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.

Correlation plot of input variables and output variables of cohesive soils stabilized with geopolymer.

More »

Fig 1 Expand

Table 1.

Statistical description of all dataset.

More »

Table 1 Expand

Table 2.

Statistical description of training dataset.

More »

Table 2 Expand

Table 3.

Statistical description of testing dataset.

More »

Table 3 Expand

Fig 2.

K-fold cross validation diagram.

More »

Fig 2 Expand

Fig 3.

Methodology of this study.

More »

Fig 3 Expand

Fig 4.

Influence of hyperparameter value on fitness function R2 value: (a) Number of estimations vs Max depth, (b) Max features vs Min samples split for RF model; (c) Neuron number of hidden 1 vs Neuron number of hidden 2 with solver LBFGS, (d) Neuron number of hidden 1 vs Neuron number of hidden 2 with solver ADAM for ANN model.

More »

Fig 4 Expand

Fig 5.

Influence of hyperparameter value on fitness function R2 value for: (a) Number of estimations vs Learning rate and (b) Max depth vs Min split loss for XGB model; (c) Number of estimations vs Max depth, (d) Max features vs Min samples split for GB model.

More »

Fig 5 Expand

Table 4.

Optimal hyperparameters of ML models.

More »

Table 4 Expand

Fig 6.

Experimental UCS of geopolymer vs predicted UCS based on (a) RF model, (b) GB model, (c) XGB model and (d) ANN model.

More »

Fig 6 Expand

Table 5.

Performance value including R2, RMSE and MAE of ML models.

More »

Table 5 Expand

Fig 7.

Taylor diagram for comparing UCS predicted by ML models and experimental UCS of geopolymer in (a) training dataset and (b) Testing dataset.

More »

Fig 7 Expand

Fig 8.

Global interpretation of two best ML model-based Shapley additive explanations.

More »

Fig 8 Expand

Table 6.

New performance values value including R2, RMSE and MAE of XGB and ANN models.

More »

Table 6 Expand

Table 7.

Comparison of performance values and database between this study and other investigation of literature.

More »

Table 7 Expand

Fig 9.

Global interpretation of ANN model-based Shapley additive explanations using the new database.

More »

Fig 9 Expand

Fig 10.

Local interpretation of ANN model-based Shapley additive explanations using the new database.

More »

Fig 10 Expand

Fig 11.

Individual interpretation of ANN model-based Shapley additive explanations using the new database for three specific cases.

More »

Fig 11 Expand