Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Methodology flowchart.

More »

Fig 1 Expand

Table 1.

The optimized parameters of the proposed GPR method.

More »

Table 1 Expand

Table 2.

The most common machine learning methods to predict νs.

More »

Table 2 Expand

Fig 2.

The comparison of νs – RHOB trends models with experimental measurements.

More »

Fig 2 Expand

Fig 3.

Trend analysis of the νs – RHOB in the range of data found in the dataset used for the optimized GPR.

More »

Fig 3 Expand

Fig 4.

The comparison of νs – DTc trends models with experimental measured values for RHOB = 2.27 g/cc and DTs = 248.99 us/ft.

More »

Fig 4 Expand

Fig 5.

The comparison of νs – DTc trends models with experimental measured values for RHOB = 2.02 g/cc and DTs = 265.03 us/ft.

More »

Fig 5 Expand

Fig 6.

Trend analysis of the νs – DTc in the range found in the dataset used for the optimized GPR.

More »

Fig 6 Expand

Fig 7.

The comparison of νs – DTs trends models with experimental measured values for RHOB = 2.72 g/cc and DTc = 51.47 us/ft.

More »

Fig 7 Expand

Fig 8.

The comparison of νs – DTs trends models with experimental measured values for RHOB = 2.33 g/cc and DTc = 118.67 us/ft.

More »

Fig 8 Expand

Fig 9.

Trend analysis of the νs – DTs in the range found in the dataset used for the optimized GPR.

More »

Fig 9 Expand

Fig 10.

The optimized GPR approach’s cross-plotting for the training dataset.

More »

Fig 10 Expand

Fig 11.

The optimized GPR approach’s cross-plotting for the validation dataset.

More »

Fig 11 Expand

Fig 12.

The optimized GPR approach’s cross-plotting for the testing dataset.

More »

Fig 12 Expand

Table 3.

Statistical error analyses of the proposed or optimized GPR model.

More »

Table 3 Expand

Fig 13.

Comparison of νs measured and predicted estimates of the optimized GPR approach for (a) training, (b) validation, and (c) testing datasets.

More »

Fig 13 Expand

Fig 14.

The optimized GPR approach’s error histogram of the training dataset.

More »

Fig 14 Expand

Fig 15.

The optimized GPR approach’s error histogram of the validation dataset.

More »

Fig 15 Expand

Fig 16.

The optimized GPR approach’s errors histogram of the testing dataset.

More »

Fig 16 Expand

Fig 17.

Group error analysis of bulk formation density for the proposed GPR and some previous approaches.

More »

Fig 17 Expand

Fig 18.

Group error analysis of compressional time for the proposed GPR and some previous approaches.

More »

Fig 18 Expand

Fig 19.

Group error analysis of shear time for the proposed GPR and some previous approaches.

More »

Fig 19 Expand

Fig 20.

Cross-plots of (a) the proposed GPR, Ranjbar-Karaml et al. [14], Christaras et al. [52], Feng et al. [16], Gowida et al. [17] models and (b) Khandelwal et al. [13], Brandås et al. [15], and Kumar et al. [12].

More »

Fig 20 Expand

Fig 21.

(a) Average absolute percentage relative error (AAPRE), and, (b) Coefficient of determination (R2) of the models.

More »

Fig 21 Expand

Fig 22.

(a, b). The statistical error analyses for the models using the same dataset.

More »

Fig 22 Expand

Fig 23.

(a) Taylor diagrams of Khandelwal et al. [13], Brabdas et al, Kumar et al. [12] models. (b) Taylor diagrams of Ranjbar-Karami et al. [14], Christaras et al. [52], Feng et al. [16], Gowida et al. [17], and the proposed GPR models.

More »

Fig 23 Expand

Table 4.

P values of Kruskal–Wallis test at 95% significance level.

More »

Table 4 Expand

Fig 24.

Error boxplot and violin graphs for the previously published and proposed GPR models.

More »

Fig 24 Expand

Fig 25.

Fracture pressure based on previous Poisson’s ratio models.

More »

Fig 25 Expand

Fig 26.

Fracture pressure based on proposed GPR Poisson’s ratio model.

More »

Fig 26 Expand

Fig 27.

Residual error of fracture pressure for all studied models.

More »

Fig 27 Expand