Using artificial intelligence methods for shear travel time prediction: A case study of Facha member, Sirte basin, Libya

Abstract

Shear wave travel time logs are major acoustic logs used for direct estimation of the mechanical properties of rocks. They are also important for prediction of critical drawdown pressure of the reservoir. However, core samples are sometimes not available for direct laboratory measurements, and the time-consuming dipole shear imager tool is generally not used. Hence, there is a need for simple indirect techniques that can be used reliably. In this study, cross-plots between the available measured shear travel time and compressional travel time from three oil wells were used, and three artificial intelligence tools (fuzzy logic, multiple linear regression and neural networks) were applied to predict the shear travel time of Facha member (Gir Formation, Lower Eocene) in Sirte Basin, Libya. The predicted times were compared to those obtained by the equation of Brocher. The basic wireline data (gamma ray, neutron porosity, bulk density and compression travel time) of five oil wells were used. Based on principle component analysis, two wireline data sets were chosen to build intelligent models for the prediction of shear travel time. Limestone, dolomite, dolomitic limestone and anhydrite are the main lithofacies in the Facha member, with an average thickness of about 66 m. The simple equation gave 87% goodness of fit, which is considered comparable to the measured shear travel time logs. The Brocher equation yielded adequate results, of which the most accurate was for the Facha member in the eastern part of the Sirte basin. On the other hand, the three intelligent tools’ predictions of shear travel time conformed with the measured log, except in the eastern area of the basin.