IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i12p3650-d577822.html
   My bibliography  Save this article

Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples

Author

Listed:
  • Zhe Yan

    (Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China)

  • Zheng Zhang

    (Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China)

  • Shaoyong Liu

    (Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China)

Abstract

Fault interpretation is an important part of seismic structural interpretation and reservoir characterization. In the conventional approach, faults are detected as reflection discontinuity or abruption and are manually tracked in post-stack seismic data, which is time-consuming. In order to improve efficiency, a variety of automatic fault detection methods have been proposed, among which widespread attention has been given to deep learning-based methods. However, deep learning techniques require a large amount of marked seismic samples as a training dataset. Although the amount of synthetic seismic data can be guaranteed and the labels are accurate, the difference between synthetic data and real data still exists. To overcome this drawback, we apply a transfer learning strategy to improve the performance of automatic fault detection by deep learning methods. We first pre-train a deep neural network with synthetic seismic data. Then we retrain the network with real seismic samples. We use a random sample consensus (RANSAC) method to obtain real seismic samples and generate corresponding labels automatically. Three real 3D examples are included to demonstrate that the fault detection accuracy of the pre-trained network models can be greatly improved by retraining the network with a few amount of real seismic samples.

Suggested Citation

  • Zhe Yan & Zheng Zhang & Shaoyong Liu, 2021. "Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples," Energies, MDPI, vol. 14(12), pages 1-13, June.
  • Handle: RePEc:gam:jeners:v:14:y:2021:i:12:p:3650-:d:577822
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/12/3650/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/14/12/3650/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Shulin Pan & Ke Yan & Haiqiang Lan & José Badal & Ziyu Qin, 2020. "A Sparse Spike Deconvolution Algorithm Based on a Recurrent Neural Network and the Iterative Shrinkage-Thresholding Algorithm," Energies, MDPI, vol. 13(12), pages 1-13, June.
    2. Shu Li & Xi Yang & Haonan Liu & Yuwei Cai & Zhenming Peng, 2020. "Seismic Data Denoising Based on Sparse and Low-Rank Regularization," Energies, MDPI, vol. 13(2), pages 1-16, January.
    3. Jianpeng Yao & Qingbin Liu & Wenling Liu & Yuyang Liu & Xiaodong Chen & Mao Pan, 2020. "3D Reservoir Geological Modeling Algorithm Based on a Deep Feedforward Neural Network: A Case Study of the Delta Reservoir of Upper Urho Formation in the X Area of Karamay, Xinjiang, China," Energies, MDPI, vol. 13(24), pages 1-14, December.
    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. Shaoyong Liu & Wenting Zhu & Zhe Yan & Peng Xu & Huazhong Wang, 2021. "An Effective Acoustic Impedance Imaging Based on a Broadband Gaussian Beam Migration," Energies, MDPI, vol. 14(14), pages 1-12, July.

    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:14:y:2021:i:12:p:3650-:d:577822. 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.