Table 7 Prediction model performance on cross–project database (Scenario 3).

From: Machine learning approach for prediction of TBM performance and risk of jamming in Himalayan geology using a cross-project tunnelling database

Model

Training Set

Testing Set

R2

MAE

RMSE

MAPE

R2

MAE

RMSE

MAPE

XGBoost

0.984

1.132

2.042

1.814

0.965

1.499

3.042

2.430

RF

0.989

0.947

1.715

1.582

0.962

1.730

3.155

2.906

Bagging

0.987

0.910

1.878

1.470

0.964

1.495

3.101

2.413

Stacking

0.986

0.983

1.922

1.573

0.965

1.464

3.021

2.351

ANN

0.960

1.538

3.258

2.488

0.960

1.547

3.269

2.508

Back to article page