1887

Abstract

Summary

Like many of the promised technological marvels we may have expected by 2020, automated seismic data processing and imaging remains stubbornly out of reach. The explosion in the widespread use of ML based algorithms has the potential to significantly alter the way seismic processing and imaging projects are undertaken. However, as well as much remaining technological development there are significant non-technical barriers (often economic and psychological) that hinder the widespread adoption of these approaches. To better understand these barriers, we present three examples of recent technological development that are intended to reduce human project time and improve turnaround and discuss the path and landscape required for widespread adoption of technologies of this type.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202130006
2021-02-23
2024-04-29
Loading full text...

Full text loading...

References

  1. Cobo, Y., Calderon, C., Felicio, R. and Wang, C.
    , 2020. FWI velocity model building using sparse nodes in a salt play basin. SEG Annual Meeting, workshop w-11.
    [Google Scholar]
  2. Jones, I.F.
    , 2020. Tutorial: a geophysical perspective on machine learning. First Break, in- press
    [Google Scholar]
  3. Minh, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M.A.
    (2013). Playing Atari with Deep Reinforcement Learning.ArXiv, abs/1312.5602.
  4. Walpole, J., Hallett, T., Brown, E. and Brittan, J.
    , 2020. Visual Identification of Noisy Seismic Records with Machine Learning. Conference Proceedings, 82nd EAGE Annual Conference & Exhibition Workshop Programme, Dec 2020, Volume 2020.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202130006
Loading
/content/papers/10.3997/2214-4609.202130006
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