A pattern recognition approach to detect oil/gas reservoirs in sand/shale sediments

Author

Yao, Zheng-He ; Wu, Li-De

Author_Institution

Shanghai Bur. of Marine Geological Survey, China

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

462

Lastpage

465

Abstract

A hybrid structural and statistical pattern recognition approach to detect oil/gas reservoirs in sand/shale sediments is presented in the paper. On the basis of the sand fiducial profile derived from log data and seismic data, a tree-based region-detecting method is used to detect sand layers, and a Marr´s-operator-based clustering algorithm is used to find oil/gas reservoirs in the detected sand layers. The ability of the approach is demonstrated by a real-data example

Keywords

geophysical prospecting; geophysical techniques; geophysics computing; pattern recognition; seismology; Marr´s-operator-based clustering algorithm; geophysical prospecting; hybrid structural/statistical pattern recognition; oil/gas reservoirs; sand fiducial profile; sand/shale sediments; seismology; tree-based region-detecting method; Application software; Clustering algorithms; Computer vision; Geology; Hydrocarbon reservoirs; Impedance; Partial response channels; Pattern recognition; Petroleum; Sediments;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2915-0

Type

conf

DOI

10.1109/ICPR.1992.201818

Filename

201818