Application of Support Vector Machine to the Prediction of the Thickness
of Channel Sand Based on Seismic Attributes

doi:10.11885/j.issn.1674-5086.2012.10.29.01

Abstract

Abstract:

Abstract：Main reservoir of Fuyu layer of middle and shallow part of northern Songliao Basin is channel sandy body，which is
characterized by its thin thickness，small sedimentary scale and lateral heterogeneity. With regard to this problem，we present the
model of support vector machine as a solution. By the optimization of the combination of effective seismic attributes，including
amplitude，frequency，phase，seismic waveform classification and coherent，the best group was for the final input data. Then
the key parameters of the SVM model include loss function C，insensitive loss function parameters ε and γ coefficient，and all
of the well point data was involved in the calculation to indicate the thickness of the channel sand. The result can maintain the
lateral resolution of the seismic data and reflect its general sedimentary pattern as well. The result of subsequently drilled wells
indicated that this method has good qualitatively predictive ability for the thickness of channel sand.

Key words: Key words：channel sand, seismic attributes, optimization, support vector machine, predication of the sand body thickness

Shen Jiagang1, Song Zongping2, Guan Xiaowei1. Application of Support Vector Machine to the Prediction of the Thickness
of Channel Sand Based on Seismic Attributes[J]. 西南石油大学学报(自然科学版), DOI: 10.11885/j.issn.1674-5086.2012.10.29.01.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: http://journal15.magtechjournal.com/Jwk_xnzk/EN/10.11885/j.issn.1674-5086.2012.10.29.01

http://journal15.magtechjournal.com/Jwk_xnzk/EN/Y2014/V36/I3/75

References

[1] 张尔华，陈树民，宋永忠，等. 突出河道砂体地质特征
的地震保幅处理技术以松辽盆地北部扶余油层
为例[J]. 地质科学，2009，44（2）：722–739.
Zhang Erhua，Chen Shumin，Song Yongzhong，et al. Preserved
amplitude processing aimed at enhancing geological
characteristics of channel sandbodies：A case study
from Fuyu oil layer in the northern Songliao Basin[J]. Chinese
Journal of Geology，2009，44（2）：722–739.
[2] 陈树民，沈加刚，宋永忠，等. 基于沉积模式的地震
多属性量化沉积微相解释方法以松辽盆地北部
高台子地区泉头组三，四段为例[J]. 地质科学，2009，
44（2）：740–758.
Chen Shumin，Shen Jiagang，Song Yongzhong，et al.
Method of interpretation by quantization of multiple seismic
attributes based on sedimentary model：A case study
from Members 3-4，Quantou Formation in the northern
Songliao Basin[J]. Chinese Journal of Geology，2009，
44（2）：740–758.
[3] 吴胜和，杨延强. 地下储层表征的不确定性及科学思
维方法[J]. 地球科学与环境学报，2012，34（2）：72–80.
Wu Shenghe，Yang Yanqiang. Uncertainty and scientific
methodology in subsurface reservoir characterization[J].
Journal of Earth Sciences and Environment，2012，34（2）：
72–80.
[4] Li J K，Castagna J，Li D G，et al. Reservoir Prediction
Via SVM Pattern Recognition[C]. SEG Annual Meeting，
2004，425–429.
[5] Zhao B，Brouwer F，Aminzadeh F，et al. Multiple prediction
and reservoir characterization of a tight sand reservoir[
C]. SEG Annual Meeting，2008.
[6] Zhang C K，Lu W K. Seismic attributes selection based on
SVM for hydrocarbon reservoir prediction[C]. SEG Annual
Meeting，2010.
[7] 张大智，纪友亮，刘洪林，等. 基于BP 神经网络的薄互
层储层预测[J]. 上海地质，2005（4）：47–50.
Zhang Dazhi，Ji Youliang，Liu Honglin，et al. Thin-inter
bed reservoir prediction based on BP neural network[J].
Shanghai Geology，2005（4）：47–50.
[8] 张彦周，刘叶玲，谢宝英. 支持向量机在储层厚度
预测中的应用[J]. 勘探地球物理进展，2005，28（6）：
422–424.
Zhang Yanzhou，Liu Yeling，Xie Baoying. Application of
SVM in prediction of reservoir thickness[J]. Progress in
Exploration Geophysics，2005，28（6）：422–424.
[9] Learning V C V. Guest editorial Vapnik-chervonenkis（
VC） learning theory and its applications[J]. IEEE
Transactions on Neural Netwoks，1999，10（5）：985–987.
[10] 张尔华，关晓巍，张元高. 支持向量机模型在火山岩储
层预测中的应用以徐家围子断陷徐东斜坡带为
例[J]．地球物理学报，2011，54（2）：428–432.
Zhang Erhua，Guan Xiaowei，Zhang Yuangao. Support
vector machine in volcanic reservoir forecast：East slope
in Xujiaweizi Depression[J]．Chinese Journal of Geophysics，
2011，54（2）：428–432.
[11] 凌云研究组. 地震分辨率极限问题的研究[J]. 石油地球
物理勘探，2004，39（4）：435–442.
Ling Yun Research Group. Study of seismic resolution
limit[J]. Oil Geophysical Prospecting，2004，39（4）：
435–442.
[12] Vapnik V. The nature of statistical learning theory[M].
New York：Springer，2000.
[13] 陈恭洋，陈玲，朱洁琼，等. 地震属性分析在河流相储
层预测中的应用[J]. 西南石油大学学报：自然科学版，
2012，34（3）：1–8.
Chen Gongyang，Chen Ling，Zhu Jieqiong，et al. Application
of seismic attributes analysis fluvial reservoir to
prediction[J]. Journal of Southwest Petroleum University：
Science & Technology Edition，2012，34（3）：1–8.
[14] 伊振林. 井震联合窄小河道砂体预测方法研究[J]. 西南
石油大学学报：自然科学版，2012，34（1）：19–24.
Yi Zhenlin. Prediction method of narrow channel sand
body in well-to-seismic integration[J]. Journal of Southwest
Petroleum University：Science & Technology Edition，
2012，34（1）：19–24.
[15] 盛海波，刘蕊，付国民，等. 塔河油田3 区石炭系超深
薄层碎屑岩储层预测研究[J]. 地球科学与环境学报，
2011，33（4）：390–396.
Sheng Haibo，Liu Rui，Fu Guomin，et al. Study on reservoir
forecasting for ultra deep thin clastic rock of carboniferous
system in Block 3 of Tahe Oilfield[J]. Journal of
Earth Sciences and Environment，2011，33（4）：390–396.
[16] Li J，Castagna J. Support vector pattern recognition and
AVO classification[C]. SEG Annual Meeting，2003.
[17] Eftekharifar M，Han D H. 3D Petrophysical modeling using
complex seismic attributes and limited well log data[
C]. SEG Annual Meeting，2011.