Intelligent Data-Driven Analytics to Predict Shear Wave Velocity in Carbonate Formations: Comparison between Recurrent and Conventional Neural Networks


Accurate estimation of shear wave velocity (VS) is pivotal for many petrophysical and geomechanical applications. Actual VS measurements can be obtained from well logs and laboratory tests. However, due to the cost and time-saving purposes, VS is not often measured. The purpose of this work is to utilize dynamic networks to accurately predict VS for carbonate formations and to compare between the conventional neural network and the dynamic networks. Dynamic and conventional neural networks were created to predict VS from compressional wave velocity (VP), bulk density (ρb), and neutron porosity (ΦN). The results showed that the dynamic network significantly outperformed the conventional neural network in the prediction of VS. The dynamic network showed the ability to predict VS with R2 of 0.99 while the conventional neural network predicted the VS with an overall R2 of 0.72. This study presents an easy, accurate, and cost-effective method to estimate VS for geomechanical and petrophysical applications. Also, this paper will present a path forward for future applications of dynamic neural networks in the petroleum industry.

Meeting Name

53rd U.S. Rock Mechanics/Geomechanics Symposium (2019: Jun. 23-26, Brooklyn, NY)


Geosciences and Geological and Petroleum Engineering

Keywords and Phrases

Acoustic wave velocity; Cost benefit analysis; Cost effectiveness; Dynamics; Forecasting; Geomechanics; Oil bearing formations; Petroleum industry; Petrophysics; Rock mechanics; Shear flow; Shear waves; Wave propagation; Well logging, Accurate estimation; Carbonate formations; Compressional wave velocity; Cost-effective methods; Dynamic neural networks; Future applications; Geomechanical applications; Shear wave velocity, Recurrent neural networks

Document Type

Article - Conference proceedings

Document Version


File Type





© 2019 American Rock Mechanics Association (ARMA), All rights reserved.

Publication Date

01 Jun 2019