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

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.<>