1887

Abstract

Summary

We present AI-drive workflow for automatic interpretation of large seismic volumes. The workflow is applied to an offshore Abu Dhabi area of 15000 km2. First, we show the fault detection results for the low-magnitude faults of strike-slip type by the fine-tuning of the DNN. The fault detection is conducted in a comprehensive way with structure-enhancing denoise for feature preservation. Second, we illustrate that automated horizon interpretation and flattening allows us to observe a variety of geological features, which are difficult to target otherwise. Finally, we show how the structure-enhancing denoise improves the geological feature identification by an example of channel detection. We further plan to apply the suggested workflow for a larger data set covering the whole Abu Dhabi offshore region.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2024101038
2024-06-10
2026-01-19
Loading full text...

Full text loading...

References

  1. Lomask, J., Guitton, A., Fomel, S., Claerbout, J. and Valenciano, A.A. [2006] Flattening without picking.Geophysics, 71(4), P13–P20.
    [Google Scholar]
  2. Noufal, A., Obaid, K. and Ali, M.Y. [2016] Tectonic Map of Abu Dhabi, UAE.Abu Dhabi International Petroleum Exhibition and Conference, SPE-183108-MS.
    [Google Scholar]
  3. Pham, N., Fomel, S. and Dunlap, D., [2019]. Automatic channel detection using deep learning.Interpretation, 7(3), SE43–SE50.
    [Google Scholar]
  4. Ronneberger, O., Fischer, P. and Brox, T. [2015] U-net: Convolutional networks for biomedical image segmentation.Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Interventions, MICCAI Society, 234–241.
    [Google Scholar]
  5. Sancheti, O. and Hou, S. [2023] A generalized U-Net for injectite detection.84th EAGE Annual Conference & Exhibition, Extended Abstracts.
    [Google Scholar]
  6. Wu, X., Geng, Z., Shi, Y., Pham, N., Fomel, S. and Caumon, G. [2020] Building realistic structure models to train convolutional neural networks for seismic structural interpretation.Geophysics, 85(4), WA27–WA39.
    [Google Scholar]
  7. Wu, X., Liang, L., Shi, Y. and Fomel, S. [2019] FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation.Geophysics, 84(3), IM35–IM45.
    [Google Scholar]
/content/papers/10.3997/2214-4609.2024101038
Loading
/content/papers/10.3997/2214-4609.2024101038
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