Rock physics model-based prediction of shear wave velocity utilizing machine learning technique for a carbonate reservoir, southwest Iran

Abstract

S-wave velocity provides important information for the purpose of seismic reservoir characterization. However, it is not usually acquired in all wells due to the high cost and technical difficulties. Hence, different methods are developed for S-wave velocity prediction from other conventional petrophysical logs, generally using rock physics methods or artificial intelligence algorithms. Both of these methods have their own challenges for predicting S-wave velocity for complex reservoirs, which affects their prediction accuracy and efficiency accordingly. This paper proposes a combination of rock physics and machine learning methods on a carbonate reservoir to predict S-wave velocity. We used the Xu and Payne model and improved the estimation of the S-wave velocity by modifying the Gassmann's fluid substitution model and deriving a simplified form of it with a so-called C-factor exponent. Firstly, an inversion-based strategy is used to calculate this C-factor in a reference well as the training input data. Then, exponential Gaussian process regression is chosen to estimate the C-factor from the measured reservoir properties. The predicted C-factor, furthermore, is used to invert for a pore model, which was also validated with the computed tomography scanning analysis results. Our results confirm that this pore model, along with the computed C-factor, gives a better estimation for S-wave velocity in a blind well where the errors associated with the routine approaches are reduced significantly.