Compressional and shear wave velocities (Vp and Vs) are important reservoir characteristics which<br>have many applications in prtrophysical, geophysical and geomechanical studies. These parameters<br>(especially Vs) are obtained directly from core analysis in the laboratory or by Dipole Sonic Imager<br>(DSI) tools. Since the laboratory methods are very expensive and time consuming; and the<br>conventional sonic tools can not measure Vs, studies are led to find new methods for wave velocity<br>estimation. Many researchers have tried to predict Vs from well log data, Most of these studies have<br>been carried out for Vs estimation in sandstone reservoirs. Since carbonate rocks are considered as the<br>major parts of the world's oil and gas reservoirs there is a need to study more about Vs and Vp<br>estimation in these types of reservoirs. In this study Vp and Vs were predicted from well log data using<br>genetic algorithms (GAs) technique in an Iranian carbonate reservoir (Sarvak Formation). A total of<br>3030 data points of two wells from Sarvak carbonate reservoir which have Vp, Vs and conventional<br>well log data were used. These data were divided into two parts, one part used for constructing GAs<br>models and the other part used for models testing. The measured mean squared error of predicted Vp<br>and Vs in the test data was 0.0296 and 0.0153 respectively. Prediction in carbonate rocks is so difficult<br>because of diagenetic processes; however, GAs give reliable results. Therefore using this methodology<br>Vp and Vs can be obtained for Sarvak Formation in other wells of Abadan Plain which have no Vp and<br>Vs data.


Article metrics loading...

Loading full text...

Full text loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error