•  
  •  
 

Turkish Journal of Earth Sciences

Abstract

Shear-wave velocity (Vs) is one of the most critical parameters for determining geomechanical properties and basin overpressure. However, assessing Vs via techniques like core analysis requires considerable effort and expense. This study predicts Vs using several approaches and compares the accuracy levels of all models. For this objective, the multiple linear regression, multiple linear stepwise regression, support vector machine, and least-squares boost (LSBoost) methodologies were selected. The six well-logging data inputs of density (RHOB), gamma-ray (GR), deep resistivity (ILD), acoustic wave velocity (Vp), shale volume (VCL), and water saturation (SW) were selected as effective variables, whereas Vs was regarded as the output. The model was developed using data from the RCW-1 well and evaluated through 5-fold cross-validation and independent blind cross-well validation. The LSBoost model demonstrated robust and stable in-well performance, achieving a mean coefficient of determination (R2) of 0.958 ± 0.003 and root mean square error (RMSE) of 56.48 ± 1.58 m/s, indicating effective learning without evidence of overfitting. Feature importance and Spearman rank correlation analyses consistently identified ILD and Vp as the most influential predictors, confirming the presence of nonlinear monotonic relationships between the input logs and Vs. However, blind application of the RCW-1-trained model to the independent RCW-2 well resulted in reduced predictive accuracy (R2 = 0.266, RMSE = 287.95 m/s), reflecting geological and petrophysical domain shifts between wells rather than model inadequacy. Comparisons with empirical Castagna and Greenberg–Castagna correlations showed that while the empirical models provided relatively stable baseline predictions across wells, LSBoost significantly outperformed them within a consistent geological domain. These results highlight the potential of LSBoost for accurate Vs prediction when representative training data are available and emphasize the importance of multiwell datasets to improve cross-well generalization.

Author ORCID Identifier

RAHMAT CATUR WIBOWO: 0000-0003-2754-1803

FADSYAH ARBY: 0009-0002-9697-7707

BAGUS MULYATNO: 0009-0008-1106-9616

ORDAS DEWANTO: 0009-0007-9467-280X

ISTI KUMALASARI: 0009-0007-6402-0085

MUH SARKOWI: 0000-0001-8554-3407

DOI

10.55730/1300-0985.2017

Keywords

Shear wave, machine learning, LSBoost, prediction

First Page

236

Last Page

249

Publisher

The Scientific and Technological Research Council of Türkiye (TÜBİTAK)

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS