Shear wave velocity estimation from conventional well log data by using a hybrid ant colony–fuzzy inference system: A case study from Cheshmeh–Khosh oilfield

• A hybrid model based on integration of fuzzy logic and ant colony optimization.
• A comparative study of Vs estimation by using five intelligent techniques.
• Using a large data set of 600 data points from Cheshmeh–Khosh oilfield.
• The proposed model outperforms other intelligent methods used.
• A robust, fast and cost-effective method for rock property estimation.

Characterization of geomechanical parameters of hydrocarbon reservoirs such as compressional and shear wave velocities is a main component of petrophysical, geophysical and geomechanical studies. Compressional wave velocity is derived from sonic log. However, Vs is either obtained from core analysis in the laboratory or dipole sonic imager (DSI) tools which are both very expensive and time consuming. Recently, several methods of artificial intelligence techniques have been used to predict this fundamental parameter by using well log data. In this paper, a new methodology is presented for shear wave velocity estimation by integration of stochastic optimization in the structure of a fuzzy inference system. The proposed model, which is called ant colony–fuzzy inference system (ACOFIS), is based on the integration of fuzzy reasoning and ant colony optimization algorithm. The methodology is illustrated by using a case study from Cheshmeh–Khosh oilfield. Comparison of the results shows that the proposed novel and hybrid scheme can sufficiently improve the performance of the shear wave velocity estimation problem. Meanwhile, the developed ACOFIS model can serve as an effective tool for estimation of other reservoir rock properties.