The Use of 3D Convolutional Autoencoder in Fault and Fracture Network Characterization

Conventional pattern recognition methods directly use 1D poststack data or 2D prestack data for the statistical pattern recognition of fault and fracture network, thereby ignoring the spatial structure information in 3D seismic data. As a result, the generated fault and fracture network is not disti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Geofluids Ročník 2021; s. 1 - 11
Hlavní autoři: Xu, Feng, Li, Zhiyong, Wen, Bo, Huang, Youhui, Wang, Yaojun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Chichester Hindawi 2021
John Wiley & Sons, Inc
Wiley
Témata:
Cluster analysis
Clustering
Coders
Convolution
Deep learning
Dimensions
Fault lines
Feature extraction
Feature selection
Fractured reservoirs
Geology
Neural networks
Pattern recognition
Principal components analysis
Seismic activity
Seismic data
Seismic simulators
Seismological data
Teaching methods
Training
Wavelet transforms
China
ISSN:1468-8115, 1468-8123
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Conventional pattern recognition methods directly use 1D poststack data or 2D prestack data for the statistical pattern recognition of fault and fracture network, thereby ignoring the spatial structure information in 3D seismic data. As a result, the generated fault and fracture network is not distinguishable and has poor continuity. In this paper, a fault and fracture network characterization method based on 3D convolutional autoencoder is proposed. First, in the autoencoder training frame, 3D prestack data are used as input, and the 3D convolution operation is used to mine the spatial structure information to the maximum and gradually reduce the spatial dimension of the input. Then, the residual network is used to recover the input’s details and the corresponding spatial dimension. Lastly, the hidden features extracted by the encoders are recognized via k-means, SOM, and two-step clustering analysis. The validity of the method is verified by testing the seismic simulation data and applying real seismic data. The 3D convolution can directly process the seismic data and maximize the prestack texture attributes and spatial structure information provided by 3D seismic data without dimensionality reduction and other preprocessing operations. The interleaving convolution layer and residual block overcome low learning and accuracy rates due to the deepening of networks.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1468-8115
1468-8123
DOI:10.1155/2021/6650823