1887

Abstract

Summary

This study explores the use of deep learning, specifically a U-Net model, for automating the interpretation of integrated soil units from 2D ultra-high-resolution (UHR) seismic data in offshore wind farms. The model effectively tracks multiple horizons, providing rapid preliminary interpretations that can be fine-tuned by geologists. It performs particularly well for continuous horizons, such as the bottoms of Units I, II, and V, but encounters challenges when delineating more complex geological structures, such as deep tunnel valleys with multiple generations of channels. Training the model on data from the same investigation area yields better results than using data from different areas, but cross-area training accelerates offshore wind farm development. Future improvements could include the creation of a foundation model trained on extensive UHR seismic datasets, offering more stable seismic pattern recognition and supporting broader applications in wind farm geological modelling.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202521088
2025-10-27
2026-01-13

  • From This Site

    /content/papers/10.3997/2214-4609.202521088
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Di, H., Aseev, A., Wang, S., and Sharma, A. [2025] A New Paradigm of Rapid Seismic Interpretation Powered by Pretrained Seismic Foundation Models. EAGE Annual Conference & Exhibition.
     [Google Scholar]
  2. Di, H., Li, Z., Maniar, H., and Abubakar, A. [2020] Seismic stratigraphy interpretation by deep convolutional neural networks: A semisupervised workflow. GEOPHYSICS, 85(4), WA77–WA86.
     [Google Scholar]
  3. Di, H., Pham, N., and Abubakar, A. [2024] Estimating geotechnical parameters using semisupervised learning: An example from the Dutch offshore wind farm zone. GEOPHYSICS, 89, WA85–WA93.
     [Google Scholar]
  4. Qu, D., Mosegaard, K., Feng, R. and Nielsen, L. [2023] Using a synthetic data trained convolutional neural network for predicting subresolution thin layers from seismic data. Interpretation, 11(2), pp.T339–T347.
     [Google Scholar]
  5. Ramboll-BSH [2023] Geological Report of the Preliminary Investigation of FEP Sites N-9.3.
     [Google Scholar]
  6. Ronneberger, O., Fischer, P. and Brox, T. [2015] U- Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241. Springer.
     [Google Scholar]
  7. Sharma, L., Dalgaard, M.T., Juberó, A.E., Zubkova, A., Nguyen, T.A., Rindom, S., Steding, S., Fuchs, F., Ruhnau, M., Geduhn, M. and Kammann, J. [2024] Geological Model Development for an Offshore Wind farm Site in the German North Sea. Fifth EAGE GET, Vol. 2024, No. 1, pp. 1–4.
     [Google Scholar]
  8. Sheng, H., Wu, X., Si, X., Li, J., Zhang, S., and Duan, X. [2025] Seismic foundation model: A next generation deep-learning model in geophysics. GEOPHYSICS, 90, IM59–IM79.
     [Google Scholar]
  9. Tan, M. and Le, Q. [2019] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 6105–6114.
     [Google Scholar]
  10. Zhao, T., Di, H., and Abubakar, A. [2023] Cascaded Deep Learning for Offshore Wind Farm 2D Seismic Horizon Interpretation. EAGE Annual Conference & Exhibition.
     [Google Scholar]
  11. Zhao, Z. and Zhao, J. [2025] Seismic horizon tracking based on the TransUnet model. GEOPHYSICS, 90, IM1–IM13.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202521088
Loading
Deep Learning-Based Horizon Interpretation on UHRS Data for Offshore Wind - Examples, Challenges and Opportunities
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202521088
/content/papers/10.3997/2214-4609.202521088
/content/papers/10.3997/2214-4609.202521088
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

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