lithofacies identification

reservoir characterization

seismic facies

Journal of Petroleum Science and Engineering

This study proposes a novel approach to predict missing shear sonic log responses more precisely and accurately using similarity patterns of various wells with similar geophysical properties, which is important in decision making and planning of hydrocarbon exploration. Deep Neural Network (DNN) along with the similarity metrics such as Jaccard and Overlap similarities are employed to examine the relationship between the wells. Further, dimensionality reduction techniques including Multi-Dimensional Scaling (MDS) and well-ranking process are applied to extract common geophysical responses of the wells. A higher response indicates the existence of a strong similarity. This can also be verified by the superimposed of well log data. The potential benefits of our novel method are following; (a) it does not follow the zone-by-zone prediction of the missing logs such as rock physics methods, (b) it outputs the uncertainties facilitated that is by the least-squares method. Having the potential of demonstrating shear sonic log prediction in hydrocarbon-bearing zones, which cannot be precisely predicted by the Greenberg-Castagna method that only works in brine-saturated rocks, this approach will provide improved accuracy, where shear sonic logs are missing and need to be predicted for geomechanics, rock physics, and other applications. • This study proposes a novel approach to predict missing shear sonic log responses. • It uses similarity patterns of various wells with similar geophysical properties. • The results confirmed that prediction of missing logs is more accurate and precise. • It supersedes conventional methods of predicting missing logs in terms of accuracy. • It allows prediction of shear sonic log without performing Gassmann fluid substitution.

Machine learning - A novel approach of well logs similarity based on synchronization measures to predict shear sonic logs