Wang, Xiao-Hui & Xiao, Peng & Sun, Yi-Fei & Pang, Wei-Xin & Li, Qing-Ping & Sun, Chang-Yu & Chen, Guang-Jin, 2023. "Stability of hydrate-bearing sediment during methane hydrate production by depressurization or intermittent CO2/N2 injection," Energy, Elsevier, vol. 269(C).
    3. Ouyang, Qian & Pandey, Jyoti Shanker & von Solms, Nicolas, 2022. "Insights into multistep depressurization of CH4/CO2 mixed hydrates in unconsolidated sediments," Energy, Elsevier, vol. 260(C).
    4. Liu, Zaixing & Li, Yanghui & Wang, Jiguang & Zhang, Mengmeng & Liu, Weiguo & Lang, Chen & Song, Yongchen, 2022. "Rheological investigation of hydrate slurry with marine sediments for hydrate exploitation," Energy, Elsevier, vol. 259(C).
    5. Choi, Wonjung & Mok, Junghoon & Lee, Jonghyuk & Lee, Yohan & Lee, Jaehyoung & Sum, Amadeu K. & Seo, Yongwon, 2022. "Effective CH4 production and novel CO2 storage through depressurization-assisted replacement in natural gas hydrate-bearing sediment," Applied Energy, Elsevier, vol. 326(C).
    6. Dong, Bao-Can & Xiao, Peng & Sun, Yi-Fei & Kan, Jing-Yu & Yang, Ming-Ke & Peng, Xiao-Wan & Sun, Chang-Yu & Chen, Guang-Jin, 2022. "Coupled flow and geomechanical analysis for gas production from marine heterogeneous hydrate-bearing sediments," Energy, Elsevier, vol. 255(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:gam:jeners:v:15:y:2022:i:13:p:4765-:d:851268. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.