1887

Abstract

Summary

Deep learning has the potential to estimate velocity models directly from shot gathers, which would reduce the turn-around time of seismic inversion. Our study addresses two challenges in implementing deep learning techniques for seismic inversion: the practical generation of a large amount of training data and the search for the best neural network architecture. First, we propose a flexible system which parametrically generates velocity models to create a large-scale, complex and fully synthetic training dataset, without using a target subsurface model. Using this system, we created 300,000 synthetic velocity models for our experiments. Second, we employ neural architecture search techniques to design a suitable neural network using Optuna, an automatic hyperparameter optimisation framework. We incorporated the residual network into an encoder–decoder model and optimised its architecture. Thus, we obtained an optimal neural network model consisting of more than 100 hidden layers. We evaluated our model using the Marmousi2 model and the 1994 Amoco statics test dataset. The model demonstrated comprehensible estimations of the benchmark velocity models.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202112777
2021-10-18
2021-12-01
Loading full text...

Full text loading...

References

  1. Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M.
    [2019] Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD Ί9), 2623–2631.
    [Google Scholar]
  2. He, K., Zhang, X., Ren, S., and Sun, J.
    [2016] Deep residual learning for image recognition. 20Ί6 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.
    [Google Scholar]
  3. Kaufman, S., Rosset, S., Perlich, C., and Stitelman, O.
    [2012] Leakage in data mining: Formulation, detection, and avoidance. ACM Transactions on Knowledge Discovery from Data, 6(4), article 15.
    [Google Scholar]
  4. Kazei, V., Ovcharenko, O., Plotnitskii, P., Peter, D., Zhang, X., and Alkhalifah, T.
    [2020] Deep learning tomography by mapping full seismic waveforms to vertical velocity profiles. 82nd EAGE Annual Conference & Exhibition Workshop Programme, 1–5.
    [Google Scholar]
  5. Li, S., Liu, B., Ren, Y., Chen, Y., Yang, S., Wang, Y., and Jiang, P.
    [2019] Deep-learning inversion of seismic data. IEEE Transactions on Geoscience and Remote Sensing, 58(3), 2135–2149.
    [Google Scholar]
  6. Liu, C., Sun, M., Dai, N., Wu, W., and Fu, H.
    [2020] Inverting elastic model properties using ResNet. First EAGE Digitalization Conference and Exhibition, 1–5.
    [Google Scholar]
  7. Martin, G. S., Wiley, R., and Marfurt, K. J.
    [2006] Marmousi2: An elastic upgrade for Marmousi. The Leading Edge, 25(2): 156–166.
    [Google Scholar]
  8. Wang, L., Meng, D., Wu, B., and Liu, N.
    [2020] Seismic inversion via closed-loop fully convolutional residual network and transfer learning. SEG Technical Program Expanded Abstracts 2020, 1521–1525.
    [Google Scholar]
  9. Zhang, Z. and Lin, Y.
    [2020] Data-driven seismic waveform inversion: A study on the robustness and generalization. IEEE Transactions on Geoscience and Remote Sensing, 58(10), 6900–6913.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202112777
Loading
/content/papers/10.3997/2214-4609.202112777
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error