eduzhai > Applied Sciences > Engineering >

Unsupervised seismic facies classification using deep convolutional autoencoder

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 22 pages

Abstract: With the increased size and complexity of seismic surveys, manual labeling ofseismic facies has become a significant challenge. Application of automaticmethods for seismic facies interpretation could significantly reduce the manuallabor and subjectivity of a particular interpreter present in conventionalmethods. A recently emerged group of methods is based on deep neural networks.These approaches are data-driven and require large labeled datasets for networktraining. We apply a deep convolutional autoencoder for unsupervised seismicfacies classification, which does not require manually labeled examples. Thefacies maps are generated by clustering the deep-feature vectors obtained fromthe input data. Our method yields accurate results on real data and providesthem instantaneously. The proposed approach opens up possibilities to analyzegeological patterns in real time without human intervention.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×