Rapid fault extraction from seismic images via deep learning

Dingkun ZHU, Chengyu ZHENG, Weiming WANG, Haoran XIE, Gary CHENG, Fu Lee WANG*, Mingqiang WEI

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)


Using deep learning to automatically and quickly extract faults from seismic images is of practical significance. An improved U-Net algorithm is proposed by reducing convolutional layers, designing skip connections, enforcing deep supervision, and improving the loss function and learning rate to build a new model. In the operation, the feature map parameters in the network are further revised, the number of training iterations is increased, a callback function is added, and the parameter adjustment training consumes less time and space and has higher accuracy. Experiments on real public datasets show that the improved network can limit the time required to extract a 128 × 128 × 128 three-dimensional image within 200 ms, which not only requires less time and computing power than existing methods but also has an extraction accuracy as high as 97.6%.
Original languageEnglish
Article number051423
JournalJournal of Electronic Imaging
Issue number5
Early online date3 Aug 2022
Publication statusPublished - 3 Aug 2022

Bibliographical note

Funding Information:
The authors would like to thank the anonymous reviewers for their valuable suggestions. The work described in this paper was supported by the Katie Shu Sui Pui Charitable Trust—Academic Publication Fellowship (Grant No. KSPF2019-02), Hong Kong Metropolitan University.

Publisher Copyright:
© 2022 SPIE and IS&T.


  • deep learning
  • deep supervision
  • fault extraction
  • seismic images
  • three-dimensional U-Net


Dive into the research topics of 'Rapid fault extraction from seismic images via deep learning'. Together they form a unique fingerprint.

Cite this