Object. Development of a method for predicting a two-three dimensional velocity model of a medium by using a shear wave. Complexly structured geological medium is studied on the basis of geophysical and geological data using an artificial neural network. Method. It provides the construction and use of medium models according to geophysical well logging data and other terrestrial geophysical methods. In contrast to existing methods, the proposed method also uses additional data on the medium. They include the thermodynamic state of the medium, stratigraphic confinement of deposits, rock lithology, distribution of data clusters, physical properties of the medium etc. According to the method, one-dimensional models are first constructed on various properties of the medium based on data of complex of well logging. Then, the neural network is studied to predict the shear wave velocity on a set of models. Subsequently, two-three-dimensional models of the medium are constructed according to the results of terresterial geophysical studies. Two-threedimensional velocity model of a shear wave is predicted by using a complex of these models studied by a neural network. Results. Velocity model of shear wave is predicted for complexly structured geological medium of the South Caspian Basin using the method. Scientific novelty. It is possible to increase the accuracy and resolution of prediction the medium model by increasing the number of types of data used. Practical value. Improving the efficiency of seismic exploration in determining oil and gas saturation, elastic geodynamic state and other physical properties of the geological medium.