Neural Network Model for Predicting Shear Wave Velocity Using Well Logging Data

Efficient well design requires accurate estimation of rock petrophysical parameters that represent a reservoir. For compressional waves, particle motion is in the direction of propagation; alternatively, for shear waves, it is perpendicular to the propagation direction. Understanding the velocity of these waves reveals important details about the reservoir. Shear wave velocity (Vs) can be used for estimating mechanical properties of rock that will be used while determining casing setting depth, rate of penetration, and fracture pressure. Unfortunately, Vs data cannot be obtained directly in the field due to field constraints and high cost. On the other hand, compressional sonic data sets are available. There are many time- and money-consuming techniques that target the estimation of Vs from core analysis. Moreover, there are uncertain models such as the Xu-Payne petrophysical model, which are based on pore structures, rock compositions, and fluid properties. Although many studies provide various methods to estimate Vs from empirical correlations, petrophysical models, and artificial intelligence, these studies are limited to small ranges of used data. In this paper, a new artificial neural network (ANN) model is developed to accurately predict Vs as a function of porosity (& empty;), gamma-ray (GR), bulk density (rho(b)), and compressional velocity (Vc) with wide data ranges. The new model is built using data set comprising 2350 data points, where 1645 data sets are used to process the model, and the other 705 data sets are used to validate the new model. Results showed high accuracy with a coefficient of determination of about 0.958. The proposed model can be applied directly in Excel sheet without need to any other software.