Fault recognition is an important section in
seismic interpretation region and there have been many
methods for this technology, but no one can recognize the
fault exactly enough. For this problem, we proposed a new
fault recognition method based on linear regression which
can locate the position of a fault precisely and then extract it
from the seismic section. First, the seismic horizons were
labeled out by the eight adjacent connected component
labeling method as connected regions; second, the horizontal
endpoints of each connected component were found out
based on the column coordinate of the pixels within the
component; finally, the linear regression method based on
least sum of square error was used to generate the direct
line which was used to fit the horizontal endpoints. As a
result, the direct line was regarded as the desired fault. To
validate the availability and advancement of the proposed
method, different fault recognition methods were compared
through experiments on the synthetic seismic model data
and the real seismic data. The comparison of the fault
recognition results indicated that the proposed method is
more accurate and effective than the traditional and latest
presented methods.
Lei CHEN : received his Master. degree in Pattern recognition and
intelligent system from Taiyuan University of Science and Technology,
Taiyuan China. He is currently a PhD Scholar at the College of Computer
Science and Technology in Beijing University of Technology. His research
interest is pattern recognition and computer vision.
BOD: 1981-04-10.
Chuang-Bai XIAO : Professor at the School of Computer Science and
Technology, Beijing University of Technology, His main research interest is
digital signal processing.
BOD: 1962.
Jing YU : lecturer at the School of Computer Science and Technology,
Beijing University of Technology, Her main research interest are Image
processing , pattern recognition.
BOD: 1981.
WANG Zhen-Li : Director and associate professor at the Key Laboratory of
Petroleum Resources Research, Institute of Geology and Geophysics,
Chinese Academy of Sciences. His main research interest is Complex
structure imaging.
BOD: 1963
Fault Recognition, Labeling, Seismic Section,
Linear Regression, Least Squares
To recognize the fault exactly enough, we proposed a new
fault recognition method based on linear regression
method in this paper. At the beginning, the method of
determining fault location is introduced, then, the
principle of the linear regression method based on least
squares fitting and the proposed fault recognition method
based on the linear regression were given out; finally, to
validate the availability and advancement of the proposed
method, different fault recognition methods were
compared through experiments on the synthetic seismic
model data and the real seismic data. The experimental
results indicated that the proposed method is more accurate and effective than the traditional presented
methods. To apply the proposed method to the problem of
multiple faults recognition is our future work.
[1] Bahorich M S, Lopez J, Haskell N L, Nissen S E, Poole
A. Stratigraphic and structural interpretation with 3-D
coherence. In: Proceedings of the 65th Annual
International SEG Meeting, Houston, Expanded
Abstracts, 1995.97-100
[2] Marfurt K J, Kirlin R L, Farmer S L, Bahorich M S. 3-
D seismic attributes using a semblance-based coherency
algorithm. GeoPhysics, 1998, 63(4):1150-1165
[3] Gersztenkorn A, Marfurt K J. Eigenstructure-based
coherence computations as an aid to 3-D structural and
stratigraphic mapping. GEOPHYSICS, 64(5):1468–
1479
[4] Trygve Randen, Stein Inge Pedersen, Lars Sønneland.
Automatic Extraction of Fault Surfaces from Three-
Dimensional Seismic Data[C]. In: Proceedings of the
62nd Ainnual International SEG Meeting, San Antonio,
Texas, SEG Technical Program Expanded Abstracts
2001: 551-554.
[5] Pedersen S I, Randen T, Sønneland L and Steen ø..
Automatic fault extraction using artificial ants.
Expanded Abstracts of the 71th Annual International
SEG Meeting, 2002, 512-515
[6] Pedersen S.I , Skov T , Randen T, Sønneland L.
Automatic fault extraction using artificial ants[J].
Springer Berlin Heidelberg, 2005, 7:107-116
[7] Gibson D, Spann M, Turner J. Automatic fault
detection for 3D seismic data. In: Proceedings of the
VIIth Digital Image Computing: Techniques and
Applications, Los Alamitos: IEEE Computer Society
Press, 2003. 821-830
[8] Tingdahl K M, Rooij M D. Semi-antomatic detection of
faults in 3D seismic data. GeoPhysical Prospecting,
2005, 53, 533-542
[9] Admasu F, Back S, Toennies K. Autotracking of faults
on 3D seismic data. GeoPhysics, 2006, 71(6):A49-A53
[10] Kadlec B J, Dorn G A, Tufo H M, Yuen D A.
Interactive 3-D computation of fault surfaces using
level sets.Visual Geosciences, 2008, 13(l): 133-138
[11] Panagiotakis C, Kokinou E, Sarris A. Curvilinear
structure enhancement and detection in geophysical
images. IEEE transactions on geoscience and remote
sensing, 2011, 49(6): 2040-2048
[12] Hashemi H. Fuzzy clustering of seismic sequences:
segmentation of time-frequency representations. IEEE
Signal Processing Magazine, 2012, 29(3): 82-87 [14] Panagiotakis C, Kokinou E. Linear pattern detection of
geological faults via a topology and shape optimization
method. IEEE Journal of Selected Topics in Applied
Earth Observations and Remote Sensing, 2015, 8(1): 3-
11.
[15] Browaeys T J. Local complex-valued correlation of
seismic phases. In: Proceedings of the 80th Annual
International SEG Meeting (SEG2010). Denver,
Colorado, USA, Expanded Abstracts, 2010: 1423-1427.
[16] Wang, S.X.; Yuan, S.Y.; Yan, B.P.; He, Y.X.; Sun, W.J.
Directional complex-valued coherence attributes for
discontinuous edge detection. Journal of Applied
Geophysics. 2016, 129, 1-7.
[17] Feng Lu; Yusuke Sugano; Takahiro Okabe; Yoichi Sato.
Adaptive Linear Regression for Appearance-Based
Gaze Estimation. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 2014, 36(10):
2033–2046.
[18] Ting Hu; Qiang Wu; Ding-Xuan Zhou. Convergence of
Gradient Descent for Minimum Error Entropy Principle
in Linear Regression. IEEE Transactions on Signal
Processing, 2016, 64(24): 6571–6579.