Paper Titles
Finite Element Analysis on Seismic Behavior of Typical Residence in Yunnan
p.1476
Ground Motion Prediction Equation for Lanzhou Region from Small Earthquake Records
p.1480
Characteristic Analysis of 3.11 Seismic Waves
p.1484
Comparison of Stiffness Degradation of Special-Shaped Column and Rectangular Column Structure in Earthquake
p.1492
Multi-Attributes and Neural Network-Based Fault Detection in 3D Seismic Interpretation
p.1497
The Improved Elastic Stiffness Method Based on Energy Dissipation System with Buckling Restrained Brace Design
p.1503
Reservoir Induced Seismicity Types in the Three Gorges Project
p.1508
Assessment Model Research of Seismic Damage for Clear Water Tanks in Water Supply System
p.1512
Characteristics and Mechanics of Earthquake Damage of Brick-Wood Building
p.1517

Multi-Attributes and Neural Network-Based Fault Detection in 3D Seismic Interpretation

Article Preview

Abstract:

Seismic attributes have been widely used in seismic object detection. While no unique attribute is expected to perfectly identify the targeted object, various attributes contributing to the same purpose should be utilized simultaneously when performing detection. Artificial neural network has been successfully applied in seismic object detection by combining multiple attributes into a single object-sensitive attribute. An optimized neural network fault detection approach was introduced by a case study from Stratton field, south Texas, United States. Results indicate that the new produced fault probability attribute could suppress the surrounding noises and highlight the faults. Application of ant-tracking to the fault-cube shows more convincible results than to individual attributes. In addition, several potential cross-strike fractures increase the structural complexity. The neural network-based fault detection contributes to better structural interpretation and is of great significance to hydrocarbon exploration, especially in area with complex fault system.

You might also be interested in these eBooks
Civil, Structural and Environmental Engineering View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 838-841)

Pages:

1497-1502

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.838-841.1497

Citation:

Cite this paper

Online since:

November 2013

Authors:

Zhi Hong Zheng*, Payam Kavousi, Hai Bin Di

Keywords:

Ant-Tracking, Fault Detection, Neural Network (NN), Seismic Attribute, Similarity

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] A. Chehrazi, H. Rahimpour-Bonab and M.R. Rezaee: Petroleum Geoscience, Vol. 19 (2013), p.169.

Google Scholar

[2] K. Tingdahl and M. De Rooij: Geophyical Prospecting, Vol. 53 (2005), p.533.

Google Scholar

[3] M. Bahorich and S. Farmer: The Leading Edge, Vol. 14 (1995), p.1053.

Google Scholar

[4] K.J. Marfurt, R.L. Kirlin, S.L. Farmer and M.S. Bahorich: Geophysics, Vol. 63 (1998), p.1150.

Google Scholar

[5] A. Roberts: First Break, Vol. 19 (2001), p.85.

Google Scholar

[6] M.E. Sigismondi and J.C. Soldo: The Leading Edge, Vol. 22 (2003), p.1122.

Google Scholar

[7] P. Meldahl, R. Heggland, B. Bril and P. De Groot: The Leading Edge, Vol. 20 (2001), p.474.

DOI: 10.1190/1.1438976

Google Scholar

[8] F. Brouwer and A. Huck: 31st. Annual GCSSEPM Foundation Bob F. Perkins Research Conference (Houston , Texas, United States, 2011). Vol. 31, p.496.

Google Scholar

[9] M. De Rooij and K. Tingdahl: The Leading Edge, Vol. 21 (2002), p.1050.

Google Scholar

[10] S. Chopra and K. Marfurt: The Leading Edge, Vol. 26 (2007), p.404.

Google Scholar