Shear wave velocity is widely used during seismic reservoir characterization such as lithology, porosity and fluid estimation, four-dimensional seismic studies and Geomechanical studies. Shear velocity logs are not necessarily acquired in all wells due to the costs. Therefore, different methods have been developed to estimate it using other logs. Methods such as empirical relations, multi-regression analysis, artificial neural networks, and rock physic modeling have been widely used for this purpose. In this study, Castagna et al (1993) and pickets (1963) relations were employed as empirical relations. Empirical relations could estimate the shear velocity log with significant error. Multi-regression was carried out employing four logs: Compressional velocity, density, neutron and porosity. In the artificial neural network step, the training is performed by the Levenberg-Marquardt algorithm with four input layers, ten middle layers and one target layer. Subsequently, a new equation is developed that estimates the shear velocity log using compressional velocity and density logs. This equation considers the impact of rock forming minerals and pore filling fluids using its modulus. Comparison of the results using different methods proved the accuracy of this method in a real case study.