A detailed understanding of rock geo-mechanical characteristics is necessary for enhancing well productivity, optimizing hydraulic fracturing, and maintaining wellbore stability. The expensive cost of measurements of these characteristics makes the log-based estimation a possible alternative. These days, in-situ rock characteristics are estimated utilizing wireline log data and machine learning algorithms. Even though there are many correlations had been proposed to estimate the Uniaxial (Unconfined) Compressive Strength (UCS), the majority of these correlations are built for specific rock types. UCS is affected by various rock properties such as porosity, texture, fluid content and grain size. In this study, an artificial neural network (ANN) model is proposed to estimate the UCS of sandstone formations from well log data (i.e., neutron porosity, bulk density, formation resistivity, and gamma ray) and the corresponding static Young's modulus and shale volume. The performance of the rock strength model is evaluated using statistical techniques to guarantee model dependability and accuracy. The findings demonstrate that the created ANN model is capable of predicting rock strength, which is supported by the excellent agreement between model predictions and Sonic-derived UCS. The Results demonstrate that the ANN model is competent in predicting the sandstone UCS with high accuracy (i.e. R coefficient of the 96% and average absolute error of 7.75%). The suggested approach is anticipated to improve wellbore performance by enhancing the ability of gas and oil professionals to estimate UCS as well as reducing the cost of estimating the geo-mechanical characteristics.

You can access this article if you purchase or spend a download.